diff options
2635 files changed, 41537 insertions, 18919 deletions
@@ -15,30 +15,31 @@ Aaron Durbin <adurbin@google.com> Adam Oldham <oldhamca@gmail.com> Adam Radford <aradford@gmail.com> -Adrian Bunk <bunk@stusta.de> Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com> +Adrian Bunk <bunk@stusta.de> Alan Cox <alan@lxorguk.ukuu.org.uk> Alan Cox <root@hraefn.swansea.linux.org.uk> -Aleksey Gorelov <aleksey_gorelov@phoenix.com> Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com> -Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com> -Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org> +Aleksey Gorelov <aleksey_gorelov@phoenix.com> Alexander Lobakin <alobakin@pm.me> <alobakin@dlink.ru> Alexander Lobakin <alobakin@pm.me> <alobakin@marvell.com> Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru> Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com> -Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com> Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com> Alexei Starovoitov <ast@kernel.org> <ast@fb.com> +Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com> +Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com> +Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org> Al Viro <viro@ftp.linux.org.uk> Al Viro <viro@zenIV.linux.org.uk> +Andi Kleen <ak@linux.intel.com> <ak@suse.de> Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com> Andreas Herrmann <aherrman@de.ibm.com> -Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com> Andrew Morton <akpm@linux-foundation.org> -Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com> Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk> +Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com> Andrew Vasquez <andrew.vasquez@qlogic.com> +Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com> Andy Adamson <andros@citi.umich.edu> Antoine Tenart <antoine.tenart@free-electrons.com> Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com> @@ -48,40 +49,42 @@ Arnaud Patard <arnaud.patard@rtp-net.org> Arnd Bergmann <arnd@arndb.de> Axel Dyks <xl@xlsigned.net> Axel Lin <axel.lin@gmail.com> -Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com> Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com> +Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com> Ben Gardner <bgardner@wabtec.com> Ben M Cahill <ben.m.cahill@intel.com> Björn Steinbrink <B.Steinbrink@gmx.de> -Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com> -Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com> Boris Brezillon <bbrezillon@kernel.org> <b.brezillon.dev@gmail.com> Boris Brezillon <bbrezillon@kernel.org> <b.brezillon@overkiz.com> +Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com> +Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com> Brian Avery <b.avery@hp.com> Brian King <brking@us.ibm.com> +Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com> +Changbin Du <changbin.du@intel.com> <changbin.du@intel.com> Chao Yu <chao@kernel.org> <chao2.yu@samsung.com> Chao Yu <chao@kernel.org> <yuchao0@huawei.com> -Christoph Hellwig <hch@lst.de> Christophe Ricard <christophe.ricard@gmail.com> +Christoph Hellwig <hch@lst.de> Corey Minyard <minyard@acm.org> Damian Hobson-Garcia <dhobsong@igel.co.jp> -Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com> -Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com> +Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com> Daniel Borkmann <daniel@iogearbox.net> <danborkmann@iogearbox.net> Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch> -Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com> +Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com> +Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com> David Brownell <david-b@pacbell.net> David Woodhouse <dwmw2@shinybook.infradead.org> -Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com> -Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com> Dengcheng Zhu <dzhu@wavecomp.com> <dczhu@mips.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com> +Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com> +Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com> <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be> Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> -Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> -Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com> +Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> +Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> Domen Puncer <domen@coderock.org> Douglas Gilbert <dougg@torque.net> Ed L. Cashin <ecashin@coraid.com> @@ -92,20 +95,22 @@ Felix Kuhling <fxkuehl@gmx.de> Felix Moeller <felix@derklecks.de> Filipe Lautert <filipe@icewall.org> Franck Bui-Huu <vagabon.xyz@gmail.com> -Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com> Frank Rowand <frowand.list@gmail.com> <frank.rowand@am.sony.com> Frank Rowand <frowand.list@gmail.com> <frank.rowand@sonymobile.com> +Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com> Frank Zago <fzago@systemfabricworks.com> Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com> Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com> -Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com> Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com> +Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com> Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@linux.vnet.ibm.com> Greg Kroah-Hartman <greg@echidna.(none)> Greg Kroah-Hartman <gregkh@suse.de> Greg Kroah-Hartman <greg@kroah.com> Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com> Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com> +Gustavo Padovan <gustavo@las.ic.unicamp.br> +Gustavo Padovan <padovan@profusion.mobi> Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org> Heiko Carstens <hca@linux.ibm.com> <h.carstens@de.ibm.com> Heiko Carstens <hca@linux.ibm.com> <heiko.carstens@de.ibm.com> @@ -115,32 +120,33 @@ Henrik Rydberg <rydberg@bitmath.org> Herbert Xu <herbert@gondor.apana.org.au> Jacob Shin <Jacob.Shin@amd.com> Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@google.com> -Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@motorola.com> Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk.kim@samsung.com> +Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@motorola.com> Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com> James Bottomley <jejb@mulgrave.(none)> James Bottomley <jejb@titanic.il.steeleye.com> James E Wilson <wilson@specifix.com> -James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> James Hogan <jhogan@kernel.org> <james@albanarts.com> +James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> James Ketrenos <jketreno@io.(none)> Jan Glauber <jan.glauber@gmail.com> <jang@de.ibm.com> Jan Glauber <jan.glauber@gmail.com> <jang@linux.vnet.ibm.com> Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com> +Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com> Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com> -Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com> <javier@osg.samsung.com> <javier.martinez@collabora.co.uk> +Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com> Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com> Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com> Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com> Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com> -Jean Tourrilhes <jt@hpl.hp.com> <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com> +Jean Tourrilhes <jt@hpl.hp.com> Jeff Garzik <jgarzik@pretzel.yyz.us> -Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com> Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net> Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com> +Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com> Jens Axboe <axboe@suse.de> Jens Osterkamp <Jens.Osterkamp@de.ibm.com> Jiri Slaby <jirislaby@kernel.org> <jirislaby@gmail.com> @@ -164,30 +170,31 @@ Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com> Kamil Konieczny <k.konieczny@samsung.com> <k.konieczny@partner.samsung.com> Kay Sievers <kay.sievers@vrfy.org> Kenneth W Chen <kenneth.w.chen@intel.com> -Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com> Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru> +Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com> Koushik <raghavendra.koushik@neterion.com> -Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com> Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com> +Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com> Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> -Leon Romanovsky <leon@kernel.org> <leon@leon.nu> -Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com> Leonardo Bras <leobras.c@gmail.com> <leonardo@linux.ibm.com> Leonid I Ananiev <leonid.i.ananiev@intel.com> +Leon Romanovsky <leon@kernel.org> <leon@leon.nu> +Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com> +Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com> Linas Vepstas <linas@austin.ibm.com> -Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de> Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch> -Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org> +Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de> Li Yang <leoyang.li@nxp.com> <leoli@freescale.com> +Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org> Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com> Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com> -Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com> Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com> +Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com> Mark Brown <broonie@sirena.org.uk> Mark Yao <markyao0591@gmail.com> <mark.yao@rock-chips.com> -Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> +Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Mathieu Othacehe <m.othacehe@gmail.com> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> Matthew Wilcox <willy@infradead.org> <matthew@wil.cx> @@ -197,17 +204,17 @@ Matthew Wilcox <willy@infradead.org> <willy@debian.org> Matthew Wilcox <willy@infradead.org> <willy@linux.intel.com> Matthew Wilcox <willy@infradead.org> <willy@parisc-linux.org> Matthieu CASTET <castet.matthieu@free.fr> -Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br> +Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting> +Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com> +Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com> +Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com> Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com> +Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br> Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@infradead.org> +Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@osg.samsung.com> Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@redhat.com> Mauro Carvalho Chehab <mchehab@kernel.org> <m.chehab@samsung.com> -Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@osg.samsung.com> Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@s-opensource.com> -Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com> -Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com> -Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting> -Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com> Maxime Ripard <mripard@kernel.org> <maxime.ripard@bootlin.com> Maxime Ripard <mripard@kernel.org> <maxime.ripard@free-electrons.com> Mayuresh Janorkar <mayur@ti.com> @@ -239,13 +246,13 @@ Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Patrick Mochel <mochel@digitalimplant.org> Paul Burton <paulburton@kernel.org> <paul.burton@imgtec.com> Paul Burton <paulburton@kernel.org> <paul.burton@mips.com> +Paul E. McKenney <paulmck@kernel.org> <paul.mckenney@linaro.org> Paul E. McKenney <paulmck@kernel.org> <paulmck@linux.ibm.com> Paul E. McKenney <paulmck@kernel.org> <paulmck@linux.vnet.ibm.com> -Paul E. McKenney <paulmck@kernel.org> <paul.mckenney@linaro.org> Paul E. McKenney <paulmck@kernel.org> <paulmck@us.ibm.com> Peter A Jonsson <pj@ludd.ltu.se> -Peter Oruba <peter@oruba.de> Peter Oruba <peter.oruba@amd.com> +Peter Oruba <peter@oruba.de> Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com> Praveen BP <praveenbp@ti.com> Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com> @@ -258,23 +265,23 @@ Ralf Baechle <ralf@linux-mips.org> Ralf Wildenhues <Ralf.Wildenhues@gmx.de> Randy Dunlap <rdunlap@infradead.org> <rdunlap@xenotime.net> Rémi Denis-Courmont <rdenis@simphalempin.com> -Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com> Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com> Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org> +Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com> Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com> Rudolf Marek <R.Marek@sh.cvut.cz> Rui Saraiva <rmps@joel.ist.utl.pt> Sachin P Sant <ssant@in.ibm.com> -Sarangdhar Joshi <spjoshi@codeaurora.org> +Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi> Sam Ravnborg <sam@mars.ravnborg.org> -Santosh Shilimkar <ssantosh@kernel.org> Santosh Shilimkar <santosh.shilimkar@oracle.org> +Santosh Shilimkar <ssantosh@kernel.org> +Sarangdhar Joshi <spjoshi@codeaurora.org> Sascha Hauer <s.hauer@pengutronix.de> S.ÇaÄŸlar Onur <caglar@pardus.org.tr> -Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi> Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk> -Sebastian Reichel <sre@kernel.org> <sre@debian.org> Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk> +Sebastian Reichel <sre@kernel.org> <sre@debian.org> Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de> Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com> Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com> @@ -285,18 +292,21 @@ Simon Arlott <simon@octiron.net> <simon@fire.lp0.eu> Simon Kelley <simon@thekelleys.org.uk> Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr> Stephen Hemminger <shemminger@osdl.org> +Steve Wise <larrystevenwise@gmail.com> <swise@chelsio.com> +Steve Wise <larrystevenwise@gmail.com> <swise@opengridcomputing.com> Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> Subhash Jadavani <subhashj@codeaurora.org> Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Sumit Semwal <sumit.semwal@ti.com> +Takashi YOSHII <takashi.yoshii.zj@renesas.com> Tejun Heo <htejun@gmail.com> Thomas Graf <tgraf@suug.ch> Thomas Pedersen <twp@codeaurora.org> Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com> Todor Tomov <todor.too@gmail.com> <todor.tomov@linaro.org> Tony Luck <tony.luck@intel.com> -TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn> TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org> +TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn> Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com> Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de> Uwe Kleine-König <ukl@pengutronix.de> @@ -305,22 +315,16 @@ Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com> Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com> Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org> +Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com> Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com> Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com> -Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com> Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com> Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com> -Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com> -Takashi YOSHII <takashi.yoshii.zj@renesas.com> +Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com> +WeiXiong Liao <gmpy.liaowx@gmail.com> <liaoweixiong@allwinnertech.com> Will Deacon <will@kernel.org> <will.deacon@arm.com> -Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de> +Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yusuke Goda <goda.yusuke@renesas.com> -Gustavo Padovan <gustavo@las.ic.unicamp.br> -Gustavo Padovan <padovan@profusion.mobi> -Changbin Du <changbin.du@intel.com> <changbin.du@intel.com> -Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com> -Steve Wise <larrystevenwise@gmail.com> <swise@chelsio.com> -Steve Wise <larrystevenwise@gmail.com> <swise@opengridcomputing.com> @@ -191,6 +191,10 @@ N: Krishna Balasubramanian E: balasub@cis.ohio-state.edu D: Wrote SYS V IPC (part of standard kernel since 0.99.10) +B: Robert Baldyga +E: r.baldyga@hackerion.com +D: Samsung S3FWRN5 NCI NFC Controller + N: Chris Ball E: chris@printf.net D: Former maintainer of the MMC/SD/SDIO subsystem. diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 index f7e32f218f73..e82fc37be802 100644 --- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 @@ -43,7 +43,7 @@ Description: read only This sysfs interface exposes the number of cores per chip present in the system. -What: /sys/devices/hv_24x7/interface/cpumask +What: /sys/devices/hv_24x7/cpumask Date: July 2020 Contact: Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org> Description: read only diff --git a/Documentation/RCU/lockdep.rst b/Documentation/RCU/lockdep.rst index f1fc8ae3846a..cc860a0c296b 100644 --- a/Documentation/RCU/lockdep.rst +++ b/Documentation/RCU/lockdep.rst @@ -49,7 +49,7 @@ checking of rcu_dereference() primitives: is invoked by both RCU-sched readers and updaters. srcu_dereference_check(p, c): Use explicit check expression "c" along with - srcu_read_lock_held()(). This is useful in code that + srcu_read_lock_held(). This is useful in code that is invoked by both SRCU readers and updaters. rcu_dereference_raw(p): Don't check. (Use sparingly, if at all.) diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt index d336f3f73a4c..63fd4e6a014b 100644 --- a/Documentation/admin-guide/devices.txt +++ b/Documentation/admin-guide/devices.txt @@ -1662,7 +1662,7 @@ 98 block User-mode virtual block device 0 = /dev/ubda First user-mode block device - 16 = /dev/udbb Second user-mode block device + 16 = /dev/ubdb Second user-mode block device ... Partitions are handled in the same way as for IDE diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst index a683976fad6d..d2795ca6821e 100644 --- a/Documentation/admin-guide/ext4.rst +++ b/Documentation/admin-guide/ext4.rst @@ -489,6 +489,9 @@ Files in /sys/fs/ext4/<devname>: multiple of this tuning parameter if the stripe size is not set in the ext4 superblock + mb_max_inode_prealloc + The maximum length of per-inode ext4_prealloc_space list. + mb_max_to_scan The maximum number of extents the multiblock allocator will search to find the best extent. @@ -529,21 +532,21 @@ Files in /sys/fs/ext4/<devname>: Ioctls ====== -There is some Ext4 specific functionality which can be accessed by applications -through the system call interfaces. The list of all Ext4 specific ioctls are -shown in the table below. +Ext4 implements various ioctls which can be used by applications to access +ext4-specific functionality. An incomplete list of these ioctls is shown in the +table below. This list includes truly ext4-specific ioctls (``EXT4_IOC_*``) as +well as ioctls that may have been ext4-specific originally but are now supported +by some other filesystem(s) too (``FS_IOC_*``). -Table of Ext4 specific ioctls +Table of Ext4 ioctls - EXT4_IOC_GETFLAGS + FS_IOC_GETFLAGS Get additional attributes associated with inode. The ioctl argument is - an integer bitfield, with bit values described in ext4.h. This ioctl is - an alias for FS_IOC_GETFLAGS. + an integer bitfield, with bit values described in ext4.h. - EXT4_IOC_SETFLAGS + FS_IOC_SETFLAGS Set additional attributes associated with inode. The ioctl argument is - an integer bitfield, with bit values described in ext4.h. This ioctl is - an alias for FS_IOC_SETFLAGS. + an integer bitfield, with bit values described in ext4.h. EXT4_IOC_GETVERSION, EXT4_IOC_GETVERSION_OLD Get the inode i_generation number stored for each inode. The diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bdc1f33fd3d1..8af893ef0d46 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1233,8 +1233,7 @@ efi= [EFI] Format: { "debug", "disable_early_pci_dma", "nochunk", "noruntime", "nosoftreserve", - "novamap", "no_disable_early_pci_dma", - "old_map" } + "novamap", "no_disable_early_pci_dma" } debug: enable misc debug output. disable_early_pci_dma: disable the busmaster bit on all PCI bridges while in the EFI boot stub. @@ -1251,8 +1250,6 @@ novamap: do not call SetVirtualAddressMap(). no_disable_early_pci_dma: Leave the busmaster bit set on all PCI bridges while in the EFI boot stub - old_map [X86-64]: switch to the old ioremap-based EFI - runtime services mapping. [Needs CONFIG_X86_UV=y] efi_no_storage_paranoia [EFI; X86] Using this parameter you can use more than 50% of @@ -1341,6 +1338,11 @@ Format: <interval>,<probability>,<space>,<times> See also Documentation/fault-injection/. + fb_tunnels= [NET] + Format: { initns | none } + See Documentation/admin-guide/sysctl/net.rst for + fb_tunnels_only_for_init_ns + floppy= [HW] See Documentation/admin-guide/blockdev/floppy.rst. diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst index 5e477869df18..5fe1ade88c17 100644 --- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst +++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst @@ -1434,7 +1434,7 @@ on the feature, restricting the viewing angles. DYTC Lapmode sensor ------------------- +------------------- sysfs: dytc_lapmode diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst index 7adef969ffee..5072e7064d13 100644 --- a/Documentation/admin-guide/pm/intel_pstate.rst +++ b/Documentation/admin-guide/pm/intel_pstate.rst @@ -123,7 +123,9 @@ Energy-Performance Bias (EPB) knob (otherwise), which means that the processor's internal P-state selection logic is expected to focus entirely on performance. This will override the EPP/EPB setting coming from the ``sysfs`` interface -(see `Energy vs Performance Hints`_ below). +(see `Energy vs Performance Hints`_ below). Moreover, any attempts to change +the EPP/EPB to a value different from 0 ("performance") via ``sysfs`` in this +configuration will be rejected. Also, in this configuration the range of P-states available to the processor's internal P-state selection logic is always restricted to the upper boundary @@ -564,8 +566,8 @@ Energy-Performance Preference (EPP) knob (if supported) or its Energy-Performance Bias (EPB) knob. It is also possible to write a positive integer value between 0 to 255, if the EPP feature is present. If the EPP feature is not present, writing integer value to this attribute is not -supported. In this case, user can use - "/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface. +supported. In this case, user can use the +"/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface. [Note that tasks may by migrated from one CPU to another by the scheduler's load-balancing algorithm and if different energy vs performance hints are diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 42cd04bca548..57fd6ce68fe0 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -300,7 +300,6 @@ Note: 0: 0 1 2 3 4 5 6 7 RSS hash key: 84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89 - netdev_tstamp_prequeue ---------------------- @@ -321,11 +320,20 @@ fb_tunnels_only_for_init_net ---------------------------- Controls if fallback tunnels (like tunl0, gre0, gretap0, erspan0, -sit0, ip6tnl0, ip6gre0) are automatically created when a new -network namespace is created, if corresponding tunnel is present -in initial network namespace. -If set to 1, these devices are not automatically created, and -user space is responsible for creating them if needed. +sit0, ip6tnl0, ip6gre0) are automatically created. There are 3 possibilities +(a) value = 0; respective fallback tunnels are created when module is +loaded in every net namespaces (backward compatible behavior). +(b) value = 1; [kcmd value: initns] respective fallback tunnels are +created only in init net namespace and every other net namespace will +not have them. +(c) value = 2; [kcmd value: none] fallback tunnels are not created +when a module is loaded in any of the net namespace. Setting value to +"2" is pointless after boot if these modules are built-in, so there is +a kernel command-line option that can change this default. Please refer to +Documentation/admin-guide/kernel-parameters.txt for additional details. + +Not creating fallback tunnels gives control to userspace to create +whatever is needed only and avoid creating devices which are redundant. Default : 0 (for compatibility reasons) diff --git a/Documentation/bpf/bpf_devel_QA.rst b/Documentation/bpf/bpf_devel_QA.rst index a26aa1b9b259..75a0dca5f295 100644 --- a/Documentation/bpf/bpf_devel_QA.rst +++ b/Documentation/bpf/bpf_devel_QA.rst @@ -149,7 +149,7 @@ In case the patch or patch series has to be reworked and sent out again in a second or later revision, it is also required to add a version number (``v2``, ``v3``, ...) into the subject prefix:: - git format-patch --subject-prefix='PATCH net-next v2' start..finish + git format-patch --subject-prefix='PATCH bpf-next v2' start..finish When changes have been requested to the patch series, always send the whole patch series again with the feedback incorporated (never send @@ -479,17 +479,18 @@ LLVM's static compiler lists the supported targets through $ llc --version LLVM (http://llvm.org/): - LLVM version 6.0.0svn + LLVM version 10.0.0 Optimized build. Default target: x86_64-unknown-linux-gnu Host CPU: skylake Registered Targets: - bpf - BPF (host endian) - bpfeb - BPF (big endian) - bpfel - BPF (little endian) - x86 - 32-bit X86: Pentium-Pro and above - x86-64 - 64-bit X86: EM64T and AMD64 + aarch64 - AArch64 (little endian) + bpf - BPF (host endian) + bpfeb - BPF (big endian) + bpfel - BPF (little endian) + x86 - 32-bit X86: Pentium-Pro and above + x86-64 - 64-bit X86: EM64T and AMD64 For developers in order to utilize the latest features added to LLVM's BPF back end, it is advisable to run the latest LLVM releases. Support @@ -517,6 +518,10 @@ from the git repositories:: The built binaries can then be found in the build/bin/ directory, where you can point the PATH variable to. +Set ``-DLLVM_TARGETS_TO_BUILD`` equal to the target you wish to build, you +will find a full list of targets within the llvm-project/llvm/lib/Target +directory. + Q: Reporting LLVM BPF issues ---------------------------- Q: Should I notify BPF kernel maintainers about issues in LLVM's BPF code diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index b5361b8621c9..44dc789de2b4 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -724,6 +724,31 @@ want to define unused entry in BTF_ID_LIST, like:: BTF_ID_UNUSED BTF_ID(struct, task_struct) +The ``BTF_SET_START/END`` macros pair defines sorted list of BTF ID values +and their count, with following syntax:: + + BTF_SET_START(set) + BTF_ID(type1, name1) + BTF_ID(type2, name2) + BTF_SET_END(set) + +resulting in following layout in .BTF_ids section:: + + __BTF_ID__set__set: + .zero 4 + __BTF_ID__type1__name1__3: + .zero 4 + __BTF_ID__type2__name2__4: + .zero 4 + +The ``struct btf_id_set set;`` variable is defined to access the list. + +The ``typeX`` name can be one of following:: + + struct, union, typedef, func + +and is used as a filter when resolving the BTF ID value. + All the BTF ID lists and sets are compiled in the .BTF_ids section and resolved during the linking phase of kernel build by ``resolve_btfids`` tool. diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index d46429be334e..4f2874b729c3 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -36,6 +36,12 @@ Two sets of Questions and Answers (Q&A) are maintained. bpf_devel_QA +Helper functions +================ + +* `bpf-helpers(7)`_ maintains a list of helpers available to eBPF programs. + + Program types ============= @@ -46,6 +52,7 @@ Program types prog_cgroup_sysctl prog_flow_dissector bpf_lsm + prog_sk_lookup Map types @@ -79,4 +86,5 @@ Other .. _networking-filter: ../networking/filter.rst .. _man-pages: https://www.kernel.org/doc/man-pages/ .. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html +.. _bpf-helpers(7): https://man7.org/linux/man-pages/man7/bpf-helpers.7.html .. _BPF and XDP Reference Guide: https://docs.cilium.io/en/latest/bpf/ diff --git a/Documentation/bpf/prog_sk_lookup.rst b/Documentation/bpf/prog_sk_lookup.rst new file mode 100644 index 000000000000..85a305c19bcd --- /dev/null +++ b/Documentation/bpf/prog_sk_lookup.rst @@ -0,0 +1,98 @@ +.. SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) + +===================== +BPF sk_lookup program +===================== + +BPF sk_lookup program type (``BPF_PROG_TYPE_SK_LOOKUP``) introduces programmability +into the socket lookup performed by the transport layer when a packet is to be +delivered locally. + +When invoked BPF sk_lookup program can select a socket that will receive the +incoming packet by calling the ``bpf_sk_assign()`` BPF helper function. + +Hooks for a common attach point (``BPF_SK_LOOKUP``) exist for both TCP and UDP. + +Motivation +========== + +BPF sk_lookup program type was introduced to address setup scenarios where +binding sockets to an address with ``bind()`` socket call is impractical, such +as: + +1. receiving connections on a range of IP addresses, e.g. 192.0.2.0/24, when + binding to a wildcard address ``INADRR_ANY`` is not possible due to a port + conflict, +2. receiving connections on all or a wide range of ports, i.e. an L7 proxy use + case. + +Such setups would require creating and ``bind()``'ing one socket to each of the +IP address/port in the range, leading to resource consumption and potential +latency spikes during socket lookup. + +Attachment +========== + +BPF sk_lookup program can be attached to a network namespace with +``bpf(BPF_LINK_CREATE, ...)`` syscall using the ``BPF_SK_LOOKUP`` attach type and a +netns FD as attachment ``target_fd``. + +Multiple programs can be attached to one network namespace. Programs will be +invoked in the same order as they were attached. + +Hooks +===== + +The attached BPF sk_lookup programs run whenever the transport layer needs to +find a listening (TCP) or an unconnected (UDP) socket for an incoming packet. + +Incoming traffic to established (TCP) and connected (UDP) sockets is delivered +as usual without triggering the BPF sk_lookup hook. + +The attached BPF programs must return with either ``SK_PASS`` or ``SK_DROP`` +verdict code. As for other BPF program types that are network filters, +``SK_PASS`` signifies that the socket lookup should continue on to regular +hashtable-based lookup, while ``SK_DROP`` causes the transport layer to drop the +packet. + +A BPF sk_lookup program can also select a socket to receive the packet by +calling ``bpf_sk_assign()`` BPF helper. Typically, the program looks up a socket +in a map holding sockets, such as ``SOCKMAP`` or ``SOCKHASH``, and passes a +``struct bpf_sock *`` to ``bpf_sk_assign()`` helper to record the +selection. Selecting a socket only takes effect if the program has terminated +with ``SK_PASS`` code. + +When multiple programs are attached, the end result is determined from return +codes of all the programs according to the following rules: + +1. If any program returned ``SK_PASS`` and selected a valid socket, the socket + is used as the result of the socket lookup. +2. If more than one program returned ``SK_PASS`` and selected a socket, the last + selection takes effect. +3. If any program returned ``SK_DROP``, and no program returned ``SK_PASS`` and + selected a socket, socket lookup fails. +4. If all programs returned ``SK_PASS`` and none of them selected a socket, + socket lookup continues on. + +API +=== + +In its context, an instance of ``struct bpf_sk_lookup``, BPF sk_lookup program +receives information about the packet that triggered the socket lookup. Namely: + +* IP version (``AF_INET`` or ``AF_INET6``), +* L4 protocol identifier (``IPPROTO_TCP`` or ``IPPROTO_UDP``), +* source and destination IP address, +* source and destination L4 port, +* the socket that has been selected with ``bpf_sk_assign()``. + +Refer to ``struct bpf_sk_lookup`` declaration in ``linux/bpf.h`` user API +header, and `bpf-helpers(7) +<https://man7.org/linux/man-pages/man7/bpf-helpers.7.html>`_ man-page section +for ``bpf_sk_assign()`` for details. + +Example +======= + +See ``tools/testing/selftests/bpf/prog_tests/sk_lookup.c`` for the reference +implementation. diff --git a/Documentation/devicetree/bindings/clock/imx23-clock.yaml b/Documentation/devicetree/bindings/clock/imx23-clock.yaml index 66cb238a1040..ad21899981af 100644 --- a/Documentation/devicetree/bindings/clock/imx23-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx23-clock.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Clock bindings for Freescale i.MX23 maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> description: | The clock consumer should specify the desired clock by having the clock diff --git a/Documentation/devicetree/bindings/clock/imx28-clock.yaml b/Documentation/devicetree/bindings/clock/imx28-clock.yaml index 72328d5ca09a..f1af1108129e 100644 --- a/Documentation/devicetree/bindings/clock/imx28-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx28-clock.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Clock bindings for Freescale i.MX28 maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> description: | The clock consumer should specify the desired clock by having the clock diff --git a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml index ccf5b50e798b..dfa1133f8c5e 100644 --- a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml +++ b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS GPIO controller maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> - Anson Huang <Anson.Huang@nxp.com> description: | diff --git a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml index d3134ed775fa..21ae7bce038e 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS Inter IC (I2C) Controller maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt deleted file mode 100644 index 7841cb099e13..000000000000 --- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt +++ /dev/null @@ -1,66 +0,0 @@ -Texas Instruments K3 Interrupt Aggregator -========================================= - -The Interrupt Aggregator (INTA) provides a centralized machine -which handles the termination of system events to that they can -be coherently processed by the host(s) in the system. A maximum -of 64 events can be mapped to a single interrupt. - - - Interrupt Aggregator - +-----------------------------------------+ - | Intmap VINT | - | +--------------+ +------------+ | - m ------>| | vint | bit | | 0 |.....|63| vint0 | - . | +--------------+ +------------+ | +------+ - . | . . | | HOST | -Globalevents ------>| . . |------>| IRQ | - . | . . | | CTRL | - . | . . | +------+ - n ------>| +--------------+ +------------+ | - | | vint | bit | | 0 |.....|63| vintx | - | +--------------+ +------------+ | - | | - +-----------------------------------------+ - -Configuration of these Intmap registers that maps global events to vint is done -by a system controller (like the Device Memory and Security Controller on K3 -AM654 SoC). Driver should request the system controller to get the range -of global events and vints assigned to the requesting host. Management -of these requested resources should be handled by driver and requests -system controller to map specific global event to vint, bit pair. - -Communication between the host processor running an OS and the system -controller happens through a protocol called TI System Control Interface -(TISCI protocol). For more details refer: -Documentation/devicetree/bindings/arm/keystone/ti,sci.txt - -TISCI Interrupt Aggregator Node: -------------------------------- -- compatible: Must be "ti,sci-inta". -- reg: Should contain registers location and length. -- interrupt-controller: Identifies the node as an interrupt controller -- msi-controller: Identifies the node as an MSI controller. -- interrupt-parent: phandle of irq parent. -- ti,sci: Phandle to TI-SCI compatible System controller node. -- ti,sci-dev-id: TISCI device ID of the Interrupt Aggregator. -- ti,sci-rm-range-vint: Array of TISCI subtype ids representing vints(inta - outputs) range within this INTA, assigned to the - requesting host context. -- ti,sci-rm-range-global-event: Array of TISCI subtype ids representing the - global events range reaching this IA and are assigned - to the requesting host context. - -Example: --------- -main_udmass_inta: interrupt-controller@33d00000 { - compatible = "ti,sci-inta"; - reg = <0x0 0x33d00000 0x0 0x100000>; - interrupt-controller; - msi-controller; - interrupt-parent = <&main_navss_intr>; - ti,sci = <&dmsc>; - ti,sci-dev-id = <179>; - ti,sci-rm-range-vint = <0x0>; - ti,sci-rm-range-global-event = <0x1>; -}; diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml new file mode 100644 index 000000000000..c7cd05656a3e --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml @@ -0,0 +1,98 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/interrupt-controller/ti,sci-inta.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments K3 Interrupt Aggregator + +maintainers: + - Lokesh Vutla <lokeshvutla@ti.com> + +allOf: + - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml# + +description: | + The Interrupt Aggregator (INTA) provides a centralized machine + which handles the termination of system events to that they can + be coherently processed by the host(s) in the system. A maximum + of 64 events can be mapped to a single interrupt. + + Interrupt Aggregator + +-----------------------------------------+ + | Intmap VINT | + | +--------------+ +------------+ | + m ------>| | vint | bit | | 0 |.....|63| vint0 | + . | +--------------+ +------------+ | +------+ + . | . . | | HOST | + Globalevents ------>| . . |----->| IRQ | + . | . . | | CTRL | + . | . . | +------+ + n ------>| +--------------+ +------------+ | + | | vint | bit | | 0 |.....|63| vintx | + | +--------------+ +------------+ | + | | + +-----------------------------------------+ + + Configuration of these Intmap registers that maps global events to vint is + done by a system controller (like the Device Memory and Security Controller + on AM654 SoC). Driver should request the system controller to get the range + of global events and vints assigned to the requesting host. Management + of these requested resources should be handled by driver and requests + system controller to map specific global event to vint, bit pair. + + Communication between the host processor running an OS and the system + controller happens through a protocol called TI System Control Interface + (TISCI protocol). + +properties: + compatible: + const: ti,sci-inta + + reg: + maxItems: 1 + + interrupt-controller: true + + msi-controller: true + + ti,interrupt-ranges: + $ref: /schemas/types.yaml#/definitions/uint32-matrix + description: | + Interrupt ranges that converts the INTA output hw irq numbers + to parents's input interrupt numbers. + items: + items: + - description: | + "output_irq" specifies the base for inta output irq + - description: | + "parent's input irq" specifies the base for parent irq + - description: | + "limit" specifies the limit for translation + +required: + - compatible + - reg + - interrupt-controller + - msi-controller + - ti,sci + - ti,sci-dev-id + - ti,interrupt-ranges + +examples: + - | + bus { + #address-cells = <2>; + #size-cells = <2>; + + main_udmass_inta: msi-controller@33d00000 { + compatible = "ti,sci-inta"; + reg = <0x0 0x33d00000 0x0 0x100000>; + interrupt-controller; + msi-controller; + interrupt-parent = <&main_navss_intr>; + ti,sci = <&dmsc>; + ti,sci-dev-id = <179>; + ti,interrupt-ranges = <0 0 256>; + }; + }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt deleted file mode 100644 index 178fca08278f..000000000000 --- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt +++ /dev/null @@ -1,82 +0,0 @@ -Texas Instruments K3 Interrupt Router -===================================== - -The Interrupt Router (INTR) module provides a mechanism to mux M -interrupt inputs to N interrupt outputs, where all M inputs are selectable -to be driven per N output. An Interrupt Router can either handle edge triggered -or level triggered interrupts and that is fixed in hardware. - - Interrupt Router - +----------------------+ - | Inputs Outputs | - +-------+ | +------+ +-----+ | - | GPIO |----------->| | irq0 | | 0 | | Host IRQ - +-------+ | +------+ +-----+ | controller - | . . | +-------+ - +-------+ | . . |----->| IRQ | - | INTA |----------->| . . | +-------+ - +-------+ | . +-----+ | - | +------+ | N | | - | | irqM | +-----+ | - | +------+ | - | | - +----------------------+ - -There is one register per output (MUXCNTL_N) that controls the selection. -Configuration of these MUXCNTL_N registers is done by a system controller -(like the Device Memory and Security Controller on K3 AM654 SoC). System -controller will keep track of the used and unused registers within the Router. -Driver should request the system controller to get the range of GIC IRQs -assigned to the requesting hosts. It is the drivers responsibility to keep -track of Host IRQs. - -Communication between the host processor running an OS and the system -controller happens through a protocol called TI System Control Interface -(TISCI protocol). For more details refer: -Documentation/devicetree/bindings/arm/keystone/ti,sci.txt - -TISCI Interrupt Router Node: ----------------------------- -Required Properties: -- compatible: Must be "ti,sci-intr". -- ti,intr-trigger-type: Should be one of the following: - 1: If intr supports edge triggered interrupts. - 4: If intr supports level triggered interrupts. -- interrupt-controller: Identifies the node as an interrupt controller -- #interrupt-cells: Specifies the number of cells needed to encode an - interrupt source. The value should be 2. - First cell should contain the TISCI device ID of source - Second cell should contain the interrupt source offset - within the device. -- ti,sci: Phandle to TI-SCI compatible System controller node. -- ti,sci-dst-id: TISCI device ID of the destination IRQ controller. -- ti,sci-rm-range-girq: Array of TISCI subtype ids representing the host irqs - assigned to this interrupt router. Each subtype id - corresponds to a range of host irqs. - -For more details on TISCI IRQ resource management refer: -https://downloads.ti.com/tisci/esd/latest/2_tisci_msgs/rm/rm_irq.html - -Example: --------- -The following example demonstrates both interrupt router node and the consumer -node(main gpio) on the AM654 SoC: - -main_intr: interrupt-controller0 { - compatible = "ti,sci-intr"; - ti,intr-trigger-type = <1>; - interrupt-controller; - interrupt-parent = <&gic500>; - #interrupt-cells = <2>; - ti,sci = <&dmsc>; - ti,sci-dst-id = <56>; - ti,sci-rm-range-girq = <0x1>; -}; - -main_gpio0: gpio@600000 { - ... - interrupt-parent = <&main_intr>; - interrupts = <57 256>, <57 257>, <57 258>, - <57 259>, <57 260>, <57 261>; - ... -}; diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml new file mode 100644 index 000000000000..cff6a956afb4 --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml @@ -0,0 +1,102 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/interrupt-controller/ti,sci-intr.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments K3 Interrupt Router + +maintainers: + - Lokesh Vutla <lokeshvutla@ti.com> + +allOf: + - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml# + +description: | + The Interrupt Router (INTR) module provides a mechanism to mux M + interrupt inputs to N interrupt outputs, where all M inputs are selectable + to be driven per N output. An Interrupt Router can either handle edge + triggered or level triggered interrupts and that is fixed in hardware. + + Interrupt Router + +----------------------+ + | Inputs Outputs | + +-------+ | +------+ +-----+ | + | GPIO |----------->| | irq0 | | 0 | | Host IRQ + +-------+ | +------+ +-----+ | controller + | . . | +-------+ + +-------+ | . . |----->| IRQ | + | INTA |----------->| . . | +-------+ + +-------+ | . +-----+ | + | +------+ | N | | + | | irqM | +-----+ | + | +------+ | + | | + +----------------------+ + + There is one register per output (MUXCNTL_N) that controls the selection. + Configuration of these MUXCNTL_N registers is done by a system controller + (like the Device Memory and Security Controller on K3 AM654 SoC). System + controller will keep track of the used and unused registers within the Router. + Driver should request the system controller to get the range of GIC IRQs + assigned to the requesting hosts. It is the drivers responsibility to keep + track of Host IRQs. + + Communication between the host processor running an OS and the system + controller happens through a protocol called TI System Control Interface + (TISCI protocol). + +properties: + compatible: + const: ti,sci-intr + + ti,intr-trigger-type: + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [1, 4] + description: | + Should be one of the following. + 1 = If intr supports edge triggered interrupts. + 4 = If intr supports level triggered interrupts. + + interrupt-controller: true + + '#interrupt-cells': + const: 1 + description: | + The 1st cell should contain interrupt router input hw number. + + ti,interrupt-ranges: + $ref: /schemas/types.yaml#/definitions/uint32-matrix + description: | + Interrupt ranges that converts the INTR output hw irq numbers + to parents's input interrupt numbers. + items: + items: + - description: | + "output_irq" specifies the base for intr output irq + - description: | + "parent's input irq" specifies the base for parent irq + - description: | + "limit" specifies the limit for translation + +required: + - compatible + - ti,intr-trigger-type + - interrupt-controller + - '#interrupt-cells' + - ti,sci + - ti,sci-dev-id + - ti,interrupt-ranges + +examples: + - | + main_gpio_intr: interrupt-controller0 { + compatible = "ti,sci-intr"; + ti,intr-trigger-type = <1>; + interrupt-controller; + interrupt-parent = <&gic500>; + #interrupt-cells = <1>; + ti,sci = <&dmsc>; + ti,sci-dev-id = <131>; + ti,interrupt-ranges = <0 360 32>; + }; diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml index 5887c917d480..58fe9d02a781 100644 --- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml @@ -30,9 +30,13 @@ allOf: then: properties: clock-output-names: - items: - - const: clk_out_sd0 - - const: clk_in_sd0 + oneOf: + - items: + - const: clk_out_sd0 + - const: clk_in_sd0 + - items: + - const: clk_out_sd1 + - const: clk_in_sd1 properties: compatible: diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml index 75dc1168d717..10b45966f1b8 100644 --- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml +++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale Enhanced Secure Digital Host Controller (eSDHC) for i.MX maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> allOf: - $ref: "mmc-controller.yaml" diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt index 0c9cf6a8808c..26a8f320a156 100644 --- a/Documentation/devicetree/bindings/mmc/mtk-sd.txt +++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt @@ -50,6 +50,8 @@ Optional properties: error caused by stop clock(fifo full) Valid range = [0:0x7]. if not present, default value is 0. applied to compatible "mediatek,mt2701-mmc". +- resets: Phandle and reset specifier pair to softreset line of MSDC IP. +- reset-names: Should be "hrst". Examples: mmc0: mmc@11230000 { diff --git a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml index 1cccc0478d49..bec8f8c71ff2 100644 --- a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml +++ b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS MMC controller maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> description: | The Freescale MXS Synchronous Serial Ports (SSP) can act as a MMC controller diff --git a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt index 2cf3affa1be7..96c0b1440c9c 100644 --- a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt +++ b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt @@ -15,8 +15,15 @@ Required properties: - "nvidia,tegra210-sdhci": for Tegra210 - "nvidia,tegra186-sdhci": for Tegra186 - "nvidia,tegra194-sdhci": for Tegra194 -- clocks : Must contain one entry, for the module clock. - See ../clocks/clock-bindings.txt for details. +- clocks: For Tegra210, Tegra186 and Tegra194 must contain two entries. + One for the module clock and one for the timeout clock. + For all other Tegra devices, must contain a single entry for + the module clock. See ../clocks/clock-bindings.txt for details. +- clock-names: For Tegra210, Tegra186 and Tegra194 must contain the + strings 'sdhci' and 'tmclk' to represent the module and + the timeout clocks, respectively. + For all other Tegra devices must contain the string 'sdhci' + to represent the module clock. - resets : Must contain an entry for each entry in reset-names. See ../reset/reset.txt for details. - reset-names : Must include the following entries: @@ -99,7 +106,7 @@ Optional properties for Tegra210, Tegra186 and Tegra194: Example: sdhci@700b0000 { - compatible = "nvidia,tegra210-sdhci", "nvidia,tegra124-sdhci"; + compatible = "nvidia,tegra124-sdhci"; reg = <0x0 0x700b0000 0x0 0x200>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; clocks = <&tegra_car TEGRA210_CLK_SDMMC1>; @@ -115,3 +122,22 @@ sdhci@700b0000 { nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>; status = "disabled"; }; + +sdhci@700b0000 { + compatible = "nvidia,tegra210-sdhci"; + reg = <0x0 0x700b0000 0x0 0x200>; + interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&tegra_car TEGRA210_CLK_SDMMC1>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; + resets = <&tegra_car 14>; + reset-names = "sdhci"; + pinctrl-names = "sdmmc-3v3", "sdmmc-1v8"; + pinctrl-0 = <&sdmmc1_3v3>; + pinctrl-1 = <&sdmmc1_1v8>; + nvidia,pad-autocal-pull-up-offset-3v3 = <0x00>; + nvidia,pad-autocal-pull-down-offset-3v3 = <0x7d>; + nvidia,pad-autocal-pull-up-offset-1v8 = <0x7b>; + nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>; + status = "disabled"; +}; diff --git a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt index 88b57b0ca1f4..97ca62b0e14d 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt +++ b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt @@ -50,6 +50,13 @@ Optional properties: - reset-names: If the "reset" property is specified, this property should have the value "switch" to denote the switch reset line. +- clocks: when provided, the first phandle is to the switch's main clock and + is valid for both BCM7445 and BCM7278. The second phandle is only applicable + to BCM7445 and is to support dividing the switch core clock. + +- clock-names: when provided, the first phandle must be "sw_switch", and the + second must be named "sw_switch_mdiv". + Port subnodes: Optional properties: diff --git a/Documentation/devicetree/bindings/net/brcm,systemport.txt b/Documentation/devicetree/bindings/net/brcm,systemport.txt index 83f29e0e11ba..75736739bfdd 100644 --- a/Documentation/devicetree/bindings/net/brcm,systemport.txt +++ b/Documentation/devicetree/bindings/net/brcm,systemport.txt @@ -20,6 +20,11 @@ Optional properties: - systemport,num-tier1-arb: number of tier 1 arbiters, an integer - systemport,num-txq: number of HW transmit queues, an integer - systemport,num-rxq: number of HW receive queues, an integer +- clocks: When provided, must be two phandles to the functional clocks nodes of + the SYSTEMPORT block. The first phandle is the main SYSTEMPORT clock used + during normal operation, while the second phandle is the Wake-on-LAN clock. +- clock-names: When provided, names of the functional clock phandles, first + name should be "sw_sysport" and second should be "sw_sysportwol". Example: ethernet@f04a0000 { diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt index bf7328aba330..dab208b5c7c7 100644 --- a/Documentation/devicetree/bindings/net/dsa/dsa.txt +++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt @@ -1,4 +1,4 @@ Distributed Switch Architecture Device Tree Bindings ---------------------------------------------------- -See Documentation/devicetree/bindings/net/dsa/dsa.yaml for the documenation. +See Documentation/devicetree/bindings/net/dsa/dsa.yaml for the documentation. diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 1c4474036d46..fa2baca8c726 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -54,7 +54,8 @@ properties: phy-connection-type: description: - Operation mode of the PHY interface + Specifies interface type between the Ethernet device and a physical + layer (PHY) device. enum: # There is not a standard bus between the MAC and the PHY, # something proprietary is being used to embed the PHY in the diff --git a/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml b/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml new file mode 100644 index 000000000000..fa3ebba4e635 --- /dev/null +++ b/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml @@ -0,0 +1,130 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/intel,dwmac-plat.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Intel DWMAC glue layer Device Tree Bindings + +maintainers: + - Vineetha G. Jaya Kumaran <vineetha.g.jaya.kumaran@intel.com> + +select: + properties: + compatible: + contains: + enum: + - intel,keembay-dwmac + required: + - compatible + +allOf: + - $ref: "snps,dwmac.yaml#" + +properties: + compatible: + oneOf: + - items: + - enum: + - intel,keembay-dwmac + - const: snps,dwmac-4.10a + + clocks: + items: + - description: GMAC main clock + - description: PTP reference clock + - description: Tx clock + + clock-names: + items: + - const: stmmaceth + - const: ptp_ref + - const: tx_clk + +required: + - compatible + - clocks + - clock-names + +examples: +# FIXME: Remove defines and include the correct header file +# once it is available in mainline. + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + #define MOVISOC_KMB_PSS_GBE + #define MOVISOC_KMB_PSS_AUX_GBE_PTP + #define MOVISOC_KMB_PSS_AUX_GBE_TX + + stmmac_axi_setup: stmmac-axi-config { + snps,lpi_en; + snps,wr_osr_lmt = <0x0>; + snps,rd_osr_lmt = <0x2>; + snps,blen = <0 0 0 0 16 8 4>; + }; + + mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <2>; + snps,rx-sched-sp; + queue0 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x0>; + snps,priority = <0x0>; + }; + + queue1 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x1>; + snps,priority = <0x1>; + }; + }; + + mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <2>; + snps,tx-sched-wrr; + queue0 { + snps,weight = <0x10>; + snps,dcb-algorithm; + snps,priority = <0x0>; + }; + + queue1 { + snps,weight = <0x10>; + snps,dcb-algorithm; + snps,priority = <0x1>; + }; + }; + + gmac0: ethernet@3a000000 { + compatible = "intel,keembay-dwmac", "snps,dwmac-4.10a"; + interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + reg = <0x3a000000 0x8000>; + snps,perfect-filter-entries = <128>; + phy-handle = <ð_phy0>; + phy-mode = "rgmii"; + rx-fifo-depth = <4096>; + tx-fifo-depth = <4096>; + clock-names = "stmmaceth", "ptp_ref", "tx_clk"; + clocks = <&scmi_clk MOVISOC_KMB_PSS_GBE>, + <&scmi_clk MOVISOC_KMB_PSS_AUX_GBE_PTP>, + <&scmi_clk MOVISOC_KMB_PSS_AUX_GBE_TX>; + snps,pbl = <0x4>; + snps,axi-config = <&stmmac_axi_setup>; + snps,mtl-rx-config = <&mtl_rx_setup>; + snps,mtl-tx-config = <&mtl_tx_setup>; + snps,tso; + status = "okay"; + + mdio0 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + ethernet-phy@0 { + reg = <0>; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt b/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt deleted file mode 100644 index f02f6fb7f81c..000000000000 --- a/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt +++ /dev/null @@ -1,25 +0,0 @@ -* Samsung S3FWRN5 NCI NFC Controller - -Required properties: -- compatible: Should be "samsung,s3fwrn5-i2c". -- reg: address on the bus -- interrupts: GPIO interrupt to which the chip is connected -- s3fwrn5,en-gpios: Output GPIO pin used for enabling/disabling the chip -- s3fwrn5,fw-gpios: Output GPIO pin used to enter firmware mode and - sleep/wakeup control - -Example: - -&hsi2c_4 { - s3fwrn5@27 { - compatible = "samsung,s3fwrn5-i2c"; - - reg = <0x27>; - - interrupt-parent = <&gpa1>; - interrupts = <3 0 0>; - - s3fwrn5,en-gpios = <&gpf1 4 0>; - s3fwrn5,fw-gpios = <&gpj0 2 0>; - }; -}; diff --git a/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml new file mode 100644 index 000000000000..cb0b8a560282 --- /dev/null +++ b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml @@ -0,0 +1,73 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/nfc/samsung,s3fwrn5.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung S3FWRN5 NCI NFC Controller + +maintainers: + - Krzysztof Kozlowski <krzk@kernel.org> + - Krzysztof Opasiak <k.opasiak@samsung.com> + +properties: + compatible: + const: samsung,s3fwrn5-i2c + + en-gpios: + maxItems: 1 + description: + Output GPIO pin used for enabling/disabling the chip + + interrupts: + maxItems: 1 + + reg: + maxItems: 1 + + wake-gpios: + maxItems: 1 + description: + Output GPIO pin used to enter firmware mode and sleep/wakeup control + + s3fwrn5,en-gpios: + maxItems: 1 + deprecated: true + description: + Use en-gpios + + s3fwrn5,fw-gpios: + maxItems: 1 + deprecated: true + description: + Use wake-gpios + +additionalProperties: false + +required: + - compatible + - en-gpios + - interrupts + - reg + - wake-gpios + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + i2c4 { + #address-cells = <1>; + #size-cells = <0>; + + s3fwrn5@27 { + compatible = "samsung,s3fwrn5-i2c"; + reg = <0x27>; + + interrupt-parent = <&gpa1>; + interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; + + en-gpios = <&gpf1 4 GPIO_ACTIVE_HIGH>; + wake-gpios = <&gpj0 2 GPIO_ACTIVE_HIGH>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml index 08678af5ed93..8ce5ed8a58dd 100644 --- a/Documentation/devicetree/bindings/net/renesas,ether.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml @@ -59,9 +59,15 @@ properties: clocks: maxItems: 1 - pinctrl-0: true + power-domains: + maxItems: 1 + + resets: + maxItems: 1 - pinctrl-names: true + phy-mode: true + + phy-handle: true renesas,no-ether-link: type: boolean @@ -74,6 +80,11 @@ properties: specify when the Ether LINK signal is active-low instead of normal active-high +patternProperties: + "^ethernet-phy@[0-9a-f]$": + type: object + $ref: ethernet-phy.yaml# + required: - compatible - reg @@ -83,7 +94,8 @@ required: - '#address-cells' - '#size-cells' - clocks - - pinctrl-0 + +additionalProperties: false examples: # Lager board @@ -99,8 +111,6 @@ examples: clocks = <&mstp8_clks R8A7790_CLK_ETHER>; phy-mode = "rmii"; phy-handle = <&phy1>; - pinctrl-0 = <ðer_pins>; - pinctrl-names = "default"; renesas,ether-link-active-low; #address-cells = <1>; #size-cells = <0>; @@ -109,7 +119,5 @@ examples: reg = <1>; interrupt-parent = <&irqc0>; interrupts = <0 IRQ_TYPE_LEVEL_LOW>; - pinctrl-0 = <&phy1_pins>; - pinctrl-names = "default"; }; }; diff --git a/Documentation/devicetree/bindings/net/smsc-lan87xx.txt b/Documentation/devicetree/bindings/net/smsc-lan87xx.txt index 8b7c719b0bb9..a8d0dc9a8c0e 100644 --- a/Documentation/devicetree/bindings/net/smsc-lan87xx.txt +++ b/Documentation/devicetree/bindings/net/smsc-lan87xx.txt @@ -5,6 +5,10 @@ through an Ethernet OF device node. Optional properties: +- clocks: + The clock used as phy reference clock and is connected to phy + pin XTAL1/CLKIN. + - smsc,disable-energy-detect: If set, do not enable energy detect mode for the SMSC phy. default: enable energy detect mode diff --git a/Documentation/devicetree/bindings/net/ti,dp83822.yaml b/Documentation/devicetree/bindings/net/ti,dp83822.yaml new file mode 100644 index 000000000000..55913534cbc2 --- /dev/null +++ b/Documentation/devicetree/bindings/net/ti,dp83822.yaml @@ -0,0 +1,80 @@ +# SPDX-License-Identifier: (GPL-2.0+ OR BSD-2-Clause) +# Copyright (C) 2020 Texas Instruments Incorporated +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/net/ti,dp83822.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: TI DP83822 ethernet PHY + +maintainers: + - Dan Murphy <dmurphy@ti.com> + +description: | + The DP83822 is a low-power, single-port, 10/100 Mbps Ethernet PHY. It + provides all of the physical layer functions needed to transmit and receive + data over standard, twisted-pair cables or to connect to an external, + fiber-optic transceiver. Additionally, the DP83822 provides flexibility to + connect to a MAC through a standard MII, RMII, or RGMII interface + + Specifications about the Ethernet PHY can be found at: + http://www.ti.com/lit/ds/symlink/dp83822i.pdf + +allOf: + - $ref: "ethernet-phy.yaml#" + +properties: + reg: + maxItems: 1 + + ti,link-loss-low: + type: boolean + description: | + DP83822 PHY in Fiber mode only. + Sets the DP83822 to detect a link drop condition when the signal goes + high. If not set then link drop will occur when the signal goes low. + This property is only applicable if the fiber mode support is strapped + to on. + + ti,fiber-mode: + type: boolean + description: | + DP83822 PHY only. + If present the DP83822 PHY is configured to operate in fiber mode + Fiber mode support can also be strapped. If the strap pin is not set + correctly or not set at all then this boolean can be used to enable it. + If the fiber mode is not strapped then signal detection for the PHY + is disabled. + In fiber mode, auto-negotiation is disabled and the PHY can only work in + 100base-fx (full and half duplex) modes. + + rx-internal-delay-ps: + description: | + DP83822 PHY only. + Setting this property to a non-zero number sets the RX internal delay + for the PHY. The internal delay for the PHY is fixed to 3.5ns relative + to receive data. + + tx-internal-delay-ps: + description: | + DP83822 PHY only. + Setting this property to a non-zero number sets the TX internal delay + for the PHY. The internal delay for the PHY is fixed to 3.5ns relative + to transmit data. + +required: + - reg + +examples: + - | + mdio0 { + #address-cells = <1>; + #size-cells = <0>; + ethphy0: ethernet-phy@0 { + reg = <0>; + rx-internal-delay-ps = <1>; + tx-internal-delay-ps = <1>; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml index 64b2c64ca806..a1e2be737eec 100644 --- a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml @@ -9,6 +9,14 @@ title: PCIe RC controller on Intel Gateway SoCs maintainers: - Dilip Kota <eswara.kota@linux.intel.com> +select: + properties: + compatible: + contains: + const: intel,lgm-pcie + required: + - compatible + properties: compatible: items: diff --git a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml index da68f4a25dd9..8740e076061e 100644 --- a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml +++ b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS PWM controller maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> - Anson Huang <anson.huang@nxp.com> properties: diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml index 1b50cedbfb3e..50df1a40bbe3 100644 --- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml +++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale (Enhanced) Configurable Serial Peripheral Interface (CSPI/eCSPI) for i.MX maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> allOf: - $ref: "/schemas/spi/spi-controller.yaml#" diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml index 22882e769e26..312d8fee9dbb 100644 --- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml +++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml @@ -39,6 +39,7 @@ properties: spi common code does not support use of CS signals discontinuously. i.MX8DXL-EVK board only uses CS1 without using CS0. Therefore, add this property to re-config the chipselect value in the LPSPI driver. + type: boolean required: - compatible diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml index aedac1669998..16b57f57d103 100644 --- a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP i.MX Thermal Binding maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> - Anson Huang <Anson.Huang@nxp.com> properties: diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml new file mode 100644 index 000000000000..2a0e9cd9fbcf --- /dev/null +++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml @@ -0,0 +1,60 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/timer/sifive,clint.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: SiFive Core Local Interruptor + +maintainers: + - Palmer Dabbelt <palmer@dabbelt.com> + - Anup Patel <anup.patel@wdc.com> + +description: + SiFive (and other RISC-V) SOCs include an implementation of the SiFive + Core Local Interruptor (CLINT) for M-mode timer and M-mode inter-processor + interrupts. It directly connects to the timer and inter-processor interrupt + lines of various HARTs (or CPUs) so RISC-V per-HART (or per-CPU) local + interrupt controller is the parent interrupt controller for CLINT device. + The clock frequency of CLINT is specified via "timebase-frequency" DT + property of "/cpus" DT node. The "timebase-frequency" DT property is + described in Documentation/devicetree/bindings/riscv/cpus.yaml + +properties: + compatible: + items: + - const: sifive,fu540-c000-clint + - const: sifive,clint0 + + description: + Should be "sifive,<chip>-clint" and "sifive,clint<version>". + Supported compatible strings are - + "sifive,fu540-c000-clint" for the SiFive CLINT v0 as integrated + onto the SiFive FU540 chip, and "sifive,clint0" for the SiFive + CLINT v0 IP block with no chip integration tweaks. + Please refer to sifive-blocks-ip-versioning.txt for details + + reg: + maxItems: 1 + + interrupts-extended: + minItems: 1 + +additionalProperties: false + +required: + - compatible + - reg + - interrupts-extended + +examples: + - | + timer@2000000 { + compatible = "sifive,fu540-c000-clint", "sifive,clint0"; + interrupts-extended = <&cpu1intc 3 &cpu1intc 7 + &cpu2intc 3 &cpu2intc 7 + &cpu3intc 3 &cpu3intc 7 + &cpu4intc 3 &cpu4intc 7>; + reg = <0x2000000 0x10000>; + }; +... diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 2baee2c817c1..63996ab03521 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -993,7 +993,7 @@ patternProperties: "^sst,.*": description: Silicon Storage Technology, Inc. "^sstar,.*": - description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd. + description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd. (formerly part of MStar Semiconductor, Inc.) "^st,.*": description: STMicroelectronics diff --git a/Documentation/devicetree/writing-schema.rst b/Documentation/devicetree/writing-schema.rst index 8c74a99f95e2..16f21e182ff6 100644 --- a/Documentation/devicetree/writing-schema.rst +++ b/Documentation/devicetree/writing-schema.rst @@ -5,7 +5,7 @@ Writing DeviceTree Bindings in json-schema Devicetree bindings are written using json-schema vocabulary. Schema files are written in a JSON compatible subset of YAML. YAML is used instead of JSON as it -considered more human readable and has some advantages such as allowing +is considered more human readable and has some advantages such as allowing comments (Prefixed with '#'). Schema Contents @@ -19,7 +19,7 @@ $id A json-schema unique identifier string. The string must be a valid URI typically containing the binding's filename and path. For DT schema, it must begin with "http://devicetree.org/schemas/". The URL is used in constructing - references to other files specified in schema "$ref" properties. A $ref values + references to other files specified in schema "$ref" properties. A $ref value with a leading '/' will have the hostname prepended. A $ref value a relative path or filename only will be prepended with the hostname and path components of the current schema file's '$id' value. A URL is used even for local files, diff --git a/Documentation/driver-api/fpga/fpga-bridge.rst b/Documentation/driver-api/fpga/fpga-bridge.rst index 71c5a40da320..ccd677ba7d76 100644 --- a/Documentation/driver-api/fpga/fpga-bridge.rst +++ b/Documentation/driver-api/fpga/fpga-bridge.rst @@ -6,9 +6,9 @@ API to implement a new FPGA bridge * struct :c:type:`fpga_bridge` — The FPGA Bridge structure * struct :c:type:`fpga_bridge_ops` — Low level Bridge driver ops -* :c:func:`devm_fpga_bridge_create()` — Allocate and init a bridge struct -* :c:func:`fpga_bridge_register()` — Register a bridge -* :c:func:`fpga_bridge_unregister()` — Unregister a bridge +* devm_fpga_bridge_create() — Allocate and init a bridge struct +* fpga_bridge_register() — Register a bridge +* fpga_bridge_unregister() — Unregister a bridge .. kernel-doc:: include/linux/fpga/fpga-bridge.h :functions: fpga_bridge diff --git a/Documentation/driver-api/fpga/fpga-mgr.rst b/Documentation/driver-api/fpga/fpga-mgr.rst index 576f1945eacd..af5382af1379 100644 --- a/Documentation/driver-api/fpga/fpga-mgr.rst +++ b/Documentation/driver-api/fpga/fpga-mgr.rst @@ -104,9 +104,9 @@ API for implementing a new FPGA Manager driver * ``fpga_mgr_states`` — Values for :c:member:`fpga_manager->state`. * struct :c:type:`fpga_manager` — the FPGA manager struct * struct :c:type:`fpga_manager_ops` — Low level FPGA manager driver ops -* :c:func:`devm_fpga_mgr_create` — Allocate and init a manager struct -* :c:func:`fpga_mgr_register` — Register an FPGA manager -* :c:func:`fpga_mgr_unregister` — Unregister an FPGA manager +* devm_fpga_mgr_create() — Allocate and init a manager struct +* fpga_mgr_register() — Register an FPGA manager +* fpga_mgr_unregister() — Unregister an FPGA manager .. kernel-doc:: include/linux/fpga/fpga-mgr.h :functions: fpga_mgr_states diff --git a/Documentation/driver-api/fpga/fpga-programming.rst b/Documentation/driver-api/fpga/fpga-programming.rst index b5484df6ff0f..f487ad64dfb9 100644 --- a/Documentation/driver-api/fpga/fpga-programming.rst +++ b/Documentation/driver-api/fpga/fpga-programming.rst @@ -6,9 +6,9 @@ Overview The in-kernel API for FPGA programming is a combination of APIs from FPGA manager, bridge, and regions. The actual function used to -trigger FPGA programming is :c:func:`fpga_region_program_fpga()`. +trigger FPGA programming is fpga_region_program_fpga(). -:c:func:`fpga_region_program_fpga()` uses functionality supplied by +fpga_region_program_fpga() uses functionality supplied by the FPGA manager and bridges. It will: * lock the region's mutex @@ -20,8 +20,8 @@ the FPGA manager and bridges. It will: * release the locks The struct fpga_image_info specifies what FPGA image to program. It is -allocated/freed by :c:func:`fpga_image_info_alloc()` and freed with -:c:func:`fpga_image_info_free()` +allocated/freed by fpga_image_info_alloc() and freed with +fpga_image_info_free() How to program an FPGA using a region ------------------------------------- @@ -84,10 +84,10 @@ will generate that list. Here's some sample code of what to do next:: API for programming an FPGA --------------------------- -* :c:func:`fpga_region_program_fpga` — Program an FPGA -* :c:type:`fpga_image_info` — Specifies what FPGA image to program -* :c:func:`fpga_image_info_alloc()` — Allocate an FPGA image info struct -* :c:func:`fpga_image_info_free()` — Free an FPGA image info struct +* fpga_region_program_fpga() — Program an FPGA +* fpga_image_info() — Specifies what FPGA image to program +* fpga_image_info_alloc() — Allocate an FPGA image info struct +* fpga_image_info_free() — Free an FPGA image info struct .. kernel-doc:: drivers/fpga/fpga-region.c :functions: fpga_region_program_fpga diff --git a/Documentation/driver-api/fpga/fpga-region.rst b/Documentation/driver-api/fpga/fpga-region.rst index 0529b2d2231a..31118a8ba218 100644 --- a/Documentation/driver-api/fpga/fpga-region.rst +++ b/Documentation/driver-api/fpga/fpga-region.rst @@ -46,18 +46,18 @@ API to add a new FPGA region ---------------------------- * struct :c:type:`fpga_region` — The FPGA region struct -* :c:func:`devm_fpga_region_create` — Allocate and init a region struct -* :c:func:`fpga_region_register` — Register an FPGA region -* :c:func:`fpga_region_unregister` — Unregister an FPGA region +* devm_fpga_region_create() — Allocate and init a region struct +* fpga_region_register() — Register an FPGA region +* fpga_region_unregister() — Unregister an FPGA region The FPGA region's probe function will need to get a reference to the FPGA Manager it will be using to do the programming. This usually would happen during the region's probe function. -* :c:func:`fpga_mgr_get` — Get a reference to an FPGA manager, raise ref count -* :c:func:`of_fpga_mgr_get` — Get a reference to an FPGA manager, raise ref count, +* fpga_mgr_get() — Get a reference to an FPGA manager, raise ref count +* of_fpga_mgr_get() — Get a reference to an FPGA manager, raise ref count, given a device node. -* :c:func:`fpga_mgr_put` — Put an FPGA manager +* fpga_mgr_put() — Put an FPGA manager The FPGA region will need to specify which bridges to control while programming the FPGA. The region driver can build a list of bridges during probe time @@ -66,11 +66,11 @@ the list of bridges to program just before programming (:c:member:`fpga_region->get_bridges`). The FPGA bridge framework supplies the following APIs to handle building or tearing down that list. -* :c:func:`fpga_bridge_get_to_list` — Get a ref of an FPGA bridge, add it to a +* fpga_bridge_get_to_list() — Get a ref of an FPGA bridge, add it to a list -* :c:func:`of_fpga_bridge_get_to_list` — Get a ref of an FPGA bridge, add it to a +* of_fpga_bridge_get_to_list() — Get a ref of an FPGA bridge, add it to a list, given a device node -* :c:func:`fpga_bridges_put` — Given a list of bridges, put them +* fpga_bridges_put() — Given a list of bridges, put them .. kernel-doc:: include/linux/fpga/fpga-region.h :functions: fpga_region diff --git a/Documentation/driver-api/iio/core.rst b/Documentation/driver-api/iio/core.rst index b0bc0c028cc5..51b21e002396 100644 --- a/Documentation/driver-api/iio/core.rst +++ b/Documentation/driver-api/iio/core.rst @@ -11,10 +11,10 @@ Industrial I/O Devices ---------------------- * struct :c:type:`iio_dev` - industrial I/O device -* :c:func:`iio_device_alloc()` - allocate an :c:type:`iio_dev` from a driver -* :c:func:`iio_device_free()` - free an :c:type:`iio_dev` from a driver -* :c:func:`iio_device_register()` - register a device with the IIO subsystem -* :c:func:`iio_device_unregister()` - unregister a device from the IIO +* iio_device_alloc() - allocate an :c:type:`iio_dev` from a driver +* iio_device_free() - free an :c:type:`iio_dev` from a driver +* iio_device_register() - register a device with the IIO subsystem +* iio_device_unregister() - unregister a device from the IIO subsystem An IIO device usually corresponds to a single hardware sensor and it @@ -34,17 +34,17 @@ A typical IIO driver will register itself as an :doc:`I2C <../i2c>` or At probe: -1. Call :c:func:`iio_device_alloc()`, which allocates memory for an IIO device. +1. Call iio_device_alloc(), which allocates memory for an IIO device. 2. Initialize IIO device fields with driver specific information (e.g. device name, device channels). -3. Call :c:func:`iio_device_register()`, this registers the device with the +3. Call iio_device_register(), this registers the device with the IIO core. After this call the device is ready to accept requests from user space applications. At remove, we free the resources allocated in probe in reverse order: -1. :c:func:`iio_device_unregister()`, unregister the device from the IIO core. -2. :c:func:`iio_device_free()`, free the memory allocated for the IIO device. +1. iio_device_unregister(), unregister the device from the IIO core. +2. iio_device_free(), free the memory allocated for the IIO device. IIO device sysfs interface ========================== diff --git a/Documentation/fault-injection/nvme-fault-injection.rst b/Documentation/fault-injection/nvme-fault-injection.rst index cdb2e829228e..1d4427890d75 100644 --- a/Documentation/fault-injection/nvme-fault-injection.rst +++ b/Documentation/fault-injection/nvme-fault-injection.rst @@ -3,7 +3,7 @@ NVMe Fault Injection Linux's fault injection framework provides a systematic way to support error injection via debugfs in the /sys/kernel/debug directory. When enabled, the default NVME_SC_INVALID_OPCODE with no retry will be -injected into the nvme_end_request. Users can change the default status +injected into the nvme_try_complete_req. Users can change the default status code and no retry flag via the debugfs. The list of Generic Command Status can be found in include/linux/nvme.h diff --git a/Documentation/filesystems/affs.rst b/Documentation/filesystems/affs.rst index 7f1a40dce6d3..5776cbd5fa53 100644 --- a/Documentation/filesystems/affs.rst +++ b/Documentation/filesystems/affs.rst @@ -110,13 +110,15 @@ The Amiga protection flags RWEDRWEDHSPARWED are handled as follows: - R maps to r for user, group and others. On directories, R implies x. - - If both W and D are allowed, w will be set. + - W maps to w. - E maps to x. - - H and P are always retained and ignored under Linux. + - D is ignored. - - A is always reset when a file is written to. + - H, S and P are always retained and ignored under Linux. + + - A is cleared when a file is written to. User id and group id will be used unless set[gu]id are given as mount options. Since most of the Amiga file systems are single user systems @@ -128,11 +130,13 @@ Linux -> Amiga: The Linux rwxrwxrwx file mode is handled as follows: - - r permission will set R for user, group and others. + - r permission will allow R for user, group and others. + + - w permission will allow W for user, group and others. - - w permission will set W and D for user, group and others. + - x permission of the user will allow E for plain files. - - x permission of the user will set E for plain files. + - D will be allowed for user, group and others. - All other flags (suid, sgid, ...) are ignored and will not be retained. diff --git a/Documentation/filesystems/ext4/about.rst b/Documentation/filesystems/ext4/about.rst index 0aadba052264..cc76b577d2f4 100644 --- a/Documentation/filesystems/ext4/about.rst +++ b/Documentation/filesystems/ext4/about.rst @@ -39,6 +39,6 @@ entry. Other References ---------------- -Also see http://www.nongnu.org/ext2-doc/ for quite a collection of +Also see https://www.nongnu.org/ext2-doc/ for quite a collection of information about ext2/3. Here's another old reference: http://wiki.osdev.org/Ext2 diff --git a/Documentation/hwmon/abituguru-datasheet.rst b/Documentation/hwmon/abituguru-datasheet.rst index 6d5253e2223b..0cd61471d2a2 100644 --- a/Documentation/hwmon/abituguru-datasheet.rst +++ b/Documentation/hwmon/abituguru-datasheet.rst @@ -68,7 +68,7 @@ See below for all known bank addresses, numbers of sensors in that bank, number of bytes data per sensor and contents/meaning of those bytes. Although both this document and the kernel driver have kept the sensor -terminoligy for the addressing within a bank this is not 100% correct, in +terminology for the addressing within a bank this is not 100% correct, in bank 0x24 for example the addressing within the bank selects a PWM output not a sensor. @@ -155,7 +155,7 @@ After wider testing of the Linux kernel driver some variants of the uGuru have turned up which do not hold 0x08 at DATA within 250 reads after writing the bank address. With these versions this happens quite frequent, using larger timeouts doesn't help, they just go offline for a second or 2, doing some -internal callibration or whatever. Your code should be prepared to handle +internal calibration or whatever. Your code should be prepared to handle this and in case of no response in this specific case just goto sleep for a while and then retry. @@ -331,6 +331,6 @@ the voltage / clock programming out, I tried reading and only reading banks 0-0x30 with the reading code used for the sensor banks (0x20-0x28) and this resulted in a _permanent_ reprogramming of the voltages, luckily I had the sensors part configured so that it would shutdown my system on any out of spec -voltages which proprably safed my computer (after a reboot I managed to +voltages which probably safed my computer (after a reboot I managed to immediately enter the bios and reload the defaults). This probably means that the read/write cycle for the non sensor part is different from the sensor part. diff --git a/Documentation/hwmon/abituguru.rst b/Documentation/hwmon/abituguru.rst index d8243c827de9..cfda60b757ce 100644 --- a/Documentation/hwmon/abituguru.rst +++ b/Documentation/hwmon/abituguru.rst @@ -17,7 +17,7 @@ Supported chips: Note: The uGuru is a microcontroller with onboard firmware which programs it to behave as a hwmon IC. There are many different revisions of the - firmware and thus effectivly many different revisions of the uGuru. + firmware and thus effectively many different revisions of the uGuru. Below is an incomplete list with which revisions are used for which Motherboards: @@ -33,7 +33,7 @@ Supported chips: sensortype (Volt or Temp) for bank1 sensors, for revision 1 uGuru's this does not always work. For these uGuru's the autodetection can be overridden with the bank1_types module param. For all 3 known - revison 1 motherboards the correct use of this param is: + revision 1 motherboards the correct use of this param is: bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1 You may also need to specify the fan_sensors option for these boards fan_sensors=5 diff --git a/Documentation/hwmon/abituguru3.rst b/Documentation/hwmon/abituguru3.rst index 514f11f41e8b..88046d866385 100644 --- a/Documentation/hwmon/abituguru3.rst +++ b/Documentation/hwmon/abituguru3.rst @@ -13,7 +13,7 @@ Supported chips: Note: The uGuru is a microcontroller with onboard firmware which programs it to behave as a hwmon IC. There are many different revisions of the - firmware and thus effectivly many different revisions of the uGuru. + firmware and thus effectively many different revisions of the uGuru. Below is an incomplete list with which revisions are used for which Motherboards: @@ -24,7 +24,7 @@ Supported chips: - uGuru 3.0.0.0 ~ 3.0.x.x (AW8, AL8, AT8, NI8 SLI, AT8 32X, AN8 32X, AW9D-MAX) - The abituguru3 driver is only for revison 3.0.x.x motherboards, + The abituguru3 driver is only for revision 3.0.x.x motherboards, this driver will not work on older motherboards. For older motherboards use the abituguru (without the 3 !) driver. diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index 2aac50b97921..334df758dce3 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -23,8 +23,8 @@ supports C and the GNU C extensions required by the kernel, and is pronounced Clang ----- -The compiler used can be swapped out via `CC=` command line argument to `make`. -`CC=` should be set when selecting a config and during a build. +The compiler used can be swapped out via ``CC=`` command line argument to ``make``. +``CC=`` should be set when selecting a config and during a build. :: make CC=clang defconfig @@ -34,33 +34,33 @@ Cross Compiling --------------- A single Clang compiler binary will typically contain all supported backends, -which can help simplify cross compiling. +which can help simplify cross compiling. :: ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- make CC=clang -`CROSS_COMPILE` is not used to prefix the Clang compiler binary, instead -`CROSS_COMPILE` is used to set a command line flag: `--target <triple>`. For -example: +``CROSS_COMPILE`` is not used to prefix the Clang compiler binary, instead +``CROSS_COMPILE`` is used to set a command line flag: ``--target <triple>``. For +example: :: clang --target aarch64-linux-gnu foo.c LLVM Utilities -------------- -LLVM has substitutes for GNU binutils utilities. Kbuild supports `LLVM=1` -to enable them. +LLVM has substitutes for GNU binutils utilities. Kbuild supports ``LLVM=1`` +to enable them. :: make LLVM=1 -They can be enabled individually. The full list of the parameters: +They can be enabled individually. The full list of the parameters: :: - make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \\ - OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \\ - READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \\ + make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \ + OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \ + READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \ HOSTLD=ld.lld Currently, the integrated assembler is disabled by default. You can pass -`LLVM_IAS=1` to enable it. +``LLVM_IAS=1`` to enable it. Getting Help ------------ diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index b81b8913a5a3..58d513a0fa95 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -16,7 +16,7 @@ This document describes the Linux kernel Makefiles. --- 3.5 Library file goals - lib-y --- 3.6 Descending down in directories --- 3.7 Compilation flags - --- 3.8 Command line dependency + --- 3.8 <deleted> --- 3.9 Dependency tracking --- 3.10 Special Rules --- 3.11 $(CC) support functions @@ -39,8 +39,8 @@ This document describes the Linux kernel Makefiles. === 7 Architecture Makefiles --- 7.1 Set variables to tweak the build to the architecture - --- 7.2 Add prerequisites to archheaders: - --- 7.3 Add prerequisites to archprepare: + --- 7.2 Add prerequisites to archheaders + --- 7.3 Add prerequisites to archprepare --- 7.4 List directories to visit when descending --- 7.5 Architecture-specific boot images --- 7.6 Building non-kbuild targets @@ -129,7 +129,7 @@ The preferred name for the kbuild files are 'Makefile' but 'Kbuild' can be used and if both a 'Makefile' and a 'Kbuild' file exists, then the 'Kbuild' file will be used. -Section 3.1 "Goal definitions" is a quick intro, further chapters provide +Section 3.1 "Goal definitions" is a quick intro; further chapters provide more details, with real examples. 3.1 Goal definitions @@ -965,7 +965,7 @@ When kbuild executes, the following steps are followed (roughly): KBUILD_LDFLAGS := -m elf_s390 Note: ldflags-y can be used to further customise - the flags used. See chapter 3.7. + the flags used. See section 3.7. LDFLAGS_vmlinux Options for $(LD) when linking vmlinux @@ -1121,7 +1121,7 @@ When kbuild executes, the following steps are followed (roughly): In this example, the file target maketools will be processed before descending down in the subdirectories. - See also chapter XXX-TODO that describe how kbuild supports + See also chapter XXX-TODO that describes how kbuild supports generating offset header files. @@ -1261,7 +1261,7 @@ When kbuild executes, the following steps are followed (roughly): always be built. Assignments to $(targets) are without $(obj)/ prefix. if_changed may be used in conjunction with custom commands as - defined in 6.8 "Custom kbuild commands". + defined in 7.8 "Custom kbuild commands". Note: It is a typical mistake to forget the FORCE prerequisite. Another common pitfall is that whitespace is sometimes @@ -1411,7 +1411,7 @@ When kbuild executes, the following steps are followed (roughly): that may be shared between individual architectures. The recommended approach how to use a generic header file is to list the file in the Kbuild file. - See "7.2 generic-y" for further info on syntax etc. + See "8.2 generic-y" for further info on syntax etc. 7.11 Post-link pass ------------------- @@ -1601,4 +1601,4 @@ is the right choice. - Describe how kbuild supports shipped files with _shipped. - Generating offset header files. -- Add more variables to section 7? +- Add more variables to chapters 7 or 9? diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst index 4cefed8048ca..ddada4a53749 100644 --- a/Documentation/locking/locktypes.rst +++ b/Documentation/locking/locktypes.rst @@ -164,14 +164,14 @@ by disabling preemption or interrupts. On non-PREEMPT_RT kernels local_lock operations map to the preemption and interrupt disabling and enabling primitives: - =========================== ====================== - local_lock(&llock) preempt_disable() - local_unlock(&llock) preempt_enable() - local_lock_irq(&llock) local_irq_disable() - local_unlock_irq(&llock) local_irq_enable() - local_lock_save(&llock) local_irq_save() - local_lock_restore(&llock) local_irq_save() - =========================== ====================== + =============================== ====================== + local_lock(&llock) preempt_disable() + local_unlock(&llock) preempt_enable() + local_lock_irq(&llock) local_irq_disable() + local_unlock_irq(&llock) local_irq_enable() + local_lock_irqsave(&llock) local_irq_save() + local_unlock_irqrestore(&llock) local_irq_restore() + =============================== ====================== The named scope of local_lock has two advantages over the regular primitives: @@ -353,14 +353,14 @@ protection scope. So the following substitution is wrong:: { local_irq_save(flags); -> local_lock_irqsave(&local_lock_1, flags); func3(); - local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_1, flags); + local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock_1, flags); } func2() { local_irq_save(flags); -> local_lock_irqsave(&local_lock_2, flags); func3(); - local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_2, flags); + local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock_2, flags); } func3() @@ -379,14 +379,14 @@ PREEMPT_RT-specific semantics of spinlock_t. The correct substitution is:: { local_irq_save(flags); -> local_lock_irqsave(&local_lock, flags); func3(); - local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags); + local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock, flags); } func2() { local_irq_save(flags); -> local_lock_irqsave(&local_lock, flags); func3(); - local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags); + local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock, flags); } func3() diff --git a/Documentation/maintainer/maintainer-entry-profile.rst b/Documentation/maintainer/maintainer-entry-profile.rst index 227f427118e8..b7a627d6c97d 100644 --- a/Documentation/maintainer/maintainer-entry-profile.rst +++ b/Documentation/maintainer/maintainer-entry-profile.rst @@ -101,3 +101,4 @@ to do something different in the near future. ../doc-guide/maintainer-profile ../nvdimm/maintainer-entry-profile + ../riscv/patch-acceptance diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst index 5bc55a4e3bce..2ccc5644cc98 100644 --- a/Documentation/networking/af_xdp.rst +++ b/Documentation/networking/af_xdp.rst @@ -258,14 +258,21 @@ socket into zero-copy mode or fail. XDP_SHARED_UMEM bind flag ------------------------- -This flag enables you to bind multiple sockets to the same UMEM, but -only if they share the same queue id. In this mode, each socket has -their own RX and TX rings, but the UMEM (tied to the fist socket -created) only has a single FILL ring and a single COMPLETION -ring. To use this mode, create the first socket and bind it in the normal -way. Create a second socket and create an RX and a TX ring, or at -least one of them, but no FILL or COMPLETION rings as the ones from -the first socket will be used. In the bind call, set he +This flag enables you to bind multiple sockets to the same UMEM. It +works on the same queue id, between queue ids and between +netdevs/devices. In this mode, each socket has their own RX and TX +rings as usual, but you are going to have one or more FILL and +COMPLETION ring pairs. You have to create one of these pairs per +unique netdev and queue id tuple that you bind to. + +Starting with the case were we would like to share a UMEM between +sockets bound to the same netdev and queue id. The UMEM (tied to the +fist socket created) will only have a single FILL ring and a single +COMPLETION ring as there is only on unique netdev,queue_id tuple that +we have bound to. To use this mode, create the first socket and bind +it in the normal way. Create a second socket and create an RX and a TX +ring, or at least one of them, but no FILL or COMPLETION rings as the +ones from the first socket will be used. In the bind call, set he XDP_SHARED_UMEM option and provide the initial socket's fd in the sxdp_shared_umem_fd field. You can attach an arbitrary number of extra sockets this way. @@ -305,11 +312,41 @@ concurrently. There are no synchronization primitives in the libbpf code that protects multiple users at this point in time. Libbpf uses this mode if you create more than one socket tied to the -same umem. However, note that you need to supply the +same UMEM. However, note that you need to supply the XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD libbpf_flag with the xsk_socket__create calls and load your own XDP program as there is no built in one in libbpf that will route the traffic for you. +The second case is when you share a UMEM between sockets that are +bound to different queue ids and/or netdevs. In this case you have to +create one FILL ring and one COMPLETION ring for each unique +netdev,queue_id pair. Let us say you want to create two sockets bound +to two different queue ids on the same netdev. Create the first socket +and bind it in the normal way. Create a second socket and create an RX +and a TX ring, or at least one of them, and then one FILL and +COMPLETION ring for this socket. Then in the bind call, set he +XDP_SHARED_UMEM option and provide the initial socket's fd in the +sxdp_shared_umem_fd field as you registered the UMEM on that +socket. These two sockets will now share one and the same UMEM. + +There is no need to supply an XDP program like the one in the previous +case where sockets were bound to the same queue id and +device. Instead, use the NIC's packet steering capabilities to steer +the packets to the right queue. In the previous example, there is only +one queue shared among sockets, so the NIC cannot do this steering. It +can only steer between queues. + +In libbpf, you need to use the xsk_socket__create_shared() API as it +takes a reference to a FILL ring and a COMPLETION ring that will be +created for you and bound to the shared UMEM. You can use this +function for all the sockets you create, or you can use it for the +second and following ones and use xsk_socket__create() for the first +one. Both methods yield the same result. + +Note that a UMEM can be shared between sockets on the same queue id +and device, as well as between queues on the same device and between +devices at the same time. + XDP_USE_NEED_WAKEUP bind flag ----------------------------- @@ -364,7 +401,7 @@ resources by only setting up one of them. Both the FILL ring and the COMPLETION ring are mandatory as you need to have a UMEM tied to your socket. But if the XDP_SHARED_UMEM flag is used, any socket after the first one does not have a UMEM and should in that case not have any -FILL or COMPLETION rings created as the ones from the shared umem will +FILL or COMPLETION rings created as the ones from the shared UMEM will be used. Note, that the rings are single-producer single-consumer, so do not try to access them from multiple processes at the same time. See the XDP_SHARED_UMEM section. @@ -567,6 +604,17 @@ A: The short answer is no, that is not supported at the moment. The switch, or other distribution mechanism, in your NIC to direct traffic to the correct queue id and socket. +Q: My packets are sometimes corrupted. What is wrong? + +A: Care has to be taken not to feed the same buffer in the UMEM into + more than one ring at the same time. If you for example feed the + same buffer into the FILL ring and the TX ring at the same time, the + NIC might receive data into the buffer at the same time it is + sending it. This will cause some packets to become corrupted. Same + thing goes for feeding the same buffer into the FILL rings + belonging to different queue ids or netdevs bound with the + XDP_SHARED_UMEM flag. + Credits ======= diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index 24168b0d16bd..adc314639085 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -2860,17 +2860,6 @@ version of the linux kernel, found on http://kernel.org The latest version of this document can be found in the latest kernel source (named Documentation/networking/bonding.rst). -Discussions regarding the usage of the bonding driver take place on the -bonding-devel mailing list, hosted at sourceforge.net. If you have questions or -problems, post them to the list. The list address is: - -bonding-devel@lists.sourceforge.net - -The administrative interface (to subscribe or unsubscribe) can -be found at: - -https://lists.sourceforge.net/lists/listinfo/bonding-devel - Discussions regarding the development of the bonding driver take place on the main Linux network mailing list, hosted at vger.kernel.org. The list address is: @@ -2881,10 +2870,3 @@ The administrative interface (to subscribe or unsubscribe) can be found at: http://vger.kernel.org/vger-lists.html#netdev - -Donald Becker's Ethernet Drivers and diag programs may be found at : - - - http://web.archive.org/web/%2E/http://www.scyld.com/network/ - -You will also find a lot of information regarding Ethernet, NWay, MII, -etc. at www.scyld.com. diff --git a/Documentation/networking/dsa/configuration.rst b/Documentation/networking/dsa/configuration.rst index af029b3ca2ab..11bd5e6108c0 100644 --- a/Documentation/networking/dsa/configuration.rst +++ b/Documentation/networking/dsa/configuration.rst @@ -180,7 +180,7 @@ The configuration can only be set up via VLAN tagging and bridge setup. # bring up the slave interfaces ip link set lan1 up - ip link set lan1 up + ip link set lan2 up ip link set lan3 up # create bridge diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index c29496fff81c..4167acc5c076 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -93,6 +93,7 @@ Contents: sctp secid seg6-sysctl + statistics strparser switchdev tc-actions-env-rules diff --git a/Documentation/networking/l2tp.rst b/Documentation/networking/l2tp.rst index a48238a2ec09..498b382d25a0 100644 --- a/Documentation/networking/l2tp.rst +++ b/Documentation/networking/l2tp.rst @@ -4,124 +4,364 @@ L2TP ==== -This document describes how to use the kernel's L2TP drivers to -provide L2TP functionality. L2TP is a protocol that tunnels one or -more sessions over an IP tunnel. It is commonly used for VPNs -(L2TP/IPSec) and by ISPs to tunnel subscriber PPP sessions over an IP -network infrastructure. With L2TPv3, it is also useful as a Layer-2 -tunneling infrastructure. - -Features +Layer 2 Tunneling Protocol (L2TP) allows L2 frames to be tunneled over +an IP network. + +This document covers the kernel's L2TP subsystem. It documents kernel +APIs for application developers who want to use the L2TP subsystem and +it provides some technical details about the internal implementation +which may be useful to kernel developers and maintainers. + +Overview ======== -L2TPv2 (PPP over L2TP (UDP tunnels)). -L2TPv3 ethernet pseudowires. -L2TPv3 PPP pseudowires. -L2TPv3 IP encapsulation. -Netlink sockets for L2TPv3 configuration management. - -History -======= - -The original pppol2tp driver was introduced in 2.6.23 and provided -L2TPv2 functionality (rfc2661). L2TPv2 is used to tunnel one or more PPP -sessions over a UDP tunnel. - -L2TPv3 (rfc3931) changes the protocol to allow different frame types -to be passed over an L2TP tunnel by moving the PPP-specific parts of -the protocol out of the core L2TP packet headers. Each frame type is -known as a pseudowire type. Ethernet, PPP, HDLC, Frame Relay and ATM -pseudowires for L2TP are defined in separate RFC standards. Another -change for L2TPv3 is that it can be carried directly over IP with no -UDP header (UDP is optional). It is also possible to create static -unmanaged L2TPv3 tunnels manually without a control protocol -(userspace daemon) to manage them. - -To support L2TPv3, the original pppol2tp driver was split up to -separate the L2TP and PPP functionality. Existing L2TPv2 userspace -apps should be unaffected as the original pppol2tp sockets API is -retained. L2TPv3, however, uses netlink to manage L2TPv3 tunnels and -sessions. - -Design -====== - -The L2TP protocol separates control and data frames. The L2TP kernel -drivers handle only L2TP data frames; control frames are always -handled by userspace. L2TP control frames carry messages between L2TP -clients/servers and are used to setup / teardown tunnels and -sessions. An L2TP client or server is implemented in userspace. - -Each L2TP tunnel is implemented using a UDP or L2TPIP socket; L2TPIP -provides L2TPv3 IP encapsulation (no UDP) and is implemented using a -new l2tpip socket family. The tunnel socket is typically created by -userspace, though for unmanaged L2TPv3 tunnels, the socket can also be -created by the kernel. Each L2TP session (pseudowire) gets a network -interface instance. In the case of PPP, these interfaces are created -indirectly by pppd using a pppol2tp socket. In the case of ethernet, -the netdevice is created upon a netlink request to create an L2TPv3 -ethernet pseudowire. - -For PPP, the PPPoL2TP driver, net/l2tp/l2tp_ppp.c, provides a -mechanism by which PPP frames carried through an L2TP session are -passed through the kernel's PPP subsystem. The standard PPP daemon, -pppd, handles all PPP interaction with the peer. PPP network -interfaces are created for each local PPP endpoint. The kernel's PPP -subsystem arranges for PPP control frames to be delivered to pppd, -while data frames are forwarded as usual. - -For ethernet, the L2TPETH driver, net/l2tp/l2tp_eth.c, implements a -netdevice driver, managing virtual ethernet devices, one per -pseudowire. These interfaces can be managed using standard Linux tools -such as "ip" and "ifconfig". If only IP frames are passed over the -tunnel, the interface can be given an IP addresses of itself and its -peer. If non-IP frames are to be passed over the tunnel, the interface -can be added to a bridge using brctl. All L2TP datapath protocol -functions are handled by the L2TP core driver. - -Each tunnel and session within a tunnel is assigned a unique tunnel_id -and session_id. These ids are carried in the L2TP header of every -control and data packet. (Actually, in L2TPv3, the tunnel_id isn't -present in data frames - it is inferred from the IP connection on -which the packet was received.) The L2TP driver uses the ids to lookup -internal tunnel and/or session contexts to determine how to handle the -packet. Zero tunnel / session ids are treated specially - zero ids are -never assigned to tunnels or sessions in the network. In the driver, -the tunnel context keeps a reference to the tunnel UDP or L2TPIP -socket. The session context holds data that lets the driver interface -to the kernel's network frame type subsystems, i.e. PPP, ethernet. - -Userspace Programming -===================== - -For L2TPv2, there are a number of requirements on the userspace L2TP -daemon in order to use the pppol2tp driver. - -1. Use a UDP socket per tunnel. - -2. Create a single PPPoL2TP socket per tunnel bound to a special null - session id. This is used only for communicating with the driver but - must remain open while the tunnel is active. Opening this tunnel - management socket causes the driver to mark the tunnel socket as an - L2TP UDP encapsulation socket and flags it for use by the - referenced tunnel id. This hooks up the UDP receive path via - udp_encap_rcv() in net/ipv4/udp.c. PPP data frames are never passed - in this special PPPoX socket. - -3. Create a PPPoL2TP socket per L2TP session. This is typically done - by starting pppd with the pppol2tp plugin and appropriate - arguments. A PPPoL2TP tunnel management socket (Step 2) must be - created before the first PPPoL2TP session socket is created. +The kernel's L2TP subsystem implements the datapath for L2TPv2 and +L2TPv3. L2TPv2 is carried over UDP. L2TPv3 is carried over UDP or +directly over IP (protocol 115). + +The L2TP RFCs define two basic kinds of L2TP packets: control packets +(the "control plane"), and data packets (the "data plane"). The kernel +deals only with data packets. The more complex control packets are +handled by user space. + +An L2TP tunnel carries one or more L2TP sessions. Each tunnel is +associated with a socket. Each session is associated with a virtual +netdevice, e.g. ``pppN``, ``l2tpethN``, through which data frames pass +to/from L2TP. Fields in the L2TP header identify the tunnel or session +and whether it is a control or data packet. When tunnels and sessions +are set up using the Linux kernel API, we're just setting up the L2TP +data path. All aspects of the control protocol are to be handled by +user space. + +This split in responsibilities leads to a natural sequence of +operations when establishing tunnels and sessions. The procedure looks +like this: + + 1) Create a tunnel socket. Exchange L2TP control protocol messages + with the peer over that socket in order to establish a tunnel. + + 2) Create a tunnel context in the kernel, using information + obtained from the peer using the control protocol messages. + + 3) Exchange L2TP control protocol messages with the peer over the + tunnel socket in order to establish a session. + + 4) Create a session context in the kernel using information + obtained from the peer using the control protocol messages. + +L2TP APIs +========= + +This section documents each userspace API of the L2TP subsystem. + +Tunnel Sockets +-------------- + +L2TPv2 always uses UDP. L2TPv3 may use UDP or IP encapsulation. + +To create a tunnel socket for use by L2TP, the standard POSIX +socket API is used. + +For example, for a tunnel using IPv4 addresses and UDP encapsulation:: + + int sockfd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP); + +Or for a tunnel using IPv6 addresses and IP encapsulation:: + + int sockfd = socket(AF_INET6, SOCK_DGRAM, IPPROTO_L2TP); + +UDP socket programming doesn't need to be covered here. + +IPPROTO_L2TP is an IP protocol type implemented by the kernel's L2TP +subsystem. The L2TPIP socket address is defined in struct +sockaddr_l2tpip and struct sockaddr_l2tpip6 at +`include/uapi/linux/l2tp.h`_. The address includes the L2TP tunnel +(connection) id. To use L2TP IP encapsulation, an L2TPv3 application +should bind the L2TPIP socket using the locally assigned +tunnel id. When the peer's tunnel id and IP address is known, a +connect must be done. + +If the L2TP application needs to handle L2TPv3 tunnel setup requests +from peers using L2TPIP, it must open a dedicated L2TPIP +socket to listen for those requests and bind the socket using tunnel +id 0 since tunnel setup requests are addressed to tunnel id 0. + +An L2TP tunnel and all of its sessions are automatically closed when +its tunnel socket is closed. + +Netlink API +----------- + +L2TP applications use netlink to manage L2TP tunnel and session +instances in the kernel. The L2TP netlink API is defined in +`include/uapi/linux/l2tp.h`_. + +L2TP uses `Generic Netlink`_ (GENL). Several commands are defined: +Create, Delete, Modify and Get for tunnel and session +instances, e.g. ``L2TP_CMD_TUNNEL_CREATE``. The API header lists the +netlink attribute types that can be used with each command. + +Tunnel and session instances are identified by a locally unique +32-bit id. L2TP tunnel ids are given by ``L2TP_ATTR_CONN_ID`` and +``L2TP_ATTR_PEER_CONN_ID`` attributes and L2TP session ids are given +by ``L2TP_ATTR_SESSION_ID`` and ``L2TP_ATTR_PEER_SESSION_ID`` +attributes. If netlink is used to manage L2TPv2 tunnel and session +instances, the L2TPv2 16-bit tunnel/session id is cast to a 32-bit +value in these attributes. + +In the ``L2TP_CMD_TUNNEL_CREATE`` command, ``L2TP_ATTR_FD`` tells the +kernel the tunnel socket fd being used. If not specified, the kernel +creates a kernel socket for the tunnel, using IP parameters set in +``L2TP_ATTR_IP[6]_SADDR``, ``L2TP_ATTR_IP[6]_DADDR``, +``L2TP_ATTR_UDP_SPORT``, ``L2TP_ATTR_UDP_DPORT`` attributes. Kernel +sockets are used to implement unmanaged L2TPv3 tunnels (iproute2's "ip +l2tp" commands). If ``L2TP_ATTR_FD`` is given, it must be a socket fd +that is already bound and connected. There is more information about +unmanaged tunnels later in this document. + +``L2TP_CMD_TUNNEL_CREATE`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Sets the tunnel (connection) id. +PEER_CONN_ID Y Sets the peer tunnel (connection) id. +PROTO_VERSION Y Protocol version. 2 or 3. +ENCAP_TYPE Y Encapsulation type: UDP or IP. +FD N Tunnel socket file descriptor. +UDP_CSUM N Enable IPv4 UDP checksums. Used only if FD is + not set. +UDP_ZERO_CSUM6_TX N Zero IPv6 UDP checksum on transmit. Used only + if FD is not set. +UDP_ZERO_CSUM6_RX N Zero IPv6 UDP checksum on receive. Used only if + FD is not set. +IP_SADDR N IPv4 source address. Used only if FD is not + set. +IP_DADDR N IPv4 destination address. Used only if FD is + not set. +UDP_SPORT N UDP source port. Used only if FD is not set. +UDP_DPORT N UDP destination port. Used only if FD is not + set. +IP6_SADDR N IPv6 source address. Used only if FD is not + set. +IP6_DADDR N IPv6 destination address. Used only if FD is + not set. +DEBUG N Debug flags. +================== ======== === + +``L2TP_CMD_TUNNEL_DESTROY`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Identifies the tunnel id to be destroyed. +================== ======== === + +``L2TP_CMD_TUNNEL_MODIFY`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Identifies the tunnel id to be modified. +DEBUG N Debug flags. +================== ======== === + +``L2TP_CMD_TUNNEL_GET`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID N Identifies the tunnel id to be queried. + Ignored in DUMP requests. +================== ======== === + +``L2TP_CMD_SESSION_CREATE`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y The parent tunnel id. +SESSION_ID Y Sets the session id. +PEER_SESSION_ID Y Sets the parent session id. +PW_TYPE Y Sets the pseudowire type. +DEBUG N Debug flags. +RECV_SEQ N Enable rx data sequence numbers. +SEND_SEQ N Enable tx data sequence numbers. +LNS_MODE N Enable LNS mode (auto-enable data sequence + numbers). +RECV_TIMEOUT N Timeout to wait when reordering received + packets. +L2SPEC_TYPE N Sets layer2-specific-sublayer type (L2TPv3 + only). +COOKIE N Sets optional cookie (L2TPv3 only). +PEER_COOKIE N Sets optional peer cookie (L2TPv3 only). +IFNAME N Sets interface name (L2TPv3 only). +================== ======== === + +For Ethernet session types, this will create an l2tpeth virtual +interface which can then be configured as required. For PPP session +types, a PPPoL2TP socket must also be opened and connected, mapping it +onto the new session. This is covered in "PPPoL2TP Sockets" later. + +``L2TP_CMD_SESSION_DESTROY`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Identifies the parent tunnel id of the session + to be destroyed. +SESSION_ID Y Identifies the session id to be destroyed. +IFNAME N Identifies the session by interface name. If + set, this overrides any CONN_ID and SESSION_ID + attributes. Currently supported for L2TPv3 + Ethernet sessions only. +================== ======== === + +``L2TP_CMD_SESSION_MODIFY`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Identifies the parent tunnel id of the session + to be modified. +SESSION_ID Y Identifies the session id to be modified. +IFNAME N Identifies the session by interface name. If + set, this overrides any CONN_ID and SESSION_ID + attributes. Currently supported for L2TPv3 + Ethernet sessions only. +DEBUG N Debug flags. +RECV_SEQ N Enable rx data sequence numbers. +SEND_SEQ N Enable tx data sequence numbers. +LNS_MODE N Enable LNS mode (auto-enable data sequence + numbers). +RECV_TIMEOUT N Timeout to wait when reordering received + packets. +================== ======== === + +``L2TP_CMD_SESSION_GET`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID N Identifies the tunnel id to be queried. + Ignored for DUMP requests. +SESSION_ID N Identifies the session id to be queried. + Ignored for DUMP requests. +IFNAME N Identifies the session by interface name. + If set, this overrides any CONN_ID and + SESSION_ID attributes. Ignored for DUMP + requests. Currently supported for L2TPv3 + Ethernet sessions only. +================== ======== === + +Application developers should refer to `include/uapi/linux/l2tp.h`_ for +netlink command and attribute definitions. + +Sample userspace code using libmnl_: + + - Open L2TP netlink socket:: + + struct nl_sock *nl_sock; + int l2tp_nl_family_id; + + nl_sock = nl_socket_alloc(); + genl_connect(nl_sock); + genl_id = genl_ctrl_resolve(nl_sock, L2TP_GENL_NAME); + + - Create a tunnel:: + + struct nlmsghdr *nlh; + struct genlmsghdr *gnlh; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = genl_id; /* assigned to genl socket */ + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + nlh->nlmsg_seq = seq; + + gnlh = mnl_nlmsg_put_extra_header(nlh, sizeof(*gnlh)); + gnlh->cmd = L2TP_CMD_TUNNEL_CREATE; + gnlh->version = L2TP_GENL_VERSION; + gnlh->reserved = 0; + + mnl_attr_put_u32(nlh, L2TP_ATTR_FD, tunl_sock_fd); + mnl_attr_put_u32(nlh, L2TP_ATTR_CONN_ID, tid); + mnl_attr_put_u32(nlh, L2TP_ATTR_PEER_CONN_ID, peer_tid); + mnl_attr_put_u8(nlh, L2TP_ATTR_PROTO_VERSION, protocol_version); + mnl_attr_put_u16(nlh, L2TP_ATTR_ENCAP_TYPE, encap); + + - Create a session:: + + struct nlmsghdr *nlh; + struct genlmsghdr *gnlh; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = genl_id; /* assigned to genl socket */ + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + nlh->nlmsg_seq = seq; + + gnlh = mnl_nlmsg_put_extra_header(nlh, sizeof(*gnlh)); + gnlh->cmd = L2TP_CMD_SESSION_CREATE; + gnlh->version = L2TP_GENL_VERSION; + gnlh->reserved = 0; + + mnl_attr_put_u32(nlh, L2TP_ATTR_CONN_ID, tid); + mnl_attr_put_u32(nlh, L2TP_ATTR_PEER_CONN_ID, peer_tid); + mnl_attr_put_u32(nlh, L2TP_ATTR_SESSION_ID, sid); + mnl_attr_put_u32(nlh, L2TP_ATTR_PEER_SESSION_ID, peer_sid); + mnl_attr_put_u16(nlh, L2TP_ATTR_PW_TYPE, pwtype); + /* there are other session options which can be set using netlink + * attributes during session creation -- see l2tp.h + */ + + - Delete a session:: + + struct nlmsghdr *nlh; + struct genlmsghdr *gnlh; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = genl_id; /* assigned to genl socket */ + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + nlh->nlmsg_seq = seq; + + gnlh = mnl_nlmsg_put_extra_header(nlh, sizeof(*gnlh)); + gnlh->cmd = L2TP_CMD_SESSION_DELETE; + gnlh->version = L2TP_GENL_VERSION; + gnlh->reserved = 0; + + mnl_attr_put_u32(nlh, L2TP_ATTR_CONN_ID, tid); + mnl_attr_put_u32(nlh, L2TP_ATTR_SESSION_ID, sid); + + - Delete a tunnel and all of its sessions (if any):: + + struct nlmsghdr *nlh; + struct genlmsghdr *gnlh; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = genl_id; /* assigned to genl socket */ + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + nlh->nlmsg_seq = seq; + + gnlh = mnl_nlmsg_put_extra_header(nlh, sizeof(*gnlh)); + gnlh->cmd = L2TP_CMD_TUNNEL_DELETE; + gnlh->version = L2TP_GENL_VERSION; + gnlh->reserved = 0; + + mnl_attr_put_u32(nlh, L2TP_ATTR_CONN_ID, tid); + +PPPoL2TP Session Socket API +--------------------------- + +For PPP session types, a PPPoL2TP socket must be opened and connected +to the L2TP session. When creating PPPoL2TP sockets, the application provides information -to the driver about the socket in a socket connect() call. Source and -destination tunnel and session ids are provided, as well as the file -descriptor of a UDP socket. See struct pppol2tp_addr in -include/linux/if_pppol2tp.h. Note that zero tunnel / session ids are -treated specially. When creating the per-tunnel PPPoL2TP management -socket in Step 2 above, zero source and destination session ids are -specified, which tells the driver to prepare the supplied UDP file -descriptor for use as an L2TP tunnel socket. +to the kernel about the tunnel and session in a socket connect() +call. Source and destination tunnel and session ids are provided, as +well as the file descriptor of a UDP or L2TPIP socket. See struct +pppol2tp_addr in `include/linux/if_pppol2tp.h`_. For historical reasons, +there are unfortunately slightly different address structures for +L2TPv2/L2TPv3 IPv4/IPv6 tunnels and userspace must use the appropriate +structure that matches the tunnel socket type. Userspace may control behavior of the tunnel or session using setsockopt and ioctl on the PPPoX socket. The following socket @@ -130,229 +370,308 @@ options are supported:- ========= =========================================================== DEBUG bitmask of debug message categories. See below. SENDSEQ - 0 => don't send packets with sequence numbers - - 1 => send packets with sequence numbers + - 1 => send packets with sequence numbers RECVSEQ - 0 => receive packet sequence numbers are optional - - 1 => drop receive packets without sequence numbers + - 1 => drop receive packets without sequence numbers LNSMODE - 0 => act as LAC. - - 1 => act as LNS. + - 1 => act as LNS. REORDERTO reorder timeout (in millisecs). If 0, don't try to reorder. ========= =========================================================== -Only the DEBUG option is supported by the special tunnel management -PPPoX socket. - In addition to the standard PPP ioctls, a PPPIOCGL2TPSTATS is provided to retrieve tunnel and session statistics from the kernel using the PPPoX socket of the appropriate tunnel or session. -For L2TPv3, userspace must use the netlink API defined in -include/linux/l2tp.h to manage tunnel and session contexts. The -general procedure to create a new L2TP tunnel with one session is:- - -1. Open a GENL socket using L2TP_GENL_NAME for configuring the kernel - using netlink. - -2. Create a UDP or L2TPIP socket for the tunnel. - -3. Create a new L2TP tunnel using a L2TP_CMD_TUNNEL_CREATE - request. Set attributes according to desired tunnel parameters, - referencing the UDP or L2TPIP socket created in the previous step. - -4. Create a new L2TP session in the tunnel using a - L2TP_CMD_SESSION_CREATE request. - -The tunnel and all of its sessions are closed when the tunnel socket -is closed. The netlink API may also be used to delete sessions and -tunnels. Configuration and status info may be set or read using netlink. - -The L2TP driver also supports static (unmanaged) L2TPv3 tunnels. These -are where there is no L2TP control message exchange with the peer to -setup the tunnel; the tunnel is configured manually at each end of the -tunnel. There is no need for an L2TP userspace application in this -case -- the tunnel socket is created by the kernel and configured -using parameters sent in the L2TP_CMD_TUNNEL_CREATE netlink -request. The "ip" utility of iproute2 has commands for managing static -L2TPv3 tunnels; do "ip l2tp help" for more information. +Sample userspace code: + + - Create session PPPoX data socket:: + + struct sockaddr_pppol2tp sax; + int fd; + + /* Note, the tunnel socket must be bound already, else it + * will not be ready + */ + sax.sa_family = AF_PPPOX; + sax.sa_protocol = PX_PROTO_OL2TP; + sax.pppol2tp.fd = tunnel_fd; + sax.pppol2tp.addr.sin_addr.s_addr = addr->sin_addr.s_addr; + sax.pppol2tp.addr.sin_port = addr->sin_port; + sax.pppol2tp.addr.sin_family = AF_INET; + sax.pppol2tp.s_tunnel = tunnel_id; + sax.pppol2tp.s_session = session_id; + sax.pppol2tp.d_tunnel = peer_tunnel_id; + sax.pppol2tp.d_session = peer_session_id; + + /* session_fd is the fd of the session's PPPoL2TP socket. + * tunnel_fd is the fd of the tunnel UDP / L2TPIP socket. + */ + fd = connect(session_fd, (struct sockaddr *)&sax, sizeof(sax)); + if (fd < 0 ) { + return -errno; + } + return 0; + +Old L2TPv2-only API +------------------- + +When L2TP was first added to the Linux kernel in 2.6.23, it +implemented only L2TPv2 and did not include a netlink API. Instead, +tunnel and session instances in the kernel were managed directly using +only PPPoL2TP sockets. The PPPoL2TP socket is used as described in +section "PPPoL2TP Session Socket API" but tunnel and session instances +are automatically created on a connect() of the socket instead of +being created by a separate netlink request: + + - Tunnels are managed using a tunnel management socket which is a + dedicated PPPoL2TP socket, connected to (invalid) session + id 0. The L2TP tunnel instance is created when the PPPoL2TP + tunnel management socket is connected and is destroyed when the + socket is closed. + + - Session instances are created in the kernel when a PPPoL2TP + socket is connected to a non-zero session id. Session parameters + are set using setsockopt. The L2TP session instance is destroyed + when the socket is closed. + +This API is still supported but its use is discouraged. Instead, new +L2TPv2 applications should use netlink to first create the tunnel and +session, then create a PPPoL2TP socket for the session. + +Unmanaged L2TPv3 tunnels +------------------------ + +The kernel L2TP subsystem also supports static (unmanaged) L2TPv3 +tunnels. Unmanaged tunnels have no userspace tunnel socket, and +exchange no control messages with the peer to set up the tunnel; the +tunnel is configured manually at each end of the tunnel. All +configuration is done using netlink. There is no need for an L2TP +userspace application in this case -- the tunnel socket is created by +the kernel and configured using parameters sent in the +``L2TP_CMD_TUNNEL_CREATE`` netlink request. The ``ip`` utility of +``iproute2`` has commands for managing static L2TPv3 tunnels; do ``ip +l2tp help`` for more information. Debugging -========= - -The driver supports a flexible debug scheme where kernel trace -messages may be optionally enabled per tunnel and per session. Care is -needed when debugging a live system since the messages are not -rate-limited and a busy system could be swamped. Userspace uses -setsockopt on the PPPoX socket to set a debug mask. +--------- -The following debug mask bits are available: +The L2TP subsystem offers a range of debugging interfaces through the +debugfs filesystem. -================ ============================== -L2TP_MSG_DEBUG verbose debug (if compiled in) -L2TP_MSG_CONTROL userspace - kernel interface -L2TP_MSG_SEQ sequence numbers handling -L2TP_MSG_DATA data packets -================ ============================== +To access these interfaces, the debugfs filesystem must first be mounted:: -If enabled, files under a l2tp debugfs directory can be used to dump -kernel state about L2TP tunnels and sessions. To access it, the -debugfs filesystem must first be mounted:: + # mount -t debugfs debugfs /debug - # mount -t debugfs debugfs /debug +Files under the l2tp directory can then be accessed, providing a summary +of the current population of tunnel and session contexts existing in the +kernel:: -Files under the l2tp directory can then be accessed:: - - # cat /debug/l2tp/tunnels + # cat /debug/l2tp/tunnels The debugfs files should not be used by applications to obtain L2TP state information because the file format is subject to change. It is implemented to provide extra debug information to help diagnose -problems.) Users should use the netlink API. +problems. Applications should instead use the netlink API. -/proc/net/pppol2tp is also provided for backwards compatibility with -the original pppol2tp driver. It lists information about L2TPv2 -tunnels and sessions only. Its use is discouraged. +In addition the L2TP subsystem implements tracepoints using the standard +kernel event tracing API. The available L2TP events can be reviewed as +follows:: -Unmanaged L2TPv3 Tunnels -======================== - -Some commercial L2TP products support unmanaged L2TPv3 ethernet -tunnels, where there is no L2TP control protocol; tunnels are -configured at each side manually. New commands are available in -iproute2's ip utility to support this. - -To create an L2TPv3 ethernet pseudowire between local host 192.168.1.1 -and peer 192.168.1.2, using IP addresses 10.5.1.1 and 10.5.1.2 for the -tunnel endpoints:: - - # ip l2tp add tunnel tunnel_id 1 peer_tunnel_id 1 udp_sport 5000 \ - udp_dport 5000 encap udp local 192.168.1.1 remote 192.168.1.2 - # ip l2tp add session tunnel_id 1 session_id 1 peer_session_id 1 - # ip -s -d show dev l2tpeth0 - # ip addr add 10.5.1.2/32 peer 10.5.1.1/32 dev l2tpeth0 - # ip li set dev l2tpeth0 up - -Choose IP addresses to be the address of a local IP interface and that -of the remote system. The IP addresses of the l2tpeth0 interface can be -anything suitable. - -Repeat the above at the peer, with ports, tunnel/session ids and IP -addresses reversed. The tunnel and session IDs can be any non-zero -32-bit number, but the values must be reversed at the peer. - -======================== =================== -Host 1 Host2 -======================== =================== -udp_sport=5000 udp_sport=5001 -udp_dport=5001 udp_dport=5000 -tunnel_id=42 tunnel_id=45 -peer_tunnel_id=45 peer_tunnel_id=42 -session_id=128 session_id=5196755 -peer_session_id=5196755 peer_session_id=128 -======================== =================== - -When done at both ends of the tunnel, it should be possible to send -data over the network. e.g.:: - - # ping 10.5.1.1 - - -Sample Userspace Code -===================== - -1. Create tunnel management PPPoX socket:: - - kernel_fd = socket(AF_PPPOX, SOCK_DGRAM, PX_PROTO_OL2TP); - if (kernel_fd >= 0) { - struct sockaddr_pppol2tp sax; - struct sockaddr_in const *peer_addr; - - peer_addr = l2tp_tunnel_get_peer_addr(tunnel); - memset(&sax, 0, sizeof(sax)); - sax.sa_family = AF_PPPOX; - sax.sa_protocol = PX_PROTO_OL2TP; - sax.pppol2tp.fd = udp_fd; /* fd of tunnel UDP socket */ - sax.pppol2tp.addr.sin_addr.s_addr = peer_addr->sin_addr.s_addr; - sax.pppol2tp.addr.sin_port = peer_addr->sin_port; - sax.pppol2tp.addr.sin_family = AF_INET; - sax.pppol2tp.s_tunnel = tunnel_id; - sax.pppol2tp.s_session = 0; /* special case: mgmt socket */ - sax.pppol2tp.d_tunnel = 0; - sax.pppol2tp.d_session = 0; /* special case: mgmt socket */ - - if(connect(kernel_fd, (struct sockaddr *)&sax, sizeof(sax) ) < 0 ) { - perror("connect failed"); - result = -errno; - goto err; - } - } - -2. Create session PPPoX data socket:: - - struct sockaddr_pppol2tp sax; - int fd; - - /* Note, the target socket must be bound already, else it will not be ready */ - sax.sa_family = AF_PPPOX; - sax.sa_protocol = PX_PROTO_OL2TP; - sax.pppol2tp.fd = tunnel_fd; - sax.pppol2tp.addr.sin_addr.s_addr = addr->sin_addr.s_addr; - sax.pppol2tp.addr.sin_port = addr->sin_port; - sax.pppol2tp.addr.sin_family = AF_INET; - sax.pppol2tp.s_tunnel = tunnel_id; - sax.pppol2tp.s_session = session_id; - sax.pppol2tp.d_tunnel = peer_tunnel_id; - sax.pppol2tp.d_session = peer_session_id; - - /* session_fd is the fd of the session's PPPoL2TP socket. - * tunnel_fd is the fd of the tunnel UDP socket. - */ - fd = connect(session_fd, (struct sockaddr *)&sax, sizeof(sax)); - if (fd < 0 ) { - return -errno; - } - return 0; + # find /debug/tracing/events/l2tp + +Finally, /proc/net/pppol2tp is also provided for backwards compatibility +with the original pppol2tp code. It lists information about L2TPv2 +tunnels and sessions only. Its use is discouraged. Internal Implementation ======================= -The driver keeps a struct l2tp_tunnel context per L2TP tunnel and a -struct l2tp_session context for each session. The l2tp_tunnel is -always associated with a UDP or L2TP/IP socket and keeps a list of -sessions in the tunnel. The l2tp_session context keeps kernel state -about the session. It has private data which is used for data specific -to the session type. With L2TPv2, the session always carried PPP -traffic. With L2TPv3, the session can also carry ethernet frames -(ethernet pseudowire) or other data types such as ATM, HDLC or Frame -Relay. - -When a tunnel is first opened, the reference count on the socket is -increased using sock_hold(). This ensures that the kernel socket -cannot be removed while L2TP's data structures reference it. - -Some L2TP sessions also have a socket (PPP pseudowires) while others -do not (ethernet pseudowires). We can't use the socket reference count -as the reference count for session contexts. The L2TP implementation -therefore has its own internal reference counts on the session -contexts. - -To Do -===== - -Add L2TP tunnel switching support. This would route tunneled traffic -from one L2TP tunnel into another. Specified in -http://tools.ietf.org/html/draft-ietf-l2tpext-tunnel-switching-08 - -Add L2TPv3 VLAN pseudowire support. - -Add L2TPv3 IP pseudowire support. - -Add L2TPv3 ATM pseudowire support. +This section is for kernel developers and maintainers. + +Sockets +------- + +UDP sockets are implemented by the networking core. When an L2TP +tunnel is created using a UDP socket, the socket is set up as an +encapsulated UDP socket by setting encap_rcv and encap_destroy +callbacks on the UDP socket. l2tp_udp_encap_recv is called when +packets are received on the socket. l2tp_udp_encap_destroy is called +when userspace closes the socket. + +L2TPIP sockets are implemented in `net/l2tp/l2tp_ip.c`_ and +`net/l2tp/l2tp_ip6.c`_. + +Tunnels +------- + +The kernel keeps a struct l2tp_tunnel context per L2TP tunnel. The +l2tp_tunnel is always associated with a UDP or L2TP/IP socket and +keeps a list of sessions in the tunnel. When a tunnel is first +registered with L2TP core, the reference count on the socket is +increased. This ensures that the socket cannot be removed while L2TP's +data structures reference it. + +Tunnels are identified by a unique tunnel id. The id is 16-bit for +L2TPv2 and 32-bit for L2TPv3. Internally, the id is stored as a 32-bit +value. + +Tunnels are kept in a per-net list, indexed by tunnel id. The tunnel +id namespace is shared by L2TPv2 and L2TPv3. The tunnel context can be +derived from the socket's sk_user_data. + +Handling tunnel socket close is perhaps the most tricky part of the +L2TP implementation. If userspace closes a tunnel socket, the L2TP +tunnel and all of its sessions must be closed and destroyed. Since the +tunnel context holds a ref on the tunnel socket, the socket's +sk_destruct won't be called until the tunnel sock_put's its +socket. For UDP sockets, when userspace closes the tunnel socket, the +socket's encap_destroy handler is invoked, which L2TP uses to initiate +its tunnel close actions. For L2TPIP sockets, the socket's close +handler initiates the same tunnel close actions. All sessions are +first closed. Each session drops its tunnel ref. When the tunnel ref +reaches zero, the tunnel puts its socket ref. When the socket is +eventually destroyed, it's sk_destruct finally frees the L2TP tunnel +context. + +Sessions +-------- + +The kernel keeps a struct l2tp_session context for each session. Each +session has private data which is used for data specific to the +session type. With L2TPv2, the session always carries PPP +traffic. With L2TPv3, the session can carry Ethernet frames (Ethernet +pseudowire) or other data types such as PPP, ATM, HDLC or Frame +Relay. Linux currently implements only Ethernet and PPP session types. + +Some L2TP session types also have a socket (PPP pseudowires) while +others do not (Ethernet pseudowires). We can't therefore use the +socket reference count as the reference count for session +contexts. The L2TP implementation therefore has its own internal +reference counts on the session contexts. + +Like tunnels, L2TP sessions are identified by a unique +session id. Just as with tunnel ids, the session id is 16-bit for +L2TPv2 and 32-bit for L2TPv3. Internally, the id is stored as a 32-bit +value. + +Sessions hold a ref on their parent tunnel to ensure that the tunnel +stays extant while one or more sessions references it. + +Sessions are kept in a per-tunnel list, indexed by session id. L2TPv3 +sessions are also kept in a per-net list indexed by session id, +because L2TPv3 session ids are unique across all tunnels and L2TPv3 +data packets do not contain a tunnel id in the header. This list is +therefore needed to find the session context associated with a +received data packet when the tunnel context cannot be derived from +the tunnel socket. + +Although the L2TPv3 RFC specifies that L2TPv3 session ids are not +scoped by the tunnel, the kernel does not police this for L2TPv3 UDP +tunnels and does not add sessions of L2TPv3 UDP tunnels into the +per-net session list. In the UDP receive code, we must trust that the +tunnel can be identified using the tunnel socket's sk_user_data and +lookup the session in the tunnel's session list instead of the per-net +session list. + +PPP +--- + +`net/l2tp/l2tp_ppp.c`_ implements the PPPoL2TP socket family. Each PPP +session has a PPPoL2TP socket. + +The PPPoL2TP socket's sk_user_data references the l2tp_session. + +Userspace sends and receives PPP packets over L2TP using a PPPoL2TP +socket. Only PPP control frames pass over this socket: PPP data +packets are handled entirely by the kernel, passing between the L2TP +session and its associated ``pppN`` netdev through the PPP channel +interface of the kernel PPP subsystem. + +The L2TP PPP implementation handles the closing of a PPPoL2TP socket +by closing its corresponding L2TP session. This is complicated because +it must consider racing with netlink session create/destroy requests +and pppol2tp_connect trying to reconnect with a session that is in the +process of being closed. Unlike tunnels, PPP sessions do not hold a +ref on their associated socket, so code must be careful to sock_hold +the socket where necessary. For all the details, see commit +3d609342cc04129ff7568e19316ce3d7451a27e8. + +Ethernet +-------- + +`net/l2tp/l2tp_eth.c`_ implements L2TPv3 Ethernet pseudowires. It +manages a netdev for each session. + +L2TP Ethernet sessions are created and destroyed by netlink request, +or are destroyed when the tunnel is destroyed. Unlike PPP sessions, +Ethernet sessions do not have an associated socket. Miscellaneous ============= -The L2TP drivers were developed as part of the OpenL2TP project by -Katalix Systems Ltd. OpenL2TP is a full-featured L2TP client / server, -designed from the ground up to have the L2TP datapath in the -kernel. The project also implemented the pppol2tp plugin for pppd -which allows pppd to use the kernel driver. Details can be found at -http://www.openl2tp.org. +RFCs +---- + +The kernel code implements the datapath features specified in the +following RFCs: + +======= =============== =================================== +RFC2661 L2TPv2 https://tools.ietf.org/html/rfc2661 +RFC3931 L2TPv3 https://tools.ietf.org/html/rfc3931 +RFC4719 L2TPv3 Ethernet https://tools.ietf.org/html/rfc4719 +======= =============== =================================== + +Implementations +--------------- + +A number of open source applications use the L2TP kernel subsystem: + +============ ============================================== +iproute2 https://github.com/shemminger/iproute2 +go-l2tp https://github.com/katalix/go-l2tp +tunneldigger https://github.com/wlanslovenija/tunneldigger +xl2tpd https://github.com/xelerance/xl2tpd +============ ============================================== + +Limitations +----------- + +The current implementation has a number of limitations: + + 1) Multiple UDP sockets with the same 5-tuple address cannot be + used. The kernel's tunnel context is identified using private + data associated with the socket so it is important that each + socket is uniquely identified by its address. + + 2) Interfacing with openvswitch is not yet implemented. It may be + useful to map OVS Ethernet and VLAN ports into L2TPv3 tunnels. + + 3) VLAN pseudowires are implemented using an ``l2tpethN`` interface + configured with a VLAN sub-interface. Since L2TPv3 VLAN + pseudowires carry one and only one VLAN, it may be better to use + a single netdevice rather than an ``l2tpethN`` and ``l2tpethN``:M + pair per VLAN session. The netlink attribute + ``L2TP_ATTR_VLAN_ID`` was added for this, but it was never + implemented. + +Testing +------- + +Unmanaged L2TPv3 Ethernet features are tested by the kernel's built-in +selftests. See `tools/testing/selftests/net/l2tp.sh`_. + +Another test suite, l2tp-ktest_, covers all +of the L2TP APIs and tunnel/session types. This may be integrated into +the kernel's built-in L2TP selftests in the future. + +.. Links +.. _Generic Netlink: generic_netlink.html +.. _libmnl: https://www.netfilter.org/projects/libmnl +.. _include/uapi/linux/l2tp.h: ../../../include/uapi/linux/l2tp.h +.. _include/linux/if_pppol2tp.h: ../../../include/linux/if_pppol2tp.h +.. _net/l2tp/l2tp_ip.c: ../../../net/l2tp/l2tp_ip.c +.. _net/l2tp/l2tp_ip6.c: ../../../net/l2tp/l2tp_ip6.c +.. _net/l2tp/l2tp_ppp.c: ../../../net/l2tp/l2tp_ppp.c +.. _net/l2tp/l2tp_eth.c: ../../../net/l2tp/l2tp_eth.c +.. _tools/testing/selftests/net/l2tp.sh: ../../../tools/testing/selftests/net/l2tp.sh +.. _l2tp-ktest: https://github.com/katalix/l2tp-ktest diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst new file mode 100644 index 000000000000..d490b535cd14 --- /dev/null +++ b/Documentation/networking/statistics.rst @@ -0,0 +1,132 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +Interface statistics +==================== + +This document is a guide to Linux network interface statistics. + +There are two main sources of interface statistics in Linux: + + - standard interface statistics based on + :c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`; and + - driver-defined statistics available via ethtool. + +There are multiple interfaces to reach the former. Most commonly used +is the `ip` command from `iproute2`:: + + $ ip -s -s link show dev ens4u1u1 + 6: ens4u1u1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP mode DEFAULT group default qlen 1000 + link/ether 48:2a:e3:4c:b1:d1 brd ff:ff:ff:ff:ff:ff + RX: bytes packets errors dropped overrun mcast + 74327665117 69016965 0 0 0 0 + RX errors: length crc frame fifo missed + 0 0 0 0 0 + TX: bytes packets errors dropped carrier collsns + 21405556176 44608960 0 0 0 0 + TX errors: aborted fifo window heartbeat transns + 0 0 0 0 128 + altname enp58s0u1u1 + +Note that `-s` has been specified twice to see all members of +:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`. +If `-s` is specified once the detailed errors won't be shown. + +`ip` supports JSON formatting via the `-j` option. + +Ethtool statistics can be dumped using `ethtool -S $ifc`, e.g.:: + + $ ethtool -S ens4u1u1 + NIC statistics: + tx_single_collisions: 0 + tx_multi_collisions: 0 + +uAPIs +===== + +procfs +------ + +The historical `/proc/net/dev` text interface gives access to the list +of interfaces as well as their statistics. + +Note that even though this interface is using +:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>` +internally it combines some of the fields. + +sysfs +----- + +Each device directory in sysfs contains a `statistics` directory (e.g. +`/sys/class/net/lo/statistics/`) with files corresponding to +members of :c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`. + +This simple interface is convenient especially in constrained/embedded +environments without access to tools. However, it's inefficient when +reading multiple stats as it internally performs a full dump of +:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>` +and reports only the stat corresponding to the accessed file. + +Sysfs files are documented in +`Documentation/ABI/testing/sysfs-class-net-statistics`. + + +netlink +------- + +`rtnetlink` (`NETLINK_ROUTE`) is the preferred method of accessing +:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>` stats. + +Statistics are reported both in the responses to link information +requests (`RTM_GETLINK`) and statistic requests (`RTM_GETSTATS`, +when `IFLA_STATS_LINK_64` bit is set in the `.filter_mask` of the request). + +ethtool +------- + +Ethtool IOCTL interface allows drivers to report implementation +specific statistics. Historically it has also been used to report +statistics for which other APIs did not exist, like per-device-queue +statistics, or standard-based statistics (e.g. RFC 2863). + +Statistics and their string identifiers are retrieved separately. +Identifiers via `ETHTOOL_GSTRINGS` with `string_set` set to `ETH_SS_STATS`, +and values via `ETHTOOL_GSTATS`. User space should use `ETHTOOL_GDRVINFO` +to retrieve the number of statistics (`.n_stats`). + +debugfs +------- + +Some drivers expose extra statistics via `debugfs`. + +struct rtnl_link_stats64 +======================== + +.. kernel-doc:: include/uapi/linux/if_link.h + :identifiers: rtnl_link_stats64 + +Notes for driver authors +======================== + +Drivers should report all statistics which have a matching member in +:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>` exclusively +via `.ndo_get_stats64`. Reporting such standard stats via ethtool +or debugfs will not be accepted. + +Drivers must ensure best possible compliance with +:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`. +Please note for example that detailed error statistics must be +added into the general `rx_error` / `tx_error` counters. + +The `.ndo_get_stats64` callback can not sleep because of accesses +via `/proc/net/dev`. If driver may sleep when retrieving the statistics +from the device it should do so periodically asynchronously and only return +a recent copy from `.ndo_get_stats64`. Ethtool interrupt coalescing interface +allows setting the frequency of refreshing statistics, if needed. + +Retrieving ethtool statistics is a multi-syscall process, drivers are advised +to keep the number of statistics constant to avoid race conditions with +user space trying to read them. + +Statistics must persist across routine operations like bringing the interface +down and up. diff --git a/Documentation/powerpc/syscall64-abi.rst b/Documentation/powerpc/syscall64-abi.rst index 46caaadbb029..379817ca64d2 100644 --- a/Documentation/powerpc/syscall64-abi.rst +++ b/Documentation/powerpc/syscall64-abi.rst @@ -49,16 +49,18 @@ Register preservation rules Register preservation rules match the ELF ABI calling sequence with the following differences: -=========== ============= ======================================== --- For the sc instruction, differences with the ELF ABI --- +=========== ============= ======================================== r0 Volatile (System call number.) r3 Volatile (Parameter 1, and return value.) r4-r8 Volatile (Parameters 2-6.) cr0 Volatile (cr0.SO is the return error condition.) cr1, cr5-7 Nonvolatile lr Nonvolatile +=========== ============= ======================================== --- For the scv 0 instruction, differences with the ELF ABI --- +=========== ============= ======================================== r0 Volatile (System call number.) r3 Volatile (Parameter 1, and return value.) r4-r8 Volatile (Parameters 2-6.) diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst index 4a9aa4f0681e..918e32d76fc4 100644 --- a/Documentation/process/deprecated.rst +++ b/Documentation/process/deprecated.rst @@ -142,7 +142,7 @@ only NUL-terminated strings. The safe replacement is strscpy(). (Users of strscpy() still needing NUL-padding should instead use strscpy_pad().) -If a caller is using non-NUL-terminated strings, strncpy()() can +If a caller is using non-NUL-terminated strings, strncpy() can still be used, but destinations should be marked with the `__nonstring <https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_ attribute to avoid future compiler warnings. diff --git a/Documentation/sound/cards/audigy-mixer.rst b/Documentation/sound/cards/audigy-mixer.rst index 998f76e19cdd..f3f4640ee2af 100644 --- a/Documentation/sound/cards/audigy-mixer.rst +++ b/Documentation/sound/cards/audigy-mixer.rst @@ -332,7 +332,7 @@ WO 9901953 (A1) US Patents (https://www.uspto.gov/) ----------------------------------- +----------------------------------- US 5925841 Digital Sampling Instrument employing cache memory (Jul. 20, 1999) diff --git a/Documentation/sound/cards/sb-live-mixer.rst b/Documentation/sound/cards/sb-live-mixer.rst index eccb0f0ffd0f..2ce41d3822d8 100644 --- a/Documentation/sound/cards/sb-live-mixer.rst +++ b/Documentation/sound/cards/sb-live-mixer.rst @@ -337,7 +337,7 @@ WO 9901953 (A1) US Patents (https://www.uspto.gov/) ----------------------------------- +----------------------------------- US 5925841 Digital Sampling Instrument employing cache memory (Jul. 20, 1999) diff --git a/Documentation/sound/designs/timestamping.rst b/Documentation/sound/designs/timestamping.rst index 2b0fff503415..7c7ecf5dbc4b 100644 --- a/Documentation/sound/designs/timestamping.rst +++ b/Documentation/sound/designs/timestamping.rst @@ -143,7 +143,7 @@ timestamp shows when the information is put together by the driver before returning from the ``STATUS`` and ``STATUS_EXT`` ioctl. in most cases this driver_timestamp will be identical to the regular system tstamp. -Examples of typestamping with HDaudio: +Examples of timestamping with HDAudio: 1. DMA timestamp, no compensation for DMA+analog delay :: diff --git a/Documentation/translations/it_IT/process/deprecated.rst b/Documentation/translations/it_IT/process/deprecated.rst index e108eaf82cf6..a642ff3fdc8b 100644 --- a/Documentation/translations/it_IT/process/deprecated.rst +++ b/Documentation/translations/it_IT/process/deprecated.rst @@ -130,7 +130,7 @@ chi usa solo stringe terminate. La versione sicura da usare è strscpy(). (chi usa strscpy() e necessita di estendere la terminazione con NUL deve aggiungere una chiamata a memset()) -Se il chiamate no usa stringhe terminate con NUL, allore strncpy()() +Se il chiamate no usa stringhe terminate con NUL, allore strncpy() può continuare ad essere usata, ma i buffer di destinazione devono essere marchiati con l'attributo `__nonstring <https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_ per evitare avvisi durante la compilazione. diff --git a/MAINTAINERS b/MAINTAINERS index deaafb617361..c99577961cc4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1286,7 +1286,7 @@ S: Supported F: Documentation/devicetree/bindings/net/apm-xgene-enet.txt F: Documentation/devicetree/bindings/net/apm-xgene-mdio.txt F: drivers/net/ethernet/apm/xgene/ -F: drivers/net/phy/mdio-xgene.c +F: drivers/net/mdio/mdio-xgene.c APPLIED MICRO (APM) X-GENE SOC PMU M: Khuong Dinh <khuong@os.amperecomputing.com> @@ -3205,6 +3205,7 @@ S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git F: block/ F: drivers/block/ +F: include/linux/blk* F: kernel/trace/blktrace.c F: lib/sbitmap.c @@ -3388,6 +3389,7 @@ M: Florian Fainelli <f.fainelli@gmail.com> L: netdev@vger.kernel.org L: openwrt-devel@lists.openwrt.org (subscribers-only) S: Supported +F: Documentation/devicetree/bindings/net/dsa/b53.txt F: drivers/net/dsa/b53/* F: include/linux/platform_data/b53.h @@ -3573,13 +3575,28 @@ L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/phy/broadcom/phy-brcm-usb* +BROADCOM ETHERNET PHY DRIVERS +M: Florian Fainelli <f.fainelli@gmail.com> +L: bcm-kernel-feedback-list@broadcom.com +L: netdev@vger.kernel.org +S: Supported +F: Documentation/devicetree/bindings/net/broadcom-bcm87xx.txt +F: drivers/net/phy/bcm*.[ch] +F: drivers/net/phy/broadcom.c +F: include/linux/brcmphy.h + BROADCOM GENET ETHERNET DRIVER M: Doug Berger <opendmb@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> L: bcm-kernel-feedback-list@broadcom.com L: netdev@vger.kernel.org S: Supported +F: Documentation/devicetree/bindings/net/brcm,bcmgenet.txt +F: Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt F: drivers/net/ethernet/broadcom/genet/ +F: drivers/net/mdio/mdio-bcm-unimac.c +F: include/linux/platform_data/bcmgenet.h +F: include/linux/platform_data/mdio-bcm-unimac.h BROADCOM IPROC ARM ARCHITECTURE M: Ray Jui <rjui@broadcom.com> @@ -4692,6 +4709,15 @@ S: Supported W: http://www.chelsio.com F: drivers/crypto/chelsio +CXGB4 INLINE CRYPTO DRIVER +M: Ayush Sawal <ayush.sawal@chelsio.com> +M: Vinay Kumar Yadav <vinay.yadav@chelsio.com> +M: Rohit Maheshwari <rohitm@chelsio.com> +L: netdev@vger.kernel.org +S: Supported +W: http://www.chelsio.com +F: drivers/net/ethernet/chelsio/inline_crypto/ + CXGB4 ETHERNET DRIVER (CXGB4) M: Vishal Kulkarni <vishal@chelsio.com> L: netdev@vger.kernel.org @@ -5050,7 +5076,7 @@ F: include/linux/dm-*.h F: include/uapi/linux/dm-*.h DEVLINK -M: Jiri Pirko <jiri@mellanox.com> +M: Jiri Pirko <jiri@nvidia.com> L: netdev@vger.kernel.org S: Supported F: Documentation/networking/devlink @@ -5239,6 +5265,7 @@ DOCUMENTATION M: Jonathan Corbet <corbet@lwn.net> L: linux-doc@vger.kernel.org S: Maintained +P: Documentation/doc-guide/maintainer-profile.rst T: git git://git.lwn.net/linux.git docs-next F: Documentation/ F: scripts/documentation-file-ref-check @@ -6081,7 +6108,7 @@ F: include/linux/dynamic_debug.h F: lib/dynamic_debug.c DYNAMIC INTERRUPT MODERATION -M: Tal Gilboa <talgi@mellanox.com> +M: Tal Gilboa <talgi@nvidia.com> S: Maintained F: Documentation/networking/net_dim.rst F: include/linux/dim.h @@ -6161,7 +6188,7 @@ F: Documentation/devicetree/bindings/edac/aspeed-sdram-edac.txt F: drivers/edac/aspeed_edac.c EDAC-BLUEFIELD -M: Shravan Kumar Ramani <sramani@mellanox.com> +M: Shravan Kumar Ramani <sramani@nvidia.com> S: Supported F: drivers/edac/bluefield_edac.c @@ -6483,8 +6510,8 @@ S: Odd Fixes F: drivers/net/ethernet/agere/ ETHERNET BRIDGE -M: Roopa Prabhu <roopa@cumulusnetworks.com> -M: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> +M: Roopa Prabhu <roopa@nvidia.com> +M: Nikolay Aleksandrov <nikolay@nvidia.com> L: bridge@lists.linux-foundation.org (moderated for non-subscribers) L: netdev@vger.kernel.org S: Maintained @@ -6494,7 +6521,6 @@ F: net/bridge/ ETHERNET PHY LIBRARY M: Andrew Lunn <andrew@lunn.ch> -M: Florian Fainelli <f.fainelli@gmail.com> M: Heiner Kallweit <hkallweit1@gmail.com> R: Russell King <linux@armlinux.org.uk> L: netdev@vger.kernel.org @@ -6504,11 +6530,14 @@ F: Documentation/devicetree/bindings/net/ethernet-phy.yaml F: Documentation/devicetree/bindings/net/mdio* F: Documentation/devicetree/bindings/net/qca,ar803x.yaml F: Documentation/networking/phy.rst +F: drivers/net/mdio/ +F: drivers/net/pcs/ F: drivers/net/phy/ F: drivers/of/of_mdio.c F: drivers/of/of_net.c F: include/dt-bindings/net/qca-ar803x.h F: include/linux/*mdio*.h +F: include/linux/mdio/*.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h @@ -6599,7 +6628,7 @@ F: drivers/iommu/exynos-iommu.c EZchip NPS platform support M: Vineet Gupta <vgupta@synopsys.com> -M: Ofer Levi <oferle@mellanox.com> +M: Ofer Levi <oferle@nvidia.com> S: Supported F: arch/arc/boot/dts/eznps.dts F: arch/arc/plat-eznps @@ -8563,7 +8592,7 @@ F: drivers/iio/pressure/dps310.c INFINIBAND SUBSYSTEM M: Doug Ledford <dledford@redhat.com> -M: Jason Gunthorpe <jgg@mellanox.com> +M: Jason Gunthorpe <jgg@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/linux-rdma/rdma-core @@ -9226,7 +9255,7 @@ F: drivers/firmware/iscsi_ibft* ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR M: Sagi Grimberg <sagi@grimberg.me> -M: Max Gurtovoy <maxg@mellanox.com> +M: Max Gurtovoy <maxg@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: http://www.openfabrics.org @@ -10281,6 +10310,13 @@ S: Maintained W: http://linux-test-project.github.io/ T: git git://github.com/linux-test-project/ltp.git +LYNX PCS MODULE +M: Ioana Ciornei <ioana.ciornei@nxp.com> +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/pcs/pcs-lynx.c +F: include/linux/pcs-lynx.h + M68K ARCHITECTURE M: Geert Uytterhoeven <geert@linux-m68k.org> L: linux-m68k@lists.linux-m68k.org @@ -10488,7 +10524,7 @@ M: Tobias Waldekranz <tobias@waldekranz.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/marvell,mvusb.yaml -F: drivers/net/phy/mdio-mvusb.c +F: drivers/net/mdio/mdio-mvusb.c MARVELL XENON MMC/SD/SDIO HOST CONTROLLER DRIVER M: Hu Ziji <huziji@marvell.com> @@ -11072,7 +11108,7 @@ F: Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt F: drivers/input/touchscreen/melfas_mip4.c MELLANOX ETHERNET DRIVER (mlx4_en) -M: Tariq Toukan <tariqt@mellanox.com> +M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11080,7 +11116,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* MELLANOX ETHERNET DRIVER (mlx5e) -M: Saeed Mahameed <saeedm@mellanox.com> +M: Saeed Mahameed <saeedm@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11088,7 +11124,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* MELLANOX ETHERNET INNOVA DRIVERS -R: Boris Pismenny <borisp@mellanox.com> +R: Boris Pismenny <borisp@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11099,8 +11135,8 @@ F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* F: include/linux/mlx5/mlx5_ifc_fpga.h MELLANOX ETHERNET SWITCH DRIVERS -M: Jiri Pirko <jiri@mellanox.com> -M: Ido Schimmel <idosch@mellanox.com> +M: Jiri Pirko <jiri@nvidia.com> +M: Ido Schimmel <idosch@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11109,7 +11145,7 @@ F: drivers/net/ethernet/mellanox/mlxsw/ F: tools/testing/selftests/drivers/net/mlxsw/ MELLANOX FIRMWARE FLASH LIBRARY (mlxfw) -M: mlxsw@mellanox.com +M: mlxsw@nvidia.com L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11119,7 +11155,7 @@ F: drivers/net/ethernet/mellanox/mlxfw/ MELLANOX HARDWARE PLATFORM SUPPORT M: Andy Shevchenko <andy@infradead.org> M: Darren Hart <dvhart@infradead.org> -M: Vadim Pasternak <vadimp@mellanox.com> +M: Vadim Pasternak <vadimp@nvidia.com> L: platform-driver-x86@vger.kernel.org S: Supported F: Documentation/ABI/testing/sysfs-platform-mellanox-bootctl @@ -11127,7 +11163,7 @@ F: drivers/platform/mellanox/ F: include/linux/platform_data/mlxreg.h MELLANOX MLX4 core VPI driver -M: Tariq Toukan <tariqt@mellanox.com> +M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported @@ -11137,7 +11173,7 @@ F: drivers/net/ethernet/mellanox/mlx4/ F: include/linux/mlx4/ MELLANOX MLX4 IB driver -M: Yishai Hadas <yishaih@mellanox.com> +M: Yishai Hadas <yishaih@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11147,8 +11183,8 @@ F: include/linux/mlx4/ F: include/uapi/rdma/mlx4-abi.h MELLANOX MLX5 core VPI driver -M: Saeed Mahameed <saeedm@mellanox.com> -M: Leon Romanovsky <leonro@mellanox.com> +M: Saeed Mahameed <saeedm@nvidia.com> +M: Leon Romanovsky <leonro@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported @@ -11159,7 +11195,7 @@ F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ MELLANOX MLX5 IB driver -M: Leon Romanovsky <leonro@mellanox.com> +M: Leon Romanovsky <leonro@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11169,8 +11205,8 @@ F: include/linux/mlx5/ F: include/uapi/rdma/mlx5-abi.h MELLANOX MLXCPLD I2C AND MUX DRIVER -M: Vadim Pasternak <vadimp@mellanox.com> -M: Michael Shych <michaelsh@mellanox.com> +M: Vadim Pasternak <vadimp@nvidia.com> +M: Michael Shych <michaelsh@nvidia.com> L: linux-i2c@vger.kernel.org S: Supported F: Documentation/i2c/busses/i2c-mlxcpld.rst @@ -11178,7 +11214,7 @@ F: drivers/i2c/busses/i2c-mlxcpld.c F: drivers/i2c/muxes/i2c-mux-mlxcpld.c MELLANOX MLXCPLD LED DRIVER -M: Vadim Pasternak <vadimp@mellanox.com> +M: Vadim Pasternak <vadimp@nvidia.com> L: linux-leds@vger.kernel.org S: Supported F: Documentation/leds/leds-mlxcpld.rst @@ -11186,7 +11222,7 @@ F: drivers/leds/leds-mlxcpld.c F: drivers/leds/leds-mlxreg.c MELLANOX PLATFORM DRIVER -M: Vadim Pasternak <vadimp@mellanox.com> +M: Vadim Pasternak <vadimp@nvidia.com> L: platform-driver-x86@vger.kernel.org S: Supported F: drivers/platform/x86/mlx-platform.c @@ -12167,8 +12203,8 @@ F: net/ipv6/syncookies.c F: net/ipv6/tcp*.c NETWORKING [TLS] -M: Boris Pismenny <borisp@mellanox.com> -M: Aviad Yehezkel <aviadye@mellanox.com> +M: Boris Pismenny <borisp@nvidia.com> +M: Aviad Yehezkel <aviadye@nvidia.com> M: John Fastabend <john.fastabend@gmail.com> M: Daniel Borkmann <daniel@iogearbox.net> M: Jakub Kicinski <kuba@kernel.org> @@ -12468,7 +12504,7 @@ S: Supported F: drivers/nfc/nxp-nci OBJAGG -M: Jiri Pirko <jiri@mellanox.com> +M: Jiri Pirko <jiri@nvidia.com> L: netdev@vger.kernel.org S: Supported F: include/linux/objagg.h @@ -13110,7 +13146,7 @@ F: drivers/video/logo/logo_parisc* F: include/linux/hp_sdc.h PARMAN -M: Jiri Pirko <jiri@mellanox.com> +M: Jiri Pirko <jiri@nvidia.com> L: netdev@vger.kernel.org S: Supported F: include/linux/parman.h @@ -13569,12 +13605,18 @@ F: kernel/events/* F: tools/lib/perf/ F: tools/perf/ -PERFORMANCE EVENTS SUBSYSTEM ARM64 PMU EVENTS +PERFORMANCE EVENTS TOOLING ARM64 R: John Garry <john.garry@huawei.com> R: Will Deacon <will@kernel.org> +R: Mathieu Poirier <mathieu.poirier@linaro.org> +R: Leo Yan <leo.yan@linaro.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported +F: tools/build/feature/test-libopencsd.c +F: tools/perf/arch/arm*/ F: tools/perf/pmu-events/arch/arm64/ +F: tools/perf/util/arm-spe* +F: tools/perf/util/cs-etm* PERSONALITY HANDLING M: Christoph Hellwig <hch@infradead.org> @@ -15250,10 +15292,11 @@ F: drivers/media/platform/s3c-camif/ F: include/media/drv-intf/s3c_camif.h SAMSUNG S3FWRN5 NFC DRIVER -M: Robert Baldyga <r.baldyga@samsung.com> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Krzysztof Opasiak <k.opasiak@samsung.com> L: linux-nfc@lists.01.org (moderated for non-subscribers) -S: Supported +S: Maintained +F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml F: drivers/nfc/s3fwrn5 SAMSUNG S5C73M3 CAMERA DRIVER @@ -15637,6 +15680,7 @@ L: netdev@vger.kernel.org S: Maintained F: drivers/net/phy/phylink.c F: drivers/net/phy/sfp* +F: include/linux/mdio/mdio-i2c.h F: include/linux/phylink.h F: include/linux/sfp.h K: phylink\.h|struct\s+phylink|\.phylink|>phylink_|phylink_(autoneg|clear|connect|create|destroy|disconnect|ethtool|helper|mac|mii|of|set|start|stop|test|validate) @@ -16034,7 +16078,7 @@ F: drivers/infiniband/sw/siw/ F: include/uapi/rdma/siw-abi.h SOFT-ROCE DRIVER (rxe) -M: Zhu Yanjun <yanjunz@mellanox.com> +M: Zhu Yanjun <yanjunz@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/sw/rxe/ @@ -16721,8 +16765,8 @@ SYNOPSYS DESIGNWARE ETHERNET XPCS DRIVER M: Jose Abreu <Jose.Abreu@synopsys.com> L: netdev@vger.kernel.org S: Supported -F: drivers/net/phy/mdio-xpcs.c -F: include/linux/mdio-xpcs.h +F: drivers/net/pcs/pcs-xpcs.c +F: include/linux/pcs/pcs-xpcs.h SYNOPSYS DESIGNWARE I2C DRIVER M: Jarkko Nikula <jarkko.nikula@linux.intel.com> @@ -17116,8 +17160,8 @@ S: Maintained F: Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml F: Documentation/devicetree/bindings/arm/keystone/ti,sci.txt F: Documentation/devicetree/bindings/clock/ti,sci-clk.txt -F: Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt -F: Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt +F: Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml +F: Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml F: Documentation/devicetree/bindings/reset/ti,sci-reset.txt F: Documentation/devicetree/bindings/soc/ti/sci-pm-domain.txt F: drivers/clk/keystone/sci-clk.c @@ -18874,6 +18918,15 @@ S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core F: arch/x86/platform +X86 PLATFORM UV HPE SUPERDOME FLEX +M: Steve Wahl <steve.wahl@hpe.com> +R: Dimitri Sivanich <dimitri.sivanich@hpe.com> +R: Russ Anderson <russ.anderson@hpe.com> +S: Supported +F: arch/x86/include/asm/uv/ +F: arch/x86/kernel/apic/x2apic_uv_x.c +F: arch/x86/platform/uv/ + X86 VDSO M: Andy Lutomirski <luto@kernel.org> L: linux-kernel@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc3 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -265,8 +265,7 @@ no-dot-config-targets := $(clean-targets) \ $(version_h) headers headers_% archheaders archscripts \ %asm-generic kernelversion %src-pkg dt_binding_check \ outputmakefile -no-sync-config-targets := $(no-dot-config-targets) install %install \ - kernelrelease +no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/ config-build := @@ -292,7 +291,7 @@ ifneq ($(KBUILD_EXTMOD),) endif ifeq ($(KBUILD_EXTMOD),) - ifneq ($(filter config %config,$(MAKECMDGOALS)),) + ifneq ($(filter %config,$(MAKECMDGOALS)),) config-build := 1 ifneq ($(words $(MAKECMDGOALS)),1) mixed-build := 1 diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c index ac110ae8f978..5b60c248de9e 100644 --- a/arch/alpha/kernel/module.c +++ b/arch/alpha/kernel/module.c @@ -212,7 +212,7 @@ apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, STO_ALPHA_STD_GPLOAD) /* Omit the prologue. */ value += 8; - /* FALLTHRU */ + fallthrough; case R_ALPHA_BRADDR: value -= (u64)location + 4; if (value & 3) diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index a813020d2f11..15bc9d1e79f4 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -453,7 +453,7 @@ syscall_restart(unsigned long r0, unsigned long r19, regs->r0 = EINTR; break; } - /* fallthrough */ + fallthrough; case ERESTARTNOINTR: regs->r0 = r0; /* reset v0 and a3 and replay syscall */ regs->r19 = r19; diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 49754e07e04f..921d4b6e4d95 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -883,7 +883,7 @@ do_entUnaUser(void __user * va, unsigned long opcode, case 0x26: /* sts */ fake_reg = s_reg_to_mem(alpha_read_fp_reg(reg)); - /* FALLTHRU */ + fallthrough; case 0x2c: /* stl */ __asm__ __volatile__( @@ -911,7 +911,7 @@ do_entUnaUser(void __user * va, unsigned long opcode, case 0x27: /* stt */ fake_reg = alpha_read_fp_reg(reg); - /* FALLTHRU */ + fallthrough; case 0x2d: /* stq */ __asm__ __volatile__( diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c index d04837d91b40..03f8b1be0c3a 100644 --- a/arch/arc/kernel/disasm.c +++ b/arch/arc/kernel/disasm.c @@ -339,7 +339,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state, case op_LDWX_S: /* LDWX_S c, [b, u6] */ state->x = 1; - /* intentional fall-through */ + fallthrough; case op_LDW_S: /* LDW_S c, [b, u6] */ state->zz = 2; diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 3d57ed0d8535..8222f8c54690 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -321,7 +321,7 @@ static void arc_restart_syscall(struct k_sigaction *ka, struct pt_regs *regs) regs->r0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: /* diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index f87758a6851b..74ad4256022e 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -572,7 +572,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end, #else BUILD_BUG_ON(sizeof(u32) != sizeof(value)); #endif - /* Fall through */ + fallthrough; case DW_EH_PE_native: if (end < (const void *)(ptr.pul + 1)) return 0; @@ -827,7 +827,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc, case DW_CFA_def_cfa: state->cfa.reg = get_uleb128(&ptr.p8, end); unw_debug("cfa_def_cfa: r%lu ", state->cfa.reg); - /* fall through */ + fallthrough; case DW_CFA_def_cfa_offset: state->cfa.offs = get_uleb128(&ptr.p8, end); unw_debug("cfa_def_cfa_offset: 0x%lx ", @@ -835,7 +835,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc, break; case DW_CFA_def_cfa_sf: state->cfa.reg = get_uleb128(&ptr.p8, end); - /* fall through */ + fallthrough; case DW_CFA_def_cfa_offset_sf: state->cfa.offs = get_sleb128(&ptr.p8, end) * state->dataAlign; diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 7fff88e61252..7a4853b1213a 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -547,7 +547,7 @@ static int arch_build_bp_info(struct perf_event *bp, if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE) && max_watchpoint_len >= 8) break; - /* Else, fall through */ + fallthrough; default: return -EINVAL; } @@ -612,12 +612,12 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, /* Allow halfword watchpoints and breakpoints. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; - /* Else, fall through */ + fallthrough; case 3: /* Allow single byte watchpoint. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; - /* Else, fall through */ + fallthrough; default: ret = -EINVAL; goto out; @@ -884,7 +884,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, break; case ARM_ENTRY_ASYNC_WATCHPOINT: WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n"); - /* Fall through */ + fallthrough; case ARM_ENTRY_SYNC_WATCHPOINT: watchpoint_handler(addr, fsr, regs); break; @@ -933,7 +933,7 @@ static bool core_has_os_save_restore(void) ARM_DBG_READ(c1, c1, 4, oslsr); if (oslsr & ARM_OSLSR_OSLM0) return true; - /* Else, fall through */ + fallthrough; default: return false; } diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index c9dc912b83f0..c1892f733f20 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -596,7 +596,7 @@ static int do_signal(struct pt_regs *regs, int syscall) switch (retval) { case -ERESTART_RESTARTBLOCK: restart -= 2; - /* Fall through */ + fallthrough; case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: diff --git a/arch/arm/mach-ep93xx/crunch.c b/arch/arm/mach-ep93xx/crunch.c index 1c05c5bf7e5c..757032d82f63 100644 --- a/arch/arm/mach-ep93xx/crunch.c +++ b/arch/arm/mach-ep93xx/crunch.c @@ -49,7 +49,7 @@ static int crunch_do(struct notifier_block *self, unsigned long cmd, void *t) * FALLTHROUGH: Ensure we don't try to overwrite our newly * initialised state information on the first fault. */ - /* Fall through */ + fallthrough; case THREAD_NOTIFY_EXIT: crunch_task_release(thread); diff --git a/arch/arm/mach-mmp/pm-mmp2.c b/arch/arm/mach-mmp/pm-mmp2.c index 2d86381e152d..7a6f74c32d42 100644 --- a/arch/arm/mach-mmp/pm-mmp2.c +++ b/arch/arm/mach-mmp/pm-mmp2.c @@ -123,19 +123,19 @@ void mmp2_pm_enter_lowpower_mode(int state) case POWER_MODE_SYS_SLEEP: apcr |= MPMU_PCR_PJ_SLPEN; /* set the SLPEN bit */ apcr |= MPMU_PCR_PJ_VCTCXOSD; /* set VCTCXOSD */ - /* fall through */ + fallthrough; case POWER_MODE_CHIP_SLEEP: apcr |= MPMU_PCR_PJ_SLPEN; - /* fall through */ + fallthrough; case POWER_MODE_APPS_SLEEP: apcr |= MPMU_PCR_PJ_APBSD; /* set APBSD */ - /* fall through */ + fallthrough; case POWER_MODE_APPS_IDLE: apcr |= MPMU_PCR_PJ_AXISD; /* set AXISDD bit */ apcr |= MPMU_PCR_PJ_DDRCORSD; /* set DDRCORSD bit */ idle_cfg |= APMU_PJ_IDLE_CFG_PJ_PWRDWN; /* PJ power down */ apcr |= MPMU_PCR_PJ_SPSD; - /* fall through */ + fallthrough; case POWER_MODE_CORE_EXTIDLE: idle_cfg |= APMU_PJ_IDLE_CFG_PJ_IDLE; /* set the IDLE bit */ idle_cfg &= ~APMU_PJ_IDLE_CFG_ISO_MODE_CNTRL_MASK; diff --git a/arch/arm/mach-mmp/pm-pxa910.c b/arch/arm/mach-mmp/pm-pxa910.c index 69ebe18ff209..1d71d73c1862 100644 --- a/arch/arm/mach-mmp/pm-pxa910.c +++ b/arch/arm/mach-mmp/pm-pxa910.c @@ -145,23 +145,23 @@ void pxa910_pm_enter_lowpower_mode(int state) case POWER_MODE_UDR: /* only shutdown APB in UDR */ apcr |= MPMU_APCR_STBYEN | MPMU_APCR_APBSD; - /* fall through */ + fallthrough; case POWER_MODE_SYS_SLEEP: apcr |= MPMU_APCR_SLPEN; /* set the SLPEN bit */ apcr |= MPMU_APCR_VCTCXOSD; /* set VCTCXOSD */ - /* fall through */ + fallthrough; case POWER_MODE_APPS_SLEEP: apcr |= MPMU_APCR_DDRCORSD; /* set DDRCORSD */ - /* fall through */ + fallthrough; case POWER_MODE_APPS_IDLE: apcr |= MPMU_APCR_AXISD; /* set AXISDD bit */ - /* fall through */ + fallthrough; case POWER_MODE_CORE_EXTIDLE: idle_cfg |= APMU_MOH_IDLE_CFG_MOH_IDLE; idle_cfg |= APMU_MOH_IDLE_CFG_MOH_PWRDWN; idle_cfg |= APMU_MOH_IDLE_CFG_MOH_PWR_SW(3) | APMU_MOH_IDLE_CFG_MOH_L2_PWR_SW(3); - /* fall through */ + fallthrough; case POWER_MODE_CORE_INTIDLE: break; } diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 1d119b974f5f..59755b5a1ad7 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -396,7 +396,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "3.1"; break; case 7: - /* FALLTHROUGH */ default: /* Use the latest known revision as default */ omap_revision = OMAP3430_REV_ES3_1_2; @@ -416,7 +415,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "1.0"; break; case 1: - /* FALLTHROUGH */ default: omap_revision = AM35XX_REV_ES1_1; cpu_rev = "1.1"; @@ -435,7 +433,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "1.1"; break; case 2: - /* FALLTHROUGH */ default: omap_revision = OMAP3630_REV_ES1_2; cpu_rev = "1.2"; @@ -456,7 +453,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "2.0"; break; case 3: - /* FALLTHROUGH */ default: omap_revision = TI8168_REV_ES2_1; cpu_rev = "2.1"; @@ -473,7 +469,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "2.0"; break; case 2: - /* FALLTHROUGH */ default: omap_revision = AM335X_REV_ES2_1; cpu_rev = "2.1"; @@ -491,7 +486,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "1.1"; break; case 2: - /* FALLTHROUGH */ default: omap_revision = AM437X_REV_ES1_2; cpu_rev = "1.2"; @@ -502,7 +496,6 @@ void __init omap3xxx_check_revision(void) case 0xb968: switch (rev) { case 0: - /* FALLTHROUGH */ case 1: omap_revision = TI8148_REV_ES1_0; cpu_rev = "1.0"; @@ -512,7 +505,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "2.0"; break; case 3: - /* FALLTHROUGH */ default: omap_revision = TI8148_REV_ES2_1; cpu_rev = "2.1"; diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index 6b4548f3b57f..fc7bb2ca1672 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -240,7 +240,7 @@ static int _omap_device_notifier_call(struct notifier_block *nb, if (pdev->dev.of_node) omap_device_build_from_dt(pdev); omap_auxdata_legacy_init(dev); - /* fall through */ + fallthrough; default: od = to_omap_device(pdev); if (od) diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 6df395fff971..f5dfddf492e2 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -298,11 +298,7 @@ static void omap3_pm_idle(void) if (omap_irq_pending()) return; - trace_cpu_idle_rcuidle(1, smp_processor_id()); - omap_sram_idle(); - - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_SUSPEND diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c index d13344b2ddcd..87cb47220e82 100644 --- a/arch/arm/mach-orion5x/dns323-setup.c +++ b/arch/arm/mach-orion5x/dns323-setup.c @@ -624,7 +624,7 @@ static void __init dns323_init(void) dns323ab_leds[0].active_low = 1; gpio_request(DNS323_GPIO_LED_POWER1, "Power Led Enable"); gpio_direction_output(DNS323_GPIO_LED_POWER1, 0); - /* Fall through */ + fallthrough; case DNS323_REV_B1: i2c_register_board_info(0, dns323ab_i2c_devices, ARRAY_SIZE(dns323ab_i2c_devices)); diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c index ea2c84214bac..d23970bd638d 100644 --- a/arch/arm/mach-rpc/riscpc.c +++ b/arch/arm/mach-rpc/riscpc.c @@ -46,7 +46,7 @@ static int __init parse_tag_acorn(const struct tag *tag) switch (tag->u.acorn.vram_pages) { case 512: vram_size += PAGE_SIZE * 256; - /* Fall through - ??? */ + fallthrough; /* ??? */ case 256: vram_size += PAGE_SIZE * 256; default: diff --git a/arch/arm/mach-tegra/reset.c b/arch/arm/mach-tegra/reset.c index 76a65df42d10..d5c805adf7a8 100644 --- a/arch/arm/mach-tegra/reset.c +++ b/arch/arm/mach-tegra/reset.c @@ -70,7 +70,7 @@ static void __init tegra_cpu_reset_handler_enable(void) switch (err) { case -ENOSYS: tegra_cpu_reset_handler_set(reset_address); - /* fall through */ + fallthrough; case 0: is_enabled = true; break; diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index f4bfc1cac91a..ea81e89e7740 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -694,7 +694,7 @@ thumb2arm(u16 tinstr) return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] | (tinstr & 255); /* register_list */ } - /* Else, fall through - for illegal instruction case */ + fallthrough; /* for illegal instruction case */ default: return BAD_INSTR; @@ -750,7 +750,7 @@ do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs, case 0xe8e0: case 0xe9e0: poffset->un = (tinst2 & 0xff) << 2; - /* Fall through */ + fallthrough; case 0xe940: case 0xe9c0: diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index c0fbfca5da8b..114c05ab4dd9 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -71,7 +71,7 @@ static void cpu_v7_spectre_init(void) /* Other ARM CPUs require no workaround */ if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) break; - /* fallthrough */ + fallthrough; /* Cortex A57/A72 require firmware workaround */ case ARM_CPU_PART_CORTEX_A57: case ARM_CPU_PART_CORTEX_A72: { diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c index b2e9e822426f..1eb59003bdec 100644 --- a/arch/arm/plat-omap/dma.c +++ b/arch/arm/plat-omap/dma.c @@ -309,14 +309,14 @@ void omap_set_dma_src_burst_mode(int lch, enum omap_dma_burst_mode burst_mode) * not supported by current hardware on OMAP1 * w |= (0x03 << 7); */ - /* fall through */ + fallthrough; case OMAP_DMA_DATA_BURST_16: if (dma_omap2plus()) { burst = 0x3; break; } /* OMAP1 don't support burst 16 */ - /* fall through */ + fallthrough; default: BUG(); } @@ -393,7 +393,7 @@ void omap_set_dma_dest_burst_mode(int lch, enum omap_dma_burst_mode burst_mode) break; } /* OMAP1 don't support burst 16 */ - /* fall through */ + fallthrough; default: printk(KERN_ERR "Invalid DMA burst mode\n"); BUG(); diff --git a/arch/arm/probes/decode.c b/arch/arm/probes/decode.c index fe81a9c21f2d..c84053a81358 100644 --- a/arch/arm/probes/decode.c +++ b/arch/arm/probes/decode.c @@ -307,7 +307,7 @@ static bool __kprobes decode_regs(probes_opcode_t *pinsn, u32 regs, bool modify) case REG_TYPE_NOPCWB: if (!is_writeback(insn)) break; /* No writeback, so any register is OK */ - /* fall through... */ + fallthrough; case REG_TYPE_NOPC: case REG_TYPE_NOPCX: /* Reject PC (R15) */ diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index 90b5bc723c83..feefa2055eba 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -280,7 +280,7 @@ void __kprobes kprobe_handler(struct pt_regs *regs) /* A nested probe was hit in FIQ, it is a BUG */ pr_warn("Unrecoverable kprobe detected.\n"); dump_kprobe(p); - /* fall through */ + fallthrough; default: /* impossible cases */ BUG(); diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 55bc8546d9c7..130569f90c54 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -82,8 +82,8 @@ endif # compiler to generate them and consequently to break the single image contract # we pass it only to the assembler. This option is utilized only in case of non # integrated assemblers. -ifneq ($(CONFIG_AS_HAS_ARMV8_4), y) -branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a +ifeq ($(CONFIG_AS_HAS_PAC), y) +asm-arch := armv8.3-a endif endif @@ -91,7 +91,12 @@ KBUILD_CFLAGS += $(branch-prot-flags-y) ifeq ($(CONFIG_AS_HAS_ARMV8_4), y) # make sure to pass the newest target architecture to -march. -KBUILD_CFLAGS += -Wa,-march=armv8.4-a +asm-arch := armv8.4-a +endif + +ifdef asm-arch +KBUILD_CFLAGS += -Wa,-march=$(asm-arch) \ + -DARM64_ASM_ARCH='"$(asm-arch)"' endif ifeq ($(CONFIG_SHADOW_CALL_STACK), y) @@ -165,6 +170,8 @@ zinstall install: PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@ + $(if $(CONFIG_COMPAT_VDSO), \ + $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@) # We use MRPROPER_FILES and CLEAN_FILES now archclean: diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi index 250fc01de78d..24aab3ea3f52 100644 --- a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi @@ -795,8 +795,8 @@ reg = <0x27>; interrupt-parent = <&gpa1>; interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; - s3fwrn5,en-gpios = <&gpf1 4 GPIO_ACTIVE_HIGH>; - s3fwrn5,fw-gpios = <&gpj0 2 GPIO_ACTIVE_HIGH>; + en-gpios = <&gpf1 4 GPIO_ACTIVE_HIGH>; + wake-gpios = <&gpj0 2 GPIO_ACTIVE_HIGH>; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 1a39e0ef776b..5b9ec032ce8d 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -686,6 +686,8 @@ clocks = <&pericfg CLK_PERI_MSDC30_0_PD>, <&topckgen CLK_TOP_MSDC50_0_SEL>; clock-names = "source", "hclk"; + resets = <&pericfg MT7622_PERI_MSDC0_SW_RST>; + reset-names = "hrst"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi index 34d249d85da7..8eb61dd9921e 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi @@ -337,8 +337,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03400000 0x0 0x10000>; interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC1>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC1>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRA &emc>, @@ -366,8 +367,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03420000 0x0 0x10000>; interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC2>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC2>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC2>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRAA &emc>, @@ -390,8 +392,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03440000 0x0 0x10000>; interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC3>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC3>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCR &emc>, @@ -416,8 +419,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03460000 0x0 0x10000>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC4>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; assigned-clocks = <&bpmp TEGRA186_CLK_SDMMC4>, <&bpmp TEGRA186_CLK_PLLC4_VCO>; assigned-clock-parents = <&bpmp TEGRA186_CLK_PLLC4_VCO>; diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index 48160f48003a..ca5cb6aef5ee 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -460,8 +460,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03400000 0x10000>; interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC1>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA194_RESET_SDMMC1>; reset-names = "sdhci"; interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCRA &emc>, @@ -485,8 +486,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03440000 0x10000>; interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC3>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA194_RESET_SDMMC3>; reset-names = "sdhci"; interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCR &emc>, @@ -511,8 +513,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03460000 0x10000>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC4>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; assigned-clocks = <&bpmp TEGRA194_CLK_SDMMC4>, <&bpmp TEGRA194_CLK_PLLC4>; assigned-clock-parents = diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi index 829f786af133..8cca2166a446 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi @@ -1194,8 +1194,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0000 0x0 0x200>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC1>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 14>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3", "sdmmc-1v8", @@ -1222,8 +1223,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0200 0x0 0x200>; interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC2>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC2>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 9>; reset-names = "sdhci"; pinctrl-names = "sdmmc-1v8-drv"; @@ -1239,8 +1241,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0400 0x0 0x200>; interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC3>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 69>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3", "sdmmc-1v8", @@ -1262,8 +1265,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0600 0x0 0x200>; interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC4>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 15>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3-drv", "sdmmc-1v8-drv"; diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi index 9edfae5944f7..24ef18fe77df 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi @@ -417,10 +417,10 @@ ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <56>; - ti,sci-rm-range-girq = <0x1>; + ti,sci-dev-id = <100>; + ti,interrupt-ranges = <0 392 32>; }; main_navss { @@ -438,10 +438,11 @@ ti,intr-trigger-type = <4>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <56>; - ti,sci-rm-range-girq = <0x0>, <0x2>; + ti,sci-dev-id = <182>; + ti,interrupt-ranges = <0 64 64>, + <64 448 64>; }; inta_main_udmass: interrupt-controller@33d00000 { @@ -452,8 +453,7 @@ msi-controller; ti,sci = <&dmsc>; ti,sci-dev-id = <179>; - ti,sci-rm-range-vint = <0x0>; - ti,sci-rm-range-global-event = <0x1>; + ti,interrupt-ranges = <0 0 256>; }; secure_proxy_main: mailbox@32c00000 { @@ -589,7 +589,7 @@ <0x0 0x33000000 0x0 0x40000>; reg-names = "rt", "fifos", "proxy_gcfg", "proxy_target"; ti,num-rings = <818>; - ti,sci-rm-range-gp-rings = <0x2>; /* GP ring range */ + ti,sci-rm-range-gp-rings = <0x1>; /* GP ring range */ ti,dma-ring-reset-quirk; ti,sci = <&dmsc>; ti,sci-dev-id = <187>; @@ -609,11 +609,11 @@ ti,sci-dev-id = <188>; ti,ringacc = <&ringacc>; - ti,sci-rm-range-tchan = <0x1>, /* TX_HCHAN */ - <0x2>; /* TX_CHAN */ - ti,sci-rm-range-rchan = <0x4>, /* RX_HCHAN */ - <0x5>; /* RX_CHAN */ - ti,sci-rm-range-rflow = <0x6>; /* GP RFLOW */ + ti,sci-rm-range-tchan = <0xf>, /* TX_HCHAN */ + <0xd>; /* TX_CHAN */ + ti,sci-rm-range-rchan = <0xb>, /* RX_HCHAN */ + <0xa>; /* RX_CHAN */ + ti,sci-rm-range-rflow = <0x0>; /* GP RFLOW */ }; cpts@310d0000 { @@ -622,7 +622,7 @@ reg-names = "cpts"; clocks = <&main_cpts_mux>; clock-names = "cpts"; - interrupts-extended = <&intr_main_navss 163 0>; + interrupts-extended = <&intr_main_navss 391>; interrupt-names = "cpts"; ti,cpts-periodic-outputs = <6>; ti,cpts-ext-ts-inputs = <8>; @@ -645,8 +645,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&intr_main_gpio>; - interrupts = <57 256>, <57 257>, <57 258>, <57 259>, <57 260>, - <57 261>; + interrupts = <192>, <193>, <194>, <195>, <196>, <197>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <96>; @@ -661,8 +660,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&intr_main_gpio>; - interrupts = <58 256>, <58 257>, <58 258>, <58 259>, <58 260>, - <58 261>; + interrupts = <200>, <201>, <202>, <203>, <204>, <205>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <90>; diff --git a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi index 8c1abcfe0860..51ca4b4d4c21 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi @@ -134,7 +134,7 @@ <0x0 0x2a500000 0x0 0x40000>; reg-names = "rt", "fifos", "proxy_gcfg", "proxy_target"; ti,num-rings = <286>; - ti,sci-rm-range-gp-rings = <0x2>; /* GP ring range */ + ti,sci-rm-range-gp-rings = <0x1>; /* GP ring range */ ti,dma-ring-reset-quirk; ti,sci = <&dmsc>; ti,sci-dev-id = <195>; @@ -154,11 +154,11 @@ ti,sci-dev-id = <194>; ti,ringacc = <&mcu_ringacc>; - ti,sci-rm-range-tchan = <0x1>, /* TX_HCHAN */ - <0x2>; /* TX_CHAN */ - ti,sci-rm-range-rchan = <0x3>, /* RX_HCHAN */ - <0x4>; /* RX_CHAN */ - ti,sci-rm-range-rflow = <0x5>; /* GP RFLOW */ + ti,sci-rm-range-tchan = <0xf>, /* TX_HCHAN */ + <0xd>; /* TX_CHAN */ + ti,sci-rm-range-rchan = <0xb>, /* RX_HCHAN */ + <0xa>; /* RX_CHAN */ + ti,sci-rm-range-rflow = <0x0>; /* GP RFLOW */ }; }; diff --git a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi index 5f55b9e82cf1..a1ffe88d9664 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi @@ -74,10 +74,10 @@ ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <56>; - ti,sci-rm-range-girq = <0x4>; + ti,sci-dev-id = <156>; + ti,interrupt-ranges = <0 712 16>; }; wkup_gpio0: wkup_gpio0@42110000 { @@ -86,7 +86,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&intr_wkup_gpio>; - interrupts = <59 128>, <59 129>, <59 130>, <59 131>; + interrupts = <60>, <61>, <62>, <63>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <56>; diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts index 611e66207010..b8a8a0fcb8af 100644 --- a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts +++ b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts @@ -384,7 +384,7 @@ }; &mailbox0_cluster0 { - interrupts = <164 0>; + interrupts = <436>; mbox_mcu_r5fss0_core0: mbox-mcu-r5fss0-core0 { ti,mbox-tx = <1 0 0>; @@ -393,7 +393,7 @@ }; &mailbox0_cluster1 { - interrupts = <165 0>; + interrupts = <432>; mbox_mcu_r5fss0_core1: mbox-mcu-r5fss0-core1 { ti,mbox-tx = <1 0 0>; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts index 8bc1e6ecc50e..e8fc01d97ada 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts @@ -287,7 +287,7 @@ }; &mailbox0_cluster0 { - interrupts = <214 0>; + interrupts = <436>; mbox_mcu_r5fss0_core0: mbox-mcu-r5fss0-core0 { ti,mbox-rx = <0 0 0>; @@ -301,7 +301,7 @@ }; &mailbox0_cluster1 { - interrupts = <215 0>; + interrupts = <432>; mbox_main_r5fss0_core0: mbox-main-r5fss0-core0 { ti,mbox-rx = <0 0 0>; @@ -315,7 +315,7 @@ }; &mailbox0_cluster2 { - interrupts = <216 0>; + interrupts = <428>; mbox_main_r5fss1_core0: mbox-main-r5fss1-core0 { ti,mbox-rx = <0 0 0>; @@ -329,7 +329,7 @@ }; &mailbox0_cluster3 { - interrupts = <217 0>; + interrupts = <424>; mbox_c66_0: mbox-c66-0 { ti,mbox-rx = <0 0 0>; @@ -343,7 +343,7 @@ }; &mailbox0_cluster4 { - interrupts = <218 0>; + interrupts = <420>; mbox_c71_0: mbox-c71-0 { ti,mbox-rx = <0 0 0>; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi index d14060207f00..12ceea9b3c9a 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi @@ -80,10 +80,10 @@ ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <14>; - ti,sci-rm-range-girq = <0x1>; + ti,sci-dev-id = <131>; + ti,interrupt-ranges = <8 392 56>; }; main_navss { @@ -101,10 +101,12 @@ ti,intr-trigger-type = <4>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <14>; - ti,sci-rm-range-girq = <0>, <2>; + ti,sci-dev-id = <213>; + ti,interrupt-ranges = <0 64 64>, + <64 448 64>, + <128 672 64>; }; main_udmass_inta: interrupt-controller@33d00000 { @@ -115,8 +117,7 @@ msi-controller; ti,sci = <&dmsc>; ti,sci-dev-id = <209>; - ti,sci-rm-range-vint = <0xa>; - ti,sci-rm-range-global-event = <0xd>; + ti,interrupt-ranges = <0 0 256>; }; secure_proxy_main: mailbox@32c00000 { @@ -296,7 +297,7 @@ reg-names = "cpts"; clocks = <&k3_clks 201 1>; clock-names = "cpts"; - interrupts-extended = <&main_navss_intr 201 0>; + interrupts-extended = <&main_navss_intr 391>; interrupt-names = "cpts"; ti,cpts-periodic-outputs = <6>; ti,cpts-ext-ts-inputs = <8>; @@ -688,8 +689,8 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <105 0>, <105 1>, <105 2>, <105 3>, - <105 4>, <105 5>, <105 6>, <105 7>; + interrupts = <256>, <257>, <258>, <259>, + <260>, <261>, <262>, <263>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <128>; @@ -705,7 +706,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <106 0>, <106 1>, <106 2>; + interrupts = <288>, <289>, <290>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <36>; @@ -721,8 +722,8 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <107 0>, <107 1>, <107 2>, <107 3>, - <107 4>, <107 5>, <107 6>, <107 7>; + interrupts = <264>, <265>, <266>, <267>, + <268>, <269>, <270>, <271>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <128>; @@ -738,7 +739,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <108 0>, <108 1>, <108 2>; + interrupts = <292>, <293>, <294>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <36>; @@ -754,8 +755,8 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <109 0>, <109 1>, <109 2>, <109 3>, - <109 4>, <109 5>, <109 6>, <109 7>; + interrupts = <272>, <273>, <274>, <275>, + <276>, <277>, <278>, <279>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <128>; @@ -771,7 +772,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <110 0>, <110 1>, <110 2>; + interrupts = <296>, <297>, <298>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <36>; @@ -787,8 +788,8 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <111 0>, <111 1>, <111 2>, <111 3>, - <111 4>, <111 5>, <111 6>, <111 7>; + interrupts = <280>, <281>, <282>, <283>, + <284>, <285>, <286>, <287>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <128>; @@ -804,7 +805,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <112 0>, <112 1>, <112 2>; + interrupts = <300>, <301>, <302>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <36>; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi index 30a735bcd0c8..c4a48e8d420a 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi @@ -101,10 +101,10 @@ ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <14>; - ti,sci-rm-range-girq = <0x5>; + ti,sci-dev-id = <137>; + ti,interrupt-ranges = <16 960 16>; }; wkup_gpio0: gpio@42110000 { @@ -113,8 +113,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&wkup_gpio_intr>; - interrupts = <113 0>, <113 1>, <113 2>, - <113 3>, <113 4>, <113 5>; + interrupts = <103>, <104>, <105>, <106>, <107>, <108>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <84>; @@ -130,8 +129,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&wkup_gpio_intr>; - interrupts = <114 0>, <114 1>, <114 2>, - <114 3>, <114 4>, <114 5>; + interrupts = <112>, <113>, <114>, <115>, <116>, <117>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <84>; diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h index 51a7ce87cdfe..6fb2e6bcc392 100644 --- a/arch/arm64/include/asm/compiler.h +++ b/arch/arm64/include/asm/compiler.h @@ -2,6 +2,12 @@ #ifndef __ASM_COMPILER_H #define __ASM_COMPILER_H +#ifdef ARM64_ASM_ARCH +#define ARM64_ASM_PREAMBLE ".arch " ARM64_ASM_ARCH "\n" +#else +#define ARM64_ASM_PREAMBLE +#endif + /* * The EL0/EL1 pointer bits used by a pointer authentication code. * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply. diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index aa4b6521ef14..ff328e5bbb75 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -95,6 +95,11 @@ static inline int arch_irqs_disabled_flags(unsigned long flags) return res; } +static inline int arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(arch_local_save_flags()); +} + static inline unsigned long arch_local_irq_save(void) { unsigned long flags; diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 51c1d9918999..1da8e3dc4455 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -71,11 +71,12 @@ * IMO: Override CPSR.I and enable signaling with VI * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate + * PTW: Take a stage2 fault if a stage1 walk steps in device memory */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ - HCR_FMO | HCR_IMO) + HCR_FMO | HCR_IMO | HCR_PTW ) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index fb1a922b31ba..6f98fbd0ac81 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -169,6 +169,34 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; *__hyp_this_cpu_ptr(sym); \ }) +#define __KVM_EXTABLE(from, to) \ + " .pushsection __kvm_ex_table, \"a\"\n" \ + " .align 3\n" \ + " .long (" #from " - .), (" #to " - .)\n" \ + " .popsection\n" + + +#define __kvm_at(at_op, addr) \ +( { \ + int __kvm_at_err = 0; \ + u64 spsr, elr; \ + asm volatile( \ + " mrs %1, spsr_el2\n" \ + " mrs %2, elr_el2\n" \ + "1: at "at_op", %3\n" \ + " isb\n" \ + " b 9f\n" \ + "2: msr spsr_el2, %1\n" \ + " msr elr_el2, %2\n" \ + " mov %w0, %4\n" \ + "9:\n" \ + __KVM_EXTABLE(1b, 2b) \ + : "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr) \ + : "r" (addr), "i" (-EFAULT)); \ + __kvm_at_err; \ +} ) + + #else /* __ASSEMBLY__ */ .macro hyp_adr_this_cpu reg, sym, tmp @@ -193,6 +221,21 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; ldr \vcpu, [\ctxt, #HOST_CONTEXT_VCPU] .endm +/* + * KVM extable for unexpected exceptions. + * In the same format _asm_extable, but output to a different section so that + * it can be mapped to EL2. The KVM version is not sorted. The caller must + * ensure: + * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented + * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup. + */ +.macro _kvm_extable, from, to + .pushsection __kvm_ex_table, "a" + .align 3 + .long (\from - .), (\to - .) + .popsection +.endm + #endif #endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 65568b23868a..e52c927aade5 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -473,7 +473,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, unsigned flags); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index d493174415db..cc3f5a33ff9c 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -28,14 +28,16 @@ * not. The macros handles invoking the asm with or without the * register argument as appropriate. */ -#define __TLBI_0(op, arg) asm ("tlbi " #op "\n" \ +#define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE \ + "tlbi " #op "\n" \ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op, \ ARM64_WORKAROUND_REPEAT_TLBI, \ CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \ : : ) -#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0\n" \ +#define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE \ + "tlbi " #op ", %0\n" \ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op ", %0", \ ARM64_WORKAROUND_REPEAT_TLBI, \ diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 455966401102..a85174d05473 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -322,7 +322,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) */ if (memblock_is_map_memory(phys)) return (void __iomem *)__phys_to_virt(phys); - /* fall through */ + fallthrough; default: if (region->attribute & EFI_MEMORY_WB) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6bd1d3ad037a..c332d49780dc 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -910,6 +910,8 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM erratum 1418040", .capability = ARM64_WORKAROUND_1418040, ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), + .type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU | + ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU), }, #endif #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index a389b999482e..6424584be01e 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -686,7 +686,7 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, case FTR_HIGHER_OR_ZERO_SAFE: if (!cur || !new) break; - /* Fallthrough */ + fallthrough; case FTR_HIGHER_SAFE: ret = new > cur ? new : cur; break; diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 393c6fb1f1cb..d0076c2159e6 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -327,7 +327,6 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info) set_bit(ICACHEF_VPIPT, &__icache_flags); break; default: - /* Fallthrough */ case ICACHE_POLICY_VIPT: /* Assume aliasing */ set_bit(ICACHEF_ALIASING, &__icache_flags); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2646178c8329..55af8b504b65 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -170,19 +170,6 @@ alternative_cb_end stp x28, x29, [sp, #16 * 14] .if \el == 0 - .if \regsize == 32 - /* - * If we're returning from a 32-bit task on a system affected by - * 1418040 then re-enable userspace access to the virtual counter. - */ -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - orr x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - .endif clear_gp_regs mrs x21, sp_el0 ldr_this_cpu tsk, __entry_task, x20 @@ -294,14 +281,6 @@ alternative_else_nop_endif tst x22, #PSR_MODE32_BIT // native task? b.eq 3f -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - bic x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - #ifdef CONFIG_ARM64_ERRATUM_845719 alternative_if ARM64_WORKAROUND_845719 #ifdef CONFIG_PID_IN_CONTEXTIDR diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index af234a1e08b7..712e97c03e54 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -257,7 +257,7 @@ static int hw_breakpoint_control(struct perf_event *bp, * level. */ enable_debug_monitors(dbg_el); - /* Fall through */ + fallthrough; case HW_BREAKPOINT_RESTORE: /* Setup the address register. */ write_wb_reg(val_reg, i, info->address); @@ -541,13 +541,13 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; - /* Fallthrough */ + fallthrough; case 3: /* Allow single byte watchpoint. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; - /* Fallthrough */ + fallthrough; default: return -EINVAL; } diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 9e897c500237..8982b68289b7 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -103,6 +103,10 @@ KVM_NVHE_ALIAS(vgic_v3_cpuif_trap); KVM_NVHE_ALIAS(gic_pmr_sync); #endif +/* EL2 exception handling */ +KVM_NVHE_ALIAS(__start___kvm_ex_table); +KVM_NVHE_ALIAS(__stop___kvm_ex_table); + #endif /* CONFIG_KVM */ #endif /* __ARM64_KERNEL_IMAGE_VARS_H */ diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 0ce3a28e3347..2e224435c024 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -305,8 +305,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, mod->arch.core.plt_shndx = i; else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt")) mod->arch.init.plt_shndx = i; - else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && - !strcmp(secstrings + sechdrs[i].sh_name, + else if (!strcmp(secstrings + sechdrs[i].sh_name, ".text.ftrace_trampoline")) tramp = sechdrs + i; else if (sechdrs[i].sh_type == SHT_SYMTAB) diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 1cd1a4d0ed30..2a1ad95d9b2c 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -315,21 +315,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, /* MOVW instruction relocations. */ case R_AARCH64_MOVW_UABS_G0_NC: overflow_check = false; - /* Fall through */ + fallthrough; case R_AARCH64_MOVW_UABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G1_NC: overflow_check = false; - /* Fall through */ + fallthrough; case R_AARCH64_MOVW_UABS_G1: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G2_NC: overflow_check = false; - /* Fall through */ + fallthrough; case R_AARCH64_MOVW_UABS_G2: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32, AARCH64_INSN_IMM_MOVKZ); @@ -397,7 +397,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, break; case R_AARCH64_ADR_PREL_PG_HI21_NC: overflow_check = false; - /* Fall through */ + fallthrough; case R_AARCH64_ADR_PREL_PG_HI21: ovf = reloc_insn_adrp(me, sechdrs, loc, val); if (ovf && ovf != -ERANGE) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 84ec630b8ab5..f1804496b935 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -123,10 +123,8 @@ void arch_cpu_idle(void) * This should do all the clock switching and wait for interrupt * tricks */ - trace_cpu_idle_rcuidle(1, smp_processor_id()); cpu_do_idle(); local_irq_enable(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_HOTPLUG_CPU @@ -516,6 +514,39 @@ static void entry_task_switch(struct task_struct *next) } /* + * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT. + * Assuming the virtual counter is enabled at the beginning of times: + * + * - disable access when switching from a 64bit task to a 32bit task + * - enable access when switching from a 32bit task to a 64bit task + */ +static void erratum_1418040_thread_switch(struct task_struct *prev, + struct task_struct *next) +{ + bool prev32, next32; + u64 val; + + if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && + cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + return; + + prev32 = is_compat_thread(task_thread_info(prev)); + next32 = is_compat_thread(task_thread_info(next)); + + if (prev32 == next32) + return; + + val = read_sysreg(cntkctl_el1); + + if (!next32) + val |= ARCH_TIMER_USR_VCT_ACCESS_EN; + else + val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN; + + write_sysreg(val, cntkctl_el1); +} + +/* * Thread switching. */ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, @@ -530,6 +561,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, entry_task_switch(next); uao_thread_switch(next); ssbs_thread_switch(next); + erratum_1418040_thread_switch(prev, next); /* * Complete any pending TLB or cache maintenance on this CPU in case diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 77c4c9bad1b8..53acbeca4f57 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -280,7 +280,6 @@ u64 cpu_logical_map(int cpu) { return __cpu_logical_map[cpu]; } -EXPORT_SYMBOL_GPL(cpu_logical_map); void __init __no_sanitize_address setup_arch(char **cmdline_p) { diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 03957a1ae6c0..355ee9eed4dd 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -151,7 +151,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) break; } pr_crit("CPU%u: may not have shut down cleanly\n", cpu); - /* Fall through */ + fallthrough; case CPU_STUCK_IN_KERNEL: pr_crit("CPU%u: is stuck in kernel\n", cpu); if (status & CPU_STUCK_REASON_52_BIT_VA) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 5139a5f19256..d6adb4677c25 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -208,7 +208,7 @@ quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ # Install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ +quiet_cmd_vdso_install = INSTALL32 $@ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so vdso.so: $(obj)/vdso.so.dbg diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index ec8e894684a7..7cba7623fcec 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -20,6 +20,13 @@ ENTRY(_text) jiffies = jiffies_64; + +#define HYPERVISOR_EXTABLE \ + . = ALIGN(SZ_8); \ + __start___kvm_ex_table = .; \ + *(__kvm_ex_table) \ + __stop___kvm_ex_table = .; + #define HYPERVISOR_TEXT \ /* \ * Align to 4 KB so that \ @@ -35,6 +42,7 @@ jiffies = jiffies_64; __hyp_idmap_text_end = .; \ __hyp_text_start = .; \ *(.hyp.text) \ + HYPERVISOR_EXTABLE \ __hyp_text_end = .; #define IDMAP_TEXT \ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 691d21e4c717..46dc3d75cf13 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1640,6 +1640,10 @@ int kvm_arch_init(void *opaque) return -ENODEV; } + if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)) + kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \ + "Only trusted guests should be used on this system.\n"); + for_each_online_cpu(cpu) { smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); if (ret < 0) { diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index fe6c7d79309d..5d690d60ccad 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -128,7 +128,7 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu) switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_WATCHPT_LOW: run->debug.arch.far = vcpu->arch.fault.far_el2; - /* fall through */ + fallthrough; case ESR_ELx_EC_SOFTSTP_LOW: case ESR_ELx_EC_BREAKPT_LOW: case ESR_ELx_EC_BKPT32: diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index ee32a7743389..76e7eaf4675e 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -196,20 +196,23 @@ alternative_endif // This is our single instruction exception window. A pending // SError is guaranteed to occur at the earliest when we unmask // it, and at the latest just after the ISB. - .global abort_guest_exit_start abort_guest_exit_start: isb - .global abort_guest_exit_end abort_guest_exit_end: msr daifset, #4 // Mask aborts + ret + + _kvm_extable abort_guest_exit_start, 9997f + _kvm_extable abort_guest_exit_end, 9997f +9997: + msr daifset, #4 // Mask aborts + mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) - // If the exception took place, restore the EL1 exception - // context so that we can report some information. - // Merge the exception code with the SError pending bit. - tbz x0, #ARM_EXIT_WITH_SERROR_BIT, 1f + // restore the EL1 exception context so that we can report some + // information. Merge the exception code with the SError pending bit. msr elr_el2, x2 msr esr_el2, x3 msr spsr_el2, x4 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 689fccbc9de7..46b4dab933d0 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -15,6 +15,30 @@ #include <asm/kvm_mmu.h> #include <asm/mmu.h> +.macro save_caller_saved_regs_vect + /* x0 and x1 were saved in the vector entry */ + stp x2, x3, [sp, #-16]! + stp x4, x5, [sp, #-16]! + stp x6, x7, [sp, #-16]! + stp x8, x9, [sp, #-16]! + stp x10, x11, [sp, #-16]! + stp x12, x13, [sp, #-16]! + stp x14, x15, [sp, #-16]! + stp x16, x17, [sp, #-16]! +.endm + +.macro restore_caller_saved_regs_vect + ldp x16, x17, [sp], #16 + ldp x14, x15, [sp], #16 + ldp x12, x13, [sp], #16 + ldp x10, x11, [sp], #16 + ldp x8, x9, [sp], #16 + ldp x6, x7, [sp], #16 + ldp x4, x5, [sp], #16 + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +.endm + .text .macro do_el2_call @@ -143,13 +167,19 @@ el1_error: b __guest_exit el2_sync: - /* Check for illegal exception return, otherwise panic */ + /* Check for illegal exception return */ mrs x0, spsr_el2 + tbnz x0, #20, 1f - /* if this was something else, then panic! */ - tst x0, #PSR_IL_BIT - b.eq __hyp_panic + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + bl kvm_unexpected_el2_exception + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect + eret + +1: /* Let's attempt a recovery from the illegal exception return */ get_vcpu_ptr x1, x0 mov x0, #ARM_EXCEPTION_IL @@ -157,27 +187,14 @@ el2_sync: el2_error: - ldp x0, x1, [sp], #16 + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + + bl kvm_unexpected_el2_exception + + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect - /* - * Only two possibilities: - * 1) Either we come from the exit path, having just unmasked - * PSTATE.A: change the return code to an EL2 fault, and - * carry on, as we're already in a sane state to handle it. - * 2) Or we come from anywhere else, and that's a bug: we panic. - * - * For (1), x0 contains the original return code and x1 doesn't - * contain anything meaningful at that stage. We can reuse them - * as temp registers. - * For (2), who cares? - */ - mrs x0, elr_el2 - adr x1, abort_guest_exit_start - cmp x0, x1 - adr x1, abort_guest_exit_end - ccmp x0, x1, #4, ne - b.ne __hyp_panic - mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) eret sb diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h index 0297dc63988c..5e28ea6aa097 100644 --- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h @@ -21,70 +21,70 @@ #define save_debug(ptr,reg,nr) \ switch (nr) { \ case 15: ptr[15] = read_debug(reg, 15); \ - /* Fall through */ \ + fallthrough; \ case 14: ptr[14] = read_debug(reg, 14); \ - /* Fall through */ \ + fallthrough; \ case 13: ptr[13] = read_debug(reg, 13); \ - /* Fall through */ \ + fallthrough; \ case 12: ptr[12] = read_debug(reg, 12); \ - /* Fall through */ \ + fallthrough; \ case 11: ptr[11] = read_debug(reg, 11); \ - /* Fall through */ \ + fallthrough; \ case 10: ptr[10] = read_debug(reg, 10); \ - /* Fall through */ \ + fallthrough; \ case 9: ptr[9] = read_debug(reg, 9); \ - /* Fall through */ \ + fallthrough; \ case 8: ptr[8] = read_debug(reg, 8); \ - /* Fall through */ \ + fallthrough; \ case 7: ptr[7] = read_debug(reg, 7); \ - /* Fall through */ \ + fallthrough; \ case 6: ptr[6] = read_debug(reg, 6); \ - /* Fall through */ \ + fallthrough; \ case 5: ptr[5] = read_debug(reg, 5); \ - /* Fall through */ \ + fallthrough; \ case 4: ptr[4] = read_debug(reg, 4); \ - /* Fall through */ \ + fallthrough; \ case 3: ptr[3] = read_debug(reg, 3); \ - /* Fall through */ \ + fallthrough; \ case 2: ptr[2] = read_debug(reg, 2); \ - /* Fall through */ \ + fallthrough; \ case 1: ptr[1] = read_debug(reg, 1); \ - /* Fall through */ \ + fallthrough; \ default: ptr[0] = read_debug(reg, 0); \ } #define restore_debug(ptr,reg,nr) \ switch (nr) { \ case 15: write_debug(ptr[15], reg, 15); \ - /* Fall through */ \ + fallthrough; \ case 14: write_debug(ptr[14], reg, 14); \ - /* Fall through */ \ + fallthrough; \ case 13: write_debug(ptr[13], reg, 13); \ - /* Fall through */ \ + fallthrough; \ case 12: write_debug(ptr[12], reg, 12); \ - /* Fall through */ \ + fallthrough; \ case 11: write_debug(ptr[11], reg, 11); \ - /* Fall through */ \ + fallthrough; \ case 10: write_debug(ptr[10], reg, 10); \ - /* Fall through */ \ + fallthrough; \ case 9: write_debug(ptr[9], reg, 9); \ - /* Fall through */ \ + fallthrough; \ case 8: write_debug(ptr[8], reg, 8); \ - /* Fall through */ \ + fallthrough; \ case 7: write_debug(ptr[7], reg, 7); \ - /* Fall through */ \ + fallthrough; \ case 6: write_debug(ptr[6], reg, 6); \ - /* Fall through */ \ + fallthrough; \ case 5: write_debug(ptr[5], reg, 5); \ - /* Fall through */ \ + fallthrough; \ case 4: write_debug(ptr[4], reg, 4); \ - /* Fall through */ \ + fallthrough; \ case 3: write_debug(ptr[3], reg, 3); \ - /* Fall through */ \ + fallthrough; \ case 2: write_debug(ptr[2], reg, 2); \ - /* Fall through */ \ + fallthrough; \ case 1: write_debug(ptr[1], reg, 1); \ - /* Fall through */ \ + fallthrough; \ default: write_debug(ptr[0], reg, 0); \ } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 426ef65601dd..5b6b8fa00f0a 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -17,6 +17,7 @@ #include <asm/barrier.h> #include <asm/cpufeature.h> +#include <asm/extable.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> @@ -29,6 +30,9 @@ extern const char __hyp_panic_string[]; +extern struct exception_table_entry __start___kvm_ex_table; +extern struct exception_table_entry __stop___kvm_ex_table; + /* Check whether the FP regs were dirtied while in the host-side run loop: */ static inline bool update_fp_enabled(struct kvm_vcpu *vcpu) { @@ -142,10 +146,10 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) * saved the guest context yet, and we may return early... */ par = read_sysreg(par_el1); - asm volatile("at s1e1r, %0" : : "r" (far)); - isb(); - - tmp = read_sysreg(par_el1); + if (!__kvm_at("s1e1r", far)) + tmp = read_sysreg(par_el1); + else + tmp = SYS_PAR_EL1_F; /* back to the guest */ write_sysreg(par, par_el1); if (unlikely(tmp & SYS_PAR_EL1_F)) @@ -508,4 +512,31 @@ static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu) #endif } +static inline void __kvm_unexpected_el2_exception(void) +{ + unsigned long addr, fixup; + struct kvm_cpu_context *host_ctxt; + struct exception_table_entry *entry, *end; + unsigned long elr_el2 = read_sysreg(elr_el2); + + entry = hyp_symbol_addr(__start___kvm_ex_table); + end = hyp_symbol_addr(__stop___kvm_ex_table); + host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; + + while (entry < end) { + addr = (unsigned long)&entry->insn + entry->insn; + fixup = (unsigned long)&entry->fixup + entry->fixup; + + if (addr != elr_el2) { + entry++; + continue; + } + + write_sysreg(fixup, elr_el2); + return; + } + + hyp_panic(host_ctxt); +} + #endif /* __ARM64_KVM_HYP_SWITCH_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 341be2f2f312..0970442d2dbc 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -270,3 +270,8 @@ void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) read_sysreg(hpfar_el2), par, vcpu); unreachable(); } + +asmlinkage void kvm_unexpected_el2_exception(void) +{ + return __kvm_unexpected_el2_exception(); +} diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 5a0073511efb..452f4cacd674 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -340,10 +340,10 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) case 7: cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3); cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2); - /* Fall through */ + fallthrough; case 6: cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1); - /* Fall through */ + fallthrough; default: cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0); } @@ -352,10 +352,10 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) case 7: cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3); cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2); - /* Fall through */ + fallthrough; case 6: cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1); - /* Fall through */ + fallthrough; default: cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0); } @@ -373,10 +373,10 @@ void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) case 7: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3); __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2); - /* Fall through */ + fallthrough; case 6: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1); - /* Fall through */ + fallthrough; default: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0); } @@ -385,10 +385,10 @@ void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) case 7: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3); __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2); - /* Fall through */ + fallthrough; case 6: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1); - /* Fall through */ + fallthrough; default: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0); } diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index c52d714e0d75..c1da4f86ccac 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -217,3 +217,8 @@ void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) __hyp_call_panic(spsr, elr, par, host_ctxt); unreachable(); } + +asmlinkage void kvm_unexpected_el2_exception(void) +{ + return __kvm_unexpected_el2_exception(); +} diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 0121ef2c7c8d..ba00bcc0c884 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -343,7 +343,8 @@ static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd, * destroying the VM), otherwise another faulting VCPU may come in and mess * with things behind our backs. */ -static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) +static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, + bool may_block) { struct kvm *kvm = mmu->kvm; pgd_t *pgd; @@ -369,11 +370,16 @@ static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 si * If the range is too large, release the kvm->mmu_lock * to prevent starvation and lockup detector warnings. */ - if (next != end) + if (may_block && next != end) cond_resched_lock(&kvm->mmu_lock); } while (pgd++, addr = next, addr != end); } +static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) +{ + __unmap_stage2_range(mmu, start, size, true); +} + static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { @@ -2208,18 +2214,21 @@ static int handle_hva_to_gpa(struct kvm *kvm, static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) { - unmap_stage2_range(&kvm->arch.mmu, gpa, size); + unsigned flags = *(unsigned *)data; + bool may_block = flags & MMU_NOTIFIER_RANGE_BLOCKABLE; + + __unmap_stage2_range(&kvm->arch.mmu, gpa, size, may_block); return 0; } int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, unsigned flags) { if (!kvm->arch.mmu.pgd) return 0; trace_kvm_unmap_hva_range(start, end); - handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); + handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, &flags); return 0; } diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index a206655a39a5..9b11c096a042 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -45,7 +45,7 @@ static u32 get_cpu_asid_bits(void) default: pr_warn("CPU%d: Unknown ASID size (%d); assuming 8-bit\n", smp_processor_id(), fld); - /* Fallthrough */ + fallthrough; case 0: asid = 8; break; diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c index e456652facce..d05c78eace1b 100644 --- a/arch/c6x/kernel/signal.c +++ b/arch/c6x/kernel/signal.c @@ -220,7 +220,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler) regs->a4 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: do_restart: regs->a4 = regs->orig_a4; @@ -252,7 +252,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs, break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->a4 = regs->orig_a4; regs->pc -= 4; diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c index 9452d6570b7e..970895df75ec 100644 --- a/arch/csky/kernel/signal.c +++ b/arch/csky/kernel/signal.c @@ -194,7 +194,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->a0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->a0 = regs->orig_a0; regs->pc -= TRAP0_SIZE; diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c index 38d335488a54..69e68949787f 100644 --- a/arch/h8300/kernel/signal.c +++ b/arch/h8300/kernel/signal.c @@ -227,7 +227,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka) regs->er0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: do_restart: regs->er0 = regs->orig_er0; diff --git a/arch/hexagon/kernel/module.c b/arch/hexagon/kernel/module.c index cf99fb79a124..cb3bf19b0640 100644 --- a/arch/hexagon/kernel/module.c +++ b/arch/hexagon/kernel/module.c @@ -120,7 +120,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, } case R_HEXAGON_HI16: value = (value>>16) & 0xffff; - /* fallthrough */ + fallthrough; case R_HEXAGON_LO16: *location &= ~0x00c03fff; *location |= value & 0x3fff; diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c index d48864c48e5a..94cc7ff52dce 100644 --- a/arch/hexagon/kernel/signal.c +++ b/arch/hexagon/kernel/signal.c @@ -155,7 +155,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->r00 = -EINTR; break; } - /* Fall through */ + fallthrough; case -ERESTARTNOINTR: regs->r06 = regs->syscall_nr; pt_set_elr(regs, pt_elr(regs) - 4); diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 10850897a91c..779b6972aa84 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -366,6 +366,15 @@ pgd_index (unsigned long address) } #define pgd_index pgd_index +/* + * In the kernel's mapped region we know everything is in region number 5, so + * as an optimisation its PGD already points to the area for that region. + * However, this also means that we cannot use pgd_index() and we must + * never add the region here. + */ +#define pgd_offset_k(addr) \ + (init_mm.pgd + (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))) + /* Look up a pgd entry in the gate area. On IA-64, the gate-area resides in the kernel-mapped segment, hence we use pgd_offset_k() here. */ diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index bec762a9b418..fec70d662d0c 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -163,7 +163,7 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data) case DIE_INIT_MONARCH_LEAVE: if (!kdump_freeze_monarch) break; - /* fall through */ + fallthrough; case DIE_INIT_SLAVE_LEAVE: case DIE_INIT_MONARCH_ENTER: case DIE_MCA_RENDZVOUS_LEAVE: diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index b49fe6f618ed..f8150ee74f29 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -3,7 +3,7 @@ * Architecture-specific kernel symbols */ -#ifdef CONFIG_VIRTUAL_MEM_MAP +#if defined(CONFIG_VIRTUAL_MEM_MAP) || defined(CONFIG_DISCONTIGMEM) #include <linux/compiler.h> #include <linux/export.h> #include <linux/memblock.h> diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 1a42ba885188..00a496cb346f 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -654,7 +654,7 @@ do_reloc (struct module *mod, uint8_t r_type, Elf64_Sym *sym, uint64_t addend, } } else if (!is_internal(mod, val)) val = get_plt(mod, location, val, &ok); - /* FALL THROUGH */ + fallthrough; default: val -= bundle(location); break; diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 971f166873aa..0dc3611e7971 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -3472,7 +3472,7 @@ pfm_restart(pfm_context_t *ctx, void *arg, int count, struct pt_regs *regs) break; case PFM_CTX_LOADED: if (CTX_HAS_SMPL(ctx) && fmt->fmt_restart_active) break; - /* fall through */ + fallthrough; case PFM_CTX_UNLOADED: case PFM_CTX_ZOMBIE: DPRINT(("invalid state=%d\n", state)); diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index d07ed65c9c6e..e67b22fc3c60 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -374,7 +374,7 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall) /* note: scr->pt.r10 is already -1 */ break; } - /*FALLTHRU*/ + fallthrough; case ERESTARTNOINTR: ia64_decrement_ip(&scr->pt); restart = 0; /* don't restart twice if handle_signal() fails... */ diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c index 2d4e65ba5c3e..6c1a8951dfbb 100644 --- a/arch/ia64/kernel/unaligned.c +++ b/arch/ia64/kernel/unaligned.c @@ -1431,7 +1431,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) if (u.insn.x) /* oops, really a semaphore op (cmpxchg, etc) */ goto failure; - /*FALLTHRU*/ + fallthrough; case LDS_IMM_OP: case LDSA_IMM_OP: case LDFS_OP: @@ -1459,7 +1459,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) if (u.insn.x) /* oops, really a semaphore op (cmpxchg, etc) */ goto failure; - /*FALLTHRU*/ + fallthrough; case LD_IMM_OP: case LDA_IMM_OP: case LDBIAS_IMM_OP: @@ -1475,7 +1475,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) if (u.insn.x) /* oops, really a semaphore op (cmpxchg, etc) */ goto failure; - /*FALLTHRU*/ + fallthrough; case ST_IMM_OP: case STREL_IMM_OP: ret = emulate_store_int(ifa, u.insn, regs); diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c index 7601fe0622d2..6bd64c35e691 100644 --- a/arch/ia64/kernel/unwind.c +++ b/arch/ia64/kernel/unwind.c @@ -324,7 +324,7 @@ unw_access_gr (struct unw_frame_info *info, int regnum, unsigned long *val, char return 0; } } - /* fall through */ + fallthrough; case UNW_NAT_NONE: dummy_nat = 0; nat_addr = &dummy_nat; diff --git a/arch/m68k/atari/atakeyb.c b/arch/m68k/atari/atakeyb.c index 37091898adb3..5e0e682f9c61 100644 --- a/arch/m68k/atari/atakeyb.c +++ b/arch/m68k/atari/atakeyb.c @@ -207,7 +207,7 @@ repeat: self_test_last_rcv = jiffies; break; } - /* FALL THROUGH */ + fallthrough; default: break_flag = scancode & BREAK_MASK; diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index fc034fd19798..a98fca977073 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -1067,7 +1067,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler) regs->d0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: do_restart: regs->d0 = regs->orig_d0; diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index 5c9f3a2d6538..a621fcc1a576 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -1018,7 +1018,7 @@ int __init mac_platform_init(void) */ platform_device_register_simple("mac_scsi", 1, mac_scsi_duo_rsrc, ARRAY_SIZE(mac_scsi_duo_rsrc)); - /* fall through */ + fallthrough; case MAC_SCSI_OLD: /* Addresses from Developer Notes for Duo System, * PowerBook 180 & 160, 140 & 170, Macintosh IIsi diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c index 1f0fad2a98a0..ac77d73af19a 100644 --- a/arch/m68k/mac/via.c +++ b/arch/m68k/mac/via.c @@ -370,7 +370,7 @@ void via_nubus_irq_startup(int irq) /* Allow NuBus slots 9 through F. */ via2[vDirA] &= 0x80 | ~(1 << irq_idx); } - /* fall through */ + fallthrough; case MAC_VIA_IICI: via_irq_enable(irq); break; diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 795f483b1050..ef46e77e97a5 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -118,7 +118,7 @@ good_area: pr_debug("do_page_fault: good_area\n"); switch (error_code & 3) { default: /* 3: write, present */ - /* fall through */ + fallthrough; case 2: /* write, not present */ if (!(vma->vm_flags & VM_WRITE)) goto acc_err; diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c index 65bf5fd8d473..4a96b59f0bee 100644 --- a/arch/microblaze/kernel/signal.c +++ b/arch/microblaze/kernel/signal.c @@ -249,7 +249,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler) regs->r3 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: do_restart: /* offset of 4 bytes to re-execute trap (brki) instruction */ diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 0880a003573d..3344d4a1fe89 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -46,6 +46,9 @@ unsigned long memory_size; EXPORT_SYMBOL(memory_size); unsigned long lowmem_size; +EXPORT_SYMBOL(min_low_pfn); +EXPORT_SYMBOL(max_low_pfn); + #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; EXPORT_SYMBOL(kmap_pte); diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h index 47a8ffc0b413..f5b8300f4573 100644 --- a/arch/mips/include/asm/irqflags.h +++ b/arch/mips/include/asm/irqflags.h @@ -137,6 +137,11 @@ static inline int arch_irqs_disabled_flags(unsigned long flags) return !(flags & 1); } +static inline int arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(arch_local_save_flags()); +} + #endif /* #ifndef __ASSEMBLY__ */ /* diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index d35eaed1668f..825d337a505a 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -969,7 +969,7 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, unsigned flags); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h index b6e9c99b85a5..eb181224eb4c 100644 --- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h @@ -26,7 +26,6 @@ #define cpu_has_counter 1 #define cpu_has_dc_aliases (PAGE_SIZE < 0x4000) #define cpu_has_divec 0 -#define cpu_has_ejtag 0 #define cpu_has_inclusive_pcaches 1 #define cpu_has_llsc 1 #define cpu_has_mcheck 0 @@ -42,7 +41,6 @@ #define cpu_has_veic 0 #define cpu_has_vint 0 #define cpu_has_vtag_icache 0 -#define cpu_has_watch 1 #define cpu_has_wsbh 1 #define cpu_has_ic_fills_f_dc 1 #define cpu_hwrena_impl_bits 0xc0000000 diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index f5e362f79701..bf2480923154 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -2,8 +2,6 @@ #ifndef __ASM_MACH_LOONGSON64_IRQ_H_ #define __ASM_MACH_LOONGSON64_IRQ_H_ -#include <boot_param.h> - /* cpu core interrupt numbers */ #define NR_IRQS_LEGACY 16 #define NR_MIPS_CPU_IRQS 8 diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h index 3a25dbd3b3e9..5eaca4fe3f92 100644 --- a/arch/mips/include/asm/mach-loongson64/mmzone.h +++ b/arch/mips/include/asm/mach-loongson64/mmzone.h @@ -9,7 +9,6 @@ #ifndef _ASM_MACH_LOONGSON64_MMZONE_H #define _ASM_MACH_LOONGSON64_MMZONE_H -#include <boot_param.h> #define NODE_ADDRSPACE_SHIFT 44 #define NODE0_ADDRSPACE_OFFSET 0x000000000000UL #define NODE1_ADDRSPACE_OFFSET 0x100000000000UL diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h index 7dd4a80e05d6..6f4ac854b12d 100644 --- a/arch/mips/include/asm/unroll.h +++ b/arch/mips/include/asm/unroll.h @@ -28,38 +28,38 @@ BUILD_BUG_ON(!__builtin_constant_p(times)); \ \ switch (times) { \ - case 32: fn(__VA_ARGS__); /* fall through */ \ - case 31: fn(__VA_ARGS__); /* fall through */ \ - case 30: fn(__VA_ARGS__); /* fall through */ \ - case 29: fn(__VA_ARGS__); /* fall through */ \ - case 28: fn(__VA_ARGS__); /* fall through */ \ - case 27: fn(__VA_ARGS__); /* fall through */ \ - case 26: fn(__VA_ARGS__); /* fall through */ \ - case 25: fn(__VA_ARGS__); /* fall through */ \ - case 24: fn(__VA_ARGS__); /* fall through */ \ - case 23: fn(__VA_ARGS__); /* fall through */ \ - case 22: fn(__VA_ARGS__); /* fall through */ \ - case 21: fn(__VA_ARGS__); /* fall through */ \ - case 20: fn(__VA_ARGS__); /* fall through */ \ - case 19: fn(__VA_ARGS__); /* fall through */ \ - case 18: fn(__VA_ARGS__); /* fall through */ \ - case 17: fn(__VA_ARGS__); /* fall through */ \ - case 16: fn(__VA_ARGS__); /* fall through */ \ - case 15: fn(__VA_ARGS__); /* fall through */ \ - case 14: fn(__VA_ARGS__); /* fall through */ \ - case 13: fn(__VA_ARGS__); /* fall through */ \ - case 12: fn(__VA_ARGS__); /* fall through */ \ - case 11: fn(__VA_ARGS__); /* fall through */ \ - case 10: fn(__VA_ARGS__); /* fall through */ \ - case 9: fn(__VA_ARGS__); /* fall through */ \ - case 8: fn(__VA_ARGS__); /* fall through */ \ - case 7: fn(__VA_ARGS__); /* fall through */ \ - case 6: fn(__VA_ARGS__); /* fall through */ \ - case 5: fn(__VA_ARGS__); /* fall through */ \ - case 4: fn(__VA_ARGS__); /* fall through */ \ - case 3: fn(__VA_ARGS__); /* fall through */ \ - case 2: fn(__VA_ARGS__); /* fall through */ \ - case 1: fn(__VA_ARGS__); /* fall through */ \ + case 32: fn(__VA_ARGS__); fallthrough; \ + case 31: fn(__VA_ARGS__); fallthrough; \ + case 30: fn(__VA_ARGS__); fallthrough; \ + case 29: fn(__VA_ARGS__); fallthrough; \ + case 28: fn(__VA_ARGS__); fallthrough; \ + case 27: fn(__VA_ARGS__); fallthrough; \ + case 26: fn(__VA_ARGS__); fallthrough; \ + case 25: fn(__VA_ARGS__); fallthrough; \ + case 24: fn(__VA_ARGS__); fallthrough; \ + case 23: fn(__VA_ARGS__); fallthrough; \ + case 22: fn(__VA_ARGS__); fallthrough; \ + case 21: fn(__VA_ARGS__); fallthrough; \ + case 20: fn(__VA_ARGS__); fallthrough; \ + case 19: fn(__VA_ARGS__); fallthrough; \ + case 18: fn(__VA_ARGS__); fallthrough; \ + case 17: fn(__VA_ARGS__); fallthrough; \ + case 16: fn(__VA_ARGS__); fallthrough; \ + case 15: fn(__VA_ARGS__); fallthrough; \ + case 14: fn(__VA_ARGS__); fallthrough; \ + case 13: fn(__VA_ARGS__); fallthrough; \ + case 12: fn(__VA_ARGS__); fallthrough; \ + case 11: fn(__VA_ARGS__); fallthrough; \ + case 10: fn(__VA_ARGS__); fallthrough; \ + case 9: fn(__VA_ARGS__); fallthrough; \ + case 8: fn(__VA_ARGS__); fallthrough; \ + case 7: fn(__VA_ARGS__); fallthrough; \ + case 6: fn(__VA_ARGS__); fallthrough; \ + case 5: fn(__VA_ARGS__); fallthrough; \ + case 4: fn(__VA_ARGS__); fallthrough; \ + case 3: fn(__VA_ARGS__); fallthrough; \ + case 2: fn(__VA_ARGS__); fallthrough; \ + case 1: fn(__VA_ARGS__); fallthrough; \ case 0: break; \ \ default: \ diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index efce5defcc5c..011eb6bbf81a 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1898,8 +1898,8 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) (base_id >= 64 && base_id < 90) || (base_id >= 128 && base_id < 164) || (base_id >= 192 && base_id < 200) || - (base_id >= 256 && base_id < 274) || - (base_id >= 320 && base_id < 358) || + (base_id >= 256 && base_id < 275) || + (base_id >= 320 && base_id < 361) || (base_id >= 384 && base_id < 574)) break; diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 2f513506a3d5..1dbfb5aadffd 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -239,6 +239,8 @@ static int bmips_boot_secondary(int cpu, struct task_struct *idle) */ static void bmips_init_secondary(void) { + bmips_cpu_setup(); + switch (current_cpu_type()) { case CPU_BMIPS4350: case CPU_BMIPS4380: diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 38aa07ccdbcc..cf788591f091 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1287,6 +1287,18 @@ static int enable_restore_fp_context(int msa) err = own_fpu_inatomic(1); if (msa && !err) { enable_msa(); + /* + * with MSA enabled, userspace can see MSACSR + * and MSA regs, but the values in them are from + * other task before current task, restore them + * from saved fp/msa context + */ + write_msa_csr(current->thread.fpu.msacsr); + /* + * own_fpu_inatomic(1) just restore low 64bit, + * fix the high 64bit + */ + init_msa_upper(); set_thread_flag(TIF_USEDMSA); set_thread_flag(TIF_MSA_CTX_LIVE); } diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 87fa8d8a1031..28c366d307e7 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -486,7 +486,8 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index fc5a6d25f74f..0ef717093262 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1712,7 +1712,11 @@ static void setup_scache(void) printk("MIPS secondary cache %ldkB, %s, linesize %d bytes.\n", scache_size >> 10, way_string[c->scache.ways], c->scache.linesz); + + if (current_cpu_type() == CPU_BMIPS5000) + c->options |= MIPS_CPU_INCLUSIVE_CACHES; } + #else if (!(c->scache.flags & MIPS_CACHE_NOT_PRESENT)) panic("Dunno how to handle MIPS32 / MIPS64 second level cache"); diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c index 1493c49ca47a..55d7b7fd18b6 100644 --- a/arch/mips/oprofile/op_model_mipsxx.c +++ b/arch/mips/oprofile/op_model_mipsxx.c @@ -245,7 +245,6 @@ static int mipsxx_perfcount_handler(void) switch (counters) { #define HANDLE_COUNTER(n) \ - fallthrough; \ case n + 1: \ control = r_c0_perfctrl ## n(); \ counter = r_c0_perfcntr ## n(); \ @@ -256,8 +255,11 @@ static int mipsxx_perfcount_handler(void) handled = IRQ_HANDLED; \ } HANDLE_COUNTER(3) + fallthrough; HANDLE_COUNTER(2) + fallthrough; HANDLE_COUNTER(1) + fallthrough; HANDLE_COUNTER(0) } diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c index 0ecffb65fd6d..b09dc844985a 100644 --- a/arch/mips/sni/a20r.c +++ b/arch/mips/sni/a20r.c @@ -222,8 +222,8 @@ void __init sni_a20r_irq_init(void) irq_set_chip_and_handler(i, &a20r_irq_type, handle_level_irq); sni_hwint = a20r_hwint; change_c0_status(ST0_IM, IE_IRQ0); - if (request_irq(SNI_A20R_IRQ_BASE + 3, sni_isa_irq_handler, 0, "ISA", - NULL)) + if (request_irq(SNI_A20R_IRQ_BASE + 3, sni_isa_irq_handler, + IRQF_SHARED, "ISA", sni_isa_irq_handler)) pr_err("Failed to register ISA interrupt\n"); } diff --git a/arch/nds32/include/asm/irqflags.h b/arch/nds32/include/asm/irqflags.h index fb45ec46bb1b..51ef800bb301 100644 --- a/arch/nds32/include/asm/irqflags.h +++ b/arch/nds32/include/asm/irqflags.h @@ -34,3 +34,8 @@ static inline int arch_irqs_disabled_flags(unsigned long flags) { return !flags; } + +static inline int arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(arch_local_save_flags()); +} diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c index 62bdafbc53f4..9edd7ed7d7bf 100644 --- a/arch/nds32/kernel/fpu.c +++ b/arch/nds32/kernel/fpu.c @@ -45,7 +45,7 @@ void save_fpu(struct task_struct *tsk) : /* no output */ : "r" (&tsk->thread.fpu) : "memory"); - /* fall through */ + fallthrough; case SP32_DP16_reg: asm volatile ("fsdi $fd15, [%0+0x78]\n\t" "fsdi $fd14, [%0+0x70]\n\t" @@ -58,7 +58,7 @@ void save_fpu(struct task_struct *tsk) : /* no output */ : "r" (&tsk->thread.fpu) : "memory"); - /* fall through */ + fallthrough; case SP16_DP8_reg: asm volatile ("fsdi $fd7, [%0+0x38]\n\t" "fsdi $fd6, [%0+0x30]\n\t" @@ -67,7 +67,7 @@ void save_fpu(struct task_struct *tsk) : /* no output */ : "r" (&tsk->thread.fpu) : "memory"); - /* fall through */ + fallthrough; case SP8_DP4_reg: asm volatile ("fsdi $fd3, [%1+0x18]\n\t" "fsdi $fd2, [%1+0x10]\n\t" @@ -108,7 +108,7 @@ void load_fpu(const struct fpu_struct *fpregs) "fldi $fd16, [%0+0x80]\n\t" : /* no output */ : "r" (fpregs)); - /* fall through */ + fallthrough; case SP32_DP16_reg: asm volatile ("fldi $fd15, [%0+0x78]\n\t" "fldi $fd14, [%0+0x70]\n\t" @@ -120,7 +120,7 @@ void load_fpu(const struct fpu_struct *fpregs) "fldi $fd8, [%0+0x40]\n\t" : /* no output */ : "r" (fpregs)); - /* fall through */ + fallthrough; case SP16_DP8_reg: asm volatile ("fldi $fd7, [%0+0x38]\n\t" "fldi $fd6, [%0+0x30]\n\t" @@ -128,7 +128,7 @@ void load_fpu(const struct fpu_struct *fpregs) "fldi $fd4, [%0+0x20]\n\t" : /* no output */ : "r" (fpregs)); - /* fall through */ + fallthrough; case SP8_DP4_reg: asm volatile ("fldi $fd3, [%1+0x18]\n\t" "fldi $fd2, [%1+0x10]\n\t" diff --git a/arch/nds32/kernel/signal.c b/arch/nds32/kernel/signal.c index 330b19fcd990..36e25a410bb0 100644 --- a/arch/nds32/kernel/signal.c +++ b/arch/nds32/kernel/signal.c @@ -316,7 +316,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->uregs[0] = -EINTR; break; } - /* Else, fall through */ + fallthrough; case -ERESTARTNOINTR: regs->uregs[0] = regs->orig_r0; regs->ipc -= 4; @@ -361,7 +361,7 @@ static void do_signal(struct pt_regs *regs) switch (regs->uregs[0]) { case -ERESTART_RESTARTBLOCK: regs->uregs[15] = __NR_restart_syscall; - /* Fall through */ + fallthrough; case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c index 97804f21a40c..c779364f0cd0 100644 --- a/arch/openrisc/kernel/signal.c +++ b/arch/openrisc/kernel/signal.c @@ -244,7 +244,7 @@ int do_signal(struct pt_regs *regs, int syscall) switch (retval) { case -ERESTART_RESTARTBLOCK: restart = -2; - /* Fall through */ + fallthrough; case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 5df5d4cd5d4c..3c037fc96038 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -502,7 +502,7 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) regs->gr[28] = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: check_syscallno_in_delay_branch(regs); break; diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 43875c289723..a52c7abf2ca4 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -437,7 +437,6 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o break; default: - /* Fall through */ break; } @@ -644,12 +643,12 @@ void notrace handle_interruption(int code, struct pt_regs *regs) case 15: /* Data TLB miss fault/Data page fault */ - /* Fall through */ + fallthrough; case 16: /* Non-access instruction TLB miss fault */ /* The instruction TLB entry needed for the target address of the FIC is absent, and hardware can't find it, so we get to cleanup */ - /* Fall through */ + fallthrough; case 17: /* Non-access data TLB miss fault/Non-access data page fault */ /* FIXME: @@ -673,7 +672,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) handle_unaligned(regs); return; } - /* Fall Through */ + fallthrough; case 26: /* PCXL: Data memory access rights trap */ fault_address = regs->ior; @@ -683,7 +682,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) case 19: /* Data memory break trap */ regs->gr[0] |= PSW_X; /* So we can single-step over the trap */ - /* fall thru */ + fallthrough; case 21: /* Page reference trap */ handle_gdb_break(regs, TRAP_HWBKPT); @@ -730,7 +729,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) } mmap_read_unlock(current->mm); } - /* Fall Through */ + fallthrough; case 27: /* Data memory protection ID trap */ if (code == 27 && !user_mode(regs) && diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 4bfe2da9fbe3..716960f5d92e 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -67,7 +67,7 @@ parisc_acctyp(unsigned long code, unsigned int inst) case 0x30000000: /* coproc2 */ if (bit22set(inst)) return VM_WRITE; - /* fall through */ + fallthrough; case 0x0: /* indexed/memory management */ if (bit22set(inst)) { @@ -370,7 +370,7 @@ bad_area: } /* probably address is outside of mapped file */ - /* fall through */ + fallthrough; case 17: /* NA data TLB miss / page fault */ case 18: /* Unaligned access - PCXS only */ signo = SIGBUS; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1f48bbfb3ce9..65bed1fdeaad 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -860,6 +860,18 @@ config PPC_SUBPAGE_PROT If unsure, say N here. +config PPC_PROT_SAO_LPAR + bool "Support PROT_SAO mappings in LPARs" + depends on PPC_BOOK3S_64 + help + This option adds support for PROT_SAO mappings from userspace + inside LPARs on supported CPUs. + + This may cause issues when performing guest migration from + a CPU that supports SAO to one that does not. + + If unsure, say N here. + config PPC_COPRO_BASE bool diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 6de56c3b33c4..495fc0ccb453 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -20,13 +20,9 @@ #define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) #define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC) #define _PAGE_PRIVILEGED 0x00008 /* kernel access only */ - -#define _PAGE_CACHE_CTL 0x00030 /* Bits for the folowing cache modes */ - /* No bits set is normal cacheable memory */ - /* 0x00010 unused, is SAO bit on radix POWER9 */ +#define _PAGE_SAO 0x00010 /* Strong access order */ #define _PAGE_NON_IDEMPOTENT 0x00020 /* non idempotent memory */ #define _PAGE_TOLERANT 0x00030 /* tolerant memory, cache inhibited */ - #define _PAGE_DIRTY 0x00080 /* C: page changed */ #define _PAGE_ACCESSED 0x00100 /* R: page referenced */ /* @@ -828,6 +824,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, return hash__set_pte_at(mm, addr, ptep, pte, percpu); } +#define _PAGE_CACHE_CTL (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT) + #define pgprot_noncached pgprot_noncached static inline pgprot_t pgprot_noncached(pgprot_t prot) { diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index fdddb822d564..32a15dc49e8c 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -9,6 +9,11 @@ #ifndef __ASSEMBLY__ +/* + * Added to include __machine_check_early_realmode_* functions + */ +#include <asm/mce.h> + /* This structure can grow, it's real size is used by head.S code * via the mkdefs mechanism. */ @@ -191,7 +196,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_SPURR LONG_ASM_CONST(0x0000000001000000) #define CPU_FTR_DSCR LONG_ASM_CONST(0x0000000002000000) #define CPU_FTR_VSX LONG_ASM_CONST(0x0000000004000000) -// Free LONG_ASM_CONST(0x0000000008000000) +#define CPU_FTR_SAO LONG_ASM_CONST(0x0000000008000000) #define CPU_FTR_CP_USE_DCBTZ LONG_ASM_CONST(0x0000000010000000) #define CPU_FTR_UNALIGNED_LD_STD LONG_ASM_CONST(0x0000000020000000) #define CPU_FTR_ASYM_SMT LONG_ASM_CONST(0x0000000040000000) @@ -436,7 +441,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | CPU_FTR_ASYM_SMT | \ + CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | \ CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX ) @@ -445,7 +450,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ @@ -456,7 +461,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ @@ -474,7 +479,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 925cf89cbf4b..6bfc87915d5d 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -52,7 +52,7 @@ enum fixed_addresses { FIX_HOLE, /* reserve the top 128K for early debugging purposes */ FIX_EARLY_DEBUG_TOP = FIX_HOLE, - FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128, PAGE_SIZE)/PAGE_SIZE)-1, + FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128K, PAGE_SIZE)/PAGE_SIZE)-1, #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 3a0db7b0b46e..35060be09073 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -200,17 +200,14 @@ static inline bool arch_irqs_disabled(void) #define powerpc_local_irq_pmu_save(flags) \ do { \ raw_local_irq_pmu_save(flags); \ - trace_hardirqs_off(); \ + if (!raw_irqs_disabled_flags(flags)) \ + trace_hardirqs_off(); \ } while(0) #define powerpc_local_irq_pmu_restore(flags) \ do { \ - if (raw_irqs_disabled_flags(flags)) { \ - raw_local_irq_pmu_restore(flags); \ - trace_hardirqs_off(); \ - } else { \ + if (!raw_irqs_disabled_flags(flags)) \ trace_hardirqs_on(); \ - raw_local_irq_pmu_restore(flags); \ - } \ + raw_local_irq_pmu_restore(flags); \ } while(0) #else #define powerpc_local_irq_pmu_save(flags) \ diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index d635b96c7ea6..7355ed05e65e 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -15,11 +15,18 @@ #ifndef __ASSEMBLY__ #include <asm/page.h> +#include <linux/sizes.h> #define KASAN_SHADOW_SCALE_SHIFT 3 +#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_MODULES) && defined(CONFIG_STRICT_KERNEL_RWX) +#define KASAN_KERN_START ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M) +#else +#define KASAN_KERN_START PAGE_OFFSET +#endif + #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - (PAGE_OFFSET >> KASAN_SHADOW_SCALE_SHIFT)) + (KASAN_KERN_START >> KASAN_SHADOW_SCALE_SHIFT)) #define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e020d269416d..10ded83414de 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -58,7 +58,8 @@ #define KVM_ARCH_WANT_MMU_NOTIFIER extern int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + unsigned flags); extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index adf2cda67f9a..89aa8248a57d 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -210,6 +210,9 @@ struct mce_error_info { #define MCE_EVENT_RELEASE true #define MCE_EVENT_DONTRELEASE false +struct pt_regs; +struct notifier_block; + extern void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, uint64_t nip, uint64_t addr, uint64_t phys_addr); @@ -225,5 +228,9 @@ int mce_register_notifier(struct notifier_block *nb); int mce_unregister_notifier(struct notifier_block *nb); #ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb(void); +long __machine_check_early_realmode_p7(struct pt_regs *regs); +long __machine_check_early_realmode_p8(struct pt_regs *regs); +long __machine_check_early_realmode_p9(struct pt_regs *regs); +long __machine_check_early_realmode_p10(struct pt_regs *regs); #endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* __ASM_PPC64_MCE_H__ */ diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index 7c07728af300..7cb6d18f5cd6 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -13,20 +13,43 @@ #include <linux/pkeys.h> #include <asm/cpu_has_feature.h> -#ifdef CONFIG_PPC_MEM_KEYS static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { - return pkey_to_vmflag_bits(pkey); +#ifdef CONFIG_PPC_MEM_KEYS + return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey)); +#else + return ((prot & PROT_SAO) ? VM_SAO : 0); +#endif } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) { - return __pgprot(vmflag_to_pte_pkey_bits(vm_flags)); +#ifdef CONFIG_PPC_MEM_KEYS + return (vm_flags & VM_SAO) ? + __pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) : + __pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags)); +#else + return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0); +#endif } #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) -#endif + +static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) +{ + if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO)) + return false; + if (prot & PROT_SAO) { + if (!cpu_has_feature(CPU_FTR_SAO)) + return false; + if (firmware_has_feature(FW_FEATURE_LPAR) && + !IS_ENABLED(CONFIG_PPC_PROT_SAO_LPAR)) + return false; + } + return true; +} +#define arch_validate_prot arch_validate_prot #endif /* CONFIG_PPC64 */ #endif /* _ASM_POWERPC_MMAN_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 59ee9fa4ae09..6cb8aa357191 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -82,6 +82,8 @@ */ #include <asm/nohash/pte-book3e.h> +#define _PAGE_SAO 0 + #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) /* diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 1e8b2e1ec1db..daec64d41b44 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -40,4 +40,7 @@ static inline bool is_sier_available(void) { return false; } /* To support perf_regs sier update */ extern bool is_sier_available(void); +/* To define perf extended regs mask value */ +extern u64 PERF_REG_EXTENDED_MASK; +#define PERF_REG_EXTENDED_MASK PERF_REG_EXTENDED_MASK #endif diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 86c9eb064b22..f6acabb6c9be 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -62,6 +62,11 @@ struct power_pmu { int *blacklist_ev; /* BHRB entries in the PMU */ int bhrb_nr; + /* + * set this flag with `PERF_PMU_CAP_EXTENDED_REGS` if + * the pmu supports extended perf regs capability + */ + int capabilities; }; /* diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index 3a700351feca..c0c737215b00 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -11,7 +11,7 @@ #include <asm-generic/mman-common.h> -#define PROT_SAO 0x10 /* Unsupported since v5.9 */ +#define PROT_SAO 0x10 /* Strong Access Ordering */ #define MAP_RENAME MAP_ANONYMOUS /* In SunOS terminology */ #define MAP_NORESERVE 0x40 /* don't reserve swap pages */ diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h index f599064dd8dc..bdf5f10f8b9f 100644 --- a/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -48,6 +48,24 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_DSISR, PERF_REG_POWERPC_SIER, PERF_REG_POWERPC_MMCRA, - PERF_REG_POWERPC_MAX, + /* Extended registers */ + PERF_REG_POWERPC_MMCR0, + PERF_REG_POWERPC_MMCR1, + PERF_REG_POWERPC_MMCR2, + PERF_REG_POWERPC_MMCR3, + PERF_REG_POWERPC_SIER2, + PERF_REG_POWERPC_SIER3, + /* Max regs without the extended regs */ + PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1, }; + +#define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1) + +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 */ +#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) - PERF_REG_PMU_MASK) +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 */ +#define PERF_REG_PMU_MASK_31 (((1ULL << (PERF_REG_POWERPC_SIER3 + 1)) - 1) - PERF_REG_PMU_MASK) + +#define PERF_REG_MAX_ISA_300 (PERF_REG_POWERPC_MMCR2 + 1) +#define PERF_REG_MAX_ISA_31 (PERF_REG_POWERPC_SIER3 + 1) #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 3d406a9626e8..2aa89c6b2896 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -72,9 +72,6 @@ extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power9(void); extern void __setup_cpu_power10(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power10(void); -extern long __machine_check_early_realmode_p7(struct pt_regs *regs); -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -542,6 +539,25 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, + { /* Power10 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00800000, + .cpu_name = "POWER10 (raw)", + .cpu_features = CPU_FTRS_POWER10, + .cpu_user_features = COMMON_USER_POWER10, + .cpu_user_features2 = COMMON_USER2_POWER10, + .mmu_features = MMU_FTRS_POWER10, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power10", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power10, + .cpu_restore = __restore_cpu_power10, + .machine_check_early = __machine_check_early_realmode_p10, + .platform = "power10", + }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, .pvr_value = 0x00700000, diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 6f8c0c6b937a..f204ad79b6b5 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -64,10 +64,6 @@ struct dt_cpu_feature { * Set up the base CPU */ -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); -extern long __machine_check_early_realmode_p10(struct pt_regs *regs); - static int hv_mode; static struct { @@ -657,7 +653,7 @@ static struct dt_cpu_feature_match __initdata {"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-utilization-of-resources-register", feat_enable_purr, 0}, {"no-execute", feat_enable, 0}, - /* strong-access-ordering is unused */ + {"strong-access-ordering", feat_enable, CPU_FTR_SAO}, {"cache-inhibited-large-page", feat_enable_large_ci, 0}, {"coprocessor-icswx", feat_enable, 0}, {"hypervisor-virtualization-interrupt", feat_enable_hvi, 0}, diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 33a42e42c56f..733e40eba4eb 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -113,6 +113,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) ld r11,exception_marker@toc(r2) std r11,-16(r10) /* "regshere" marker */ +BEGIN_FTR_SECTION + HMT_MEDIUM +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + /* * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which * would clobber syscall parameters. Also we always enter with IRQs diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 016bd831908e..73a57043ee66 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -548,7 +548,7 @@ void notrace restore_math(struct pt_regs *regs) * are live for the user thread). */ if ((!(msr & MSR_FP)) && should_restore_fp()) - new_msr |= MSR_FP | current->thread.fpexc_mode; + new_msr |= MSR_FP; if ((!(msr & MSR_VEC)) && should_restore_altivec()) new_msr |= MSR_VEC; @@ -559,11 +559,17 @@ void notrace restore_math(struct pt_regs *regs) } if (new_msr) { + unsigned long fpexc_mode = 0; + msr_check_and_set(new_msr); - if (new_msr & MSR_FP) + if (new_msr & MSR_FP) { do_restore_fp(); + // This also covers VSX, because VSX implies FP + fpexc_mode = current->thread.fpexc_mode; + } + if (new_msr & MSR_VEC) do_restore_altivec(); @@ -572,7 +578,7 @@ void notrace restore_math(struct pt_regs *regs) msr_check_and_clear(new_msr); - regs->msr |= new_msr; + regs->msr |= new_msr | fpexc_mode; } } #endif diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index b198b0ff25bc..808ec9fab605 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -311,6 +311,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) min = pvr & 0xFF; break; case 0x004e: /* POWER9 bits 12-15 give chip type */ + case 0x0080: /* POWER10 bit 12 gives SMT8/4 */ maj = (pvr >> 8) & 0x0F; min = pvr & 0xFF; break; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 41fedec69ac3..49db50d1db04 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -834,7 +834,8 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); } diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index d6c1069e9954..ed0c9c43d0cf 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -734,7 +734,8 @@ static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { /* kvm_unmap_hva flushes everything anyways */ kvm_unmap_hva(kvm, start); diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index c0162911f6cb..d426eaf76bb0 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -191,10 +191,17 @@ static bool is_module_segment(unsigned long addr) { if (!IS_ENABLED(CONFIG_MODULES)) return false; +#ifdef MODULES_VADDR + if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M)) + return false; + if (addr > ALIGN(MODULES_END, SZ_256M) - 1) + return false; +#else if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M)) return false; - if (addr >= ALIGN(VMALLOC_END, SZ_256M)) + if (addr > ALIGN(VMALLOC_END, SZ_256M) - 1) return false; +#endif return true; } diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 1da9dbba9217..c663e7ba801f 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -232,6 +232,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) rflags |= HPTE_R_I; else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT) rflags |= (HPTE_R_I | HPTE_R_G); + else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) + rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M); else /* * Add memory coherence if cache inhibited is not set @@ -1115,8 +1117,10 @@ void hash__early_init_mmu_secondary(void) && cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); - if (IS_ENABLED(CONFIG_PPC_MEM_KEYS) && mmu_has_feature(MMU_FTR_PKEY)) +#ifdef CONFIG_PPC_MEM_KEYS + if (mmu_has_feature(MMU_FTR_PKEY)) mtspr(SPRN_UAMOR, default_uamor); +#endif } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 16d09b36fe06..78d61f97371e 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -475,7 +475,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: true_cond = COND_NE; - /* Fall through */ + fallthrough; cond_branch: /* same targets, can avoid doing the test :) */ if (filter[i].jt == filter[i].jf) { diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 78fe34986594..08643cba1494 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1557,9 +1557,16 @@ nocheck: ret = 0; out: if (has_branch_stack(event)) { - power_pmu_bhrb_enable(event); - cpuhw->bhrb_filter = ppmu->bhrb_filter_map( - event->attr.branch_sample_type); + u64 bhrb_filter = -1; + + if (ppmu->bhrb_filter_map) + bhrb_filter = ppmu->bhrb_filter_map( + event->attr.branch_sample_type); + + if (bhrb_filter != -1) { + cpuhw->bhrb_filter = bhrb_filter; + power_pmu_bhrb_enable(event); + } } perf_pmu_enable(event->pmu); @@ -1881,7 +1888,6 @@ static int power_pmu_event_init(struct perf_event *event) int n; int err; struct cpu_hw_events *cpuhw; - u64 bhrb_filter; if (!ppmu) return -ENOENT; @@ -1987,7 +1993,10 @@ static int power_pmu_event_init(struct perf_event *event) err = power_check_constraints(cpuhw, events, cflags, n + 1); if (has_branch_stack(event)) { - bhrb_filter = ppmu->bhrb_filter_map( + u64 bhrb_filter = -1; + + if (ppmu->bhrb_filter_map) + bhrb_filter = ppmu->bhrb_filter_map( event->attr.branch_sample_type); if (bhrb_filter == -1) { @@ -2141,6 +2150,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); + } else if (period) { + /* Account for interrupt in case of invalid SIAR */ + if (perf_event_account_interrupt(event)) + power_pmu_stop(event, 0); } } @@ -2323,6 +2336,7 @@ int register_power_pmu(struct power_pmu *pmu) pmu->name); power_pmu.attr_groups = ppmu->attr_groups; + power_pmu.capabilities |= (ppmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS); #ifdef MSR_HV /* diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index cdb7bfbd157e..6e7e820508df 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1128,6 +1128,15 @@ static struct bin_attribute *if_bin_attrs[] = { NULL, }; +static struct attribute *cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group cpumask_attr_group = { + .attrs = cpumask_attrs, +}; + static struct attribute *if_attrs[] = { &dev_attr_catalog_len.attr, &dev_attr_catalog_version.attr, @@ -1135,7 +1144,6 @@ static struct attribute *if_attrs[] = { &dev_attr_sockets.attr, &dev_attr_chipspersocket.attr, &dev_attr_coresperchip.attr, - &dev_attr_cpumask.attr, NULL, }; @@ -1151,6 +1159,7 @@ static const struct attribute_group *attr_groups[] = { &event_desc_group, &event_long_desc_group, &if_group, + &cpumask_attr_group, NULL, }; diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index a45d694a5d5d..62d0b54086f8 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1289,7 +1289,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem, header->misc = 0; if (cpu_has_feature(CPU_FTR_ARCH_31)) { - switch (IMC_TRACE_RECORD_VAL_HVPR(mem->val)) { + switch (IMC_TRACE_RECORD_VAL_HVPR(be64_to_cpu(READ_ONCE(mem->val)))) { case 0:/* when MSR HV and PR not set in the trace-record */ header->misc |= PERF_RECORD_MISC_GUEST_KERNEL; break; @@ -1297,7 +1297,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem, header->misc |= PERF_RECORD_MISC_GUEST_USER; break; case 2: /* MSR HV is 1 and PR is 0 */ - header->misc |= PERF_RECORD_MISC_HYPERVISOR; + header->misc |= PERF_RECORD_MISC_KERNEL; break; case 3: /* MSR HV is 1 and PR is 1 */ header->misc |= PERF_RECORD_MISC_USER; diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index a213a0aa5d25..8e53f2fc3fe0 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -13,9 +13,11 @@ #include <asm/ptrace.h> #include <asm/perf_regs.h> +u64 PERF_REG_EXTENDED_MASK; + #define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) -#define REG_RESERVED (~((1ULL << PERF_REG_POWERPC_MAX) - 1)) +#define REG_RESERVED (~(PERF_REG_EXTENDED_MASK | PERF_REG_PMU_MASK)) static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_R0, gpr[0]), @@ -69,10 +71,36 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr), }; +/* Function to return the extended register values */ +static u64 get_ext_regs_value(int idx) +{ + switch (idx) { + case PERF_REG_POWERPC_MMCR0: + return mfspr(SPRN_MMCR0); + case PERF_REG_POWERPC_MMCR1: + return mfspr(SPRN_MMCR1); + case PERF_REG_POWERPC_MMCR2: + return mfspr(SPRN_MMCR2); +#ifdef CONFIG_PPC64 + case PERF_REG_POWERPC_MMCR3: + return mfspr(SPRN_MMCR3); + case PERF_REG_POWERPC_SIER2: + return mfspr(SPRN_SIER2); + case PERF_REG_POWERPC_SIER3: + return mfspr(SPRN_SIER3); +#endif + default: return 0; + } +} + u64 perf_reg_value(struct pt_regs *regs, int idx) { - if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX)) - return 0; + u64 perf_reg_extended_max = PERF_REG_POWERPC_MAX; + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + perf_reg_extended_max = PERF_REG_MAX_ISA_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) + perf_reg_extended_max = PERF_REG_MAX_ISA_300; if (idx == PERF_REG_POWERPC_SIER && (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) || @@ -85,6 +113,16 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) IS_ENABLED(CONFIG_PPC32))) return 0; + if (idx >= PERF_REG_POWERPC_MAX && idx < perf_reg_extended_max) + return get_ext_regs_value(idx); + + /* + * If the idx is referring to value beyond the + * supported registers, return 0 with a warning + */ + if (WARN_ON_ONCE(idx >= perf_reg_extended_max)) + return 0; + return regs_get_register(regs, pt_regs_offset[idx]); } diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index f7cff7f36a1c..83148656b524 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -87,6 +87,8 @@ #define POWER10_MMCRA_IFM3 0x00000000C0000000UL #define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { { PM_RUN_CYC_ALT, PM_RUN_CYC }, @@ -397,6 +399,7 @@ static struct power_pmu power10_pmu = { .cache_events = &power10_cache_events, .attr_groups = power10_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power10_pmu(void) @@ -408,6 +411,9 @@ int init_power10_pmu(void) strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10")) return -ENODEV; + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31; + rc = register_power_pmu(&power10_pmu); if (rc) return rc; diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 05dae38b969a..2a57e93a79dc 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -90,6 +90,8 @@ enum { #define POWER9_MMCRA_IFM3 0x00000000C0000000UL #define POWER9_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Nasty Power9 specific hack */ #define PVR_POWER9_CUMULUS 0x00002000 @@ -434,6 +436,7 @@ static struct power_pmu power9_pmu = { .cache_events = &power9_cache_events, .attr_groups = power9_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power9_pmu(void) @@ -457,6 +460,9 @@ int init_power9_pmu(void) } } + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_300; + rc = register_power_pmu(&power9_pmu); if (rc) return rc; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 87737ec86d39..1dc9d3c81872 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -36,7 +36,7 @@ config PPC_BOOK3S_6xx select PPC_HAVE_PMU_SUPPORT select PPC_HAVE_KUEP select PPC_HAVE_KUAP - select HAVE_ARCH_VMAP_STACK + select HAVE_ARCH_VMAP_STACK if !ADB_PMU config PPC_BOOK3S_601 bool "PowerPC 601" diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 77513a80cef9..345ab062b21a 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -1223,7 +1223,7 @@ static void __init pnv_probe_idle_states(void) return; } - if (pvr_version_is(PVR_POWER9)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) pnv_power9_idle_init(); for (i = 0; i < nr_pnv_idle_states; i++) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index c9c25fb0783c..023a4f987bb2 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2705,7 +2705,7 @@ void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe) struct iommu_table *tbl = pe->table_group.tables[0]; int64_t rc; - if (pe->dma_setup_done) + if (!pe->dma_setup_done) return; rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index c6e0d8abf75e..7a974ed6b240 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -107,22 +107,28 @@ static int pseries_cpu_disable(void) */ static void pseries_cpu_die(unsigned int cpu) { - int tries; int cpu_status = 1; unsigned int pcpu = get_hard_smp_processor_id(cpu); + unsigned long timeout = jiffies + msecs_to_jiffies(120000); - for (tries = 0; tries < 25; tries++) { + while (true) { cpu_status = smp_query_cpu_stopped(pcpu); if (cpu_status == QCSS_STOPPED || cpu_status == QCSS_HARDWARE_ERROR) break; - cpu_relax(); + if (time_after(jiffies, timeout)) { + pr_warn("CPU %i (hwid %i) didn't die after 120 seconds\n", + cpu, pcpu); + timeout = jiffies + msecs_to_jiffies(120000); + } + + cond_resched(); } - if (cpu_status != 0) { - printk("Querying DEAD? cpu %i (%i) shows %i\n", - cpu, pcpu, cpu_status); + if (cpu_status == QCSS_HARDWARE_ERROR) { + pr_warn("CPU %i (hwid %i) reported error while dying\n", + cpu, pcpu); } /* Isolation and deallocation are definitely done by diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index f3736fcd98fc..13c86a292c6d 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -184,7 +184,6 @@ static void handle_system_shutdown(char event_modifier) case EPOW_SHUTDOWN_ON_UPS: pr_emerg("Loss of system power detected. System is running on" " UPS/battery. Check RTAS error log for details\n"); - orderly_poweroff(true); break; case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 7b5905529146..df18372861d8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -81,7 +81,7 @@ config RISCV select PCI_DOMAINS_GENERIC if PCI select PCI_MSI if PCI select RISCV_INTC - select RISCV_TIMER + select RISCV_TIMER if RISCV_SBI select SPARSEMEM_STATIC if 32BIT select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6c88148f1b9b..8a55f6156661 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -12,6 +12,7 @@ config SOC_SIFIVE config SOC_VIRT bool "QEMU Virt Machine" + select CLINT_TIMER if RISCV_M_MODE select POWER_RESET select POWER_RESET_SYSCON select POWER_RESET_SYSCON_POWEROFF @@ -24,6 +25,7 @@ config SOC_VIRT config SOC_KENDRYTE bool "Kendryte K210 SoC" depends on !MMU + select CLINT_TIMER if RISCV_M_MODE select SERIAL_SIFIVE if TTY select SERIAL_SIFIVE_CONSOLE if TTY select SIFIVE_PLIC diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig index f27596e9663e..e046a0babde4 100644 --- a/arch/riscv/configs/nommu_virt_defconfig +++ b/arch/riscv/configs/nommu_virt_defconfig @@ -26,6 +26,7 @@ CONFIG_EXPERT=y CONFIG_SLOB=y # CONFIG_SLAB_MERGE_DEFAULT is not set # CONFIG_MMU is not set +CONFIG_SOC_VIRT=y CONFIG_MAXPHYSMEM_2GB=y CONFIG_SMP=y CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0" @@ -49,7 +50,6 @@ CONFIG_VIRTIO_BLK=y # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set # CONFIG_LDISC_AUTOLOAD is not set -# CONFIG_DEVMEM is not set CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y @@ -57,16 +57,13 @@ CONFIG_SERIAL_8250_NR_UARTS=1 CONFIG_SERIAL_8250_RUNTIME_UARTS=1 CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set # CONFIG_HWMON is not set -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set # CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y -CONFIG_SIFIVE_PLIC=y -# CONFIG_VALIDATE_FS_PARSER is not set CONFIG_EXT2_FS=y # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 3a55f0e00d6c..2c2cda6cc1c5 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -14,6 +14,7 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y +CONFIG_SOC_SIFIVE=y CONFIG_SOC_VIRT=y CONFIG_ARCH_RV32I=y CONFIG_SMP=y @@ -62,6 +63,8 @@ CONFIG_HVC_RISCV_SBI=y CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_SPI=y +CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y @@ -77,6 +80,8 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y +CONFIG_MMC=y +CONFIG_MMC_SPI=y CONFIG_RTC_CLASS=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h deleted file mode 100644 index a279b17a6aad..000000000000 --- a/arch/riscv/include/asm/clint.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_RISCV_CLINT_H -#define _ASM_RISCV_CLINT_H 1 - -#include <linux/io.h> -#include <linux/smp.h> - -#ifdef CONFIG_RISCV_M_MODE -extern u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void); - -static inline void clint_send_ipi_single(unsigned long hartid) -{ - writel(1, clint_ipi_base + hartid); -} - -static inline void clint_send_ipi_mask(const struct cpumask *mask) -{ - int cpu; - - for_each_cpu(cpu, mask) - clint_send_ipi_single(cpuid_to_hartid_map(cpu)); -} - -static inline void clint_clear_ipi(unsigned long hartid) -{ - writel(0, clint_ipi_base + hartid); -} -#else /* CONFIG_RISCV_M_MODE */ -#define clint_init_boot_cpu() do { } while (0) - -/* stubs to for code is only reachable under IS_ENABLED(CONFIG_RISCV_M_MODE): */ -void clint_send_ipi_single(unsigned long hartid); -void clint_send_ipi_mask(const struct cpumask *hartid_mask); -void clint_clear_ipi(unsigned long hartid); -#endif /* CONFIG_RISCV_M_MODE */ - -#endif /* _ASM_RISCV_CLINT_H */ diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h index 6dfd2a1446d5..df1f7c4cd433 100644 --- a/arch/riscv/include/asm/smp.h +++ b/arch/riscv/include/asm/smp.h @@ -15,6 +15,11 @@ struct seq_file; extern unsigned long boot_cpu_hartid; +struct riscv_ipi_ops { + void (*ipi_inject)(const struct cpumask *target); + void (*ipi_clear)(void); +}; + #ifdef CONFIG_SMP /* * Mapping between linux logical cpu index and hartid. @@ -40,6 +45,12 @@ void arch_send_call_function_single_ipi(int cpu); int riscv_hartid_to_cpuid(int hartid); void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out); +/* Set custom IPI operations */ +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops); + +/* Clear IPI for current CPU */ +void riscv_clear_ipi(void); + /* Secondary hart entry */ asmlinkage void smp_callin(void); @@ -81,6 +92,14 @@ static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in, cpumask_set_cpu(boot_cpu_hartid, out); } +static inline void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ +} + +static inline void riscv_clear_ipi(void) +{ +} + #endif /* CONFIG_SMP */ #if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP) diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index bad2a7c2cda5..a3fb85d505d4 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -7,41 +7,27 @@ #define _ASM_RISCV_TIMEX_H #include <asm/csr.h> -#include <asm/mmio.h> typedef unsigned long cycles_t; -extern u64 __iomem *riscv_time_val; -extern u64 __iomem *riscv_time_cmp; - -#ifdef CONFIG_64BIT -#define mmio_get_cycles() readq_relaxed(riscv_time_val) -#else -#define mmio_get_cycles() readl_relaxed(riscv_time_val) -#define mmio_get_cycles_hi() readl_relaxed(((u32 *)riscv_time_val) + 1) -#endif - static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIME); - return mmio_get_cycles(); + return csr_read(CSR_TIME); } #define get_cycles get_cycles +static inline u32 get_cycles_hi(void) +{ + return csr_read(CSR_TIMEH); +} +#define get_cycles_hi get_cycles_hi + #ifdef CONFIG_64BIT static inline u64 get_cycles64(void) { return get_cycles(); } #else /* CONFIG_64BIT */ -static inline u32 get_cycles_hi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIMEH); - return mmio_get_cycles_hi(); -} - static inline u64 get_cycles64(void) { u32 hi, lo; diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index a5287ab9f7f2..dc93710f0b2f 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -31,7 +31,7 @@ obj-y += cacheinfo.o obj-y += patch.o obj-$(CONFIG_MMU) += vdso.o vdso/ -obj-$(CONFIG_RISCV_M_MODE) += clint.o traps_misaligned.o +obj-$(CONFIG_RISCV_M_MODE) += traps_misaligned.o obj-$(CONFIG_FPU) += fpu.o obj-$(CONFIG_SMP) += smpboot.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/riscv/kernel/clint.c b/arch/riscv/kernel/clint.c deleted file mode 100644 index 3647980d14c3..000000000000 --- a/arch/riscv/kernel/clint.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2019 Christoph Hellwig. - */ - -#include <linux/io.h> -#include <linux/of_address.h> -#include <linux/types.h> -#include <asm/clint.h> -#include <asm/csr.h> -#include <asm/timex.h> -#include <asm/smp.h> - -/* - * This is the layout used by the SiFive clint, which is also shared by the qemu - * virt platform, and the Kendryte KD210 at least. - */ -#define CLINT_IPI_OFF 0 -#define CLINT_TIME_CMP_OFF 0x4000 -#define CLINT_TIME_VAL_OFF 0xbff8 - -u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void) -{ - struct device_node *np; - void __iomem *base; - - np = of_find_compatible_node(NULL, NULL, "riscv,clint0"); - if (!np) { - panic("clint not found"); - return; - } - - base = of_iomap(np, 0); - if (!base) - panic("could not map CLINT"); - - clint_ipi_base = base + CLINT_IPI_OFF; - riscv_time_cmp = base + CLINT_TIME_CMP_OFF; - riscv_time_val = base + CLINT_TIME_VAL_OFF; - - clint_clear_ipi(boot_cpu_hartid); -} diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index f383ef5672b2..226ccce0f9e0 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -547,6 +547,18 @@ static inline long sbi_get_firmware_version(void) return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION); } +static void sbi_send_cpumask_ipi(const struct cpumask *target) +{ + struct cpumask hartid_mask; + + riscv_cpuid_to_hartid_mask(target, &hartid_mask); + + sbi_send_ipi(cpumask_bits(&hartid_mask)); +} + +static struct riscv_ipi_ops sbi_ipi_ops = { + .ipi_inject = sbi_send_cpumask_ipi +}; int __init sbi_init(void) { @@ -587,5 +599,7 @@ int __init sbi_init(void) __sbi_rfence = __sbi_rfence_v01; } + riscv_set_ipi_ops(&sbi_ipi_ops); + return 0; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index f04373be54a6..2c6dd329312b 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -18,7 +18,6 @@ #include <linux/swiotlb.h> #include <linux/smp.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/setup.h> #include <asm/sections.h> @@ -79,7 +78,6 @@ void __init setup_arch(char **cmdline_p) #else unflatten_device_tree(); #endif - clint_init_boot_cpu(); #ifdef CONFIG_SWIOTLB swiotlb_init(1); diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 17ba190e84a5..e996e08f1061 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -250,7 +250,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->a0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->a0 = regs->orig_a0; regs->epc -= 0x4; diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 554b0fb47060..ea028d9e0d24 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -18,7 +18,6 @@ #include <linux/delay.h> #include <linux/irq_work.h> -#include <asm/clint.h> #include <asm/sbi.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> @@ -86,9 +85,25 @@ static void ipi_stop(void) wait_for_interrupt(); } +static struct riscv_ipi_ops *ipi_ops; + +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ + ipi_ops = ops; +} +EXPORT_SYMBOL_GPL(riscv_set_ipi_ops); + +void riscv_clear_ipi(void) +{ + if (ipi_ops && ipi_ops->ipi_clear) + ipi_ops->ipi_clear(); + + csr_clear(CSR_IP, IE_SIE); +} +EXPORT_SYMBOL_GPL(riscv_clear_ipi); + static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) { - struct cpumask hartid_mask; int cpu; smp_mb__before_atomic(); @@ -96,33 +111,22 @@ static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - riscv_cpuid_to_hartid_mask(mask, &hartid_mask); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(&hartid_mask)); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(mask); else - clint_send_ipi_mask(mask); + pr_warn("SMP: IPI inject method not available\n"); } static void send_ipi_single(int cpu, enum ipi_message_type op) { - int hartid = cpuid_to_hartid_map(cpu); - smp_mb__before_atomic(); set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(cpumask_of(hartid))); - else - clint_send_ipi_single(hartid); -} - -static inline void clear_ipi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - csr_clear(CSR_IP, IE_SIE); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(cpumask_of(cpu)); else - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + pr_warn("SMP: IPI inject method not available\n"); } #ifdef CONFIG_IRQ_WORK @@ -140,7 +144,7 @@ void handle_IPI(struct pt_regs *regs) irq_enter(); - clear_ipi(); + riscv_clear_ipi(); while (true) { unsigned long ops; diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 356825a57551..96167d55ed98 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -24,7 +24,6 @@ #include <linux/of.h> #include <linux/sched/task_stack.h> #include <linux/sched/mm.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/irq.h> #include <asm/mmu_context.h> @@ -147,8 +146,7 @@ asmlinkage __visible void smp_callin(void) struct mm_struct *mm = &init_mm; unsigned int curr_cpuid = smp_processor_id(); - if (!IS_ENABLED(CONFIG_RISCV_SBI)) - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + riscv_clear_ipi(); /* All kernel threads share the same mm context. */ mmgrab(mm); diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index bc5f2204693f..579575f9cdae 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -1020,7 +1020,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_zext64(dst, ctx); break; } - /* Fallthrough. */ + fallthrough; case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_SUB | BPF_X: @@ -1079,7 +1079,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case 16: emit(rv_slli(lo(rd), lo(rd), 16), ctx); emit(rv_srli(lo(rd), lo(rd), 16), ctx); - /* Fallthrough. */ + fallthrough; case 32: if (!ctx->prog->aux->verifier_zext) emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 3d86e12e8e3c..b29fcc66ec39 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -30,7 +30,7 @@ config GENERIC_BUG_RELATIVE_POINTERS def_bool y config GENERIC_LOCKBREAK - def_bool y if PREEMPTTION + def_bool y if PREEMPTION config PGSTE def_bool y if KVM diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 0cf9a82326a8..7228aabe9da6 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -626,6 +626,7 @@ CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS_INODE64=y CONFIG_HUGETLBFS=y CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m @@ -807,6 +808,7 @@ CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 # CONFIG_RCU_TRACE is not set CONFIG_LATENCYTOP=y @@ -818,6 +820,7 @@ CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_S390_PTDUMP=y CONFIG_NOTIFIER_ERROR_INJECTION=m @@ -829,6 +832,7 @@ CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y +CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 5df9759e8ff6..fab03b7a6932 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -617,6 +617,7 @@ CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS_INODE64=y CONFIG_HUGETLBFS=y CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m @@ -763,6 +764,7 @@ CONFIG_PANIC_ON_OOPS=y CONFIG_TEST_LOCKUP=m CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y CONFIG_BOOTTIME_TRACING=y @@ -771,6 +773,7 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_S390_PTDUMP=y CONFIG_LKDTM=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 4091c50449cd..8f67c55625f9 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -74,5 +74,6 @@ CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 +# CONFIG_RCU_TRACE is not set # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index 50b4ce8cddfd..918f0ba4f4d2 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -29,7 +29,7 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ old__, new__, prev__; \ pcp_op_T__ *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ prev__ = *ptr__; \ do { \ @@ -37,7 +37,7 @@ new__ = old__ op (val); \ prev__ = cmpxchg(ptr__, old__, new__); \ } while (prev__ != old__); \ - preempt_enable(); \ + preempt_enable_notrace(); \ new__; \ }) @@ -68,7 +68,7 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ if (__builtin_constant_p(val__) && \ ((szcast)val__ > -129) && ((szcast)val__ < 128)) { \ @@ -84,7 +84,7 @@ : [val__] "d" (val__) \ : "cc"); \ } \ - preempt_enable(); \ + preempt_enable_notrace(); \ } #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int) @@ -95,14 +95,14 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ asm volatile( \ op " %[old__],%[val__],%[ptr__]\n" \ : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ : [val__] "d" (val__) \ : "cc"); \ - preempt_enable(); \ + preempt_enable_notrace(); \ old__ + val__; \ }) @@ -114,14 +114,14 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ asm volatile( \ op " %[old__],%[val__],%[ptr__]\n" \ : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ : [val__] "d" (val__) \ : "cc"); \ - preempt_enable(); \ + preempt_enable_notrace(); \ } #define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lan") @@ -136,10 +136,10 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ ret__; \ pcp_op_T__ *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ ret__ = cmpxchg(ptr__, oval, nval); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) @@ -152,10 +152,10 @@ ({ \ typeof(pcp) *ptr__; \ typeof(pcp) ret__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ ret__ = xchg(ptr__, nval); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) @@ -171,11 +171,11 @@ typeof(pcp1) *p1__; \ typeof(pcp2) *p2__; \ int ret__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ p1__ = raw_cpu_ptr(&(pcp1)); \ p2__ = raw_cpu_ptr(&(pcp2)); \ ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 88bb42ca5008..c73f50649e7e 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -33,14 +33,13 @@ void enabled_wait(void) PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; clear_cpu_flag(CIF_NOHZ_DELAY); - trace_cpu_idle_rcuidle(1, smp_processor_id()); local_irq_save(flags); /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); local_irq_restore(flags); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); /* Account time spent with enabled wait psw loaded as idle time. */ + /* XXX seqcount has tracepoints that require RCU */ write_seqcount_begin(&idle->seqcount); idle_time = idle->clock_idle_exit - idle->clock_idle_enter; idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 11d2f7d05f91..a76dd27fb2e8 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -1268,7 +1268,6 @@ static bool is_ri_cb_valid(struct runtime_instr_cb *cb) cb->pc == 1 && cb->qc == 0 && cb->reserved2 == 0 && - cb->key == PAGE_DEFAULT_KEY && cb->reserved3 == 0 && cb->reserved4 == 0 && cb->reserved5 == 0 && @@ -1330,7 +1329,11 @@ static int s390_runtime_instr_set(struct task_struct *target, kfree(data); return -EINVAL; } - + /* + * Override access key in any case, since user space should + * not be able to set it, nor should it care about it. + */ + ri_cb.key = PAGE_DEFAULT_KEY >> 4; preempt_disable(); if (!target->thread.ri_cb) target->thread.ri_cb = data; diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 125c7f6e8715..1788a5454b6f 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -57,7 +57,7 @@ static void init_runtime_instr_cb(struct runtime_instr_cb *cb) cb->k = 1; cb->ps = 1; cb->pc = 1; - cb->key = PAGE_DEFAULT_KEY; + cb->key = PAGE_DEFAULT_KEY >> 4; cb->v = 1; } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 1aed1a4dfc2d..eddf71c22875 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -402,6 +402,7 @@ static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end, pud = vmem_crst_alloc(_REGION3_ENTRY_EMPTY); if (!pud) goto out; + p4d_populate(&init_mm, p4d, pud); } ret = modify_pud_table(p4d, addr, next, add, direct); if (ret) diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 3902c9f6f2d6..4b62d6b55024 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -672,6 +672,19 @@ int zpci_disable_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_disable_device); +void zpci_remove_device(struct zpci_dev *zdev) +{ + struct zpci_bus *zbus = zdev->zbus; + struct pci_dev *pdev; + + pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (pdev) { + if (pdev->is_virtfn) + return zpci_remove_virtfn(pdev, zdev->vfn); + pci_stop_and_remove_bus_device_locked(pdev); + } +} + int zpci_create_device(struct zpci_dev *zdev) { int rc; @@ -716,13 +729,8 @@ void zpci_release_device(struct kref *kref) { struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); - if (zdev->zbus->bus) { - struct pci_dev *pdev; - - pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); - if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); - } + if (zdev->zbus->bus) + zpci_remove_device(zdev); switch (zdev->state) { case ZPCI_FN_STATE_ONLINE: diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 642a99384688..5967f3014156 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -132,13 +132,14 @@ static int zpci_bus_link_virtfn(struct pci_dev *pdev, { int rc; - virtfn->physfn = pci_dev_get(pdev); rc = pci_iov_sysfs_link(pdev, virtfn, vfid); - if (rc) { - pci_dev_put(pdev); - virtfn->physfn = NULL; + if (rc) return rc; - } + + virtfn->is_virtfn = 1; + virtfn->multifunction = 0; + virtfn->physfn = pci_dev_get(pdev); + return 0; } @@ -151,9 +152,9 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ int rc = 0; - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; - WARN_ON(vfid < 0); + if (!zbus->multifunction) + return 0; + /* If the parent PF for the given VF is also configured in the * instance, it must be on the same zbus. * We can then identify the parent PF by checking what @@ -165,11 +166,17 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, zdev = zbus->function[i]; if (zdev && zdev->is_physfn) { pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (!pdev) + continue; cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); if (cand_devfn == virtfn->devfn) { rc = zpci_bus_link_virtfn(pdev, virtfn, vfid); + /* balance pci_get_slot() */ + pci_dev_put(pdev); break; } + /* balance pci_get_slot() */ + pci_dev_put(pdev); } } return rc; @@ -178,12 +185,23 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, static inline int zpci_bus_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) { - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; return 0; } #endif +void pcibios_bus_add_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = to_zpci(pdev); + + /* + * With pdev->no_vf_scan the common PCI probing code does not + * perform PF/VF linking. + */ + if (zdev->vfn) + zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn); + +} + static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) { struct pci_bus *bus; @@ -214,20 +232,10 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) } pdev = pci_scan_single_device(bus, zdev->devfn); - if (pdev) { - if (!zdev->is_physfn) { - rc = zpci_bus_setup_virtfn(zbus, pdev, zdev->vfn); - if (rc) - goto failed_with_pdev; - } + if (pdev) pci_bus_add_device(pdev); - } - return 0; -failed_with_pdev: - pci_stop_and_remove_bus_device(pdev); - pci_dev_put(pdev); - return rc; + return 0; } static void zpci_bus_add_devices(struct zpci_bus *zbus) diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index 89be3c354b7b..4972433df458 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -29,3 +29,16 @@ static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus, return (devfn >= ZPCI_FUNCTIONS_PER_BUS) ? NULL : zbus->function[devfn]; } + +#ifdef CONFIG_PCI_IOV +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) +{ + + pci_lock_rescan_remove(); + /* Linux' vfid's start at 0 vfn at 1 */ + pci_iov_remove_virtfn(pdev->physfn, vfn - 1); + pci_unlock_rescan_remove(); +} +#else /* CONFIG_PCI_IOV */ +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) {} +#endif /* CONFIG_PCI_IOV */ diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index fdebd286f402..9a3a291cad43 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -92,6 +92,9 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) ret = clp_add_pci_device(ccdf->fid, ccdf->fh, 1); break; } + /* the configuration request may be stale */ + if (zdev->state != ZPCI_FN_STATE_STANDBY) + break; zdev->fh = ccdf->fh; zdev->state = ZPCI_FN_STATE_CONFIGURED; ret = zpci_enable_device(zdev); @@ -118,7 +121,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (!zdev) break; if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); ret = zpci_disable_device(zdev); if (ret) @@ -137,7 +140,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) /* Give the driver a hint that the function is * already unusable. */ pdev->error_state = pci_channel_io_perm_failure; - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); } zdev->state = ZPCI_FN_STATE_STANDBY; diff --git a/arch/sh/drivers/platform_early.c b/arch/sh/drivers/platform_early.c index f3dc3f25b3ff..143747c45206 100644 --- a/arch/sh/drivers/platform_early.c +++ b/arch/sh/drivers/platform_early.c @@ -246,7 +246,7 @@ static int __init sh_early_platform_driver_probe_id(char *class_str, case EARLY_PLATFORM_ID_ERROR: pr_warn("%s: unable to parse %s parameter\n", class_str, epdrv->pdrv->driver.name); - /* fall-through */ + fallthrough; case EARLY_PLATFORM_ID_UNSET: match = NULL; break; diff --git a/arch/sh/kernel/disassemble.c b/arch/sh/kernel/disassemble.c index 08e1af63edd9..34e25a439c81 100644 --- a/arch/sh/kernel/disassemble.c +++ b/arch/sh/kernel/disassemble.c @@ -486,7 +486,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) pr_cont("xd%d", rn & ~1); break; } - /* else, fall through */ + fallthrough; case D_REG_N: pr_cont("dr%d", rn); break; @@ -495,7 +495,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) pr_cont("xd%d", rm & ~1); break; } - /* else, fall through */ + fallthrough; case D_REG_M: pr_cont("dr%d", rm); break; diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c index 0d5f3c9d52f3..e4147efa9ec6 100644 --- a/arch/sh/kernel/kgdb.c +++ b/arch/sh/kernel/kgdb.c @@ -266,7 +266,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, ptr = &remcomInBuffer[1]; if (kgdb_hex2long(&ptr, &addr)) linux_regs->pc = addr; - /* fallthrough */ + fallthrough; case 'D': case 'k': atomic_set(&kgdb_cpu_doing_single_step, -1); diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index a0fbb8427b39..4fe3f00137bc 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -418,7 +418,7 @@ handle_syscall_restart(unsigned long save_r0, struct pt_regs *regs, case -ERESTARTSYS: if (!(sa->sa_flags & SA_RESTART)) goto no_system_call_restart; - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->regs[0] = save_r0; regs->pc -= instruction_size(__raw_readw(regs->pc - 4)); diff --git a/arch/sparc/kernel/auxio_64.c b/arch/sparc/kernel/auxio_64.c index 4843f48bfe85..774a82b0c649 100644 --- a/arch/sparc/kernel/auxio_64.c +++ b/arch/sparc/kernel/auxio_64.c @@ -87,7 +87,6 @@ void auxio_set_lte(int on) __auxio_sbus_set_lte(on); break; case AUXIO_TYPE_EBUS: - /* FALL-THROUGH */ default: break; } diff --git a/arch/sparc/kernel/central.c b/arch/sparc/kernel/central.c index bfae98ab8638..23f8838dd96e 100644 --- a/arch/sparc/kernel/central.c +++ b/arch/sparc/kernel/central.c @@ -55,7 +55,7 @@ static int clock_board_calc_nslots(struct clock_board *p) else return 5; } - /* Fallthrough */ + fallthrough; default: return 4; } diff --git a/arch/sparc/kernel/kgdb_32.c b/arch/sparc/kernel/kgdb_32.c index 7580775a14b9..58ad3f7de1fb 100644 --- a/arch/sparc/kernel/kgdb_32.c +++ b/arch/sparc/kernel/kgdb_32.c @@ -122,7 +122,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, linux_regs->pc = addr; linux_regs->npc = addr + 4; } - /* fall through */ + fallthrough; case 'D': case 'k': diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c index 5d6c2d287e85..177746ae2c81 100644 --- a/arch/sparc/kernel/kgdb_64.c +++ b/arch/sparc/kernel/kgdb_64.c @@ -148,7 +148,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, linux_regs->tpc = addr; linux_regs->tnpc = addr + 4; } - /* fall through */ + fallthrough; case 'D': case 'k': diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index c0886b400dad..2a12c86af956 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -359,7 +359,7 @@ int __init pcr_arch_init(void) * counter overflow interrupt so we can't make use of * their hardware currently. */ - /* fallthrough */ + fallthrough; default: err = -ENODEV; goto out_unregister; diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c index da8902295c8c..3df960c137f7 100644 --- a/arch/sparc/kernel/prom_32.c +++ b/arch/sparc/kernel/prom_32.c @@ -224,7 +224,7 @@ void __init of_console_init(void) case PROMDEV_TTYB: skip = 1; - /* FALLTHRU */ + fallthrough; case PROMDEV_TTYA: type = "serial"; diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index e2c6f0abda00..e9695a06492f 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -646,7 +646,7 @@ static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs case ERESTARTSYS: if (!(sa->sa_flags & SA_RESTART)) goto no_system_call_restart; - /* fallthrough */ + fallthrough; case ERESTARTNOINTR: regs->u_regs[UREG_I0] = orig_i0; regs->tpc -= 4; @@ -686,7 +686,7 @@ void do_signal32(struct pt_regs * regs) regs->tpc -= 4; regs->tnpc -= 4; pt_regs_clear_syscall(regs); - /* fall through */ + fallthrough; case ERESTART_RESTARTBLOCK: regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->tpc -= 4; diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index f1f8c8ebe641..d0e0025ee3ba 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -440,7 +440,7 @@ static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs, case ERESTARTSYS: if (!(sa->sa_flags & SA_RESTART)) goto no_system_call_restart; - /* fallthrough */ + fallthrough; case ERESTARTNOINTR: regs->u_regs[UREG_I0] = orig_i0; regs->pc -= 4; @@ -506,7 +506,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) regs->pc -= 4; regs->npc -= 4; pt_regs_clear_syscall(regs); - /* fall through */ + fallthrough; case ERESTART_RESTARTBLOCK: regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->pc -= 4; diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 6937339a272c..255264bcb46a 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -461,7 +461,7 @@ static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs, case ERESTARTSYS: if (!(sa->sa_flags & SA_RESTART)) goto no_system_call_restart; - /* fallthrough */ + fallthrough; case ERESTARTNOINTR: regs->u_regs[UREG_I0] = orig_i0; regs->tpc -= 4; @@ -532,7 +532,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) regs->tpc -= 4; regs->tnpc -= 4; pt_regs_clear_syscall(regs); - /* fall through */ + fallthrough; case ERESTART_RESTARTBLOCK: regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->tpc -= 4; diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c index 72e560ef4a09..d5beec856146 100644 --- a/arch/sparc/math-emu/math_32.c +++ b/arch/sparc/math-emu/math_32.c @@ -359,7 +359,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs) *pfsr |= (6 << 14); return 0; /* simulate invalid_fp_register exception */ } - /* fall through */ + fallthrough; case 2: if (freg & 1) { /* doublewords must have bit 5 zeroed */ *pfsr |= (6 << 14); @@ -380,7 +380,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs) *pfsr |= (6 << 14); return 0; /* simulate invalid_fp_register exception */ } - /* fall through */ + fallthrough; case 2: if (freg & 1) { /* doublewords must have bit 5 zeroed */ *pfsr |= (6 << 14); @@ -408,13 +408,13 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs) *pfsr |= (6 << 14); return 0; /* simulate invalid_fp_register exception */ } - /* fall through */ + fallthrough; case 2: if (freg & 1) { /* doublewords must have bit 5 zeroed */ *pfsr |= (6 << 14); return 0; } - /* fall through */ + fallthrough; case 1: rd = (void *)&fregs[freg]; break; diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c index c8eabb973b86..b1dbf2fa8c0a 100644 --- a/arch/sparc/net/bpf_jit_comp_32.c +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -491,7 +491,7 @@ void bpf_jit_compile(struct bpf_prog *fp) } else { emit_loadimm(K, r_A); } - /* Fallthrough */ + fallthrough; case BPF_RET | BPF_A: if (seen_or_pass0) { if (i != flen - 1) { diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 3d57c71c532e..88cd9b5c1b74 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -70,7 +70,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) PT_REGS_SYSCALL_RET(regs) = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: PT_REGS_RESTART_SYSCALL(regs); PT_REGS_ORIG_SYSCALL(regs) = PT_REGS_SYSCALL_NR(regs); diff --git a/arch/x86/boot/cmdline.c b/arch/x86/boot/cmdline.c index 4ff01176c1cc..21d56ae83cdf 100644 --- a/arch/x86/boot/cmdline.c +++ b/arch/x86/boot/cmdline.c @@ -54,7 +54,7 @@ int __cmdline_find_option(unsigned long cmdline_ptr, const char *option, char *b /* else */ state = st_wordcmp; opptr = option; - /* fall through */ + fallthrough; case st_wordcmp: if (c == '=' && !*opptr) { @@ -129,7 +129,7 @@ int __cmdline_find_option_bool(unsigned long cmdline_ptr, const char *option) state = st_wordcmp; opptr = option; wstart = pos; - /* fall through */ + fallthrough; case st_wordcmp: if (!*opptr) diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 0048269180d5..dde7cb3724df 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -178,7 +178,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size, } *size = 0; } - /* Fall through */ + fallthrough; default: /* * If w/o offset, only size specified, memmap=nn[KMG] has the diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 39e592d0e0b4..e478e40fbe5a 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -30,12 +30,9 @@ #define STATIC static /* - * Use normal definitions of mem*() from string.c. There are already - * included header files which expect a definition of memset() and by - * the time we define memset macro, it is too late. + * Provide definitions of memzero and memmove as some of the decompressors will + * try to define their own functions if these are not defined as macros. */ -#undef memcpy -#undef memset #define memzero(s, n) memset((s), 0, (n)) #define memmove memmove diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 995f7b7ad512..a232da487cd2 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -11,10 +11,7 @@ void *memcpy(void *dst, const void *src, size_t len); void *memset(void *dst, int c, size_t len); int memcmp(const void *s1, const void *s2, size_t len); -/* - * Access builtin version by default. If one needs to use optimized version, - * do "undef memcpy" in .c file and link against right string.c - */ +/* Access builtin version by default. */ #define memcpy(d,s,l) __builtin_memcpy(d,s,l) #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 98e4d8886f11..ae9b0d4615b3 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -374,12 +374,14 @@ For 32-bit we have the following conventions - kernel is built with * Fetch the per-CPU GSBASE value for this processor and put it in @reg. * We normally use %gs for accessing per-CPU data, but we are setting up * %gs here and obviously can not use %gs itself to access per-CPU data. + * + * Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and + * may not restore the host's value until the CPU returns to userspace. + * Thus the kernel would consume a guest's TSC_AUX if an NMI arrives + * while running KVM's run loop. */ .macro GET_PERCPU_BASE reg:req - ALTERNATIVE \ - "LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \ - "RDPID \reg", \ - X86_FEATURE_RDPID + LOAD_CPU_AND_NODE_SEG_LIMIT \reg andq $VDSO_CPUNODE_MASK, \reg movq __per_cpu_offset(, \reg, 8), \reg .endm diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index 3a07ce3ec70b..f1f96d4d8cd6 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -29,11 +29,6 @@ SYM_CODE_START_NOALIGN(\name) SYM_CODE_END(\name) .endm -#ifdef CONFIG_TRACE_IRQFLAGS - THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1 - THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1 -#endif - #ifdef CONFIG_PREEMPTION THUNK preempt_schedule_thunk, preempt_schedule THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 50963472ee85..31e6887d24f1 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4682,7 +4682,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_CORE2_MEROM: x86_add_quirk(intel_clovertown_quirk); - /* fall through */ + fallthrough; case INTEL_FAM6_CORE2_MEROM_L: case INTEL_FAM6_CORE2_PENRYN: @@ -5062,7 +5062,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SKYLAKE_X: pmem = true; - /* fall through */ + fallthrough; case INTEL_FAM6_SKYLAKE_L: case INTEL_FAM6_SKYLAKE: case INTEL_FAM6_KABYLAKE_L: @@ -5114,7 +5114,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_ICELAKE_D: pmem = true; - /* fall through */ + fallthrough; case INTEL_FAM6_ICELAKE_L: case INTEL_FAM6_ICELAKE: case INTEL_FAM6_TIGERLAKE_L: diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 63f58bdf556c..8961653c5dd2 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1268,7 +1268,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) ret = X86_BR_ZERO_CALL; break; } - /* fall through */ + fallthrough; case 0x9a: /* call far absolute */ ret = X86_BR_CALL; break; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index cb94ba86efd2..6a4ca27b2c9e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -390,6 +390,18 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(gt_requests, "event=0x03"), + INTEL_UNCORE_EVENT_DESC(gt_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(gt_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(ia_requests, "event=0x04"), + INTEL_UNCORE_EVENT_DESC(ia_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(ia_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(io_requests, "event=0x05"), + INTEL_UNCORE_EVENT_DESC(io_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(io_requests.unit, "MiB"), + { /* end: all zeroes */ }, }; @@ -405,13 +417,35 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { #define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 #define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE +/* BW break down- legacy counters */ +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS 0x3 +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE 0x5040 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS 0x4 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE 0x5044 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS 0x5 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE 0x5048 + enum perf_snb_uncore_imc_freerunning_types { - SNB_PCI_UNCORE_IMC_DATA = 0, + SNB_PCI_UNCORE_IMC_DATA_READS = 0, + SNB_PCI_UNCORE_IMC_DATA_WRITES, + SNB_PCI_UNCORE_IMC_GT_REQUESTS, + SNB_PCI_UNCORE_IMC_IA_REQUESTS, + SNB_PCI_UNCORE_IMC_IO_REQUESTS, + SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, }; static struct freerunning_counters snb_uncore_imc_freerunning[] = { - [SNB_PCI_UNCORE_IMC_DATA] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IA_REQUESTS] = { SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IO_REQUESTS] = { SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, }; static struct attribute *snb_uncore_imc_formats_attr[] = { @@ -525,6 +559,18 @@ static int snb_uncore_imc_event_init(struct perf_event *event) base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; idx = UNCORE_PMC_IDX_FREERUNNING; break; + case SNB_UNCORE_PCI_IMC_GT_REQUESTS: + base = SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IA_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IO_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; default: return -EINVAL; } @@ -598,7 +644,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = { static struct intel_uncore_type snb_uncore_imc = { .name = "imc", - .num_counters = 2, + .num_counters = 5, .num_boxes = 1, .num_freerunning_types = SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, .mmio_map_size = SNB_UNCORE_PCI_IMC_MAP_SIZE, diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index b9c2667ac46c..bc9758ef292e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -81,11 +81,8 @@ extern unsigned long efi_fw_vendor, efi_config_table; kernel_fpu_end(); \ }) - #define arch_efi_call_virt(p, f, args...) p->f(args) -#define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) - #else /* !CONFIG_X86_32 */ #define EFI_LOADER_SIGNATURE "EL64" @@ -125,9 +122,6 @@ struct efi_scratch { kernel_fpu_end(); \ }) -extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, - u32 type, u64 attribute); - #ifdef CONFIG_KASAN /* * CONFIG_KASAN may redefine memset to __memset. __memset function is present @@ -143,17 +137,13 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern struct efi_scratch efi_scratch; -extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); extern void __init efi_print_memmap(void); -extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); extern int __init efi_alloc_page_tables(void); extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages); -extern void __init old_map_region(efi_memory_desc_t *md); -extern void __init runtime_code_page_mkexec(void); extern void __init efi_runtime_update_mappings(void); extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5ab3af7275d8..5303dbc5c9bc 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1596,7 +1596,8 @@ asmlinkage void kvm_spurious_fault(void); _ASM_EXTABLE(666b, 667b) #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 0a301ad0b02f..9257667d13c5 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -59,5 +59,6 @@ typedef struct { } void leave_mm(int cpu); +#define leave_mm leave_mm #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c3daf0aaa0ee..cdaab30880b9 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -239,7 +239,7 @@ void __init arch_init_ideal_nops(void) return; } - /* fall through */ + fallthrough; default: #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 21325a4a78b9..779a89e31c4c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -800,7 +800,7 @@ static int irq_polarity(int idx) return IOAPIC_POL_HIGH; case MP_IRQPOL_RESERVED: pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n"); - /* fall through */ + fallthrough; case MP_IRQPOL_ACTIVE_LOW: default: /* Pointless default required due to do gcc stupidity */ return IOAPIC_POL_LOW; @@ -848,7 +848,7 @@ static int irq_trigger(int idx) return IOAPIC_EDGE; case MP_IRQTRIG_RESERVED: pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n"); - /* fall through */ + fallthrough; case MP_IRQTRIG_LEVEL: default: /* Pointless default required due to do gcc stupidity */ return IOAPIC_LEVEL; diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 7bda71def557..99ee61c9ba54 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -149,7 +149,7 @@ void __init default_setup_apic_routing(void) break; } /* P4 and above */ - /* fall through */ + fallthrough; case X86_VENDOR_HYGON: case X86_VENDOR_AMD: def_to_bigsmp = 1; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index dae32d948bf2..f8a56b5dc29f 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -161,6 +161,7 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec, apicd->move_in_progress = true; apicd->prev_vector = apicd->vector; apicd->prev_cpu = apicd->cpu; + WARN_ON_ONCE(apicd->cpu == newcpu); } else { irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector, managed); @@ -910,7 +911,7 @@ void send_cleanup_vector(struct irq_cfg *cfg) __send_cleanup_vector(apicd); } -static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) +void irq_complete_move(struct irq_cfg *cfg) { struct apic_chip_data *apicd; @@ -918,15 +919,16 @@ static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) if (likely(!apicd->move_in_progress)) return; - if (vector == apicd->vector && apicd->cpu == smp_processor_id()) + /* + * If the interrupt arrived on the new target CPU, cleanup the + * vector on the old target CPU. A vector check is not required + * because an interrupt can never move from one vector to another + * on the same CPU. + */ + if (apicd->cpu == smp_processor_id()) __send_cleanup_vector(apicd); } -void irq_complete_move(struct irq_cfg *cfg) -{ - __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); -} - /* * Called from fixup_irqs() with @desc->lock held and interrupts disabled. */ diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index c7503be92f35..57074cf3ad7c 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -248,7 +248,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, switch (leaf) { case 1: l1 = &l1i; - /* fall through */ + fallthrough; case 0: if (!l1->val) return; diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 7843ab3fde09..3a44346f2276 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -199,7 +199,7 @@ static int raise_local(void) * calling irq_enter, but the necessary * machinery isn't exported currently. */ - /*FALL THROUGH*/ + fallthrough; case MCJ_CTX_PROCESS: raise_exception(m, NULL); break; diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index d8f9230d2034..abe9fe0fb851 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -193,7 +193,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval) if (!atomic_sub_return(1, &cmci_storm_on_cpus)) pr_notice("CMCI storm subsided: switching to interrupt mode\n"); - /* FALLTHROUGH */ + fallthrough; case CMCI_STORM_SUBSIDED: /* diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 72182809b333..ca670919b561 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -98,7 +98,7 @@ cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg) case 7: if (size < 0x40) break; - /* Else, fall through */ + fallthrough; case 6: case 5: case 4: diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 8cdf29ffd95f..b98ff620ba77 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -349,7 +349,7 @@ static int arch_build_bp_info(struct perf_event *bp, hw->len = X86_BREAKPOINT_LEN_X; return 0; } - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 68acd30c6b87..c2f02f308ecf 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -450,7 +450,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, ptr = &remcomInBuffer[1]; if (kgdb_hex2long(&ptr, &addr)) linux_regs->ip = addr; - /* fall through */ + fallthrough; case 'D': case 'k': /* clear the trace bit */ @@ -539,7 +539,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd) * a system call which should be ignored */ return NOTIFY_DONE; - /* fall through */ + fallthrough; default: if (user_mode(regs)) return NOTIFY_DONE; diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 411af4aa7b51..baa21090c9be 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -312,7 +312,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) case 2: if (i == 0 || i == 13) continue; /* IRQ0 & IRQ13 not connected */ - /* fall through */ + fallthrough; default: if (i == 2) continue; /* IRQ2 is never connected */ @@ -356,7 +356,7 @@ static void __init construct_ioapic_table(int mpc_default_type) default: pr_err("???\nUnknown standard configuration %d\n", mpc_default_type); - /* fall through */ + fallthrough; case 1: case 5: memcpy(bus.bustype, "ISA ", 6); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 994d8393f2f7..13ce616cc7af 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -684,9 +684,7 @@ void arch_cpu_idle(void) */ void __cpuidle default_idle(void) { - trace_cpu_idle_rcuidle(1, smp_processor_id()); safe_halt(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); @@ -792,7 +790,6 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) static __cpuidle void mwait_idle(void) { if (!current_set_polling_and_test()) { - trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); @@ -804,7 +801,6 @@ static __cpuidle void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 5679aa3fdcb8..e7537c5440bb 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -204,7 +204,7 @@ static int set_segment_reg(struct task_struct *task, case offsetof(struct user_regs_struct, ss): if (unlikely(value == 0)) return -EIO; - /* Else, fall through */ + fallthrough; default: *pt_regs_access(task_pt_regs(task), offset) = value; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0ec7ced727fe..a515e2d230b7 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -654,7 +654,7 @@ static void native_machine_emergency_restart(void) case BOOT_CF9_FORCE: port_cf9_safe = true; - /* Fall through */ + fallthrough; case BOOT_CF9_SAFE: if (port_cf9_safe) { diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index d5fa494c2304..be0d7d4152ec 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -726,7 +726,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->ax = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->ax = regs->orig_ax; regs->ip -= 2; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 27aa04a95702..f5ef689dd62a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1594,14 +1594,28 @@ int native_cpu_disable(void) if (ret) return ret; - /* - * Disable the local APIC. Otherwise IPI broadcasts will reach - * it. It still responds normally to INIT, NMI, SMI, and SIPI - * messages. - */ - apic_soft_disable(); cpu_disable_common(); + /* + * Disable the local APIC. Otherwise IPI broadcasts will reach + * it. It still responds normally to INIT, NMI, SMI, and SIPI + * messages. + * + * Disabling the APIC must happen after cpu_disable_common() + * which invokes fixup_irqs(). + * + * Disabling the APIC preserves already set bits in IRR, but + * an interrupt arriving after disabling the local APIC does not + * set the corresponding IRR bit. + * + * fixup_irqs() scans IRR for set bits so it can raise a not + * yet handled interrupt on the new destination CPU via an IPI + * but obviously it can't do so for IRR bits which are not set. + * IOW, interrupts arriving after disabling the local APIC will + * be lost. + */ + apic_soft_disable(); + return 0; } diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 15e5aad8ac2c..3fdaa042823d 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -735,7 +735,7 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) * OPCODE1() of the "short" jmp which checks the same condition. */ opc1 = OPCODE2(insn) - 0x10; - /* fall through */ + fallthrough; default: if (!is_cond_jmp_opcode(opc1)) return -ENOSYS; @@ -892,7 +892,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, fix_ip_or_call = 0; break; } - /* fall through */ + fallthrough; default: riprel_analyze(auprobe, &insn); } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d0e2825ae617..5299ef5ff18d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3016,7 +3016,7 @@ static void string_registers_quirk(struct x86_emulate_ctxt *ctxt) case 0xa4: /* movsb */ case 0xa5: /* movsd/w */ *reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1; - /* fall through */ + fallthrough; case 0xaa: /* stosb */ case 0xab: /* stosd/w */ *reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 814d3aee5cef..1d330564eed8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1779,7 +1779,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) ret = kvm_hvcall_signal_event(vcpu, fast, ingpa); if (ret != HV_STATUS_INVALID_PORT_ID) break; - /* fall through - maybe userspace knows this conn_id. */ + fallthrough; /* maybe userspace knows this conn_id */ case HVCALL_POST_MESSAGE: /* don't bother userspace if it has no way to handle it */ if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) { diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index c47d2acec529..4aa1c2e00e2a 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -285,7 +285,7 @@ int kvm_set_routing_entry(struct kvm *kvm, switch (ue->u.irqchip.irqchip) { case KVM_IRQCHIP_PIC_SLAVE: e->irqchip.pin += PIC_NUM_PINS / 2; - /* fall through */ + fallthrough; case KVM_IRQCHIP_PIC_MASTER: if (ue->u.irqchip.pin >= PIC_NUM_PINS / 2) return -EINVAL; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5ccbee7165a2..35cca2e0c802 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1053,7 +1053,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, switch (delivery_mode) { case APIC_DM_LOWEST: vcpu->arch.apic_arb_prio++; - /* fall through */ + fallthrough; case APIC_DM_FIXED: if (unlikely(trig_mode && !level)) break; @@ -1341,7 +1341,7 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) break; case APIC_TASKPRI: report_tpr_access(apic, false); - /* fall thru */ + fallthrough; default: val = kvm_lapic_get_reg(apic, offset); break; @@ -2027,7 +2027,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVT0: apic_manage_nmi_watchdog(apic, val); - /* fall through */ + fallthrough; case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4e03841f053d..43fdb0c12a5d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1916,7 +1916,8 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); } @@ -4421,7 +4422,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; - /* fall through */ + fallthrough; case PT64_ROOT_4LEVEL: rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd | nonleaf_bit8_rsvd | rsvd_bits(7, 7) | diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 03dd7bac8034..0194336b64a4 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2668,7 +2668,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_IA32_APICBASE: if (kvm_vcpu_apicv_active(vcpu)) avic_update_vapic_bar(to_svm(vcpu), data); - /* Fall through */ + fallthrough; default: return kvm_set_msr_common(vcpu, msr); } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 46ba2e03a892..819c185adf09 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4654,7 +4654,7 @@ static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) vmcs_read32(VM_EXIT_INSTRUCTION_LEN); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) return false; - /* fall through */ + fallthrough; case DB_VECTOR: return !(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)); @@ -4827,7 +4827,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) } kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); - /* fall through */ + fallthrough; case BP_VECTOR: /* * Update instruction length as we may reinject #BP from @@ -5257,7 +5257,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) error_code = vmcs_read32(IDT_VECTORING_ERROR_CODE); } - /* fall through */ + fallthrough; case INTR_TYPE_SOFT_EXCEPTION: kvm_clear_exception_queue(vcpu); break; @@ -5610,7 +5610,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) * keeping track of global entries in shadow page tables. */ - /* fall-through */ + fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: kvm_mmu_unload(vcpu); return kvm_skip_emulated_instruction(vcpu); @@ -6578,7 +6578,7 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, break; case INTR_TYPE_SOFT_EXCEPTION: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ + fallthrough; case INTR_TYPE_HARD_EXCEPTION: if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { u32 err = vmcs_read32(error_code_field); @@ -6588,7 +6588,7 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, break; case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ + fallthrough; case INTR_TYPE_EXT_INTR: kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR); break; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 599d73206299..d39d6cf1d473 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,7 +975,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + X86_CR4_SMEP; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -1116,14 +1116,12 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) vcpu->arch.eff_db[dr] = val; break; case 4: - /* fall through */ case 6: if (!kvm_dr6_valid(val)) return -1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); break; case 5: - /* fall through */ default: /* 7 */ if (!kvm_dr7_valid(val)) return -1; /* #GP */ @@ -1154,12 +1152,10 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) *val = vcpu->arch.db[array_index_nospec(dr, size)]; break; case 4: - /* fall through */ case 6: *val = vcpu->arch.dr6; break; case 5: - /* fall through */ default: /* 7 */ *val = vcpu->arch.dr7; break; @@ -3051,7 +3047,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: - pr = true; /* fall through */ + pr = true; + fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) @@ -4359,7 +4356,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; - /* fall through */ + fallthrough; case KVM_CAP_HYPERV_SYNIC: if (!irqchip_in_kernel(vcpu->kvm)) @@ -8672,7 +8669,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - /* fall through */ + fallthrough; case KVM_MP_STATE_RUNNABLE: vcpu->arch.apf.halted = false; break; @@ -10751,9 +10748,11 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { struct x86_exception fault; + u32 access = error_code & + (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, error_code, &fault) != UNMAPPED_GVA) { + vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c index 4f1719e22d3c..b6da09339308 100644 --- a/arch/x86/lib/cmdline.c +++ b/arch/x86/lib/cmdline.c @@ -58,7 +58,7 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size, state = st_wordcmp; opptr = option; wstart = pos; - /* fall through */ + fallthrough; case st_wordcmp: if (!*opptr) { @@ -89,7 +89,7 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size, break; } state = st_wordskip; - /* fall through */ + fallthrough; case st_wordskip: if (!c) @@ -151,7 +151,7 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size, state = st_wordcmp; opptr = option; - /* fall through */ + fallthrough; case st_wordcmp: if ((c == '=') && !*opptr) { @@ -172,7 +172,7 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size, break; } state = st_wordskip; - /* fall through */ + fallthrough; case st_wordskip: if (myisspace(c)) diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 31600d851fd8..5e69603ff63f 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -179,7 +179,7 @@ static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off) if (insn->addr_bytes == 2) return -EINVAL; - /* fall through */ + fallthrough; case -EDOM: case offsetof(struct pt_regs, bx): @@ -362,7 +362,6 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) case INAT_SEG_REG_GS: return vm86regs->gs; case INAT_SEG_REG_IGNORE: - /* fall through */ default: return -EINVAL; } @@ -386,7 +385,6 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) */ return get_user_gs(regs); case INAT_SEG_REG_IGNORE: - /* fall through */ default: return -EINVAL; } @@ -786,7 +784,7 @@ int insn_get_code_seg_params(struct pt_regs *regs) */ return INSN_CODE_SEG_PARAMS(4, 8); case 3: /* Invalid setting. CS.L=1, CS.D=1 */ - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c index 73dc66d887f3..ec071cbb0804 100644 --- a/arch/x86/math-emu/errors.c +++ b/arch/x86/math-emu/errors.c @@ -186,7 +186,7 @@ void FPU_printall(void) case TAG_Special: /* Update tagi for the printk below */ tagi = FPU_Special(r); - /* fall through */ + fallthrough; case TAG_Valid: printk("st(%d) %c .%04lx %04lx %04lx %04lx e%+-6d ", i, getsign(r) ? '-' : '+', diff --git a/arch/x86/math-emu/fpu_trig.c b/arch/x86/math-emu/fpu_trig.c index 127ea54122d7..4a9887851ad8 100644 --- a/arch/x86/math-emu/fpu_trig.c +++ b/arch/x86/math-emu/fpu_trig.c @@ -1352,7 +1352,7 @@ static void fyl2xp1(FPU_REG *st0_ptr, u_char st0_tag) case TW_Denormal: if (denormal_operand() < 0) return; - /* fall through */ + fallthrough; case TAG_Zero: case TAG_Valid: setsign(st0_ptr, getsign(st0_ptr) ^ getsign(st1_ptr)); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 84d85dbd1dad..9e5ccc56f8e0 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -574,7 +574,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr, /* For SEV, these areas are encrypted */ if (sev_active()) break; - /* Fallthrough */ + fallthrough; case E820_TYPE_PRAM: return true; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 1a3569b43aa5..0951b47e64c1 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -555,21 +555,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); load_new_mm_cr3(next->pgd, new_asid, true); - /* - * NB: This gets called via leave_mm() in the idle path - * where RCU functions differently. Tracing normally - * uses RCU, so we need to use the _rcuidle variant. - * - * (There is no good reason for this. The idle code should - * be rearranged to call this before rcu_idle_enter().) - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ load_new_mm_cr3(next->pgd, new_asid, false); - /* See above wrt _rcuidle. */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); } /* Make sure we write CR3 before loaded_mm. */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 42b6709e6dc7..7d9ea7b41c71 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1379,10 +1379,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, u8 *prog = *pprog; int cnt = 0; - if (emit_call(&prog, __bpf_prog_enter, prog)) - return -EINVAL; - /* remember prog start time returned by __bpf_prog_enter */ - emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); + if (p->aux->sleepable) { + if (emit_call(&prog, __bpf_prog_enter_sleepable, prog)) + return -EINVAL; + } else { + if (emit_call(&prog, __bpf_prog_enter, prog)) + return -EINVAL; + /* remember prog start time returned by __bpf_prog_enter */ + emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); + } /* arg1: lea rdi, [rbp - stack_size] */ EMIT4(0x48, 0x8D, 0x7D, -stack_size); @@ -1402,13 +1407,18 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, if (mod_ret) emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); - /* arg1: mov rdi, progs[i] */ - emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, - (u32) (long) p); - /* arg2: mov rsi, rbx <- start time in nsec */ - emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); - if (emit_call(&prog, __bpf_prog_exit, prog)) - return -EINVAL; + if (p->aux->sleepable) { + if (emit_call(&prog, __bpf_prog_exit_sleepable, prog)) + return -EINVAL; + } else { + /* arg1: mov rdi, progs[i] */ + emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, + (u32) (long) p); + /* arg2: mov rsi, rbx <- start time in nsec */ + emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); + if (emit_call(&prog, __bpf_prog_exit, prog)) + return -EINVAL; + } *pprog = prog; return 0; diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9f9aad42ccff..89395a5049bb 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -26,6 +26,7 @@ #include <asm/xen/pci.h> #include <asm/xen/cpuid.h> #include <asm/apic.h> +#include <asm/acpi.h> #include <asm/i8259.h> static int xen_pcifront_enable_irq(struct pci_dev *dev) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index f6ea8f1a9d57..d37ebe6e70d7 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -49,7 +49,6 @@ #include <asm/efi.h> #include <asm/e820/api.h> #include <asm/time.h> -#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> #include <asm/uv/uv.h> @@ -496,74 +495,6 @@ void __init efi_init(void) efi_print_memmap(); } -#if defined(CONFIG_X86_32) - -void __init efi_set_executable(efi_memory_desc_t *md, bool executable) -{ - u64 addr, npages; - - addr = md->virt_addr; - npages = md->num_pages; - - memrange_efi_to_native(&addr, &npages); - - if (executable) - set_memory_x(addr, npages); - else - set_memory_nx(addr, npages); -} - -void __init runtime_code_page_mkexec(void) -{ - efi_memory_desc_t *md; - - /* Make EFI runtime service code area executable */ - for_each_efi_memory_desc(md) { - if (md->type != EFI_RUNTIME_SERVICES_CODE) - continue; - - efi_set_executable(md, true); - } -} - -void __init efi_memory_uc(u64 addr, unsigned long size) -{ - unsigned long page_shift = 1UL << EFI_PAGE_SHIFT; - u64 npages; - - npages = round_up(size, page_shift) / page_shift; - memrange_efi_to_native(&addr, &npages); - set_memory_uc(addr, npages); -} - -void __init old_map_region(efi_memory_desc_t *md) -{ - u64 start_pfn, end_pfn, end; - unsigned long size; - void *va; - - start_pfn = PFN_DOWN(md->phys_addr); - size = md->num_pages << PAGE_SHIFT; - end = md->phys_addr + size; - end_pfn = PFN_UP(end); - - if (pfn_range_is_mapped(start_pfn, end_pfn)) { - va = __va(md->phys_addr); - - if (!(md->attribute & EFI_MEMORY_WB)) - efi_memory_uc((u64)(unsigned long)va, size); - } else - va = efi_ioremap(md->phys_addr, size, - md->type, md->attribute); - - md->virt_addr = (u64) (unsigned long) va; - if (!va) - pr_err("ioremap of 0x%llX failed!\n", - (unsigned long long)md->phys_addr); -} - -#endif - /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 826ead67753d..e06a199423c0 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -29,9 +29,35 @@ #include <asm/io.h> #include <asm/desc.h> #include <asm/page.h> +#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/efi.h> +void __init efi_map_region(efi_memory_desc_t *md) +{ + u64 start_pfn, end_pfn, end; + unsigned long size; + void *va; + + start_pfn = PFN_DOWN(md->phys_addr); + size = md->num_pages << PAGE_SHIFT; + end = md->phys_addr + size; + end_pfn = PFN_UP(end); + + if (pfn_range_is_mapped(start_pfn, end_pfn)) { + va = __va(md->phys_addr); + + if (!(md->attribute & EFI_MEMORY_WB)) + set_memory_uc((unsigned long)va, md->num_pages); + } else { + va = ioremap_cache(md->phys_addr, size); + } + + md->virt_addr = (unsigned long)va; + if (!va) + pr_err("ioremap of 0x%llX failed!\n", md->phys_addr); +} + /* * To make EFI call EFI runtime service in physical addressing mode we need * prolog/epilog before/after the invocation to claim the EFI runtime service @@ -58,11 +84,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 0; } -void __init efi_map_region(efi_memory_desc_t *md) -{ - old_map_region(md); -} - void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} @@ -107,6 +128,15 @@ efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, void __init efi_runtime_update_mappings(void) { - if (__supported_pte_mask & _PAGE_NX) - runtime_code_page_mkexec(); + if (__supported_pte_mask & _PAGE_NX) { + efi_memory_desc_t *md; + + /* Make EFI runtime service code area executable */ + for_each_efi_memory_desc(md) { + if (md->type != EFI_RUNTIME_SERVICES_CODE) + continue; + + set_memory_x(md->virt_addr, md->num_pages); + } + } } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 413583f904a6..6af4da1149ba 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -259,6 +259,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT; rodata = __pa(__start_rodata); pfn = rodata >> PAGE_SHIFT; + + pf = _PAGE_NX | _PAGE_ENC; if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) { pr_err("Failed to map kernel rodata 1:1\n"); return 1; diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 76cee341507b..b3b17d6c50f0 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -448,7 +448,7 @@ static void do_signal(struct pt_regs *regs) regs->areg[2] = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->areg[2] = regs->syscall; regs->pc -= 3; diff --git a/block/badblocks.c b/block/badblocks.c index 2e5f5697db35..d39056630d9c 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -525,7 +525,7 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, case 3: if (newline != '\n') return -EINVAL; - /* fall through */ + fallthrough; case 2: if (length <= 0) return -EINVAL; diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 68882b9b8f11..b791e2041e49 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -332,7 +332,7 @@ static void bfqg_put(struct bfq_group *bfqg) kfree(bfqg); } -void bfqg_and_blkg_get(struct bfq_group *bfqg) +static void bfqg_and_blkg_get(struct bfq_group *bfqg) { /* see comments in bfq_bic_update_cgroup for why refcounting bfqg */ bfqg_get(bfqg); diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index a4c0bec920cb..c34b090178a9 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4980,7 +4980,7 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) pr_err("bdi %s: bfq: bad prio class %d\n", bdi_dev_name(bfqq->bfqd->queue->backing_dev_info), ioprio_class); - /* fall through */ + fallthrough; case IOPRIO_CLASS_NONE: /* * No prio set, inherit CPU scheduling settings. @@ -5112,7 +5112,7 @@ static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd, return &bfqg->async_bfqq[0][ioprio]; case IOPRIO_CLASS_NONE: ioprio = IOPRIO_NORM; - /* fall through */ + fallthrough; case IOPRIO_CLASS_BE: return &bfqg->async_bfqq[1][ioprio]; case IOPRIO_CLASS_IDLE: diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index cd224aaf9f52..703895224562 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -986,7 +986,6 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg); struct bfq_group *bfqq_group(struct bfq_queue *bfqq); struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node); -void bfqg_and_blkg_get(struct bfq_group *bfqg); void bfqg_and_blkg_put(struct bfq_group *bfqg); #ifdef CONFIG_BFQ_GROUP_IOSCHED diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index eb0e2a6daabe..26776bdbdf36 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -533,9 +533,7 @@ static void bfq_get_entity(struct bfq_entity *entity) bfqq->ref++; bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d", bfqq, bfqq->ref); - } else - bfqg_and_blkg_get(container_of(entity, struct bfq_group, - entity)); + } } /** @@ -649,14 +647,8 @@ static void bfq_forget_entity(struct bfq_service_tree *st, entity->on_st_or_in_serv = false; st->wsum -= entity->weight; - if (is_in_service) - return; - - if (bfqq) + if (bfqq && !is_in_service) bfq_put_queue(bfqq); - else - bfqg_and_blkg_put(container_of(entity, struct bfq_group, - entity)); } /** diff --git a/block/bio.c b/block/bio.c index c63ba04bd629..a9931f23d933 100644 --- a/block/bio.c +++ b/block/bio.c @@ -740,8 +740,8 @@ static inline bool page_is_mergeable(const struct bio_vec *bv, struct page *page, unsigned int len, unsigned int off, bool *same_page) { - phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + - bv->bv_offset + bv->bv_len - 1; + size_t bv_end = bv->bv_offset + bv->bv_len; + phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1; phys_addr_t page_addr = page_to_phys(page); if (vec_end_addr + 1 != page_addr + off) @@ -750,9 +750,9 @@ static inline bool page_is_mergeable(const struct bio_vec *bv, return false; *same_page = ((vec_end_addr & PAGE_MASK) == page_addr); - if (!*same_page && pfn_to_page(PFN_DOWN(vec_end_addr)) + 1 != page) - return false; - return true; + if (*same_page) + return true; + return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE); } /* diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 619a79b51068..c195365c9817 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1152,13 +1152,15 @@ int blkcg_init_queue(struct request_queue *q) if (preloaded) radix_tree_preload_end(); - ret = blk_iolatency_init(q); + ret = blk_throtl_init(q); if (ret) goto err_destroy_all; - ret = blk_throtl_init(q); - if (ret) + ret = blk_iolatency_init(q); + if (ret) { + blk_throtl_exit(q); goto err_destroy_all; + } return 0; err_destroy_all: diff --git a/block/blk-core.c b/block/blk-core.c index d9d632639bd1..10c08ac50697 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -539,6 +539,7 @@ struct request_queue *blk_alloc_queue(int node_id) goto fail_stats; q->backing_dev_info->ra_pages = VM_READAHEAD_PAGES; + q->backing_dev_info->io_pages = VM_READAHEAD_PAGES; q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK; q->node = node_id; diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 413e0b5c8e6b..d37b55db2409 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2092,14 +2092,15 @@ static void ioc_pd_free(struct blkg_policy_data *pd) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; + unsigned long flags; if (ioc) { - spin_lock(&ioc->lock); + spin_lock_irqsave(&ioc->lock, flags); if (!list_empty(&iocg->active_list)) { propagate_active_weight(iocg, 0, 0); list_del_init(&iocg->active_list); } - spin_unlock(&ioc->lock); + spin_unlock_irqrestore(&ioc->lock, flags); hrtimer_cancel(&iocg->waitq_timer); hrtimer_cancel(&iocg->delay_timer); diff --git a/block/blk-merge.c b/block/blk-merge.c index 6529e3aab001..f685d633bcc9 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -154,7 +154,7 @@ static inline unsigned get_max_io_size(struct request_queue *q, if (max_sectors > start_offset) return max_sectors - start_offset; - return sectors & (lbs - 1); + return sectors & ~(lbs - 1); } static inline unsigned get_max_segment_size(const struct request_queue *q, @@ -533,10 +533,17 @@ int __blk_rq_map_sg(struct request_queue *q, struct request *rq, } EXPORT_SYMBOL(__blk_rq_map_sg); +static inline unsigned int blk_rq_get_max_segments(struct request *rq) +{ + if (req_op(rq) == REQ_OP_DISCARD) + return queue_max_discard_segments(rq->q); + return queue_max_segments(rq->q); +} + static inline int ll_new_hw_segment(struct request *req, struct bio *bio, unsigned int nr_phys_segs) { - if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(req->q)) + if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) goto no_merge; if (blk_integrity_merge_bio(req->q, req, bio) == false) @@ -624,7 +631,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, return 0; total_phys_segments = req->nr_phys_segments + next->nr_phys_segments; - if (total_phys_segments > queue_max_segments(q)) + if (total_phys_segments > blk_rq_get_max_segments(req)) return 0; if (blk_integrity_merge_rq(q, req, next) == false) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index a19cdf159b75..d2790e5b06d1 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -78,6 +78,15 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) return; clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); + /* + * Order clearing SCHED_RESTART and list_empty_careful(&hctx->dispatch) + * in blk_mq_run_hw_queue(). Its pair is the barrier in + * blk_mq_dispatch_rq_list(). So dispatch code won't see SCHED_RESTART, + * meantime new request added to hctx->dispatch is missed to check in + * blk_mq_run_hw_queue(). + */ + smp_mb(); + blk_mq_run_hw_queue(hctx, true); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 0015a1892153..b3d2785eefe9 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1438,6 +1438,15 @@ out: spin_unlock(&hctx->lock); /* + * Order adding requests to hctx->dispatch and checking + * SCHED_RESTART flag. The pair of this smp_mb() is the one + * in blk_mq_sched_restart(). Avoid restart code path to + * miss the new added requests to hctx->dispatch, meantime + * SCHED_RESTART is observed here. + */ + smp_mb(); + + /* * If SCHED_RESTART was set by the caller of this function and * it is no longer set that means that it was cleared by another * thread and hence that a queue rerun is needed. @@ -1834,6 +1843,7 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, /** * blk_mq_request_bypass_insert - Insert a request at dispatch list. * @rq: Pointer to request to be inserted. + * @at_head: true if the request should be inserted at the head of the list. * @run_queue: If we should run the hardware queue after inserting the request. * * Should only be used carefully, when the caller knows we want to @@ -2016,7 +2026,8 @@ insert: if (bypass_insert) return BLK_STS_RESOURCE; - blk_mq_request_bypass_insert(rq, false, run_queue); + blk_mq_sched_insert_request(rq, false, run_queue, false); + return BLK_STS_OK; } diff --git a/block/blk-stat.c b/block/blk-stat.c index 7da302ff88d0..ae3dd1fb8e61 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -137,6 +137,7 @@ void blk_stat_add_callback(struct request_queue *q, struct blk_stat_callback *cb) { unsigned int bucket; + unsigned long flags; int cpu; for_each_possible_cpu(cpu) { @@ -147,20 +148,22 @@ void blk_stat_add_callback(struct request_queue *q, blk_rq_stat_init(&cpu_stat[bucket]); } - spin_lock(&q->stats->lock); + spin_lock_irqsave(&q->stats->lock, flags); list_add_tail_rcu(&cb->list, &q->stats->callbacks); blk_queue_flag_set(QUEUE_FLAG_STATS, q); - spin_unlock(&q->stats->lock); + spin_unlock_irqrestore(&q->stats->lock, flags); } void blk_stat_remove_callback(struct request_queue *q, struct blk_stat_callback *cb) { - spin_lock(&q->stats->lock); + unsigned long flags; + + spin_lock_irqsave(&q->stats->lock, flags); list_del_rcu(&cb->list); if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting) blk_queue_flag_clear(QUEUE_FLAG_STATS, q); - spin_unlock(&q->stats->lock); + spin_unlock_irqrestore(&q->stats->lock, flags); del_timer_sync(&cb->timer); } @@ -183,10 +186,12 @@ void blk_stat_free_callback(struct blk_stat_callback *cb) void blk_stat_enable_accounting(struct request_queue *q) { - spin_lock(&q->stats->lock); + unsigned long flags; + + spin_lock_irqsave(&q->stats->lock, flags); q->stats->enable_accounting = true; blk_queue_flag_set(QUEUE_FLAG_STATS, q); - spin_unlock(&q->stats->lock); + spin_unlock_irqrestore(&q->stats->lock, flags); } EXPORT_SYMBOL_GPL(blk_stat_enable_accounting); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 0fa615eefd52..fd410086fe1d 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -528,7 +528,7 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio) if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) == (REQ_SYNC | REQ_IDLE)) return false; - /* fallthrough */ + fallthrough; case REQ_OP_DISCARD: return true; default: diff --git a/block/bsg-lib.c b/block/bsg-lib.c index fb7b347f8010..d185396d88bb 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -378,7 +378,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, bset->timeout_fn = timeout; set = &bset->tag_set; - set->ops = &bsg_mq_ops, + set->ops = &bsg_mq_ops; set->nr_hw_queues = 1; set->queue_depth = 128; set->numa_node = NUMA_NO_NODE; diff --git a/block/ioprio.c b/block/ioprio.c index 77bcab11dce5..04ebd37966f1 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -71,7 +71,7 @@ int ioprio_check_cap(int ioprio) case IOPRIO_CLASS_RT: if (!capable(CAP_SYS_ADMIN)) return -EPERM; - /* fall through */ + fallthrough; /* rt has prio field too */ case IOPRIO_CLASS_BE: if (data >= IOPRIO_BE_NR || data < 0) diff --git a/block/partitions/core.c b/block/partitions/core.c index e62a98a8eeb7..5b4869c08fb3 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -278,6 +278,15 @@ static void hd_struct_free_work(struct work_struct *work) { struct hd_struct *part = container_of(to_rcu_work(work), struct hd_struct, rcu_work); + struct gendisk *disk = part_to_disk(part); + + /* + * Release the disk reference acquired in delete_partition here. + * We can't release it in hd_struct_free because the final put_device + * needs process context and thus can't be run directly from a + * percpu_ref ->release handler. + */ + put_device(disk_to_dev(disk)); part->start_sect = 0; part->nr_sects = 0; @@ -293,7 +302,6 @@ static void hd_struct_free(struct percpu_ref *ref) rcu_dereference_protected(disk->part_tbl, 1); rcu_assign_pointer(ptbl->last_lookup, NULL); - put_device(disk_to_dev(disk)); INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work); queue_rcu_work(system_wq, &part->rcu_work); @@ -524,19 +532,20 @@ int bdev_add_partition(struct block_device *bdev, int partno, int bdev_del_partition(struct block_device *bdev, int partno) { struct block_device *bdevp; - struct hd_struct *part; - int ret = 0; + struct hd_struct *part = NULL; + int ret; - part = disk_get_part(bdev->bd_disk, partno); - if (!part) - return -ENXIO; - - ret = -ENOMEM; - bdevp = bdget(part_devt(part)); + bdevp = bdget_disk(bdev->bd_disk, partno); if (!bdevp) - goto out_put_part; + return -ENOMEM; mutex_lock(&bdevp->bd_mutex); + mutex_lock_nested(&bdev->bd_mutex, 1); + + ret = -ENXIO; + part = disk_get_part(bdev->bd_disk, partno); + if (!part) + goto out_unlock; ret = -EBUSY; if (bdevp->bd_openers) @@ -545,16 +554,14 @@ int bdev_del_partition(struct block_device *bdev, int partno) sync_blockdev(bdevp); invalidate_bdev(bdevp); - mutex_lock_nested(&bdev->bd_mutex, 1); delete_partition(bdev->bd_disk, part); - mutex_unlock(&bdev->bd_mutex); - ret = 0; out_unlock: + mutex_unlock(&bdev->bd_mutex); mutex_unlock(&bdevp->bd_mutex); bdput(bdevp); -out_put_part: - disk_put_part(part); + if (part) + disk_put_part(part); return ret; } diff --git a/crypto/af_alg.c b/crypto/af_alg.c index a6f581ab200c..8be8bec07cdd 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/net.h> #include <linux/rwsem.h> +#include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/security.h> @@ -845,9 +846,15 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, } lock_sock(sk); - if (ctx->init && (init || !ctx->more)) { - err = -EINVAL; - goto unlock; + if (ctx->init && !ctx->more) { + if (ctx->used) { + err = -EINVAL; + goto unlock; + } + + pr_info_once( + "%s sent an empty control message without MSG_MORE.\n", + current->comm); } ctx->init = true; diff --git a/crypto/drbg.c b/crypto/drbg.c index e99fe34cfa00..3132967a1749 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -1521,7 +1521,7 @@ static int drbg_prepare_hrng(struct drbg_state *drbg) case -EALREADY: err = 0; - /* fall through */ + fallthrough; default: drbg->random_ready.func = NULL; diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index ba0b7702f2e9..12e82a61b896 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -2348,121 +2348,121 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) test_hash_speed(alg, sec, generic_hash_speed_template); break; } - /* fall through */ + fallthrough; case 301: test_hash_speed("md4", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 302: test_hash_speed("md5", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 303: test_hash_speed("sha1", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 304: test_hash_speed("sha256", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 305: test_hash_speed("sha384", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 306: test_hash_speed("sha512", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 307: test_hash_speed("wp256", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 308: test_hash_speed("wp384", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 309: test_hash_speed("wp512", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 310: test_hash_speed("tgr128", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 311: test_hash_speed("tgr160", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 312: test_hash_speed("tgr192", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 313: test_hash_speed("sha224", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 314: test_hash_speed("rmd128", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 315: test_hash_speed("rmd160", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 316: test_hash_speed("rmd256", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 317: test_hash_speed("rmd320", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 318: test_hash_speed("ghash-generic", sec, hash_speed_template_16); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 319: test_hash_speed("crc32c", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 320: test_hash_speed("crct10dif", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 321: test_hash_speed("poly1305", sec, poly1305_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 322: test_hash_speed("sha3-224", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 323: test_hash_speed("sha3-256", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 324: test_hash_speed("sha3-384", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 325: test_hash_speed("sha3-512", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 326: test_hash_speed("sm3", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 327: test_hash_speed("streebog256", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 328: test_hash_speed("streebog512", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; - /* fall through */ + fallthrough; case 399: break; @@ -2471,121 +2471,121 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) test_ahash_speed(alg, sec, generic_hash_speed_template); break; } - /* fall through */ + fallthrough; case 401: test_ahash_speed("md4", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 402: test_ahash_speed("md5", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 403: test_ahash_speed("sha1", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 404: test_ahash_speed("sha256", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 405: test_ahash_speed("sha384", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 406: test_ahash_speed("sha512", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 407: test_ahash_speed("wp256", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 408: test_ahash_speed("wp384", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 409: test_ahash_speed("wp512", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 410: test_ahash_speed("tgr128", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 411: test_ahash_speed("tgr160", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 412: test_ahash_speed("tgr192", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 413: test_ahash_speed("sha224", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 414: test_ahash_speed("rmd128", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 415: test_ahash_speed("rmd160", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 416: test_ahash_speed("rmd256", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 417: test_ahash_speed("rmd320", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 418: test_ahash_speed("sha3-224", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 419: test_ahash_speed("sha3-256", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 420: test_ahash_speed("sha3-384", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 421: test_ahash_speed("sha3-512", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 422: test_mb_ahash_speed("sha1", sec, generic_hash_speed_template, num_mb); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 423: test_mb_ahash_speed("sha256", sec, generic_hash_speed_template, num_mb); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 424: test_mb_ahash_speed("sha512", sec, generic_hash_speed_template, num_mb); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 425: test_mb_ahash_speed("sm3", sec, generic_hash_speed_template, num_mb); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 426: test_mb_ahash_speed("streebog256", sec, generic_hash_speed_template, num_mb); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 427: test_mb_ahash_speed("streebog512", sec, generic_hash_speed_template, num_mb); if (mode > 400 && mode < 500) break; - /* fall through */ + fallthrough; case 499: break; diff --git a/drivers/accessibility/braille/braille_console.c b/drivers/accessibility/braille/braille_console.c index c2b452af6806..9861302cc7db 100644 --- a/drivers/accessibility/braille/braille_console.c +++ b/drivers/accessibility/braille/braille_console.c @@ -290,7 +290,7 @@ static int vt_notifier_call(struct notifier_block *blk, break; case '\t': c = ' '; - /* Fallthrough */ + fallthrough; default: if (c < 32) /* Ignore other control sequences */ diff --git a/drivers/accessibility/speakup/Kconfig b/drivers/accessibility/speakup/Kconfig index 0803c2013cf4..07ecbbde0384 100644 --- a/drivers/accessibility/speakup/Kconfig +++ b/drivers/accessibility/speakup/Kconfig @@ -42,6 +42,11 @@ config SPEAKUP one of the listed synthesizers, you should say n. if SPEAKUP + +config SPEAKUP_SERIALIO + def_bool y + depends on ISA || COMPILE_TEST + config SPEAKUP_SYNTH_ACNTSA tristate "Accent SA synthesizer support" help @@ -52,7 +57,7 @@ config SPEAKUP_SYNTH_ACNTSA config SPEAKUP_SYNTH_ACNTPC tristate "Accent PC synthesizer support" - depends on ISA || COMPILE_TEST + depends on SPEAKUP_SERIALIO help This is the Speakup driver for the accent pc synthesizer. You can say y to build it into the kernel, @@ -104,7 +109,7 @@ config SPEAKUP_SYNTH_DECEXT config SPEAKUP_SYNTH_DECPC depends on m - depends on ISA || COMPILE_TEST + depends on SPEAKUP_SERIALIO tristate "DECtalk PC (big ISA card) synthesizer support" help @@ -127,7 +132,7 @@ config SPEAKUP_SYNTH_DECPC config SPEAKUP_SYNTH_DTLK tristate "DoubleTalk PC synthesizer support" - depends on ISA || COMPILE_TEST + depends on SPEAKUP_SERIALIO help This is the Speakup driver for the internal DoubleTalk @@ -138,7 +143,7 @@ config SPEAKUP_SYNTH_DTLK config SPEAKUP_SYNTH_KEYPC tristate "Keynote Gold PC synthesizer support" - depends on ISA || COMPILE_TEST + depends on SPEAKUP_SERIALIO help This is the Speakup driver for the Keynote Gold diff --git a/drivers/accessibility/speakup/Makefile b/drivers/accessibility/speakup/Makefile index 5befb4933b85..6e4bfac8af65 100644 --- a/drivers/accessibility/speakup/Makefile +++ b/drivers/accessibility/speakup/Makefile @@ -25,8 +25,8 @@ speakup-y := \ keyhelp.o \ kobjects.o \ selection.o \ - serialio.o \ spk_ttyio.o \ synth.o \ thread.o \ varhandlers.o +speakup-$(CONFIG_SPEAKUP_SERIALIO) += serialio.o diff --git a/drivers/accessibility/speakup/serialio.c b/drivers/accessibility/speakup/serialio.c index 177a2988641c..403b01d66367 100644 --- a/drivers/accessibility/speakup/serialio.c +++ b/drivers/accessibility/speakup/serialio.c @@ -32,6 +32,7 @@ static void spk_serial_tiocmset(unsigned int set, unsigned int clear); static unsigned char spk_serial_in(void); static unsigned char spk_serial_in_nowait(void); static void spk_serial_flush_buffer(void); +static int spk_serial_wait_for_xmitr(struct spk_synth *in_synth); struct spk_io_ops spk_serial_io_ops = { .synth_out = spk_serial_out, @@ -40,6 +41,7 @@ struct spk_io_ops spk_serial_io_ops = { .synth_in = spk_serial_in, .synth_in_nowait = spk_serial_in_nowait, .flush_buffer = spk_serial_flush_buffer, + .wait_for_xmitr = spk_serial_wait_for_xmitr, }; EXPORT_SYMBOL_GPL(spk_serial_io_ops); @@ -211,7 +213,7 @@ void spk_stop_serial_interrupt(void) } EXPORT_SYMBOL_GPL(spk_stop_serial_interrupt); -int spk_wait_for_xmitr(struct spk_synth *in_synth) +static int spk_serial_wait_for_xmitr(struct spk_synth *in_synth) { int tmout = SPK_XMITR_TIMEOUT; @@ -280,7 +282,7 @@ static void spk_serial_flush_buffer(void) static int spk_serial_out(struct spk_synth *in_synth, const char ch) { - if (in_synth->alive && spk_wait_for_xmitr(in_synth)) { + if (in_synth->alive && spk_serial_wait_for_xmitr(in_synth)) { outb_p(ch, speakup_info.port_tts); return 1; } @@ -295,7 +297,7 @@ const char *spk_serial_synth_immediate(struct spk_synth *synth, while ((ch = *buff)) { if (ch == '\n') ch = synth->procspeech; - if (spk_wait_for_xmitr(synth)) + if (spk_serial_wait_for_xmitr(synth)) outb(ch, speakup_info.port_tts); else return buff; diff --git a/drivers/accessibility/speakup/spk_priv.h b/drivers/accessibility/speakup/spk_priv.h index c75b40838794..0f4bcbe5ddb9 100644 --- a/drivers/accessibility/speakup/spk_priv.h +++ b/drivers/accessibility/speakup/spk_priv.h @@ -34,7 +34,6 @@ const struct old_serial_port *spk_serial_init(int index); void spk_stop_serial_interrupt(void); -int spk_wait_for_xmitr(struct spk_synth *in_synth); void spk_serial_release(void); void spk_ttyio_release(void); void spk_ttyio_register_ldisc(void); diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c index 9b95f77f9265..a831ff64f8ba 100644 --- a/drivers/accessibility/speakup/spk_ttyio.c +++ b/drivers/accessibility/speakup/spk_ttyio.c @@ -116,6 +116,7 @@ static void spk_ttyio_tiocmset(unsigned int set, unsigned int clear); static unsigned char spk_ttyio_in(void); static unsigned char spk_ttyio_in_nowait(void); static void spk_ttyio_flush_buffer(void); +static int spk_ttyio_wait_for_xmitr(struct spk_synth *in_synth); struct spk_io_ops spk_ttyio_ops = { .synth_out = spk_ttyio_out, @@ -125,6 +126,7 @@ struct spk_io_ops spk_ttyio_ops = { .synth_in = spk_ttyio_in, .synth_in_nowait = spk_ttyio_in_nowait, .flush_buffer = spk_ttyio_flush_buffer, + .wait_for_xmitr = spk_ttyio_wait_for_xmitr, }; EXPORT_SYMBOL_GPL(spk_ttyio_ops); @@ -286,6 +288,11 @@ static void spk_ttyio_tiocmset(unsigned int set, unsigned int clear) mutex_unlock(&speakup_tty_mutex); } +static int spk_ttyio_wait_for_xmitr(struct spk_synth *in_synth) +{ + return 1; +} + static unsigned char ttyio_in(int timeout) { struct spk_ldisc_data *ldisc_data = speakup_tty->disc_data; diff --git a/drivers/accessibility/speakup/spk_types.h b/drivers/accessibility/speakup/spk_types.h index d3272c6d199a..7398f1196e10 100644 --- a/drivers/accessibility/speakup/spk_types.h +++ b/drivers/accessibility/speakup/spk_types.h @@ -158,6 +158,7 @@ struct spk_io_ops { unsigned char (*synth_in)(void); unsigned char (*synth_in_nowait)(void); void (*flush_buffer)(void); + int (*wait_for_xmitr)(struct spk_synth *synth); }; struct spk_synth { diff --git a/drivers/accessibility/speakup/synth.c b/drivers/accessibility/speakup/synth.c index 3568bfb89912..ac47dbac7207 100644 --- a/drivers/accessibility/speakup/synth.c +++ b/drivers/accessibility/speakup/synth.c @@ -159,7 +159,7 @@ int spk_synth_is_alive_restart(struct spk_synth *synth) { if (synth->alive) return 1; - if (spk_wait_for_xmitr(synth) > 0) { + if (synth->io_ops->wait_for_xmitr(synth) > 0) { /* restart */ synth->alive = 1; synth_printf("%s", synth->init); diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c index 4c348377a39d..806b8ce05624 100644 --- a/drivers/acpi/acpi_apd.c +++ b/drivers/acpi/acpi_apd.c @@ -99,8 +99,8 @@ static int fch_misc_setup(struct apd_private_data *pdata) if (ret < 0) return -ENOENT; - acpi_dev_get_property(adev, "is-rv", ACPI_TYPE_INTEGER, &obj); - clk_data->is_rv = obj->integer.value; + if (!acpi_dev_get_property(adev, "is-rv", ACPI_TYPE_INTEGER, &obj)) + clk_data->is_rv = obj->integer.value; list_for_each_entry(rentry, &resource_list, node) { clk_data->base = devm_ioremap(&adev->dev, rentry->res->start, diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 6ad8cb05f672..4a0b07792233 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -350,7 +350,7 @@ void __iomem __ref pg_off = round_down(phys, PAGE_SIZE); pg_sz = round_up(phys + size, PAGE_SIZE) - pg_off; - virt = acpi_map(pg_off, pg_sz); + virt = acpi_map(phys, size); if (!virt) { mutex_unlock(&acpi_ioremap_lock); kfree(map); @@ -358,7 +358,7 @@ void __iomem __ref } INIT_LIST_HEAD(&map->list); - map->virt = virt; + map->virt = (void __iomem __force *)((unsigned long)virt & PAGE_MASK); map->phys = pg_off; map->size = pg_sz; map->track.refcount = 1; @@ -1575,11 +1575,26 @@ static acpi_status acpi_deactivate_mem_region(acpi_handle handle, u32 level, acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, u32 level) { + acpi_status status; + if (!(res->flags & IORESOURCE_MEM)) return AE_TYPE; - return acpi_walk_namespace(ACPI_TYPE_REGION, handle, level, - acpi_deactivate_mem_region, NULL, res, NULL); + status = acpi_walk_namespace(ACPI_TYPE_REGION, handle, level, + acpi_deactivate_mem_region, NULL, + res, NULL); + if (ACPI_FAILURE(status)) + return status; + + /* + * Wait for all of the mappings queued up for removal by + * acpi_deactivate_mem_region() to actually go away. + */ + synchronize_rcu(); + rcu_barrier(); + flush_scheduled_work(); + + return AE_OK; } EXPORT_SYMBOL_GPL(acpi_release_memory); diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 0c0a736eb861..fbd8eaa32d32 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -807,8 +807,7 @@ static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class, (sstatus & 0xf) != 1) break; - ata_link_printk(link, KERN_INFO, "avn bounce port%d\n", - port); + ata_link_info(link, "avn bounce port%d\n", port); pci_read_config_word(pdev, 0x92, &val); val &= ~(1 << port); diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index 6853dbb4131d..49f7acbfcf01 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -470,7 +470,7 @@ static int brcm_ahci_probe(struct platform_device *pdev) switch (priv->version) { case BRCM_SATA_BCM7425: hpriv->flags |= AHCI_HFLAG_DELAY_ENGINE; - /* fall through */ + fallthrough; case BRCM_SATA_NSP: hpriv->flags |= AHCI_HFLAG_NO_NCQ; priv->quirks |= BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE; diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 129556fcf6be..86261deeb4c5 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -326,7 +326,7 @@ static int ahci_platform_get_phy(struct ahci_host_priv *hpriv, u32 port, node); break; } - /* fall through */ + fallthrough; case -ENODEV: /* continue normally */ hpriv->phys[port] = NULL; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b1cd4d97bc2a..f546a5761c4f 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -190,7 +190,7 @@ struct ata_link *ata_link_next(struct ata_link *link, struct ata_port *ap, case ATA_LITER_PMP_FIRST: if (sata_pmp_attached(ap)) return ap->pmp_link; - /* fall through */ + fallthrough; case ATA_LITER_HOST_FIRST: return &ap->link; } @@ -201,11 +201,11 @@ struct ata_link *ata_link_next(struct ata_link *link, struct ata_port *ap, case ATA_LITER_HOST_FIRST: if (sata_pmp_attached(ap)) return ap->pmp_link; - /* fall through */ + fallthrough; case ATA_LITER_PMP_FIRST: if (unlikely(ap->slave_link)) return ap->slave_link; - /* fall through */ + fallthrough; case ATA_LITER_EDGE: return NULL; } @@ -523,7 +523,7 @@ int atapi_cmd_type(u8 opcode) case ATA_12: if (atapi_passthru16) return ATAPI_PASS_THRU; - /* fall thru */ + fallthrough; default: return ATAPI_MISC; } @@ -1800,7 +1800,7 @@ retry: switch (class) { case ATA_DEV_SEMB: class = ATA_DEV_ATA; /* some hard drives report SEMB sig */ - /* fall through */ + fallthrough; case ATA_DEV_ATA: case ATA_DEV_ZAC: tf.command = ATA_CMD_ID_ATA; @@ -2907,7 +2907,7 @@ int ata_bus_probe(struct ata_port *ap) case -ENODEV: /* give it just one more chance */ tries[dev->devno] = min(tries[dev->devno], 1); - /* fall through */ + fallthrough; case -EIO: if (tries[dev->devno] == 1) { /* This is the last chance, better to slow @@ -3158,7 +3158,7 @@ int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel) case ATA_DNXFER_FORCE_PIO0: pio_mask &= 1; - /* fall through */ + fallthrough; case ATA_DNXFER_FORCE_PIO: mwdma_mask = 0; udma_mask = 0; @@ -3868,9 +3868,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */ { "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ, }, - /* Some Sandisk SSDs lock up hard with NCQ enabled. Reported on - SD7SN6S256G and SD8SN8U256G */ - { "SanDisk SD[78]SN*G", NULL, ATA_HORKAGE_NONCQ, }, + /* Sandisk SD7/8/9s lock up hard on large trims */ + { "SanDisk SD[789]*", NULL, ATA_HORKAGE_MAX_TRIM_128M, }, /* devices which puke on READ_NATIVE_MAX */ { "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA, }, @@ -4694,7 +4693,7 @@ void ata_qc_complete(struct ata_queued_cmd *qc) qc->tf.feature != SETFEATURES_RA_ON && qc->tf.feature != SETFEATURES_RA_OFF) break; - /* fall through */ + fallthrough; case ATA_CMD_INIT_DEV_PARAMS: /* CHS translation changed */ case ATA_CMD_SET_MULTI: /* multi_count changed */ /* revalidate device */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 474c6c34fe02..d912eaa65c94 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1576,7 +1576,7 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc, case ATA_DEV_ZAC: if (stat & ATA_SENSE) ata_eh_request_sense(qc, qc->scsicmd); - /* fall through */ + fallthrough; case ATA_DEV_ATA: if (err & ATA_ICRC) qc->err_mask |= AC_ERR_ATA_BUS; @@ -3473,11 +3473,11 @@ static int ata_eh_handle_dev_fail(struct ata_device *dev, int err) case -ENODEV: /* device missing or wrong IDENTIFY data, schedule probing */ ehc->i.probe_mask |= (1 << dev->devno); - /* fall through */ + fallthrough; case -EINVAL: /* give it just one more chance */ ehc->tries[dev->devno] = min(ehc->tries[dev->devno], 1); - /* fall through */ + fallthrough; case -EIO: if (ehc->tries[dev->devno] == 1) { /* This is the last chance, better to slow diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index ec233208585b..70431912dc63 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2080,6 +2080,7 @@ static unsigned int ata_scsiop_inq_89(struct ata_scsi_args *args, u8 *rbuf) static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf) { + struct ata_device *dev = args->dev; u16 min_io_sectors; rbuf[1] = 0xb0; @@ -2105,7 +2106,12 @@ static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf) * with the unmap bit set. */ if (ata_id_has_trim(args->id)) { - put_unaligned_be64(65535 * ATA_MAX_TRIM_RNUM, &rbuf[36]); + u64 max_blocks = 65535 * ATA_MAX_TRIM_RNUM; + + if (dev->horkage & ATA_HORKAGE_MAX_TRIM_128M) + max_blocks = 128 << (20 - SECTOR_SHIFT); + + put_unaligned_be64(max_blocks, &rbuf[36]); put_unaligned_be32(1, &rbuf[28]); } @@ -4162,7 +4168,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd) ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b6); break; } - /* Fallthrough */ + fallthrough; default: ata_scsi_set_invalid_field(dev, cmd, 2, 0xff); break; @@ -4198,7 +4204,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd) * turning this into a no-op. */ case SYNCHRONIZE_CACHE: - /* fall through */ + fallthrough; /* no-op's, complete with success */ case REZERO_UNIT: diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c index e01a3a6e4d46..2bc5fc81efe3 100644 --- a/drivers/ata/pata_atp867x.c +++ b/drivers/ata/pata_atp867x.c @@ -157,7 +157,7 @@ static int atp867x_get_active_clocks_shifted(struct ata_port *ap, default: printk(KERN_WARNING "ATP867X: active %dclk is invalid. " "Using 12clk.\n", clk); - /* fall through */ + fallthrough; case 9 ... 12: clocks = 7; /* 12 clk */ break; @@ -190,7 +190,7 @@ static int atp867x_get_recover_clocks_shifted(unsigned int clk) default: printk(KERN_WARNING "ATP867X: recover %dclk is invalid. " "Using default 12clk.\n", clk); - /* fall through */ + fallthrough; case 12: /* default 12 clk */ clocks = 0; break; diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c index 916bf024d737..7511e11eef4d 100644 --- a/drivers/ata/pata_serverworks.c +++ b/drivers/ata/pata_serverworks.c @@ -369,7 +369,7 @@ static int serverworks_fixup(struct pci_dev *pdev) break; case PCI_DEVICE_ID_SERVERWORKS_CSB5IDE: ata_pci_bmdma_clear_simplex(pdev); - /* fall through */ + fallthrough; case PCI_DEVICE_ID_SERVERWORKS_CSB6IDE: case PCI_DEVICE_ID_SERVERWORKS_CSB6IDE2: rc = serverworks_fixup_csb(pdev); diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index d7228f8e9297..664ef658a955 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -2010,7 +2010,7 @@ static void mv_rw_multi_errata_sata24(struct ata_queued_cmd *qc) break; case ATA_CMD_WRITE_MULTI_FUA_EXT: tf->flags &= ~ATA_TFLAG_FUA; /* ugh */ - /* fall through */ + fallthrough; case ATA_CMD_WRITE_MULTI_EXT: tf->command = ATA_CMD_PIO_WRITE_EXT; break; @@ -2044,7 +2044,7 @@ static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc) case ATA_PROT_DMA: if (tf->command == ATA_CMD_DSM) return AC_ERR_OK; - /* fall-thru */ + fallthrough; case ATA_PROT_NCQ: break; /* continue below */ case ATA_PROT_PIO: @@ -2296,7 +2296,7 @@ static unsigned int mv_qc_issue_fis(struct ata_queued_cmd *qc) switch (qc->tf.protocol) { case ATAPI_PROT_PIO: pp->pp_flags |= MV_PP_FLAG_FAKE_ATA_BUSY; - /* fall through */ + fallthrough; case ATAPI_PROT_NODATA: ap->hsm_task_state = HSM_ST_FIRST; break; @@ -2347,7 +2347,7 @@ static unsigned int mv_qc_issue(struct ata_queued_cmd *qc) return AC_ERR_OTHER; break; /* use bmdma for this */ } - /* fall thru */ + fallthrough; case ATA_PROT_NCQ: mv_start_edma(ap, port_mmio, pp, qc->tf.protocol); pp->req_idx = (pp->req_idx + 1) & MV_MAX_Q_DEPTH_MASK; @@ -2376,7 +2376,7 @@ static unsigned int mv_qc_issue(struct ata_queued_cmd *qc) ": attempting PIO w/multiple DRQ: " "this may fail due to h/w errata\n"); } - /* fall through */ + fallthrough; case ATA_PROT_NODATA: case ATAPI_PROT_PIO: case ATAPI_PROT_NODATA: @@ -3864,7 +3864,7 @@ static int mv_chip_id(struct ata_host *host, unsigned int board_idx) " and avoid the final two gigabytes on" " all RocketRAID BIOS initialized drives.\n"); } - /* fall through */ + fallthrough; case chip_6042: hpriv->ops = &mv6xxx_ops; hp_flags |= MV_HP_GEN_IIE; diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 8729f78cef5f..7815da8ef9e5 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -637,7 +637,7 @@ static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc) switch (qc->tf.protocol) { case ATA_PROT_DMA: pdc_fill_sg(qc); - /*FALLTHROUGH*/ + fallthrough; case ATA_PROT_NODATA: i = pdc_pkt_header(&qc->tf, qc->ap->bmdma_prd_dma, qc->dev->devno, pp->pkt); @@ -652,7 +652,7 @@ static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc) break; case ATAPI_PROT_DMA: pdc_fill_sg(qc); - /*FALLTHROUGH*/ + fallthrough; case ATAPI_PROT_NODATA: pdc_atapi_pkt(qc); break; @@ -1022,11 +1022,11 @@ static unsigned int pdc_qc_issue(struct ata_queued_cmd *qc) case ATAPI_PROT_NODATA: if (qc->dev->flags & ATA_DFLAG_CDB_INTR) break; - /*FALLTHROUGH*/ + fallthrough; case ATA_PROT_NODATA: if (qc->tf.flags & ATA_TFLAG_POLLING) break; - /*FALLTHROUGH*/ + fallthrough; case ATAPI_PROT_DMA: case ATA_PROT_DMA: pdc_packet_start(qc); diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 2c7b30c5ea3d..4c01190a5e37 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -669,7 +669,7 @@ static unsigned int pdc20621_qc_issue(struct ata_queued_cmd *qc) case ATA_PROT_NODATA: if (qc->tf.flags & ATA_TFLAG_POLLING) break; - /*FALLTHROUGH*/ + fallthrough; case ATA_PROT_DMA: pdc20621_packet_start(qc); return 0; diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index 2ca9ec802734..0ddd611b4277 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -711,7 +711,7 @@ static void process_txdone_queue (struct fs_dev *dev, struct queue *q) switch (STATUS_CODE (qe)) { case 0x01: /* This is for AAL0 where we put the chip in streaming mode */ - /* Fall through */ + fallthrough; case 0x02: /* Process a real txdone entry. */ tmp = qe->p0; @@ -998,6 +998,7 @@ static int fs_open(struct atm_vcc *atm_vcc) error = make_rate (pcr, r, &tmc0, NULL); if (error) { kfree(tc); + kfree(vcc); return error; } } diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index a81bc49c14ac..9a70bee84125 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -376,33 +376,33 @@ fore200e_shutdown(struct fore200e* fore200e) case FORE200E_STATE_COMPLETE: kfree(fore200e->stats); - /* fall through */ + fallthrough; case FORE200E_STATE_IRQ: free_irq(fore200e->irq, fore200e->atm_dev); - /* fall through */ + fallthrough; case FORE200E_STATE_ALLOC_BUF: fore200e_free_rx_buf(fore200e); - /* fall through */ + fallthrough; case FORE200E_STATE_INIT_BSQ: fore200e_uninit_bs_queue(fore200e); - /* fall through */ + fallthrough; case FORE200E_STATE_INIT_RXQ: fore200e_dma_chunk_free(fore200e, &fore200e->host_rxq.status); fore200e_dma_chunk_free(fore200e, &fore200e->host_rxq.rpd); - /* fall through */ + fallthrough; case FORE200E_STATE_INIT_TXQ: fore200e_dma_chunk_free(fore200e, &fore200e->host_txq.status); fore200e_dma_chunk_free(fore200e, &fore200e->host_txq.tpd); - /* fall through */ + fallthrough; case FORE200E_STATE_INIT_CMDQ: fore200e_dma_chunk_free(fore200e, &fore200e->host_cmdq.status); - /* fall through */ + fallthrough; case FORE200E_STATE_INITIALIZE: /* nothing to do for that state */ @@ -415,7 +415,7 @@ fore200e_shutdown(struct fore200e* fore200e) case FORE200E_STATE_MAP: fore200e->bus->unmap(fore200e); - /* fall through */ + fallthrough; case FORE200E_STATE_CONFIGURE: /* nothing to do for that state */ diff --git a/drivers/atm/he.c b/drivers/atm/he.c index 8af793f5e811..17f44abc9418 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -1944,14 +1944,14 @@ he_tasklet(unsigned long data) switch (type) { case ITYPE_RBRQ_THRESH: HPRINTK("rbrq%d threshold\n", group); - /* fall through */ + fallthrough; case ITYPE_RBRQ_TIMER: if (he_service_rbrq(he_dev, group)) he_service_rbpl(he_dev, group); break; case ITYPE_TBRQ_THRESH: HPRINTK("tbrq%d threshold\n", group); - /* fall through */ + fallthrough; case ITYPE_TPD_COMPLETE: he_service_tbrq(he_dev, group); break; diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c index 63871859e6e8..3c081b6171a8 100644 --- a/drivers/atm/idt77105.c +++ b/drivers/atm/idt77105.c @@ -192,7 +192,7 @@ static int idt77105_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg) switch (cmd) { case IDT77105_GETSTATZ: if (!capable(CAP_NET_ADMIN)) return -EPERM; - /* fall through */ + fallthrough; case IDT77105_GETSTAT: return fetch_stats(dev, arg, cmd == IDT77105_GETSTATZ); case ATM_SETLOOP: diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c index 986c1313694c..ac811cfa6843 100644 --- a/drivers/atm/lanai.c +++ b/drivers/atm/lanai.c @@ -2019,7 +2019,7 @@ static int lanai_normalize_ci(struct lanai_dev *lanai, switch (*vpip) { case ATM_VPI_ANY: *vpip = 0; - /* FALLTHROUGH */ + fallthrough; case 0: break; default: diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index ee059c77e3bb..cf5fffcf98a1 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1447,7 +1447,7 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg) switch (cmd) { case ZATM_GETPOOLZ: if (!capable(CAP_NET_ADMIN)) return -EPERM; - /* fall through */ + fallthrough; case ZATM_GETPOOL: { struct zatm_pool_info info; diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index 99980aa3644b..1c82d824ae00 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -1365,7 +1365,7 @@ static void panel_process_inputs(void) break; input->rise_timer = 0; input->state = INPUT_ST_RISING; - /* fall through */ + fallthrough; case INPUT_ST_RISING: if ((phys_curr & input->mask) != input->value) { input->state = INPUT_ST_LOW; @@ -1378,11 +1378,11 @@ static void panel_process_inputs(void) } input->high_timer = 0; input->state = INPUT_ST_HIGH; - /* fall through */ + fallthrough; case INPUT_ST_HIGH: if (input_state_high(input)) break; - /* fall through */ + fallthrough; case INPUT_ST_FALLING: input_state_falling(input); } diff --git a/drivers/base/core.c b/drivers/base/core.c index ac1046a382bc..f6f620aa9408 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4264,9 +4264,9 @@ static inline bool fwnode_is_primary(struct fwnode_handle *fwnode) */ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) { - if (fwnode) { - struct fwnode_handle *fn = dev->fwnode; + struct fwnode_handle *fn = dev->fwnode; + if (fwnode) { if (fwnode_is_primary(fn)) fn = fn->secondary; @@ -4276,8 +4276,12 @@ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) } dev->fwnode = fwnode; } else { - dev->fwnode = fwnode_is_primary(dev->fwnode) ? - dev->fwnode->secondary : NULL; + if (fwnode_is_primary(fn)) { + dev->fwnode = fn->secondary; + fn->secondary = NULL; + } else { + dev->fwnode = NULL; + } } } EXPORT_SYMBOL_GPL(set_primary_fwnode); diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c index 5327bfc6ba71..283ca2de76d4 100644 --- a/drivers/base/firmware_loader/fallback.c +++ b/drivers/base/firmware_loader/fallback.c @@ -289,10 +289,10 @@ static ssize_t firmware_loading_store(struct device *dev, } break; } - /* fallthrough */ + fallthrough; default: dev_err(dev, "%s: unexpected value (%d)\n", __func__, loading); - /* fallthrough */ + fallthrough; case -1: fw_load_abort(fw_sysfs); break; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 9dd85bea4026..205a06752ca9 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1606,13 +1606,17 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) } /* - * If a device configured to wake up the system from sleep states - * has been suspended at run time and there's a resume request pending - * for it, this is equivalent to the device signaling wakeup, so the - * system suspend operation should be aborted. + * Wait for possible runtime PM transitions of the device in progress + * to complete and if there's a runtime resume request pending for it, + * resume it before proceeding with invoking the system-wide suspend + * callbacks for it. + * + * If the system-wide suspend callbacks below change the configuration + * of the device, they must disable runtime PM for it or otherwise + * ensure that its runtime-resume callbacks will not be confused by that + * change in case they are invoked going forward. */ - if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) - pm_wakeup_event(dev, 0); + pm_runtime_barrier(dev); if (pm_wakeup_pending()) { dev->power.direct_complete = false; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 3cf9bc5d8d95..6dba41395155 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -1135,7 +1135,7 @@ noskb: if (buf) break; } bvcpy(skb, f->buf->bio, f->iter, n); - /* fall through */ + fallthrough; case ATA_CMD_PIO_WRITE: case ATA_CMD_PIO_WRITE_EXT: spin_lock_irq(&d->lock); diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 1553d41f0b91..a50e13af0305 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1726,7 +1726,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* MSch: invalidate default_params */ default_params[drive].blocks = 0; set_capacity(floppy->disk, MAX_DISK_SIZE * 2); - /* Fall through */ + fallthrough; case FDFMTEND: case FDFLUSH: /* invalidate the buffer track to force a reread */ diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index fe6cb99eb917..740e93bad21f 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1733,7 +1733,7 @@ static inline void __drbd_chk_io_error_(struct drbd_device *device, _drbd_set_state(_NS(device, disk, D_INCONSISTENT), CS_HARD, NULL); break; } - /* fall through - for DRBD_META_IO_ERROR or DRBD_FORCE_DETACH */ + fallthrough; /* for DRBD_META_IO_ERROR or DRBD_FORCE_DETACH */ case EP_DETACH: case EP_CALL_HELPER: /* Remember whether we saw a READ or WRITE error. diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index cb687ccdbd96..04b6bde9419d 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -430,7 +430,7 @@ int drbd_thread_start(struct drbd_thread *thi) thi->t_state = RESTARTING; drbd_info(resource, "Restarting %s thread (from %s [%d])\n", thi->name, current->comm, current->pid); - /* fall through */ + fallthrough; case RUNNING: case RESTARTING: default: diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 28eb078f8b75..43c8ae4d9fca 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -3883,7 +3883,7 @@ static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device, if (nla_put_u32(skb, T_helper_exit_code, sib->helper_exit_code)) goto nla_put_failure; - /* fall through */ + fallthrough; case SIB_HELPER_PRE: if (nla_put_string(skb, T_helper, sib->helper_name)) goto nla_put_failure; diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 1d17593f5d2b..422363daa618 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1797,7 +1797,7 @@ static int receive_Barrier(struct drbd_connection *connection, struct packet_inf break; else drbd_warn(connection, "Allocation of an epoch failed, slowing down\n"); - /* Fall through */ + fallthrough; case WO_BDEV_FLUSH: case WO_DRAIN_IO: @@ -2917,7 +2917,7 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet then we would do something smarter here than reading the block... */ peer_req->flags |= EE_RS_THIN_REQ; - /* fall through */ + fallthrough; case P_RS_DATA_REQUEST: peer_req->w.cb = w_e_end_rsdata_req; fault_type = DRBD_FAULT_RS_RD; @@ -3083,7 +3083,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold rv = 1; break; } - /* Else fall through - to one of the other strategies... */ + fallthrough; /* to one of the other strategies */ case ASB_DISCARD_OLDER_PRI: if (self == 0 && peer == 1) { rv = 1; @@ -3096,7 +3096,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold /* Else fall through to one of the other strategies... */ drbd_warn(device, "Discard younger/older primary did not find a decision\n" "Using discard-least-changes instead\n"); - /* fall through */ + fallthrough; case ASB_DISCARD_ZERO_CHG: if (ch_peer == 0 && ch_self == 0) { rv = test_bit(RESOLVE_CONFLICTS, &peer_device->connection->flags) @@ -3108,7 +3108,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold } if (after_sb_0p == ASB_DISCARD_ZERO_CHG) break; - /* else, fall through */ + fallthrough; case ASB_DISCARD_LEAST_CHG: if (ch_self < ch_peer) rv = -1; @@ -3608,7 +3608,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device, switch (rr_conflict) { case ASB_CALL_HELPER: drbd_khelper(device, "pri-lost"); - /* fall through */ + fallthrough; case ASB_DISCONNECT: drbd_err(device, "I shall become SyncTarget, but I am primary!\n"); return C_MASK; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 674be09b2da9..5c975af9c15f 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -611,7 +611,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what, drbd_set_out_of_sync(device, req->i.sector, req->i.size); drbd_report_io_error(device, req); __drbd_chk_io_error(device, DRBD_READ_ERROR); - /* fall through. */ + fallthrough; case READ_AHEAD_COMPLETED_WITH_ERROR: /* it is legal to fail read-ahead, no __drbd_chk_io_error in that case. */ mod_rq_state(req, m, RQ_LOCAL_PENDING, RQ_LOCAL_COMPLETED); @@ -836,7 +836,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what, } /* else: FIXME can this happen? */ break; } - /* else, fall through - to BARRIER_ACKED */ + fallthrough; /* to BARRIER_ACKED */ case BARRIER_ACKED: /* barrier ack for READ requests does not make sense */ diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 09079aee8dc4..a563b023458a 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -1680,7 +1680,7 @@ static void recal_interrupt(void) clear_bit(FD_DISK_NEWCHANGE_BIT, &drive_state[current_drive].flags); drive_state[current_drive].select_date = jiffies; - /* fall through */ + fallthrough; default: debugt(__func__, "default"); /* Recalibrate moves the head by at @@ -3592,7 +3592,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR) return -EINTR; process_fd_request(); - /* fall through */ + fallthrough; case FDGETDRVSTAT: outparam = &drive_state[drive]; break; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 2f137d6ce169..d3394191e168 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -878,6 +878,7 @@ static void loop_config_discard(struct loop_device *lo) struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct request_queue *q = lo->lo_queue; + u32 granularity, max_discard_sectors; /* * If the backing device is a block device, mirror its zeroing @@ -890,11 +891,10 @@ static void loop_config_discard(struct loop_device *lo) struct request_queue *backingq; backingq = bdev_get_queue(inode->i_bdev); - blk_queue_max_discard_sectors(q, - backingq->limits.max_write_zeroes_sectors); - blk_queue_max_write_zeroes_sectors(q, - backingq->limits.max_write_zeroes_sectors); + max_discard_sectors = backingq->limits.max_write_zeroes_sectors; + granularity = backingq->limits.discard_granularity ?: + queue_physical_block_size(backingq); /* * We use punch hole to reclaim the free space used by the @@ -903,23 +903,26 @@ static void loop_config_discard(struct loop_device *lo) * useful information. */ } else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) { - q->limits.discard_granularity = 0; - q->limits.discard_alignment = 0; - blk_queue_max_discard_sectors(q, 0); - blk_queue_max_write_zeroes_sectors(q, 0); + max_discard_sectors = 0; + granularity = 0; } else { - q->limits.discard_granularity = inode->i_sb->s_blocksize; - q->limits.discard_alignment = 0; - - blk_queue_max_discard_sectors(q, UINT_MAX >> 9); - blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9); + max_discard_sectors = UINT_MAX >> 9; + granularity = inode->i_sb->s_blocksize; } - if (q->limits.max_write_zeroes_sectors) + if (max_discard_sectors) { + q->limits.discard_granularity = granularity; + blk_queue_max_discard_sectors(q, max_discard_sectors); + blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); - else + } else { + q->limits.discard_granularity = 0; + blk_queue_max_discard_sectors(q, 0); + blk_queue_max_write_zeroes_sectors(q, 0); blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); + } + q->limits.discard_alignment = 0; } static void loop_unprepare_queue(struct loop_device *lo) @@ -1111,8 +1114,6 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, mapping = file->f_mapping; inode = mapping->host; - size = get_loop_size(lo, file); - if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) { error = -EINVAL; goto out_unlock; @@ -1162,6 +1163,8 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, loop_update_rotational(lo); loop_update_dio(lo); loop_sysfs_init(lo); + + size = get_loop_size(lo, file); loop_set_size(lo, size); set_blocksize(bdev, S_ISBLK(inode->i_mode) ? @@ -1719,7 +1722,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, case LOOP_SET_BLOCK_SIZE: if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN)) return -EPERM; - /* Fall through */ + fallthrough; default: err = lo_simple_ioctl(lo, cmd, arg); break; @@ -1867,7 +1870,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, case LOOP_SET_STATUS64: case LOOP_CONFIGURE: arg = (unsigned long) compat_ptr(arg); - /* fall through */ + fallthrough; case LOOP_SET_FD: case LOOP_CHANGE_FD: case LOOP_SET_BLOCK_SIZE: diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 3ff4054d6834..edf8b632e3d2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1363,6 +1363,8 @@ static void nbd_set_cmd_timeout(struct nbd_device *nbd, u64 timeout) nbd->tag_set.timeout = timeout * HZ; if (timeout) blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ); + else + blk_queue_rq_timeout(nbd->disk->queue, 30 * HZ); } /* Must be called with config_lock held */ diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 47a9dad880af..d74443a9c8fa 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1147,7 +1147,7 @@ static int null_handle_rq(struct nullb_cmd *cmd) len = bvec.bv_len; err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset, op_is_write(req_op(rq)), sector, - req_op(rq) & REQ_FUA); + rq->cmd_flags & REQ_FUA); if (err) { spin_unlock_irq(&nullb->lock); return err; diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index c0967507d085..a7af4f27b7c3 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -440,7 +440,7 @@ static void run_fsm(void) pd_claimed = 1; if (!pi_schedule_claimed(pi_current, run_fsm)) return; - /* fall through */ + fallthrough; case 1: pd_claimed = 2; pi_current->proto->connect(pi_current); @@ -465,7 +465,7 @@ static void run_fsm(void) if (stop) return; } - /* fall through */ + fallthrough; case Hold: schedule_fsm(); return; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 4becc1efe775..1034e445680c 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2641,7 +2641,7 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, */ if (pd->refcnt == 1) pkt_lock_door(pd, 0); - /* fall through */ + fallthrough; /* * forward selected CDROM ioctls to CD-ROM, for UDF */ diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index d9c0e7d154f9..011539039693 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3293,7 +3293,7 @@ again: case __RBD_OBJ_COPYUP_OBJECT_MAPS: if (!pending_result_dec(&obj_req->pending, result)) return false; - /* fall through */ + fallthrough; case RBD_OBJ_COPYUP_OBJECT_MAPS: if (*result) { rbd_warn(rbd_dev, "snap object map update failed: %d", @@ -3312,7 +3312,7 @@ again: case __RBD_OBJ_COPYUP_WRITE_OBJECT: if (!pending_result_dec(&obj_req->pending, result)) return false; - /* fall through */ + fallthrough; case RBD_OBJ_COPYUP_WRITE_OBJECT: return true; default: @@ -3399,7 +3399,7 @@ again: case __RBD_OBJ_WRITE_COPYUP: if (!rbd_obj_advance_copyup(obj_req, result)) return false; - /* fall through */ + fallthrough; case RBD_OBJ_WRITE_COPYUP: if (*result) { rbd_warn(rbd_dev, "copyup failed: %d", *result); @@ -3592,7 +3592,7 @@ again: case __RBD_IMG_OBJECT_REQUESTS: if (!pending_result_dec(&img_req->pending, result)) return false; - /* fall through */ + fallthrough; case RBD_IMG_OBJECT_REQUESTS: return true; default: diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 0fb94843a495..e1bc8b4cd592 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -148,7 +148,8 @@ static int process_rdma(struct rtrs_srv *sess, /* Generate bio with pages pointing to the rdma buffer */ bio = rnbd_bio_map_kern(data, sess_dev->rnbd_dev->ibd_bio_set, datalen, GFP_KERNEL); if (IS_ERR(bio)) { - rnbd_srv_err(sess_dev, "Failed to generate bio, err: %ld\n", PTR_ERR(bio)); + err = PTR_ERR(bio); + rnbd_srv_err(sess_dev, "Failed to generate bio, err: %d\n", err); goto sess_dev_put; } diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c index 7e261224ff10..8799e3bab067 100644 --- a/drivers/block/rsxx/core.c +++ b/drivers/block/rsxx/core.c @@ -425,7 +425,7 @@ static void card_state_change(struct rsxx_cardinfo *card, * Fall through so the DMA devices can be attached and * the user can attempt to pull off their data. */ - /* fall through */ + fallthrough; case CARD_STATE_GOOD: st = rsxx_get_card_size8(card, &card->size8); if (st) diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 3a476dc1d14f..ae6454c24594 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -1436,7 +1436,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev, blk_mq_requeue_request(req, true); break; } - /* fall through */ + fallthrough; case SKD_CHECK_STATUS_REPORT_ERROR: default: diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 63b213e00b37..b2e48dac1ebd 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -126,16 +126,31 @@ static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap) if (!range) return -ENOMEM; - __rq_for_each_bio(bio, req) { - u64 sector = bio->bi_iter.bi_sector; - u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT; - - range[n].flags = cpu_to_le32(flags); - range[n].num_sectors = cpu_to_le32(num_sectors); - range[n].sector = cpu_to_le64(sector); - n++; + /* + * Single max discard segment means multi-range discard isn't + * supported, and block layer only runs contiguity merge like + * normal RW request. So we can't reply on bio for retrieving + * each range info. + */ + if (queue_max_discard_segments(req->q) == 1) { + range[0].flags = cpu_to_le32(flags); + range[0].num_sectors = cpu_to_le32(blk_rq_sectors(req)); + range[0].sector = cpu_to_le64(blk_rq_pos(req)); + n = 1; + } else { + __rq_for_each_bio(bio, req) { + u64 sector = bio->bi_iter.bi_sector; + u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT; + + range[n].flags = cpu_to_le32(flags); + range[n].num_sectors = cpu_to_le32(num_sectors); + range[n].sector = cpu_to_le64(sector); + n++; + } } + WARN_ON_ONCE(n != segments); + req->special_vec.bv_page = virt_to_page(range); req->special_vec.bv_offset = offset_in_page(range); req->special_vec.bv_len = sizeof(*range) * segments; diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index c2f71265af4b..adfc9352351d 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -1260,7 +1260,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring, break; case BLKIF_OP_WRITE_BARRIER: drain = true; - /* fall through */ + fallthrough; case BLKIF_OP_FLUSH_DISKCACHE: ring->st_f_req++; operation = REQ_OP_WRITE; diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 42944d41aea0..b9aa5d1ac10b 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -843,7 +843,7 @@ static void frontend_changed(struct xenbus_device *dev, xenbus_switch_state(dev, XenbusStateClosed); if (xenbus_dev_is_online(dev)) break; - /* fall through */ + fallthrough; /* if not online */ case XenbusStateUnknown: /* implies xen_blkif_disconnect() via xen_blkbk_remove() */ diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 3bb3dd8da9b0..91de2e0755ae 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1403,7 +1403,6 @@ static enum blk_req_status blkif_rsp_to_req_status(int rsp) case BLKIF_RSP_EOPNOTSUPP: return REQ_EOPNOTSUPP; case BLKIF_RSP_ERROR: - /* Fallthrough. */ default: return REQ_ERROR; } @@ -1643,7 +1642,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) info->feature_flush = 0; xlvbd_flush(info); } - /* fall through */ + fallthrough; case BLKIF_OP_READ: case BLKIF_OP_WRITE: if (unlikely(bret->status != BLKIF_RSP_OKAY)) @@ -2484,7 +2483,7 @@ static void blkback_changed(struct xenbus_device *dev, case XenbusStateClosed: if (dev->state == XenbusStateClosed) break; - /* fall through */ + fallthrough; case XenbusStateClosing: if (info) blkfront_closing(info); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index fb5a901fd89e..efb088df1276 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1849,7 +1849,7 @@ static int sysc_clockdomain_init(struct sysc *ddata) switch (ddata->nr_clocks) { case 2: ick = ddata->clocks[SYSC_ICK]; - /* fallthrough */ + fallthrough; case 1: fck = ddata->clocks[SYSC_FCK]; break; diff --git a/drivers/char/agp/ali-agp.c b/drivers/char/agp/ali-agp.c index 89527bae4602..760d9a931289 100644 --- a/drivers/char/agp/ali-agp.c +++ b/drivers/char/agp/ali-agp.c @@ -357,7 +357,7 @@ found: default: break; } - /*FALLTHROUGH*/ + fallthrough; default: bridge->driver = &ali_generic_bridge; } diff --git a/drivers/char/hw_random/ingenic-rng.c b/drivers/char/hw_random/ingenic-rng.c index d704cef64b64..055cfe59f519 100644 --- a/drivers/char/hw_random/ingenic-rng.c +++ b/drivers/char/hw_random/ingenic-rng.c @@ -92,8 +92,7 @@ static int ingenic_rng_probe(struct platform_device *pdev) priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { pr_err("%s: Failed to map RNG registers\n", __func__); - ret = PTR_ERR(priv->base); - goto err_free_rng; + return PTR_ERR(priv->base); } priv->version = (enum ingenic_rng_version)of_device_get_match_data(&pdev->dev); @@ -106,17 +105,13 @@ static int ingenic_rng_probe(struct platform_device *pdev) ret = hwrng_register(&priv->rng); if (ret) { dev_err(&pdev->dev, "Failed to register hwrng\n"); - goto err_free_rng; + return ret; } platform_set_drvdata(pdev, priv); dev_info(&pdev->dev, "Ingenic RNG driver registered\n"); return 0; - -err_free_rng: - kfree(priv); - return ret; } static int ingenic_rng_remove(struct platform_device *pdev) diff --git a/drivers/char/ipmi/kcs_bmc.c b/drivers/char/ipmi/kcs_bmc.c index ed4dc3b1843e..f292e74bd4a5 100644 --- a/drivers/char/ipmi/kcs_bmc.c +++ b/drivers/char/ipmi/kcs_bmc.c @@ -99,7 +99,7 @@ static void kcs_bmc_handle_data(struct kcs_bmc *kcs_bmc) switch (kcs_bmc->phase) { case KCS_PHASE_WRITE_START: kcs_bmc->phase = KCS_PHASE_WRITE_DATA; - /* fall through */ + fallthrough; case KCS_PHASE_WRITE_DATA: if (kcs_bmc->data_in_idx < KCS_MSG_BUFSIZ) { diff --git a/drivers/char/lp.c b/drivers/char/lp.c index bd95aba1f9fe..45932f05fd67 100644 --- a/drivers/char/lp.c +++ b/drivers/char/lp.c @@ -734,7 +734,7 @@ static long lp_ioctl(struct file *file, unsigned int cmd, ret = lp_set_timeout32(minor, (void __user *)arg); break; } - /* fall through - for 64-bit */ + fallthrough; /* for 64-bit */ case LPSETTIMEOUT_NEW: ret = lp_set_timeout64(minor, (void __user *)arg); break; @@ -762,7 +762,7 @@ static long lp_compat_ioctl(struct file *file, unsigned int cmd, ret = lp_set_timeout32(minor, (void __user *)arg); break; } - /* fall through - for x32 mode */ + fallthrough; /* for x32 mode */ case LPSETTIMEOUT_NEW: ret = lp_set_timeout64(minor, (void __user *)arg); break; diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 687d4af6945d..abd4ffdc8cde 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -791,7 +791,7 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig) switch (orig) { case SEEK_CUR: offset += file->f_pos; - /* fall through */ + fallthrough; case SEEK_SET: /* to avoid userland mistaking f_pos=-9 as -EBADF=-9 */ if ((unsigned long long)offset >= -MAX_ERRNO) { diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c index 8206412d25ba..e9f694b36871 100644 --- a/drivers/char/nvram.c +++ b/drivers/char/nvram.c @@ -286,7 +286,7 @@ static long nvram_misc_ioctl(struct file *file, unsigned int cmd, #ifdef CONFIG_PPC case OBSOLETE_PMAC_NVRAM_GET_OFFSET: pr_warn("nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n"); - /* fall through */ + fallthrough; case IOC_NVRAM_GET_OFFSET: ret = -EINVAL; #ifdef CONFIG_PPC_PMAC diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 3576ad7bd380..68b087bff59c 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -653,9 +653,8 @@ config ATCPIT100_TIMER This option enables support for the Andestech ATCPIT100 timers. config RISCV_TIMER - bool "Timer for the RISC-V platform" + bool "Timer for the RISC-V platform" if COMPILE_TEST depends on GENERIC_SCHED_CLOCK && RISCV - default y select TIMER_PROBE select TIMER_OF help @@ -663,6 +662,15 @@ config RISCV_TIMER is accessed via both the SBI and the rdcycle instruction. This is required for all RISC-V systems. +config CLINT_TIMER + bool "CLINT Timer for the RISC-V platform" if COMPILE_TEST + depends on GENERIC_SCHED_CLOCK && RISCV + select TIMER_PROBE + select TIMER_OF + help + This option enables the CLINT timer for RISC-V systems. The CLINT + driver is usually used for NoMMU RISC-V systems. + config CSKY_MP_TIMER bool "SMP Timer for the C-SKY platform" if COMPILE_TEST depends on CSKY diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index eaedb7240ae7..1c444cc3bb44 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -89,6 +89,7 @@ obj-$(CONFIG_CLKSRC_ST_LPC) += clksrc_st_lpc.o obj-$(CONFIG_X86_NUMACHIP) += numachip.o obj-$(CONFIG_ATCPIT100_TIMER) += timer-atcpit100.o obj-$(CONFIG_RISCV_TIMER) += timer-riscv.o +obj-$(CONFIG_CLINT_TIMER) += timer-clint.o obj-$(CONFIG_CSKY_MP_TIMER) += timer-mp-csky.o obj-$(CONFIG_GX6605S_TIMER) += timer-gx6605s.o obj-$(CONFIG_HYPERV_TIMER) += hyperv_timer.o diff --git a/drivers/clocksource/timer-cadence-ttc.c b/drivers/clocksource/timer-cadence-ttc.c index 38858e141731..80e960602030 100644 --- a/drivers/clocksource/timer-cadence-ttc.c +++ b/drivers/clocksource/timer-cadence-ttc.c @@ -309,7 +309,7 @@ static int ttc_rate_change_clocksource_cb(struct notifier_block *nb, /* restore original register value */ writel_relaxed(ttccs->scale_clk_ctrl_reg_old, ttccs->ttc.base_addr + TTC_CLK_CNTRL_OFFSET); - /* fall through */ + fallthrough; default: return NOTIFY_DONE; } @@ -392,7 +392,7 @@ static int ttc_rate_change_clockevent_cb(struct notifier_block *nb, clockevents_update_freq(&ttcce->ce, ndata->new_rate / PRESCALE); - /* fall through */ + fallthrough; case PRE_RATE_CHANGE: case ABORT_RATE_CHANGE: default: diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c new file mode 100644 index 000000000000..8eeafa82c03d --- /dev/null +++ b/drivers/clocksource/timer-clint.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * + * Most of the M-mode (i.e. NoMMU) RISC-V systems usually have a + * CLINT MMIO timer device. + */ + +#define pr_fmt(fmt) "clint: " fmt +#include <linux/bitops.h> +#include <linux/clocksource.h> +#include <linux/clockchips.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/sched_clock.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/interrupt.h> +#include <linux/of_irq.h> +#include <linux/smp.h> + +#define CLINT_IPI_OFF 0 +#define CLINT_TIMER_CMP_OFF 0x4000 +#define CLINT_TIMER_VAL_OFF 0xbff8 + +/* CLINT manages IPI and Timer for RISC-V M-mode */ +static u32 __iomem *clint_ipi_base; +static u64 __iomem *clint_timer_cmp; +static u64 __iomem *clint_timer_val; +static unsigned long clint_timer_freq; +static unsigned int clint_timer_irq; + +static void clint_send_ipi(const struct cpumask *target) +{ + unsigned int cpu; + + for_each_cpu(cpu, target) + writel(1, clint_ipi_base + cpuid_to_hartid_map(cpu)); +} + +static void clint_clear_ipi(void) +{ + writel(0, clint_ipi_base + cpuid_to_hartid_map(smp_processor_id())); +} + +static struct riscv_ipi_ops clint_ipi_ops = { + .ipi_inject = clint_send_ipi, + .ipi_clear = clint_clear_ipi, +}; + +#ifdef CONFIG_64BIT +#define clint_get_cycles() readq_relaxed(clint_timer_val) +#else +#define clint_get_cycles() readl_relaxed(clint_timer_val) +#define clint_get_cycles_hi() readl_relaxed(((u32 *)clint_timer_val) + 1) +#endif + +#ifdef CONFIG_64BIT +static u64 notrace clint_get_cycles64(void) +{ + return clint_get_cycles(); +} +#else /* CONFIG_64BIT */ +static u64 notrace clint_get_cycles64(void) +{ + u32 hi, lo; + + do { + hi = clint_get_cycles_hi(); + lo = clint_get_cycles(); + } while (hi != clint_get_cycles_hi()); + + return ((u64)hi << 32) | lo; +} +#endif /* CONFIG_64BIT */ + +static u64 clint_rdtime(struct clocksource *cs) +{ + return clint_get_cycles64(); +} + +static struct clocksource clint_clocksource = { + .name = "clint_clocksource", + .rating = 300, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .read = clint_rdtime, +}; + +static int clint_clock_next_event(unsigned long delta, + struct clock_event_device *ce) +{ + void __iomem *r = clint_timer_cmp + + cpuid_to_hartid_map(smp_processor_id()); + + csr_set(CSR_IE, IE_TIE); + writeq_relaxed(clint_get_cycles64() + delta, r); + return 0; +} + +static DEFINE_PER_CPU(struct clock_event_device, clint_clock_event) = { + .name = "clint_clockevent", + .features = CLOCK_EVT_FEAT_ONESHOT, + .rating = 100, + .set_next_event = clint_clock_next_event, +}; + +static int clint_timer_starting_cpu(unsigned int cpu) +{ + struct clock_event_device *ce = per_cpu_ptr(&clint_clock_event, cpu); + + ce->cpumask = cpumask_of(cpu); + clockevents_config_and_register(ce, clint_timer_freq, 100, 0x7fffffff); + + enable_percpu_irq(clint_timer_irq, + irq_get_trigger_type(clint_timer_irq)); + return 0; +} + +static int clint_timer_dying_cpu(unsigned int cpu) +{ + disable_percpu_irq(clint_timer_irq); + return 0; +} + +static irqreturn_t clint_timer_interrupt(int irq, void *dev_id) +{ + struct clock_event_device *evdev = this_cpu_ptr(&clint_clock_event); + + csr_clear(CSR_IE, IE_TIE); + evdev->event_handler(evdev); + + return IRQ_HANDLED; +} + +static int __init clint_timer_init_dt(struct device_node *np) +{ + int rc; + u32 i, nr_irqs; + void __iomem *base; + struct of_phandle_args oirq; + + /* + * Ensure that CLINT device interrupts are either RV_IRQ_TIMER or + * RV_IRQ_SOFT. If it's anything else then we ignore the device. + */ + nr_irqs = of_irq_count(np); + for (i = 0; i < nr_irqs; i++) { + if (of_irq_parse_one(np, i, &oirq)) { + pr_err("%pOFP: failed to parse irq %d.\n", np, i); + continue; + } + + if ((oirq.args_count != 1) || + (oirq.args[0] != RV_IRQ_TIMER && + oirq.args[0] != RV_IRQ_SOFT)) { + pr_err("%pOFP: invalid irq %d (hwirq %d)\n", + np, i, oirq.args[0]); + return -ENODEV; + } + + /* Find parent irq domain and map timer irq */ + if (!clint_timer_irq && + oirq.args[0] == RV_IRQ_TIMER && + irq_find_host(oirq.np)) + clint_timer_irq = irq_of_parse_and_map(np, i); + } + + /* If CLINT timer irq not found then fail */ + if (!clint_timer_irq) { + pr_err("%pOFP: timer irq not found\n", np); + return -ENODEV; + } + + base = of_iomap(np, 0); + if (!base) { + pr_err("%pOFP: could not map registers\n", np); + return -ENODEV; + } + + clint_ipi_base = base + CLINT_IPI_OFF; + clint_timer_cmp = base + CLINT_TIMER_CMP_OFF; + clint_timer_val = base + CLINT_TIMER_VAL_OFF; + clint_timer_freq = riscv_timebase; + + pr_info("%pOFP: timer running at %ld Hz\n", np, clint_timer_freq); + + rc = clocksource_register_hz(&clint_clocksource, clint_timer_freq); + if (rc) { + pr_err("%pOFP: clocksource register failed [%d]\n", np, rc); + goto fail_iounmap; + } + + sched_clock_register(clint_get_cycles64, 64, clint_timer_freq); + + rc = request_percpu_irq(clint_timer_irq, clint_timer_interrupt, + "clint-timer", &clint_clock_event); + if (rc) { + pr_err("registering percpu irq failed [%d]\n", rc); + goto fail_iounmap; + } + + rc = cpuhp_setup_state(CPUHP_AP_CLINT_TIMER_STARTING, + "clockevents/clint/timer:starting", + clint_timer_starting_cpu, + clint_timer_dying_cpu); + if (rc) { + pr_err("%pOFP: cpuhp setup state failed [%d]\n", np, rc); + goto fail_free_irq; + } + + riscv_set_ipi_ops(&clint_ipi_ops); + clint_clear_ipi(); + + return 0; + +fail_free_irq: + free_irq(clint_timer_irq, &clint_clock_event); +fail_iounmap: + iounmap(base); + return rc; +} + +TIMER_OF_DECLARE(clint_timer, "riscv,clint0", clint_timer_init_dt); +TIMER_OF_DECLARE(clint_timer1, "sifive,clint0", clint_timer_init_dt); diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 9de1dabfb126..c51c5ed15aa7 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -19,26 +19,13 @@ #include <linux/of_irq.h> #include <asm/smp.h> #include <asm/sbi.h> - -u64 __iomem *riscv_time_cmp; -u64 __iomem *riscv_time_val; - -static inline void mmio_set_timer(u64 val) -{ - void __iomem *r; - - r = riscv_time_cmp + cpuid_to_hartid_map(smp_processor_id()); - writeq_relaxed(val, r); -} +#include <asm/timex.h> static int riscv_clock_next_event(unsigned long delta, struct clock_event_device *ce) { csr_set(CSR_IE, IE_TIE); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_set_timer(get_cycles64() + delta); - else - mmio_set_timer(get_cycles64() + delta); + sbi_set_timer(get_cycles64() + delta); return 0; } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 02ab56b2a0d8..47aa90f9a7c2 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -703,8 +703,7 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf) freq = arch_freq_get_on_cpu(policy->cpu); if (freq) ret = sprintf(buf, "%u\n", freq); - else if (cpufreq_driver && cpufreq_driver->setpolicy && - cpufreq_driver->get) + else if (cpufreq_driver->setpolicy && cpufreq_driver->get) ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu)); else ret = sprintf(buf, "%u\n", policy->cur); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index e0220a6fbc69..a827b000ef51 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -219,14 +219,13 @@ struct global_params { * @epp_policy: Last saved policy used to set EPP/EPB * @epp_default: Power on default HWP energy performance * preference/bias - * @epp_saved: Saved EPP/EPB during system suspend or CPU offline - * operation * @epp_cached Cached HWP energy-performance preference value * @hwp_req_cached: Cached value of the last HWP Request MSR * @hwp_cap_cached: Cached value of the last HWP Capabilities MSR * @last_io_update: Last time when IO wake flag was set * @sched_flags: Store scheduler flags for possible cross CPU update * @hwp_boost_min: Last HWP boosted min performance + * @suspended: Whether or not the driver has been suspended. * * This structure stores per CPU instance data for all CPUs. */ @@ -258,13 +257,13 @@ struct cpudata { s16 epp_powersave; s16 epp_policy; s16 epp_default; - s16 epp_saved; s16 epp_cached; u64 hwp_req_cached; u64 hwp_cap_cached; u64 last_io_update; unsigned int sched_flags; u32 hwp_boost_min; + bool suspended; }; static struct cpudata **all_cpu_data; @@ -644,6 +643,8 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data, int *raw static int intel_pstate_set_epp(struct cpudata *cpu, u32 epp) { + int ret; + /* * Use the cached HWP Request MSR value, because in the active mode the * register itself may be updated by intel_pstate_hwp_boost_up() or @@ -659,7 +660,11 @@ static int intel_pstate_set_epp(struct cpudata *cpu, u32 epp) * function, so it cannot run in parallel with the update below. */ WRITE_ONCE(cpu->hwp_req_cached, value); - return wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value); + ret = wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value); + if (!ret) + cpu->epp_cached = epp; + + return ret; } static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data, @@ -678,6 +683,14 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data, else if (epp == -EINVAL) epp = epp_values[pref_index - 1]; + /* + * To avoid confusion, refuse to set EPP to any values different + * from 0 (performance) if the current policy is "performance", + * because those values would be overridden. + */ + if (epp > 0 && cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) + return -EBUSY; + ret = intel_pstate_set_epp(cpu_data, epp); } else { if (epp == -EINVAL) @@ -762,10 +775,8 @@ static ssize_t store_energy_performance_preference( cpufreq_stop_governor(policy); ret = intel_pstate_set_epp(cpu, epp); err = cpufreq_start_governor(policy); - if (!ret) { - cpu->epp_cached = epp; + if (!ret) ret = err; - } } } @@ -825,7 +836,7 @@ static void intel_pstate_get_hwp_max(unsigned int cpu, int *phy_max, rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); WRITE_ONCE(all_cpu_data[cpu]->hwp_cap_cached, cap); - if (global.no_turbo) + if (global.no_turbo || global.turbo_disabled) *current_max = HWP_GUARANTEED_PERF(cap); else *current_max = HWP_HIGHEST_PERF(cap); @@ -859,12 +870,6 @@ static void intel_pstate_hwp_set(unsigned int cpu) cpu_data->epp_policy = cpu_data->policy; - if (cpu_data->epp_saved >= 0) { - epp = cpu_data->epp_saved; - cpu_data->epp_saved = -EINVAL; - goto update_epp; - } - if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) { epp = intel_pstate_get_epp(cpu_data, value); cpu_data->epp_powersave = epp; @@ -891,7 +896,6 @@ static void intel_pstate_hwp_set(unsigned int cpu) epp = cpu_data->epp_powersave; } -update_epp: if (boot_cpu_has(X86_FEATURE_HWP_EPP)) { value &= ~GENMASK_ULL(31, 24); value |= (u64)epp << 24; @@ -903,14 +907,24 @@ skip_epp: wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); } -static void intel_pstate_hwp_force_min_perf(int cpu) +static void intel_pstate_hwp_offline(struct cpudata *cpu) { - u64 value; + u64 value = READ_ONCE(cpu->hwp_req_cached); int min_perf; - value = all_cpu_data[cpu]->hwp_req_cached; + if (boot_cpu_has(X86_FEATURE_HWP_EPP)) { + /* + * In case the EPP has been set to "performance" by the + * active mode "performance" scaling algorithm, replace that + * temporary value with the cached EPP one. + */ + value &= ~GENMASK_ULL(31, 24); + value |= HWP_ENERGY_PERF_PREFERENCE(cpu->epp_cached); + WRITE_ONCE(cpu->hwp_req_cached, value); + } + value &= ~GENMASK_ULL(31, 0); - min_perf = HWP_LOWEST_PERF(all_cpu_data[cpu]->hwp_cap_cached); + min_perf = HWP_LOWEST_PERF(cpu->hwp_cap_cached); /* Set hwp_max = hwp_min */ value |= HWP_MAX_PERF(min_perf); @@ -920,19 +934,7 @@ static void intel_pstate_hwp_force_min_perf(int cpu) if (boot_cpu_has(X86_FEATURE_HWP_EPP)) value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE); - wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); -} - -static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) -{ - struct cpudata *cpu_data = all_cpu_data[policy->cpu]; - - if (!hwp_active) - return 0; - - cpu_data->epp_saved = intel_pstate_get_epp(cpu_data, 0); - - return 0; + wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value); } #define POWER_CTL_EE_ENABLE 1 @@ -959,8 +961,28 @@ static void set_power_ctl_ee_state(bool input) static void intel_pstate_hwp_enable(struct cpudata *cpudata); +static void intel_pstate_hwp_reenable(struct cpudata *cpu) +{ + intel_pstate_hwp_enable(cpu); + wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, READ_ONCE(cpu->hwp_req_cached)); +} + +static int intel_pstate_suspend(struct cpufreq_policy *policy) +{ + struct cpudata *cpu = all_cpu_data[policy->cpu]; + + pr_debug("CPU %d suspending\n", cpu->cpu); + + cpu->suspended = true; + + return 0; +} + static int intel_pstate_resume(struct cpufreq_policy *policy) { + struct cpudata *cpu = all_cpu_data[policy->cpu]; + + pr_debug("CPU %d resuming\n", cpu->cpu); /* Only restore if the system default is changed */ if (power_ctl_ee_state == POWER_CTL_EE_ENABLE) @@ -968,18 +990,16 @@ static int intel_pstate_resume(struct cpufreq_policy *policy) else if (power_ctl_ee_state == POWER_CTL_EE_DISABLE) set_power_ctl_ee_state(false); - if (!hwp_active) - return 0; + if (cpu->suspended && hwp_active) { + mutex_lock(&intel_pstate_limits_lock); - mutex_lock(&intel_pstate_limits_lock); + /* Re-enable HWP, because "online" has not done that. */ + intel_pstate_hwp_reenable(cpu); - if (policy->cpu == 0) - intel_pstate_hwp_enable(all_cpu_data[policy->cpu]); + mutex_unlock(&intel_pstate_limits_lock); + } - all_cpu_data[policy->cpu]->epp_policy = 0; - intel_pstate_hwp_set(policy->cpu); - - mutex_unlock(&intel_pstate_limits_lock); + cpu->suspended = false; return 0; } @@ -1428,7 +1448,6 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1); - cpudata->epp_policy = 0; if (cpudata->epp_default == -EINVAL) cpudata->epp_default = intel_pstate_get_epp(cpudata, 0); } @@ -2097,25 +2116,31 @@ static int intel_pstate_init_cpu(unsigned int cpunum) all_cpu_data[cpunum] = cpu; - cpu->epp_default = -EINVAL; - cpu->epp_powersave = -EINVAL; - cpu->epp_saved = -EINVAL; - } - - cpu = all_cpu_data[cpunum]; + cpu->cpu = cpunum; - cpu->cpu = cpunum; + cpu->epp_default = -EINVAL; - if (hwp_active) { - const struct x86_cpu_id *id; + if (hwp_active) { + const struct x86_cpu_id *id; - intel_pstate_hwp_enable(cpu); + intel_pstate_hwp_enable(cpu); - id = x86_match_cpu(intel_pstate_hwp_boost_ids); - if (id && intel_pstate_acpi_pm_profile_server()) - hwp_boost = true; + id = x86_match_cpu(intel_pstate_hwp_boost_ids); + if (id && intel_pstate_acpi_pm_profile_server()) + hwp_boost = true; + } + } else if (hwp_active) { + /* + * Re-enable HWP in case this happens after a resume from ACPI + * S3 if the CPU was offline during the whole system/resume + * cycle. + */ + intel_pstate_hwp_reenable(cpu); } + cpu->epp_powersave = -EINVAL; + cpu->epp_policy = 0; + intel_pstate_get_cpu_pstates(cpu); pr_debug("controlling: cpu %d\n", cpunum); @@ -2296,28 +2321,61 @@ static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy) return 0; } -static void intel_cpufreq_stop_cpu(struct cpufreq_policy *policy) +static int intel_pstate_cpu_offline(struct cpufreq_policy *policy) { + struct cpudata *cpu = all_cpu_data[policy->cpu]; + + pr_debug("CPU %d going offline\n", cpu->cpu); + + if (cpu->suspended) + return 0; + + /* + * If the CPU is an SMT thread and it goes offline with the performance + * settings different from the minimum, it will prevent its sibling + * from getting to lower performance levels, so force the minimum + * performance on CPU offline to prevent that from happening. + */ if (hwp_active) - intel_pstate_hwp_force_min_perf(policy->cpu); + intel_pstate_hwp_offline(cpu); else - intel_pstate_set_min_pstate(all_cpu_data[policy->cpu]); + intel_pstate_set_min_pstate(cpu); + + intel_pstate_exit_perf_limits(policy); + + return 0; +} + +static int intel_pstate_cpu_online(struct cpufreq_policy *policy) +{ + struct cpudata *cpu = all_cpu_data[policy->cpu]; + + pr_debug("CPU %d going online\n", cpu->cpu); + + intel_pstate_init_acpi_perf_limits(policy); + + if (hwp_active) { + /* + * Re-enable HWP and clear the "suspended" flag to let "resume" + * know that it need not do that. + */ + intel_pstate_hwp_reenable(cpu); + cpu->suspended = false; + } + + return 0; } static void intel_pstate_stop_cpu(struct cpufreq_policy *policy) { - pr_debug("CPU %d exiting\n", policy->cpu); + pr_debug("CPU %d stopping\n", policy->cpu); intel_pstate_clear_update_util_hook(policy->cpu); - if (hwp_active) - intel_pstate_hwp_save_state(policy); - - intel_cpufreq_stop_cpu(policy); } static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) { - intel_pstate_exit_perf_limits(policy); + pr_debug("CPU %d exiting\n", policy->cpu); policy->fast_switch_possible = false; @@ -2378,6 +2436,12 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) */ policy->policy = CPUFREQ_POLICY_POWERSAVE; + if (hwp_active) { + struct cpudata *cpu = all_cpu_data[policy->cpu]; + + cpu->epp_cached = intel_pstate_get_epp(cpu, 0); + } + return 0; } @@ -2385,11 +2449,13 @@ static struct cpufreq_driver intel_pstate = { .flags = CPUFREQ_CONST_LOOPS, .verify = intel_pstate_verify_policy, .setpolicy = intel_pstate_set_policy, - .suspend = intel_pstate_hwp_save_state, + .suspend = intel_pstate_suspend, .resume = intel_pstate_resume, .init = intel_pstate_cpu_init, .exit = intel_pstate_cpu_exit, .stop_cpu = intel_pstate_stop_cpu, + .offline = intel_pstate_cpu_offline, + .online = intel_pstate_cpu_online, .update_limits = intel_pstate_update_limits, .name = "intel_pstate", }; @@ -2585,7 +2651,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY_HWP; rdmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, &value); WRITE_ONCE(cpu->hwp_req_cached, value); - cpu->epp_cached = (value & GENMASK_ULL(31, 24)) >> 24; + cpu->epp_cached = intel_pstate_get_epp(cpu, value); } else { turbo_max = cpu->pstate.turbo_pstate; policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY; @@ -2644,7 +2710,10 @@ static struct cpufreq_driver intel_cpufreq = { .fast_switch = intel_cpufreq_fast_switch, .init = intel_cpufreq_cpu_init, .exit = intel_cpufreq_cpu_exit, - .stop_cpu = intel_cpufreq_stop_cpu, + .offline = intel_pstate_cpu_offline, + .online = intel_pstate_cpu_online, + .suspend = intel_pstate_suspend, + .resume = intel_pstate_resume, .update_limits = intel_pstate_update_limits, .name = "intel_cpufreq", }; @@ -2667,9 +2736,6 @@ static void intel_pstate_driver_cleanup(void) } put_online_cpus(); - if (intel_pstate_driver == &intel_pstate) - intel_pstate_sysfs_hide_hwp_dynamic_boost(); - intel_pstate_driver = NULL; } @@ -2695,14 +2761,6 @@ static int intel_pstate_register_driver(struct cpufreq_driver *driver) return 0; } -static int intel_pstate_unregister_driver(void) -{ - cpufreq_unregister_driver(intel_pstate_driver); - intel_pstate_driver_cleanup(); - - return 0; -} - static ssize_t intel_pstate_show_status(char *buf) { if (!intel_pstate_driver) @@ -2714,20 +2772,23 @@ static ssize_t intel_pstate_show_status(char *buf) static int intel_pstate_update_status(const char *buf, size_t size) { - int ret; + if (size == 3 && !strncmp(buf, "off", size)) { + if (!intel_pstate_driver) + return -EINVAL; + + if (hwp_active) + return -EBUSY; - if (size == 3 && !strncmp(buf, "off", size)) - return intel_pstate_driver ? - intel_pstate_unregister_driver() : -EINVAL; + cpufreq_unregister_driver(intel_pstate_driver); + intel_pstate_driver_cleanup(); + } if (size == 6 && !strncmp(buf, "active", size)) { if (intel_pstate_driver) { if (intel_pstate_driver == &intel_pstate) return 0; - ret = intel_pstate_unregister_driver(); - if (ret) - return ret; + cpufreq_unregister_driver(intel_pstate_driver); } return intel_pstate_register_driver(&intel_pstate); @@ -2738,9 +2799,8 @@ static int intel_pstate_update_status(const char *buf, size_t size) if (intel_pstate_driver == &intel_cpufreq) return 0; - ret = intel_pstate_unregister_driver(); - if (ret) - return ret; + cpufreq_unregister_driver(intel_pstate_driver); + intel_pstate_sysfs_hide_hwp_dynamic_boost(); } return intel_pstate_register_driver(&intel_cpufreq); diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c index bb61677c11c7..ef0a3216a386 100644 --- a/drivers/cpufreq/p4-clockmod.c +++ b/drivers/cpufreq/p4-clockmod.c @@ -129,7 +129,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE); case 0x0D: /* Pentium M (Dothan) */ p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; - /* fall through */ + fallthrough; case 0x09: /* Pentium M (Banias) */ return speedstep_get_frequency(SPEEDSTEP_CPU_PM); } diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c index 5c4f8f07c5a6..a13a2d1e444e 100644 --- a/drivers/cpufreq/speedstep-lib.c +++ b/drivers/cpufreq/speedstep-lib.c @@ -366,7 +366,7 @@ enum speedstep_processor speedstep_detect_processor(void) } else return SPEEDSTEP_CPU_PIII_C; } - /* fall through */ + fallthrough; default: return 0; } diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index bae527e507e0..e1d931c457a7 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -56,9 +56,11 @@ struct read_counters_work { static struct workqueue_struct *read_counters_wq; -static enum cluster get_cpu_cluster(u8 cpu) +static void get_cpu_cluster(void *cluster) { - return MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1); + u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; + + *((uint32_t *)cluster) = MPIDR_AFFINITY_LEVEL(mpidr, 1); } /* @@ -186,8 +188,10 @@ static unsigned int tegra194_get_speed(u32 cpu) static int tegra194_cpufreq_init(struct cpufreq_policy *policy) { struct tegra194_cpufreq_data *data = cpufreq_get_driver_data(); - int cl = get_cpu_cluster(policy->cpu); u32 cpu; + u32 cl; + + smp_call_function_single(policy->cpu, get_cpu_cluster, &cl, true); if (cl >= data->num_clusters) return -EINVAL; diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index ab0de27539ad..8f9fdd864391 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -86,11 +86,11 @@ static unsigned long dra7_efuse_xlate(struct ti_cpufreq_data *opp_data, case DRA76_EFUSE_HAS_PLUS_MPU_OPP: case DRA76_EFUSE_HAS_ALL_MPU_OPP: calculated_efuse |= DRA76_EFUSE_PLUS_MPU_OPP; - /* Fall through */ + fallthrough; case DRA7_EFUSE_HAS_ALL_MPU_OPP: case DRA7_EFUSE_HAS_HIGH_MPU_OPP: calculated_efuse |= DRA7_EFUSE_HIGH_MPU_OPP; - /* Fall through */ + fallthrough; case DRA7_EFUSE_HAS_OD_MPU_OPP: calculated_efuse |= DRA7_EFUSE_OD_MPU_OPP; } diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 87197319ab06..04becd70cc41 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -22,6 +22,7 @@ #include <linux/module.h> #include <linux/suspend.h> #include <linux/tick.h> +#include <linux/mmu_context.h> #include <trace/events/power.h> #include "cpuidle.h" @@ -145,21 +146,24 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv, * executing it contains RCU usage regarded as invalid in the idle * context, so tell RCU about that. */ - RCU_NONIDLE(tick_freeze()); + tick_freeze(); /* * The state used here cannot be a "coupled" one, because the "coupled" * cpuidle mechanism enables interrupts and doing that with timekeeping * suspended is generally unsafe. */ stop_critical_timings(); + rcu_idle_enter(); drv->states[index].enter_s2idle(dev, drv, index); - WARN_ON(!irqs_disabled()); + if (WARN_ON_ONCE(!irqs_disabled())) + local_irq_disable(); /* * timekeeping_resume() that will be called by tick_unfreeze() for the * first CPU executing it calls functions containing RCU read-side * critical sections, so tell RCU about that. */ - RCU_NONIDLE(tick_unfreeze()); + rcu_idle_exit(); + tick_unfreeze(); start_critical_timings(); time_end = ns_to_ktime(local_clock()); @@ -225,19 +229,24 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, broadcast = false; } + if (target_state->flags & CPUIDLE_FLAG_TLB_FLUSHED) + leave_mm(dev->cpu); + /* Take note of the planned idle state. */ sched_idle_set_state(target_state); - trace_cpu_idle_rcuidle(index, dev->cpu); + trace_cpu_idle(index, dev->cpu); time_start = ns_to_ktime(local_clock()); stop_critical_timings(); + rcu_idle_enter(); entered_state = target_state->enter(dev, drv, index); + rcu_idle_exit(); start_critical_timings(); sched_clock_idle_wakeup_event(); time_end = ns_to_ktime(local_clock()); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu); /* The cpu is no longer idle or about to enter idle. */ sched_idle_set_state(NULL); diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index aa3a4ed07a66..52a9b7cf6576 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -873,6 +873,9 @@ config CRYPTO_DEV_SA2UL select CRYPTO_AES select CRYPTO_AES_ARM64 select CRYPTO_ALGAPI + select CRYPTO_SHA1 + select CRYPTO_SHA256 + select CRYPTO_SHA512 select HW_RANDOM select SG_SPLIT help diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c index 1a46eeddf082..809c3033ca74 100644 --- a/drivers/crypto/axis/artpec6_crypto.c +++ b/drivers/crypto/axis/artpec6_crypto.c @@ -2310,7 +2310,7 @@ static int artpec6_crypto_prepare_submit_hash(struct ahash_request *req) case ARTPEC6_CRYPTO_PREPARE_HASH_NO_START: ret = 0; - /* Fallthrough */ + fallthrough; default: artpec6_crypto_common_destroy(&req_ctx->common); diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c index dc5fda522719..4fe7898c8561 100644 --- a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c +++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c @@ -90,11 +90,11 @@ static int setup_sgio_components(struct cpt_vf *cptvf, struct buf_ptr *list, case 3: sg_ptr->u.s.len2 = cpu_to_be16(list[i * 4 + 2].size); sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr); - /* Fall through */ + fallthrough; case 2: sg_ptr->u.s.len1 = cpu_to_be16(list[i * 4 + 1].size); sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr); - /* Fall through */ + fallthrough; case 1: sg_ptr->u.s.len0 = cpu_to_be16(list[i * 4 + 0].size); sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr); diff --git a/drivers/crypto/chelsio/Kconfig b/drivers/crypto/chelsio/Kconfig index 2984fdf51e85..af161dab49bd 100644 --- a/drivers/crypto/chelsio/Kconfig +++ b/drivers/crypto/chelsio/Kconfig @@ -22,27 +22,6 @@ config CRYPTO_DEV_CHELSIO To compile this driver as a module, choose M here: the module will be called chcr. -config CHELSIO_IPSEC_INLINE - bool "Chelsio IPSec XFRM Tx crypto offload" - depends on CHELSIO_T4 - depends on CRYPTO_DEV_CHELSIO - depends on XFRM_OFFLOAD - depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD - default n - help - Enable support for IPSec Tx Inline. - -config CRYPTO_DEV_CHELSIO_TLS - tristate "Chelsio Crypto Inline TLS Driver" - depends on CHELSIO_T4 - depends on TLS_TOE - select CRYPTO_DEV_CHELSIO - help - Support Chelsio Inline TLS with Chelsio crypto accelerator. - - To compile this driver as a module, choose M here: the module - will be called chtls. - config CHELSIO_TLS_DEVICE bool "Chelsio Inline KTLS Offload" depends on CHELSIO_T4 diff --git a/drivers/crypto/chelsio/Makefile b/drivers/crypto/chelsio/Makefile index 0e9d035927e9..f2e8e2fb4e60 100644 --- a/drivers/crypto/chelsio/Makefile +++ b/drivers/crypto/chelsio/Makefile @@ -6,5 +6,3 @@ chcr-objs := chcr_core.o chcr_algo.o #ifdef CONFIG_CHELSIO_TLS_DEVICE chcr-objs += chcr_ktls.o #endif -chcr-$(CONFIG_CHELSIO_IPSEC_INLINE) += chcr_ipsec.o -obj-$(CONFIG_CRYPTO_DEV_CHELSIO_TLS) += chtls/ diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h index d4f6e010dc79..507aafe93f21 100644 --- a/drivers/crypto/chelsio/chcr_algo.h +++ b/drivers/crypto/chelsio/chcr_algo.h @@ -86,39 +86,6 @@ KEY_CONTEXT_OPAD_PRESENT_M) #define KEY_CONTEXT_OPAD_PRESENT_F KEY_CONTEXT_OPAD_PRESENT_V(1U) -#define TLS_KEYCTX_RXFLIT_CNT_S 24 -#define TLS_KEYCTX_RXFLIT_CNT_V(x) ((x) << TLS_KEYCTX_RXFLIT_CNT_S) - -#define TLS_KEYCTX_RXPROT_VER_S 20 -#define TLS_KEYCTX_RXPROT_VER_M 0xf -#define TLS_KEYCTX_RXPROT_VER_V(x) ((x) << TLS_KEYCTX_RXPROT_VER_S) - -#define TLS_KEYCTX_RXCIPH_MODE_S 16 -#define TLS_KEYCTX_RXCIPH_MODE_M 0xf -#define TLS_KEYCTX_RXCIPH_MODE_V(x) ((x) << TLS_KEYCTX_RXCIPH_MODE_S) - -#define TLS_KEYCTX_RXAUTH_MODE_S 12 -#define TLS_KEYCTX_RXAUTH_MODE_M 0xf -#define TLS_KEYCTX_RXAUTH_MODE_V(x) ((x) << TLS_KEYCTX_RXAUTH_MODE_S) - -#define TLS_KEYCTX_RXCIAU_CTRL_S 11 -#define TLS_KEYCTX_RXCIAU_CTRL_V(x) ((x) << TLS_KEYCTX_RXCIAU_CTRL_S) - -#define TLS_KEYCTX_RX_SEQCTR_S 9 -#define TLS_KEYCTX_RX_SEQCTR_M 0x3 -#define TLS_KEYCTX_RX_SEQCTR_V(x) ((x) << TLS_KEYCTX_RX_SEQCTR_S) - -#define TLS_KEYCTX_RX_VALID_S 8 -#define TLS_KEYCTX_RX_VALID_V(x) ((x) << TLS_KEYCTX_RX_VALID_S) - -#define TLS_KEYCTX_RXCK_SIZE_S 3 -#define TLS_KEYCTX_RXCK_SIZE_M 0x7 -#define TLS_KEYCTX_RXCK_SIZE_V(x) ((x) << TLS_KEYCTX_RXCK_SIZE_S) - -#define TLS_KEYCTX_RXMK_SIZE_S 0 -#define TLS_KEYCTX_RXMK_SIZE_M 0x7 -#define TLS_KEYCTX_RXMK_SIZE_V(x) ((x) << TLS_KEYCTX_RXMK_SIZE_S) - #define CHCR_HASH_MAX_DIGEST_SIZE 64 #define CHCR_MAX_SHA_DIGEST_SIZE 64 diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c index bd8dac806e7a..b3570b41a737 100644 --- a/drivers/crypto/chelsio/chcr_core.c +++ b/drivers/crypto/chelsio/chcr_core.c @@ -40,10 +40,6 @@ static const struct tlsdev_ops chcr_ktls_ops = { }; #endif -#ifdef CONFIG_CHELSIO_IPSEC_INLINE -static void update_netdev_features(void); -#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ - static chcr_handler_func work_handlers[NUM_CPL_CMDS] = { [CPL_FW6_PLD] = cpl_fw6_pld_handler, #ifdef CONFIG_CHELSIO_TLS_DEVICE @@ -60,10 +56,8 @@ static struct cxgb4_uld_info chcr_uld_info = { .add = chcr_uld_add, .state_change = chcr_uld_state_change, .rx_handler = chcr_uld_rx_handler, -#if defined(CONFIG_CHELSIO_IPSEC_INLINE) || defined(CONFIG_CHELSIO_TLS_DEVICE) - .tx_handler = chcr_uld_tx_handler, -#endif /* CONFIG_CHELSIO_IPSEC_INLINE || CONFIG_CHELSIO_TLS_DEVICE */ #if defined(CONFIG_CHELSIO_TLS_DEVICE) + .tx_handler = chcr_uld_tx_handler, .tlsdev_ops = &chcr_ktls_ops, #endif }; @@ -241,19 +235,11 @@ int chcr_uld_rx_handler(void *handle, const __be64 *rsp, return 0; } -#if defined(CONFIG_CHELSIO_IPSEC_INLINE) || defined(CONFIG_CHELSIO_TLS_DEVICE) +#if defined(CONFIG_CHELSIO_TLS_DEVICE) int chcr_uld_tx_handler(struct sk_buff *skb, struct net_device *dev) { - /* In case if skb's decrypted bit is set, it's nic tls packet, else it's - * ipsec packet. - */ -#ifdef CONFIG_CHELSIO_TLS_DEVICE if (skb->decrypted) return chcr_ktls_xmit(skb, dev); -#endif -#ifdef CONFIG_CHELSIO_IPSEC_INLINE - return chcr_ipsec_xmit(skb, dev); -#endif return 0; } #endif /* CONFIG_CHELSIO_IPSEC_INLINE || CONFIG_CHELSIO_TLS_DEVICE */ @@ -305,24 +291,6 @@ static int chcr_uld_state_change(void *handle, enum cxgb4_state state) return ret; } -#ifdef CONFIG_CHELSIO_IPSEC_INLINE -static void update_netdev_features(void) -{ - struct uld_ctx *u_ctx, *tmp; - - mutex_lock(&drv_data.drv_mutex); - list_for_each_entry_safe(u_ctx, tmp, &drv_data.inact_dev, entry) { - if (u_ctx->lldi.crypto & ULP_CRYPTO_IPSEC_INLINE) - chcr_add_xfrmops(&u_ctx->lldi); - } - list_for_each_entry_safe(u_ctx, tmp, &drv_data.act_dev, entry) { - if (u_ctx->lldi.crypto & ULP_CRYPTO_IPSEC_INLINE) - chcr_add_xfrmops(&u_ctx->lldi); - } - mutex_unlock(&drv_data.drv_mutex); -} -#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ - static int __init chcr_crypto_init(void) { INIT_LIST_HEAD(&drv_data.act_dev); @@ -332,12 +300,6 @@ static int __init chcr_crypto_init(void) drv_data.last_dev = NULL; cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info); - #ifdef CONFIG_CHELSIO_IPSEC_INLINE - rtnl_lock(); - update_netdev_features(); - rtnl_unlock(); - #endif /* CONFIG_CHELSIO_IPSEC_INLINE */ - return 0; } diff --git a/drivers/crypto/chelsio/chcr_core.h b/drivers/crypto/chelsio/chcr_core.h index 67d77abd6775..81f6e61401e5 100644 --- a/drivers/crypto/chelsio/chcr_core.h +++ b/drivers/crypto/chelsio/chcr_core.h @@ -72,54 +72,6 @@ struct _key_ctx { unsigned char key[]; }; -#define KEYCTX_TX_WR_IV_S 55 -#define KEYCTX_TX_WR_IV_M 0x1ffULL -#define KEYCTX_TX_WR_IV_V(x) ((x) << KEYCTX_TX_WR_IV_S) -#define KEYCTX_TX_WR_IV_G(x) \ - (((x) >> KEYCTX_TX_WR_IV_S) & KEYCTX_TX_WR_IV_M) - -#define KEYCTX_TX_WR_AAD_S 47 -#define KEYCTX_TX_WR_AAD_M 0xffULL -#define KEYCTX_TX_WR_AAD_V(x) ((x) << KEYCTX_TX_WR_AAD_S) -#define KEYCTX_TX_WR_AAD_G(x) (((x) >> KEYCTX_TX_WR_AAD_S) & \ - KEYCTX_TX_WR_AAD_M) - -#define KEYCTX_TX_WR_AADST_S 39 -#define KEYCTX_TX_WR_AADST_M 0xffULL -#define KEYCTX_TX_WR_AADST_V(x) ((x) << KEYCTX_TX_WR_AADST_S) -#define KEYCTX_TX_WR_AADST_G(x) \ - (((x) >> KEYCTX_TX_WR_AADST_S) & KEYCTX_TX_WR_AADST_M) - -#define KEYCTX_TX_WR_CIPHER_S 30 -#define KEYCTX_TX_WR_CIPHER_M 0x1ffULL -#define KEYCTX_TX_WR_CIPHER_V(x) ((x) << KEYCTX_TX_WR_CIPHER_S) -#define KEYCTX_TX_WR_CIPHER_G(x) \ - (((x) >> KEYCTX_TX_WR_CIPHER_S) & KEYCTX_TX_WR_CIPHER_M) - -#define KEYCTX_TX_WR_CIPHERST_S 23 -#define KEYCTX_TX_WR_CIPHERST_M 0x7f -#define KEYCTX_TX_WR_CIPHERST_V(x) ((x) << KEYCTX_TX_WR_CIPHERST_S) -#define KEYCTX_TX_WR_CIPHERST_G(x) \ - (((x) >> KEYCTX_TX_WR_CIPHERST_S) & KEYCTX_TX_WR_CIPHERST_M) - -#define KEYCTX_TX_WR_AUTH_S 14 -#define KEYCTX_TX_WR_AUTH_M 0x1ff -#define KEYCTX_TX_WR_AUTH_V(x) ((x) << KEYCTX_TX_WR_AUTH_S) -#define KEYCTX_TX_WR_AUTH_G(x) \ - (((x) >> KEYCTX_TX_WR_AUTH_S) & KEYCTX_TX_WR_AUTH_M) - -#define KEYCTX_TX_WR_AUTHST_S 7 -#define KEYCTX_TX_WR_AUTHST_M 0x7f -#define KEYCTX_TX_WR_AUTHST_V(x) ((x) << KEYCTX_TX_WR_AUTHST_S) -#define KEYCTX_TX_WR_AUTHST_G(x) \ - (((x) >> KEYCTX_TX_WR_AUTHST_S) & KEYCTX_TX_WR_AUTHST_M) - -#define KEYCTX_TX_WR_AUTHIN_S 0 -#define KEYCTX_TX_WR_AUTHIN_M 0x7f -#define KEYCTX_TX_WR_AUTHIN_V(x) ((x) << KEYCTX_TX_WR_AUTHIN_S) -#define KEYCTX_TX_WR_AUTHIN_G(x) \ - (((x) >> KEYCTX_TX_WR_AUTHIN_S) & KEYCTX_TX_WR_AUTHIN_M) - #define WQ_RETRY 5 struct chcr_driver_data { struct list_head act_dev; @@ -157,42 +109,6 @@ struct uld_ctx { struct chcr_dev dev; }; -struct sge_opaque_hdr { - void *dev; - dma_addr_t addr[MAX_SKB_FRAGS + 1]; -}; - -struct chcr_ipsec_req { - struct ulp_txpkt ulptx; - struct ulptx_idata sc_imm; - struct cpl_tx_sec_pdu sec_cpl; - struct _key_ctx key_ctx; -}; - -struct chcr_ipsec_wr { - struct fw_ulptx_wr wreq; - struct chcr_ipsec_req req; -}; - -#define ESN_IV_INSERT_OFFSET 12 -struct chcr_ipsec_aadiv { - __be32 spi; - u8 seq_no[8]; - u8 iv[8]; -}; - -struct ipsec_sa_entry { - int hmac_ctrl; - u16 esn; - u16 resv; - unsigned int enckey_len; - unsigned int kctx_len; - unsigned int authsize; - __be32 key_ctx_hdr; - char salt[MAX_SALT]; - char key[2 * AES_MAX_KEY_SIZE]; -}; - /* * sgl_len - calculates the size of an SGL of the given capacity * @n: the number of SGL entries diff --git a/drivers/crypto/chelsio/chcr_ktls.c b/drivers/crypto/chelsio/chcr_ktls.c index 91dee616d15e..c5cce024886a 100644 --- a/drivers/crypto/chelsio/chcr_ktls.c +++ b/drivers/crypto/chelsio/chcr_ktls.c @@ -135,7 +135,7 @@ static int chcr_ktls_update_connection_state(struct chcr_ktls_info *tx_info, break; /* update to the next state and also initialize TCB */ tx_info->connection_state = new_state; - /* FALLTHRU */ + fallthrough; case KTLS_CONN_ACT_OPEN_RPL: /* if we are stuck in this state, means tcb init might not * received by HW, try sending it again. @@ -150,7 +150,7 @@ static int chcr_ktls_update_connection_state(struct chcr_ktls_info *tx_info, break; /* update to the next state and check if l2t_state is valid */ tx_info->connection_state = new_state; - /* FALLTHRU */ + fallthrough; case KTLS_CONN_SET_TCB_RPL: /* Check if l2t state is valid, then move to ready state. */ if (cxgb4_check_l2t_valid(tx_info->l2te)) { diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c b/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c index cbc3d7869ebe..c80baf1ad90b 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c +++ b/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c @@ -140,11 +140,11 @@ static inline int setup_sgio_components(struct pci_dev *pdev, case 3: sg_ptr->u.s.len2 = cpu_to_be16(list[i * 4 + 2].size); sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr); - /* Fall through */ + fallthrough; case 2: sg_ptr->u.s.len1 = cpu_to_be16(list[i * 4 + 1].size); sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr); - /* Fall through */ + fallthrough; case 1: sg_ptr->u.s.len0 = cpu_to_be16(list[i * 4 + 0].size); sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr); diff --git a/drivers/crypto/qat/qat_common/adf_admin.c b/drivers/crypto/qat/qat_common/adf_admin.c index 1c8ca151a963..ec9b390276d6 100644 --- a/drivers/crypto/qat/qat_common/adf_admin.c +++ b/drivers/crypto/qat/qat_common/adf_admin.c @@ -131,9 +131,10 @@ static int adf_put_admin_msg_sync(struct adf_accel_dev *accel_dev, u32 ae, memcpy(admin->virt_addr + offset, in, ADF_ADMINMSG_LEN); ADF_CSR_WR(mailbox, mb_offset, 1); - ret = readl_poll_timeout(mailbox + mb_offset, status, - status == 0, ADF_ADMIN_POLL_DELAY_US, - ADF_ADMIN_POLL_TIMEOUT_US); + ret = read_poll_timeout(ADF_CSR_RD, status, status == 0, + ADF_ADMIN_POLL_DELAY_US, + ADF_ADMIN_POLL_TIMEOUT_US, true, + mailbox, mb_offset); if (ret < 0) { /* Response timeout */ dev_err(&GET_DEV(accel_dev), diff --git a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c index 519fd5acf713..8b090b7ae8c6 100644 --- a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c +++ b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c @@ -340,7 +340,7 @@ static int adf_vf2pf_request_version(struct adf_accel_dev *accel_dev) /* VF is newer than PF and decides whether it is compatible */ if (accel_dev->vf.pf_version >= hw_data->min_iov_compat_ver) break; - /* fall through */ + fallthrough; case ADF_PF2VF_VF_INCOMPATIBLE: dev_err(&GET_DEV(accel_dev), "PF (vers %d) and VF (vers %d) are not compatible\n", diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c index bff759e2f811..00c615f9f9a8 100644 --- a/drivers/crypto/qat/qat_common/qat_uclo.c +++ b/drivers/crypto/qat/qat_common/qat_uclo.c @@ -752,7 +752,7 @@ static int qat_uclo_init_reg(struct icp_qat_fw_loader_handle *handle, case ICP_GPA_ABS: case ICP_GPB_ABS: ctx_mask = 0; - /* fall through */ + fallthrough; case ICP_GPA_REL: case ICP_GPB_REL: return qat_hal_init_gpr(handle, ae, ctx_mask, reg_type, @@ -762,7 +762,7 @@ static int qat_uclo_init_reg(struct icp_qat_fw_loader_handle *handle, case ICP_SR_RD_ABS: case ICP_DR_RD_ABS: ctx_mask = 0; - /* fall through */ + fallthrough; case ICP_SR_REL: case ICP_DR_REL: case ICP_SR_RD_REL: @@ -772,7 +772,7 @@ static int qat_uclo_init_reg(struct icp_qat_fw_loader_handle *handle, case ICP_SR_WR_ABS: case ICP_DR_WR_ABS: ctx_mask = 0; - /* fall through */ + fallthrough; case ICP_SR_WR_REL: case ICP_DR_WR_REL: return qat_hal_init_wr_xfer(handle, ae, ctx_mask, reg_type, diff --git a/drivers/crypto/ux500/cryp/cryp.c b/drivers/crypto/ux500/cryp/cryp.c index f22f6fa612b3..9866c2a5e9a7 100644 --- a/drivers/crypto/ux500/cryp/cryp.c +++ b/drivers/crypto/ux500/cryp/cryp.c @@ -314,17 +314,17 @@ void cryp_save_device_context(struct cryp_device_data *device_data, case CRYP_KEY_SIZE_256: ctx->key_4_l = readl_relaxed(&src_reg->key_4_l); ctx->key_4_r = readl_relaxed(&src_reg->key_4_r); - /* Fall through */ + fallthrough; case CRYP_KEY_SIZE_192: ctx->key_3_l = readl_relaxed(&src_reg->key_3_l); ctx->key_3_r = readl_relaxed(&src_reg->key_3_r); - /* Fall through */ + fallthrough; case CRYP_KEY_SIZE_128: ctx->key_2_l = readl_relaxed(&src_reg->key_2_l); ctx->key_2_r = readl_relaxed(&src_reg->key_2_r); - /* Fall through */ + fallthrough; default: ctx->key_1_l = readl_relaxed(&src_reg->key_1_l); @@ -364,17 +364,17 @@ void cryp_restore_device_context(struct cryp_device_data *device_data, case CRYP_KEY_SIZE_256: writel_relaxed(ctx->key_4_l, ®->key_4_l); writel_relaxed(ctx->key_4_r, ®->key_4_r); - /* Fall through */ + fallthrough; case CRYP_KEY_SIZE_192: writel_relaxed(ctx->key_3_l, ®->key_3_l); writel_relaxed(ctx->key_3_r, ®->key_3_r); - /* Fall through */ + fallthrough; case CRYP_KEY_SIZE_128: writel_relaxed(ctx->key_2_l, ®->key_2_l); writel_relaxed(ctx->key_2_r, ®->key_2_r); - /* Fall through */ + fallthrough; default: writel_relaxed(ctx->key_1_l, ®->key_1_l); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index c82cbcb64202..32642634c1bb 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -100,6 +100,12 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, return false; } + if (!dax_dev && !bdev_dax_supported(bdev, blocksize)) { + pr_debug("%s: error: dax unsupported by block device\n", + bdevname(bdev, buf)); + return false; + } + id = dax_read_lock(); len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn); len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn); diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c index 35f4804ea4af..235f1396f968 100644 --- a/drivers/dma/acpi-dma.c +++ b/drivers/dma/acpi-dma.c @@ -135,11 +135,13 @@ static void acpi_dma_parse_csrt(struct acpi_device *adev, struct acpi_dma *adma) if (ret < 0) { dev_warn(&adev->dev, "error in parsing resource group\n"); - return; + break; } grp = (struct acpi_csrt_group *)((void *)grp + grp->length); } + + acpi_put_table((struct acpi_table_header *)csrt); } /** diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c index 9adc7a2fa3d3..a24882ba3764 100644 --- a/drivers/dma/amba-pl08x.c +++ b/drivers/dma/amba-pl08x.c @@ -1767,7 +1767,7 @@ static u32 pl08x_memcpy_cctl(struct pl08x_driver_data *pl08x) default: dev_err(&pl08x->adev->dev, "illegal burst size for memcpy, set to 1\n"); - /* Fall through */ + fallthrough; case PL08X_BURST_SZ_1: cctl |= PL080_BSIZE_1 << PL080_CONTROL_SB_SIZE_SHIFT | PL080_BSIZE_1 << PL080_CONTROL_DB_SIZE_SHIFT; @@ -1806,7 +1806,7 @@ static u32 pl08x_memcpy_cctl(struct pl08x_driver_data *pl08x) default: dev_err(&pl08x->adev->dev, "illegal bus width for memcpy, set to 8 bits\n"); - /* Fall through */ + fallthrough; case PL08X_BUS_WIDTH_8_BITS: cctl |= PL080_WIDTH_8BIT << PL080_CONTROL_SWIDTH_SHIFT | PL080_WIDTH_8BIT << PL080_CONTROL_DWIDTH_SHIFT; @@ -1850,7 +1850,7 @@ static u32 pl08x_ftdmac020_memcpy_cctl(struct pl08x_driver_data *pl08x) default: dev_err(&pl08x->adev->dev, "illegal bus width for memcpy, set to 8 bits\n"); - /* Fall through */ + fallthrough; case PL08X_BUS_WIDTH_8_BITS: cctl |= PL080_WIDTH_8BIT << FTDMAC020_LLI_SRC_WIDTH_SHIFT | PL080_WIDTH_8BIT << FTDMAC020_LLI_DST_WIDTH_SHIFT; @@ -2612,7 +2612,7 @@ static int pl08x_of_probe(struct amba_device *adev, switch (val) { default: dev_err(&adev->dev, "illegal burst size for memcpy, set to 1\n"); - /* Fall through */ + fallthrough; case 1: pd->memcpy_burst_size = PL08X_BURST_SZ_1; break; @@ -2647,7 +2647,7 @@ static int pl08x_of_probe(struct amba_device *adev, switch (val) { default: dev_err(&adev->dev, "illegal bus width for memcpy, set to 8 bits\n"); - /* Fall through */ + fallthrough; case 8: pd->memcpy_bus_width = PL08X_BUS_WIDTH_8_BITS; break; diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 45bbcd6146fd..a2cf25c6e3b3 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -1650,13 +1650,17 @@ static struct dma_chan *at_dma_xlate(struct of_phandle_args *dma_spec, return NULL; dmac_pdev = of_find_device_by_node(dma_spec->np); + if (!dmac_pdev) + return NULL; dma_cap_zero(mask); dma_cap_set(DMA_SLAVE, mask); atslave = kmalloc(sizeof(*atslave), GFP_KERNEL); - if (!atslave) + if (!atslave) { + put_device(&dmac_pdev->dev); return NULL; + } atslave->cfg = ATC_DST_H2SEL_HW | ATC_SRC_H2SEL_HW; /* @@ -1685,8 +1689,11 @@ static struct dma_chan *at_dma_xlate(struct of_phandle_args *dma_spec, atslave->dma_dev = &dmac_pdev->dev; chan = dma_request_channel(mask, at_dma_filter, atslave); - if (!chan) + if (!chan) { + put_device(&dmac_pdev->dev); + kfree(atslave); return NULL; + } atchan = to_at_dma_chan(chan); atchan->per_if = dma_spec->args[0] & 0xff; diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c index 448f663da89c..8beed91428bd 100644 --- a/drivers/dma/dma-jz4780.c +++ b/drivers/dma/dma-jz4780.c @@ -879,24 +879,11 @@ static int jz4780_dma_probe(struct platform_device *pdev) return -EINVAL; } - ret = platform_get_irq(pdev, 0); - if (ret < 0) - return ret; - - jzdma->irq = ret; - - ret = request_irq(jzdma->irq, jz4780_dma_irq_handler, 0, dev_name(dev), - jzdma); - if (ret) { - dev_err(dev, "failed to request IRQ %u!\n", jzdma->irq); - return ret; - } - jzdma->clk = devm_clk_get(dev, NULL); if (IS_ERR(jzdma->clk)) { dev_err(dev, "failed to get clock\n"); ret = PTR_ERR(jzdma->clk); - goto err_free_irq; + return ret; } clk_prepare_enable(jzdma->clk); @@ -949,10 +936,23 @@ static int jz4780_dma_probe(struct platform_device *pdev) jzchan->vchan.desc_free = jz4780_dma_desc_free; } + ret = platform_get_irq(pdev, 0); + if (ret < 0) + goto err_disable_clk; + + jzdma->irq = ret; + + ret = request_irq(jzdma->irq, jz4780_dma_irq_handler, 0, dev_name(dev), + jzdma); + if (ret) { + dev_err(dev, "failed to request IRQ %u!\n", jzdma->irq); + goto err_disable_clk; + } + ret = dmaenginem_async_device_register(dd); if (ret) { dev_err(dev, "failed to register device\n"); - goto err_disable_clk; + goto err_free_irq; } /* Register with OF DMA helpers. */ @@ -960,17 +960,17 @@ static int jz4780_dma_probe(struct platform_device *pdev) jzdma); if (ret) { dev_err(dev, "failed to register OF DMA controller\n"); - goto err_disable_clk; + goto err_free_irq; } dev_info(dev, "JZ4780 DMA controller initialised\n"); return 0; -err_disable_clk: - clk_disable_unprepare(jzdma->clk); - err_free_irq: free_irq(jzdma->irq, jzdma); + +err_disable_clk: + clk_disable_unprepare(jzdma->clk); return ret; } diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c index ed430ad9b3dd..b971505b8715 100644 --- a/drivers/dma/dw-edma/dw-edma-core.c +++ b/drivers/dma/dw-edma/dw-edma-core.c @@ -405,7 +405,7 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer) if (xfer->cyclic) { burst->dar = xfer->xfer.cyclic.paddr; } else { - burst->dar = sg_dma_address(sg); + burst->dar = dst_addr; /* Unlike the typical assumption by other * drivers/IPs the peripheral memory isn't * a FIFO memory, in this case, it's a @@ -413,14 +413,13 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer) * and destination addresses are increased * by the same portion (data length) */ - src_addr += sg_dma_len(sg); } } else { burst->dar = dst_addr; if (xfer->cyclic) { burst->sar = xfer->xfer.cyclic.paddr; } else { - burst->sar = sg_dma_address(sg); + burst->sar = src_addr; /* Unlike the typical assumption by other * drivers/IPs the peripheral memory isn't * a FIFO memory, in this case, it's a @@ -428,12 +427,14 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer) * and destination addresses are increased * by the same portion (data length) */ - dst_addr += sg_dma_len(sg); } } - if (!xfer->cyclic) + if (!xfer->cyclic) { + src_addr += sg_dma_len(sg); + dst_addr += sg_dma_len(sg); sg = sg_next(sg); + } } return vchan_tx_prep(&chan->vc, &desc->vd, xfer->flags); diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index ad72b3f42ffa..e342cf52d296 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -1163,7 +1163,7 @@ static int fsl_dma_chan_probe(struct fsldma_device *fdev, switch (chan->feature & FSL_DMA_IP_MASK) { case FSL_DMA_IP_85XX: chan->toggle_ext_pause = fsl_chan_toggle_ext_pause; - /* Fall through */ + fallthrough; case FSL_DMA_IP_83XX: chan->toggle_ext_start = fsl_chan_toggle_ext_start; chan->set_src_loop_size = fsl_chan_set_src_loop_size; diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h index 56f18ae99233..308bed0a560a 100644 --- a/drivers/dma/fsldma.h +++ b/drivers/dma/fsldma.h @@ -205,10 +205,10 @@ struct fsldma_chan { #else static u64 fsl_ioread64(const u64 __iomem *addr) { - u32 fsl_addr = lower_32_bits(addr); - u64 fsl_addr_hi = (u64)in_le32((u32 *)(fsl_addr + 1)) << 32; + u32 val_lo = in_le32((u32 __iomem *)addr); + u32 val_hi = in_le32((u32 __iomem *)addr + 1); - return fsl_addr_hi | in_le32((u32 *)fsl_addr); + return ((u64)val_hi << 32) + val_lo; } static void fsl_iowrite64(u64 val, u64 __iomem *addr) @@ -219,10 +219,10 @@ static void fsl_iowrite64(u64 val, u64 __iomem *addr) static u64 fsl_ioread64be(const u64 __iomem *addr) { - u32 fsl_addr = lower_32_bits(addr); - u64 fsl_addr_hi = (u64)in_be32((u32 *)fsl_addr) << 32; + u32 val_hi = in_be32((u32 __iomem *)addr); + u32 val_lo = in_be32((u32 __iomem *)addr + 1); - return fsl_addr_hi | in_be32((u32 *)(fsl_addr + 1)); + return ((u64)val_hi << 32) + val_lo; } static void fsl_iowrite64be(u64 val, u64 __iomem *addr) diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 14b45853aa5f..b75d699160bf 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -410,10 +410,27 @@ int idxd_device_enable(struct idxd_device *idxd) return 0; } +void idxd_device_wqs_clear_state(struct idxd_device *idxd) +{ + int i; + + lockdep_assert_held(&idxd->dev_lock); + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + if (wq->state == IDXD_WQ_ENABLED) { + idxd_wq_disable_cleanup(wq); + wq->state = IDXD_WQ_DISABLED; + } + } +} + int idxd_device_disable(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; u32 status; + unsigned long flags; if (!idxd_is_enabled(idxd)) { dev_dbg(dev, "Device is not enabled\n"); @@ -429,13 +446,22 @@ int idxd_device_disable(struct idxd_device *idxd) return -ENXIO; } + spin_lock_irqsave(&idxd->dev_lock, flags); + idxd_device_wqs_clear_state(idxd); idxd->state = IDXD_DEV_CONF_READY; + spin_unlock_irqrestore(&idxd->dev_lock, flags); return 0; } void idxd_device_reset(struct idxd_device *idxd) { + unsigned long flags; + idxd_cmd_exec(idxd, IDXD_CMD_RESET_DEVICE, 0, NULL); + spin_lock_irqsave(&idxd->dev_lock, flags); + idxd_device_wqs_clear_state(idxd); + idxd->state = IDXD_DEV_CONF_READY; + spin_unlock_irqrestore(&idxd->dev_lock, flags); } /* Device configuration bits */ diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index b5142556cc4e..1e9e6991f543 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -11,18 +11,6 @@ #include "idxd.h" #include "registers.h" -void idxd_device_wqs_clear_state(struct idxd_device *idxd) -{ - int i; - - lockdep_assert_held(&idxd->dev_lock); - for (i = 0; i < idxd->max_wqs; i++) { - struct idxd_wq *wq = &idxd->wqs[i]; - - wq->state = IDXD_WQ_DISABLED; - } -} - static void idxd_device_reinit(struct work_struct *work) { struct idxd_device *idxd = container_of(work, struct idxd_device, work); diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index 5c0fb3134825..88717506c1f6 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -556,7 +556,7 @@ static int imxdma_xfer_desc(struct imxdma_desc *d) * We fall-through here intentionally, since a 2D transfer is * similar to MEMCPY just adding the 2D slot configuration. */ - /* Fall through */ + fallthrough; case IMXDMA_DESC_MEMCPY: imx_dmav1_writel(imxdma, d->src, DMA_SAR(imxdmac->channel)); imx_dmav1_writel(imxdma, d->dest, DMA_DAR(imxdmac->channel)); diff --git a/drivers/dma/iop-adma.h b/drivers/dma/iop-adma.h index c499c9578f00..d44eabb6f5eb 100644 --- a/drivers/dma/iop-adma.h +++ b/drivers/dma/iop-adma.h @@ -496,7 +496,7 @@ iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt, } hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = edcr; src_cnt = 24; - /* fall through */ + fallthrough; case 17 ... 24: if (!u_desc_ctrl.field.blk_ctrl) { hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = 0; @@ -510,7 +510,7 @@ iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt, } hw_desc->src_edc[AAU_EDCR1_IDX].e_desc_ctrl = edcr; src_cnt = 16; - /* fall through */ + fallthrough; case 9 ... 16: if (!u_desc_ctrl.field.blk_ctrl) u_desc_ctrl.field.blk_ctrl = 0x2; /* use EDCR0 */ @@ -522,7 +522,7 @@ iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt, } hw_desc->src_edc[AAU_EDCR0_IDX].e_desc_ctrl = edcr; src_cnt = 8; - /* fall through */ + fallthrough; case 2 ... 8: shift = 1; for (i = 0; i < src_cnt; i++) { @@ -602,19 +602,19 @@ iop_desc_init_null_xor(struct iop_adma_desc_slot *desc, int src_cnt, case 25 ... 32: u_desc_ctrl.field.blk_ctrl = 0x3; /* use EDCR[2:0] */ hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = 0; - /* fall through */ + fallthrough; case 17 ... 24: if (!u_desc_ctrl.field.blk_ctrl) { hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = 0; u_desc_ctrl.field.blk_ctrl = 0x3; /* use EDCR[2:0] */ } hw_desc->src_edc[AAU_EDCR1_IDX].e_desc_ctrl = 0; - /* fall through */ + fallthrough; case 9 ... 16: if (!u_desc_ctrl.field.blk_ctrl) u_desc_ctrl.field.blk_ctrl = 0x2; /* use EDCR0 */ hw_desc->src_edc[AAU_EDCR0_IDX].e_desc_ctrl = 0; - /* fall through */ + fallthrough; case 1 ... 8: if (!u_desc_ctrl.field.blk_ctrl && src_cnt > 4) u_desc_ctrl.field.blk_ctrl = 0x1; /* use mini-desc */ diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c index 74df621402e1..ca4e0930207a 100644 --- a/drivers/dma/nbpfaxi.c +++ b/drivers/dma/nbpfaxi.c @@ -483,7 +483,7 @@ static size_t nbpf_xfer_size(struct nbpf_device *nbpf, default: pr_warn("%s(): invalid bus width %u\n", __func__, width); - /* fall through */ + fallthrough; case DMA_SLAVE_BUSWIDTH_1_BYTE: size = burst; } diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c index 863f2aaf5c8f..8a4f608904b9 100644 --- a/drivers/dma/of-dma.c +++ b/drivers/dma/of-dma.c @@ -71,12 +71,12 @@ static struct dma_chan *of_dma_router_xlate(struct of_phandle_args *dma_spec, return NULL; chan = ofdma_target->of_dma_xlate(&dma_spec_target, ofdma_target); - if (chan) { - chan->router = ofdma->dma_router; - chan->route_data = route_data; - } else { + if (IS_ERR_OR_NULL(chan)) { ofdma->dma_router->route_free(ofdma->dma_router->dev, route_data); + } else { + chan->router = ofdma->dma_router; + chan->route_data = route_data; } /* diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 2c508ee672b9..5274a0704d96 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1061,16 +1061,16 @@ static bool _start(struct pl330_thread *thrd) if (_state(thrd) == PL330_STATE_KILLING) UNTIL(thrd, PL330_STATE_STOPPED) - /* fall through */ + fallthrough; case PL330_STATE_FAULTING: _stop(thrd); - /* fall through */ + fallthrough; case PL330_STATE_KILLING: case PL330_STATE_COMPLETING: UNTIL(thrd, PL330_STATE_STOPPED) - /* fall through */ + fallthrough; case PL330_STATE_STOPPED: return _trigger(thrd); @@ -1121,7 +1121,6 @@ static u32 _emit_load(unsigned int dry_run, u8 buf[], switch (direction) { case DMA_MEM_TO_MEM: - /* fall through */ case DMA_MEM_TO_DEV: off += _emit_LD(dry_run, &buf[off], cond); break; @@ -1155,7 +1154,6 @@ static inline u32 _emit_store(unsigned int dry_run, u8 buf[], switch (direction) { case DMA_MEM_TO_MEM: - /* fall through */ case DMA_DEV_TO_MEM: off += _emit_ST(dry_run, &buf[off], cond); break; @@ -1216,7 +1214,6 @@ static int _bursts(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[], switch (pxs->desc->rqtype) { case DMA_MEM_TO_DEV: - /* fall through */ case DMA_DEV_TO_MEM: off += _ldst_peripheral(pl330, dry_run, &buf[off], pxs, cyc, cond); @@ -1266,7 +1263,6 @@ static int _dregs(struct pl330_dmac *pl330, unsigned int dry_run, u8 buf[], switch (pxs->desc->rqtype) { case DMA_MEM_TO_DEV: - /* fall through */ case DMA_DEV_TO_MEM: off += _emit_MOV(dry_run, &buf[off], CCR, dregs_ccr); off += _ldst_peripheral(pl330, dry_run, &buf[off], pxs, 1, @@ -2801,6 +2797,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, while (burst != (1 << desc->rqcfg.brst_size)) desc->rqcfg.brst_size++; + desc->rqcfg.brst_len = get_burst_len(desc, len); /* * If burst size is smaller than bus width then make sure we only * transfer one at a time to avoid a burst stradling an MFIFO entry. @@ -2808,7 +2805,6 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width) desc->rqcfg.brst_len = 1; - desc->rqcfg.brst_len = get_burst_len(desc, len); desc->bytes_requested = len; desc->txd.flags = flags; diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c index 2deeaab078a4..788d696323bb 100644 --- a/drivers/dma/sh/shdma-base.c +++ b/drivers/dma/sh/shdma-base.c @@ -383,7 +383,7 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all) switch (desc->mark) { case DESC_COMPLETED: desc->mark = DESC_WAITING; - /* Fall through */ + fallthrough; case DESC_WAITING: if (head_acked) async_tx_ack(&desc->async_tx); diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index c14e6cb105cd..d86dba0fd8e6 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -2059,9 +2059,9 @@ udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl, return NULL; } - cppi5_tr_init(&tr_req[i].flags, CPPI5_TR_TYPE1, false, false, - CPPI5_TR_EVENT_SIZE_COMPLETION, 0); - cppi5_tr_csf_set(&tr_req[i].flags, CPPI5_TR_CSF_SUPR_EVT); + cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, false, + false, CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + cppi5_tr_csf_set(&tr_req[tr_idx].flags, CPPI5_TR_CSF_SUPR_EVT); tr_req[tr_idx].addr = sg_addr; tr_req[tr_idx].icnt0 = tr0_cnt0; @@ -3101,14 +3101,14 @@ static struct udma_match_data am654_main_data = { .psil_base = 0x1000, .enable_memcpy_support = true, .statictr_z_mask = GENMASK(11, 0), - .rchan_oes_offset = 0x2000, + .rchan_oes_offset = 0x200, }; static struct udma_match_data am654_mcu_data = { .psil_base = 0x6000, .enable_memcpy_support = false, .statictr_z_mask = GENMASK(11, 0), - .rchan_oes_offset = 0x2000, + .rchan_oes_offset = 0x200, }; static struct udma_match_data j721e_main_data = { diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 6262f6370c5d..fcc08bbf6945 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -3375,7 +3375,7 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt) pvt->ops = &family_types[F17_M70H_CPUS].ops; break; } - /* fall through */ + fallthrough; case 0x18: fam_type = &family_types[F17_CPUS]; pvt->ops = &family_types[F17_CPUS].ops; diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index da60c29468a7..54ebc8afc6b1 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -55,6 +55,8 @@ static DEFINE_SPINLOCK(ghes_lock); static bool __read_mostly force_load; module_param(force_load, bool, 0); +static bool system_scanned; + /* Memory Device - Type 17 of SMBIOS spec */ struct memdev_dmi_entry { u8 type; @@ -225,14 +227,12 @@ static void enumerate_dimms(const struct dmi_header *dh, void *arg) static void ghes_scan_system(void) { - static bool scanned; - - if (scanned) + if (system_scanned) return; dmi_walk(enumerate_dimms, &ghes_hw); - scanned = true; + system_scanned = true; } void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) @@ -631,6 +631,8 @@ void ghes_edac_unregister(struct ghes *ghes) mutex_lock(&ghes_reg_mutex); + system_scanned = false; + if (!refcount_dec_and_test(&ghes_refcount)) goto unlock; diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 5860ca41185c..2acd9f9284a2 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1710,9 +1710,9 @@ static void i7core_mce_output_error(struct mem_ctl_info *mci, if (uncorrected_error) { core_err_cnt = 1; if (ripv) - tp_event = HW_EVENT_ERR_FATAL; - else tp_event = HW_EVENT_ERR_UNCORRECTED; + else + tp_event = HW_EVENT_ERR_FATAL; } else { tp_event = HW_EVENT_ERR_CORRECTED; } diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c index fd363746f5b0..928f63a374c7 100644 --- a/drivers/edac/pnd2_edac.c +++ b/drivers/edac/pnd2_edac.c @@ -198,7 +198,7 @@ static int apl_rd_reg(int port, int off, int op, void *data, size_t sz, char *na switch (sz) { case 8: ret = _apl_rd_reg(port, off + 4, op, (u32 *)(data + 4)); - /* fall through */ + fallthrough; case 4: ret |= _apl_rd_reg(port, off, op, (u32 *)data); pnd2_printk(KERN_DEBUG, "%s=%x%08x ret=%d\n", name, @@ -1155,7 +1155,7 @@ static void pnd2_mce_output_error(struct mem_ctl_info *mci, const struct mce *m, u32 optypenum = GET_BITFIELD(m->status, 4, 6); int rc; - tp_event = uc_err ? (ripv ? HW_EVENT_ERR_FATAL : HW_EVENT_ERR_UNCORRECTED) : + tp_event = uc_err ? (ripv ? HW_EVENT_ERR_UNCORRECTED : HW_EVENT_ERR_FATAL) : HW_EVENT_ERR_CORRECTED; /* diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index d414698ca324..c5ab634cb6a4 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -2982,9 +2982,9 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, if (uncorrected_error) { core_err_cnt = 1; if (ripv) { - tp_event = HW_EVENT_ERR_FATAL; - } else { tp_event = HW_EVENT_ERR_UNCORRECTED; + } else { + tp_event = HW_EVENT_ERR_FATAL; } } else { tp_event = HW_EVENT_ERR_CORRECTED; diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 6d8d6dc626bf..2b4ce8e5ac2f 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -493,9 +493,9 @@ static void skx_mce_output_error(struct mem_ctl_info *mci, if (uncorrected_error) { core_err_cnt = 1; if (ripv) { - tp_event = HW_EVENT_ERR_FATAL; - } else { tp_event = HW_EVENT_ERR_UNCORRECTED; + } else { + tp_event = HW_EVENT_ERR_FATAL; } } else { tp_event = HW_EVENT_ERR_CORRECTED; diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index b785e936244f..80db43a22069 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -957,7 +957,7 @@ static void set_broadcast_channel(struct fw_device *device, int generation) device->bc_implemented = BC_IMPLEMENTED; break; } - /* else, fall through - to case address error */ + fallthrough; /* to case address error */ case RCODE_ADDRESS_ERROR: device->bc_implemented = BC_UNIMPLEMENTED; } diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index 185b0b78b3d6..af70e74f9a7e 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -277,7 +277,7 @@ static int manage_channel(struct fw_card *card, int irm_id, int generation, if ((data[0] & bit) == (data[1] & bit)) continue; - /* fall through - It's a 1394-1995 IRM, retry. */ + fallthrough; /* It's a 1394-1995 IRM, retry */ default: if (retry) { retry--; diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index 94a13fca8267..ec68ed27b0a5 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -54,7 +54,7 @@ static u32 *count_ports(u32 *sid, int *total_port_count, int *child_port_count) switch (port_type) { case SELFID_PORT_CHILD: (*child_port_count)++; - /* fall through */ + fallthrough; case SELFID_PORT_PARENT: case SELFID_PORT_NCONN: (*total_port_count)++; diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index 439d918bbaaf..ac487c96bb71 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -1097,14 +1097,14 @@ static void handle_registers(struct fw_card *card, struct fw_request *request, rcode = RCODE_ADDRESS_ERROR; break; } - /* else fall through */ + fallthrough; case CSR_NODE_IDS: /* * per IEEE 1394-2008 8.3.22.3, not IEEE 1394.1-2004 3.2.8 * and 9.6, but interoperable with IEEE 1394.1-2004 bridges */ - /* fall through */ + fallthrough; case CSR_STATE_CLEAR: case CSR_STATE_SET: diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 7dde21b18b04..020cb15a4d8f 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -1495,7 +1495,7 @@ static int handle_at_packet(struct context *context, packet->ack = RCODE_GENERATION; break; } - /* fall through */ + fallthrough; default: packet->ack = RCODE_SEND_ERROR; @@ -3054,7 +3054,7 @@ static int ohci_start_iso(struct fw_iso_context *base, case FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL: control |= IR_CONTEXT_BUFFER_FILL|IR_CONTEXT_MULTI_CHANNEL_MODE; - /* fall through */ + fallthrough; case FW_ISO_CONTEXT_RECEIVE: index = ctx - ohci->ir_context_list; match = (tags << 28) | (sync << 8) | ctx->base.channel; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index fdd1db025dbf..3aa07c3b5136 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -381,6 +381,7 @@ static int __init efisubsys_init(void) efi_kobj = kobject_create_and_add("efi", firmware_kobj); if (!efi_kobj) { pr_err("efi: Firmware registration failed.\n"); + destroy_workqueue(efi_rts_wq); return -ENOMEM; } @@ -424,6 +425,7 @@ err_unregister: generic_ops_unregister(); err_put: kobject_put(efi_kobj); + destroy_workqueue(efi_rts_wq); return error; } diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 6bca70bbb43d..f735db55adc0 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -187,20 +187,28 @@ int efi_printk(const char *fmt, ...) */ efi_status_t efi_parse_options(char const *cmdline) { - size_t len = strlen(cmdline) + 1; + size_t len; efi_status_t status; char *str, *buf; + if (!cmdline) + return EFI_SUCCESS; + + len = strnlen(cmdline, COMMAND_LINE_SIZE - 1) + 1; status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, len, (void **)&buf); if (status != EFI_SUCCESS) return status; - str = skip_spaces(memcpy(buf, cmdline, len)); + memcpy(buf, cmdline, len - 1); + buf[len - 1] = '\0'; + str = skip_spaces(buf); while (*str) { char *param, *val; str = next_arg(str, ¶m, &val); + if (!val && !strcmp(param, "--")) + break; if (!strcmp(param, "nokaslr")) { efi_nokaslr = true; diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c index 53cee17d0115..722af9ee53d6 100644 --- a/drivers/firmware/ti_sci.c +++ b/drivers/firmware/ti_sci.c @@ -65,36 +65,18 @@ struct ti_sci_xfers_info { }; /** - * struct ti_sci_rm_type_map - Structure representing TISCI Resource - * management representation of dev_ids. - * @dev_id: TISCI device ID - * @type: Corresponding id as identified by TISCI RM. - * - * Note: This is used only as a work around for using RM range apis - * for AM654 SoC. For future SoCs dev_id will be used as type - * for RM range APIs. In order to maintain ABI backward compatibility - * type is not being changed for AM654 SoC. - */ -struct ti_sci_rm_type_map { - u32 dev_id; - u16 type; -}; - -/** * struct ti_sci_desc - Description of SoC integration * @default_host_id: Host identifier representing the compute entity * @max_rx_timeout_ms: Timeout for communication with SoC (in Milliseconds) * @max_msgs: Maximum number of messages that can be pending * simultaneously in the system * @max_msg_size: Maximum size of data per message that can be handled. - * @rm_type_map: RM resource type mapping structure. */ struct ti_sci_desc { u8 default_host_id; int max_rx_timeout_ms; int max_msgs; int max_msg_size; - struct ti_sci_rm_type_map *rm_type_map; }; /** @@ -1710,33 +1692,6 @@ fail: return ret; } -static int ti_sci_get_resource_type(struct ti_sci_info *info, u16 dev_id, - u16 *type) -{ - struct ti_sci_rm_type_map *rm_type_map = info->desc->rm_type_map; - bool found = false; - int i; - - /* If map is not provided then assume dev_id is used as type */ - if (!rm_type_map) { - *type = dev_id; - return 0; - } - - for (i = 0; rm_type_map[i].dev_id; i++) { - if (rm_type_map[i].dev_id == dev_id) { - *type = rm_type_map[i].type; - found = true; - break; - } - } - - if (!found) - return -EINVAL; - - return 0; -} - /** * ti_sci_get_resource_range - Helper to get a range of resources assigned * to a host. Resource is uniquely identified by @@ -1760,7 +1715,6 @@ static int ti_sci_get_resource_range(const struct ti_sci_handle *handle, struct ti_sci_xfer *xfer; struct ti_sci_info *info; struct device *dev; - u16 type; int ret = 0; if (IS_ERR(handle)) @@ -1780,15 +1734,9 @@ static int ti_sci_get_resource_range(const struct ti_sci_handle *handle, return ret; } - ret = ti_sci_get_resource_type(info, dev_id, &type); - if (ret) { - dev_err(dev, "rm type lookup failed for %u\n", dev_id); - goto fail; - } - req = (struct ti_sci_msg_req_get_resource_range *)xfer->xfer_buf; req->secondary_host = s_host; - req->type = type & MSG_RM_RESOURCE_TYPE_MASK; + req->type = dev_id & MSG_RM_RESOURCE_TYPE_MASK; req->subtype = subtype & MSG_RM_RESOURCE_SUBTYPE_MASK; ret = ti_sci_do_xfer(info, xfer); @@ -3260,61 +3208,50 @@ u32 ti_sci_get_num_resources(struct ti_sci_resource *res) EXPORT_SYMBOL_GPL(ti_sci_get_num_resources); /** - * devm_ti_sci_get_of_resource() - Get a TISCI resource assigned to a device + * devm_ti_sci_get_resource_sets() - Get a TISCI resources assigned to a device * @handle: TISCI handle * @dev: Device pointer to which the resource is assigned * @dev_id: TISCI device id to which the resource is assigned - * @of_prop: property name by which the resource are represented + * @sub_types: Array of sub_types assigned corresponding to device + * @sets: Number of sub_types * * Return: Pointer to ti_sci_resource if all went well else appropriate * error pointer. */ -struct ti_sci_resource * -devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, - struct device *dev, u32 dev_id, char *of_prop) +static struct ti_sci_resource * +devm_ti_sci_get_resource_sets(const struct ti_sci_handle *handle, + struct device *dev, u32 dev_id, u32 *sub_types, + u32 sets) { struct ti_sci_resource *res; bool valid_set = false; - u32 resource_subtype; int i, ret; res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL); if (!res) return ERR_PTR(-ENOMEM); - ret = of_property_count_elems_of_size(dev_of_node(dev), of_prop, - sizeof(u32)); - if (ret < 0) { - dev_err(dev, "%s resource type ids not available\n", of_prop); - return ERR_PTR(ret); - } - res->sets = ret; - + res->sets = sets; res->desc = devm_kcalloc(dev, res->sets, sizeof(*res->desc), GFP_KERNEL); if (!res->desc) return ERR_PTR(-ENOMEM); for (i = 0; i < res->sets; i++) { - ret = of_property_read_u32_index(dev_of_node(dev), of_prop, i, - &resource_subtype); - if (ret) - return ERR_PTR(-EINVAL); - ret = handle->ops.rm_core_ops.get_range(handle, dev_id, - resource_subtype, + sub_types[i], &res->desc[i].start, &res->desc[i].num); if (ret) { dev_dbg(dev, "dev = %d subtype %d not allocated for this host\n", - dev_id, resource_subtype); + dev_id, sub_types[i]); res->desc[i].start = 0; res->desc[i].num = 0; continue; } dev_dbg(dev, "dev = %d, subtype = %d, start = %d, num = %d\n", - dev_id, resource_subtype, res->desc[i].start, + dev_id, sub_types[i], res->desc[i].start, res->desc[i].num); valid_set = true; @@ -3332,6 +3269,62 @@ devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, return ERR_PTR(-EINVAL); } +/** + * devm_ti_sci_get_of_resource() - Get a TISCI resource assigned to a device + * @handle: TISCI handle + * @dev: Device pointer to which the resource is assigned + * @dev_id: TISCI device id to which the resource is assigned + * @of_prop: property name by which the resource are represented + * + * Return: Pointer to ti_sci_resource if all went well else appropriate + * error pointer. + */ +struct ti_sci_resource * +devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, + struct device *dev, u32 dev_id, char *of_prop) +{ + struct ti_sci_resource *res; + u32 *sub_types; + int sets; + + sets = of_property_count_elems_of_size(dev_of_node(dev), of_prop, + sizeof(u32)); + if (sets < 0) { + dev_err(dev, "%s resource type ids not available\n", of_prop); + return ERR_PTR(sets); + } + + sub_types = kcalloc(sets, sizeof(*sub_types), GFP_KERNEL); + if (!sub_types) + return ERR_PTR(-ENOMEM); + + of_property_read_u32_array(dev_of_node(dev), of_prop, sub_types, sets); + res = devm_ti_sci_get_resource_sets(handle, dev, dev_id, sub_types, + sets); + + kfree(sub_types); + return res; +} +EXPORT_SYMBOL_GPL(devm_ti_sci_get_of_resource); + +/** + * devm_ti_sci_get_resource() - Get a resource range assigned to the device + * @handle: TISCI handle + * @dev: Device pointer to which the resource is assigned + * @dev_id: TISCI device id to which the resource is assigned + * @suub_type: TISCI resource subytpe representing the resource. + * + * Return: Pointer to ti_sci_resource if all went well else appropriate + * error pointer. + */ +struct ti_sci_resource * +devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, + u32 dev_id, u32 sub_type) +{ + return devm_ti_sci_get_resource_sets(handle, dev, dev_id, &sub_type, 1); +} +EXPORT_SYMBOL_GPL(devm_ti_sci_get_resource); + static int tisci_reboot_handler(struct notifier_block *nb, unsigned long mode, void *cmd) { @@ -3352,17 +3345,6 @@ static const struct ti_sci_desc ti_sci_pmmc_k2g_desc = { /* Limited by MBOX_TX_QUEUE_LEN. K2G can handle upto 128 messages! */ .max_msgs = 20, .max_msg_size = 64, - .rm_type_map = NULL, -}; - -static struct ti_sci_rm_type_map ti_sci_am654_rm_type_map[] = { - {.dev_id = 56, .type = 0x00b}, /* GIC_IRQ */ - {.dev_id = 179, .type = 0x000}, /* MAIN_NAV_UDMASS_IA0 */ - {.dev_id = 187, .type = 0x009}, /* MAIN_NAV_RA */ - {.dev_id = 188, .type = 0x006}, /* MAIN_NAV_UDMAP */ - {.dev_id = 194, .type = 0x007}, /* MCU_NAV_UDMAP */ - {.dev_id = 195, .type = 0x00a}, /* MCU_NAV_RA */ - {.dev_id = 0, .type = 0x000}, /* end of table */ }; /* Description for AM654 */ @@ -3373,7 +3355,6 @@ static const struct ti_sci_desc ti_sci_pmmc_am654_desc = { /* Limited by MBOX_TX_QUEUE_LEN. K2G can handle upto 128 messages! */ .max_msgs = 20, .max_msg_size = 60, - .rm_type_map = ti_sci_am654_rm_type_map, }; static const struct of_device_id ti_sci_of_match[] = { diff --git a/drivers/gpio/gpio-aspeed-sgpio.c b/drivers/gpio/gpio-aspeed-sgpio.c index d16645c1d8d9..3aa45934d60c 100644 --- a/drivers/gpio/gpio-aspeed-sgpio.c +++ b/drivers/gpio/gpio-aspeed-sgpio.c @@ -303,16 +303,16 @@ static int aspeed_sgpio_set_type(struct irq_data *d, unsigned int type) switch (type & IRQ_TYPE_SENSE_MASK) { case IRQ_TYPE_EDGE_BOTH: type2 |= bit; - /* fall through */ + fallthrough; case IRQ_TYPE_EDGE_RISING: type0 |= bit; - /* fall through */ + fallthrough; case IRQ_TYPE_EDGE_FALLING: handler = handle_edge_irq; break; case IRQ_TYPE_LEVEL_HIGH: type0 |= bit; - /* fall through */ + fallthrough; case IRQ_TYPE_LEVEL_LOW: type1 |= bit; handler = handle_level_irq; diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index 879db23d8454..bf08b4561f36 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -611,16 +611,16 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type) switch (type & IRQ_TYPE_SENSE_MASK) { case IRQ_TYPE_EDGE_BOTH: type2 |= bit; - /* fall through */ + fallthrough; case IRQ_TYPE_EDGE_RISING: type0 |= bit; - /* fall through */ + fallthrough; case IRQ_TYPE_EDGE_FALLING: handler = handle_edge_irq; break; case IRQ_TYPE_LEVEL_HIGH: type0 |= bit; - /* fall through */ + fallthrough; case IRQ_TYPE_LEVEL_LOW: type1 |= bit; handler = handle_level_irq; diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c index 53fae02c40ad..d5359341cc6b 100644 --- a/drivers/gpio/gpio-ath79.c +++ b/drivers/gpio/gpio-ath79.c @@ -129,7 +129,7 @@ static int ath79_gpio_irq_set_type(struct irq_data *data, case IRQ_TYPE_LEVEL_HIGH: polarity |= mask; - /* fall through */ + fallthrough; case IRQ_TYPE_LEVEL_LOW: type |= mask; break; diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index 8c9757774010..ad61daf6c212 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -617,14 +617,12 @@ static int sprd_eic_probe(struct platform_device *pdev) sprd_eic->chip.free = sprd_eic_free; sprd_eic->chip.set_config = sprd_eic_set_config; sprd_eic->chip.set = sprd_eic_set; - /* fall-through */ + fallthrough; case SPRD_EIC_ASYNC: - /* fall-through */ case SPRD_EIC_SYNC: sprd_eic->chip.get = sprd_eic_get; break; case SPRD_EIC_LATCH: - /* fall-through */ default: break; } diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c index 6c48809d0505..b0155d6007c8 100644 --- a/drivers/gpio/gpio-stmpe.c +++ b/drivers/gpio/gpio-stmpe.c @@ -308,7 +308,7 @@ static void stmpe_dbg_show_one(struct seq_file *s, if (ret < 0) return; edge_det = !!(ret & mask); - /* fall through */ + fallthrough; case STMPE1801: rise_reg = stmpe->regs[STMPE_IDX_GPRER_LSB + bank]; fall_reg = stmpe->regs[STMPE_IDX_GPFER_LSB + bank]; @@ -321,7 +321,7 @@ static void stmpe_dbg_show_one(struct seq_file *s, if (ret < 0) return; fall = !!(ret & mask); - /* fall through */ + fallthrough; case STMPE801: case STMPE1600: irqen_reg = stmpe->regs[STMPE_IDX_IEGPIOR_LSB + bank]; diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 9276051663da..54ca3c18b291 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1264,7 +1264,7 @@ static int acpi_gpio_package_count(const union acpi_object *obj) switch (element->type) { case ACPI_TYPE_LOCAL_REFERENCE: element += 3; - /* Fallthrough */ + fallthrough; case ACPI_TYPE_INTEGER: element++; count++; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c index 7e59e473a190..cdea1338c8dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c @@ -152,7 +152,7 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev, dev_warn(adev->dev, "Invalid sdma engine id (%d), using engine id 0\n", engine_id); - /* fall through */ + fallthrough; case 0: sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index c7fd0c47b254..1102de76d876 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -195,19 +195,32 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev, unsigned int engine_id, unsigned int queue_id) { - uint32_t sdma_engine_reg_base[2] = { - SOC15_REG_OFFSET(SDMA0, 0, - mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL, - SOC15_REG_OFFSET(SDMA1, 0, - mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL - }; - uint32_t retval = sdma_engine_reg_base[engine_id] + uint32_t sdma_engine_reg_base = 0; + uint32_t sdma_rlc_reg_offset; + + switch (engine_id) { + default: + dev_warn(adev->dev, + "Invalid sdma engine id (%d), using engine id 0\n", + engine_id); + fallthrough; + case 0: + sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0, + mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; + break; + case 1: + sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA1, 0, + mmSDMA1_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; + break; + } + + sdma_rlc_reg_offset = sdma_engine_reg_base + queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL); pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id, - queue_id, retval); + queue_id, sdma_rlc_reg_offset); - return retval; + return sdma_rlc_reg_offset; } static inline struct v9_mqd *get_mqd(void *mqd) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 0047da06041f..414548064648 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -179,6 +179,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) case CHIP_VEGA20: case CHIP_ARCTURUS: case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: /* enable runpm if runpm=1 */ if (amdgpu_runtime_pm > 0) adev->runpm = true; @@ -678,8 +679,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file * in the bitfields */ if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) se_num = 0xffffffff; + else if (se_num >= AMDGPU_GFX_MAX_SE) + return -EINVAL; if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) sh_num = 0xffffffff; + else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) + return -EINVAL; if (info->read_mmr_reg.count > 128) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 7fe564275457..d8c6520ff74a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -522,8 +522,7 @@ static int psp_asd_load(struct psp_context *psp) * add workaround to bypass it for sriov now. * TODO: add version check to make it common */ - if (amdgpu_sriov_vf(psp->adev) || - (psp->adev->asic_type == CHIP_NAVY_FLOUNDER)) + if (amdgpu_sriov_vf(psp->adev) || !psp->asd_fw) return 0; cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index bcce4c0be462..1bedb416eebd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1243,7 +1243,6 @@ void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, if (!obj || !obj->ent) return; - debugfs_remove(obj->ent); obj->ent = NULL; put_obj(obj); } @@ -1257,7 +1256,6 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev) amdgpu_ras_debugfs_remove(adev, &obj->head); } - debugfs_remove_recursive(con->dir); con->dir = NULL; } /* debugfs end */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 134cc36e30c5..0739e259bf91 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -462,7 +462,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, unsigned int pages; int i, r; - *sgt = kmalloc(sizeof(*sg), GFP_KERNEL); + *sgt = kmalloc(sizeof(**sgt), GFP_KERNEL); if (!*sgt) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 65997ffaed45..037a187aa42f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -7263,10 +7263,8 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK | RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK | - RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK); - - /* only for Vega10 & Raven1 */ - data |= RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK; + RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK | + RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK); if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 33f1c4a46ebe..88f63d7ea371 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -3250,7 +3250,7 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev) dev_warn(adev->dev, "Unknown chip type (%d) in function gfx_v8_0_tiling_mode_table_init() falling through to CHIP_CARRIZO\n", adev->asic_type); - /* fall through */ + fallthrough; case CHIP_CARRIZO: modearray[0] = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index cb9d60a4e05e..b95f22262a90 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -691,6 +691,7 @@ static const struct soc15_reg_golden golden_settings_gc_9_4_1_arct[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_5_ARCT, 0x3ff, 0x135), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_CONFIG, 0xffffffff, 0x011A0000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_FIFO_SIZES, 0xffffffff, 0x00000f00), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_UTCL1_CNTL1, 0x30000000, 0x30000000) }; static const struct soc15_reg_rlcg rlcg_access_gc_9_0[] = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c index fa0bca3e1f73..5d2505956f84 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c @@ -135,6 +135,12 @@ static void gfxhub_v2_1_init_cache_regs(struct amdgpu_device *adev) { uint32_t tmp; + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + /* Setup L2 cache */ tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_CNTL); tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL, ENABLE_L2_CACHE, 1); @@ -190,6 +196,12 @@ static void gfxhub_v2_1_enable_system_domain(struct amdgpu_device *adev) static void gfxhub_v2_1_disable_identity_aperture(struct amdgpu_device *adev) { + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32, 0xFFFFFFFF); WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_HI32, @@ -326,6 +338,13 @@ void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev, bool value) { u32 tmp; + + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL); tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL, RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 6e4f3ff4810f..b67ba38a195f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1297,7 +1297,7 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev) case CHIP_VEGA10: if (amdgpu_sriov_vf(adev)) break; - /* fall through */ + fallthrough; case CHIP_VEGA20: soc15_program_register_sequence(adev, golden_settings_mmhub_1_0_0, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index 757fa8e83f5b..c79fc54bc3c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -134,6 +134,12 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev) { uint32_t tmp; + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + /* Setup L2 cache */ tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL); tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL, ENABLE_L2_CACHE, 1); @@ -189,6 +195,12 @@ static void mmhub_v2_0_enable_system_domain(struct amdgpu_device *adev) static void mmhub_v2_0_disable_identity_aperture(struct amdgpu_device *adev) { + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32, 0xFFFFFFFF); @@ -318,6 +330,13 @@ void mmhub_v2_0_gart_disable(struct amdgpu_device *adev) void mmhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, bool value) { u32 tmp; + + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_PROTECTION_FAULT_CNTL); tmp = REG_SET_FIELD(tmp, MMVM_L2_PROTECTION_FAULT_CNTL, RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index da8024c2826e..ca11253e787c 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -364,6 +364,7 @@ nv_asic_reset_method(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: return AMD_RESET_METHOD_MODE1; default: if (smu_baco_is_support(smu)) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index d488d250805d..e16874f30d5d 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -179,12 +179,11 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) } break; case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: err = psp_init_ta_microcode(&adev->psp, chip_name); if (err) return err; break; - case CHIP_NAVY_FLOUNDER: - break; default: BUG(); } diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index ea914b256ebd..b5986d19dc08 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -6196,7 +6196,7 @@ static void si_request_link_speed_change_before_state_change(struct amdgpu_devic si_pi->force_pcie_gen = AMDGPU_PCIE_GEN2; if (current_link_speed == AMDGPU_PCIE_GEN2) break; - /* fall through */ + fallthrough; case AMDGPU_PCIE_GEN2: if (amdgpu_acpi_pcie_performance_request(adev, PCIE_PERF_REQ_PECI_GEN2, false) == 0) break; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index e4b33c67b634..b51c527a3f0d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2196,6 +2196,7 @@ void amdgpu_dm_update_connector_after_detect( drm_connector_update_edid_property(connector, aconnector->edid); + drm_add_edid_modes(connector, aconnector->edid); if (aconnector->dc_link->aux_mode) drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, @@ -2833,12 +2834,18 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) &dm_atomic_state_funcs); r = amdgpu_display_modeset_create_props(adev); - if (r) + if (r) { + dc_release_state(state->context); + kfree(state); return r; + } r = amdgpu_dm_audio_init(adev); - if (r) + if (r) { + dc_release_state(state->context); + kfree(state); return r; + } return 0; } @@ -2855,6 +2862,8 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm) #if defined(CONFIG_ACPI) struct amdgpu_dm_backlight_caps caps; + memset(&caps, 0, sizeof(caps)); + if (dm->backlight_caps.caps_valid) return; @@ -2893,51 +2902,50 @@ static int set_backlight_via_aux(struct dc_link *link, uint32_t brightness) return rc ? 0 : 1; } -static u32 convert_brightness(const struct amdgpu_dm_backlight_caps *caps, - const uint32_t user_brightness) +static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps, + unsigned *min, unsigned *max) { - u32 min, max, conversion_pace; - u32 brightness = user_brightness; - if (!caps) - goto out; + return 0; - if (!caps->aux_support) { - max = caps->max_input_signal; - min = caps->min_input_signal; - /* - * The brightness input is in the range 0-255 - * It needs to be rescaled to be between the - * requested min and max input signal - * It also needs to be scaled up by 0x101 to - * match the DC interface which has a range of - * 0 to 0xffff - */ - conversion_pace = 0x101; - brightness = - user_brightness - * conversion_pace - * (max - min) - / AMDGPU_MAX_BL_LEVEL - + min * conversion_pace; + if (caps->aux_support) { + // Firmware limits are in nits, DC API wants millinits. + *max = 1000 * caps->aux_max_input_signal; + *min = 1000 * caps->aux_min_input_signal; } else { - /* TODO - * We are doing a linear interpolation here, which is OK but - * does not provide the optimal result. We probably want - * something close to the Perceptual Quantizer (PQ) curve. - */ - max = caps->aux_max_input_signal; - min = caps->aux_min_input_signal; - - brightness = (AMDGPU_MAX_BL_LEVEL - user_brightness) * min - + user_brightness * max; - // Multiple the value by 1000 since we use millinits - brightness *= 1000; - brightness = DIV_ROUND_CLOSEST(brightness, AMDGPU_MAX_BL_LEVEL); + // Firmware limits are 8-bit, PWM control is 16-bit. + *max = 0x101 * caps->max_input_signal; + *min = 0x101 * caps->min_input_signal; } + return 1; +} -out: - return brightness; +static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *caps, + uint32_t brightness) +{ + unsigned min, max; + + if (!get_brightness_range(caps, &min, &max)) + return brightness; + + // Rescale 0..255 to min..max + return min + DIV_ROUND_CLOSEST((max - min) * brightness, + AMDGPU_MAX_BL_LEVEL); +} + +static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *caps, + uint32_t brightness) +{ + unsigned min, max; + + if (!get_brightness_range(caps, &min, &max)) + return brightness; + + if (brightness < min) + return 0; + // Rescale min..max to 0..255 + return DIV_ROUND_CLOSEST(AMDGPU_MAX_BL_LEVEL * (brightness - min), + max - min); } static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) @@ -2953,7 +2961,7 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) link = (struct dc_link *)dm->backlight_link; - brightness = convert_brightness(&caps, bd->props.brightness); + brightness = convert_brightness_from_user(&caps, bd->props.brightness); // Change brightness based on AUX property if (caps.aux_support) return set_backlight_via_aux(link, brightness); @@ -2970,7 +2978,7 @@ static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd) if (ret == DC_ERROR_UNEXPECTED) return bd->props.brightness; - return ret; + return convert_brightness_to_user(&dm->backlight_caps, ret); } static const struct backlight_ops amdgpu_dm_backlight_ops = { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index e85b58f0f416..336aaa09be46 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -67,7 +67,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload, &operation_result); - if (payload.write) + if (payload.write && result >= 0) result = msg->size; if (result < 0) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 078b7e344185..2d5c7daaee23 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1108,6 +1108,18 @@ static enum bp_result bios_parser_enable_disp_power_gating( action); } +static enum bp_result bios_parser_enable_lvtma_control( + struct dc_bios *dcb, + uint8_t uc_pwr_on) +{ + struct bios_parser *bp = BP_FROM_DCB(dcb); + + if (!bp->cmd_tbl.enable_lvtma_control) + return BP_RESULT_FAILURE; + + return bp->cmd_tbl.enable_lvtma_control(bp, uc_pwr_on); +} + static bool bios_parser_is_accelerated_mode( struct dc_bios *dcb) { @@ -2208,7 +2220,9 @@ static const struct dc_vbios_funcs vbios_funcs = { .get_board_layout_info = bios_get_board_layout_info, .pack_data_tables = bios_parser_pack_data_tables, - .get_atom_dc_golden_table = bios_get_atom_dc_golden_table + .get_atom_dc_golden_table = bios_get_atom_dc_golden_table, + + .enable_lvtma_control = bios_parser_enable_lvtma_control }; static bool bios_parser2_construct( diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c index bed91572f82a..eb3ae5c3677c 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c @@ -904,6 +904,33 @@ static unsigned int get_smu_clock_info_v3_1(struct bios_parser *bp, uint8_t id) return 0; } +/****************************************************************************** + ****************************************************************************** + ** + ** LVTMA CONTROL + ** + ****************************************************************************** + *****************************************************************************/ + +static enum bp_result enable_lvtma_control( + struct bios_parser *bp, + uint8_t uc_pwr_on); + +static void init_enable_lvtma_control(struct bios_parser *bp) +{ + /* TODO add switch for table vrsion */ + bp->cmd_tbl.enable_lvtma_control = enable_lvtma_control; + +} + +static enum bp_result enable_lvtma_control( + struct bios_parser *bp, + uint8_t uc_pwr_on) +{ + enum bp_result result = BP_RESULT_FAILURE; + return result; +} + void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp) { init_dig_encoder_control(bp); @@ -919,4 +946,5 @@ void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp) init_set_dce_clock(bp); init_get_smu_clock_info(bp); + init_enable_lvtma_control(bp); } diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h index 7a2af24dfe60..7bdce013cde5 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h @@ -94,7 +94,8 @@ struct cmd_tbl { struct bp_set_dce_clock_parameters *bp_params); unsigned int (*get_smu_clock_info)( struct bios_parser *bp, uint8_t id); - + enum bp_result (*enable_lvtma_control)(struct bios_parser *bp, + uint8_t uc_pwr_on); }; void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index c664404a75d4..543afa34d87a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -94,6 +94,15 @@ int rn_get_active_display_cnt_wa( return display_count; } +void rn_set_low_power_state(struct clk_mgr *clk_mgr_base) +{ + struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + + rn_vbios_smu_set_dcn_low_power_state(clk_mgr, DCN_PWR_STATE_LOW_POWER); + /* update power state */ + clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER; +} + void rn_update_clocks(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool safe_to_lower) @@ -516,6 +525,7 @@ static struct clk_mgr_funcs dcn21_funcs = { .init_clocks = rn_init_clocks, .enable_pme_wa = rn_enable_pme_wa, .are_clock_states_equal = rn_are_clock_states_equal, + .set_low_power_state = rn_set_low_power_state, .notify_wm_ranges = rn_notify_wm_ranges, .notify_link_rate_change = rn_notify_link_rate_change, }; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 4bd6e03a7ef3..437d1a7a16fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -763,6 +763,7 @@ static bool detect_dp(struct dc_link *link, sink_caps->signal = dp_passive_dongle_detection(link->ddc, sink_caps, audio_support); + link->dpcd_caps.dongle_type = sink_caps->dongle_type; } return true; @@ -3289,7 +3290,6 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx) #if defined(CONFIG_DRM_AMD_DC_HDCP) update_psp_stream_config(pipe_ctx, true); #endif - dc->hwss.blank_stream(pipe_ctx); if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 9bc03f26efda..b2be6ad5101d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -4409,9 +4409,9 @@ bool dc_link_get_backlight_level_nits(struct dc_link *link, link->connector_signal != SIGNAL_TYPE_DISPLAY_PORT)) return false; - if (!core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_CURRENT_PEAK, + if (core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_CURRENT_PEAK, dpcd_backlight_get.raw, - sizeof(union dpcd_source_backlight_get))) + sizeof(union dpcd_source_backlight_get)) != DC_OK) return false; *backlight_millinits_avg = @@ -4450,9 +4450,9 @@ bool dc_link_read_default_bl_aux(struct dc_link *link, uint32_t *backlight_milli link->connector_signal != SIGNAL_TYPE_DISPLAY_PORT)) return false; - if (!core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL, + if (core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL, (uint8_t *) backlight_millinits, - sizeof(uint32_t))) + sizeof(uint32_t)) != DC_OK) return false; return true; diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h index d06d07042a12..0811f941f430 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h @@ -136,6 +136,10 @@ struct dc_vbios_funcs { enum bp_result (*get_atom_dc_golden_table)( struct dc_bios *dcb); + + enum bp_result (*enable_lvtma_control)( + struct dc_bios *bios, + uint8_t uc_pwr_on); }; struct bios_registers { diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 633442bc7ef2..d9888f316da6 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -233,7 +233,7 @@ struct dc_stream_state { union stream_update_flags update_flags; }; -#define ABM_LEVEL_IMMEDIATE_DISABLE 0xFFFFFFFF +#define ABM_LEVEL_IMMEDIATE_DISABLE 255 struct dc_stream_update { struct dc_stream_state *stream; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h index 70ec691e14d2..99c68ca9c7e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h @@ -49,7 +49,7 @@ #define DCN_PANEL_CNTL_REG_LIST()\ DCN_PANEL_CNTL_SR(PWRSEQ_CNTL, LVTMA), \ DCN_PANEL_CNTL_SR(PWRSEQ_STATE, LVTMA), \ - DCE_PANEL_CNTL_SR(PWRSEQ_REF_DIV, LVTMA), \ + DCN_PANEL_CNTL_SR(PWRSEQ_REF_DIV, LVTMA), \ SR(BL_PWM_CNTL), \ SR(BL_PWM_CNTL2), \ SR(BL_PWM_PERIOD_CNTL), \ diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 49380ed3aeae..45c9e9027886 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -842,6 +842,17 @@ void dce110_edp_power_control( cntl.coherent = false; cntl.lanes_number = LANE_COUNT_FOUR; cntl.hpd_sel = link->link_enc->hpd_source; + + if (ctx->dc->ctx->dmub_srv && + ctx->dc->debug.dmub_command_table) { + if (cntl.action == TRANSMITTER_CONTROL_POWER_ON) + bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_POWER_ON); + else + bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_POWER_OFF); + } + bp_result = link_transmitter_control(ctx->dc_bios, &cntl); if (!power_up) @@ -919,8 +930,21 @@ void dce110_edp_backlight_control( /*edp 1.2*/ if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) edp_receiver_ready_T7(link); + + if (ctx->dc->ctx->dmub_srv && + ctx->dc->debug.dmub_command_table) { + if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) + ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_LCD_BLON); + else + ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_LCD_BLOFF); + } + link_transmitter_control(ctx->dc_bios, &cntl); + + if (enable && link->dpcd_sink_ext_caps.bits.oled) msleep(OLED_POST_T7_DELAY); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index a643927e272b..fa643ec5a876 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1450,33 +1450,42 @@ void dcn10_init_hw(struct dc *dc) void dcn10_power_down_on_boot(struct dc *dc) { int i = 0; + struct dc_link *edp_link; - if (dc->config.power_down_display_on_boot) { - struct dc_link *edp_link = get_edp_link(dc); - - if (edp_link && - edp_link->link_enc->funcs->is_dig_enabled && - edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) && - dc->hwseq->funcs.edp_backlight_control && - dc->hwss.power_down && - dc->hwss.edp_power_control) { - dc->hwseq->funcs.edp_backlight_control(edp_link, false); - dc->hwss.power_down(dc); - dc->hwss.edp_power_control(edp_link, false); - } else { - for (i = 0; i < dc->link_count; i++) { - struct dc_link *link = dc->links[i]; - - if (link->link_enc->funcs->is_dig_enabled && - link->link_enc->funcs->is_dig_enabled(link->link_enc) && - dc->hwss.power_down) { - dc->hwss.power_down(dc); - break; - } + if (!dc->config.power_down_display_on_boot) + return; + + edp_link = get_edp_link(dc); + if (edp_link && + edp_link->link_enc->funcs->is_dig_enabled && + edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) && + dc->hwseq->funcs.edp_backlight_control && + dc->hwss.power_down && + dc->hwss.edp_power_control) { + dc->hwseq->funcs.edp_backlight_control(edp_link, false); + dc->hwss.power_down(dc); + dc->hwss.edp_power_control(edp_link, false); + } else { + for (i = 0; i < dc->link_count; i++) { + struct dc_link *link = dc->links[i]; + if (link->link_enc->funcs->is_dig_enabled && + link->link_enc->funcs->is_dig_enabled(link->link_enc) && + dc->hwss.power_down) { + dc->hwss.power_down(dc); + break; } + } } + + /* + * Call update_clocks with empty context + * to send DISPLAY_OFF + * Otherwise DISPLAY_OFF may not be asserted + */ + if (dc->clk_mgr->funcs->set_low_power_state) + dc->clk_mgr->funcs->set_low_power_state(dc->clk_mgr); } void dcn10_reset_hw_ctx_wrap( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 17d5cb422025..8939541ad7af 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -1213,6 +1213,7 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont bool video_large = false; bool desktop_large = false; bool dcc_disabled = false; + bool mpo_enabled = false; for (i = 0; i < context->stream_count; i++) { if (context->stream_status[i].plane_count == 0) @@ -1221,6 +1222,9 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont if (context->stream_status[i].plane_count > 2) return DC_FAIL_UNSUPPORTED_1; + if (context->stream_status[i].plane_count > 1) + mpo_enabled = true; + for (j = 0; j < context->stream_status[i].plane_count; j++) { struct dc_plane_state *plane = context->stream_status[i].plane_states[j]; @@ -1244,6 +1248,10 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont } } + /* Disable MPO in multi-display configurations. */ + if (context->stream_count > 1 && mpo_enabled) + return DC_FAIL_UNSUPPORTED_1; + /* * Workaround: On DCN10 there is UMC issue that causes underflow when * playing 4k video on 4k desktop with video downscaled and single channel diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c index 07b2f9399671..842abb4c475b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c @@ -121,35 +121,35 @@ void enc1_update_generic_info_packet( switch (packet_index) { case 0: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC0_FRAME_UPDATE, 1); + AFMT_GENERIC0_IMMEDIATE_UPDATE, 1); break; case 1: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC1_FRAME_UPDATE, 1); + AFMT_GENERIC1_IMMEDIATE_UPDATE, 1); break; case 2: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC2_FRAME_UPDATE, 1); + AFMT_GENERIC2_IMMEDIATE_UPDATE, 1); break; case 3: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC3_FRAME_UPDATE, 1); + AFMT_GENERIC3_IMMEDIATE_UPDATE, 1); break; case 4: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC4_FRAME_UPDATE, 1); + AFMT_GENERIC4_IMMEDIATE_UPDATE, 1); break; case 5: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC5_FRAME_UPDATE, 1); + AFMT_GENERIC5_IMMEDIATE_UPDATE, 1); break; case 6: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC6_FRAME_UPDATE, 1); + AFMT_GENERIC6_IMMEDIATE_UPDATE, 1); break; case 7: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC7_FRAME_UPDATE, 1); + AFMT_GENERIC7_IMMEDIATE_UPDATE, 1); break; default: break; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h index ed385b1477be..30eae7459d50 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h @@ -281,7 +281,14 @@ struct dcn10_stream_enc_registers { SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_FRAME_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC0_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC1_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_IMMEDIATE_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_IMMEDIATE_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_FRAME_UPDATE, mask_sh),\ @@ -345,7 +352,14 @@ struct dcn10_stream_enc_registers { type AFMT_GENERIC2_FRAME_UPDATE;\ type AFMT_GENERIC3_FRAME_UPDATE;\ type AFMT_GENERIC4_FRAME_UPDATE;\ + type AFMT_GENERIC0_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC1_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC2_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC3_IMMEDIATE_UPDATE;\ type AFMT_GENERIC4_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC5_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC6_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC7_IMMEDIATE_UPDATE;\ type AFMT_GENERIC5_FRAME_UPDATE;\ type AFMT_GENERIC6_FRAME_UPDATE;\ type AFMT_GENERIC7_FRAME_UPDATE;\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 66180b4332f1..c8cfd3ba1c15 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1457,8 +1457,8 @@ static void dcn20_update_dchubp_dpp( /* Any updates are handled in dc interface, just need to apply existing for plane enable */ if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed || - pipe_ctx->update_flags.bits.scaler || pipe_ctx->update_flags.bits.viewport) - && pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { + pipe_ctx->update_flags.bits.scaler || viewport_changed == true) && + pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { dc->hwss.set_cursor_position(pipe_ctx); dc->hwss.set_cursor_attribute(pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h index bf0044f7417e..dcbf28dd72d4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h @@ -167,7 +167,9 @@ LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\ LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\ LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\ - LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh) + LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh) #define LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh)\ LINK_ENCODER_MASK_SH_LIST_DCN10(mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 790baf552695..9140b3fc767a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3141,7 +3141,7 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co int vlevel = 0; int pipe_split_from[MAX_PIPES]; int pipe_cnt = 0; - display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL); + display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); DC_LOGGER_INIT(dc->ctx->logger); BW_VAL_TRACE_COUNT(); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h index 8e9fd59ccde8..2fbf879cd327 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h @@ -61,7 +61,10 @@ DPCS_DCN2_MASK_SH_LIST(mask_sh),\ LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_ORDER_INVERT_18_BIT, mask_sh),\ LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_TX_VBOOST_LVL, mask_sh),\ - LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_TX_CLK_EN, mask_sh) + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_TX_CLK_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh) + void dcn30_link_encoder_construct( struct dcn20_link_encoder *enc20, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 653a571e366d..ebe0cc5b833b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -491,6 +491,7 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = { [id] = {\ LE_DCN3_REG_LIST(id), \ UNIPHY_DCN2_REG_LIST(phyid), \ + SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \ } static const struct dce110_aux_registers_shift aux_shift = { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index b54814f11b74..2beb284f89b0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -63,6 +63,7 @@ typedef struct { #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff +#define DCN30_MAX_DSC_IMAGE_WIDTH 5184 static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib); static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation( @@ -3984,6 +3985,9 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } else if (v->PlaneRequiredDISPCLKWithoutODMCombine > v->MaxDispclkRoundedDownToDFSGranularity) { v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine2To1; + } else if (v->DSCEnabled[k] && (v->HActive[k] > DCN30_MAX_DSC_IMAGE_WIDTH)) { + v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; + v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine2To1; } else { v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled; v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithoutODMCombine; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index 5994d2a33c40..947d6106f341 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -230,6 +230,8 @@ struct clk_mgr_funcs { int (*get_dp_ref_clk_frequency)(struct clk_mgr *clk_mgr); + void (*set_low_power_state)(struct clk_mgr *clk_mgr); + void (*init_clocks)(struct clk_mgr *clk_mgr); void (*enable_pme_wa) (struct clk_mgr *clk_mgr); diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h index c30437ae8395..21011edea337 100644 --- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h +++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h @@ -101,6 +101,13 @@ enum bp_pipe_control_action { ASIC_PIPE_INIT }; +enum bp_lvtma_control_action { + LVTMA_CONTROL_LCD_BLOFF = 2, + LVTMA_CONTROL_LCD_BLON = 3, + LVTMA_CONTROL_POWER_ON = 12, + LVTMA_CONTROL_POWER_OFF = 13 +}; + struct bp_encoder_control { enum bp_encoder_control_action action; enum engine_id engine_id; diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h index 89ef9f6860e5..16df2a485dd0 100644 --- a/drivers/gpu/drm/amd/display/include/fixed31_32.h +++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h @@ -431,6 +431,9 @@ struct fixed31_32 dc_fixpt_log(struct fixed31_32 arg); */ static inline struct fixed31_32 dc_fixpt_pow(struct fixed31_32 arg1, struct fixed31_32 arg2) { + if (arg1.value == 0) + return arg2.value == 0 ? dc_fixpt_one : dc_fixpt_zero; + return dc_fixpt_exp( dc_fixpt_mul( dc_fixpt_log(arg1), diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 81820f3d6b3b..d988533d4af5 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -324,22 +324,44 @@ static void apply_below_the_range(struct core_freesync *core_freesync, /* Choose number of frames to insert based on how close it * can get to the mid point of the variable range. + * - Delta for CEIL: delta_from_mid_point_in_us_1 + * - Delta for FLOOR: delta_from_mid_point_in_us_2 */ - if ((frame_time_in_us / mid_point_frames_ceil) > in_out_vrr->min_duration_in_us && - (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2 || - mid_point_frames_floor < 2)) { + if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) { + /* Check for out of range. + * If using CEIL produces a value that is out of range, + * then we are forced to use FLOOR. + */ + frames_to_insert = mid_point_frames_floor; + } else if (mid_point_frames_floor < 2) { + /* Check if FLOOR would result in non-LFC. In this case + * choose to use CEIL + */ + frames_to_insert = mid_point_frames_ceil; + } else if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) { + /* If choosing CEIL results in a frame duration that is + * closer to the mid point of the range. + * Choose CEIL + */ frames_to_insert = mid_point_frames_ceil; - delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 - - delta_from_mid_point_in_us_1; } else { + /* If choosing FLOOR results in a frame duration that is + * closer to the mid point of the range. + * Choose FLOOR + */ frames_to_insert = mid_point_frames_floor; - delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_1 - - delta_from_mid_point_in_us_2; } /* Prefer current frame multiplier when BTR is enabled unless it drifts * too far from the midpoint */ + if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) { + delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 - + delta_from_mid_point_in_us_1; + } else { + delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_1 - + delta_from_mid_point_in_us_2; + } if (in_out_vrr->btr.frames_to_insert != 0 && delta_from_mid_point_delta_in_us < BTR_DRIFT_MARGIN) { if (((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) < diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index 6c991de8f371..9582b38162f0 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -1840,10 +1840,14 @@ static bool arcturus_is_dpm_running(struct smu_context *smu) { int ret = 0; uint32_t feature_mask[2]; - unsigned long feature_enabled; + uint64_t feature_enabled; + ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2); - feature_enabled = (unsigned long)((uint64_t)feature_mask[0] | - ((uint64_t)feature_mask[1] << 32)); + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0]; + return !!(feature_enabled & SMC_DPM_FEATURE); } @@ -2204,14 +2208,17 @@ static const struct throttling_logging_label { }; static void arcturus_log_thermal_throttling_event(struct smu_context *smu) { + int ret; int throttler_idx, throtting_events = 0, buf_idx = 0; struct amdgpu_device *adev = smu->adev; uint32_t throttler_status; char log_buf[256]; - arcturus_get_smu_metrics_data(smu, - METRICS_THROTTLER_STATUS, - &throttler_status); + ret = arcturus_get_smu_metrics_data(smu, + METRICS_THROTTLER_STATUS, + &throttler_status); + if (ret) + return; memset(log_buf, 0, sizeof(log_buf)); for (throttler_idx = 0; throttler_idx < ARRAY_SIZE(logging_label); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index c9cfe90a2947..9ee8cf8267c8 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -204,8 +204,7 @@ static int smu10_set_min_deep_sleep_dcefclk(struct pp_hwmgr *hwmgr, uint32_t clo { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->need_min_deep_sleep_dcefclk && - smu10_data->deep_sleep_dcefclk != clock) { + if (clock && smu10_data->deep_sleep_dcefclk != clock) { smu10_data->deep_sleep_dcefclk = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetMinDeepSleepDcefclk, @@ -219,8 +218,7 @@ static int smu10_set_hard_min_dcefclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t c { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->dcf_actual_hard_min_freq && - smu10_data->dcf_actual_hard_min_freq != clock) { + if (clock && smu10_data->dcf_actual_hard_min_freq != clock) { smu10_data->dcf_actual_hard_min_freq = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinDcefclkByFreq, @@ -234,8 +232,7 @@ static int smu10_set_hard_min_fclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t cloc { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->f_actual_hard_min_freq && - smu10_data->f_actual_hard_min_freq != clock) { + if (clock && smu10_data->f_actual_hard_min_freq != clock) { smu10_data->f_actual_hard_min_freq = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index ffe05b7cc1f0..4a3b64aa21ce 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3581,7 +3581,8 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx, case AMDGPU_PP_SENSOR_GPU_POWER: return smu7_get_gpu_power(hwmgr, (uint32_t *)value); case AMDGPU_PP_SENSOR_VDDGFX: - if ((data->vr_config & 0xff) == 0x2) + if ((data->vr_config & VRCONF_VDDGFX_MASK) == + (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT)) val_vid = PHM_READ_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_SVI2_STATUS, PLANE2_VID); else diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c index 468bdd6f6697..952cd3d7240e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c @@ -363,17 +363,29 @@ int vega10_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v2_information *pp_table_info = + (struct phm_ppt_v2_information *)(hwmgr->pptable); + struct phm_tdp_table *tdp_table = pp_table_info->tdp_table; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + + /* + * As a common sense, usSoftwareShutdownTemp should be bigger + * than ThotspotLimit. For any invalid usSoftwareShutdownTemp, + * we will just use the max possible setting VEGA10_THERMAL_MAXIMUM_ALERT_TEMP + * to avoid false alarms. + */ + if ((tdp_table->usSoftwareShutdownTemp > + range->hotspot_crit_max / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)) { + if (high > tdp_table->usSoftwareShutdownTemp) + high = tdp_table->usSoftwareShutdownTemp; + } if (low > high) return -EINVAL; @@ -382,8 +394,8 @@ static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val &= (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK) & (~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK) & (~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c index c15b9756025d..7ace439dcde7 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c @@ -170,17 +170,18 @@ int vega12_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (high > pptable_information->us_software_shutdown_temp) + high = pptable_information->us_software_shutdown_temp; if (low > high) return -EINVAL; @@ -189,8 +190,8 @@ static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 3b8839641770..ea70d736f6a8 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -979,10 +979,7 @@ static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - uint64_t features_enabled; - int i; - bool enabled; - int ret = 0; + int i, ret = 0; PP_ASSERT_WITH_CODE((ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_DisableAllSmuFeatures, @@ -990,17 +987,8 @@ static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) "[DisableAllSMUFeatures] Failed to disable all smu features!", return ret); - ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled); - PP_ASSERT_WITH_CODE(!ret, - "[DisableAllSMUFeatures] Failed to get enabled smc features!", - return ret); - - for (i = 0; i < GNLD_FEATURES_MAX; i++) { - enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? - true : false; - data->smu_features[i].enabled = enabled; - data->smu_features[i].supported = enabled; - } + for (i = 0; i < GNLD_FEATURES_MAX; i++) + data->smu_features[i].enabled = 0; return 0; } @@ -1652,12 +1640,6 @@ static void vega20_init_powergate_state(struct pp_hwmgr *hwmgr) data->uvd_power_gated = true; data->vce_power_gated = true; - - if (data->smu_features[GNLD_DPM_UVD].enabled) - data->uvd_power_gated = false; - - if (data->smu_features[GNLD_DPM_VCE].enabled) - data->vce_power_gated = false; } static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) @@ -3230,10 +3212,11 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf) static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfeature_masks) { - uint64_t features_enabled; - uint64_t features_to_enable; - uint64_t features_to_disable; - int ret = 0; + struct vega20_hwmgr *data = + (struct vega20_hwmgr *)(hwmgr->backend); + uint64_t features_enabled, features_to_enable, features_to_disable; + int i, ret = 0; + bool enabled; if (new_ppfeature_masks >= (1ULL << GNLD_FEATURES_MAX)) return -EINVAL; @@ -3262,6 +3245,17 @@ static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfe return ret; } + /* Update the cached feature enablement state */ + ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled); + if (ret) + return ret; + + for (i = 0; i < GNLD_FEATURES_MAX; i++) { + enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? + true : false; + data->smu_features[i].enabled = enabled; + } + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c index 7add2f60f49c..364162ddaa9c 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c @@ -240,17 +240,18 @@ int vega20_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (high > pptable_information->us_software_shutdown_temp) + high = pptable_information->us_software_shutdown_temp; if (low > high) return -EINVAL; @@ -259,8 +260,8 @@ static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 9f62af9abd23..3d5eae956a23 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -1331,10 +1331,14 @@ static bool navi10_is_dpm_running(struct smu_context *smu) { int ret = 0; uint32_t feature_mask[2]; - unsigned long feature_enabled; + uint64_t feature_enabled; + ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2); - feature_enabled = (unsigned long)((uint64_t)feature_mask[0] | - ((uint64_t)feature_mask[1] << 32)); + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0]; + return !!(feature_enabled & SMC_DPM_FEATURE); } diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c index 3865dbed5f93..61f4ddae262d 100644 --- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c @@ -68,7 +68,8 @@ FEATURE_MASK(FEATURE_DPM_LINK_BIT) | \ FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT) | \ FEATURE_MASK(FEATURE_DPM_FCLK_BIT) | \ - FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT)) + FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT) | \ + FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT)) #define SMU_11_0_7_GFX_BUSY_THRESHOLD 15 @@ -95,6 +96,7 @@ static struct cmn2asic_msg_mapping sienna_cichlid_message_map[SMU_MSG_MAX_COUNT] MSG_MAP(TransferTableSmu2Dram, PPSMC_MSG_TransferTableSmu2Dram, 0), MSG_MAP(TransferTableDram2Smu, PPSMC_MSG_TransferTableDram2Smu, 0), MSG_MAP(UseDefaultPPTable, PPSMC_MSG_UseDefaultPPTable, 0), + MSG_MAP(RunDcBtc, PPSMC_MSG_RunDcBtc, 0), MSG_MAP(EnterBaco, PPSMC_MSG_EnterBaco, 0), MSG_MAP(SetSoftMinByFreq, PPSMC_MSG_SetSoftMinByFreq, 0), MSG_MAP(SetSoftMaxByFreq, PPSMC_MSG_SetSoftMaxByFreq, 0), @@ -228,6 +230,7 @@ sienna_cichlid_get_allowed_feature_mask(struct smu_context *smu, *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_PREFETCHER_BIT) | FEATURE_MASK(FEATURE_DPM_FCLK_BIT) + | FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT) | FEATURE_MASK(FEATURE_DS_SOCCLK_BIT) | FEATURE_MASK(FEATURE_DS_DCEFCLK_BIT) | FEATURE_MASK(FEATURE_DS_FCLK_BIT) @@ -775,7 +778,7 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 0, NULL); if (ret) return ret; - if (adev->asic_type == CHIP_SIENNA_CICHLID) { + if (adev->vcn.num_vcn_inst > 1) { ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 0x10000, NULL); if (ret) @@ -787,7 +790,7 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, 0, NULL); if (ret) return ret; - if (adev->asic_type == CHIP_SIENNA_CICHLID) { + if (adev->vcn.num_vcn_inst > 1) { ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, 0x10000, NULL); if (ret) @@ -1146,10 +1149,14 @@ static bool sienna_cichlid_is_dpm_running(struct smu_context *smu) { int ret = 0; uint32_t feature_mask[2]; - unsigned long feature_enabled; + uint64_t feature_enabled; + ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2); - feature_enabled = (unsigned long)((uint64_t)feature_mask[0] | - ((uint64_t)feature_mask[1] << 32)); + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0]; + return !!(feature_enabled & SMC_DPM_FEATURE); } @@ -1732,6 +1739,11 @@ static int sienna_cichlid_get_dpm_ultimate_freq(struct smu_context *smu, return ret; } +static int sienna_cichlid_run_btc(struct smu_context *smu) +{ + return smu_cmn_send_smc_msg(smu, SMU_MSG_RunDcBtc, NULL); +} + static bool sienna_cichlid_is_baco_supported(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -2719,6 +2731,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .mode1_reset = smu_v11_0_mode1_reset, .get_dpm_ultimate_freq = sienna_cichlid_get_dpm_ultimate_freq, .set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range, + .run_btc = sienna_cichlid_run_btc, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, .set_pp_feature_mask = smu_cmn_set_pp_feature_mask, }; diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c index c18169aa59ce..e4d1f3d66ef4 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c @@ -37,6 +37,7 @@ #include "cgs_common.h" #include "atombios.h" #include "pppcielanes.h" +#include "smu7_smumgr.h" #include "smu/smu_7_0_1_d.h" #include "smu/smu_7_0_1_sh_mask.h" @@ -2948,6 +2949,7 @@ const struct pp_smumgr_func ci_smu_funcs = { .request_smu_load_specific_fw = NULL, .send_msg_to_smc = ci_send_msg_to_smc, .send_msg_to_smc_with_parameter = ci_send_msg_to_smc_with_parameter, + .get_argument = smu7_get_argument, .download_pptable_settings = NULL, .upload_pptable_settings = NULL, .get_offsetof = ci_get_offsetof, diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c index ca570b135478..e9de542f9b7c 100644 --- a/drivers/gpu/drm/arm/malidp_hw.c +++ b/drivers/gpu/drm/arm/malidp_hw.c @@ -532,7 +532,7 @@ static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev, malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW); malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH); malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE); - /* fall through */ + fallthrough; case 1: malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW); malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH); @@ -869,7 +869,7 @@ static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev, malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW); malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH); malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE); - /* fall through */ + fallthrough; case 1: malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW); malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH); @@ -1324,7 +1324,7 @@ static irqreturn_t malidp_se_irq(int irq, void *arg) break; case MW_RESTART: drm_writeback_signal_completion(&malidp->mw_connector, 0); - /* fall through - to a new start */ + fallthrough; /* to a new start */ case MW_START: /* writeback started, need to emulate one-shot mode */ hw->disable_memwrite(hwdev); diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index dd12b55d57a2..6a9fba051d13 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -238,7 +238,7 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) ast->dp501_fw_addr = NULL; } } - /* fallthrough */ + fallthrough; case 0x0c: ast->tx_chip_type = AST_TX_DP501; } diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c index ce94f797d090..66b67402f1ac 100644 --- a/drivers/gpu/drm/bridge/nwl-dsi.c +++ b/drivers/gpu/drm/bridge/nwl-dsi.c @@ -409,7 +409,6 @@ static bool nwl_dsi_read_packet(struct nwl_dsi *dsi, u32 status) switch (data_type) { case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_2BYTE: - fallthrough; case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_2BYTE: if (xfer->msg->rx_len > 1) { /* read second byte */ @@ -418,7 +417,6 @@ static bool nwl_dsi_read_packet(struct nwl_dsi *dsi, u32 status) } fallthrough; case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_1BYTE: - fallthrough; case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_1BYTE: if (xfer->msg->rx_len > 0) { /* read first byte */ diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c index d7e65c869415..9fef6413741d 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c @@ -61,10 +61,10 @@ static int dw_hdmi_i2s_hw_params(struct device *dev, void *data, switch (hparms->channels) { case 7 ... 8: conf0 |= HDMI_AUD_CONF0_I2S_EN3; - /* Fall-thru */ + fallthrough; case 5 ... 6: conf0 |= HDMI_AUD_CONF0_I2S_EN2; - /* Fall-thru */ + fallthrough; case 3 ... 4: conf0 |= HDMI_AUD_CONF0_I2S_EN1; /* Fall-thru */ diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 86b9f0f87a14..5b6e19ecbc84 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -604,13 +604,13 @@ static void ti_sn_bridge_read_valid_rates(struct ti_sn_bridge *pdata, DRM_DEV_ERROR(pdata->dev, "Unexpected max rate (%#x); assuming 5.4 GHz\n", (int)dpcd_val); - /* fall through */ + fallthrough; case DP_LINK_BW_5_4: rate_valid[7] = 1; - /* fall through */ + fallthrough; case DP_LINK_BW_2_7: rate_valid[4] = 1; - /* fall through */ + fallthrough; case DP_LINK_BW_1_62: rate_valid[1] = 1; break; diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index f68c69a45752..9e1ad493e689 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -34,6 +34,7 @@ #include <drm/drm_bridge.h> #include <drm/drm_damage_helper.h> #include <drm/drm_device.h> +#include <drm/drm_drv.h> #include <drm/drm_plane_helper.h> #include <drm/drm_print.h> #include <drm/drm_self_refresh_helper.h> @@ -3106,7 +3107,7 @@ void drm_atomic_helper_shutdown(struct drm_device *dev) if (ret) DRM_ERROR("Disabling all crtc's during unload failed with %i\n", ret); - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); } EXPORT_SYMBOL(drm_atomic_helper_shutdown); @@ -3246,7 +3247,7 @@ struct drm_atomic_state *drm_atomic_helper_suspend(struct drm_device *dev) } unlock: - DRM_MODESET_LOCK_ALL_END(ctx, err); + DRM_MODESET_LOCK_ALL_END(dev, ctx, err); if (err) return ERR_PTR(err); @@ -3327,7 +3328,7 @@ int drm_atomic_helper_resume(struct drm_device *dev, err = drm_atomic_helper_commit_duplicated_state(state, &ctx); - DRM_MODESET_LOCK_ALL_END(ctx, err); + DRM_MODESET_LOCK_ALL_END(dev, ctx, err); drm_atomic_state_put(state); return err; diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c index a0735fbc144b..7a01d0918861 100644 --- a/drivers/gpu/drm/drm_bufs.c +++ b/drivers/gpu/drm/drm_bufs.c @@ -537,7 +537,7 @@ int drm_legacy_rmmap_locked(struct drm_device *dev, struct drm_local_map *map) switch (map->type) { case _DRM_REGISTERS: iounmap(map->handle); - /* FALLTHROUGH */ + fallthrough; case _DRM_FRAME_BUFFER: arch_phys_wc_del(map->mtrr); break; diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index c93123ff7c21..138ff34b31db 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -294,7 +294,7 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev, crtc->gamma_size, &ctx); out: - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); return ret; } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 283bcc4362ca..aecdd7ea26dc 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -588,7 +588,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, if (crtc_req->mode_valid && !drm_lease_held(file_priv, plane->base.id)) return -EACCES; - mutex_lock(&crtc->dev->mode_config.mutex); DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE, ret); @@ -756,8 +755,7 @@ out: fb = NULL; mode = NULL; - DRM_MODESET_LOCK_ALL_END(ctx, ret); - mutex_unlock(&crtc->dev->mode_config.mutex); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); return ret; } diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index a3c82e726057..092c8c985911 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -492,7 +492,7 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], case DP_DS_16BPC: return 16; } - /* fall through */ + fallthrough; default: return 0; } diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index b23cb2fec3f3..67dd72ea200e 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -5040,8 +5040,8 @@ int drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, struct drm crtc = conn_state->crtc; - if (WARN_ON(!crtc)) - return -EINVAL; + if (!crtc) + continue; if (!drm_dp_mst_dsc_aux_for_port(pos->port)) continue; diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c index 901b078abf40..db05f386a709 100644 --- a/drivers/gpu/drm/drm_mode_object.c +++ b/drivers/gpu/drm/drm_mode_object.c @@ -428,7 +428,7 @@ int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data, out_unref: drm_mode_object_put(obj); out: - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); return ret; } @@ -470,7 +470,7 @@ static int set_property_legacy(struct drm_mode_object *obj, break; } drm_property_change_valid_put(prop, ref); - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); return ret; } diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 14b6f7638728..501b4fe55a3d 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1930,7 +1930,7 @@ void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out, default: WARN(1, "Invalid aspect ratio (0%x) on mode\n", in->picture_aspect_ratio); - /* fall through */ + fallthrough; case HDMI_PICTURE_ASPECT_NONE: out->flags |= DRM_MODE_FLAG_PIC_AR_NONE; break; diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index b7b90b3a2e38..affe1cfed009 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -792,7 +792,7 @@ static int setplane_internal(struct drm_plane *plane, crtc_x, crtc_y, crtc_w, crtc_h, src_x, src_y, src_w, src_h, &ctx); - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(plane->dev, ctx, ret); return ret; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index d5a4cd85a0f6..c6404b8d067f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -337,9 +337,16 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu->identity.model = gpu_read(gpu, VIVS_HI_CHIP_MODEL); gpu->identity.revision = gpu_read(gpu, VIVS_HI_CHIP_REV); - gpu->identity.product_id = gpu_read(gpu, VIVS_HI_CHIP_PRODUCT_ID); gpu->identity.customer_id = gpu_read(gpu, VIVS_HI_CHIP_CUSTOMER_ID); - gpu->identity.eco_id = gpu_read(gpu, VIVS_HI_CHIP_ECO_ID); + + /* + * Reading these two registers on GC600 rev 0x19 result in a + * unhandled fault: external abort on non-linefetch + */ + if (!etnaviv_is_model_rev(gpu, GC600, 0x19)) { + gpu->identity.product_id = gpu_read(gpu, VIVS_HI_CHIP_PRODUCT_ID); + gpu->identity.eco_id = gpu_read(gpu, VIVS_HI_CHIP_ECO_ID); + } /* * !!!! HACK ALERT !!!! diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 4e3e95dce6d8..cd46c882269c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -89,12 +89,15 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) u32 dma_addr; int change; + /* block scheduler */ + drm_sched_stop(&gpu->sched, sched_job); + /* * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. */ if (dma_fence_is_signaled(submit->out_fence)) - return; + goto out_no_timeout; /* * If the GPU is still making forward progress on the front-end (which @@ -105,12 +108,9 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) change = dma_addr - gpu->hangcheck_dma_addr; if (change < 0 || change > 16) { gpu->hangcheck_dma_addr = dma_addr; - return; + goto out_no_timeout; } - /* block scheduler */ - drm_sched_stop(&gpu->sched, sched_job); - if(sched_job) drm_sched_increase_karma(sched_job); @@ -120,6 +120,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) drm_sched_resubmit_jobs(&gpu->sched); +out_no_timeout: /* restart scheduler after GPU is usable again */ drm_sched_start(&gpu->sched, true); } diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 7a6f6df5e954..b38e9b592b8a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -987,10 +987,10 @@ static void exynos_dsi_send_to_fifo(struct exynos_dsi *dsi, switch (length) { case 3: reg |= payload[2] << 16; - /* Fall through */ + fallthrough; case 2: reg |= payload[1] << 8; - /* Fall through */ + fallthrough; case 1: reg |= payload[0]; exynos_dsi_write(dsi, DSIM_PAYLOAD_REG, reg); @@ -1038,7 +1038,7 @@ static void exynos_dsi_read_from_fifo(struct exynos_dsi *dsi, payload[1] = reg >> 16; ++xfer->rx_done; } - /* Fall through */ + fallthrough; case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_1BYTE: case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_1BYTE: payload[0] = reg >> 8; @@ -1082,10 +1082,10 @@ static void exynos_dsi_read_from_fifo(struct exynos_dsi *dsi, switch (length) { case 3: payload[2] = (reg >> 16) & 0xff; - /* Fall through */ + fallthrough; case 2: payload[1] = (reg >> 8) & 0xff; - /* Fall through */ + fallthrough; case 1: payload[0] = reg & 0xff; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 56a2b47e1af7..5147f5929be7 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -92,7 +92,7 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper, offset = fbi->var.xoffset * fb->format->cpp[0]; offset += fbi->var.yoffset * fb->pitches[0]; - fbi->screen_base = exynos_gem->kvaddr + offset; + fbi->screen_buffer = exynos_gem->kvaddr + offset; fbi->screen_size = size; fbi->fix.smem_len = size; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h index 7445748288da..74e926abeff0 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.h +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h @@ -40,7 +40,7 @@ struct exynos_drm_gem { unsigned int flags; unsigned long size; void *cookie; - void __iomem *kvaddr; + void *kvaddr; dma_addr_t dma_addr; unsigned long dma_attrs; struct sg_table *sgt; diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c index 86fac677fe69..3c6d9f3913d5 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c @@ -101,19 +101,19 @@ static void fsl_dcu_drm_plane_atomic_update(struct drm_plane *plane, break; case DRM_FORMAT_ARGB8888: alpha = DCU_LAYER_AB_WHOLE_FRAME; - /* fall-through */ + fallthrough; case DRM_FORMAT_XRGB8888: bpp = FSL_DCU_ARGB8888; break; case DRM_FORMAT_ARGB4444: alpha = DCU_LAYER_AB_WHOLE_FRAME; - /* fall-through */ + fallthrough; case DRM_FORMAT_XRGB4444: bpp = FSL_DCU_ARGB4444; break; case DRM_FORMAT_ARGB1555: alpha = DCU_LAYER_AB_WHOLE_FRAME; - /* fall-through */ + fallthrough; case DRM_FORMAT_XRGB1555: bpp = FSL_DCU_ARGB1555; break; diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 8c55f5bee9ab..f4053dd6bde9 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -712,7 +712,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder, switch (intel_dsi->pixel_format) { default: MISSING_CASE(intel_dsi->pixel_format); - /* fallthrough */ + fallthrough; case MIPI_DSI_FMT_RGB565: tmp |= PIX_FMT_RGB565; break; @@ -739,7 +739,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder, switch (intel_dsi->video_mode_format) { default: MISSING_CASE(intel_dsi->video_mode_format); - /* fallthrough */ + fallthrough; case VIDEO_MODE_NON_BURST_WITH_SYNC_EVENTS: tmp |= VIDEO_MODE_SYNC_EVENT; break; @@ -792,7 +792,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder, switch (pipe) { default: MISSING_CASE(pipe); - /* fallthrough */ + fallthrough; case PIPE_A: tmp |= TRANS_DDI_EDP_INPUT_A_ON; break; diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index c53c85d38fa5..a0a41ec5c341 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -905,7 +905,7 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) drm_dbg_kms(&dev_priv->drm, "VBT tp1 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n", psr_table->tp1_wakeup_time); - /* fallthrough */ + fallthrough; case 2: dev_priv->vbt.psr.tp1_wakeup_time_us = 2500; break; @@ -925,7 +925,7 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) drm_dbg_kms(&dev_priv->drm, "VBT tp2_tp3 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n", psr_table->tp2_tp3_wakeup_time); - /* fallthrough */ + fallthrough; case 2: dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 2500; break; @@ -1775,7 +1775,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, switch (child->hdmi_max_data_rate) { default: MISSING_CASE(child->hdmi_max_data_rate); - /* fall through */ + fallthrough; case HDMI_MAX_DATA_RATE_PLATFORM: max_tmds_clock = 0; break; diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index bb91dace304a..91a8161e7c05 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -326,7 +326,7 @@ static void pnv_get_cdclk(struct drm_i915_private *dev_priv, default: drm_err(&dev_priv->drm, "Unknown pnv display core clock 0x%04x\n", gcfgc); - /* fall through */ + fallthrough; case GC_DISPLAY_CLOCK_133_MHZ_PNV: cdclk_config->cdclk = 133333; break; @@ -766,7 +766,7 @@ static void bdw_set_cdclk(struct drm_i915_private *dev_priv, switch (cdclk) { default: MISSING_CASE(cdclk); - /* fall through */ + fallthrough; case 337500: val |= LCPLL_CLK_FREQ_337_5_BDW; break; @@ -1042,7 +1042,7 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv, drm_WARN_ON(&dev_priv->drm, cdclk != dev_priv->cdclk.hw.bypass); drm_WARN_ON(&dev_priv->drm, vco != 0); - /* fall through */ + fallthrough; case 308571: case 337500: freq_select = CDCLK_FREQ_337_308; @@ -1333,7 +1333,7 @@ static void icl_readout_refclk(struct drm_i915_private *dev_priv, switch (dssm) { default: MISSING_CASE(dssm); - /* fall through */ + fallthrough; case ICL_DSSM_CDCLK_PLL_REFCLK_24MHz: cdclk_config->ref = 24000; break; @@ -1561,7 +1561,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, drm_WARN_ON(&dev_priv->drm, cdclk != dev_priv->cdclk.hw.bypass); drm_WARN_ON(&dev_priv->drm, vco != 0); - /* fall through */ + fallthrough; case 2: divider = BXT_CDCLK_CD2X_DIV_SEL_1; break; diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy.c b/drivers/gpu/drm/i915/display/intel_combo_phy.c index eccaa79cb4a9..157d8c8c605a 100644 --- a/drivers/gpu/drm/i915/display/intel_combo_phy.c +++ b/drivers/gpu/drm/i915/display/intel_combo_phy.c @@ -52,7 +52,7 @@ cnl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy) switch (val & (PROCESS_INFO_MASK | VOLTAGE_INFO_MASK)) { default: MISSING_CASE(val); - /* fall through */ + fallthrough; case VOLTAGE_INFO_0_85V | PROCESS_INFO_DOT_0: procmon = &cnl_procmon_values[PROCMON_0_85V_DOT_0]; break; @@ -258,7 +258,7 @@ static bool phy_is_master(struct drm_i915_private *dev_priv, enum phy phy) static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv, enum phy phy) { - bool ret; + bool ret = true; u32 expected_val = 0; if (!icl_combo_phy_enabled(dev_priv, phy)) @@ -276,7 +276,7 @@ static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv, DCC_MODE_SELECT_CONTINUOSLY); } - ret = cnl_verify_procmon_ref_values(dev_priv, phy); + ret &= cnl_verify_procmon_ref_values(dev_priv, phy); if (phy_is_master(dev_priv, phy)) { ret &= check_phy_reg(dev_priv, phy, ICL_PORT_COMP_DW8(phy), @@ -320,7 +320,7 @@ void intel_combo_phy_power_up_lanes(struct drm_i915_private *dev_priv, break; default: MISSING_CASE(lane_count); - /* fall-through */ + fallthrough; case 4: lane_mask = PWR_UP_ALL_LANES; break; @@ -337,7 +337,7 @@ void intel_combo_phy_power_up_lanes(struct drm_i915_private *dev_priv, break; default: MISSING_CASE(lane_count); - /* fall-through */ + fallthrough; case 4: lane_mask = PWR_UP_ALL_LANES; break; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 2c484b55bcdf..a49ff3a1a63c 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -1888,7 +1888,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder, switch (tmp & TRANS_DDI_EDP_INPUT_MASK) { default: MISSING_CASE(tmp & TRANS_DDI_EDP_INPUT_MASK); - /* fallthrough */ + fallthrough; case TRANS_DDI_EDP_INPUT_A_ON: case TRANS_DDI_EDP_INPUT_A_ONOFF: *pipe_mask = BIT(PIPE_A); @@ -4268,7 +4268,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder, pipe_config->hdmi_scrambling = true; if (temp & TRANS_DDI_HIGH_TMDS_CHAR_RATE) pipe_config->hdmi_high_tmds_clock_ratio = true; - /* fall through */ + fallthrough; case TRANS_DDI_MODE_SELECT_DVI: pipe_config->output_types |= BIT(INTEL_OUTPUT_HDMI); pipe_config->lane_count = 4; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 729ec6e0d43a..68325678f5ef 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -2029,12 +2029,12 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane) case I915_FORMAT_MOD_Y_TILED_CCS: if (is_ccs_plane(fb, color_plane)) return 128; - /* fall through */ + fallthrough; case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS: case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: if (is_ccs_plane(fb, color_plane)) return 64; - /* fall through */ + fallthrough; case I915_FORMAT_MOD_Y_TILED: if (IS_GEN(dev_priv, 2) || HAS_128_BYTE_Y_TILING(dev_priv)) return 128; @@ -2043,7 +2043,7 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane) case I915_FORMAT_MOD_Yf_TILED_CCS: if (is_ccs_plane(fb, color_plane)) return 128; - /* fall through */ + fallthrough; case I915_FORMAT_MOD_Yf_TILED: switch (cpp) { case 1: @@ -2185,7 +2185,7 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb, case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: if (is_semiplanar_uv_plane(fb, color_plane)) return intel_tile_row_size(fb, color_plane); - /* Fall-through */ + fallthrough; case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS: return 16 * 1024; case I915_FORMAT_MOD_Y_TILED_CCS: @@ -2194,7 +2194,7 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb, if (INTEL_GEN(dev_priv) >= 12 && is_semiplanar_uv_plane(fb, color_plane)) return intel_tile_row_size(fb, color_plane); - /* Fall-through */ + fallthrough; case I915_FORMAT_MOD_Yf_TILED: return 1 * 1024 * 1024; default: @@ -6211,7 +6211,7 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state, case DRM_FORMAT_ARGB16161616F: if (INTEL_GEN(dev_priv) >= 11) break; - /* fall through */ + fallthrough; default: drm_dbg_kms(&dev_priv->drm, "[PLANE:%d:%s] FB:%d unsupported scaling format 0x%x\n", @@ -10896,7 +10896,7 @@ static void hsw_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port, break; default: MISSING_CASE(ddi_pll_sel); - /* fall through */ + fallthrough; case PORT_CLK_SEL_NONE: return; } @@ -10956,10 +10956,10 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc, drm_WARN(dev, 1, "unknown pipe linked to transcoder %s\n", transcoder_name(panel_transcoder)); - /* fall through */ + fallthrough; case TRANS_DDI_EDP_INPUT_A_ONOFF: force_thru = true; - /* fall through */ + fallthrough; case TRANS_DDI_EDP_INPUT_A_ON: trans_pipe = PIPE_A; break; @@ -13183,7 +13183,7 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state) case INTEL_OUTPUT_DDI: if (drm_WARN_ON(dev, !HAS_DDI(to_i915(dev)))) break; - /* else, fall through */ + fallthrough; case INTEL_OUTPUT_DP: case INTEL_OUTPUT_HDMI: case INTEL_OUTPUT_EDP: @@ -14930,7 +14930,7 @@ static int intel_atomic_check(struct drm_device *dev, if (any_ms && !check_digital_port_conflicts(state)) { drm_dbg_kms(&dev_priv->drm, "rejecting conflicting digital port configuration\n"); - ret = EINVAL; + ret = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index 3644752cc5ec..5a5cfe25085b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -2044,9 +2044,12 @@ DEFINE_SHOW_ATTRIBUTE(i915_hdcp_sink_capability); static int i915_lpsp_capability_show(struct seq_file *m, void *data) { struct drm_connector *connector = m->private; - struct intel_encoder *encoder = - intel_attached_encoder(to_intel_connector(connector)); struct drm_i915_private *i915 = to_i915(connector->dev); + struct intel_encoder *encoder; + + encoder = intel_attached_encoder(to_intel_connector(connector)); + if (!encoder) + return -ENODEV; if (connector->status != connector_status_connected) return -ENODEV; diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 0c713e83274d..e0fcb89c736b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -4147,6 +4147,12 @@ static const struct i915_power_well_desc tgl_power_wells[] = { }, }, { + .name = "TC cold off", + .domains = TGL_TC_COLD_OFF_POWER_DOMAINS, + .ops = &tgl_tc_cold_off_ops, + .id = DISP_PW_ID_NONE, + }, + { .name = "AUX A", .domains = TGL_AUX_A_IO_POWER_DOMAINS, .ops = &icl_aux_power_well_ops, @@ -4332,12 +4338,6 @@ static const struct i915_power_well_desc tgl_power_wells[] = { .hsw.irq_pipe_mask = BIT(PIPE_D), }, }, - { - .name = "TC cold off", - .domains = TGL_TC_COLD_OFF_POWER_DOMAINS, - .ops = &tgl_tc_cold_off_ops, - .id = DISP_PW_ID_NONE, - }, }; static const struct i915_power_well_desc rkl_power_wells[] = { @@ -5240,10 +5240,10 @@ struct buddy_page_mask { }; static const struct buddy_page_mask tgl_buddy_page_masks[] = { - { .num_channels = 1, .type = INTEL_DRAM_LPDDR4, .page_mask = 0xE }, { .num_channels = 1, .type = INTEL_DRAM_DDR4, .page_mask = 0xF }, { .num_channels = 2, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x1C }, { .num_channels = 2, .type = INTEL_DRAM_DDR4, .page_mask = 0x1F }, + { .num_channels = 4, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x38 }, {} }; diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index aeb6ee395cce..afa7a378b31d 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -892,7 +892,7 @@ static int hsw_ddi_wrpll_get_freq(struct drm_i915_private *dev_priv, refclk = dev_priv->dpll.ref_clks.nssc; break; } - /* fall through */ + fallthrough; case WRPLL_REF_PCH_SSC: /* * We could calculate spread here, but our checking @@ -2977,7 +2977,7 @@ static bool icl_calc_tbt_pll(struct intel_crtc_state *crtc_state, switch (dev_priv->dpll.ref_clks.nssc) { default: MISSING_CASE(dev_priv->dpll.ref_clks.nssc); - /* fall-through */ + fallthrough; case 19200: *pll_params = tgl_tbt_pll_19_2MHz_values; break; @@ -2992,7 +2992,7 @@ static bool icl_calc_tbt_pll(struct intel_crtc_state *crtc_state, switch (dev_priv->dpll.ref_clks.nssc) { default: MISSING_CASE(dev_priv->dpll.ref_clks.nssc); - /* fall-through */ + fallthrough; case 19200: case 38400: *pll_params = icl_tbt_pll_19_2MHz_values; @@ -3120,7 +3120,7 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc, switch (div1) { default: MISSING_CASE(div1); - /* fall through */ + fallthrough; case 2: hsdiv = MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_2; break; diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 89a4d294822d..1a0d49af2a08 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -336,8 +336,10 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector, /* Fill up the empty slots in sha_text and write it out */ sha_empty = sizeof(sha_text) - sha_leftovers; - for (j = 0; j < sha_empty; j++) - sha_text |= ksv[j] << ((sizeof(sha_text) - j - 1) * 8); + for (j = 0; j < sha_empty; j++) { + u8 off = ((sizeof(sha_text) - j - 1 - sha_leftovers) * 8); + sha_text |= ksv[j] << off; + } ret = intel_write_sha_text(dev_priv, sha_text); if (ret < 0) @@ -435,7 +437,7 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector, /* Write 32 bits of text */ intel_de_write(dev_priv, HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32); - sha_text |= bstatus[0] << 24 | bstatus[1] << 16; + sha_text |= bstatus[0] << 8 | bstatus[1]; ret = intel_write_sha_text(dev_priv, sha_text); if (ret < 0) return ret; @@ -450,17 +452,29 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector, return ret; sha_idx += sizeof(sha_text); } + + /* + * Terminate the SHA-1 stream by hand. For the other leftover + * cases this is appended by the hardware. + */ + intel_de_write(dev_priv, HDCP_REP_CTL, + rep_ctl | HDCP_SHA1_TEXT_32); + sha_text = DRM_HDCP_SHA1_TERMINATOR << 24; + ret = intel_write_sha_text(dev_priv, sha_text); + if (ret < 0) + return ret; + sha_idx += sizeof(sha_text); } else if (sha_leftovers == 3) { - /* Write 32 bits of text */ + /* Write 32 bits of text (filled from LSB) */ intel_de_write(dev_priv, HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32); - sha_text |= bstatus[0] << 24; + sha_text |= bstatus[0]; ret = intel_write_sha_text(dev_priv, sha_text); if (ret < 0) return ret; sha_idx += sizeof(sha_text); - /* Write 8 bits of text, 24 bits of M0 */ + /* Write 8 bits of text (filled from LSB), 24 bits of M0 */ intel_de_write(dev_priv, HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_8); ret = intel_write_sha_text(dev_priv, bstatus[1]); @@ -781,6 +795,7 @@ static int _intel_hdcp_disable(struct intel_connector *connector) struct intel_hdcp *hdcp = &connector->hdcp; enum port port = dig_port->base.port; enum transcoder cpu_transcoder = hdcp->cpu_transcoder; + u32 repeater_ctl; int ret; drm_dbg_kms(&dev_priv->drm, "[%s:%d] HDCP is being disabled...\n", @@ -796,6 +811,11 @@ static int _intel_hdcp_disable(struct intel_connector *connector) return -ETIMEDOUT; } + repeater_ctl = intel_hdcp_get_repeater_ctl(dev_priv, cpu_transcoder, + port); + intel_de_write(dev_priv, HDCP_REP_CTL, + intel_de_read(dev_priv, HDCP_REP_CTL) & ~repeater_ctl); + ret = hdcp->shim->toggle_signalling(dig_port, false); if (ret) { drm_err(&dev_priv->drm, "Failed to disable HDCP signalling\n"); diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index bbde3b12c311..4072d7062efd 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -229,7 +229,7 @@ int intel_pch_panel_fitting(struct intel_crtc_state *crtc_state, case DRM_MODE_SCALE_NONE: WARN_ON(adjusted_mode->crtc_hdisplay != crtc_state->pipe_src_w); WARN_ON(adjusted_mode->crtc_vdisplay != crtc_state->pipe_src_h); - /* fall through */ + fallthrough; case DRM_MODE_SCALE_FULLSCREEN: x = y = 0; width = adjusted_mode->crtc_hdisplay; diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 2da4388e1540..5e9fb349c829 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -1531,7 +1531,7 @@ static void intel_sdvo_pre_enable(struct intel_atomic_state *state, default: drm_WARN(&dev_priv->drm, 1, "unknown pixel multiplier specified\n"); - /* fall through */ + fallthrough; case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break; case 2: rate = SDVO_CLOCK_RATE_MULT_2X; break; case 4: rate = SDVO_CLOCK_RATE_MULT_4X; break; @@ -2549,19 +2549,19 @@ intel_sdvo_guess_ddc_bus(struct intel_sdvo *sdvo) switch (sdvo->controlled_output) { case SDVO_OUTPUT_LVDS1: mask |= SDVO_OUTPUT_LVDS1; - /* fall through */ + fallthrough; case SDVO_OUTPUT_LVDS0: mask |= SDVO_OUTPUT_LVDS0; - /* fall through */ + fallthrough; case SDVO_OUTPUT_TMDS1: mask |= SDVO_OUTPUT_TMDS1; - /* fall through */ + fallthrough; case SDVO_OUTPUT_TMDS0: mask |= SDVO_OUTPUT_TMDS0; - /* fall through */ + fallthrough; case SDVO_OUTPUT_RGB1: mask |= SDVO_OUTPUT_RGB1; - /* fall through */ + fallthrough; case SDVO_OUTPUT_RGB0: mask |= SDVO_OUTPUT_RGB0; break; diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index d03860fef2d7..c89f5f7ccb06 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -2147,7 +2147,7 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state, case DRM_FORMAT_RGB565: if (INTEL_GEN(dev_priv) >= 11) break; - /* fall through */ + fallthrough; case DRM_FORMAT_C8: case DRM_FORMAT_XRGB16161616F: case DRM_FORMAT_XBGR16161616F: @@ -2702,7 +2702,7 @@ static bool g4x_sprite_format_mod_supported(struct drm_plane *_plane, if (modifier == DRM_FORMAT_MOD_LINEAR || modifier == I915_FORMAT_MOD_X_TILED) return true; - /* fall through */ + fallthrough; default: return false; } @@ -2733,7 +2733,7 @@ static bool snb_sprite_format_mod_supported(struct drm_plane *_plane, if (modifier == DRM_FORMAT_MOD_LINEAR || modifier == I915_FORMAT_MOD_X_TILED) return true; - /* fall through */ + fallthrough; default: return false; } @@ -2768,7 +2768,7 @@ static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane, if (modifier == DRM_FORMAT_MOD_LINEAR || modifier == I915_FORMAT_MOD_X_TILED) return true; - /* fall through */ + fallthrough; default: return false; } @@ -2801,7 +2801,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_ABGR8888: if (is_ccs_modifier(modifier)) return true; - /* fall through */ + fallthrough; case DRM_FORMAT_RGB565: case DRM_FORMAT_XRGB2101010: case DRM_FORMAT_XBGR2101010: @@ -2819,7 +2819,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_XVYU2101010: if (modifier == I915_FORMAT_MOD_Yf_TILED) return true; - /* fall through */ + fallthrough; case DRM_FORMAT_C8: case DRM_FORMAT_XBGR16161616F: case DRM_FORMAT_ABGR16161616F: @@ -2834,7 +2834,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, modifier == I915_FORMAT_MOD_X_TILED || modifier == I915_FORMAT_MOD_Y_TILED) return true; - /* fall through */ + fallthrough; default: return false; } @@ -2860,7 +2860,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: if (!gen12_plane_supports_mc_ccs(dev_priv, plane->id)) return false; - /* fall through */ + fallthrough; case DRM_FORMAT_MOD_LINEAR: case I915_FORMAT_MOD_X_TILED: case I915_FORMAT_MOD_Y_TILED: @@ -2877,7 +2877,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_ABGR8888: if (is_ccs_modifier(modifier)) return true; - /* fall through */ + fallthrough; case DRM_FORMAT_YUYV: case DRM_FORMAT_YVYU: case DRM_FORMAT_UYVY: @@ -2889,7 +2889,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_P016: if (modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS) return true; - /* fall through */ + fallthrough; case DRM_FORMAT_RGB565: case DRM_FORMAT_XRGB2101010: case DRM_FORMAT_XBGR2101010: @@ -2910,7 +2910,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, modifier == I915_FORMAT_MOD_X_TILED || modifier == I915_FORMAT_MOD_Y_TILED) return true; - /* fall through */ + fallthrough; default: return false; } diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 5b5dc86a5737..8f67aef18b2d 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -159,7 +159,7 @@ int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port) switch (lane_mask) { default: MISSING_CASE(lane_mask); - /* fall-through */ + fallthrough; case 0x1: case 0x2: case 0x4: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index b23368529a40..753f82d87a31 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -209,7 +209,7 @@ static vm_fault_t i915_error_to_vmf_fault(int err) switch (err) { default: WARN_ONCE(err, "unhandled error in %s: %i\n", __func__, err); - /* fallthrough */ + fallthrough; case -EIO: /* shmemfs failure from swap device */ case -EFAULT: /* purged object */ case -ENODEV: /* bad object, how did you get here! */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 7050519c87a4..d15ff6748a50 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -276,7 +276,7 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, switch (type) { default: MISSING_CASE(type); - /* fallthrough - to use PAGE_KERNEL anyway */ + fallthrough; /* to use PAGE_KERNEL anyway */ case I915_MAP_WB: pgprot = PAGE_KERNEL; break; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index e0f21f12d3ce..0be5e8683337 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -249,7 +249,7 @@ static void vlv_get_stolen_reserved(struct drm_i915_private *i915, switch (reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK) { default: MISSING_CASE(reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK); - /* fall through */ + fallthrough; case GEN7_STOLEN_RESERVED_1M: *size = 1024 * 1024; break; @@ -416,7 +416,7 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915) case 4: if (!IS_G4X(i915)) break; - /* fall through */ + fallthrough; case 5: g4x_get_stolen_reserved(i915, uncore, &reserved_base, &reserved_size); @@ -445,7 +445,7 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915) break; default: MISSING_CASE(INTEL_GEN(i915)); - /* fall-through */ + fallthrough; case 11: case 12: icl_get_stolen_reserved(i915, uncore, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 2c2bf24140c9..12b30075134a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -596,14 +596,6 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - /* - * Using __get_user_pages_fast() with a read-only - * access is questionable. A read-only page may be - * COW-broken, and then this might end up giving - * the wrong side of the COW.. - * - * We may or may not care. - */ if (pvec) { /* defer to worker if malloc fails */ if (!i915_gem_object_is_readonly(obj)) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index dd1a42c4d344..26087dd79782 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -213,7 +213,7 @@ u32 intel_engine_context_size(struct intel_gt *gt, u8 class) break; default: MISSING_CASE(class); - /* fall through */ + fallthrough; case VIDEO_DECODE_CLASS: case VIDEO_ENHANCEMENT_CLASS: case COPY_ENGINE_CLASS: diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 62979ea591f0..99e28d9021e8 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -1437,7 +1437,7 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma) switch (vma->ggtt_view.type) { default: GEM_BUG_ON(vma->ggtt_view.type); - /* fall through */ + fallthrough; case I915_GGTT_VIEW_NORMAL: vma->pages = vma->obj->mm.pages; return 0; diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 94915f668715..898593ca4889 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -100,7 +100,7 @@ static void set_hwsp(struct intel_engine_cs *engine, u32 offset) */ default: GEM_BUG_ON(engine->id); - /* fallthrough */ + fallthrough; case RCS0: hwsp = RENDER_HWS_PGA_GEN7; break; diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index 072725a448db..ad86c5eb5bba 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -70,6 +70,7 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off, { u8 *cfg_base = vgpu_cfg_space(vgpu); u8 mask, new, old; + pci_power_t pwr; int i = 0; for (; i < bytes && (off + i < sizeof(pci_cfg_space_rw_bmp)); i++) { @@ -91,6 +92,15 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off, /* For other configuration space directly copy as it is. */ if (i < bytes) memcpy(cfg_base + off + i, src + i, bytes - i); + + if (off == vgpu->cfg_space.pmcsr_off && vgpu->cfg_space.pmcsr_off) { + pwr = (pci_power_t __force)(*(u16*)(&vgpu_cfg_space(vgpu)[off]) + & PCI_PM_CTRL_STATE_MASK); + if (pwr == PCI_D3hot) + vgpu->d3_entered = true; + gvt_dbg_core("vgpu-%d power status changed to %d\n", + vgpu->id, pwr); + } } /** @@ -366,6 +376,7 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, struct intel_gvt *gvt = vgpu->gvt; const struct intel_gvt_device_info *info = &gvt->device_info; u16 *gmch_ctl; + u8 next; memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space, info->cfg_space_size); @@ -401,6 +412,19 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, pci_resource_len(gvt->gt->i915->drm.pdev, 2); memset(vgpu_cfg_space(vgpu) + PCI_ROM_ADDRESS, 0, 4); + + /* PM Support */ + vgpu->cfg_space.pmcsr_off = 0; + if (vgpu_cfg_space(vgpu)[PCI_STATUS] & PCI_STATUS_CAP_LIST) { + next = vgpu_cfg_space(vgpu)[PCI_CAPABILITY_LIST]; + do { + if (vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_ID] == PCI_CAP_ID_PM) { + vgpu->cfg_space.pmcsr_off = next + PCI_PM_CTRL; + break; + } + next = vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_NEXT]; + } while (next); + } } /** diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 210016192ce7..a3a4305eda01 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2501,7 +2501,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) return create_scratch_page_tree(vgpu); } -static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) +void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) { struct list_head *pos, *n; struct intel_vgpu_mm *mm; diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 320b8d6ad92f..52d0d88abd86 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -279,4 +279,6 @@ int intel_vgpu_emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, int intel_vgpu_emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, void *p_data, unsigned int bytes); +void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu); + #endif /* _GVT_GTT_H_ */ diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index a4a6db6b7f90..ff7f2515a6fe 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -106,6 +106,7 @@ struct intel_vgpu_pci_bar { struct intel_vgpu_cfg_space { unsigned char virtual_cfg_space[PCI_CFG_SPACE_EXP_SIZE]; struct intel_vgpu_pci_bar bar[INTEL_GVT_MAX_BAR_NUM]; + u32 pmcsr_off; }; #define vgpu_cfg_space(vgpu) ((vgpu)->cfg_space.virtual_cfg_space) @@ -198,6 +199,8 @@ struct intel_vgpu { struct intel_vgpu_submission submission; struct radix_tree_root page_track_tree; u32 hws_pga[I915_NUM_ENGINES]; + /* Set on PCI_D3, reset on DMLR, not reflecting the actual PM state */ + bool d3_entered; struct dentry *debugfs; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 63bba7b4bb2f..05f3bc98d242 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1226,7 +1226,7 @@ static int handle_g2v_notification(struct intel_vgpu *vgpu, int notification) switch (notification) { case VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE: root_entry_type = GTT_TYPE_PPGTT_ROOT_L3_ENTRY; - /* fall through */ + fallthrough; case VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE: mm = intel_vgpu_get_ppgtt_mm(vgpu, root_entry_type, pdps); return PTR_ERR_OR_ZERO(mm); diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 7d361623ff67..8fa9b31a2484 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -257,6 +257,7 @@ void intel_gvt_release_vgpu(struct intel_vgpu *vgpu) intel_gvt_deactivate_vgpu(vgpu); mutex_lock(&vgpu->vgpu_lock); + vgpu->d3_entered = false; intel_vgpu_clean_workloads(vgpu, ALL_ENGINES); intel_vgpu_dmabuf_cleanup(vgpu); mutex_unlock(&vgpu->vgpu_lock); @@ -393,6 +394,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, INIT_RADIX_TREE(&vgpu->page_track_tree, GFP_KERNEL); idr_init(&vgpu->object_idr); intel_vgpu_init_cfg_space(vgpu, param->primary); + vgpu->d3_entered = false; ret = intel_vgpu_init_mmio(vgpu); if (ret) @@ -557,10 +559,15 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, /* full GPU reset or device model level reset */ if (engine_mask == ALL_ENGINES || dmlr) { intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0); - intel_vgpu_invalidate_ppgtt(vgpu); + if (engine_mask == ALL_ENGINES) + intel_vgpu_invalidate_ppgtt(vgpu); /*fence will not be reset during virtual reset */ if (dmlr) { - intel_vgpu_reset_gtt(vgpu); + if(!vgpu->d3_entered) { + intel_vgpu_invalidate_ppgtt(vgpu); + intel_vgpu_destroy_all_ppgtt_mm(vgpu); + } + intel_vgpu_reset_ggtt(vgpu, true); intel_vgpu_reset_resource(vgpu); } @@ -572,7 +579,14 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, intel_vgpu_reset_cfg_space(vgpu); /* only reset the failsafe mode when dmlr reset */ vgpu->failsafe = false; - vgpu->pv_notified = false; + /* + * PCI_D0 is set before dmlr, so reset d3_entered here + * after done using. + */ + if(vgpu->d3_entered) + vgpu->d3_entered = false; + else + vgpu->pv_notified = false; } } diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 372354d33f55..5ac4a999f05a 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1204,6 +1204,12 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, return dst; } +static inline bool cmd_desc_is(const struct drm_i915_cmd_descriptor * const desc, + const u32 cmd) +{ + return desc->cmd.value == (cmd & desc->cmd.mask); +} + static bool check_cmd(const struct intel_engine_cs *engine, const struct drm_i915_cmd_descriptor *desc, const u32 *cmd, u32 length) @@ -1242,19 +1248,19 @@ static bool check_cmd(const struct intel_engine_cs *engine, * allowed mask/value pair given in the whitelist entry. */ if (reg->mask) { - if (desc->cmd.value == MI_LOAD_REGISTER_MEM) { + if (cmd_desc_is(desc, MI_LOAD_REGISTER_MEM)) { DRM_DEBUG("CMD: Rejected LRM to masked register 0x%08X\n", reg_addr); return false; } - if (desc->cmd.value == MI_LOAD_REGISTER_REG) { + if (cmd_desc_is(desc, MI_LOAD_REGISTER_REG)) { DRM_DEBUG("CMD: Rejected LRR to masked register 0x%08X\n", reg_addr); return false; } - if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) && + if (cmd_desc_is(desc, MI_LOAD_REGISTER_IMM(1)) && (offset + 2 > length || (cmd[offset + 1] & reg->mask) != reg->value)) { DRM_DEBUG("CMD: Rejected LRI to masked register 0x%08X\n", @@ -1478,7 +1484,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, break; } - if (desc->cmd.value == MI_BATCH_BUFFER_START) { + if (cmd_desc_is(desc, MI_BATCH_BUFFER_START)) { ret = check_bbstart(cmd, offset, length, batch_length, batch_addr, shadow_addr, jump_whitelist); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 6a3a2ce0b394..3e6cbb0d1150 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1159,7 +1159,7 @@ static void engine_record_registers(struct intel_engine_coredump *ee) switch (engine->id) { default: MISSING_CASE(engine->id); - /* fall through */ + fallthrough; case RCS0: mmio = RENDER_HWS_PGA_GEN7; break; diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 28bc5f13ae52..69c0fa20eba1 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -445,8 +445,6 @@ static void i915_pmu_event_destroy(struct perf_event *event) container_of(event->pmu, typeof(*i915), pmu.base); drm_WARN_ON(&i915->drm, event->parent); - - module_put(THIS_MODULE); } static int @@ -476,7 +474,7 @@ config_status(struct drm_i915_private *i915, u64 config) if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) /* Requires a mutex for sampling! */ return -ENODEV; - /* Fall-through. */ + fallthrough; case I915_PMU_REQUESTED_FREQUENCY: if (INTEL_GEN(i915) < 6) return -ENODEV; @@ -538,10 +536,8 @@ static int i915_pmu_event_init(struct perf_event *event) if (ret) return ret; - if (!event->parent) { - __module_get(THIS_MODULE); + if (!event->parent) event->destroy = i915_pmu_event_destroy; - } return 0; } @@ -1130,6 +1126,7 @@ void i915_pmu_register(struct drm_i915_private *i915) if (!pmu->base.attr_groups) goto err_attr; + pmu->base.module = THIS_MODULE; pmu->base.task_ctx_nr = perf_invalid_context; pmu->base.event_init = i915_pmu_event_init; pmu->base.add = i915_pmu_event_add; diff --git a/drivers/gpu/drm/i915/selftests/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c index 939a6caebb03..632b912b0bc9 100644 --- a/drivers/gpu/drm/i915/selftests/i915_buddy.c +++ b/drivers/gpu/drm/i915/selftests/i915_buddy.c @@ -8,8 +8,6 @@ #include "../i915_selftest.h" #include "i915_random.h" -#define SZ_8G (1ULL << 33) - static void __igt_dump_block(struct i915_buddy_mm *mm, struct i915_buddy_block *block, bool buddy) @@ -281,18 +279,22 @@ static int igt_check_mm(struct i915_buddy_mm *mm) static void igt_mm_config(u64 *size, u64 *chunk_size) { I915_RND_STATE(prng); - u64 s, ms; + u32 s, ms; /* Nothing fancy, just try to get an interesting bit pattern */ prandom_seed_state(&prng, i915_selftest.random_seed); - s = i915_prandom_u64_state(&prng) & (SZ_8G - 1); - ms = BIT_ULL(12 + (prandom_u32_state(&prng) % ilog2(s >> 12))); - s = max(s & -ms, ms); + /* Let size be a random number of pages up to 8 GB (2M pages) */ + s = 1 + i915_prandom_u32_max_state((BIT(33 - 12)) - 1, &prng); + /* Let the chunk size be a random power of 2 less than size */ + ms = BIT(i915_prandom_u32_max_state(ilog2(s), &prng)); + /* Round size down to the chunk size */ + s &= -ms; - *chunk_size = ms; - *size = s; + /* Convert from pages to bytes */ + *chunk_size = (u64)ms << 12; + *size = (u64)s << 12; } static int igt_buddy_alloc_smoke(void *arg) diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index b9810bf156c3..f127e633f7ca 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -78,6 +78,7 @@ static void mock_device_release(struct drm_device *dev) drm_mode_config_cleanup(&i915->drm); out: + i915_params_free(&i915->params); put_device(&i915->drm.pdev->dev); i915->drm.pdev = NULL; } @@ -165,6 +166,8 @@ struct drm_i915_private *mock_gem_device(void) i915->drm.pdev = pdev; drmm_add_final_kfree(&i915->drm, i915); + i915_params_copy(&i915->params, &i915_modparams); + intel_runtime_pm_init_early(&i915->runtime_pm); /* Using the global GTT may ask questions about KMS users, so prepare */ diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 6776ebb3246d..8a4235d9d9f1 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -447,7 +447,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane, if (fb->pitches[1] != fb->pitches[2]) return -EINVAL; - /* fall-through */ + fallthrough; case DRM_FORMAT_NV12: case DRM_FORMAT_NV16: ubo = drm_plane_state_to_ubo(state); diff --git a/drivers/gpu/drm/meson/meson_osd_afbcd.c b/drivers/gpu/drm/meson/meson_osd_afbcd.c index f12e0271f166..ffc6b584dbf8 100644 --- a/drivers/gpu/drm/meson/meson_osd_afbcd.c +++ b/drivers/gpu/drm/meson/meson_osd_afbcd.c @@ -205,7 +205,7 @@ static int meson_g12a_afbcd_pixel_fmt(u64 modifier, uint32_t format) /* YTR is forbidden for non XBGR formats */ if (modifier & AFBC_FORMAT_MOD_YTR) return -EINVAL; - /* fall through */ + fallthrough; case DRM_FORMAT_XBGR8888: case DRM_FORMAT_ABGR8888: return MAFBC_FMT_RGBA8888; diff --git a/drivers/gpu/drm/meson/meson_overlay.c b/drivers/gpu/drm/meson/meson_overlay.c index a8bcc70644df..1ffbbecafa22 100644 --- a/drivers/gpu/drm/meson/meson_overlay.c +++ b/drivers/gpu/drm/meson/meson_overlay.c @@ -654,7 +654,7 @@ static void meson_overlay_atomic_update(struct drm_plane *plane, priv->viu.vd1_addr2, priv->viu.vd1_stride2, priv->viu.vd1_height2); - /* fallthrough */ + fallthrough; case 2: gem = drm_fb_cma_get_gem_obj(fb, 1); priv->viu.vd1_addr1 = gem->paddr + fb->offsets[1]; @@ -666,7 +666,7 @@ static void meson_overlay_atomic_update(struct drm_plane *plane, priv->viu.vd1_addr1, priv->viu.vd1_stride1, priv->viu.vd1_height1); - /* fallthrough */ + fallthrough; case 1: gem = drm_fb_cma_get_gem_obj(fb, 0); priv->viu.vd1_addr0 = gem->paddr + fb->offsets[0]; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 9e63a190642c..84a5d9c1f2a2 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -59,7 +59,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; - /* fall-thru */ + fallthrough; case MSM_SUBMIT_CMD_BUF: /* copy commands into RB: */ obj = submit->bos[submit->cmd[i].idx].obj; @@ -150,7 +150,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; - /* fall-thru */ + fallthrough; case MSM_SUBMIT_CMD_BUF: OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index b67b38c8fadf..e1c7bcd1b1eb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -133,7 +133,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) if (!gmu->legacy) { a6xx_hfi_set_freq(gmu, perf_index); - icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216)); + dev_pm_opp_set_bw(&gpu->pdev->dev, opp); pm_runtime_put(gmu->dev); return; } @@ -157,11 +157,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) if (ret) dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret); - /* - * Eventually we will want to scale the path vote with the frequency but - * for now leave it at max so that the performance is nominal. - */ - icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216)); + dev_pm_opp_set_bw(&gpu->pdev->dev, opp); pm_runtime_put(gmu->dev); } @@ -204,6 +200,16 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) { int ret; u32 val; + u32 mask, reset_val; + + val = gmu_read(gmu, REG_A6XX_GMU_CM3_DTCM_START + 0xff8); + if (val <= 0x20010004) { + mask = 0xffffffff; + reset_val = 0xbabeface; + } else { + mask = 0x1ff; + reset_val = 0x100; + } gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1); @@ -215,7 +221,7 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 0); ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_CM3_FW_INIT_RESULT, val, - val == 0xbabeface, 100, 10000); + (val & mask) == reset_val, 100, 10000); if (ret) DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n"); @@ -602,7 +608,7 @@ static void a6xx_gmu_power_config(struct a6xx_gmu *gmu) gmu_rmw(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_CTRL, 0, A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_IFPC_ENABLE | A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_HM_POWER_COLLAPSE_ENABLE); - /* Fall through */ + fallthrough; case GMU_IDLE_STATE_SPTP: gmu_write(gmu, REG_A6XX_GMU_PWR_COL_SPTPRAC_HYST, GMU_PWR_COL_HYST); @@ -845,10 +851,24 @@ static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu) if (IS_ERR_OR_NULL(gpu_opp)) return; + gmu->freq = 0; /* so a6xx_gmu_set_freq() doesn't exit early */ a6xx_gmu_set_freq(gpu, gpu_opp); dev_pm_opp_put(gpu_opp); } +static void a6xx_gmu_set_initial_bw(struct msm_gpu *gpu, struct a6xx_gmu *gmu) +{ + struct dev_pm_opp *gpu_opp; + unsigned long gpu_freq = gmu->gpu_freqs[gmu->current_perf_index]; + + gpu_opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, gpu_freq, true); + if (IS_ERR_OR_NULL(gpu_opp)) + return; + + dev_pm_opp_set_bw(&gpu->pdev->dev, gpu_opp); + dev_pm_opp_put(gpu_opp); +} + int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; @@ -882,7 +902,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) } /* Set the bus quota to a reasonable value for boot */ - icc_set_bw(gpu->icc_path, 0, MBps_to_icc(3072)); + a6xx_gmu_set_initial_bw(gpu, gmu); /* Enable the GMU interrupt */ gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_CLR, ~0); @@ -1051,7 +1071,7 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu) a6xx_gmu_shutdown(gmu); /* Remove the bus vote */ - icc_set_bw(gpu->icc_path, 0, 0); + dev_pm_opp_set_bw(&gpu->pdev->dev, NULL); /* * Make sure the GX domain is off before turning off the GMU (CX) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index c5a3e4d4c007..3966abd523cc 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -117,7 +117,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; - /* fall-thru */ + fallthrough; case MSM_SUBMIT_CMD_BUF: OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 959656ad6987..b12f5b4a1bea 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -938,7 +938,8 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) msm_gem_kernel_put(dumper.bo, gpu->aspace, true); } - a6xx_get_debugbus(gpu, a6xx_state); + if (snapshot_debugbus) + a6xx_get_debugbus(gpu, a6xx_state); return &a6xx_state->base; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 846fd5b54c23..2fb58b7098e4 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -372,7 +372,7 @@ static const struct a6xx_indexed_registers { u32 data; u32 count; } a6xx_indexed_reglist[] = { - { "CP_SEQ_STAT", REG_A6XX_CP_SQE_STAT_ADDR, + { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, REG_A6XX_CP_SQE_STAT_DATA, 0x33 }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100 }, diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 4e84f3c76f4f..9eeb46bf2a5d 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -14,6 +14,10 @@ bool hang_debug = false; MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)"); module_param_named(hang_debug, hang_debug, bool, 0600); +bool snapshot_debugbus = false; +MODULE_PARM_DESC(snapshot_debugbus, "Include debugbus sections in GPU devcoredump (if not fused off)"); +module_param_named(snapshot_debugbus, snapshot_debugbus, bool, 0600); + static const struct adreno_info gpulist[] = { { .rev = ADRENO_REV(2, 0, 0, 0), diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index e23641a5ec84..288141fe4c58 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -396,7 +396,7 @@ int adreno_hw_init(struct msm_gpu *gpu) ring->next = ring->start; /* reset completed fence seqno: */ - ring->memptrs->fence = ring->seqno; + ring->memptrs->fence = ring->fctx->completed_fence; ring->memptrs->rptr = 0; } @@ -474,7 +474,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, /* ignore if there has not been a ctx switch: */ if (priv->lastctx == ctx) break; - /* fall-thru */ + fallthrough; case MSM_SUBMIT_CMD_BUF: OUT_PKT3(ring, adreno_is_a4xx(adreno_gpu) ? CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 99bb468f5f24..e55abae365b5 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -21,6 +21,8 @@ #define REG_SKIP ~0 #define REG_ADRENO_SKIP(_offset) [_offset] = REG_SKIP +extern bool snapshot_debugbus; + /** * adreno_regs: List of registers that are used in across all * 3D devices. Each device type has different offset value for the same diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index f272a8d0f95b..c2729f71e2fa 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -827,7 +827,7 @@ static void dpu_crtc_enable(struct drm_crtc *crtc, { struct dpu_crtc *dpu_crtc; struct drm_encoder *encoder; - bool request_bandwidth; + bool request_bandwidth = false; if (!crtc) { DPU_ERROR("invalid crtc\n"); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index a97f6d2e5a08..bd6def436c65 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -599,7 +599,10 @@ static int dpu_encoder_virt_atomic_check( dpu_kms = to_dpu_kms(priv->kms); mode = &crtc_state->mode; adj_mode = &crtc_state->adjusted_mode; - global_state = dpu_kms_get_existing_global_state(dpu_kms); + global_state = dpu_kms_get_global_state(crtc_state->state); + if (IS_ERR(global_state)) + return PTR_ERR(global_state); + trace_dpu_enc_atomic_check(DRMID(drm_enc)); /* perform atomic check on the first physical encoder (master) */ @@ -625,12 +628,15 @@ static int dpu_encoder_virt_atomic_check( /* Reserve dynamic resources now. */ if (!ret) { /* - * Avoid reserving resources when mode set is pending. Topology - * info may not be available to complete reservation. + * Release and Allocate resources on every modeset + * Dont allocate when active is false. */ if (drm_atomic_crtc_needs_modeset(crtc_state)) { - ret = dpu_rm_reserve(&dpu_kms->rm, global_state, - drm_enc, crtc_state, topology); + dpu_rm_release(global_state, drm_enc); + + if (!crtc_state->active_changed || crtc_state->active) + ret = dpu_rm_reserve(&dpu_kms->rm, global_state, + drm_enc, crtc_state, topology); } } @@ -1181,7 +1187,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) struct dpu_encoder_virt *dpu_enc = NULL; struct msm_drm_private *priv; struct dpu_kms *dpu_kms; - struct dpu_global_state *global_state; int i = 0; if (!drm_enc) { @@ -1200,7 +1205,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) priv = drm_enc->dev->dev_private; dpu_kms = to_dpu_kms(priv->kms); - global_state = dpu_kms_get_existing_global_state(dpu_kms); trace_dpu_enc_disable(DRMID(drm_enc)); @@ -1230,8 +1234,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n"); - dpu_rm_release(global_state, drm_enc); - mutex_unlock(&dpu_enc->enc_lock); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 33f6c56f01ed..29e373d2e7b5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -866,9 +866,9 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc); - min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxdwnscale); + min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxupscale); ret = drm_atomic_helper_check_plane_state(state, crtc_state, min_scale, - pdpu->pipe_sblk->maxupscale << 16, + pdpu->pipe_sblk->maxdwnscale << 16, true, true); if (ret) { DPU_DEBUG_PLANE(pdpu, "Check plane state failed (%d)\n", ret); diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 5ccfad794c6a..561bfa48841c 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -27,6 +27,34 @@ int msm_atomic_prepare_fb(struct drm_plane *plane, return msm_framebuffer_prepare(new_state->fb, kms->aspace); } +/* + * Helpers to control vblanks while we flush.. basically just to ensure + * that vblank accounting is switched on, so we get valid seqn/timestamp + * on pageflip events (if requested) + */ + +static void vblank_get(struct msm_kms *kms, unsigned crtc_mask) +{ + struct drm_crtc *crtc; + + for_each_crtc_mask(kms->dev, crtc, crtc_mask) { + if (!crtc->state->active) + continue; + drm_crtc_vblank_get(crtc); + } +} + +static void vblank_put(struct msm_kms *kms, unsigned crtc_mask) +{ + struct drm_crtc *crtc; + + for_each_crtc_mask(kms->dev, crtc, crtc_mask) { + if (!crtc->state->active) + continue; + drm_crtc_vblank_put(crtc); + } +} + static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx) { unsigned crtc_mask = BIT(crtc_idx); @@ -44,6 +72,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx) kms->funcs->enable_commit(kms); + vblank_get(kms, crtc_mask); + /* * Flush hardware updates: */ @@ -58,6 +88,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx) kms->funcs->wait_flush(kms, crtc_mask); trace_msm_atomic_wait_flush_finish(crtc_mask); + vblank_put(kms, crtc_mask); + mutex_lock(&kms->commit_lock); kms->funcs->complete_commit(kms, crtc_mask); mutex_unlock(&kms->commit_lock); @@ -221,6 +253,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) */ kms->pending_crtc_mask &= ~crtc_mask; + vblank_get(kms, crtc_mask); + /* * Flush hardware updates: */ @@ -235,6 +269,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) kms->funcs->wait_flush(kms, crtc_mask); trace_msm_atomic_wait_flush_finish(crtc_mask); + vblank_put(kms, crtc_mask); + mutex_lock(&kms->commit_lock); kms->funcs->complete_commit(kms, crtc_mask); mutex_unlock(&kms->commit_lock); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 7d641c7e3514..79333842f70a 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -1320,6 +1320,13 @@ static int msm_pdev_remove(struct platform_device *pdev) return 0; } +static void msm_pdev_shutdown(struct platform_device *pdev) +{ + struct drm_device *drm = platform_get_drvdata(pdev); + + drm_atomic_helper_shutdown(drm); +} + static const struct of_device_id dt_match[] = { { .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 }, { .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 }, @@ -1332,6 +1339,7 @@ MODULE_DEVICE_TABLE(of, dt_match); static struct platform_driver msm_platform_driver = { .probe = msm_pdev_probe, .remove = msm_pdev_remove, + .shutdown = msm_pdev_shutdown, .driver = { .name = "msm", .of_match_table = dt_match, diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index e397c44cc011..39ecb5a18431 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -27,7 +27,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, ring->id = id; ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ, - MSM_BO_WC, gpu->aspace, &ring->bo, &ring->iova); + MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &ring->bo, + &ring->iova); if (IS_ERR(ring->start)) { ret = PTR_ERR(ring->start); diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c index ad1f09a143aa..248edf69e168 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c @@ -50,7 +50,10 @@ core507d_update(struct nv50_core *core, u32 *interlock, bool ntfy) interlock[NV50_DISP_INTERLOCK_OVLY] | NVDEF(NV507D, UPDATE, NOT_DRIVER_FRIENDLY, FALSE) | NVDEF(NV507D, UPDATE, NOT_DRIVER_UNFRIENDLY, FALSE) | - NVDEF(NV507D, UPDATE, INHIBIT_INTERRUPTS, FALSE)); + NVDEF(NV507D, UPDATE, INHIBIT_INTERRUPTS, FALSE), + + SET_NOTIFIER_CONTROL, + NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, DISABLE)); return PUSH_KICK(push); } diff --git a/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c b/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c index 9afe9a87bde0..814e5bd97446 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c @@ -6,7 +6,7 @@ #include "disp.h" #include "head.h" -#include <nvif/push507c.h> +#include <nvif/pushc37b.h> #include <nvhw/class/clc37d.h> diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index e7874877da85..1ed242070001 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -257,6 +257,12 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp, dmac->push->end = dmac->push->bgn; dmac->max = 0x1000/4 - 1; + /* EVO channels are affected by a HW bug where the last 12 DWORDs + * of the push buffer aren't able to be used safely. + */ + if (disp->oclass < GV100_DISP) + dmac->max -= 12; + args->pushbuf = nvif_handle(&dmac->_push.mem.object); ret = nv50_chan_create(device, disp, oclass, head, data, size, diff --git a/drivers/gpu/drm/nouveau/include/nvif/push507c.h b/drivers/gpu/drm/nouveau/include/nvif/push507c.h index 889467f13fd9..7917bead4845 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/push507c.h +++ b/drivers/gpu/drm/nouveau/include/nvif/push507c.h @@ -20,6 +20,6 @@ PUSH_ASSERT(!((o) & ~DRF_SMASK(NV507C_DMA_JUMP_OFFSET)), "offset"); \ PUSH_DATA__((p), NVDEF(NV507C, DMA, OPCODE, JUMP) | \ NVVAL(NV507C, DMA, JUMP_OFFSET, (o) >> 2), \ - "jump 0x%08x - %s", (u32)(o), __func__); \ + " jump 0x%08x - %s", (u32)(o), __func__); \ } while(0) #endif diff --git a/drivers/gpu/drm/omapdrm/dss/venc.c b/drivers/gpu/drm/omapdrm/dss/venc.c index e0817934ee16..bd12eae0cb31 100644 --- a/drivers/gpu/drm/omapdrm/dss/venc.c +++ b/drivers/gpu/drm/omapdrm/dss/venc.c @@ -597,7 +597,7 @@ static void venc_bridge_mode_set(struct drm_bridge *bridge, switch (venc_mode) { default: WARN_ON_ONCE(1); - /* Fall-through */ + fallthrough; case VENC_MODE_PAL: venc->config = &venc_config_pal_trm; break; diff --git a/drivers/gpu/drm/omapdrm/omap_crtc.c b/drivers/gpu/drm/omapdrm/omap_crtc.c index 6d40914675da..328a4a74f534 100644 --- a/drivers/gpu/drm/omapdrm/omap_crtc.c +++ b/drivers/gpu/drm/omapdrm/omap_crtc.c @@ -451,11 +451,12 @@ static void omap_crtc_atomic_enable(struct drm_crtc *crtc, if (omap_state->manually_updated) return; - spin_lock_irq(&crtc->dev->event_lock); drm_crtc_vblank_on(crtc); + ret = drm_crtc_vblank_get(crtc); WARN_ON(ret != 0); + spin_lock_irq(&crtc->dev->event_lock); omap_crtc_arm_event(crtc); spin_unlock_irq(&crtc->dev->event_lock); } diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index ba20c6f03719..886e9959496f 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -4856,7 +4856,7 @@ static void ci_request_link_speed_change_before_state_change(struct radeon_devic pi->force_pcie_gen = RADEON_PCIE_GEN2; if (current_link_speed == RADEON_PCIE_GEN2) break; - /* fall through */ + fallthrough; case RADEON_PCIE_GEN2: if (radeon_acpi_pcie_performance_request(rdev, PCIE_PERF_REQ_PECI_GEN2, false) == 0) break; diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 3b7ead5be5bf..73f67bf222e1 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -820,7 +820,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, ((idx_value >> 21) & 0xF)); return -EINVAL; } - /* Fall through. */ + fallthrough; case 6: track->cb[i].cpp = 4; break; @@ -971,7 +971,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, return -EINVAL; } /* The same rules apply as for DXT3/5. */ - /* Fall through. */ + fallthrough; case R300_TX_FORMAT_DXT3: case R300_TX_FORMAT_DXT5: track->textures[i].cpp = 1; diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c index 1d4c04e0a449..50b89b6d9a6c 100644 --- a/drivers/gpu/drm/radeon/r420.c +++ b/drivers/gpu/drm/radeon/r420.c @@ -115,7 +115,7 @@ void r420_pipes_init(struct radeon_device *rdev) default: /* force to 1 pipe */ num_pipes = 1; - /* fall through */ + fallthrough; case 1: tmp = (0 << 1); break; diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 49e8266461f8..390a9621604a 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -487,7 +487,7 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) return -EINVAL; } } - /* fall through */ + fallthrough; case V_0280A0_CLEAR_ENABLE: { uint32_t block_max = G_028100_CMASK_BLOCK_MAX(track->cb_color_mask[i]); @@ -1535,7 +1535,7 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p, u32 idx, break; case V_038000_SQ_TEX_DIM_2D_ARRAY_MSAA: is_array = true; - /* fall through */ + fallthrough; case V_038000_SQ_TEX_DIM_2D_MSAA: array_check.nsamples = 1 << llevel; llevel = 0; diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index e0ae911ef427..7b69d6dfe44a 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -933,7 +933,7 @@ static void avivo_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div, /* get matching reference and feedback divider */ *ref_div = min(max(den/post_div, 1u), ref_div_max); - *fb_div = DIV_ROUND_CLOSEST(nom * *ref_div * post_div, den); + *fb_div = max(nom * *ref_div * post_div / den, 1u); /* limit fb divider to its maximum */ if (*fb_div > fb_div_max) { diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 1ad5c3b86b64..57fb3eb3a4b4 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -454,7 +454,7 @@ static int radeon_uvd_validate_codec(struct radeon_cs_parser *p, if (p->rdev->family >= CHIP_PALM) return 0; - /* fall through */ + fallthrough; default: DRM_ERROR("UVD codec not supported by hardware %d!\n", stream_type); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index a167e1c36d24..d1c73e9db889 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -5744,7 +5744,7 @@ static void si_request_link_speed_change_before_state_change(struct radeon_devic si_pi->force_pcie_gen = RADEON_PCIE_GEN2; if (current_link_speed == RADEON_PCIE_GEN2) break; - /* fall through */ + fallthrough; case RADEON_PCIE_GEN2: if (radeon_acpi_pcie_performance_request(rdev, PCIE_PERF_REQ_PECI_GEN2, false) == 0) break; diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c index f858d8d06347..800721153d51 100644 --- a/drivers/gpu/drm/radeon/uvd_v1_0.c +++ b/drivers/gpu/drm/radeon/uvd_v1_0.c @@ -219,7 +219,7 @@ done: WREG32(RS_DQ_RD_RET_CONF, 0x3f); WREG32(MC_CONFIG, 0x1f); - /* fall through */ + fallthrough; case CHIP_RV670: case CHIP_RV635: diff --git a/drivers/gpu/drm/savage/savage_state.c b/drivers/gpu/drm/savage/savage_state.c index a2ac25c11c90..e0d40ae67d54 100644 --- a/drivers/gpu/drm/savage/savage_state.c +++ b/drivers/gpu/drm/savage/savage_state.c @@ -306,7 +306,7 @@ static int savage_dispatch_dma_prim(drm_savage_private_t * dev_priv, case SAVAGE_PRIM_TRILIST_201: reorder = 1; prim = SAVAGE_PRIM_TRILIST; - /* fall through */ + fallthrough; case SAVAGE_PRIM_TRILIST: if (n % 3 != 0) { DRM_ERROR("wrong number of vertices %u in TRILIST\n", @@ -444,7 +444,7 @@ static int savage_dispatch_vb_prim(drm_savage_private_t * dev_priv, case SAVAGE_PRIM_TRILIST_201: reorder = 1; prim = SAVAGE_PRIM_TRILIST; - /* fall through */ + fallthrough; case SAVAGE_PRIM_TRILIST: if (n % 3 != 0) { DRM_ERROR("wrong number of vertices %u in TRILIST\n", @@ -566,7 +566,7 @@ static int savage_dispatch_dma_idx(drm_savage_private_t * dev_priv, case SAVAGE_PRIM_TRILIST_201: reorder = 1; prim = SAVAGE_PRIM_TRILIST; - /* fall through */ + fallthrough; case SAVAGE_PRIM_TRILIST: if (n % 3 != 0) { DRM_ERROR("wrong number of indices %u in TRILIST\n", n); @@ -705,7 +705,7 @@ static int savage_dispatch_vb_idx(drm_savage_private_t * dev_priv, case SAVAGE_PRIM_TRILIST_201: reorder = 1; prim = SAVAGE_PRIM_TRILIST; - /* fall through */ + fallthrough; case SAVAGE_PRIM_TRILIST: if (n % 3 != 0) { DRM_ERROR("wrong number of indices %u in TRILIST\n", n); @@ -1066,7 +1066,7 @@ int savage_bci_cmdbuf(struct drm_device *dev, void *data, struct drm_file *file_ ret = -EINVAL; goto done; } - /* fall through */ + fallthrough; case SAVAGE_CMD_DMA_PRIM: case SAVAGE_CMD_VB_PRIM: if (!first_draw_cmd) diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index 008f07923bbc..38a558768e53 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -850,13 +850,13 @@ static int hdmi_audio_configure(struct sti_hdmi *hdmi) switch (info->channels) { case 8: audio_cfg |= HDMI_AUD_CFG_CH78_VALID; - /* fall through */ + fallthrough; case 6: audio_cfg |= HDMI_AUD_CFG_CH56_VALID; - /* fall through */ + fallthrough; case 4: audio_cfg |= HDMI_AUD_CFG_CH34_VALID | HDMI_AUD_CFG_8CH; - /* fall through */ + fallthrough; case 2: audio_cfg |= HDMI_AUD_CFG_CH12_VALID; break; diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 359b56e43b83..ced9a8287dd8 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -195,7 +195,7 @@ void sun4i_tcon_set_status(struct sun4i_tcon *tcon, switch (encoder->encoder_type) { case DRM_MODE_ENCODER_LVDS: is_lvds = true; - /* Fallthrough */ + fallthrough; case DRM_MODE_ENCODER_DSI: case DRM_MODE_ENCODER_NONE: channel = 0; @@ -342,7 +342,7 @@ static void sun4i_tcon0_mode_set_dithering(struct sun4i_tcon *tcon, /* R and B components are only 5 bits deep */ val |= SUN4I_TCON0_FRM_CTL_MODE_R; val |= SUN4I_TCON0_FRM_CTL_MODE_B; - /* Fall through */ + fallthrough; case MEDIA_BUS_FMT_RGB666_1X18: case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: /* Fall through: enable dithering */ diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index aa67cb037e9d..7f13f4d715bf 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -1027,7 +1027,7 @@ static ssize_t sun6i_dsi_transfer(struct mipi_dsi_host *host, ret = sun6i_dsi_dcs_read(dsi, msg); break; } - /* Else, fall through */ + fallthrough; default: ret = -EINVAL; diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 9a0b3240bc58..424ad60b4f38 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -135,7 +135,7 @@ static inline u32 compute_dda_inc(unsigned int in, unsigned int out, bool v, default: WARN_ON_ONCE(1); - /* fallthrough */ + fallthrough; case 4: max = 4; break; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c index 1856962411c7..518220bd092a 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c @@ -386,7 +386,7 @@ static void tilcdc_crtc_set_mode(struct drm_crtc *crtc) case DRM_FORMAT_XBGR8888: case DRM_FORMAT_XRGB8888: reg |= LCDC_V2_TFT_24BPP_UNPACK; - /* fallthrough */ + fallthrough; case DRM_FORMAT_BGR888: case DRM_FORMAT_RGB888: reg |= LCDC_V2_TFT_24BPP_MODE; diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 33526c5df0e8..4732dcc80e11 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -525,7 +525,7 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, if (unlikely(ret != 0)) return ret; } - /* fall through */ + fallthrough; case TTM_PL_TT: ret = ttm_bo_vm_access_kmap(bo, offset, buf, len, write); break; diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c index 551fa31629af..5771bb53ce6a 100644 --- a/drivers/gpu/drm/via/via_dmablit.c +++ b/drivers/gpu/drm/via/via_dmablit.c @@ -179,21 +179,21 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg) switch (vsg->state) { case dr_via_device_mapped: via_unmap_blit_from_device(pdev, vsg); - /* fall through */ + fallthrough; case dr_via_desc_pages_alloc: for (i = 0; i < vsg->num_desc_pages; ++i) { if (vsg->desc_pages[i] != NULL) free_page((unsigned long)vsg->desc_pages[i]); } kfree(vsg->desc_pages); - /* fall through */ + fallthrough; case dr_via_pages_locked: unpin_user_pages_dirty_lock(vsg->pages, vsg->num_pages, (vsg->direction == DMA_FROM_DEVICE)); - /* fall through */ + fallthrough; case dr_via_pages_alloc: vfree(vsg->pages); - /* fall through */ + fallthrough; default: vsg->state = dr_via_sg_init; } diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 7a2430e34e00..c8da7adc6b30 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -179,6 +179,7 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, virtio_gpu_cmd_submit(vgdev, buf, exbuf->size, vfpriv->ctx_id, buflist, out_fence); + dma_fence_put(&out_fence->f); virtio_gpu_notify(vgdev); return 0; diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 2cdd3cd9ce75..e83651b7747d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -79,6 +79,7 @@ void virtio_gpu_cleanup_object(struct virtio_gpu_object *bo) } sg_free_table(shmem->pages); + kfree(shmem->pages); shmem->pages = NULL; drm_gem_shmem_unpin(&bo->base.base); } diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index 013c9e0e412c..cc93a8c9547b 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -649,9 +649,7 @@ static void displback_changed(struct xenbus_device *xb_dev, switch (backend_state) { case XenbusStateReconfiguring: - /* fall through */ case XenbusStateReconfigured: - /* fall through */ case XenbusStateInitialised: break; @@ -701,7 +699,6 @@ static void displback_changed(struct xenbus_device *xb_dev, break; case XenbusStateUnknown: - /* fall through */ case XenbusStateClosed: if (xb_dev->state == XenbusStateClosed) break; diff --git a/drivers/gpu/ipu-v3/ipu-dc.c b/drivers/gpu/ipu-v3/ipu-dc.c index dbcc16721931..34b4075a6a8e 100644 --- a/drivers/gpu/ipu-v3/ipu-dc.c +++ b/drivers/gpu/ipu-v3/ipu-dc.c @@ -141,7 +141,7 @@ static int ipu_bus_format_to_map(u32 fmt) switch (fmt) { default: WARN_ON(1); - /* fall-through */ + fallthrough; case MEDIA_BUS_FMT_RGB888_1X24: return IPU_DC_MAP_RGB24; case MEDIA_BUS_FMT_RGB565_1X16: diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 359616e3efbb..d2ecc9c45255 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1598,6 +1598,17 @@ static void hid_output_field(const struct hid_device *hid, } /* + * Compute the size of a report. + */ +static size_t hid_compute_report_size(struct hid_report *report) +{ + if (report->size) + return ((report->size - 1) >> 3) + 1; + + return 0; +} + +/* * Create a report. 'data' has to be allocated using * hid_alloc_report_buf() so that it has proper size. */ @@ -1609,7 +1620,7 @@ void hid_output_report(struct hid_report *report, __u8 *data) if (report->id > 0) *data++ = report->id; - memset(data, 0, ((report->size - 1) >> 3) + 1); + memset(data, 0, hid_compute_report_size(report)); for (n = 0; n < report->maxfield; n++) hid_output_field(report->device, report->field[n], data); } @@ -1739,7 +1750,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, csize--; } - rsize = ((report->size - 1) >> 3) + 1; + rsize = hid_compute_report_size(report); if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) rsize = HID_MAX_BUFFER_SIZE - 1; diff --git a/drivers/hid/hid-cougar.c b/drivers/hid/hid-cougar.c index 4ff3bc1d25e2..28d671c5e0ca 100644 --- a/drivers/hid/hid-cougar.c +++ b/drivers/hid/hid-cougar.c @@ -321,7 +321,7 @@ static const struct kernel_param_ops cougar_g6_is_space_ops = { }; module_param_cb(g6_is_space, &cougar_g6_is_space_ops, &g6_is_space, 0644); -static struct hid_device_id cougar_id_table[] = { +static const struct hid_device_id cougar_id_table[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SOLID_YEAR, USB_DEVICE_ID_COUGAR_500K_GAMING_KEYBOARD) }, { HID_USB_DEVICE(USB_VENDOR_ID_SOLID_YEAR, diff --git a/drivers/hid/hid-elan.c b/drivers/hid/hid-elan.c index 45c4f888b7c4..dae193749d44 100644 --- a/drivers/hid/hid-elan.c +++ b/drivers/hid/hid-elan.c @@ -188,6 +188,7 @@ static int elan_input_configured(struct hid_device *hdev, struct hid_input *hi) ret = input_mt_init_slots(input, ELAN_MAX_FINGERS, INPUT_MT_POINTER); if (ret) { hid_err(hdev, "Failed to init elan MT slots: %d\n", ret); + input_free_device(input); return ret; } @@ -198,6 +199,7 @@ static int elan_input_configured(struct hid_device *hdev, struct hid_input *hi) if (ret) { hid_err(hdev, "Failed to register elan input device: %d\n", ret); + input_mt_destroy_slots(input); input_free_device(input); return ret; } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 6221888aae99..74fc1df6e3c2 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -728,6 +728,9 @@ #define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067 #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D 0x608d +#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019 0x6019 +#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_602E 0x602e +#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6093 0x6093 #define USB_VENDOR_ID_LG 0x1fd2 #define USB_DEVICE_ID_LG_MULTITOUCH 0x0064 @@ -847,6 +850,7 @@ #define USB_DEVICE_ID_MS_POWER_COVER 0x07da #define USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER 0x02fd #define USB_DEVICE_ID_MS_PIXART_MOUSE 0x00cb +#define USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS 0x02e0 #define USB_VENDOR_ID_MOJO 0x8282 #define USB_DEVICE_ID_RETRO_ADAPTER 0x3201 @@ -1012,6 +1016,8 @@ #define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa #define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0 #define USB_DEVICE_ID_SAITEK_X52 0x075c +#define USB_DEVICE_ID_SAITEK_X52_2 0x0255 +#define USB_DEVICE_ID_SAITEK_X52_PRO 0x0762 #define USB_VENDOR_ID_SAMSUNG 0x0419 #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index b8eabf206e74..88e19996427e 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1132,6 +1132,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel } mapped: + /* Mapping failed, bail out */ + if (!bit) + return; + if (device->driver->input_mapped && device->driver->input_mapped(device, hidinput, field, usage, &bit, &max) < 0) { diff --git a/drivers/hid/hid-lg-g15.c b/drivers/hid/hid-lg-g15.c index ef0cbcd7540d..fcaf8466e627 100644 --- a/drivers/hid/hid-lg-g15.c +++ b/drivers/hid/hid-lg-g15.c @@ -680,7 +680,7 @@ static int lg_g15_register_led(struct lg_g15_data *g15, int i) * but it does have a separate power-on (reset) value. */ g15->leds[i].cdev.name = "g15::power_on_backlight_val"; - /* fall through */ + fallthrough; case LG_G15_KBD_BRIGHTNESS: g15->leds[i].cdev.brightness_set_blocking = lg_g510_kbd_led_set; diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index a78c13cc9f47..38ee25a813b9 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -844,7 +844,7 @@ static void logi_dj_recv_queue_notification(struct dj_receiver_dev *djrcv_dev, workitem.type = WORKITEM_TYPE_EMPTY; break; } - /* fall-through */ + fallthrough; case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED: workitem.quad_id_msb = dj_report->report_params[DEVICE_PAIRED_PARAM_EQUAD_ID_MSB]; diff --git a/drivers/hid/hid-macally.c b/drivers/hid/hid-macally.c index 9a4fc7dffb14..aea46e522008 100644 --- a/drivers/hid/hid-macally.c +++ b/drivers/hid/hid-macally.c @@ -29,7 +29,7 @@ static __u8 *macally_report_fixup(struct hid_device *hdev, __u8 *rdesc, return rdesc; } -static struct hid_device_id macally_id_table[] = { +static const struct hid_device_id macally_id_table[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SOLID_YEAR, USB_DEVICE_ID_MACALLY_IKEY_KEYBOARD) }, { } diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c index 2d8b589201a4..071fd093a5f4 100644 --- a/drivers/hid/hid-microsoft.c +++ b/drivers/hid/hid-microsoft.c @@ -163,16 +163,13 @@ static int ms_surface_dial_quirk(struct hid_input *hi, struct hid_field *field, { switch (usage->hid & HID_USAGE_PAGE) { case 0xff070000: - /* fall-through */ case HID_UP_DIGITIZER: /* ignore those axis */ return -1; case HID_UP_GENDESK: switch (usage->hid) { case HID_GD_X: - /* fall-through */ case HID_GD_Y: - /* fall-through */ case HID_GD_RFKILL_BTN: /* ignore those axis */ return -1; @@ -451,6 +448,8 @@ static const struct hid_device_id ms_devices[] = { .driver_data = MS_SURFACE_DIAL }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER), .driver_data = MS_QUIRK_FF }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS), + .driver_data = MS_QUIRK_FF }, { } }; MODULE_DEVICE_TABLE(hid, ms_devices); diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 3f94b4954225..e3152155c4b8 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -856,6 +856,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, code = BTN_0 + ((usage->hid - 1) & HID_USAGE); hid_map_usage(hi, usage, bit, max, EV_KEY, code); + if (!*bit) + return -1; input_set_capability(hi->input, EV_KEY, code); return 1; diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index c242150d35a3..7a2be0205dfd 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -105,6 +105,9 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_PIXART_USB_OPTICAL_MOUSE_ID2), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_602E), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6093), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C007), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS), HID_QUIRK_NOGET }, @@ -147,6 +150,8 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52_2), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52_PRO), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB), HID_QUIRK_NOGET }, diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c index 8cffa84c9650..7f41213d5ae3 100644 --- a/drivers/hid/hid-rmi.c +++ b/drivers/hid/hid-rmi.c @@ -428,7 +428,6 @@ static void rmi_report(struct hid_device *hid, struct hid_report *report) switch (report->id) { case RMI_READ_DATA_REPORT_ID: - /* fall-through */ case RMI_ATTN_REPORT_ID: return; } diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c index 1a6e600197d0..2ff4c8e366ff 100644 --- a/drivers/hid/hid-roccat-kone.c +++ b/drivers/hid/hid-roccat-kone.c @@ -780,7 +780,7 @@ static void kone_keep_values_up_to_date(struct kone_device *kone, case kone_mouse_event_switch_profile: kone->actual_dpi = kone->profiles[event->value - 1]. startup_dpi; - /* fall through */ + fallthrough; case kone_mouse_event_osd_profile: kone->actual_profile = event->value; break; diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 78a364ae2f68..7d20d1fcf8d2 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -974,7 +974,7 @@ int uclogic_params_init(struct uclogic_params *params, } break; } - /* FALL THROUGH */ + fallthrough; case VID_PID(USB_VENDOR_ID_HUION, USB_DEVICE_ID_HUION_TABLET): case VID_PID(USB_VENDOR_ID_HUION, diff --git a/drivers/hid/hid-wiimote-core.c b/drivers/hid/hid-wiimote-core.c index 679e142fc850..e484c3618dec 100644 --- a/drivers/hid/hid-wiimote-core.c +++ b/drivers/hid/hid-wiimote-core.c @@ -1672,7 +1672,6 @@ static ssize_t wiimote_ext_show(struct device *dev, case WIIMOTE_EXT_GUITAR: return sprintf(buf, "guitar\n"); case WIIMOTE_EXT_UNKNOWN: - /* fallthrough */ default: return sprintf(buf, "unknown\n"); } @@ -1722,7 +1721,6 @@ static ssize_t wiimote_dev_show(struct device *dev, case WIIMOTE_DEV_PENDING: return sprintf(buf, "pending\n"); case WIIMOTE_DEV_UNKNOWN: - /* fallthrough */ default: return sprintf(buf, "unknown\n"); } diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 294c84e136d7..dbd04492825d 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -420,6 +420,19 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state) dev_err(&client->dev, "failed to change power setting.\n"); set_pwr_exit: + + /* + * The HID over I2C specification states that if a DEVICE needs time + * after the PWR_ON request, it should utilise CLOCK stretching. + * However, it has been observered that the Windows driver provides a + * 1ms sleep between the PWR_ON and RESET requests. + * According to Goodix Windows even waits 60 ms after (other?) + * PWR_ON requests. Testing has confirmed that several devices + * will not work properly without a delay after a PWR_ON request. + */ + if (!ret && power_state == I2C_HID_PWR_ON) + msleep(60); + return ret; } @@ -441,15 +454,6 @@ static int i2c_hid_hwreset(struct i2c_client *client) if (ret) goto out_unlock; - /* - * The HID over I2C specification states that if a DEVICE needs time - * after the PWR_ON request, it should utilise CLOCK stretching. - * However, it has been observered that the Windows driver provides a - * 1ms sleep between the PWR_ON and RESET requests and that some devices - * rely on this. - */ - usleep_range(1000, 5000); - i2c_hid_dbg(ihid, "resetting...\n"); ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0); diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 492dd641a25d..17a29ee0ac6c 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -26,7 +26,6 @@ #include <linux/wait.h> #include <linux/workqueue.h> #include <linux/string.h> -#include <linux/timekeeping.h> #include <linux/usb.h> @@ -96,18 +95,6 @@ static int hid_start_in(struct hid_device *hid) set_bit(HID_NO_BANDWIDTH, &usbhid->iofl); } else { clear_bit(HID_NO_BANDWIDTH, &usbhid->iofl); - - if (test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) { - /* - * In case events are generated while nobody was - * listening, some are released when the device - * is re-opened. Wait 50 msec for the queue to - * empty before allowing events to go through - * hid. - */ - usbhid->input_start_time = - ktime_add_ms(ktime_get_coarse(), 50); - } } } spin_unlock_irqrestore(&usbhid->lock, flags); @@ -293,23 +280,20 @@ static void hid_irq_in(struct urb *urb) if (!test_bit(HID_OPENED, &usbhid->iofl)) break; usbhid_mark_busy(usbhid); - if (test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) { - if (ktime_before(ktime_get_coarse(), - usbhid->input_start_time)) - break; - clear_bit(HID_RESUME_RUNNING, &usbhid->iofl); + if (!test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) { + hid_input_report(urb->context, HID_INPUT_REPORT, + urb->transfer_buffer, + urb->actual_length, 1); + /* + * autosuspend refused while keys are pressed + * because most keyboards don't wake up when + * a key is released + */ + if (hid_check_keys_pressed(hid)) + set_bit(HID_KEYS_PRESSED, &usbhid->iofl); + else + clear_bit(HID_KEYS_PRESSED, &usbhid->iofl); } - hid_input_report(urb->context, HID_INPUT_REPORT, - urb->transfer_buffer, urb->actual_length, 1); - /* - * autosuspend refused while keys are pressed - * because most keyboards don't wake up when - * a key is released - */ - if (hid_check_keys_pressed(hid)) - set_bit(HID_KEYS_PRESSED, &usbhid->iofl); - else - clear_bit(HID_KEYS_PRESSED, &usbhid->iofl); break; case -EPIPE: /* stall */ usbhid_mark_busy(usbhid); @@ -736,6 +720,17 @@ static int usbhid_open(struct hid_device *hid) usb_autopm_put_interface(usbhid->intf); + /* + * In case events are generated while nobody was listening, + * some are released when the device is re-opened. + * Wait 50 msec for the queue to empty before allowing events + * to go through hid. + */ + if (res == 0) + msleep(50); + + clear_bit(HID_RESUME_RUNNING, &usbhid->iofl); + Done: mutex_unlock(&usbhid->mutex); return res; diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 4140dea693e9..45e0b1c75cb1 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -519,12 +519,16 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, switch (cmd) { case HIDIOCGUSAGE: + if (uref->usage_index >= field->report_count) + goto inval; uref->value = field->value[uref->usage_index]; if (copy_to_user(user_arg, uref, sizeof(*uref))) goto fault; goto goodreturn; case HIDIOCSUSAGE: + if (uref->usage_index >= field->report_count) + goto inval; field->value[uref->usage_index] = uref->value; goto goodreturn; @@ -781,7 +785,6 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; case HIDIOCGUCODE: - /* fall through */ case HIDIOCGUSAGE: case HIDIOCSUSAGE: case HIDIOCGUSAGES: diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h index c6ad684d099a..75fe85d3d27a 100644 --- a/drivers/hid/usbhid/usbhid.h +++ b/drivers/hid/usbhid/usbhid.h @@ -13,7 +13,6 @@ #include <linux/types.h> #include <linux/slab.h> -#include <linux/ktime.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/timer.h> @@ -84,7 +83,6 @@ struct usbhid_device { struct mutex mutex; /* start/stop/open/close */ spinlock_t lock; /* fifo spinlock */ unsigned long iofl; /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */ - ktime_t input_start_time; /* When to start handling input */ struct timer_list io_retry; /* Retry timer */ unsigned long stop_retry; /* Time to give up, in jiffies */ unsigned int retry_delay; /* Delay length in ms */ diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 1c96809b51c9..83dfec327c42 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -341,7 +341,7 @@ static int wacom_graphire_irq(struct wacom_wac *wacom) case 2: /* Mouse with wheel */ input_report_key(input, BTN_MIDDLE, data[1] & 0x04); - /* fall through */ + fallthrough; case 3: /* Mouse without wheel */ wacom->tool[0] = BTN_TOOL_MOUSE; @@ -1201,7 +1201,7 @@ static int wacom_intuos_bt_irq(struct wacom_wac *wacom, size_t len) case 0x04: wacom_intuos_bt_process_data(wacom, data + i); i += 10; - /* fall through */ + fallthrough; case 0x03: wacom_intuos_bt_process_data(wacom, data + i); i += 10; @@ -2148,7 +2148,7 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field for (i = 0; i < wacom->led.count; i++) wacom_update_led(wacom, features->numbered_buttons, value, i); - /* fall through*/ + fallthrough; default: do_report = true; break; @@ -3602,14 +3602,14 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev, switch (features->type) { case GRAPHIRE_BT: __clear_bit(ABS_MISC, input_dev->absbit); - /* fall through */ + fallthrough; case WACOM_MO: case WACOM_G4: input_set_abs_params(input_dev, ABS_DISTANCE, 0, features->distance_max, features->distance_fuzz, 0); - /* fall through */ + fallthrough; case GRAPHIRE: input_set_capability(input_dev, EV_REL, REL_WHEEL); @@ -3649,7 +3649,7 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev, case INTUOS4S: input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0); input_abs_set_res(input_dev, ABS_Z, 287); - /* fall through */ + fallthrough; case INTUOS: wacom_setup_intuos(wacom_wac); @@ -3682,7 +3682,7 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev, case TABLETPC: case TABLETPCE: __clear_bit(ABS_MISC, input_dev->absbit); - /* fall through */ + fallthrough; case DTUS: case DTUSX: @@ -3696,7 +3696,7 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev, case PTU: __set_bit(BTN_STYLUS2, input_dev->keybit); - /* fall through */ + fallthrough; case PENPARTNER: __set_bit(BTN_TOOL_PEN, input_dev->keybit); @@ -3799,7 +3799,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev, input_abs_set_res(input_dev, ABS_MT_POSITION_X, 40); input_abs_set_res(input_dev, ABS_MT_POSITION_Y, 40); - /* fall through */ + fallthrough; case INTUOS5: case INTUOS5L: @@ -3817,7 +3817,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev, input_set_abs_params(input_dev, ABS_MT_WIDTH_MAJOR, 0, features->x_max, 0, 0); input_set_abs_params(input_dev, ABS_MT_WIDTH_MINOR, 0, features->y_max, 0, 0); input_set_abs_params(input_dev, ABS_MT_ORIENTATION, 0, 1, 0, 0); - /* fall through */ + fallthrough; case WACOM_27QHDT: if (wacom_wac->shared->touch->product == 0x32C || @@ -3826,14 +3826,14 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev, __set_bit(SW_MUTE_DEVICE, input_dev->swbit); wacom_wac->shared->has_mute_touch_switch = true; } - /* fall through */ + fallthrough; case MTSCREEN: case MTTPC: case MTTPC_B: case TABLETPC2FG: input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_DIRECT); - /*fall through */ + fallthrough; case TABLETPC: case TABLETPCE: @@ -3843,7 +3843,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev, case INTUOSHT2: input_dev->evbit[0] |= BIT_MASK(EV_SW); __set_bit(SW_MUTE_DEVICE, input_dev->swbit); - /* fall through */ + fallthrough; case BAMBOO_PT: case BAMBOO_TOUCH: @@ -4099,7 +4099,7 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev, __set_bit(KEY_BUTTONCONFIG, input_dev->keybit); __set_bit(KEY_INFO, input_dev->keybit); - /* fall through */ + fallthrough; case WACOM_21UX2: case WACOM_BEE: @@ -4115,7 +4115,7 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev, case INTUOS3: case INTUOS3L: input_set_abs_params(input_dev, ABS_RY, 0, 4096, 0, 0); - /* fall through */ + fallthrough; case INTUOS3S: input_set_abs_params(input_dev, ABS_RX, 0, 4096, 0, 0); @@ -4139,7 +4139,7 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev, * ID_INPUT_TABLET to be set. */ __set_bit(BTN_STYLUS, input_dev->keybit); - /* fall through */ + fallthrough; case INTUOS4: case INTUOS4L: diff --git a/drivers/hsi/clients/ssi_protocol.c b/drivers/hsi/clients/ssi_protocol.c index 365b5d5967ac..96d0eccca3aa 100644 --- a/drivers/hsi/clients/ssi_protocol.c +++ b/drivers/hsi/clients/ssi_protocol.c @@ -291,7 +291,7 @@ static void ssip_set_rxstate(struct ssi_protocol *ssi, unsigned int state) /* CMT speech workaround */ if (atomic_read(&ssi->tx_usecnt)) break; - /* Else, fall through */ + fallthrough; case RECEIVING: mod_timer(&ssi->keep_alive, jiffies + msecs_to_jiffies(SSIP_KATOUT)); @@ -466,7 +466,7 @@ static void ssip_keep_alive(struct timer_list *t) case SEND_READY: if (atomic_read(&ssi->tx_usecnt) == 0) break; - /* Fall through */ + fallthrough; /* * Workaround for cmt-speech in that case * we relay on audio timers. @@ -668,7 +668,7 @@ static void ssip_rx_bootinforeq(struct hsi_client *cl, u32 cmd) case ACTIVE: dev_err(&cl->device, "Boot info req on active state\n"); ssip_error(cl); - /* Fall through */ + fallthrough; case INIT: case HANDSHAKE: spin_lock_bh(&ssi->lock); diff --git a/drivers/hsi/controllers/omap_ssi_core.c b/drivers/hsi/controllers/omap_ssi_core.c index 4bc4a201f0f6..fa69b94debd9 100644 --- a/drivers/hsi/controllers/omap_ssi_core.c +++ b/drivers/hsi/controllers/omap_ssi_core.c @@ -296,7 +296,7 @@ static int ssi_clk_event(struct notifier_block *nb, unsigned long event, break; case ABORT_RATE_CHANGE: dev_dbg(&ssi->device, "abort rate change\n"); - /* Fall through */ + fallthrough; case POST_RATE_CHANGE: dev_dbg(&ssi->device, "post rate change (%lu -> %lu)\n", clk_data->old_rate, clk_data->new_rate); diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index e74b144b8f3d..754d35a25a1c 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -354,7 +354,7 @@ static void process_ib_ipinfo(void *in_msg, void *out_msg, int op) out->body.kvp_ip_val.dhcp_enabled = in->kvp_ip_val.dhcp_enabled; - /* fallthrough */ + fallthrough; case KVP_OP_GET_IP_INFO: utf16s_to_utf8s((wchar_t *)in->kvp_ip_val.adapter_id, diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 92ee0fe4c919..a4e8d96513c2 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -282,26 +282,52 @@ static struct { spinlock_t lock; } host_ts; -static struct timespec64 hv_get_adj_host_time(void) +static inline u64 reftime_to_ns(u64 reftime) { - struct timespec64 ts; - u64 newtime, reftime; + return (reftime - WLTIMEDELTA) * 100; +} + +/* + * Hard coded threshold for host timesync delay: 600 seconds + */ +static const u64 HOST_TIMESYNC_DELAY_THRESH = 600 * (u64)NSEC_PER_SEC; + +static int hv_get_adj_host_time(struct timespec64 *ts) +{ + u64 newtime, reftime, timediff_adj; unsigned long flags; + int ret = 0; spin_lock_irqsave(&host_ts.lock, flags); reftime = hv_read_reference_counter(); - newtime = host_ts.host_time + (reftime - host_ts.ref_time); - ts = ns_to_timespec64((newtime - WLTIMEDELTA) * 100); + + /* + * We need to let the caller know that last update from host + * is older than the max allowable threshold. clock_gettime() + * and PTP ioctl do not have a documented error that we could + * return for this specific case. Use ESTALE to report this. + */ + timediff_adj = reftime - host_ts.ref_time; + if (timediff_adj * 100 > HOST_TIMESYNC_DELAY_THRESH) { + pr_warn_once("TIMESYNC IC: Stale time stamp, %llu nsecs old\n", + (timediff_adj * 100)); + ret = -ESTALE; + } + + newtime = host_ts.host_time + timediff_adj; + *ts = ns_to_timespec64(reftime_to_ns(newtime)); spin_unlock_irqrestore(&host_ts.lock, flags); - return ts; + return ret; } static void hv_set_host_time(struct work_struct *work) { - struct timespec64 ts = hv_get_adj_host_time(); - do_settimeofday64(&ts); + struct timespec64 ts; + + if (!hv_get_adj_host_time(&ts)) + do_settimeofday64(&ts); } /* @@ -361,10 +387,23 @@ static void timesync_onchannelcallback(void *context) struct ictimesync_ref_data *refdata; u8 *time_txf_buf = util_timesynch.recv_buffer; - vmbus_recvpacket(channel, time_txf_buf, - HV_HYP_PAGE_SIZE, &recvlen, &requestid); + /* + * Drain the ring buffer and use the last packet to update + * host_ts + */ + while (1) { + int ret = vmbus_recvpacket(channel, time_txf_buf, + HV_HYP_PAGE_SIZE, &recvlen, + &requestid); + if (ret) { + pr_warn_once("TimeSync IC pkt recv failed (Err: %d)\n", + ret); + break; + } + + if (!recvlen) + break; - if (recvlen > 0) { icmsghdrp = (struct icmsg_hdr *)&time_txf_buf[ sizeof(struct vmbuspipe_hdr)]; @@ -622,9 +661,7 @@ static int hv_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) static int hv_ptp_gettime(struct ptp_clock_info *info, struct timespec64 *ts) { - *ts = hv_get_adj_host_time(); - - return 0; + return hv_get_adj_host_time(ts); } static struct ptp_clock_info ptp_hyperv_info = { diff --git a/drivers/hwmon/adt7462.c b/drivers/hwmon/adt7462.c index 319a0519ebdb..208813158bb4 100644 --- a/drivers/hwmon/adt7462.c +++ b/drivers/hwmon/adt7462.c @@ -435,7 +435,7 @@ static const char *voltage_label(struct adt7462_data *data, int which) case 3: return "+1.5V"; } - /* fall through */ + fallthrough; case 2: if (!(data->pin_cfg[1] & ADT7462_PIN22_INPUT)) return "+12V3"; @@ -493,7 +493,7 @@ static const char *voltage_label(struct adt7462_data *data, int which) case 3: return "+1.5"; } - /* fall through */ + fallthrough; case 11: if (data->pin_cfg[3] >> ADT7462_PIN28_SHIFT == ADT7462_PIN28_VOLT && @@ -531,7 +531,7 @@ static int voltage_multiplier(struct adt7462_data *data, int which) case 3: return 7800; } - /* fall through */ + fallthrough; case 2: if (!(data->pin_cfg[1] & ADT7462_PIN22_INPUT)) return 62500; @@ -589,7 +589,7 @@ static int voltage_multiplier(struct adt7462_data *data, int which) case 3: return 7800; } - /* fall through */ + fallthrough; case 11: case 12: if (data->pin_cfg[3] >> ADT7462_PIN28_SHIFT == diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index 316618409315..a18887990f4a 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -753,15 +753,18 @@ static ssize_t applesmc_light_show(struct device *dev, } ret = applesmc_read_key(LIGHT_SENSOR_LEFT_KEY, buffer, data_length); + if (ret) + goto out; /* newer macbooks report a single 10-bit bigendian value */ if (data_length == 10) { left = be16_to_cpu(*(__be16 *)(buffer + 6)) >> 2; goto out; } left = buffer[2]; + + ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length); if (ret) goto out; - ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length); right = buffer[2]; out: @@ -810,12 +813,11 @@ static ssize_t applesmc_show_fan_speed(struct device *dev, to_index(attr)); ret = applesmc_read_key(newkey, buffer, 2); - speed = ((buffer[0] << 8 | buffer[1]) >> 2); - if (ret) return ret; - else - return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed); + + speed = ((buffer[0] << 8 | buffer[1]) >> 2); + return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed); } static ssize_t applesmc_store_fan_speed(struct device *dev, @@ -851,12 +853,11 @@ static ssize_t applesmc_show_fan_manual(struct device *dev, u8 buffer[2]; ret = applesmc_read_key(FANS_MANUAL, buffer, 2); - manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01; - if (ret) return ret; - else - return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual); + + manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01; + return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual); } static ssize_t applesmc_store_fan_manual(struct device *dev, @@ -872,10 +873,11 @@ static ssize_t applesmc_store_fan_manual(struct device *dev, return -EINVAL; ret = applesmc_read_key(FANS_MANUAL, buffer, 2); - val = (buffer[0] << 8 | buffer[1]); if (ret) goto out; + val = (buffer[0] << 8 | buffer[1]); + if (input) val = val | (0x01 << to_index(attr)); else @@ -951,13 +953,12 @@ static ssize_t applesmc_key_count_show(struct device *dev, u32 count; ret = applesmc_read_key(KEY_COUNT_KEY, buffer, 4); - count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) + - ((u32)buffer[2]<<8) + buffer[3]; - if (ret) return ret; - else - return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count); + + count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) + + ((u32)buffer[2]<<8) + buffer[3]; + return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count); } static ssize_t applesmc_key_at_index_read_show(struct device *dev, diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c index cf0962f7a020..e9c0bbc2caa9 100644 --- a/drivers/hwmon/emc1403.c +++ b/drivers/hwmon/emc1403.c @@ -406,10 +406,10 @@ static int emc1403_probe(struct i2c_client *client, switch (id->driver_data) { case emc1404: data->groups[2] = &emc1404_group; - /* fall through */ + fallthrough; case emc1403: data->groups[1] = &emc1403_group; - /* fall through */ + fallthrough; case emc1402: data->groups[0] = &emc1402_group; } diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c index d09deb409de7..4dec793fd07d 100644 --- a/drivers/hwmon/f71882fg.c +++ b/drivers/hwmon/f71882fg.c @@ -1285,7 +1285,7 @@ static struct f71882fg_data *f71882fg_update_device(struct device *dev) data->pwm_auto_point_pwm[nr][0] = f71882fg_read8(data, F71882FG_REG_POINT_PWM(nr, 0)); - /* Fall through */ + fallthrough; case f71862fg: data->pwm_auto_point_pwm[nr][1] = f71882fg_read8(data, @@ -2442,7 +2442,7 @@ static int f71882fg_probe(struct platform_device *pdev) case f71869a: /* These always have signed auto point temps */ data->auto_point_temp_signed = 1; - /* Fall through - to select correct fan/pwm reg bank! */ + fallthrough; /* to select correct fan/pwm reg bank! */ case f71889fg: case f71889ed: case f71889a: diff --git a/drivers/hwmon/gsc-hwmon.c b/drivers/hwmon/gsc-hwmon.c index 3dfe2ca2f8c8..c6d4567f3952 100644 --- a/drivers/hwmon/gsc-hwmon.c +++ b/drivers/hwmon/gsc-hwmon.c @@ -172,6 +172,7 @@ gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, case mode_temperature: if (tmp > 0x8000) tmp -= 0xffff; + tmp *= 100; /* convert to millidegrees celsius */ break; case mode_voltage_raw: tmp = clamp_val(tmp, 0, BIT(GSC_HWMON_RESOLUTION)); diff --git a/drivers/hwmon/hwmon-vid.c b/drivers/hwmon/hwmon-vid.c index eb72e390844e..6d1175a51832 100644 --- a/drivers/hwmon/hwmon-vid.c +++ b/drivers/hwmon/hwmon-vid.c @@ -96,7 +96,7 @@ int vid_from_reg(int val, u8 vrm) val &= 0x1f; if (val == 0x1f) return 0; - /* fall through */ + fallthrough; case 25: /* AMD NPT 0Fh */ val &= 0x3f; return (val < 32) ? 1550 - 25 * val @@ -122,7 +122,7 @@ int vid_from_reg(int val, u8 vrm) case 84: /* VRM 8.4 */ val &= 0x0f; - /* fall through */ + fallthrough; case 82: /* VRM 8.2 */ val &= 0x1f; return val == 0x1f ? 0 : diff --git a/drivers/hwmon/ina3221.c b/drivers/hwmon/ina3221.c index 7fc5b065ad8b..81e155692aba 100644 --- a/drivers/hwmon/ina3221.c +++ b/drivers/hwmon/ina3221.c @@ -352,7 +352,7 @@ static int ina3221_read_curr(struct device *dev, u32 attr, if (ret) return ret; - /* fall through */ + fallthrough; case hwmon_curr_crit: case hwmon_curr_max: if (!resistance_uo) diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 750b08713dee..5bd15622a85f 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -2669,7 +2669,7 @@ static void pwm_update_registers(struct nct6775_data *data, int nr) case thermal_cruise: nct6775_write_value(data, data->REG_TARGET[nr], data->target_temp[nr]); - /* fall through */ + fallthrough; default: reg = nct6775_read_value(data, data->REG_FAN_MODE[nr]); reg = (reg & ~data->tolerance_mask) | diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c index b0425694f702..242ff8bee78d 100644 --- a/drivers/hwmon/nct7904.c +++ b/drivers/hwmon/nct7904.c @@ -231,7 +231,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel, if (ret < 0) return ret; cnt = ((ret & 0xff00) >> 3) | (ret & 0x1f); - if (cnt == 0x1fff) + if (cnt == 0 || cnt == 0x1fff) rpm = 0; else rpm = 1350000 / cnt; @@ -243,7 +243,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel, if (ret < 0) return ret; cnt = ((ret & 0xff00) >> 3) | (ret & 0x1f); - if (cnt == 0x1fff) + if (cnt == 0 || cnt == 0x1fff) rpm = 0; else rpm = 1350000 / cnt; diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index 30e18eb60da7..a71777990d49 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -752,7 +752,7 @@ static int occ_setup_sensor_attrs(struct occ *occ) switch (sensors->freq.version) { case 2: show_freq = occ_show_freq_2; - /* fall through */ + fallthrough; case 1: num_attrs += (sensors->freq.num_sensors * 2); break; @@ -763,7 +763,7 @@ static int occ_setup_sensor_attrs(struct occ *occ) switch (sensors->power.version) { case 2: show_power = occ_show_power_2; - /* fall through */ + fallthrough; case 1: num_attrs += (sensors->power.num_sensors * 4); break; @@ -781,7 +781,7 @@ static int occ_setup_sensor_attrs(struct occ *occ) break; case 3: show_caps = occ_show_caps_3; - /* fall through */ + fallthrough; case 2: num_attrs += (sensors->caps.num_sensors * 8); break; diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c index 0c622711ef7e..58aa95a3c010 100644 --- a/drivers/hwmon/pmbus/isl68137.c +++ b/drivers/hwmon/pmbus/isl68137.c @@ -67,6 +67,7 @@ enum variants { raa_dmpvr1_2rail, raa_dmpvr2_1rail, raa_dmpvr2_2rail, + raa_dmpvr2_2rail_nontc, raa_dmpvr2_3rail, raa_dmpvr2_hv, }; @@ -241,6 +242,10 @@ static int isl68137_probe(struct i2c_client *client, info->pages = 1; info->read_word_data = raa_dmpvr2_read_word_data; break; + case raa_dmpvr2_2rail_nontc: + info->func[0] &= ~PMBUS_HAVE_TEMP; + info->func[1] &= ~PMBUS_HAVE_TEMP; + fallthrough; case raa_dmpvr2_2rail: info->pages = 2; info->read_word_data = raa_dmpvr2_read_word_data; @@ -304,7 +309,7 @@ static const struct i2c_device_id raa_dmpvr_id[] = { {"raa228000", raa_dmpvr2_hv}, {"raa228004", raa_dmpvr2_hv}, {"raa228006", raa_dmpvr2_hv}, - {"raa228228", raa_dmpvr2_2rail}, + {"raa228228", raa_dmpvr2_2rail_nontc}, {"raa229001", raa_dmpvr2_2rail}, {"raa229004", raa_dmpvr2_2rail}, {} diff --git a/drivers/hwmon/w83627hf.c b/drivers/hwmon/w83627hf.c index e1d10a6b7f7c..a07b97400cba 100644 --- a/drivers/hwmon/w83627hf.c +++ b/drivers/hwmon/w83627hf.c @@ -1213,7 +1213,7 @@ temp_type_store(struct device *dev, struct device_attribute *devattr, case W83781D_DEFAULT_BETA: dev_warn(dev, "Sensor type %d is deprecated, please use 4 " "instead\n", W83781D_DEFAULT_BETA); - /* fall through */ + fallthrough; case 4: /* thermistor */ tmp = w83627hf_read_value(data, W83781D_REG_SCFG1); w83627hf_write_value(data, W83781D_REG_SCFG1, diff --git a/drivers/hwmon/w83781d.c b/drivers/hwmon/w83781d.c index 015f1ea31966..d833a4f16c47 100644 --- a/drivers/hwmon/w83781d.c +++ b/drivers/hwmon/w83781d.c @@ -814,7 +814,7 @@ store_sensor(struct device *dev, struct device_attribute *da, dev_warn(dev, "Sensor type %d is deprecated, please use 4 instead\n", W83781D_DEFAULT_BETA); - /* fall through */ + fallthrough; case 4: /* thermistor */ tmp = w83781d_read_value(data, W83781D_REG_SCFG1); w83781d_write_value(data, W83781D_REG_SCFG1, diff --git a/drivers/hwmon/w83795.c b/drivers/hwmon/w83795.c index 44f68b965aec..6d52b530b429 100644 --- a/drivers/hwmon/w83795.c +++ b/drivers/hwmon/w83795.c @@ -2127,7 +2127,7 @@ static void w83795_apply_temp_config(struct w83795_data *data, u8 config, if (temp_chan >= 4) break; data->temp_mode |= 1 << temp_chan; - /* fall through */ + fallthrough; case 0x3: /* Thermistor */ data->has_temp |= 1 << temp_chan; break; diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c index 96544b348c27..7e642fb3ed15 100644 --- a/drivers/hwtracing/coresight/coresight-cpu-debug.c +++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c @@ -346,10 +346,10 @@ static void debug_init_arch_data(void *info) switch (mode) { case EDDEVID_IMPL_FULL: drvdata->edvidsr_present = true; - /* Fall through */ + fallthrough; case EDDEVID_IMPL_EDPCSR_EDCIDSR: drvdata->edcidsr_present = true; - /* Fall through */ + fallthrough; case EDDEVID_IMPL_EDPCSR: /* * In ARM DDI 0487A.k, the EDDEVID1.PCSROffset is used to diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c index 6d7d2169bfb2..96425e818fc2 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ b/drivers/hwtracing/coresight/coresight-etm4x.c @@ -1382,7 +1382,6 @@ static int etm4_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, return NOTIFY_BAD; break; case CPU_PM_EXIT: - /* fallthrough */ case CPU_PM_ENTER_FAILED: if (drvdata->state_needs_restore) etm4_cpu_restore(drvdata); diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c index 7040d583bed9..9ca3aaafcfbc 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ b/drivers/hwtracing/coresight/coresight-tmc.c @@ -84,9 +84,7 @@ u32 tmc_get_memwidth_mask(struct tmc_drvdata *drvdata) */ switch (drvdata->memwidth) { case TMC_MEM_INTF_WIDTH_32BITS: - /* fallthrough */ case TMC_MEM_INTF_WIDTH_64BITS: - /* fallthrough */ case TMC_MEM_INTF_WIDTH_128BITS: mask = GENMASK(31, 4); break; diff --git a/drivers/hwtracing/intel_th/sth.c b/drivers/hwtracing/intel_th/sth.c index a1529f571491..9ca8c4e045f8 100644 --- a/drivers/hwtracing/intel_th/sth.c +++ b/drivers/hwtracing/intel_th/sth.c @@ -84,11 +84,11 @@ static ssize_t notrace sth_stm_packet(struct stm_data *stm_data, /* Global packets (GERR, XSYNC, TRIG) are sent with register writes */ case STP_PACKET_GERR: reg += 4; - /* fall through */ + fallthrough; case STP_PACKET_XSYNC: reg += 8; - /* fall through */ + fallthrough; case STP_PACKET_TRIG: if (flags & STP_PACKET_TIMESTAMPED) diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index 688e92818821..d8295b1c379d 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -720,7 +720,7 @@ static int bcm_iproc_i2c_xfer_internal(struct bcm_iproc_i2c_dev *iproc_i2c, /* mark the last byte */ if (!process_call && (i == msg->len - 1)) - val |= 1 << M_TX_WR_STATUS_SHIFT; + val |= BIT(M_TX_WR_STATUS_SHIFT); iproc_i2c_wr_reg(iproc_i2c, M_TX_OFFSET, val); } @@ -738,7 +738,7 @@ static int bcm_iproc_i2c_xfer_internal(struct bcm_iproc_i2c_dev *iproc_i2c, */ addr = i2c_8bit_addr_from_msg(msg); /* mark it the last byte out */ - val = addr | (1 << M_TX_WR_STATUS_SHIFT); + val = addr | BIT(M_TX_WR_STATUS_SHIFT); iproc_i2c_wr_reg(iproc_i2c, M_TX_OFFSET, val); } diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 175c590b93b7..12ac4212aded 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1425,7 +1425,6 @@ omap_i2c_probe(struct platform_device *pdev) major = OMAP_I2C_REV_SCHEME_0_MAJOR(omap->rev); break; case OMAP_I2C_SCHEME_1: - /* FALLTHROUGH */ default: omap->regs = (u8 *)reg_map_ip_v2; rev = (rev << 16) | diff --git a/drivers/i2c/busses/i2c-opal.c b/drivers/i2c/busses/i2c-opal.c index 1c4c9bb06a0b..6eb0f50c5d28 100644 --- a/drivers/i2c/busses/i2c-opal.c +++ b/drivers/i2c/busses/i2c-opal.c @@ -125,7 +125,7 @@ static int i2c_opal_smbus_xfer(struct i2c_adapter *adap, u16 addr, case I2C_SMBUS_BYTE: req.buffer_ra = cpu_to_be64(__pa(&data->byte)); req.size = cpu_to_be32(1); - /* Fall through */ + fallthrough; case I2C_SMBUS_QUICK: req.type = (read_write == I2C_SMBUS_READ) ? OPAL_I2C_RAW_READ : OPAL_I2C_RAW_WRITE; diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 9e883474db8c..c7c543483b08 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -590,6 +590,7 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv) /* master sent stop */ if (ssr_filtered & SSR) { i2c_slave_event(priv->slave, I2C_SLAVE_STOP, &value); + rcar_i2c_write(priv, ICSCR, SIE | SDBS); /* clear our NACK */ rcar_i2c_write(priv, ICSIER, SAR); rcar_i2c_write(priv, ICSSR, ~SSR & 0xff); } diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 2ade99b105b9..e627d7b2790f 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -276,16 +276,6 @@ void i2c_acpi_register_devices(struct i2c_adapter *adap) dev_warn(&adap->dev, "failed to enumerate I2C slaves\n"); } -const struct acpi_device_id * -i2c_acpi_match_device(const struct acpi_device_id *matches, - struct i2c_client *client) -{ - if (!(client && matches)) - return NULL; - - return acpi_match_device(matches, &client->dev); -} - static const struct acpi_device_id i2c_acpi_force_400khz_device_ids[] = { /* * These Silead touchscreen controllers only work at 400KHz, for diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 34a9609f256d..5ec082e2039d 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -480,7 +480,7 @@ static int i2c_device_probe(struct device *dev) * or ACPI ID table is supplied for the probing device. */ if (!driver->id_table && - !i2c_acpi_match_device(dev->driver->acpi_match_table, client) && + !acpi_driver_match_device(dev, dev->driver) && !i2c_of_match_device(dev->driver->of_match_table, client)) { status = -ENODEV; goto put_sync_adapter; diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h index 94ff1693b391..8ce261167a2d 100644 --- a/drivers/i2c/i2c-core.h +++ b/drivers/i2c/i2c-core.h @@ -59,20 +59,11 @@ static inline int __i2c_check_suspended(struct i2c_adapter *adap) } #ifdef CONFIG_ACPI -const struct acpi_device_id * -i2c_acpi_match_device(const struct acpi_device_id *matches, - struct i2c_client *client); void i2c_acpi_register_devices(struct i2c_adapter *adap); int i2c_acpi_get_irq(struct i2c_client *client); #else /* CONFIG_ACPI */ static inline void i2c_acpi_register_devices(struct i2c_adapter *adap) { } -static inline const struct acpi_device_id * -i2c_acpi_match_device(const struct acpi_device_id *matches, - struct i2c_client *client) -{ - return NULL; -} static inline int i2c_acpi_get_irq(struct i2c_client *client) { diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 5c5306cd50ec..8513bd353c05 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -603,7 +603,7 @@ static int dw_i3c_master_bus_init(struct i3c_master_controller *m) ret = dw_i2c_clk_cfg(master); if (ret) return ret; - /* fall through */ + fallthrough; case I3C_BUS_MODE_PURE: ret = dw_i3c_clk_cfg(master); if (ret) diff --git a/drivers/ide/hpt366.c b/drivers/ide/hpt366.c index fd3b5da44619..50c9a41467c8 100644 --- a/drivers/ide/hpt366.c +++ b/drivers/ide/hpt366.c @@ -575,14 +575,14 @@ static u8 hpt3xx_udma_filter(ide_drive_t *drive) if (!HPT370_ALLOW_ATA100_5 || check_in_drive_list(drive, bad_ata100_5)) return ATA_UDMA4; - /* fall through */ + fallthrough; case HPT372 : case HPT372A: case HPT372N: case HPT374 : if (ata_id_is_sata(drive->id)) mask &= ~0x0e; - /* fall through */ + fallthrough; default: return mask; } @@ -602,7 +602,7 @@ static u8 hpt3xx_mdma_filter(ide_drive_t *drive) case HPT374 : if (ata_id_is_sata(drive->id)) return 0x00; - /* fall through */ + fallthrough; default: return 0x07; } diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 7f17f8303988..212bb2d8bf34 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -350,7 +350,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) */ if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT) break; - /* fall-through */ + fallthrough; case DATA_PROTECT: /* * No point in retrying after an illegal request or data @@ -750,7 +750,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) case REQ_OP_DRV_IN: case REQ_OP_DRV_OUT: expiry = ide_cd_expiry; - /*FALLTHRU*/ + fallthrough; default: timeout = ATAPI_WAIT_PC; break; diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index 1fe1f9d37a51..af7503b47dbe 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -428,7 +428,7 @@ static int ide_floppy_get_capacity(ide_drive_t *drive) * (maintains previous driver behaviour) */ break; - /* fall through */ + fallthrough; case CAPACITY_CURRENT: /* Normal Zip/LS-120 disks */ if (memcmp(cap_desc, &floppy->cap_desc, 8)) diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index e867129466b0..1ddc45a04418 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -143,7 +143,7 @@ static void ide_classify_atapi_dev(ide_drive_t *drive) } /* Early cdrom models used zero */ type = ide_cdrom; - /* fall through */ + fallthrough; case ide_cdrom: drive->dev_flags |= IDE_DFLAG_REMOVABLE; #ifdef CONFIG_PPC diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c index a26f85ab58a9..d016cbe68cba 100644 --- a/drivers/ide/ide-taskfile.c +++ b/drivers/ide/ide-taskfile.c @@ -129,7 +129,7 @@ ide_startstop_t do_rw_taskfile(ide_drive_t *drive, struct ide_cmd *orig_cmd) return pre_task_out_intr(drive, cmd); } handler = task_pio_intr; - /* fall through */ + fallthrough; case ATA_PROT_NODATA: if (handler == NULL) handler = task_no_data_intr; @@ -141,7 +141,7 @@ ide_startstop_t do_rw_taskfile(ide_drive_t *drive, struct ide_cmd *orig_cmd) hwif->expiry = dma_ops->dma_timer_expiry; ide_execute_command(drive, cmd, ide_dma_intr, 2 * WAIT_CMD); dma_ops->dma_start(drive); - /* fall through */ + fallthrough; default: return ide_started; } @@ -579,10 +579,10 @@ int ide_taskfile_ioctl(ide_drive_t *drive, unsigned long arg) goto abort; } cmd.tf_flags |= IDE_TFLAG_MULTI_PIO; - /* fall through */ + fallthrough; case TASKFILE_OUT: cmd.protocol = ATA_PROT_PIO; - /* fall through */ + fallthrough; case TASKFILE_OUT_DMAQ: case TASKFILE_OUT_DMA: cmd.tf_flags |= IDE_TFLAG_WRITE; @@ -598,10 +598,10 @@ int ide_taskfile_ioctl(ide_drive_t *drive, unsigned long arg) goto abort; } cmd.tf_flags |= IDE_TFLAG_MULTI_PIO; - /* fall through */ + fallthrough; case TASKFILE_IN: cmd.protocol = ATA_PROT_PIO; - /* fall through */ + fallthrough; case TASKFILE_IN_DMAQ: case TASKFILE_IN_DMA: nsect = taskin / SECTOR_SIZE; diff --git a/drivers/ide/sis5513.c b/drivers/ide/sis5513.c index 024bc7ba49ee..1a700bef6c56 100644 --- a/drivers/ide/sis5513.c +++ b/drivers/ide/sis5513.c @@ -494,7 +494,7 @@ static int init_chipset_sis5513(struct pci_dev *dev) pci_read_config_byte(dev, 0x09, ®); if ((reg & 0x0f) != 0x00) pci_write_config_byte(dev, 0x09, reg&0xf0); - /* fall through */ + fallthrough; case ATA_16: /* force per drive recovery and active timings needed on ATA_33 and below chips */ diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 8e0fb1a5bdbd..9a810e4a7946 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -90,14 +90,6 @@ static unsigned int mwait_substates __initdata; #define CPUIDLE_FLAG_ALWAYS_ENABLE BIT(15) /* - * Set this flag for states where the HW flushes the TLB for us - * and so we don't need cross-calls to keep it consistent. - * If this flag is set, SW flushes the TLB, so even if the - * HW doesn't do the flushing, this flag is safe to use. - */ -#define CPUIDLE_FLAG_TLB_FLUSHED BIT(16) - -/* * MWAIT takes an 8-bit "hint" in EAX "suggesting" * the C-state (top nibble) and sub-state (bottom nibble) * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc. @@ -131,14 +123,6 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev, unsigned long eax = flg2MWAIT(state->flags); unsigned long ecx = 1; /* break on interrupt flag */ bool tick; - int cpu = smp_processor_id(); - - /* - * leave_mm() to avoid costly and often unnecessary wakeups - * for flushing the user TLB's associated with the active mm. - */ - if (state->flags & CPUIDLE_FLAG_TLB_FLUSHED) - leave_mm(cpu); if (!static_cpu_has(X86_FEATURE_ARAT)) { /* diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c index ba27f8673131..4e6e70250048 100644 --- a/drivers/iio/accel/mma8452.c +++ b/drivers/iio/accel/mma8452.c @@ -1580,7 +1580,7 @@ static int mma8452_probe(struct i2c_client *client, case FXLS8471_DEVICE_ID: if (ret == data->chip_info->chip_id) break; - /* fall through */ + fallthrough; default: ret = -ENODEV; goto disable_regulators; diff --git a/drivers/iio/adc/ab8500-gpadc.c b/drivers/iio/adc/ab8500-gpadc.c index 7fdc5d2d1d35..1bb987a4acba 100644 --- a/drivers/iio/adc/ab8500-gpadc.c +++ b/drivers/iio/adc/ab8500-gpadc.c @@ -484,7 +484,7 @@ static int ab8500_gpadc_read(struct ab8500_gpadc *gpadc, delay_max = 10000; /* large range optimises sleepmode */ break; } - /* Fall through */ + fallthrough; default: ctrl1 |= AB8500_GPADC_CTRL1_BUF_ENA; break; diff --git a/drivers/iio/adc/cpcap-adc.c b/drivers/iio/adc/cpcap-adc.c index 84a1733e5913..64c3cc382311 100644 --- a/drivers/iio/adc/cpcap-adc.c +++ b/drivers/iio/adc/cpcap-adc.c @@ -690,7 +690,7 @@ static void cpcap_adc_phase(struct cpcap_adc_request *req) break; case CPCAP_ADC_BATTI_PI17: index = req->bank_index; - /* fallthrough */ + fallthrough; default: req->result += conv_tbl[index].cal_offset; req->result += conv_tbl[index].align_offset; diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c index 5a29e32c295f..2ea9a5c4d846 100644 --- a/drivers/iio/chemical/sps30.c +++ b/drivers/iio/chemical/sps30.c @@ -118,7 +118,7 @@ static int sps30_do_cmd(struct sps30_state *state, u16 cmd, u8 *data, int size) case SPS30_READ_AUTO_CLEANING_PERIOD: buf[0] = SPS30_AUTO_CLEANING_PERIOD >> 8; buf[1] = (u8)(SPS30_AUTO_CLEANING_PERIOD & 0xff); - /* fall through */ + fallthrough; case SPS30_READ_DATA_READY_FLAG: case SPS30_READ_DATA: case SPS30_READ_SERIAL: diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index cc4875660a69..1fd75c02a7cd 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -220,7 +220,6 @@ static int ad5592r_set_channel_modes(struct ad5592r_state *st) break; case CH_MODE_UNUSED: - /* fall-through */ default: switch (st->channel_offstate[i]) { case CH_OFFSTATE_OUT_TRISTATE: @@ -237,7 +236,6 @@ static int ad5592r_set_channel_modes(struct ad5592r_state *st) break; case CH_OFFSTATE_PULLDOWN: - /* fall-through */ default: pulldown |= BIT(i); break; diff --git a/drivers/iio/dac/dpot-dac.c b/drivers/iio/dac/dpot-dac.c index b3835fb6b862..1a9609eda5c5 100644 --- a/drivers/iio/dac/dpot-dac.c +++ b/drivers/iio/dac/dpot-dac.c @@ -74,11 +74,12 @@ static int dpot_dac_read_raw(struct iio_dev *indio_dev, case IIO_VAL_INT: /* * Convert integer scale to fractional scale by - * setting the denominator (val2) to one, and... + * setting the denominator (val2) to one... */ *val2 = 1; ret = IIO_VAL_FRACTIONAL; - /* fall through */ + /* ...and fall through. Say it again for GCC. */ + fallthrough; case IIO_VAL_FRACTIONAL: *val *= regulator_get_voltage(dac->vref) / 1000; *val2 *= dac->max_ohms; diff --git a/drivers/iio/health/max30102.c b/drivers/iio/health/max30102.c index 9b47d9472a4f..d9b2ed80882a 100644 --- a/drivers/iio/health/max30102.c +++ b/drivers/iio/health/max30102.c @@ -273,10 +273,10 @@ static int max30102_read_measurement(struct max30102_data *data, switch (measurements) { case 3: MAX30102_COPY_DATA(2); - /* fall through */ + fallthrough; case 2: MAX30102_COPY_DATA(1); - /* fall through */ + fallthrough; case 1: MAX30102_COPY_DATA(0); break; diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index c539dfa3b8d3..319b64b2fd88 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -97,11 +97,11 @@ int __adis_write_reg(struct adis *adis, unsigned int reg, adis->tx[9] = (value >> 24) & 0xff; adis->tx[6] = ADIS_WRITE_REG(reg + 2); adis->tx[7] = (value >> 16) & 0xff; - /* fall through */ + fallthrough; case 2: adis->tx[4] = ADIS_WRITE_REG(reg + 1); adis->tx[5] = (value >> 8) & 0xff; - /* fall through */ + fallthrough; case 1: adis->tx[2] = ADIS_WRITE_REG(reg); adis->tx[3] = value & 0xff; @@ -191,7 +191,7 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, adis->tx[2] = ADIS_READ_REG(reg + 2); adis->tx[3] = 0; spi_message_add_tail(&xfers[1], &msg); - /* fall through */ + fallthrough; case 2: adis->tx[4] = ADIS_READ_REG(reg); adis->tx[5] = 0; diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 606d5e61c575..cdcd16f19500 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -599,7 +599,7 @@ static ssize_t __iio_format_value(char *buf, size_t len, unsigned int type, return scnprintf(buf, len, "%d", vals[0]); case IIO_VAL_INT_PLUS_MICRO_DB: scale_db = true; - /* fall through */ + fallthrough; case IIO_VAL_INT_PLUS_MICRO: if (vals[1] < 0) return scnprintf(buf, len, "-%d.%06u%s", abs(vals[0]), @@ -918,7 +918,7 @@ static ssize_t iio_write_channel_info(struct device *dev, break; case IIO_VAL_INT_PLUS_MICRO_DB: scale_db = true; - /* fall through */ + fallthrough; case IIO_VAL_INT_PLUS_MICRO: fract_mult = 100000; break; diff --git a/drivers/iio/light/si1145.c b/drivers/iio/light/si1145.c index 155faaea8c72..8f5f857c2e7d 100644 --- a/drivers/iio/light/si1145.c +++ b/drivers/iio/light/si1145.c @@ -1042,7 +1042,7 @@ static int si1145_initialize(struct si1145_data *data) SI1145_LED_CURRENT_45mA); if (ret < 0) return ret; - /* fallthrough */ + fallthrough; case 2: ret = i2c_smbus_write_byte_data(client, SI1145_REG_PS_LED21, diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c index 6a8ae145f0c0..cbb44e401c0a 100644 --- a/drivers/iio/magnetometer/ak8974.c +++ b/drivers/iio/magnetometer/ak8974.c @@ -499,7 +499,7 @@ static int ak8974_detect(struct ak8974 *ak8974) switch (whoami) { case AK8974_WHOAMI_VALUE_AMI306: name = "ami306"; - /* fall-through */ + fallthrough; case AK8974_WHOAMI_VALUE_AMI305: ret = regmap_read(ak8974->map, AMI305_VER, &fw); if (ret) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index dc0558b23158..fbc28f1a8b92 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3034,7 +3034,7 @@ static int cm_rej_handler(struct cm_work *work) case IB_CM_REP_SENT: case IB_CM_MRA_REP_RCVD: ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg); - /* fall through */ + fallthrough; case IB_CM_REQ_RCVD: case IB_CM_MRA_REQ_SENT: if (IBA_GET(CM_REJ_REASON, rej_msg) == IB_CM_REJ_STALE_CONN) @@ -3044,7 +3044,7 @@ static int cm_rej_handler(struct cm_work *work) break; case IB_CM_DREQ_SENT: ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg); - /* fall through */ + fallthrough; case IB_CM_REP_RCVD: case IB_CM_MRA_REP_SENT: cm_enter_timewait(cm_id_priv); @@ -3058,7 +3058,7 @@ static int cm_rej_handler(struct cm_work *work) cm_enter_timewait(cm_id_priv); break; } - /* fall through */ + fallthrough; default: pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n", __func__, be32_to_cpu(cm_id_priv->id.local_id), @@ -3116,7 +3116,7 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id, msg_response = CM_MSG_RESPONSE_OTHER; break; } - /* fall through */ + fallthrough; default: pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n", __func__, be32_to_cpu(cm_id_priv->id.local_id), @@ -3227,7 +3227,7 @@ static int cm_mra_handler(struct cm_work *work) case IB_CM_MRA_REP_RCVD: atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES]. counter[CM_MRA_COUNTER]); - /* fall through */ + fallthrough; default: pr_debug("%s local_id %d, cm_id_priv->id.state: %d\n", __func__, be32_to_cpu(cm_id_priv->id.local_id), @@ -4214,7 +4214,7 @@ static int cm_init_qp_rts_attr(struct cm_id_private *cm_id_priv, qp_attr->retry_cnt = cm_id_priv->retry_count; qp_attr->rnr_retry = cm_id_priv->rnr_retry_count; qp_attr->max_rd_atomic = cm_id_priv->initiator_depth; - /* fall through */ + fallthrough; case IB_QPT_XRC_TGT: *qp_attr_mask |= IB_QP_TIMEOUT; qp_attr->timeout = cm_id_priv->av.timeout; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 26de0dab60bb..7f0e91e92968 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1985,7 +1985,8 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, event.event = RDMA_CM_EVENT_ESTABLISHED; break; case IB_CM_DREQ_ERROR: - event.status = -ETIMEDOUT; /* fall through */ + event.status = -ETIMEDOUT; + fallthrough; case IB_CM_DREQ_RECEIVED: case IB_CM_DREP_RECEIVED: if (!cma_comp_exch(id_priv, RDMA_CM_CONNECT, diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index ef0cd2998671..c36b4d2b61e0 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2751,7 +2751,7 @@ static int __init ib_core_init(void) ret = addr_init(); if (ret) { - pr_warn("Could't init IB address resolution\n"); + pr_warn("Couldn't init IB address resolution\n"); goto err_ibnl; } diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c index 614cff89fc71..13f43ab7220b 100644 --- a/drivers/infiniband/core/rw.c +++ b/drivers/infiniband/core/rw.c @@ -510,7 +510,6 @@ struct ib_send_wr *rdma_rw_ctx_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp, switch (ctx->type) { case RDMA_RW_SIG_MR: case RDMA_RW_MR: - /* fallthrough */ for (i = 0; i < ctx->nr_ops; i++) { rdma_rw_update_lkey(&ctx->reg[i], ctx->reg[i].wr.wr.opcode != diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index d03dacaef788..1d184ea05eba 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -794,7 +794,7 @@ static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp, case 2: ib_copy_path_rec_to_user(&resp->ib_route[1], &route->path_rec[1]); - /* fall through */ + fallthrough; case 1: ib_copy_path_rec_to_user(&resp->ib_route[0], &route->path_rec[0]); @@ -820,7 +820,7 @@ static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp, case 2: ib_copy_path_rec_to_user(&resp->ib_route[1], &route->path_rec[1]); - /* fall through */ + fallthrough; case 1: ib_copy_path_rec_to_user(&resp->ib_route[0], &route->path_rec[0]); diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c index ef04a261097f..e47c5949013f 100644 --- a/drivers/infiniband/core/uverbs_ioctl.c +++ b/drivers/infiniband/core/uverbs_ioctl.c @@ -259,7 +259,7 @@ static int uverbs_process_attr(struct bundle_priv *pbundle, return -EOPNOTSUPP; e->ptr_attr.enum_id = uattr->attr_data.enum_data.elem_id; - /* fall through */ + fallthrough; case UVERBS_ATTR_TYPE_PTR_IN: /* Ensure that any data provided by userspace beyond the known * struct is zero. Userspace that knows how to use some future @@ -271,7 +271,7 @@ static int uverbs_process_attr(struct bundle_priv *pbundle, !uverbs_is_attr_cleared(uattr, val_spec->u.ptr.len)) return -EOPNOTSUPP; - /* fall through */ + fallthrough; case UVERBS_ATTR_TYPE_PTR_OUT: if (uattr->len < val_spec->u.ptr.min_len || (!val_spec->zero_trailing && diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 3f18efc0c297..5ee272d27aaa 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -2657,7 +2657,7 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr, default: break; } - /* fall through */ + fallthrough; case IB_WR_SEND_WITH_INV: rc = bnxt_re_build_send_wqe(qp, wr, &wqe); break; diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index dad0df8a2467..17ac8b7c5710 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -821,7 +821,8 @@ static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event, struct ib_event event; unsigned int flags; - if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { + if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR && + rdma_is_kernel_res(&qp->ib_qp.res)) { flags = bnxt_re_lock_cqs(qp); bnxt_qplib_add_flush_qp(&qp->qplib_qp); bnxt_re_unlock_cqs(qp, flags); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 117b42349a28..d60e3dcea087 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -1779,7 +1779,7 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp, break; } - /* fall thru */ + fallthrough; case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM: case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV: { diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 77bc02a9228e..1f288c73ccfc 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -2885,7 +2885,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) case MORIBUND: case CLOSING: stop_ep_timer(ep); - /*FALLTHROUGH*/ + fallthrough; case FPDU_MODE: if (ep->com.qp && ep->com.qp->srq) { srqidx = ABORT_RSS_SRQIDX_G( @@ -3759,7 +3759,7 @@ static void active_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb, send_fw_act_open_req(ep, atid); return; } - /* fall through */ + fallthrough; case FW_EADDRINUSE: set_bit(ACT_RETRY_INUSE, &ep->com.history); if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) { diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index ac48012c992f..cbddb20c6121 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1165,7 +1165,7 @@ int c4iw_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, break; } fw_flags |= FW_RI_RDMA_WRITE_WITH_IMMEDIATE; - /*FALLTHROUGH*/ + fallthrough; case IB_WR_RDMA_WRITE: fw_opcode = FW_RI_RDMA_WRITE_WR; swsqe->opcode = FW_RI_RDMA_WRITE; diff --git a/drivers/infiniband/hw/hfi1/pio_copy.c b/drivers/infiniband/hw/hfi1/pio_copy.c index b12e4665c9ab..4a4ec2397857 100644 --- a/drivers/infiniband/hw/hfi1/pio_copy.c +++ b/drivers/infiniband/hw/hfi1/pio_copy.c @@ -209,7 +209,6 @@ static inline void jcopy(u8 *dest, const u8 *src, u32 n) fallthrough; case 1: *dest++ = *src++; - /* fall through */ } } diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 9af82ff933d7..73d197e21730 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -3215,6 +3215,7 @@ bool hfi1_tid_rdma_wqe_interlock(struct rvt_qp *qp, struct rvt_swqe *wqe) case IB_WR_ATOMIC_CMP_AND_SWP: case IB_WR_ATOMIC_FETCH_AND_ADD: case IB_WR_RDMA_WRITE: + case IB_WR_RDMA_WRITE_WITH_IMM: switch (prev->wr.opcode) { case IB_WR_TID_RDMA_WRITE: req = wqe_to_tid_req(prev); diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index da9888deff8c..6edcbdcd8f43 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -65,8 +65,6 @@ #define HNS_ROCE_CQE_WCMD_EMPTY_BIT 0x2 #define HNS_ROCE_MIN_CQE_CNT 16 -#define HNS_ROCE_RESERVED_SGE 1 - #define HNS_ROCE_MAX_IRQ_NUM 128 #define HNS_ROCE_SGE_IN_WQE 2 diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 07b4c85d341d..aeb3a6fa7d47 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -535,7 +535,7 @@ static void hns_roce_set_sdb_ext(struct hns_roce_dev *hr_dev, u32 ext_sdb_alept, roce_write(hr_dev, ROCEE_EXT_DB_SQ_H_REG, val); dev_dbg(dev, "ext SDB depth: 0x%x\n", db->ext_db->esdb_dep); - dev_dbg(dev, "ext SDB threshold: epmty: 0x%x, ful: 0x%x\n", + dev_dbg(dev, "ext SDB threshold: empty: 0x%x, ful: 0x%x\n", ext_sdb_alept, ext_sdb_alful); } diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index d2968594664b..4cda95ed1fbe 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -633,7 +633,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1); - if (unlikely(wr->num_sge >= hr_qp->rq.max_gs)) { + if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) { ibdev_err(ibdev, "rq:num_sge=%d >= qp->sq.max_gs=%d\n", wr->num_sge, hr_qp->rq.max_gs); ret = -EINVAL; @@ -653,7 +653,6 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, if (wr->num_sge < hr_qp->rq.max_gs) { dseg->lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY); dseg->addr = 0; - dseg->len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH); } /* rq support inline data */ @@ -787,8 +786,8 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq, } if (wr->num_sge < srq->max_gs) { - dseg[i].len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH); - dseg[i].lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY); + dseg[i].len = 0; + dseg[i].lkey = cpu_to_le32(0x100); dseg[i].addr = 0; } @@ -5070,7 +5069,7 @@ static int hns_roce_v2_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr) attr->srq_limit = limit_wl; attr->max_wr = srq->wqe_cnt - 1; - attr->max_sge = srq->max_gs - HNS_ROCE_RESERVED_SGE; + attr->max_sge = srq->max_gs; out: hns_roce_free_cmd_mailbox(hr_dev, mailbox); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 1fb1c583d0f8..ac29be43b6bd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -92,9 +92,7 @@ #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ PAGE_SIZE #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFFF000 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM 2 -#define HNS_ROCE_INVALID_LKEY 0x0 -#define HNS_ROCE_INVALID_SGE_LENGTH 0x80000000 - +#define HNS_ROCE_INVALID_LKEY 0x100 #define HNS_ROCE_CMQ_TX_TIMEOUT 30000 #define HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE 2 #define HNS_ROCE_V2_RSV_QPS 8 diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index e94ca130ff5e..c063c450c715 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -386,8 +386,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, return -EINVAL; } - hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) + - HNS_ROCE_RESERVED_SGE); + hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge)); if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE) hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz); @@ -402,7 +401,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, hr_qp->rq_inl_buf.wqe_cnt = 0; cap->max_recv_wr = cnt; - cap->max_recv_sge = hr_qp->rq.max_gs - HNS_ROCE_RESERVED_SGE; + cap->max_recv_sge = hr_qp->rq.max_gs; return 0; } diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index f40a000e94ee..b9e2dbd372b6 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -297,7 +297,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq, spin_lock_init(&srq->lock); srq->wqe_cnt = roundup_pow_of_two(init_attr->attr.max_wr + 1); - srq->max_gs = init_attr->attr.max_sge + HNS_ROCE_RESERVED_SGE; + srq->max_gs = init_attr->attr.max_sge; if (udata) { ret = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)); diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index fa7a5ff498c7..a3b95805c154 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -2443,7 +2443,7 @@ static void i40iw_handle_rst_pkt(struct i40iw_cm_node *cm_node, case I40IW_CM_STATE_FIN_WAIT1: case I40IW_CM_STATE_LAST_ACK: cm_node->cm_id->rem_ref(cm_node->cm_id); - /* fall through */ + fallthrough; case I40IW_CM_STATE_TIME_WAIT: cm_node->state = I40IW_CM_STATE_CLOSED; i40iw_rem_ref_cm_node(cm_node); diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c index 688f19667221..86d3f8aff329 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c +++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c @@ -1964,7 +1964,6 @@ static enum i40iw_status_code i40iw_sc_get_next_aeqe(struct i40iw_sc_aeq *aeq, info->out_rdrsp = true; break; case I40IW_AE_SOURCE_RSVD: - /* fallthrough */ default: break; } @@ -3762,14 +3761,14 @@ static enum i40iw_status_code cqp_sds_wqe_fill(struct i40iw_sc_cqp *cqp, LS_64(1, I40IW_CQPSQ_UPESD_ENTRY_VALID))); set_64bit_val(wqe, 56, info->entry[2].data); - /* fallthrough */ + fallthrough; case 2: set_64bit_val(wqe, 32, (LS_64(info->entry[1].cmd, I40IW_CQPSQ_UPESD_SDCMD) | LS_64(1, I40IW_CQPSQ_UPESD_ENTRY_VALID))); set_64bit_val(wqe, 40, info->entry[1].data); - /* fallthrough */ + fallthrough; case 1: set_64bit_val(wqe, 0, LS_64(info->entry[0].cmd, I40IW_CQPSQ_UPESD_SDCMD)); diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c index ae8b97c30665..e1085634b8d9 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_hw.c +++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c @@ -353,7 +353,6 @@ void i40iw_process_aeq(struct i40iw_device *iwdev) i40iw_cm_disconn(iwqp); break; case I40IW_AE_BAD_CLOSE: - /* fall through */ case I40IW_AE_RESET_SENT: i40iw_next_iw_state(iwqp, I40IW_QP_STATE_ERROR, 1, 0, 0); i40iw_cm_disconn(iwqp); @@ -413,7 +412,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev) case I40IW_AE_UDA_XMIT_DGRAM_TOO_LONG: case I40IW_AE_UDA_XMIT_DGRAM_TOO_SHORT: ctx_info->err_rq_idx_valid = false; - /* fall through */ + fallthrough; default: if (!info->sq && ctx_info->err_rq_idx_valid) { ctx_info->err_rq_idx = info->wqe_idx; diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index 9c96ece5e7f3..58a433135a03 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -1489,36 +1489,35 @@ static void i40iw_deinit_device(struct i40iw_device *iwdev) iwdev->iw_status = 0; i40iw_port_ibevent(iwdev); i40iw_destroy_rdma_device(iwdev->iwibdev); - /* fallthrough */ + fallthrough; case IP_ADDR_REGISTERED: if (!iwdev->reset) i40iw_del_macip_entry(iwdev, (u8)iwdev->mac_ip_table_idx); - /* fallthrough */ - /* fallthrough */ + fallthrough; case PBLE_CHUNK_MEM: i40iw_destroy_pble_pool(dev, iwdev->pble_rsrc); - /* fallthrough */ + fallthrough; case CEQ_CREATED: i40iw_dele_ceqs(iwdev); - /* fallthrough */ + fallthrough; case AEQ_CREATED: i40iw_destroy_aeq(iwdev); - /* fallthrough */ + fallthrough; case IEQ_CREATED: i40iw_puda_dele_resources(&iwdev->vsi, I40IW_PUDA_RSRC_TYPE_IEQ, iwdev->reset); - /* fallthrough */ + fallthrough; case ILQ_CREATED: i40iw_puda_dele_resources(&iwdev->vsi, I40IW_PUDA_RSRC_TYPE_ILQ, iwdev->reset); - /* fallthrough */ + fallthrough; case CCQ_CREATED: i40iw_destroy_ccq(iwdev); - /* fallthrough */ + fallthrough; case HMC_OBJS_CREATED: i40iw_del_hmc_objects(dev, dev->hmc_info, true, iwdev->reset); - /* fallthrough */ + fallthrough; case CQP_CREATED: i40iw_destroy_cqp(iwdev, true); - /* fallthrough */ + fallthrough; case INITIAL_STATE: i40iw_cleanup_cm_core(&iwdev->cm_core); if (iwdev->vsi.pestat) { @@ -1528,7 +1527,6 @@ static void i40iw_deinit_device(struct i40iw_device *iwdev) i40iw_del_init_mem(iwdev); break; case INVALID_STATE: - /* fallthrough */ default: i40iw_pr_err("bad init_state = %d\n", iwdev->init_state); break; diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c index d9c7ae6a7030..924be4b03c9a 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_puda.c +++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c @@ -814,13 +814,13 @@ void i40iw_puda_dele_resources(struct i40iw_sc_vsi *vsi, switch (rsrc->completion) { case PUDA_HASH_CRC_COMPLETE: i40iw_free_hash_desc(rsrc->hash_desc); - /* fall through */ + fallthrough; case PUDA_QP_CREATED: if (!reset) i40iw_puda_free_qp(rsrc); i40iw_free_dma_mem(dev->hw, &rsrc->qpmem); - /* fallthrough */ + fallthrough; case PUDA_CQ_CREATED: if (!reset) i40iw_puda_free_cq(rsrc); diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index 016524683e17..e07fb37af086 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -190,9 +190,8 @@ int i40iw_inetaddr_event(struct notifier_block *notifier, switch (event) { case NETDEV_DOWN: action = I40IW_ARP_DELETE; - /* Fall through */ + fallthrough; case NETDEV_UP: - /* Fall through */ case NETDEV_CHANGEADDR: /* Just skip if no need to handle ARP cache */ @@ -247,9 +246,8 @@ int i40iw_inet6addr_event(struct notifier_block *notifier, switch (event) { case NETDEV_DOWN: action = I40IW_ARP_DELETE; - /* Fall through */ + fallthrough; case NETDEV_UP: - /* Fall through */ case NETDEV_CHANGEADDR: i40iw_manage_arp_cache(iwdev, netdev->dev_addr, @@ -344,7 +342,7 @@ int i40iw_netdevice_event(struct notifier_block *notifier, switch (event) { case NETDEV_DOWN: iwdev->iw_status = 0; - /* Fall through */ + fallthrough; case NETDEV_UP: i40iw_port_ibevent(iwdev); break; diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 6957e4f3404b..b51339328a51 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -810,7 +810,7 @@ void i40iw_hw_modify_qp(struct i40iw_device *iwdev, struct i40iw_qp *iwqp, case I40IW_QP_STATE_RTS: if (iwqp->iwarp_state == I40IW_QP_STATE_IDLE) i40iw_send_reset(iwqp->cm_node); - /* fall through */ + fallthrough; case I40IW_QP_STATE_IDLE: case I40IW_QP_STATE_TERMINATE: case I40IW_QP_STATE_CLOSING: @@ -2144,7 +2144,6 @@ static int i40iw_post_send(struct ib_qp *ibqp, switch (ib_wr->opcode) { case IB_WR_SEND: - /* fall-through */ case IB_WR_SEND_WITH_INV: if (ib_wr->opcode == IB_WR_SEND) { if (ib_wr->send_flags & IB_SEND_SOLICITED) @@ -2201,7 +2200,7 @@ static int i40iw_post_send(struct ib_qp *ibqp, break; case IB_WR_RDMA_READ_WITH_INV: inv_stag = true; - /* fall-through*/ + fallthrough; case IB_WR_RDMA_READ: if (ib_wr->num_sge > I40IW_MAX_SGE_RD) { err = -EINVAL; diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index f8b936b76dcd..8a3436994f80 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -765,13 +765,13 @@ repoll: switch (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) { case MLX4_OPCODE_RDMA_WRITE_IMM: wc->wc_flags |= IB_WC_WITH_IMM; - /* fall through */ + fallthrough; case MLX4_OPCODE_RDMA_WRITE: wc->opcode = IB_WC_RDMA_WRITE; break; case MLX4_OPCODE_SEND_IMM: wc->wc_flags |= IB_WC_WITH_IMM; - /* fall through */ + fallthrough; case MLX4_OPCODE_SEND: case MLX4_OPCODE_SEND_INVAL: wc->opcode = IB_WC_SEND; diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c index d844831179cf..5e4ec9786081 100644 --- a/drivers/infiniband/hw/mlx4/mcg.c +++ b/drivers/infiniband/hw/mlx4/mcg.c @@ -944,7 +944,7 @@ int mlx4_ib_mcg_multiplex_handler(struct ib_device *ibdev, int port, switch (sa_mad->mad_hdr.method) { case IB_MGMT_METHOD_SET: may_create = 1; - /* fall through */ + fallthrough; case IB_SA_METHOD_DELETE: req = kzalloc(sizeof *req, GFP_KERNEL); if (!req) diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index f9ca6e000a81..2975f350b9fd 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1578,12 +1578,12 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, pd = to_mxrcd(init_attr->xrcd)->pd; xrcdn = to_mxrcd(init_attr->xrcd)->xrcdn; init_attr->send_cq = to_mxrcd(init_attr->xrcd)->cq; - /* fall through */ + fallthrough; case IB_QPT_XRC_INI: if (!(to_mdev(pd->device)->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC)) return ERR_PTR(-ENOSYS); init_attr->recv_cq = init_attr->send_cq; - /* fall through */ + fallthrough; case IB_QPT_RC: case IB_QPT_UC: case IB_QPT_RAW_PACKET: @@ -1592,7 +1592,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, return ERR_PTR(-ENOMEM); qp->pri.vid = 0xFFFF; qp->alt.vid = 0xFFFF; - /* fall through */ + fallthrough; case IB_QPT_UD: { err = create_qp_common(pd, init_attr, udata, 0, &qp); diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 0133ebb8d740..dceb0eb2bed1 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -121,13 +121,13 @@ static void handle_good_req(struct ib_wc *wc, struct mlx5_cqe64 *cqe, switch (be32_to_cpu(cqe->sop_drop_qpn) >> 24) { case MLX5_OPCODE_RDMA_WRITE_IMM: wc->wc_flags |= IB_WC_WITH_IMM; - /* fall through */ + fallthrough; case MLX5_OPCODE_RDMA_WRITE: wc->opcode = IB_WC_RDMA_WRITE; break; case MLX5_OPCODE_SEND_IMM: wc->wc_flags |= IB_WC_WITH_IMM; - /* fall through */ + fallthrough; case MLX5_OPCODE_SEND: case MLX5_OPCODE_SEND_INVAL: wc->opcode = IB_WC_SEND; diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 454ce5de2de7..9bb9bb058932 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -250,9 +250,8 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, if (MLX5_CAP_GEN(dev->mdev, vport_counters) && method == IB_MGMT_METHOD_GET) return process_pma_cmd(dev, port_num, in, out); - /* fallthrough */ + fallthrough; case MLX5_IB_VENDOR_CLASS1: - /* fallthrough */ case MLX5_IB_VENDOR_CLASS2: case IB_MGMT_CLASS_CONG_MGMT: { if (method != IB_MGMT_METHOD_GET && diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index fbc45a5e76c5..d60d63221b14 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2872,7 +2872,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work) break; case MLX5_EVENT_TYPE_GENERAL_EVENT: handle_general_event(ibdev, work->param, &ibev); - /* fall through */ + fallthrough; default: goto out; } diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 59fce5fac7a3..5758dbe64045 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -416,7 +416,7 @@ static int sq_overhead(struct ib_qp_init_attr *attr) switch (attr->qp_type) { case IB_QPT_XRC_INI: size += sizeof(struct mlx5_wqe_xrc_seg); - /* fall through */ + fallthrough; case IB_QPT_RC: size += sizeof(struct mlx5_wqe_ctrl_seg) + max(sizeof(struct mlx5_wqe_atomic_seg) + @@ -441,7 +441,7 @@ static int sq_overhead(struct ib_qp_init_attr *attr) if (attr->create_flags & IB_QP_CREATE_IPOIB_UD_LSO) size += sizeof(struct mlx5_wqe_eth_pad) + sizeof(struct mlx5_wqe_eth_seg); - /* fall through */ + fallthrough; case IB_QPT_SMI: case MLX5_IB_QPT_HW_GSI: size += sizeof(struct mlx5_wqe_ctrl_seg) + diff --git a/drivers/infiniband/hw/mthca/mthca_av.c b/drivers/infiniband/hw/mthca/mthca_av.c index 0823c0bc7e73..f051f4e06b53 100644 --- a/drivers/infiniband/hw/mthca/mthca_av.c +++ b/drivers/infiniband/hw/mthca/mthca_av.c @@ -115,7 +115,7 @@ static u8 ib_rate_to_memfree(u8 req_rate, u8 cur_rate) switch ((cur_rate - 1) / req_rate) { case 0: return MTHCA_RATE_MEMFREE_FULL; case 1: return MTHCA_RATE_MEMFREE_HALF; - case 2: /* fall through */ + case 2: case 3: return MTHCA_RATE_MEMFREE_QUARTER; default: return MTHCA_RATE_MEMFREE_EIGHTH; } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index 6cdbec13756a..c1751c9a0f62 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -2134,7 +2134,7 @@ int ocrdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, case IB_WR_SEND_WITH_IMM: hdr->cw |= (OCRDMA_FLAG_IMM << OCRDMA_WQE_FLAGS_SHIFT); hdr->immdt = ntohl(wr->ex.imm_data); - /* fall through */ + fallthrough; case IB_WR_SEND: hdr->cw |= (OCRDMA_SEND << OCRDMA_WQE_OPCODE_SHIFT); ocrdma_build_send(qp, hdr, wr); @@ -2148,7 +2148,7 @@ int ocrdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, case IB_WR_RDMA_WRITE_WITH_IMM: hdr->cw |= (OCRDMA_FLAG_IMM << OCRDMA_WQE_FLAGS_SHIFT); hdr->immdt = ntohl(wr->ex.imm_data); - /* fall through */ + fallthrough; case IB_WR_RDMA_WRITE: hdr->cw |= (OCRDMA_WRITE << OCRDMA_WQE_OPCODE_SHIFT); status = ocrdma_build_write(qp, hdr, wr); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 4ce4e2eef6cc..b49bef94637e 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -3528,7 +3528,7 @@ static int __qedr_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, break; case IB_WR_RDMA_READ_WITH_INV: SET_FIELD2(wqe->flags, RDMA_SQ_RDMA_WQE_1ST_READ_INV_FLG, 1); - /* fallthrough -- same is identical to RDMA READ */ + fallthrough; /* same is identical to RDMA READ */ case IB_WR_RDMA_READ: wqe->req_type = RDMA_SQ_REQ_TYPE_RDMA_RD; diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c index ca5ea734e3d0..44150be215bf 100644 --- a/drivers/infiniband/hw/qib/qib_iba6120.c +++ b/drivers/infiniband/hw/qib/qib_iba6120.c @@ -2973,11 +2973,11 @@ static u32 qib_6120_iblink_state(u64 ibcs) state = IB_PORT_ARMED; break; case IB_6120_L_STATE_ACTIVE: - /* fall through */ case IB_6120_L_STATE_ACT_DEFER: state = IB_PORT_ACTIVE; break; - default: /* fall through */ + default: + fallthrough; case IB_6120_L_STATE_DOWN: state = IB_PORT_DOWN; break; diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c index ea3ddb05cbad..0a6f26d4cb31 100644 --- a/drivers/infiniband/hw/qib/qib_iba7220.c +++ b/drivers/infiniband/hw/qib/qib_iba7220.c @@ -3586,11 +3586,11 @@ static u32 qib_7220_iblink_state(u64 ibcs) state = IB_PORT_ARMED; break; case IB_7220_L_STATE_ACTIVE: - /* fall through */ case IB_7220_L_STATE_ACT_DEFER: state = IB_PORT_ACTIVE; break; - default: /* fall through */ + default: + fallthrough; case IB_7220_L_STATE_DOWN: state = IB_PORT_DOWN; break; diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index 8bcbc884e5b6..a10eab89aee4 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -5508,11 +5508,11 @@ static u32 qib_7322_iblink_state(u64 ibcs) state = IB_PORT_ARMED; break; case IB_7322_L_STATE_ACTIVE: - /* fall through */ case IB_7322_L_STATE_ACT_DEFER: state = IB_PORT_ACTIVE; break; - default: /* fall through */ + default: + fallthrough; case IB_7322_L_STATE_DOWN: state = IB_PORT_DOWN; break; @@ -6533,7 +6533,7 @@ static int qib_init_7322_variables(struct qib_devdata *dd) "Invalid num_vls %u, using 4 VLs\n", qib_num_cfg_vls); qib_num_cfg_vls = 4; - /* fall through */ + fallthrough; case 4: ppd->vls_supported = IB_VL_VL0_3; break; diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c index 79bb83222e8d..e7789e724f56 100644 --- a/drivers/infiniband/hw/qib/qib_mad.c +++ b/drivers/infiniband/hw/qib/qib_mad.c @@ -433,7 +433,7 @@ static int check_mkey(struct qib_ibport *ibp, struct ib_smp *smp, int mad_flags) /* Bad mkey not a violation below level 2 */ if (ibp->rvp.mkeyprot < 2) break; - /* fall through */ + fallthrough; case IB_MGMT_METHOD_SET: case IB_MGMT_METHOD_TRAP_REPRESS: if (ibp->rvp.mkey_violations != 0xFFFF) @@ -828,7 +828,7 @@ static int subn_set_portinfo(struct ib_smp *smp, struct ib_device *ibdev, case IB_PORT_NOP: if (lstate == 0) break; - /* FALLTHROUGH */ + fallthrough; case IB_PORT_DOWN: if (lstate == 0) lstate = QIB_IB_LINKDOWN_ONLY; @@ -1928,7 +1928,7 @@ static int process_subn(struct ib_device *ibdev, int mad_flags, ret = IB_MAD_RESULT_SUCCESS; goto bail; } - /* FALLTHROUGH */ + fallthrough; default: smp->status |= IB_SMP_UNSUP_METH_ATTR; ret = reply(smp); @@ -1962,7 +1962,7 @@ static int process_subn(struct ib_device *ibdev, int mad_flags, ret = IB_MAD_RESULT_SUCCESS; goto bail; } - /* FALLTHROUGH */ + fallthrough; default: smp->status |= IB_SMP_UNSUP_METH_ATTR; ret = reply(smp); @@ -2322,7 +2322,7 @@ static int process_cc(struct ib_device *ibdev, int mad_flags, ret = cc_get_congestion_control_table(ccp, ibdev, port); goto bail; - /* FALLTHROUGH */ + fallthrough; default: ccp->status |= IB_SMP_UNSUP_METH_ATTR; ret = reply((struct ib_smp *) ccp); @@ -2339,7 +2339,7 @@ static int process_cc(struct ib_device *ibdev, int mad_flags, ret = cc_set_congestion_control_table(ccp, ibdev, port); goto bail; - /* FALLTHROUGH */ + fallthrough; default: ccp->status |= IB_SMP_UNSUP_METH_ATTR; ret = reply((struct ib_smp *) ccp); diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c index aaf7438258fa..3915e5b4a9bc 100644 --- a/drivers/infiniband/hw/qib/qib_rc.c +++ b/drivers/infiniband/hw/qib/qib_rc.c @@ -83,7 +83,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct rvt_qp *qp, rvt_put_mr(e->rdma_sge.mr); e->rdma_sge.mr = NULL; } - /* FALLTHROUGH */ + fallthrough; case OP(ATOMIC_ACKNOWLEDGE): /* * We can increment the tail pointer now that the last @@ -92,7 +92,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct rvt_qp *qp, */ if (++qp->s_tail_ack_queue > QIB_MAX_RDMA_ATOMIC) qp->s_tail_ack_queue = 0; - /* FALLTHROUGH */ + fallthrough; case OP(SEND_ONLY): case OP(ACKNOWLEDGE): /* Check for no next entry in the queue. */ @@ -149,7 +149,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct rvt_qp *qp, case OP(RDMA_READ_RESPONSE_FIRST): qp->s_ack_state = OP(RDMA_READ_RESPONSE_MIDDLE); - /* FALLTHROUGH */ + fallthrough; case OP(RDMA_READ_RESPONSE_MIDDLE): qp->s_cur_sge = &qp->s_ack_rdma_sge; qp->s_rdma_mr = qp->s_ack_rdma_sge.sge.mr; @@ -471,10 +471,10 @@ no_flow_control: * See qib_restart_rc(). */ qp->s_len = restart_sge(&qp->s_sge, wqe, qp->s_psn, pmtu); - /* FALLTHROUGH */ + fallthrough; case OP(SEND_FIRST): qp->s_state = OP(SEND_MIDDLE); - /* FALLTHROUGH */ + fallthrough; case OP(SEND_MIDDLE): bth2 = qp->s_psn++ & QIB_PSN_MASK; ss = &qp->s_sge; @@ -510,10 +510,10 @@ no_flow_control: * See qib_restart_rc(). */ qp->s_len = restart_sge(&qp->s_sge, wqe, qp->s_psn, pmtu); - /* FALLTHROUGH */ + fallthrough; case OP(RDMA_WRITE_FIRST): qp->s_state = OP(RDMA_WRITE_MIDDLE); - /* FALLTHROUGH */ + fallthrough; case OP(RDMA_WRITE_MIDDLE): bth2 = qp->s_psn++ & QIB_PSN_MASK; ss = &qp->s_sge; @@ -1807,7 +1807,7 @@ void qib_rc_rcv(struct qib_ctxtdata *rcd, struct ib_header *hdr, if (!ret) goto rnr_nak; qp->r_rcv_len = 0; - /* FALLTHROUGH */ + fallthrough; case OP(SEND_MIDDLE): case OP(RDMA_WRITE_MIDDLE): send_middle: @@ -1839,7 +1839,7 @@ send_middle: qp->r_rcv_len = 0; if (opcode == OP(SEND_ONLY)) goto no_immediate_data; - /* fall through -- for SEND_ONLY_WITH_IMMEDIATE */ + fallthrough; /* for SEND_ONLY_WITH_IMMEDIATE */ case OP(SEND_LAST_WITH_IMMEDIATE): send_last_imm: wc.ex.imm_data = ohdr->u.imm_data; diff --git a/drivers/infiniband/hw/qib/qib_sdma.c b/drivers/infiniband/hw/qib/qib_sdma.c index 99e11c347130..8f8d61736656 100644 --- a/drivers/infiniband/hw/qib/qib_sdma.c +++ b/drivers/infiniband/hw/qib/qib_sdma.c @@ -763,7 +763,7 @@ void __qib_sdma_process_event(struct qib_pportdata *ppd, * bringing the link up with traffic active on * 7220, e.g. */ ss->go_s99_running = 1; - /* fall through -- and start dma engine */ + fallthrough; /* and start dma engine */ case qib_sdma_event_e10_go_hw_start: /* This reference means the state machine is started */ sdma_get(&ppd->sdma_state); diff --git a/drivers/infiniband/hw/qib/qib_uc.c b/drivers/infiniband/hw/qib/qib_uc.c index e17b91e2c22a..554af4273a13 100644 --- a/drivers/infiniband/hw/qib/qib_uc.c +++ b/drivers/infiniband/hw/qib/qib_uc.c @@ -161,7 +161,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags) case OP(SEND_FIRST): qp->s_state = OP(SEND_MIDDLE); - /* FALLTHROUGH */ + fallthrough; case OP(SEND_MIDDLE): len = qp->s_len; if (len > pmtu) { @@ -185,7 +185,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags) case OP(RDMA_WRITE_FIRST): qp->s_state = OP(RDMA_WRITE_MIDDLE); - /* FALLTHROUGH */ + fallthrough; case OP(RDMA_WRITE_MIDDLE): len = qp->s_len; if (len > pmtu) { @@ -351,7 +351,7 @@ send_first: goto no_immediate_data; else if (opcode == OP(SEND_ONLY_WITH_IMMEDIATE)) goto send_last_imm; - /* FALLTHROUGH */ + fallthrough; case OP(SEND_MIDDLE): /* Check for invalid length PMTU or posted rwqe len. */ if (unlikely(tlen != (hdrsize + pmtu + 4))) @@ -440,7 +440,7 @@ rdma_first: wc.ex.imm_data = ohdr->u.rc.imm_data; goto rdma_last_imm; } - /* FALLTHROUGH */ + fallthrough; case OP(RDMA_WRITE_MIDDLE): /* Check for invalid length PMTU or posted rwqe len. */ if (unlikely(tlen != (hdrsize + pmtu + 4))) diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c index 7acf9ba5358a..f6c01bad5a74 100644 --- a/drivers/infiniband/hw/qib/qib_verbs.c +++ b/drivers/infiniband/hw/qib/qib_verbs.c @@ -237,7 +237,7 @@ static void qib_qp_rcv(struct qib_ctxtdata *rcd, struct ib_header *hdr, case IB_QPT_GSI: if (ib_qib_disable_sma) break; - /* FALLTHROUGH */ + fallthrough; case IB_QPT_UD: qib_ud_rcv(ibp, hdr, has_grh, data, tlen, qp); break; diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index c9abe1c01e4e..662e7fc7f628 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -120,7 +120,7 @@ static void usnic_ib_qp_grp_modify_active_to_err(struct usnic_ib_dev *us_ibdev) IB_QPS_ERR, NULL); if (status) { - usnic_err("Failed to transistion qp grp %u from %s to %s\n", + usnic_err("Failed to transition qp grp %u from %s to %s\n", qp_grp->grp_id, usnic_ib_qp_grp_state_to_string (cur_state), diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c index afcc2abcf55c..9a8f2a9507be 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c @@ -238,7 +238,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd, ret = -EINVAL; goto err_qp; } - /* fall through */ + fallthrough; case IB_QPT_RC: case IB_QPT_UD: qp = kzalloc(sizeof(*qp), GFP_KERNEL); diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 332a8ba94b81..ee48befc8978 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1111,7 +1111,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, if (init_attr->port_num == 0 || init_attr->port_num > ibpd->device->phys_port_cnt) return ERR_PTR(-EINVAL); - /* fall through */ + fallthrough; case IB_QPT_UC: case IB_QPT_RC: case IB_QPT_UD: diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 4bc88708b355..7b4df0028388 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -282,7 +282,7 @@ static inline enum comp_state check_ack(struct rxe_qp *qp, if ((syn & AETH_TYPE_MASK) != AETH_ACK) return COMPST_ERROR; - /* fall through */ + fallthrough; /* (IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE doesn't have an AETH) */ case IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE: diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index 08f05ac5f5d5..ecdac3f8fcc9 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -71,7 +71,7 @@ void rxe_do_task(unsigned long data) case TASK_STATE_BUSY: task->state = TASK_STATE_ARMED; - /* fall through */ + fallthrough; case TASK_STATE_ARMED: spin_unlock_irqrestore(&task->state_lock, flags); return; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index bb61e534e468..658939e5c34a 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -540,7 +540,7 @@ static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr, switch (wr->opcode) { case IB_WR_RDMA_WRITE_WITH_IMM: wr->ex.imm_data = ibwr->ex.imm_data; - /* fall through */ + fallthrough; case IB_WR_RDMA_READ: case IB_WR_RDMA_WRITE: wr->wr.rdma.remote_addr = rdma_wr(ibwr)->remote_addr; diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 1662216be66d..66764f7ef072 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -1224,12 +1224,10 @@ static void siw_cm_llp_data_ready(struct sock *sk) switch (cep->state) { case SIW_EPSTATE_RDMA_MODE: - /* fall through */ case SIW_EPSTATE_LISTENING: break; case SIW_EPSTATE_AWAIT_MPAREQ: - /* fall through */ case SIW_EPSTATE_AWAIT_MPAREP: siw_cm_queue_work(cep, SIW_CM_WORK_READ_MPAHDR); break; diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c index 857be5a7d0bd..4bd1f1f84057 100644 --- a/drivers/infiniband/sw/siw/siw_qp_rx.c +++ b/drivers/infiniband/sw/siw/siw_qp_rx.c @@ -1215,7 +1215,7 @@ static int siw_rdmap_complete(struct siw_qp *qp, int error) case RDMAP_SEND_SE: case RDMAP_SEND_SE_INVAL: wqe->rqe.flags |= SIW_WQE_SOLICITED; - /* Fall through */ + fallthrough; case RDMAP_SEND: case RDMAP_SEND_INVAL: @@ -1386,7 +1386,7 @@ int siw_tcp_rx_data(read_descriptor_t *rd_desc, struct sk_buff *skb, * DDP segment. */ qp->rx_fpdu->first_ddp_seg = 0; - /* Fall through */ + fallthrough; case SIW_GET_DATA_START: /* diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index 9f53aa4feb87..d19d8325588b 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -1042,7 +1042,7 @@ next_wqe: case SIW_OP_SEND_REMOTE_INV: case SIW_OP_WRITE: siw_wqe_put_mem(wqe, tx_type); - /* Fall through */ + fallthrough; case SIW_OP_INVAL_STAG: case SIW_OP_REG_MR: @@ -1128,7 +1128,7 @@ next_wqe: case SIW_OP_READ: case SIW_OP_READ_LOCAL_INV: siw_wqe_put_mem(wqe, tx_type); - /* Fall through */ + fallthrough; case SIW_OP_INVAL_STAG: case SIW_OP_REG_MR: diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 9bf0fa30df28..7c41fb040f7c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -512,13 +512,13 @@ static int ipoib_cm_rx_handler(struct ib_cm_id *cm_id, return ipoib_cm_req_handler(cm_id, event); case IB_CM_DREQ_RECEIVED: ib_send_cm_drep(cm_id, NULL, 0); - /* Fall through */ + fallthrough; case IB_CM_REJ_RECEIVED: p = cm_id->context; priv = ipoib_priv(p->dev); if (ib_modify_qp(p->qp, &ipoib_cm_err_attr, IB_QP_STATE)) ipoib_warn(priv, "unable to move qp to error state\n"); - /* Fall through */ + fallthrough; default: return 0; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 752581a8627b..ab75b7f745d4 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -502,7 +502,7 @@ static struct net_device *ipoib_get_net_dev_by_params( default: dev_warn_ratelimited(&dev->dev, "duplicate IP address detected\n"); - /* Fall through */ + fallthrough; case 1: return net_dev; } diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index 699e075ae1b3..2f3ebc0a75d9 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -711,7 +711,7 @@ static int iser_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *eve case RDMA_CM_EVENT_REJECTED: iser_info("Connection rejected: %s\n", rdma_reject_msg(cma_id, event->status)); - /* FALLTHROUGH */ + fallthrough; case RDMA_CM_EVENT_ADDR_ERROR: case RDMA_CM_EVENT_ROUTE_ERROR: case RDMA_CM_EVENT_CONNECT_ERROR: diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 61e2f7fc513d..e86acda3cf8c 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -664,8 +664,8 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) case RDMA_CM_EVENT_ESTABLISHED: isert_connected_handler(cma_id); break; - case RDMA_CM_EVENT_ADDR_CHANGE: /* FALLTHRU */ - case RDMA_CM_EVENT_DISCONNECTED: /* FALLTHRU */ + case RDMA_CM_EVENT_ADDR_CHANGE: + case RDMA_CM_EVENT_DISCONNECTED: case RDMA_CM_EVENT_TIMEWAIT_EXIT: /* FALLTHRU */ ret = isert_disconnected_handler(cma_id, event->event); break; @@ -684,7 +684,7 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) case RDMA_CM_EVENT_REJECTED: isert_info("Connection rejected: %s\n", rdma_reject_msg(cma_id, event->status)); - /* fall through */ + fallthrough; case RDMA_CM_EVENT_UNREACHABLE: case RDMA_CM_EVENT_CONNECT_ERROR: ret = isert_connect_error(cma_id); @@ -1470,7 +1470,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err) transport_generic_free_cmd(&cmd->se_cmd, 0); break; } - /* fall through */ + fallthrough; default: iscsit_release_cmd(cmd); break; @@ -1648,7 +1648,7 @@ isert_do_control_comp(struct work_struct *work) switch (cmd->i_state) { case ISTATE_SEND_TASKMGTRSP: iscsit_tmr_post_handler(cmd, cmd->conn); - /* fall through */ + fallthrough; case ISTATE_SEND_REJECT: case ISTATE_SEND_TEXTRSP: cmd->i_state = ISTATE_SENT_STATUS; diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c index 874a8eb7638c..4933085a864a 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c @@ -547,7 +547,6 @@ static void vema_get(struct opa_vnic_vema_port *port, vema_get_mac_entries(port, recvd_mad, rsp_mad); break; case OPA_EM_ATTR_IFACE_UCAST_MACS: - /* fall through */ case OPA_EM_ATTR_IFACE_MCAST_MACS: vema_get_mac_list(port, recvd_mad, rsp_mad, attr_id); break; diff --git a/drivers/input/joystick/fsia6b.c b/drivers/input/joystick/fsia6b.c index e78c4c768990..76ffdec5c183 100644 --- a/drivers/input/joystick/fsia6b.c +++ b/drivers/input/joystick/fsia6b.c @@ -102,12 +102,12 @@ static irqreturn_t fsia6b_serio_irq(struct serio *serio, input_report_key(fsia6b->dev, sw_id++, sw_state == 0); - /* fall-through */ + fallthrough; case '2': input_report_key(fsia6b->dev, sw_id++, sw_state == 1); - /* fall-through */ + fallthrough; case '1': input_report_key(fsia6b->dev, sw_id++, diff --git a/drivers/input/joystick/gamecon.c b/drivers/input/joystick/gamecon.c index 88df68cc4ac6..d37645e496ff 100644 --- a/drivers/input/joystick/gamecon.c +++ b/drivers/input/joystick/gamecon.c @@ -885,7 +885,6 @@ static int gc_setup_pad(struct gc *gc, int idx, int pad_type) case GC_MULTI: input_set_capability(input_dev, EV_KEY, BTN_TRIGGER); - /* fall through */ break; case GC_PSX: diff --git a/drivers/input/tablet/wacom_serial4.c b/drivers/input/tablet/wacom_serial4.c index 959c1d82aa66..1cedb45ba497 100644 --- a/drivers/input/tablet/wacom_serial4.c +++ b/drivers/input/tablet/wacom_serial4.c @@ -213,7 +213,7 @@ static void wacom_handle_model_response(struct wacom *wacom) case 0x3731: /* PL-710 */ wacom->res_x = 2540; wacom->res_y = 2540; - /* fall through */ + fallthrough; case 0x3535: /* PL-550 */ case 0x3830: /* PL-800 */ wacom->extra_z_bits = 2; diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index 6b71b0aff115..98f17fa3a892 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -477,7 +477,7 @@ static int mxt_lookup_bootloader_address(struct mxt_data *data, bool retry) bootloader = appmode - 0x24; break; } - /* Fall through - for normal case */ + fallthrough; /* for normal case */ case 0x4c: case 0x4d: case 0x5a: diff --git a/drivers/input/touchscreen/wm831x-ts.c b/drivers/input/touchscreen/wm831x-ts.c index 607d1aeb595d..bb1699e0d3c7 100644 --- a/drivers/input/touchscreen/wm831x-ts.c +++ b/drivers/input/touchscreen/wm831x-ts.c @@ -290,7 +290,7 @@ static int wm831x_ts_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Unsupported ISEL setting: %d\n", pdata->isel); - /* Fall through */ + fallthrough; case 200: case 0: wm831x_set_bits(wm831x, WM831X_TOUCH_CONTROL_2, diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 958050c213f9..c652f16eb702 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -2258,7 +2258,7 @@ static void iommu_enable_ga(struct amd_iommu *iommu) switch (amd_iommu_guest_ir) { case AMD_IOMMU_GUEST_IR_VAPIC: iommu_feature_enable(iommu, CONTROL_GAM_EN); - /* Fall through */ + fallthrough; case AMD_IOMMU_GUEST_IR_LEGACY_GA: iommu_feature_enable(iommu, CONTROL_GA_EN); iommu->irte_ops = &irte_128_ops; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 7196207be7ea..c192544e874b 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -903,7 +903,7 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) break; case CMDQ_OP_CFGI_CD: cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SSID, ent->cfgi.ssid); - /* Fallthrough */ + fallthrough; case CMDQ_OP_CFGI_STE: cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid); cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_LEAF, ent->cfgi.leaf); @@ -936,7 +936,7 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) break; case CMDQ_OP_TLBI_NH_ASID: cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); - /* Fallthrough */ + fallthrough; case CMDQ_OP_TLBI_S12_VMALL: cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); break; @@ -1036,7 +1036,6 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) */ return; case CMDQ_ERR_CERROR_ILL_IDX: - /* Fallthrough */ default: break; } @@ -3758,7 +3757,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) switch (FIELD_GET(IDR0_STALL_MODEL, reg)) { case IDR0_STALL_MODEL_FORCE: smmu->features |= ARM_SMMU_FEAT_STALL_FORCE; - /* Fallthrough */ + fallthrough; case IDR0_STALL_MODEL_STALL: smmu->features |= ARM_SMMU_FEAT_STALLS; } @@ -3778,7 +3777,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) switch (FIELD_GET(IDR0_TTF, reg)) { case IDR0_TTF_AARCH32_64: smmu->ias = 40; - /* Fallthrough */ + fallthrough; case IDR0_TTF_AARCH64: break; default: @@ -3875,7 +3874,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) default: dev_info(smmu->dev, "unknown output address size. Truncating to 48-bit\n"); - /* Fallthrough */ + fallthrough; case IDR5_OAS_48_BIT: smmu->oas = 48; } diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 4959f5df21bd..5141d49a046b 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1035,8 +1035,8 @@ static void *iommu_dma_alloc(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !gfpflags_allow_blocking(gfp) && !coherent) - cpu_addr = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &page, - gfp); + page = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &cpu_addr, + gfp, NULL); else cpu_addr = iommu_dma_alloc_pages(dev, size, &page, gfp, attrs); if (!cpu_addr) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index e9864e52b0e9..f8177c59d229 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -5070,7 +5070,6 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) switch (type) { case IOMMU_DOMAIN_DMA: - /* fallthrough */ case IOMMU_DOMAIN_UNMANAGED: dmar_domain = alloc_domain(0); if (!dmar_domain) { diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index b4da396cce60..2bfdd5734844 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -440,7 +440,7 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev, default: dev_warn(vdev->dev, "unknown resv mem subtype 0x%x\n", mem->subtype); - /* Fall-through */ + fallthrough; case VIRTIO_IOMMU_RESV_MEM_T_RESERVED: region = iommu_alloc_resv_region(start, size, 0, IOMMU_RESV_RESERVED); diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index bb70b7177f94..bfc9719dbcdc 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -425,7 +425,7 @@ config GOLDFISH_PIC for Goldfish based virtual platforms. config QCOM_PDC - tristate "QCOM PDC" + bool "QCOM PDC" depends on ARCH_QCOM select IRQ_DOMAIN_HIERARCHY help diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 95f097448f97..548de7538632 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2737,7 +2737,7 @@ static bool allocate_vpe_l2_table(int cpu, u32 id) switch (gpsz) { default: WARN_ON(1); - /* fall through */ + fallthrough; case GIC_PAGE_SIZE_4K: psz = SZ_4K; break; @@ -2832,7 +2832,7 @@ static int allocate_vpe_l1_table(void) switch (gpsz) { default: gpsz = GIC_PAGE_SIZE_4K; - /* fall through */ + fallthrough; case GIC_PAGE_SIZE_4K: psz = SZ_4K; break; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 324f280ff606..850842f27bee 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -965,10 +965,10 @@ static void gic_cpu_sys_reg_init(void) case 7: write_gicreg(0, ICC_AP0R3_EL1); write_gicreg(0, ICC_AP0R2_EL1); - /* Fall through */ + fallthrough; case 6: write_gicreg(0, ICC_AP0R1_EL1); - /* Fall through */ + fallthrough; case 5: case 4: write_gicreg(0, ICC_AP0R0_EL1); @@ -982,10 +982,10 @@ static void gic_cpu_sys_reg_init(void) case 7: write_gicreg(0, ICC_AP1R3_EL1); write_gicreg(0, ICC_AP1R2_EL1); - /* Fall through */ + fallthrough; case 6: write_gicreg(0, ICC_AP1R1_EL1); - /* Fall through */ + fallthrough; case 5: case 4: write_gicreg(0, ICC_AP1R0_EL1); diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c index 4f74c15c4755..7031ef44de4f 100644 --- a/drivers/irqchip/irq-imx-gpcv2.c +++ b/drivers/irqchip/irq-imx-gpcv2.c @@ -259,7 +259,7 @@ static int __init imx_gpcv2_irqchip_init(struct device_node *node, case 4: writel_relaxed(~0, reg + GPC_IMR1_CORE2); writel_relaxed(~0, reg + GPC_IMR1_CORE3); - /* fall through */ + fallthrough; case 2: writel_relaxed(~0, reg + GPC_IMR1_CORE0); writel_relaxed(~0, reg + GPC_IMR1_CORE1); diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c index 9f3da4260ca6..b61a8901ef72 100644 --- a/drivers/irqchip/irq-ingenic.c +++ b/drivers/irqchip/irq-ingenic.c @@ -125,7 +125,7 @@ static int __init ingenic_intc_of_init(struct device_node *node, irq_reg_writel(gc, IRQ_MSK(32), JZ_REG_INTC_SET_MASK); } - if (request_irq(parent_irq, intc_cascade, 0, + if (request_irq(parent_irq, intc_cascade, IRQF_NO_SUSPEND, "SoC intc cascade interrupt", NULL)) pr_err("Failed to register SoC intc cascade interrupt\n"); return 0; diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index aacfa012c082..215885962bb0 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -480,7 +480,7 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, case GIC_LOCAL_INT_TIMER: /* CONFIG_MIPS_CMP workaround (see __gic_init) */ map = GIC_MAP_PIN_MAP_TO_PIN | timer_cpu_pin; - /* fall-through */ + fallthrough; case GIC_LOCAL_INT_PERFCTR: case GIC_LOCAL_INT_FDC: /* diff --git a/drivers/irqchip/irq-mtk-cirq.c b/drivers/irqchip/irq-mtk-cirq.c index 62a61275aaa3..69ba8ce3c178 100644 --- a/drivers/irqchip/irq-mtk-cirq.c +++ b/drivers/irqchip/irq-mtk-cirq.c @@ -295,6 +295,4 @@ out_free: return ret; } -IRQCHIP_PLATFORM_DRIVER_BEGIN(mtk_cirq) -IRQCHIP_MATCH("mediatek,mtk-cirq", mtk_cirq_of_init) -IRQCHIP_PLATFORM_DRIVER_END(mtk_cirq) +IRQCHIP_DECLARE(mtk_cirq, "mediatek,mtk-cirq", mtk_cirq_of_init); diff --git a/drivers/irqchip/irq-mtk-sysirq.c b/drivers/irqchip/irq-mtk-sysirq.c index 7299c5ab4d10..6ff98b87e5c0 100644 --- a/drivers/irqchip/irq-mtk-sysirq.c +++ b/drivers/irqchip/irq-mtk-sysirq.c @@ -231,6 +231,4 @@ out_free_chip: kfree(chip_data); return ret; } -IRQCHIP_PLATFORM_DRIVER_BEGIN(mtk_sysirq) -IRQCHIP_MATCH("mediatek,mt6577-sysirq", mtk_sysirq_of_init) -IRQCHIP_PLATFORM_DRIVER_END(mtk_sysirq) +IRQCHIP_DECLARE(mtk_sysirq, "mediatek,mt6577-sysirq", mtk_sysirq_of_init); diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 03a36be757d8..0c2c61db26b4 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -416,6 +416,16 @@ static void stm32_irq_ack(struct irq_data *d) irq_gc_unlock(gc); } +/* directly set the target bit without reading first. */ +static inline void stm32_exti_write_bit(struct irq_data *d, u32 reg) +{ + struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d); + void __iomem *base = chip_data->host_data->base; + u32 val = BIT(d->hwirq % IRQS_PER_BANK); + + writel_relaxed(val, base + reg); +} + static inline u32 stm32_exti_set_bit(struct irq_data *d, u32 reg) { struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d); @@ -449,9 +459,9 @@ static void stm32_exti_h_eoi(struct irq_data *d) raw_spin_lock(&chip_data->rlock); - stm32_exti_set_bit(d, stm32_bank->rpr_ofst); + stm32_exti_write_bit(d, stm32_bank->rpr_ofst); if (stm32_bank->fpr_ofst != UNDEF_REG) - stm32_exti_set_bit(d, stm32_bank->fpr_ofst); + stm32_exti_write_bit(d, stm32_bank->fpr_ofst); raw_spin_unlock(&chip_data->rlock); diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index b7cc5d6580d8..d4e97605456b 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -8,6 +8,7 @@ #include <linux/err.h> #include <linux/io.h> +#include <linux/irq.h> #include <linux/irqchip.h> #include <linux/irqdomain.h> #include <linux/interrupt.h> @@ -83,6 +84,7 @@ struct ti_sci_inta_vint_desc { * @vint_mutex: Mutex to protect vint_list * @base: Base address of the memory mapped IO registers * @pdev: Pointer to platform device. + * @ti_sci_id: TI-SCI device identifier */ struct ti_sci_inta_irq_domain { const struct ti_sci_handle *sci; @@ -93,6 +95,7 @@ struct ti_sci_inta_irq_domain { struct mutex vint_mutex; void __iomem *base; struct platform_device *pdev; + u32 ti_sci_id; }; #define to_vint_desc(e, i) container_of(e, struct ti_sci_inta_vint_desc, \ @@ -129,6 +132,37 @@ static void ti_sci_inta_irq_handler(struct irq_desc *desc) } /** + * ti_sci_inta_xlate_irq() - Translate hwirq to parent's hwirq. + * @inta: IRQ domain corresponding to Interrupt Aggregator + * @irq: Hardware irq corresponding to the above irq domain + * + * Return parent irq number if translation is available else -ENOENT. + */ +static int ti_sci_inta_xlate_irq(struct ti_sci_inta_irq_domain *inta, + u16 vint_id) +{ + struct device_node *np = dev_of_node(&inta->pdev->dev); + u32 base, parent_base, size; + const __be32 *range; + int len; + + range = of_get_property(np, "ti,interrupt-ranges", &len); + if (!range) + return vint_id; + + for (len /= sizeof(*range); len >= 3; len -= 3) { + base = be32_to_cpu(*range++); + parent_base = be32_to_cpu(*range++); + size = be32_to_cpu(*range++); + + if (base <= vint_id && vint_id < base + size) + return vint_id - base + parent_base; + } + + return -ENOENT; +} + +/** * ti_sci_inta_alloc_parent_irq() - Allocate parent irq to Interrupt aggregator * @domain: IRQ domain corresponding to Interrupt Aggregator * @@ -139,30 +173,52 @@ static struct ti_sci_inta_vint_desc *ti_sci_inta_alloc_parent_irq(struct irq_dom struct ti_sci_inta_irq_domain *inta = domain->host_data; struct ti_sci_inta_vint_desc *vint_desc; struct irq_fwspec parent_fwspec; + struct device_node *parent_node; unsigned int parent_virq; - u16 vint_id; + u16 vint_id, p_hwirq; + int ret; vint_id = ti_sci_get_free_resource(inta->vint); if (vint_id == TI_SCI_RESOURCE_NULL) return ERR_PTR(-EINVAL); + p_hwirq = ti_sci_inta_xlate_irq(inta, vint_id); + if (p_hwirq < 0) { + ret = p_hwirq; + goto free_vint; + } + vint_desc = kzalloc(sizeof(*vint_desc), GFP_KERNEL); - if (!vint_desc) - return ERR_PTR(-ENOMEM); + if (!vint_desc) { + ret = -ENOMEM; + goto free_vint; + } vint_desc->domain = domain; vint_desc->vint_id = vint_id; INIT_LIST_HEAD(&vint_desc->list); - parent_fwspec.fwnode = of_node_to_fwnode(of_irq_find_parent(dev_of_node(&inta->pdev->dev))); - parent_fwspec.param_count = 2; - parent_fwspec.param[0] = inta->pdev->id; - parent_fwspec.param[1] = vint_desc->vint_id; + parent_node = of_irq_find_parent(dev_of_node(&inta->pdev->dev)); + parent_fwspec.fwnode = of_node_to_fwnode(parent_node); + + if (of_device_is_compatible(parent_node, "arm,gic-v3")) { + /* Parent is GIC */ + parent_fwspec.param_count = 3; + parent_fwspec.param[0] = 0; + parent_fwspec.param[1] = p_hwirq - 32; + parent_fwspec.param[2] = IRQ_TYPE_LEVEL_HIGH; + } else { + /* Parent is Interrupt Router */ + parent_fwspec.param_count = 1; + parent_fwspec.param[0] = p_hwirq; + } parent_virq = irq_create_fwspec_mapping(&parent_fwspec); if (parent_virq == 0) { - kfree(vint_desc); - return ERR_PTR(-EINVAL); + dev_err(&inta->pdev->dev, "Parent IRQ allocation failed\n"); + ret = -EINVAL; + goto free_vint_desc; + } vint_desc->parent_virq = parent_virq; @@ -171,6 +227,11 @@ static struct ti_sci_inta_vint_desc *ti_sci_inta_alloc_parent_irq(struct irq_dom ti_sci_inta_irq_handler, vint_desc); return vint_desc; +free_vint_desc: + kfree(vint_desc); +free_vint: + ti_sci_release_resource(inta->vint, vint_id); + return ERR_PTR(ret); } /** @@ -202,7 +263,7 @@ static struct ti_sci_inta_event_desc *ti_sci_inta_alloc_event(struct ti_sci_inta err = inta->sci->ops.rm_irq_ops.set_event_map(inta->sci, dev_id, dev_index, - inta->pdev->id, + inta->ti_sci_id, vint_desc->vint_id, event_desc->global_event, free_bit); @@ -299,7 +360,7 @@ static void ti_sci_inta_free_irq(struct ti_sci_inta_event_desc *event_desc, inta->sci->ops.rm_irq_ops.free_event_map(inta->sci, HWIRQ_TO_DEVID(hwirq), HWIRQ_TO_IRQID(hwirq), - inta->pdev->id, + inta->ti_sci_id, vint_desc->vint_id, event_desc->global_event, event_desc->vint_bit); @@ -547,21 +608,21 @@ static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev) return ret; } - ret = of_property_read_u32(dev->of_node, "ti,sci-dev-id", &pdev->id); + ret = of_property_read_u32(dev->of_node, "ti,sci-dev-id", &inta->ti_sci_id); if (ret) { dev_err(dev, "missing 'ti,sci-dev-id' property\n"); return -EINVAL; } - inta->vint = devm_ti_sci_get_of_resource(inta->sci, dev, pdev->id, - "ti,sci-rm-range-vint"); + inta->vint = devm_ti_sci_get_resource(inta->sci, dev, inta->ti_sci_id, + TI_SCI_RESASG_SUBTYPE_IA_VINT); if (IS_ERR(inta->vint)) { dev_err(dev, "VINT resource allocation failed\n"); return PTR_ERR(inta->vint); } - inta->global_event = devm_ti_sci_get_of_resource(inta->sci, dev, pdev->id, - "ti,sci-rm-range-global-event"); + inta->global_event = devm_ti_sci_get_resource(inta->sci, dev, inta->ti_sci_id, + TI_SCI_RESASG_SUBTYPE_GLOBAL_EVENT_SEVT); if (IS_ERR(inta->global_event)) { dev_err(dev, "Global event resource allocation failed\n"); return PTR_ERR(inta->global_event); @@ -592,6 +653,8 @@ static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev) INIT_LIST_HEAD(&inta->vint_list); mutex_init(&inta->vint_mutex); + dev_info(dev, "Interrupt Aggregator domain %d created\n", pdev->id); + return 0; } diff --git a/drivers/irqchip/irq-ti-sci-intr.c b/drivers/irqchip/irq-ti-sci-intr.c index 5ea148faf2ab..cbc1758228d9 100644 --- a/drivers/irqchip/irq-ti-sci-intr.c +++ b/drivers/irqchip/irq-ti-sci-intr.c @@ -17,29 +17,20 @@ #include <linux/of_irq.h> #include <linux/soc/ti/ti_sci_protocol.h> -#define TI_SCI_DEV_ID_MASK 0xffff -#define TI_SCI_DEV_ID_SHIFT 16 -#define TI_SCI_IRQ_ID_MASK 0xffff -#define TI_SCI_IRQ_ID_SHIFT 0 -#define HWIRQ_TO_DEVID(hwirq) (((hwirq) >> (TI_SCI_DEV_ID_SHIFT)) & \ - (TI_SCI_DEV_ID_MASK)) -#define HWIRQ_TO_IRQID(hwirq) ((hwirq) & (TI_SCI_IRQ_ID_MASK)) -#define TO_HWIRQ(dev, index) ((((dev) & TI_SCI_DEV_ID_MASK) << \ - TI_SCI_DEV_ID_SHIFT) | \ - ((index) & TI_SCI_IRQ_ID_MASK)) - /** * struct ti_sci_intr_irq_domain - Structure representing a TISCI based * Interrupt Router IRQ domain. * @sci: Pointer to TISCI handle - * @dst_irq: TISCI resource pointer representing GIC irq controller. - * @dst_id: TISCI device ID of the GIC irq controller. + * @out_irqs: TISCI resource pointer representing INTR irqs. + * @dev: Struct device pointer. + * @ti_sci_id: TI-SCI device identifier * @type: Specifies the trigger type supported by this Interrupt Router */ struct ti_sci_intr_irq_domain { const struct ti_sci_handle *sci; - struct ti_sci_resource *dst_irq; - u32 dst_id; + struct ti_sci_resource *out_irqs; + struct device *dev; + u32 ti_sci_id; u32 type; }; @@ -70,16 +61,45 @@ static int ti_sci_intr_irq_domain_translate(struct irq_domain *domain, { struct ti_sci_intr_irq_domain *intr = domain->host_data; - if (fwspec->param_count != 2) + if (fwspec->param_count != 1) return -EINVAL; - *hwirq = TO_HWIRQ(fwspec->param[0], fwspec->param[1]); + *hwirq = fwspec->param[0]; *type = intr->type; return 0; } /** + * ti_sci_intr_xlate_irq() - Translate hwirq to parent's hwirq. + * @intr: IRQ domain corresponding to Interrupt Router + * @irq: Hardware irq corresponding to the above irq domain + * + * Return parent irq number if translation is available else -ENOENT. + */ +static int ti_sci_intr_xlate_irq(struct ti_sci_intr_irq_domain *intr, u32 irq) +{ + struct device_node *np = dev_of_node(intr->dev); + u32 base, pbase, size, len; + const __be32 *range; + + range = of_get_property(np, "ti,interrupt-ranges", &len); + if (!range) + return irq; + + for (len /= sizeof(*range); len >= 3; len -= 3) { + base = be32_to_cpu(*range++); + pbase = be32_to_cpu(*range++); + size = be32_to_cpu(*range++); + + if (base <= irq && irq < base + size) + return irq - base + pbase; + } + + return -ENOENT; +} + +/** * ti_sci_intr_irq_domain_free() - Free the specified IRQs from the domain. * @domain: Domain to which the irqs belong * @virq: Linux virtual IRQ to be freed. @@ -89,66 +109,76 @@ static void ti_sci_intr_irq_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { struct ti_sci_intr_irq_domain *intr = domain->host_data; - struct irq_data *data, *parent_data; - u16 dev_id, irq_index; + struct irq_data *data; + int out_irq; - parent_data = irq_domain_get_irq_data(domain->parent, virq); data = irq_domain_get_irq_data(domain, virq); - irq_index = HWIRQ_TO_IRQID(data->hwirq); - dev_id = HWIRQ_TO_DEVID(data->hwirq); + out_irq = (uintptr_t)data->chip_data; - intr->sci->ops.rm_irq_ops.free_irq(intr->sci, dev_id, irq_index, - intr->dst_id, parent_data->hwirq); - ti_sci_release_resource(intr->dst_irq, parent_data->hwirq); + intr->sci->ops.rm_irq_ops.free_irq(intr->sci, + intr->ti_sci_id, data->hwirq, + intr->ti_sci_id, out_irq); + ti_sci_release_resource(intr->out_irqs, out_irq); irq_domain_free_irqs_parent(domain, virq, 1); irq_domain_reset_irq_data(data); } /** - * ti_sci_intr_alloc_gic_irq() - Allocate GIC specific IRQ + * ti_sci_intr_alloc_parent_irq() - Allocate parent IRQ * @domain: Pointer to the interrupt router IRQ domain * @virq: Corresponding Linux virtual IRQ number * @hwirq: Corresponding hwirq for the IRQ within this IRQ domain * - * Returns 0 if all went well else appropriate error pointer. + * Returns parent irq if all went well else appropriate error pointer. */ -static int ti_sci_intr_alloc_gic_irq(struct irq_domain *domain, - unsigned int virq, u32 hwirq) +static int ti_sci_intr_alloc_parent_irq(struct irq_domain *domain, + unsigned int virq, u32 hwirq) { struct ti_sci_intr_irq_domain *intr = domain->host_data; + struct device_node *parent_node; struct irq_fwspec fwspec; - u16 dev_id, irq_index; - u16 dst_irq; - int err; - - dev_id = HWIRQ_TO_DEVID(hwirq); - irq_index = HWIRQ_TO_IRQID(hwirq); + u16 out_irq, p_hwirq; + int err = 0; - dst_irq = ti_sci_get_free_resource(intr->dst_irq); - if (dst_irq == TI_SCI_RESOURCE_NULL) + out_irq = ti_sci_get_free_resource(intr->out_irqs); + if (out_irq == TI_SCI_RESOURCE_NULL) return -EINVAL; - fwspec.fwnode = domain->parent->fwnode; - fwspec.param_count = 3; - fwspec.param[0] = 0; /* SPI */ - fwspec.param[1] = dst_irq - 32; /* SPI offset */ - fwspec.param[2] = intr->type; + p_hwirq = ti_sci_intr_xlate_irq(intr, out_irq); + if (p_hwirq < 0) + goto err_irqs; + + parent_node = of_irq_find_parent(dev_of_node(intr->dev)); + fwspec.fwnode = of_node_to_fwnode(parent_node); + + if (of_device_is_compatible(parent_node, "arm,gic-v3")) { + /* Parent is GIC */ + fwspec.param_count = 3; + fwspec.param[0] = 0; /* SPI */ + fwspec.param[1] = p_hwirq - 32; /* SPI offset */ + fwspec.param[2] = intr->type; + } else { + /* Parent is Interrupt Router */ + fwspec.param_count = 1; + fwspec.param[0] = p_hwirq; + } err = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec); if (err) goto err_irqs; - err = intr->sci->ops.rm_irq_ops.set_irq(intr->sci, dev_id, irq_index, - intr->dst_id, dst_irq); + err = intr->sci->ops.rm_irq_ops.set_irq(intr->sci, + intr->ti_sci_id, hwirq, + intr->ti_sci_id, out_irq); if (err) goto err_msg; - return 0; + return p_hwirq; err_msg: irq_domain_free_irqs_parent(domain, virq, 1); err_irqs: - ti_sci_release_resource(intr->dst_irq, dst_irq); + ti_sci_release_resource(intr->out_irqs, out_irq); return err; } @@ -168,18 +198,19 @@ static int ti_sci_intr_irq_domain_alloc(struct irq_domain *domain, struct irq_fwspec *fwspec = data; unsigned long hwirq; unsigned int flags; - int err; + int err, p_hwirq; err = ti_sci_intr_irq_domain_translate(domain, fwspec, &hwirq, &flags); if (err) return err; - err = ti_sci_intr_alloc_gic_irq(domain, virq, hwirq); - if (err) - return err; + p_hwirq = ti_sci_intr_alloc_parent_irq(domain, virq, hwirq); + if (p_hwirq < 0) + return p_hwirq; irq_domain_set_hwirq_and_chip(domain, virq, hwirq, - &ti_sci_intr_irq_chip, NULL); + &ti_sci_intr_irq_chip, + (void *)(uintptr_t)p_hwirq); return 0; } @@ -214,6 +245,7 @@ static int ti_sci_intr_irq_domain_probe(struct platform_device *pdev) if (!intr) return -ENOMEM; + intr->dev = dev; ret = of_property_read_u32(dev_of_node(dev), "ti,intr-trigger-type", &intr->type); if (ret) { @@ -230,19 +262,19 @@ static int ti_sci_intr_irq_domain_probe(struct platform_device *pdev) return ret; } - ret = of_property_read_u32(dev_of_node(dev), "ti,sci-dst-id", - &intr->dst_id); + ret = of_property_read_u32(dev_of_node(dev), "ti,sci-dev-id", + &intr->ti_sci_id); if (ret) { - dev_err(dev, "missing 'ti,sci-dst-id' property\n"); + dev_err(dev, "missing 'ti,sci-dev-id' property\n"); return -EINVAL; } - intr->dst_irq = devm_ti_sci_get_of_resource(intr->sci, dev, - intr->dst_id, - "ti,sci-rm-range-girq"); - if (IS_ERR(intr->dst_irq)) { + intr->out_irqs = devm_ti_sci_get_resource(intr->sci, dev, + intr->ti_sci_id, + TI_SCI_RESASG_SUBTYPE_IR_OUTPUT); + if (IS_ERR(intr->out_irqs)) { dev_err(dev, "Destination irq resource allocation failed\n"); - return PTR_ERR(intr->dst_irq); + return PTR_ERR(intr->out_irqs); } domain = irq_domain_add_hierarchy(parent_domain, 0, 0, dev_of_node(dev), @@ -252,6 +284,8 @@ static int ti_sci_intr_irq_domain_probe(struct platform_device *pdev) return -ENOMEM; } + dev_info(dev, "Interrupt Router %d domain created\n", intr->ti_sci_id); + return 0; } diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c index bc235db8a4c5..e46036374227 100644 --- a/drivers/irqchip/irq-vic.c +++ b/drivers/irqchip/irq-vic.c @@ -455,7 +455,7 @@ static void __init __vic_init(void __iomem *base, int parent_irq, int irq_start, return; default: printk(KERN_WARNING "VIC: unknown vendor, continuing anyways\n"); - /* fall through */ + fallthrough; case AMBA_VENDOR_ARM: break; } diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c index 1bb0e36c2bf3..d2341153e181 100644 --- a/drivers/irqchip/irqchip.c +++ b/drivers/irqchip/irqchip.c @@ -52,7 +52,7 @@ int platform_irqchip_probe(struct platform_device *pdev) * interrupt controller. The actual initialization callback of this * interrupt controller can check for specific domains as necessary. */ - if (par_np && !irq_find_matching_host(np, DOMAIN_BUS_ANY)) + if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY)) return -EPROBE_DEFER; return irq_init_cb(np, par_np); diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c index c1c5dfad57cc..6ae9e1f0819d 100644 --- a/drivers/irqchip/qcom-pdc.c +++ b/drivers/irqchip/qcom-pdc.c @@ -11,11 +11,9 @@ #include <linux/irqdomain.h> #include <linux/io.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_device.h> -#include <linux/of_irq.h> #include <linux/soc/qcom/irq.h> #include <linux/spinlock.h> #include <linux/slab.h> @@ -432,8 +430,4 @@ fail: return ret; } -IRQCHIP_PLATFORM_DRIVER_BEGIN(qcom_pdc) -IRQCHIP_MATCH("qcom,pdc", qcom_pdc_init) -IRQCHIP_PLATFORM_DRIVER_END(qcom_pdc) -MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Power Domain Controller"); -MODULE_LICENSE("GPL v2"); +IRQCHIP_DECLARE(qcom_pdc, "qcom,pdc", qcom_pdc_init); diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c index ecc1ef6c386d..f68569bfef7a 100644 --- a/drivers/isdn/hardware/mISDN/avmfritz.c +++ b/drivers/isdn/hardware/mISDN/avmfritz.c @@ -348,7 +348,7 @@ modehdlc(struct bchannel *bch, int protocol) switch (protocol) { case -1: /* used for init */ bch->state = -1; - /* fall through */ + fallthrough; case ISDN_P_NONE: if (bch->state == ISDN_P_NONE) break; diff --git a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h index b0d772340e16..448ded8f9d24 100644 --- a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h +++ b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h @@ -121,7 +121,6 @@ setup_embedded(struct hfc_multi *hc, struct hm_map *m) case HFC_IO_MODE_EMBSD: test_and_set_bit(HFC_CHIP_EMBSD, &hc->chip); hc->slots = 128; /* required */ - /* fall through */ hc->HFC_outb = HFC_outb_embsd; hc->HFC_inb = HFC_inb_embsd; hc->HFC_inw = HFC_inw_embsd; diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index 904a4f4c5ff9..56bd2e9db6ed 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -1280,7 +1280,7 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol) case (-1): /* used for init */ bch->state = -1; bch->nr = bc; - /* fall through */ + fallthrough; case (ISDN_P_NONE): if (bch->state == ISDN_P_NONE) return 0; diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 4274906f8654..70061991915a 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -695,7 +695,7 @@ hfcsusb_setup_bch(struct bchannel *bch, int protocol) switch (protocol) { case (-1): /* used for init */ bch->state = -1; - /* fall through */ + fallthrough; case (ISDN_P_NONE): if (bch->state == ISDN_P_NONE) return 0; /* already in idle state */ diff --git a/drivers/isdn/hardware/mISDN/isdnhdlc.c b/drivers/isdn/hardware/mISDN/isdnhdlc.c index 9fea16ed3dd8..985367e6711d 100644 --- a/drivers/isdn/hardware/mISDN/isdnhdlc.c +++ b/drivers/isdn/hardware/mISDN/isdnhdlc.c @@ -397,7 +397,7 @@ int isdnhdlc_encode(struct isdnhdlc_vars *hdlc, const u8 *src, u16 slen, dsize--; break; } - /* fall through */ + fallthrough; case HDLC_SENDFLAG_ONE: if (hdlc->bit_shift == 8) { hdlc->cbin = hdlc->ffvalue >> diff --git a/drivers/isdn/hardware/mISDN/mISDNinfineon.c b/drivers/isdn/hardware/mISDN/mISDNinfineon.c index f4cb29766888..a16c7a2a7f3d 100644 --- a/drivers/isdn/hardware/mISDN/mISDNinfineon.c +++ b/drivers/isdn/hardware/mISDN/mISDNinfineon.c @@ -875,7 +875,7 @@ release_card(struct inf_hw *card) { release_card(card->sc[i]); card->sc[i] = NULL; } - /* fall through */ + fallthrough; default: pci_disable_device(card->pdev); pci_set_drvdata(card->pdev, NULL); diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c index 11e8c7d8b6e8..56943409b60d 100644 --- a/drivers/isdn/hardware/mISDN/mISDNisar.c +++ b/drivers/isdn/hardware/mISDN/mISDNisar.c @@ -957,7 +957,7 @@ isar_pump_statev_fax(struct isar_ch *ch, u8 devt) { break; case PCTRL_CMD_FTM: p1 = 2; - /* fall through */ + fallthrough; case PCTRL_CMD_FTH: send_mbox(ch->is, dps | ISAR_HIS_PUMPCTRL, PCTRL_CMD_SILON, 1, &p1); @@ -1163,7 +1163,7 @@ setup_pump(struct isar_ch *ch) { send_mbox(ch->is, dps | ISAR_HIS_PUMPCFG, PMOD_DTMF, 1, param); } - /* fall through */ + fallthrough; case ISDN_P_B_MODEM_ASYNC: ctrl = PMOD_DATAMODEM; if (test_bit(FLG_ORIGIN, &ch->bch.Flags)) { @@ -1255,7 +1255,7 @@ setup_iom2(struct isar_ch *ch) { case ISDN_P_B_MODEM_ASYNC: case ISDN_P_B_T30_FAX: cmsb |= IOM_CTRL_RCV; - /* fall through */ + fallthrough; case ISDN_P_B_L2DTMF: if (test_bit(FLG_DTMFSEND, &ch->bch.Flags)) cmsb |= IOM_CTRL_RCV; @@ -1548,7 +1548,7 @@ isar_l2l1(struct mISDNchannel *ch, struct sk_buff *skb) ich->is->name, hh->id); ret = -EINVAL; } - /* fall through */ + fallthrough; default: pr_info("%s: %s unknown prim(%x,%x)\n", ich->is->name, __func__, hh->prim, hh->id); diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c index 27aa32914425..c2f76f398613 100644 --- a/drivers/isdn/mISDN/stack.c +++ b/drivers/isdn/mISDN/stack.c @@ -528,7 +528,7 @@ create_l2entity(struct mISDNdevice *dev, struct mISDNchannel *ch, rq.protocol = ISDN_P_NT_S0; if (dev->Dprotocols & (1 << ISDN_P_NT_E1)) rq.protocol = ISDN_P_NT_E1; - /* fall through */ + fallthrough; case ISDN_P_LAPD_TE: ch->recv = mISDN_queue_message; ch->peer = &dev->D.st->own; diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c index b413bafe93fd..97c68731406b 100644 --- a/drivers/lightnvm/pblk-core.c +++ b/drivers/lightnvm/pblk-core.c @@ -301,7 +301,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type) switch (type) { case PBLK_WRITE: kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap); - /* fall through */ + fallthrough; case PBLK_WRITE_INT: pool = &pblk->w_rq_pool; break; diff --git a/drivers/macintosh/adbhid.c b/drivers/macintosh/adbhid.c index 75482eeab2c4..994ba5cb3678 100644 --- a/drivers/macintosh/adbhid.c +++ b/drivers/macintosh/adbhid.c @@ -881,7 +881,7 @@ adbhid_input_register(int id, int default_id, int original_handler_id, } if (hid->name[0]) break; - /* else fall through */ + fallthrough; default: pr_info("Trying to register unknown ADB device to input layer.\n"); diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 23f1f41c8602..96684581a25d 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -852,7 +852,7 @@ int smu_queue_i2c(struct smu_i2c_cmd *cmd) break; case SMU_I2C_TRANSFER_COMBINED: cmd->info.devaddr &= 0xfe; - /* fall through */ + fallthrough; case SMU_I2C_TRANSFER_STDSUB: if (cmd->info.sublen > 3) return -EINVAL; diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 77fbfd52edcf..c1227bdb57e7 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -608,7 +608,7 @@ static void do_journal_discard(struct cache *ca) ca->sb.njournal_buckets; atomic_set(&ja->discard_in_flight, DISCARD_READY); - /* fallthrough */ + fallthrough; case DISCARD_READY: if (ja->discard_idx == ja->last_idx) diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index 62fb917f7a4f..ae380bc3992e 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -33,27 +33,27 @@ int bch_ ## name ## _h(const char *cp, type *res) \ case 'y': \ case 'z': \ u++; \ - /* fall through */ \ + fallthrough; \ case 'e': \ u++; \ - /* fall through */ \ + fallthrough; \ case 'p': \ u++; \ - /* fall through */ \ + fallthrough; \ case 't': \ u++; \ - /* fall through */ \ + fallthrough; \ case 'g': \ u++; \ - /* fall through */ \ + fallthrough; \ case 'm': \ u++; \ - /* fall through */ \ + fallthrough; \ case 'k': \ u++; \ if (e++ == cp) \ return -EINVAL; \ - /* fall through */ \ + fallthrough; \ case '\n': \ case '\0': \ if (*e == '\n') \ diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 151aa95775be..af6d4f898e4c 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -537,12 +537,16 @@ static int __create_persistent_data_objects(struct dm_cache_metadata *cmd, CACHE_MAX_CONCURRENT_LOCKS); if (IS_ERR(cmd->bm)) { DMERR("could not create block manager"); - return PTR_ERR(cmd->bm); + r = PTR_ERR(cmd->bm); + cmd->bm = NULL; + return r; } r = __open_or_format_metadata(cmd, may_format_device); - if (r) + if (r) { dm_block_manager_destroy(cmd->bm); + cmd->bm = NULL; + } return r; } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 148960721254..380386c36921 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -739,7 +739,7 @@ static int crypt_iv_eboiv_gen(struct crypt_config *cc, u8 *iv, u8 buf[MAX_CIPHER_BLOCKSIZE] __aligned(__alignof__(__le64)); struct skcipher_request *req; struct scatterlist src, dst; - struct crypto_wait wait; + DECLARE_CRYPTO_WAIT(wait); int err; req = skcipher_request_alloc(any_tfm(cc), GFP_NOIO); @@ -936,7 +936,7 @@ static int crypt_iv_elephant(struct crypt_config *cc, struct dm_crypt_request *d u8 *es, *ks, *data, *data2, *data_offset; struct skcipher_request *req; struct scatterlist *sg, *sg2, src, dst; - struct crypto_wait wait; + DECLARE_CRYPTO_WAIT(wait); int i, r; req = skcipher_request_alloc(elephant->tfm, GFP_NOIO); @@ -1552,7 +1552,7 @@ static blk_status_t crypt_convert(struct crypt_config *cc, case -EBUSY: wait_for_completion(&ctx->restart); reinit_completion(&ctx->restart); - /* fall through */ + fallthrough; /* * The request is queued and processed asynchronously, * completion function kcryptd_async_done() will be called. diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 8c8d940e532e..3fc3757def55 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -2487,6 +2487,7 @@ next_chunk: range.logical_sector = le64_to_cpu(ic->sb->recalc_sector); if (unlikely(range.logical_sector >= ic->provided_data_sectors)) { if (ic->mode == 'B') { + block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR); DEBUG_print("queue_delayed_work: bitmap_flush_work\n"); queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, 0); } @@ -2564,6 +2565,17 @@ next_chunk: goto err; } + if (ic->mode == 'B') { + sector_t start, end; + start = (range.logical_sector >> + (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit)) << + (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit); + end = ((range.logical_sector + range.n_sectors) >> + (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit)) << + (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit); + block_bitmap_op(ic, ic->recalc_bitmap, start, end - start, BITMAP_OP_CLEAR); + } + advance_and_next: cond_resched(); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 53645a6f474c..de4da825ade6 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1287,17 +1287,25 @@ static void multipath_wait_for_pg_init_completion(struct multipath *m) static void flush_multipath_work(struct multipath *m) { if (m->hw_handler_name) { - set_bit(MPATHF_PG_INIT_DISABLED, &m->flags); - smp_mb__after_atomic(); + unsigned long flags; + + if (!atomic_read(&m->pg_init_in_progress)) + goto skip; + + spin_lock_irqsave(&m->lock, flags); + if (atomic_read(&m->pg_init_in_progress) && + !test_and_set_bit(MPATHF_PG_INIT_DISABLED, &m->flags)) { + spin_unlock_irqrestore(&m->lock, flags); - if (atomic_read(&m->pg_init_in_progress)) flush_workqueue(kmpath_handlerd); - multipath_wait_for_pg_init_completion(m); + multipath_wait_for_pg_init_completion(m); - clear_bit(MPATHF_PG_INIT_DISABLED, &m->flags); - smp_mb__after_atomic(); + spin_lock_irqsave(&m->lock, flags); + clear_bit(MPATHF_PG_INIT_DISABLED, &m->flags); + } + spin_unlock_irqrestore(&m->lock, flags); } - +skip: if (m->queue_mode == DM_TYPE_BIO_BASED) flush_work(&m->process_queued_bios); flush_work(&m->trigger_event); @@ -1554,7 +1562,7 @@ static void pg_init_done(void *data, int errors) case SCSI_DH_RETRY: /* Wait before retrying. */ delay_retry = true; - /* fall through */ + fallthrough; case SCSI_DH_IMM_RETRY: case SCSI_DH_RES_TEMP_UNAVAIL: if (pg_init_limit_reached(m, pgpath)) diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 76b6b323bf4b..b461836b6d26 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -739,12 +739,16 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f THIN_MAX_CONCURRENT_LOCKS); if (IS_ERR(pmd->bm)) { DMERR("could not create block manager"); - return PTR_ERR(pmd->bm); + r = PTR_ERR(pmd->bm); + pmd->bm = NULL; + return r; } r = __open_or_format_metadata(pmd, format_device); - if (r) + if (r) { dm_block_manager_destroy(pmd->bm); + pmd->bm = NULL; + } return r; } @@ -954,7 +958,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd) } pmd_write_lock_in_core(pmd); - if (!dm_bm_is_read_only(pmd->bm) && !pmd->fail_io) { + if (!pmd->fail_io && !dm_bm_is_read_only(pmd->bm)) { r = __commit_transaction(pmd); if (r < 0) DMWARN("%s: __commit_transaction() failed, error = %d", diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 86dbe0c8b45c..6271d1e741cf 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -231,6 +231,7 @@ static int persistent_memory_claim(struct dm_writecache *wc) pfn_t pfn; int id; struct page **pages; + sector_t offset; wc->memory_vmapped = false; @@ -245,9 +246,16 @@ static int persistent_memory_claim(struct dm_writecache *wc) goto err1; } + offset = get_start_sect(wc->ssd_dev->bdev); + if (offset & (PAGE_SIZE / 512 - 1)) { + r = -EINVAL; + goto err1; + } + offset >>= PAGE_SHIFT - 9; + id = dax_read_lock(); - da = dax_direct_access(wc->ssd_dev->dax_dev, 0, p, &wc->memory_map, &pfn); + da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, &wc->memory_map, &pfn); if (da < 0) { wc->memory_map = NULL; r = da; @@ -269,7 +277,7 @@ static int persistent_memory_claim(struct dm_writecache *wc) i = 0; do { long daa; - daa = dax_direct_access(wc->ssd_dev->dax_dev, i, p - i, + daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i, p - i, NULL, &pfn); if (daa <= 0) { r = daa ? daa : -EINVAL; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 32fa6499739f..fb0255d25e4b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1021,7 +1021,7 @@ static void clone_endio(struct bio *bio) switch (r) { case DM_ENDIO_REQUEUE: error = BLK_STS_DM_REQUEUE; - /*FALLTHRU*/ + fallthrough; case DM_ENDIO_DONE: break; case DM_ENDIO_INCOMPLETE: diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index 6bbec89976a7..2cf973722f59 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -102,10 +102,10 @@ static int __init md_setup(char *str) pername = "raid0"; break; } - /* FALL THROUGH */ + fallthrough; case 1: /* the first device is numeric */ str = str1; - /* FALL THROUGH */ + fallthrough; case 0: md_setup_args[ent].level = LEVEL_NONE; pername="super-block"; diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index d61b524ae440..b10c51988c8e 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -1433,7 +1433,7 @@ int md_bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long s case 0: md_bitmap_file_set_bit(bitmap, offset); md_bitmap_count_page(&bitmap->counts, offset, 1); - /* fall through */ + fallthrough; case 1: *bmc = 2; } diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 749ec268d957..54c089a50b15 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -493,7 +493,7 @@ int dm_bm_write_lock(struct dm_block_manager *bm, void *p; int r; - if (bm->read_only) + if (dm_bm_is_read_only(bm)) return -EPERM; p = dm_bufio_read(bm->bufio, b, (struct dm_buffer **) result); @@ -562,7 +562,7 @@ int dm_bm_write_lock_zero(struct dm_block_manager *bm, struct buffer_aux *aux; void *p; - if (bm->read_only) + if (dm_bm_is_read_only(bm)) return -EPERM; p = dm_bufio_new(bm->bufio, b, (struct dm_buffer **) result); @@ -602,7 +602,7 @@ EXPORT_SYMBOL_GPL(dm_bm_unlock); int dm_bm_flush(struct dm_block_manager *bm) { - if (bm->read_only) + if (dm_bm_is_read_only(bm)) return -EPERM; return dm_bufio_write_dirty_buffers(bm->bufio); @@ -616,19 +616,21 @@ void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b) bool dm_bm_is_read_only(struct dm_block_manager *bm) { - return bm->read_only; + return (bm ? bm->read_only : true); } EXPORT_SYMBOL_GPL(dm_bm_is_read_only); void dm_bm_set_read_only(struct dm_block_manager *bm) { - bm->read_only = true; + if (bm) + bm->read_only = true; } EXPORT_SYMBOL_GPL(dm_bm_set_read_only); void dm_bm_set_read_write(struct dm_block_manager *bm) { - bm->read_only = false; + if (bm) + bm->read_only = false; } EXPORT_SYMBOL_GPL(dm_bm_set_read_write); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ef0fd4830803..225380efd1e2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4083,7 +4083,7 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, break; } dev = &sh->dev[s->failed_num[0]]; - /* fall through */ + fallthrough; case check_state_compute_result: sh->check_state = check_state_idle; if (!dev) @@ -4214,7 +4214,7 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, /* we have 2-disk failure */ BUG_ON(s->failed != 2); - /* fall through */ + fallthrough; case check_state_compute_result: sh->check_state = check_state_idle; @@ -6514,9 +6514,12 @@ raid5_store_stripe_size(struct mddev *mddev, const char *page, size_t len) /* * The value should not be bigger than PAGE_SIZE. It requires to - * be multiple of DEFAULT_STRIPE_SIZE. + * be multiple of DEFAULT_STRIPE_SIZE and the value should be power + * of two. */ - if (new % DEFAULT_STRIPE_SIZE != 0 || new > PAGE_SIZE || new == 0) + if (new % DEFAULT_STRIPE_SIZE != 0 || + new > PAGE_SIZE || new == 0 || + new != roundup_pow_of_two(new)) return -EINVAL; err = mddev_lock(mddev); diff --git a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c index 630a75e0eeb1..7607b516a7c4 100644 --- a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c +++ b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c @@ -210,7 +210,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc) tpg->vdownsampling[1] = 1; tpg->hdownsampling[1] = 1; tpg->planes = 2; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_RGB332: case V4L2_PIX_FMT_RGB565: case V4L2_PIX_FMT_RGB565X: @@ -271,7 +271,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc) case V4L2_PIX_FMT_YUV420M: case V4L2_PIX_FMT_YVU420M: tpg->buffers = 3; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_YUV420: case V4L2_PIX_FMT_YVU420: tpg->vdownsampling[1] = 2; @@ -284,7 +284,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc) case V4L2_PIX_FMT_YUV422M: case V4L2_PIX_FMT_YVU422M: tpg->buffers = 3; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_YUV422P: tpg->vdownsampling[1] = 1; tpg->vdownsampling[2] = 1; @@ -296,7 +296,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc) case V4L2_PIX_FMT_NV16M: case V4L2_PIX_FMT_NV61M: tpg->buffers = 2; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_NV16: case V4L2_PIX_FMT_NV61: tpg->vdownsampling[1] = 1; @@ -308,7 +308,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc) case V4L2_PIX_FMT_NV12M: case V4L2_PIX_FMT_NV21M: tpg->buffers = 2; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: tpg->vdownsampling[1] = 2; @@ -1275,7 +1275,7 @@ static void gen_twopix(struct tpg_data *tpg, case V4L2_PIX_FMT_RGB444: case V4L2_PIX_FMT_XRGB444: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_YUV444: case V4L2_PIX_FMT_ARGB444: buf[0][offset] = (g_u_s << 4) | b_v; @@ -1283,21 +1283,21 @@ static void gen_twopix(struct tpg_data *tpg, break; case V4L2_PIX_FMT_RGBX444: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_RGBA444: buf[0][offset] = (b_v << 4) | (alpha >> 4); buf[0][offset + 1] = (r_y_h << 4) | g_u_s; break; case V4L2_PIX_FMT_XBGR444: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_ABGR444: buf[0][offset] = (g_u_s << 4) | r_y_h; buf[0][offset + 1] = (alpha & 0xf0) | b_v; break; case V4L2_PIX_FMT_BGRX444: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_BGRA444: buf[0][offset] = (r_y_h << 4) | (alpha >> 4); buf[0][offset + 1] = (b_v << 4) | g_u_s; @@ -1305,7 +1305,7 @@ static void gen_twopix(struct tpg_data *tpg, case V4L2_PIX_FMT_RGB555: case V4L2_PIX_FMT_XRGB555: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_YUV555: case V4L2_PIX_FMT_ARGB555: buf[0][offset] = (g_u_s << 5) | b_v; @@ -1314,7 +1314,7 @@ static void gen_twopix(struct tpg_data *tpg, break; case V4L2_PIX_FMT_RGBX555: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_RGBA555: buf[0][offset] = (g_u_s << 6) | (b_v << 1) | ((alpha & 0x80) >> 7); @@ -1322,7 +1322,7 @@ static void gen_twopix(struct tpg_data *tpg, break; case V4L2_PIX_FMT_XBGR555: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_ABGR555: buf[0][offset] = (g_u_s << 5) | r_y_h; buf[0][offset + 1] = (alpha & 0x80) | (b_v << 2) @@ -1330,7 +1330,7 @@ static void gen_twopix(struct tpg_data *tpg, break; case V4L2_PIX_FMT_BGRX555: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_BGRA555: buf[0][offset] = (g_u_s << 6) | (r_y_h << 1) | ((alpha & 0x80) >> 7); @@ -1339,7 +1339,7 @@ static void gen_twopix(struct tpg_data *tpg, case V4L2_PIX_FMT_RGB555X: case V4L2_PIX_FMT_XRGB555X: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_ARGB555X: buf[0][offset] = (alpha & 0x80) | (r_y_h << 2) | (g_u_s >> 3); buf[0][offset + 1] = (g_u_s << 5) | b_v; @@ -1366,7 +1366,7 @@ static void gen_twopix(struct tpg_data *tpg, case V4L2_PIX_FMT_HSV32: case V4L2_PIX_FMT_XYUV32: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_YUV32: case V4L2_PIX_FMT_ARGB32: case V4L2_PIX_FMT_AYUV32: @@ -1377,7 +1377,7 @@ static void gen_twopix(struct tpg_data *tpg, break; case V4L2_PIX_FMT_RGBX32: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_RGBA32: buf[0][offset] = r_y_h; buf[0][offset + 1] = g_u_s; @@ -1388,7 +1388,7 @@ static void gen_twopix(struct tpg_data *tpg, case V4L2_PIX_FMT_XBGR32: case V4L2_PIX_FMT_VUYX32: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_ABGR32: case V4L2_PIX_FMT_VUYA32: buf[0][offset] = b_v; @@ -1398,7 +1398,7 @@ static void gen_twopix(struct tpg_data *tpg, break; case V4L2_PIX_FMT_BGRX32: alpha = 0; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_BGRA32: buf[0][offset] = alpha; buf[0][offset + 1] = b_v; diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index 630509ecee20..89620da983ba 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -546,7 +546,7 @@ static int dvb_net_ule_new_payload(struct dvb_net_ule_handle *h) h->priv->ule_sndu_type_1 = 1; h->ts_remain -= 1; h->from_where += 1; - /* fallthrough */ + fallthrough; case 0: h->new_ts = 1; h->ts += TS_SZ; diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c index e92542b92d34..da0ff7b44da4 100644 --- a/drivers/media/dvb-frontends/bcm3510.c +++ b/drivers/media/dvb-frontends/bcm3510.c @@ -773,7 +773,7 @@ static int bcm3510_init(struct dvb_frontend* fe) deb_info("attempting to download firmware\n"); if ((ret = bcm3510_init_cold(st)) < 0) return ret; - /* fall-through */ + fallthrough; case JDEC_EEPROM_LOAD_WAIT: deb_info("firmware is loaded\n"); bcm3510_check_firmware_version(st); diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c index bc374750529b..08a85831e917 100644 --- a/drivers/media/dvb-frontends/dib0090.c +++ b/drivers/media/dvb-frontends/dib0090.c @@ -1693,7 +1693,7 @@ static int dib0090_dc_offset_calibration(struct dib0090_state *state, enum front if (state->identity.p1g) state->dc = dc_p1g_table; - /* fall through */ + fallthrough; case CT_TUNER_STEP_0: dprintk("Start/continue DC calibration for %s path\n", (state->dc->i == 1) ? "I" : "Q"); diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c index 0f0480d8576d..a6c2fc4586eb 100644 --- a/drivers/media/dvb-frontends/dib3000mb.c +++ b/drivers/media/dvb-frontends/dib3000mb.c @@ -224,7 +224,7 @@ static int dib3000mb_set_frontend(struct dvb_frontend *fe, int tuner) switch (c->hierarchy) { case HIERARCHY_NONE: deb_setf("hierarchy: none\n"); - /* fall through */ + fallthrough; case HIERARCHY_1: deb_setf("hierarchy: alpha=1\n"); wr(DIB3000MB_REG_VIT_ALPHA, DIB3000_ALPHA_1); diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c index 0a7790c4bad3..55bee50aa871 100644 --- a/drivers/media/dvb-frontends/dib7000p.c +++ b/drivers/media/dvb-frontends/dib7000p.c @@ -276,7 +276,7 @@ static int dib7000p_set_power_mode(struct dib7000p_state *state, enum dib7000p_p if (state->version != SOC7090) reg_1280 &= ~((1 << 11)); reg_1280 &= ~(1 << 6); - /* fall-through */ + fallthrough; case DIB7000P_POWER_INTERFACE_ONLY: /* just leave power on the control-interfaces: GPIO and (I2C or SDIO) */ /* TODO power up either SDIO or I2C */ diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c index 5de016412c42..237b9d04c076 100644 --- a/drivers/media/dvb-frontends/drx39xyj/drxj.c +++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c @@ -2306,7 +2306,7 @@ hi_command(struct i2c_device_addr *dev_addr, const struct drxj_hi_cmd *cmd, u16 pr_err("error %d\n", rc); goto rw_error; } - /* fallthrough */ + fallthrough; case SIO_HI_RA_RAM_CMD_BRDCTRL: rc = drxj_dap_write_reg16(dev_addr, SIO_HI_RA_RAM_PAR_2__A, cmd->param2, 0); if (rc != 0) { @@ -2318,7 +2318,7 @@ hi_command(struct i2c_device_addr *dev_addr, const struct drxj_hi_cmd *cmd, u16 pr_err("error %d\n", rc); goto rw_error; } - /* fallthrough */ + fallthrough; case SIO_HI_RA_RAM_CMD_NULL: /* No parameters */ break; @@ -2841,7 +2841,7 @@ ctrl_set_cfg_mpeg_output(struct drx_demod_instance *demod, struct drx_cfg_mpeg_o /* coef = 188/204 */ max_bit_rate = (ext_attr->curr_symbol_rate / 8) * nr_bits * 188; - /* fall-through - as b/c Annex A/C need following settings */ + fallthrough; /* as b/c Annex A/C need following settings */ case DRX_STANDARD_ITU_B: rc = drxj_dap_write_reg16(dev_addr, FEC_OC_FCT_USAGE__A, FEC_OC_FCT_USAGE__PRE, 0); if (rc != 0) { @@ -3555,8 +3555,8 @@ static int ctrl_set_uio_cfg(struct drx_demod_instance *demod, struct drxuio_cfg if (!ext_attr->has_smatx) return -EIO; switch (uio_cfg->mode) { - case DRX_UIO_MODE_FIRMWARE_SMA: /* fall through */ - case DRX_UIO_MODE_FIRMWARE_SAW: /* fall through */ + case DRX_UIO_MODE_FIRMWARE_SMA: + case DRX_UIO_MODE_FIRMWARE_SAW: case DRX_UIO_MODE_READWRITE: ext_attr->uio_sma_tx_mode = uio_cfg->mode; break; @@ -3579,7 +3579,7 @@ static int ctrl_set_uio_cfg(struct drx_demod_instance *demod, struct drxuio_cfg if (!ext_attr->has_smarx) return -EIO; switch (uio_cfg->mode) { - case DRX_UIO_MODE_FIRMWARE0: /* fall through */ + case DRX_UIO_MODE_FIRMWARE0: case DRX_UIO_MODE_READWRITE: ext_attr->uio_sma_rx_mode = uio_cfg->mode; break; @@ -3603,7 +3603,7 @@ static int ctrl_set_uio_cfg(struct drx_demod_instance *demod, struct drxuio_cfg if (!ext_attr->has_gpio) return -EIO; switch (uio_cfg->mode) { - case DRX_UIO_MODE_FIRMWARE0: /* fall through */ + case DRX_UIO_MODE_FIRMWARE0: case DRX_UIO_MODE_READWRITE: ext_attr->uio_gpio_mode = uio_cfg->mode; break; @@ -3639,7 +3639,7 @@ static int ctrl_set_uio_cfg(struct drx_demod_instance *demod, struct drxuio_cfg } ext_attr->uio_irqn_mode = uio_cfg->mode; break; - case DRX_UIO_MODE_FIRMWARE0: /* fall through */ + case DRX_UIO_MODE_FIRMWARE0: default: return -EINVAL; break; @@ -4004,31 +4004,36 @@ static int scu_command(struct i2c_device_addr *dev_addr, struct drxjscu_cmd *cmd if (rc != 0) { pr_err("error %d\n", rc); goto rw_error; - } /* fallthrough */ + } + fallthrough; case 4: rc = drxj_dap_write_reg16(dev_addr, SCU_RAM_PARAM_3__A, *(cmd->parameter + 3), 0); if (rc != 0) { pr_err("error %d\n", rc); goto rw_error; - } /* fallthrough */ + } + fallthrough; case 3: rc = drxj_dap_write_reg16(dev_addr, SCU_RAM_PARAM_2__A, *(cmd->parameter + 2), 0); if (rc != 0) { pr_err("error %d\n", rc); goto rw_error; - } /* fallthrough */ + } + fallthrough; case 2: rc = drxj_dap_write_reg16(dev_addr, SCU_RAM_PARAM_1__A, *(cmd->parameter + 1), 0); if (rc != 0) { pr_err("error %d\n", rc); goto rw_error; - } /* fallthrough */ + } + fallthrough; case 1: rc = drxj_dap_write_reg16(dev_addr, SCU_RAM_PARAM_0__A, *(cmd->parameter + 0), 0); if (rc != 0) { pr_err("error %d\n", rc); goto rw_error; - } /* fallthrough */ + } + fallthrough; case 0: /* do nothing */ break; @@ -4068,25 +4073,29 @@ static int scu_command(struct i2c_device_addr *dev_addr, struct drxjscu_cmd *cmd if (rc != 0) { pr_err("error %d\n", rc); goto rw_error; - } /* fallthrough */ + } + fallthrough; case 3: rc = drxj_dap_read_reg16(dev_addr, SCU_RAM_PARAM_2__A, cmd->result + 2, 0); if (rc != 0) { pr_err("error %d\n", rc); goto rw_error; - } /* fallthrough */ + } + fallthrough; case 2: rc = drxj_dap_read_reg16(dev_addr, SCU_RAM_PARAM_1__A, cmd->result + 1, 0); if (rc != 0) { pr_err("error %d\n", rc); goto rw_error; - } /* fallthrough */ + } + fallthrough; case 1: rc = drxj_dap_read_reg16(dev_addr, SCU_RAM_PARAM_0__A, cmd->result + 0, 0); if (rc != 0) { pr_err("error %d\n", rc); goto rw_error; - } /* fallthrough */ + } + fallthrough; case 0: /* do nothing */ break; @@ -4791,7 +4800,7 @@ set_frequency(struct drx_demod_instance *demod, Sound carrier is already 3Mhz above centre frequency due to tuner setting so now add an extra shift of 1MHz... */ fm_frequency_shift = 1000; - /*fall through */ + fallthrough; case DRX_STANDARD_ITU_B: case DRX_STANDARD_NTSC: case DRX_STANDARD_PAL_SECAM_BG: @@ -10475,11 +10484,11 @@ ctrl_set_channel(struct drx_demod_instance *demod, struct drx_channel *channel) (standard == DRX_STANDARD_NTSC)) { switch (channel->bandwidth) { case DRX_BANDWIDTH_6MHZ: - case DRX_BANDWIDTH_UNKNOWN: /* fall through */ + case DRX_BANDWIDTH_UNKNOWN: channel->bandwidth = DRX_BANDWIDTH_6MHZ; break; - case DRX_BANDWIDTH_8MHZ: /* fall through */ - case DRX_BANDWIDTH_7MHZ: /* fall through */ + case DRX_BANDWIDTH_8MHZ: + case DRX_BANDWIDTH_7MHZ: default: return -EINVAL; } @@ -10511,10 +10520,10 @@ ctrl_set_channel(struct drx_demod_instance *demod, struct drx_channel *channel) } switch (channel->constellation) { - case DRX_CONSTELLATION_QAM16: /* fall through */ - case DRX_CONSTELLATION_QAM32: /* fall through */ - case DRX_CONSTELLATION_QAM64: /* fall through */ - case DRX_CONSTELLATION_QAM128: /* fall through */ + case DRX_CONSTELLATION_QAM16: + case DRX_CONSTELLATION_QAM32: + case DRX_CONSTELLATION_QAM64: + case DRX_CONSTELLATION_QAM128: case DRX_CONSTELLATION_QAM256: bandwidth_temp = channel->symbolrate * bw_rolloff_factor; bandwidth = bandwidth_temp / 100; @@ -10628,8 +10637,8 @@ ctrl_set_channel(struct drx_demod_instance *demod, struct drx_channel *channel) } break; #ifndef DRXJ_VSB_ONLY - case DRX_STANDARD_ITU_A: /* fallthrough */ - case DRX_STANDARD_ITU_B: /* fallthrough */ + case DRX_STANDARD_ITU_A: + case DRX_STANDARD_ITU_B: case DRX_STANDARD_ITU_C: rc = set_qam_channel(demod, channel, tuner_freq_offset); if (rc != 0) { @@ -10820,7 +10829,7 @@ ctrl_lock_status(struct drx_demod_instance *demod, enum drx_lock_status *lock_st SCU_RAM_COMMAND_CMD_DEMOD_GET_LOCK; break; #endif - case DRX_STANDARD_UNKNOWN: /* fallthrough */ + case DRX_STANDARD_UNKNOWN: default: return -EIO; } @@ -10888,8 +10897,8 @@ ctrl_set_standard(struct drx_demod_instance *demod, enum drx_standard *standard) */ switch (prev_standard) { #ifndef DRXJ_VSB_ONLY - case DRX_STANDARD_ITU_A: /* fallthrough */ - case DRX_STANDARD_ITU_B: /* fallthrough */ + case DRX_STANDARD_ITU_A: + case DRX_STANDARD_ITU_B: case DRX_STANDARD_ITU_C: rc = power_down_qam(demod, false); if (rc != 0) { @@ -10908,7 +10917,7 @@ ctrl_set_standard(struct drx_demod_instance *demod, enum drx_standard *standard) case DRX_STANDARD_UNKNOWN: /* Do nothing */ break; - case DRX_STANDARD_AUTO: /* fallthrough */ + case DRX_STANDARD_AUTO: default: return -EINVAL; } @@ -10921,8 +10930,8 @@ ctrl_set_standard(struct drx_demod_instance *demod, enum drx_standard *standard) switch (*standard) { #ifndef DRXJ_VSB_ONLY - case DRX_STANDARD_ITU_A: /* fallthrough */ - case DRX_STANDARD_ITU_B: /* fallthrough */ + case DRX_STANDARD_ITU_A: + case DRX_STANDARD_ITU_B: case DRX_STANDARD_ITU_C: do { u16 dummy; @@ -11111,12 +11120,12 @@ ctrl_power_mode(struct drx_demod_instance *demod, enum drx_power_mode *mode) goto rw_error; } break; - case DRX_STANDARD_PAL_SECAM_BG: /* fallthrough */ - case DRX_STANDARD_PAL_SECAM_DK: /* fallthrough */ - case DRX_STANDARD_PAL_SECAM_I: /* fallthrough */ - case DRX_STANDARD_PAL_SECAM_L: /* fallthrough */ - case DRX_STANDARD_PAL_SECAM_LP: /* fallthrough */ - case DRX_STANDARD_NTSC: /* fallthrough */ + case DRX_STANDARD_PAL_SECAM_BG: + case DRX_STANDARD_PAL_SECAM_DK: + case DRX_STANDARD_PAL_SECAM_I: + case DRX_STANDARD_PAL_SECAM_L: + case DRX_STANDARD_PAL_SECAM_LP: + case DRX_STANDARD_NTSC: case DRX_STANDARD_FM: rc = power_down_atv(demod, ext_attr->standard, true); if (rc != 0) { @@ -11127,7 +11136,7 @@ ctrl_power_mode(struct drx_demod_instance *demod, enum drx_power_mode *mode) case DRX_STANDARD_UNKNOWN: /* Do nothing */ break; - case DRX_STANDARD_AUTO: /* fallthrough */ + case DRX_STANDARD_AUTO: default: return -EIO; } @@ -11220,8 +11229,8 @@ ctrl_set_cfg_pre_saw(struct drx_demod_instance *demod, struct drxj_cfg_pre_saw * ext_attr->vsb_pre_saw_cfg = *pre_saw; break; #ifndef DRXJ_VSB_ONLY - case DRX_STANDARD_ITU_A: /* fallthrough */ - case DRX_STANDARD_ITU_B: /* fallthrough */ + case DRX_STANDARD_ITU_A: + case DRX_STANDARD_ITU_B: case DRX_STANDARD_ITU_C: ext_attr->qam_pre_saw_cfg = *pre_saw; break; @@ -11264,10 +11273,10 @@ ctrl_set_cfg_afe_gain(struct drx_demod_instance *demod, struct drxj_cfg_afe_gain ext_attr = (struct drxj_data *) demod->my_ext_attr; switch (afe_gain->standard) { - case DRX_STANDARD_8VSB: /* fallthrough */ + case DRX_STANDARD_8VSB: fallthrough; #ifndef DRXJ_VSB_ONLY - case DRX_STANDARD_ITU_A: /* fallthrough */ - case DRX_STANDARD_ITU_B: /* fallthrough */ + case DRX_STANDARD_ITU_A: + case DRX_STANDARD_ITU_B: case DRX_STANDARD_ITU_C: #endif /* Do nothing */ @@ -11301,8 +11310,8 @@ ctrl_set_cfg_afe_gain(struct drx_demod_instance *demod, struct drxj_cfg_afe_gain ext_attr->vsb_pga_cfg = gain * 13 + 140; break; #ifndef DRXJ_VSB_ONLY - case DRX_STANDARD_ITU_A: /* fallthrough */ - case DRX_STANDARD_ITU_B: /* fallthrough */ + case DRX_STANDARD_ITU_A: + case DRX_STANDARD_ITU_B: case DRX_STANDARD_ITU_C: ext_attr->qam_pga_cfg = gain * 13 + 140; break; diff --git a/drivers/media/dvb-frontends/drxd_hard.c b/drivers/media/dvb-frontends/drxd_hard.c index fae6f3763364..45f982863904 100644 --- a/drivers/media/dvb-frontends/drxd_hard.c +++ b/drivers/media/dvb-frontends/drxd_hard.c @@ -1512,14 +1512,14 @@ static int SetDeviceTypeId(struct drxd_state *state) switch (deviceId) { case 4: state->diversity = 1; - /* fall through */ + fallthrough; case 3: case 7: state->PGA = 1; break; case 6: state->diversity = 1; - /* fall through */ + fallthrough; case 5: case 8: break; @@ -1966,7 +1966,7 @@ static int DRX_Start(struct drxd_state *state, s32 off) switch (p->transmission_mode) { default: /* Not set, detect it automatically */ operationMode |= SC_RA_RAM_OP_AUTO_MODE__M; - /* fall through - try first guess DRX_FFTMODE_8K */ + fallthrough; /* try first guess DRX_FFTMODE_8K */ case TRANSMISSION_MODE_8K: transmissionParams |= SC_RA_RAM_OP_PARAM_MODE_8K; if (state->type_A) { @@ -2139,7 +2139,7 @@ static int DRX_Start(struct drxd_state *state, s32 off) switch (p->modulation) { default: operationMode |= SC_RA_RAM_OP_AUTO_CONST__M; - /* fall through - try first guess DRX_CONSTELLATION_QAM64 */ + fallthrough; /* try first guess DRX_CONSTELLATION_QAM64 */ case QAM_64: transmissionParams |= SC_RA_RAM_OP_PARAM_CONST_QAM64; if (state->type_A) { @@ -2266,7 +2266,7 @@ static int DRX_Start(struct drxd_state *state, s32 off) break; default: operationMode |= SC_RA_RAM_OP_AUTO_RATE__M; - /* fall through */ + fallthrough; case FEC_2_3: transmissionParams |= SC_RA_RAM_OP_PARAM_RATE_2_3; if (state->type_A) @@ -2301,7 +2301,7 @@ static int DRX_Start(struct drxd_state *state, s32 off) switch (p->bandwidth_hz) { case 0: p->bandwidth_hz = 8000000; - /* fall through */ + fallthrough; case 8000000: /* (64/7)*(8/8)*1000000 */ bandwidth = DRXD_BANDWIDTH_8MHZ_IN_HZ; diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c index 0ae9d8c72d8d..32f9346deb3e 100644 --- a/drivers/media/dvb-frontends/drxk_hard.c +++ b/drivers/media/dvb-frontends/drxk_hard.c @@ -1756,7 +1756,7 @@ static int setoperation_mode(struct drxk_state *state, goto error; state->m_operation_mode = OM_NONE; break; - case OM_QAM_ITU_A: /* fallthrough */ + case OM_QAM_ITU_A: case OM_QAM_ITU_C: status = mpegts_stop(state); if (status < 0) @@ -1783,7 +1783,7 @@ static int setoperation_mode(struct drxk_state *state, if (status < 0) goto error; break; - case OM_QAM_ITU_A: /* fallthrough */ + case OM_QAM_ITU_A: case OM_QAM_ITU_C: dprintk(1, ": DVB-C Annex %c\n", (state->m_operation_mode == OM_QAM_ITU_A) ? 'A' : 'C'); @@ -2012,7 +2012,7 @@ static int mpegts_dto_setup(struct drxk_state *state, fec_oc_rcn_ctl_rate = 0xC00000; static_clk = state->m_dvbt_static_clk; break; - case OM_QAM_ITU_A: /* fallthrough */ + case OM_QAM_ITU_A: case OM_QAM_ITU_C: fec_oc_tmd_mode = 0x0004; fec_oc_rcn_ctl_rate = 0xD2B4EE; /* good for >63 Mb/s */ @@ -3249,11 +3249,11 @@ static int dvbt_sc_command(struct drxk_state *state, case OFDM_SC_RA_RAM_CMD_SET_PREF_PARAM: case OFDM_SC_RA_RAM_CMD_PROGRAM_PARAM: status |= write16(state, OFDM_SC_RA_RAM_PARAM1__A, param1); - /* fall through - All commands using 1 parameters */ + fallthrough; /* All commands using 1 parameters */ case OFDM_SC_RA_RAM_CMD_SET_ECHO_TIMING: case OFDM_SC_RA_RAM_CMD_USER_IO: status |= write16(state, OFDM_SC_RA_RAM_PARAM0__A, param0); - /* fall through - All commands using 0 parameters */ + fallthrough; /* All commands using 0 parameters */ case OFDM_SC_RA_RAM_CMD_GET_OP_PARAM: case OFDM_SC_RA_RAM_CMD_NULL: /* Write command */ @@ -3761,7 +3761,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz, case TRANSMISSION_MODE_AUTO: default: operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_MODE__M; - /* fall through - try first guess DRX_FFTMODE_8K */ + fallthrough; /* try first guess DRX_FFTMODE_8K */ case TRANSMISSION_MODE_8K: transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_MODE_8K; break; @@ -3775,7 +3775,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz, default: case GUARD_INTERVAL_AUTO: operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_GUARD__M; - /* fall through - try first guess DRX_GUARD_1DIV4 */ + fallthrough; /* try first guess DRX_GUARD_1DIV4 */ case GUARD_INTERVAL_1_4: transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_GUARD_4; break; @@ -3798,7 +3798,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz, operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_HIER__M; /* try first guess SC_RA_RAM_OP_PARAM_HIER_NO */ /* transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_HIER_NO; */ - /* fall through */ + fallthrough; case HIERARCHY_1: transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_HIER_A1; break; @@ -3816,7 +3816,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz, case QAM_AUTO: default: operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_CONST__M; - /* fall through - try first guess DRX_CONSTELLATION_QAM64 */ + fallthrough; /* try first guess DRX_CONSTELLATION_QAM64 */ case QAM_64: transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_CONST_QAM64; break; @@ -3841,7 +3841,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz, WR16(dev_addr, OFDM_EC_SB_PRIOR__A, OFDM_EC_SB_PRIOR_HI)); break; - case DRX_PRIORITY_UNKNOWN: /* fall through */ + case DRX_PRIORITY_UNKNOWN: default: status = -EINVAL; goto error; @@ -3859,7 +3859,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz, case FEC_AUTO: default: operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_RATE__M; - /* fall through - try first guess DRX_CODERATE_2DIV3 */ + fallthrough; /* try first guess DRX_CODERATE_2DIV3 */ case FEC_2_3: transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_RATE_2_3; break; @@ -3893,7 +3893,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz, switch (state->props.bandwidth_hz) { case 0: state->props.bandwidth_hz = 8000000; - /* fall through */ + fallthrough; case 8000000: bandwidth = DRXK_BANDWIDTH_8MHZ_IN_HZ; status = write16(state, OFDM_SC_RA_RAM_SRMM_FIX_FACT_8K__A, diff --git a/drivers/media/dvb-frontends/lgdt3306a.c b/drivers/media/dvb-frontends/lgdt3306a.c index d3c330e035c4..722576f1732a 100644 --- a/drivers/media/dvb-frontends/lgdt3306a.c +++ b/drivers/media/dvb-frontends/lgdt3306a.c @@ -768,7 +768,7 @@ static int lgdt3306a_set_if(struct lgdt3306a_state *state, default: pr_warn("IF=%d KHz is not supported, 3250 assumed\n", if_freq_khz); - /* fallthrough */ + fallthrough; case 3250: /* 3.25Mhz */ nco1 = 0x34; nco2 = 0x00; diff --git a/drivers/media/dvb-frontends/mt352.c b/drivers/media/dvb-frontends/mt352.c index 881897583cf2..399d5c519027 100644 --- a/drivers/media/dvb-frontends/mt352.c +++ b/drivers/media/dvb-frontends/mt352.c @@ -201,7 +201,7 @@ static int mt352_set_parameters(struct dvb_frontend *fe) if (op->hierarchy == HIERARCHY_AUTO || op->hierarchy == HIERARCHY_NONE) break; - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/drivers/media/dvb-frontends/mxl5xx.c b/drivers/media/dvb-frontends/mxl5xx.c index 290b9eab099f..4404ace82981 100644 --- a/drivers/media/dvb-frontends/mxl5xx.c +++ b/drivers/media/dvb-frontends/mxl5xx.c @@ -739,7 +739,7 @@ static int get_frontend(struct dvb_frontend *fe, default: break; } - /* Fall through */ + fallthrough; case SYS_DVBS: switch ((enum MXL_HYDRA_MODULATION_E) reg_data[DMD_MODULATION_SCHEME_ADDR]) { diff --git a/drivers/media/dvb-frontends/or51132.c b/drivers/media/dvb-frontends/or51132.c index 35a3e47497c2..24de1b115158 100644 --- a/drivers/media/dvb-frontends/or51132.c +++ b/drivers/media/dvb-frontends/or51132.c @@ -482,7 +482,7 @@ start: switch (reg&0xff) { case 0x06: if (reg & 0x1000) usK = 3 << 24; - /* fall through */ + fallthrough; case 0x43: /* QAM64 */ c = 150204167; break; diff --git a/drivers/media/dvb-frontends/s5h1411.c b/drivers/media/dvb-frontends/s5h1411.c index 89402916d301..c1334d7eb442 100644 --- a/drivers/media/dvb-frontends/s5h1411.c +++ b/drivers/media/dvb-frontends/s5h1411.c @@ -398,7 +398,7 @@ static int s5h1411_set_if_freq(struct dvb_frontend *fe, int KHz) default: dprintk("%s(%d KHz) Invalid, defaulting to 5380\n", __func__, KHz); - /* fall through */ + fallthrough; case 5380: case 44000: s5h1411_writereg(state, S5H1411_I2C_TOP_ADDR, 0x38, 0x1be4); diff --git a/drivers/media/dvb-frontends/zl10353.c b/drivers/media/dvb-frontends/zl10353.c index 2fc6aea580f9..2a2cf20a73d6 100644 --- a/drivers/media/dvb-frontends/zl10353.c +++ b/drivers/media/dvb-frontends/zl10353.c @@ -201,7 +201,7 @@ static int zl10353_set_parameters(struct dvb_frontend *fe) break; default: c->bandwidth_hz = 8000000; - /* fall through */ + fallthrough; case 8000000: zl10353_single_write(fe, MCLK_RATIO, 0x75); zl10353_single_write(fe, 0x64, 0x36); @@ -258,7 +258,7 @@ static int zl10353_set_parameters(struct dvb_frontend *fe) if (c->hierarchy == HIERARCHY_AUTO || c->hierarchy == HIERARCHY_NONE) break; - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig index 48ae60a2c603..c7ba76fee599 100644 --- a/drivers/media/i2c/Kconfig +++ b/drivers/media/i2c/Kconfig @@ -467,7 +467,7 @@ config VIDEO_VPX3220 config VIDEO_MAX9286 tristate "Maxim MAX9286 GMSL deserializer support" depends on I2C && I2C_MUX - depends on OF + depends on OF_GPIO select V4L2_FWNODE select VIDEO_V4L2_SUBDEV_API select MEDIA_CONTROLLER @@ -741,7 +741,7 @@ config VIDEO_HI556 config VIDEO_IMX214 tristate "Sony IMX214 sensor support" depends on GPIOLIB && I2C && VIDEO_V4L2 - depends on V4L2_FWNODE + select V4L2_FWNODE select MEDIA_CONTROLLER select VIDEO_V4L2_SUBDEV_API select REGMAP_I2C diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c index 570a4a09c387..03eee606af91 100644 --- a/drivers/media/pci/cx23885/cx23885-cards.c +++ b/drivers/media/pci/cx23885/cx23885-cards.c @@ -2209,7 +2209,7 @@ void cx23885_card_setup(struct cx23885_dev *dev) ts2->gen_ctrl_val = 0xc; /* Serial bus + punctured clock */ ts2->ts_clk_en_val = 0x1; /* Enable TS_CLK */ ts2->src_sel_val = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO; - /* fall-through */ + fallthrough; case CX23885_BOARD_DVICO_FUSIONHDTV_5_EXP: ts1->gen_ctrl_val = 0xc; /* Serial bus + punctured clock */ ts1->ts_clk_en_val = 0x1; /* Enable TS_CLK */ @@ -2370,7 +2370,7 @@ void cx23885_card_setup(struct cx23885_dev *dev) /* Currently only enabled for the integrated IR controller */ if (!enable_885_ir) break; - /* fall-through */ + fallthrough; case CX23885_BOARD_HAUPPAUGE_HVR1250: case CX23885_BOARD_HAUPPAUGE_HVR1800: case CX23885_BOARD_HAUPPAUGE_IMPACTVCBE: diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c index 7cabb9e9ffe2..92fe051c672f 100644 --- a/drivers/media/pci/ddbridge/ddbridge-core.c +++ b/drivers/media/pci/ddbridge/ddbridge-core.c @@ -1310,7 +1310,7 @@ static void dvb_input_detach(struct ddb_input *input) dvb_unregister_frontend(dvb->fe2); if (dvb->fe) dvb_unregister_frontend(dvb->fe); - /* fallthrough */ + fallthrough; case 0x30: dvb_module_release(dvb->i2c_client[0]); dvb->i2c_client[0] = NULL; @@ -1321,22 +1321,22 @@ static void dvb_input_detach(struct ddb_input *input) dvb_frontend_detach(dvb->fe); dvb->fe = NULL; dvb->fe2 = NULL; - /* fallthrough */ + fallthrough; case 0x20: dvb_net_release(&dvb->dvbnet); - /* fallthrough */ + fallthrough; case 0x12: dvbdemux->dmx.remove_frontend(&dvbdemux->dmx, &dvb->hw_frontend); dvbdemux->dmx.remove_frontend(&dvbdemux->dmx, &dvb->mem_frontend); - /* fallthrough */ + fallthrough; case 0x11: dvb_dmxdev_release(&dvb->dmxdev); - /* fallthrough */ + fallthrough; case 0x10: dvb_dmx_release(&dvb->demux); - /* fallthrough */ + fallthrough; case 0x01: break; } @@ -1559,7 +1559,7 @@ static int dvb_input_attach(struct ddb_input *input) osc24 = 0; else osc24 = 1; - /* fall-through */ + fallthrough; case DDB_TUNER_DVBCT2_SONY_P: case DDB_TUNER_DVBC2T2_SONY_P: case DDB_TUNER_ISDBT_SONY_P: @@ -1575,7 +1575,7 @@ static int dvb_input_attach(struct ddb_input *input) break; case DDB_TUNER_DVBC2T2I_SONY: osc24 = 1; - /* fall-through */ + fallthrough; case DDB_TUNER_DVBCT2_SONY: case DDB_TUNER_DVBC2T2_SONY: case DDB_TUNER_ISDBT_SONY: @@ -2036,7 +2036,7 @@ static int ddb_port_attach(struct ddb_port *port) ret = ddb_ci_attach(port, ci_bitrate); if (ret < 0) break; - /* fall-through */ + fallthrough; case DDB_PORT_LOOP: ret = dvb_register_device(port->dvb[0].adap, &port->dvb[0].dev, @@ -2432,7 +2432,8 @@ void ddb_ports_init(struct ddb *dev) ddb_input_init(port, 4 + i, 1, 4 + i); ddb_output_init(port, i); break; - } /* fallthrough */ + } + fallthrough; case DDB_OCTOPUS: ddb_input_init(port, 2 * i, 0, 2 * i); ddb_input_init(port, 2 * i + 1, 1, 2 * i + 1); @@ -3417,7 +3418,7 @@ int ddb_exit_ddbridge(int stage, int error) default: case 2: destroy_workqueue(ddb_wq); - /* fall-through */ + fallthrough; case 1: ddb_class_destroy(); break; diff --git a/drivers/media/pci/meye/meye.c b/drivers/media/pci/meye/meye.c index 7fb3b1853b87..8944e4bd4638 100644 --- a/drivers/media/pci/meye/meye.c +++ b/drivers/media/pci/meye/meye.c @@ -952,7 +952,7 @@ static int meyeioc_sync(struct file *file, void *fh, int *i) mutex_unlock(&meye.lock); return -EINTR; } - /* fall through */ + fallthrough; case MEYE_BUF_DONE: meye.grab_buffer[*i].state = MEYE_BUF_UNUSED; if (kfifo_out_locked(&meye.doneq, (unsigned char *)&unused, diff --git a/drivers/media/pci/ttpci/av7110.c b/drivers/media/pci/ttpci/av7110.c index bf36b1e22b63..45228f4f6fc6 100644 --- a/drivers/media/pci/ttpci/av7110.c +++ b/drivers/media/pci/ttpci/av7110.c @@ -637,7 +637,7 @@ static void gpioirq(unsigned long cookie) iwdebi(av7110, DEBINOSWAP, RX_BUFF, 0, 2); break; } - /* fall through */ + fallthrough; case DATA_TS_RECORD: case DATA_PES_RECORD: @@ -2176,7 +2176,7 @@ static int frontend_init(struct av7110 *av7110) break; } } - /* fall-thru */ + fallthrough; case 0x0008: // Hauppauge/TT DVB-T // Grundig 29504-401 diff --git a/drivers/media/pci/ttpci/av7110_hw.c b/drivers/media/pci/ttpci/av7110_hw.c index e8a8ec5405e2..93ca31e38ddd 100644 --- a/drivers/media/pci/ttpci/av7110_hw.c +++ b/drivers/media/pci/ttpci/av7110_hw.c @@ -1107,7 +1107,7 @@ int av7110_osd_cmd(struct av7110 *av7110, osd_cmd_t *dc) break; case OSD_SetRow: dc->y1 = dc->y0; - /* fall through */ + fallthrough; case OSD_SetBlock: ret = OSDSetBlock(av7110, dc->x0, dc->y0, dc->x1, dc->y1, dc->color, dc->data); break; diff --git a/drivers/media/pci/ttpci/av7110_ipack.c b/drivers/media/pci/ttpci/av7110_ipack.c index ec528fae7333..30330ed01ce8 100644 --- a/drivers/media/pci/ttpci/av7110_ipack.c +++ b/drivers/media/pci/ttpci/av7110_ipack.c @@ -182,7 +182,7 @@ int av7110_ipack_instant_repack (const u8 *buf, int count, struct ipack *p) case DSM_CC_STREAM : case ISO13522_STREAM: p->done = 1; - /* fall through */ + fallthrough; case PRIVATE_STREAM1: case VIDEO_STREAM_S ... VIDEO_STREAM_E: case AUDIO_STREAM_S ... AUDIO_STREAM_E: diff --git a/drivers/media/pci/ttpci/budget-av.c b/drivers/media/pci/ttpci/budget-av.c index 38cac508bd72..3cb83005cf09 100644 --- a/drivers/media/pci/ttpci/budget-av.c +++ b/drivers/media/pci/ttpci/budget-av.c @@ -1226,7 +1226,7 @@ static void frontend_init(struct budget_av *budget_av) * but so far it has been only confirmed for this type */ budget_av->reinitialise_demod = 1; - /* fall through */ + fallthrough; case SUBID_DVBS_KNC1_PLUS: case SUBID_DVBS_EASYWATCH_1: if (saa->pci->subsystem_vendor == 0x1894) { diff --git a/drivers/media/pci/ttpci/budget.c b/drivers/media/pci/ttpci/budget.c index 9c811272abfe..a88711a3ac7f 100644 --- a/drivers/media/pci/ttpci/budget.c +++ b/drivers/media/pci/ttpci/budget.c @@ -613,7 +613,7 @@ static void frontend_init(struct budget *budget) break; } } - /* fall through */ + fallthrough; case 0x1018: // TT Budget-S-1401 (philips tda10086/philips tda8262) { struct dvb_frontend *fe; @@ -638,7 +638,7 @@ static void frontend_init(struct budget *budget) break; } } - /* fall through */ + fallthrough; case 0x101c: { /* TT S2-1600 */ const struct stv6110x_devctl *ctl; diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c index 36e5f2ff4ef1..b22dc1d72527 100644 --- a/drivers/media/platform/sh_vou.c +++ b/drivers/media/platform/sh_vou.c @@ -220,7 +220,7 @@ static void sh_vou_stream_config(struct sh_vou_device *vou_dev) break; case V4L2_PIX_FMT_RGB565: dataswap ^= 1; - /* fall through */ + fallthrough; case V4L2_PIX_FMT_RGB565X: row_coeff = 2; break; @@ -802,7 +802,7 @@ static u32 sh_vou_ntsc_mode(enum sh_vou_bus_fmt bus_fmt) default: pr_warn("%s(): Invalid bus-format code %d, using default 8-bit\n", __func__, bus_fmt); - /* fall through */ + fallthrough; case SH_VOU_BUS_8BIT: return 1; case SH_VOU_BUS_16BIT: diff --git a/drivers/media/platform/ti-vpe/cal.h b/drivers/media/platform/ti-vpe/cal.h index e496083715d2..4123405ee0cf 100644 --- a/drivers/media/platform/ti-vpe/cal.h +++ b/drivers/media/platform/ti-vpe/cal.h @@ -226,7 +226,7 @@ static inline void cal_write_field(struct cal_dev *cal, u32 offset, u32 value, u32 val = cal_read(cal, offset); val &= ~mask; - val |= FIELD_PREP(mask, value); + val |= (value << __ffs(mask)) & mask; cal_write(cal, offset, val); } diff --git a/drivers/media/radio/radio-si476x.c b/drivers/media/radio/radio-si476x.c index b203296de977..7e2460263882 100644 --- a/drivers/media/radio/radio-si476x.c +++ b/drivers/media/radio/radio-si476x.c @@ -105,7 +105,8 @@ static inline enum phase_diversity_modes_idx si476x_phase_diversity_mode_to_idx(enum si476x_phase_diversity_mode mode) { switch (mode) { - default: /* FALLTHROUGH */ + default: + fallthrough; case SI476X_PHDIV_DISABLED: return SI476X_IDX_PHDIV_DISABLED; case SI476X_PHDIV_PRIMARY_COMBINING: diff --git a/drivers/media/radio/tea575x.c b/drivers/media/radio/tea575x.c index b0303cf00387..c37315226c42 100644 --- a/drivers/media/radio/tea575x.c +++ b/drivers/media/radio/tea575x.c @@ -249,7 +249,7 @@ int snd_tea575x_enum_freq_bands(struct snd_tea575x *tea, index = BAND_AM; break; } - /* Fall through */ + fallthrough; default: return -EINVAL; } diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index 5bb144435c16..3fe3edd80876 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -112,7 +112,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_trace_printk: if (perfmon_capable()) return bpf_get_trace_printk_proto(); - /* fall through */ + fallthrough; default: return NULL; } diff --git a/drivers/media/rc/gpio-ir-tx.c b/drivers/media/rc/gpio-ir-tx.c index f33b443bfa47..c6cd2e6d8e65 100644 --- a/drivers/media/rc/gpio-ir-tx.c +++ b/drivers/media/rc/gpio-ir-tx.c @@ -19,8 +19,6 @@ struct gpio_ir { struct gpio_desc *gpio; unsigned int carrier; unsigned int duty_cycle; - /* we need a spinlock to hold the cpu while transmitting */ - spinlock_t lock; }; static const struct of_device_id gpio_ir_tx_of_match[] = { @@ -53,12 +51,11 @@ static int gpio_ir_tx_set_carrier(struct rc_dev *dev, u32 carrier) static void gpio_ir_tx_unmodulated(struct gpio_ir *gpio_ir, uint *txbuf, uint count) { - unsigned long flags; ktime_t edge; s32 delta; int i; - spin_lock_irqsave(&gpio_ir->lock, flags); + local_irq_disable(); edge = ktime_get(); @@ -72,14 +69,11 @@ static void gpio_ir_tx_unmodulated(struct gpio_ir *gpio_ir, uint *txbuf, } gpiod_set_value(gpio_ir->gpio, 0); - - spin_unlock_irqrestore(&gpio_ir->lock, flags); } static void gpio_ir_tx_modulated(struct gpio_ir *gpio_ir, uint *txbuf, uint count) { - unsigned long flags; ktime_t edge; /* * delta should never exceed 0.5 seconds (IR_MAX_DURATION) and on @@ -95,7 +89,7 @@ static void gpio_ir_tx_modulated(struct gpio_ir *gpio_ir, uint *txbuf, space = DIV_ROUND_CLOSEST((100 - gpio_ir->duty_cycle) * (NSEC_PER_SEC / 100), gpio_ir->carrier); - spin_lock_irqsave(&gpio_ir->lock, flags); + local_irq_disable(); edge = ktime_get(); @@ -128,19 +122,20 @@ static void gpio_ir_tx_modulated(struct gpio_ir *gpio_ir, uint *txbuf, edge = last; } } - - spin_unlock_irqrestore(&gpio_ir->lock, flags); } static int gpio_ir_tx(struct rc_dev *dev, unsigned int *txbuf, unsigned int count) { struct gpio_ir *gpio_ir = dev->priv; + unsigned long flags; + local_irq_save(flags); if (gpio_ir->carrier) gpio_ir_tx_modulated(gpio_ir, txbuf, count); else gpio_ir_tx_unmodulated(gpio_ir, txbuf, count); + local_irq_restore(flags); return count; } @@ -176,7 +171,6 @@ static int gpio_ir_tx_probe(struct platform_device *pdev) gpio_ir->carrier = 38000; gpio_ir->duty_cycle = 50; - spin_lock_init(&gpio_ir->lock); rc = devm_rc_register_device(&pdev->dev, rcdev); if (rc < 0) diff --git a/drivers/media/rc/ir-rc6-decoder.c b/drivers/media/rc/ir-rc6-decoder.c index 95727ca910f7..0cda78f72fd8 100644 --- a/drivers/media/rc/ir-rc6-decoder.c +++ b/drivers/media/rc/ir-rc6-decoder.c @@ -64,7 +64,7 @@ static enum rc6_mode rc6_mode(struct rc6_dec *data) case 6: if (!data->toggle) return RC6_MODE_6A; - /* fall through */ + fallthrough; default: return RC6_MODE_UNKNOWN; } diff --git a/drivers/media/rc/ir-sony-decoder.c b/drivers/media/rc/ir-sony-decoder.c index 9fa58d92eb09..7d9a7c000c75 100644 --- a/drivers/media/rc/ir-sony-decoder.c +++ b/drivers/media/rc/ir-sony-decoder.c @@ -102,7 +102,7 @@ static int ir_sony_decode(struct rc_dev *dev, struct ir_raw_event ev) } data->state = STATE_FINISHED; - /* Fall through */ + fallthrough; case STATE_FINISHED: if (ev.pulse) diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index f9616158bcf4..98681ba10428 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -1726,7 +1726,7 @@ static int mceusb_dev_probe(struct usb_interface *intf, goto mem_alloc_fail; ir->pipe_in = pipe; - ir->buf_in = usb_alloc_coherent(dev, maxp, GFP_ATOMIC, &ir->dma_in); + ir->buf_in = usb_alloc_coherent(dev, maxp, GFP_KERNEL, &ir->dma_in); if (!ir->buf_in) goto buf_in_alloc_fail; diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 7b53066d9d07..dee8a9f3d80a 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -1292,6 +1292,10 @@ static ssize_t store_protocols(struct device *device, } mutex_lock(&dev->lock); + if (!dev->registered) { + mutex_unlock(&dev->lock); + return -ENODEV; + } old_protocols = *current_protocols; new_protocols = old_protocols; @@ -1430,6 +1434,10 @@ static ssize_t store_filter(struct device *device, return -EINVAL; mutex_lock(&dev->lock); + if (!dev->registered) { + mutex_unlock(&dev->lock); + return -ENODEV; + } new_filter = *filter; if (fattr->mask) @@ -1544,6 +1552,10 @@ static ssize_t store_wakeup_protocols(struct device *device, int i; mutex_lock(&dev->lock); + if (!dev->registered) { + mutex_unlock(&dev->lock); + return -ENODEV; + } allowed = dev->allowed_wakeup_protocols; @@ -1601,25 +1613,25 @@ static void rc_dev_release(struct device *device) kfree(dev); } -#define ADD_HOTPLUG_VAR(fmt, val...) \ - do { \ - int err = add_uevent_var(env, fmt, val); \ - if (err) \ - return err; \ - } while (0) - static int rc_dev_uevent(struct device *device, struct kobj_uevent_env *env) { struct rc_dev *dev = to_rc_dev(device); + int ret = 0; - if (dev->rc_map.name) - ADD_HOTPLUG_VAR("NAME=%s", dev->rc_map.name); - if (dev->driver_name) - ADD_HOTPLUG_VAR("DRV_NAME=%s", dev->driver_name); - if (dev->device_name) - ADD_HOTPLUG_VAR("DEV_NAME=%s", dev->device_name); + mutex_lock(&dev->lock); - return 0; + if (!dev->registered) + ret = -ENODEV; + if (ret == 0 && dev->rc_map.name) + ret = add_uevent_var(env, "NAME=%s", dev->rc_map.name); + if (ret == 0 && dev->driver_name) + ret = add_uevent_var(env, "DRV_NAME=%s", dev->driver_name); + if (ret == 0 && dev->device_name) + ret = add_uevent_var(env, "DEV_NAME=%s", dev->device_name); + + mutex_unlock(&dev->lock); + + return ret; } /* @@ -2011,14 +2023,14 @@ void rc_unregister_device(struct rc_dev *dev) del_timer_sync(&dev->timer_keyup); del_timer_sync(&dev->timer_repeat); - rc_free_rx_device(dev); - mutex_lock(&dev->lock); if (dev->users && dev->close) dev->close(dev); dev->registered = false; mutex_unlock(&dev->lock); + rc_free_rx_device(dev); + /* * lirc device should be freed with dev->registered = false, so * that userspace polling will get notified. diff --git a/drivers/media/test-drivers/vicodec/vicodec-core.c b/drivers/media/test-drivers/vicodec/vicodec-core.c index 8941d73f6611..71928e30dae8 100644 --- a/drivers/media/test-drivers/vicodec/vicodec-core.c +++ b/drivers/media/test-drivers/vicodec/vicodec-core.c @@ -1994,6 +1994,7 @@ static int vicodec_request_validate(struct media_request *req) } ctrl = v4l2_ctrl_request_hdl_ctrl_find(hdl, vicodec_ctrl_stateless_state.id); + v4l2_ctrl_request_hdl_put(hdl); if (!ctrl) { v4l2_info(&ctx->dev->v4l2_dev, "Missing required codec control\n"); diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c index 734a92caad8d..7b7d9fe4f945 100644 --- a/drivers/media/tuners/xc5000.c +++ b/drivers/media/tuners/xc5000.c @@ -756,7 +756,7 @@ static int xc5000_set_digital_params(struct dvb_frontend *fe) if (!bw) bw = 6000000; /* fall to OFDM handling */ - /* fall through */ + fallthrough; case SYS_DMBTH: case SYS_DVBT: case SYS_DVBT2: diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c index 198ddfb8d2b1..e3234d169065 100644 --- a/drivers/media/usb/b2c2/flexcop-usb.c +++ b/drivers/media/usb/b2c2/flexcop-usb.c @@ -525,7 +525,7 @@ static int flexcop_usb_init(struct flexcop_usb *fc_usb) case USB_SPEED_HIGH: info("running at HIGH speed."); break; - case USB_SPEED_UNKNOWN: /* fall through */ + case USB_SPEED_UNKNOWN: default: err("cannot handle USB speed because it is unknown."); return -ENODEV; diff --git a/drivers/media/usb/cpia2/cpia2_core.c b/drivers/media/usb/cpia2/cpia2_core.c index 20c50c2d042e..e747548ab286 100644 --- a/drivers/media/usb/cpia2/cpia2_core.c +++ b/drivers/media/usb/cpia2/cpia2_core.c @@ -165,7 +165,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_VP_BRIGHTNESS: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_VP_BRIGHTNESS: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -176,7 +176,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_CONTRAST: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_CONTRAST: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -184,7 +184,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_VP_SATURATION: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_VP_SATURATION: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -195,7 +195,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_VP_GPIO_DATA: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_VP_GPIO_DATA: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -203,7 +203,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_VP_GPIO_DIRECTION: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_VP_GPIO_DIRECTION: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -211,7 +211,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_VC_MP_GPIO_DATA: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_VC_MP_GPIO_DATA: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC; cmd.reg_count = 1; @@ -219,7 +219,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_VC_MP_GPIO_DIRECTION: cmd.buffer.block_data[0] = param; - /*fall through */ + fallthrough; case CPIA2_CMD_GET_VC_MP_GPIO_DIRECTION: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC; cmd.reg_count = 1; @@ -234,7 +234,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_FLICKER_MODES: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_FLICKER_MODES: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -281,7 +281,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_USER_MODE: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_USER_MODE: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -301,7 +301,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_WAKEUP: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_WAKEUP: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC; cmd.reg_count = 1; @@ -309,7 +309,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_PW_CONTROL: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_PW_CONTROL: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC; cmd.reg_count = 1; @@ -322,7 +322,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_SYSTEM_CTRL: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_SYSTEM_CTRL: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_SYSTEM; @@ -331,7 +331,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_VP_SYSTEM_CTRL: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_VP_SYSTEM_CTRL: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -339,7 +339,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_VP_EXP_MODES: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_VP_EXP_MODES: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -347,7 +347,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_DEVICE_CONFIG: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_DEVICE_CONFIG: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -368,7 +368,7 @@ int cpia2_do_command(struct camera_data *cam, break; case CPIA2_CMD_SET_VC_CONTROL: cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_VC_CONTROL: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC; cmd.reg_count = 1; @@ -403,7 +403,7 @@ int cpia2_do_command(struct camera_data *cam, this register can also affect flicker modes */ cmd.buffer.block_data[0] = param; - /* fall through */ + fallthrough; case CPIA2_CMD_GET_USER_EFFECTS: cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP; cmd.reg_count = 1; @@ -1751,7 +1751,7 @@ int cpia2_set_fps(struct camera_data *cam, int framerate) CPIA2_VP_SENSOR_FLAGS_500) { return -EINVAL; } - /* Fall through */ + fallthrough; case CPIA2_VP_FRAMERATE_15: case CPIA2_VP_FRAMERATE_12_5: case CPIA2_VP_FRAMERATE_7_5: diff --git a/drivers/media/usb/cx231xx/cx231xx-video.c b/drivers/media/usb/cx231xx/cx231xx-video.c index d9f953f2d088..425e470b0fd3 100644 --- a/drivers/media/usb/cx231xx/cx231xx-video.c +++ b/drivers/media/usb/cx231xx/cx231xx-video.c @@ -996,7 +996,7 @@ void cx231xx_v4l2_create_entities(struct cx231xx *dev) /* The DVB core will handle it */ if (dev->tuner_type == TUNER_ABSENT) continue; - /* fall through */ + fallthrough; default: /* just to shut up a gcc warning */ ent->function = MEDIA_ENT_F_CONN_RF; break; diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c index 4ef3fa98d20f..52e648e2713a 100644 --- a/drivers/media/usb/dvb-usb/dib0700_devices.c +++ b/drivers/media/usb/dvb-usb/dib0700_devices.c @@ -1659,14 +1659,14 @@ static int dib8096_set_param_override(struct dvb_frontend *fe) switch (band) { default: - deb_info("Warning : Rf frequency (%iHz) is not in the supported range, using VHF switch ", fe->dtv_property_cache.frequency); - /* fall through */ + deb_info("Warning : Rf frequency (%iHz) is not in the supported range, using VHF switch ", fe->dtv_property_cache.frequency); + fallthrough; case BAND_VHF: - state->dib8000_ops.set_gpio(fe, 3, 0, 1); - break; + state->dib8000_ops.set_gpio(fe, 3, 0, 1); + break; case BAND_UHF: - state->dib8000_ops.set_gpio(fe, 3, 0, 0); - break; + state->dib8000_ops.set_gpio(fe, 3, 0, 0); + break; } ret = state->set_param_save(fe); diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index f96626fe2c0b..a27a68440325 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -1886,12 +1886,12 @@ static int dw2102_load_firmware(struct usb_device *dev, switch (le16_to_cpu(dev->descriptor.idProduct)) { case USB_PID_TEVII_S650: dw2104_properties.rc.core.rc_codes = RC_MAP_TEVII_NEC; - /* fall through */ + fallthrough; case USB_PID_DW2104: reset = 1; dw210x_op_rw(dev, 0xc4, 0x0000, 0, &reset, 1, DW210X_WRITE_MSG); - /* fall through */ + fallthrough; case USB_PID_DW3101: reset = 0; dw210x_op_rw(dev, 0xbf, 0x0040, 0, &reset, 0, @@ -1924,7 +1924,7 @@ static int dw2102_load_firmware(struct usb_device *dev, break; } } - /* fall through */ + fallthrough; case 0x2101: dw210x_op_rw(dev, 0xbc, 0x0030, 0, &reset16[0], 2, DW210X_READ_MSG); diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 3f3fbcd60cc6..45a2403aa039 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -2200,7 +2200,7 @@ static int check_range(enum v4l2_ctrl_type type, case V4L2_CTRL_TYPE_BOOLEAN: if (step != 1 || max > 1 || min < 0) return -ERANGE; - /* fall through */ + fallthrough; case V4L2_CTRL_TYPE_U8: case V4L2_CTRL_TYPE_U16: case V4L2_CTRL_TYPE_U32: diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index a556880f225a..f74b42280892 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -782,7 +782,6 @@ static void v4l_print_frmsizeenum(const void *arg, bool write_only) p->stepwise.step_height); break; case V4L2_FRMSIZE_TYPE_CONTINUOUS: - /* fall through */ default: pr_cont("\n"); break; @@ -816,7 +815,6 @@ static void v4l_print_frmivalenum(const void *arg, bool write_only) p->stepwise.step.denominator); break; case V4L2_FRMIVAL_TYPE_CONTINUOUS: - /* fall through */ default: pr_cont("\n"); break; @@ -3189,14 +3187,16 @@ static int video_put_user(void __user *arg, void *parg, unsigned int cmd) #ifdef CONFIG_COMPAT_32BIT_TIME case VIDIOC_DQEVENT_TIME32: { struct v4l2_event *ev = parg; - struct v4l2_event_time32 ev32 = { - .type = ev->type, - .pending = ev->pending, - .sequence = ev->sequence, - .timestamp.tv_sec = ev->timestamp.tv_sec, - .timestamp.tv_nsec = ev->timestamp.tv_nsec, - .id = ev->id, - }; + struct v4l2_event_time32 ev32; + + memset(&ev32, 0, sizeof(ev32)); + + ev32.type = ev->type; + ev32.pending = ev->pending; + ev32.sequence = ev->sequence; + ev32.timestamp.tv_sec = ev->timestamp.tv_sec; + ev32.timestamp.tv_nsec = ev->timestamp.tv_nsec; + ev32.id = ev->id; memcpy(&ev32.u, &ev->u, sizeof(ev->u)); memcpy(&ev32.reserved, &ev->reserved, sizeof(ev->reserved)); @@ -3210,21 +3210,23 @@ static int video_put_user(void __user *arg, void *parg, unsigned int cmd) case VIDIOC_DQBUF_TIME32: case VIDIOC_PREPARE_BUF_TIME32: { struct v4l2_buffer *vb = parg; - struct v4l2_buffer_time32 vb32 = { - .index = vb->index, - .type = vb->type, - .bytesused = vb->bytesused, - .flags = vb->flags, - .field = vb->field, - .timestamp.tv_sec = vb->timestamp.tv_sec, - .timestamp.tv_usec = vb->timestamp.tv_usec, - .timecode = vb->timecode, - .sequence = vb->sequence, - .memory = vb->memory, - .m.userptr = vb->m.userptr, - .length = vb->length, - .request_fd = vb->request_fd, - }; + struct v4l2_buffer_time32 vb32; + + memset(&vb32, 0, sizeof(vb32)); + + vb32.index = vb->index; + vb32.type = vb->type; + vb32.bytesused = vb->bytesused; + vb32.flags = vb->flags; + vb32.field = vb->field; + vb32.timestamp.tv_sec = vb->timestamp.tv_sec; + vb32.timestamp.tv_usec = vb->timestamp.tv_usec; + vb32.timecode = vb->timecode; + vb32.sequence = vb->sequence; + vb32.memory = vb->memory; + vb32.m.userptr = vb->m.userptr; + vb32.length = vb->length; + vb32.request_fd = vb->request_fd; if (copy_to_user(arg, &vb32, sizeof(vb32))) return -EFAULT; diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c index 5c91fc3e65b5..606a271bdd2d 100644 --- a/drivers/media/v4l2-core/videobuf-core.c +++ b/drivers/media/v4l2-core/videobuf-core.c @@ -354,7 +354,7 @@ static void videobuf_status(struct videobuf_queue *q, struct v4l2_buffer *b, break; case VIDEOBUF_ERROR: b->flags |= V4L2_BUF_FLAG_ERROR; - /* fall through */ + fallthrough; case VIDEOBUF_DONE: b->flags |= V4L2_BUF_FLAG_DONE; break; diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index f512cbc7a36c..ca0097664b12 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -313,7 +313,6 @@ static unsigned long gpmc_get_clk_period(int cs, enum gpmc_clk_domain cd) tick_ps *= div; break; case GPMC_CD_FCLK: - /* FALL-THROUGH */ default: break; } diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c index d9ee8e3dc72d..178954228631 100644 --- a/drivers/memstick/core/ms_block.c +++ b/drivers/memstick/core/ms_block.c @@ -371,7 +371,7 @@ again: serial mode), then just fall through */ if (msb_read_int_reg(msb, -1)) return 0; - /* fallthrough */ + fallthrough; case MSB_RP_RECEIVE_INT_REQ_RESULT: intreg = mrq->data[0]; @@ -403,7 +403,7 @@ again: case MSB_RP_RECEIVE_STATUS_REG: msb->regs.status = *(struct ms_status_register *)mrq->data; msb->state = MSB_RP_SEND_OOB_READ; - /* fallthrough */ + fallthrough; case MSB_RP_SEND_OOB_READ: if (!msb_read_regs(msb, @@ -418,7 +418,7 @@ again: msb->regs.extra_data = *(struct ms_extra_data_register *) mrq->data; msb->state = MSB_RP_SEND_READ_DATA; - /* fallthrough */ + fallthrough; case MSB_RP_SEND_READ_DATA: /* Skip that state if we only read the oob */ @@ -518,7 +518,7 @@ again: msb->state = MSB_WB_RECEIVE_INT_REQ; if (msb_read_int_reg(msb, -1)) return 0; - /* fallthrough */ + fallthrough; case MSB_WB_RECEIVE_INT_REQ: intreg = mrq->data[0]; @@ -549,7 +549,7 @@ again: msb->int_polling = false; msb->state = MSB_WB_SEND_WRITE_DATA; - /* fallthrough */ + fallthrough; case MSB_WB_SEND_WRITE_DATA: sg_init_table(sg, ARRAY_SIZE(sg)); @@ -628,7 +628,7 @@ again: msb->state = MSB_SC_RECEIVE_INT_REQ; if (msb_read_int_reg(msb, -1)) return 0; - /* fallthrough */ + fallthrough; case MSB_SC_RECEIVE_INT_REQ: intreg = mrq->data[0]; diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c index 4a6b866b0291..e83c3ada9389 100644 --- a/drivers/memstick/host/jmb38x_ms.c +++ b/drivers/memstick/host/jmb38x_ms.c @@ -255,11 +255,11 @@ static unsigned int jmb38x_ms_write_data(struct jmb38x_ms_host *host, case 3: host->io_word[0] |= buf[off + 2] << 16; host->io_pos++; - /* fall through */ + fallthrough; case 2: host->io_word[0] |= buf[off + 1] << 8; host->io_pos++; - /* fall through */ + fallthrough; case 1: host->io_word[0] |= buf[off]; host->io_pos++; diff --git a/drivers/memstick/host/tifm_ms.c b/drivers/memstick/host/tifm_ms.c index fc35c7404429..786e46798da2 100644 --- a/drivers/memstick/host/tifm_ms.c +++ b/drivers/memstick/host/tifm_ms.c @@ -162,11 +162,11 @@ static unsigned int tifm_ms_write_data(struct tifm_ms *host, case 3: host->io_word |= buf[off + 2] << 16; host->io_pos++; - /* fall through */ + fallthrough; case 2: host->io_word |= buf[off + 1] << 8; host->io_pos++; - /* fall through */ + fallthrough; case 1: host->io_word |= buf[off]; host->io_pos++; diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index 5216487db4fb..9903e9660a38 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -642,7 +642,7 @@ mptbase_reply(MPT_ADAPTER *ioc, MPT_FRAME_HDR *req, MPT_FRAME_HDR *reply) freereq = 0; if (event != MPI_EVENT_EVENT_CHANGE) break; - /* fall through */ + fallthrough; case MPI_FUNCTION_CONFIG: case MPI_FUNCTION_SAS_IO_UNIT_CONTROL: ioc->mptbase_cmds.status |= MPT_MGMT_STATUS_COMMAND_GOOD; @@ -1887,7 +1887,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id) case MPI_MANUFACTPAGE_DEVICEID_FC939X: case MPI_MANUFACTPAGE_DEVICEID_FC949X: ioc->errata_flag_1064 = 1; - /* fall through */ + fallthrough; case MPI_MANUFACTPAGE_DEVICEID_FC909: case MPI_MANUFACTPAGE_DEVICEID_FC929: case MPI_MANUFACTPAGE_DEVICEID_FC919: @@ -1932,7 +1932,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id) pcixcmd &= 0x8F; pci_write_config_byte(pdev, 0x6a, pcixcmd); } - /* fall through */ + fallthrough; case MPI_MANUFACTPAGE_DEVID_1030_53C1035: ioc->bus_type = SPI; diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c index 6a79cd0ebe2b..18b91ea1a353 100644 --- a/drivers/message/fusion/mptsas.c +++ b/drivers/message/fusion/mptsas.c @@ -4326,7 +4326,7 @@ mptsas_hotplug_work(MPT_ADAPTER *ioc, struct fw_event_work *fw_event, } } mpt_findImVolumes(ioc); - /* fall through */ + fallthrough; case MPTSAS_ADD_DEVICE: memset(&sas_device, 0, sizeof(struct mptsas_devinfo)); diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c index 1491561d2e5c..8543f0324d5a 100644 --- a/drivers/message/fusion/mptscsih.c +++ b/drivers/message/fusion/mptscsih.c @@ -784,7 +784,7 @@ mptscsih_io_done(MPT_ADAPTER *ioc, MPT_FRAME_HDR *mf, MPT_FRAME_HDR *mr) /* * Allow non-SAS & non-NEXUS_LOSS to drop into below code */ - /* Fall through */ + fallthrough; case MPI_IOCSTATUS_SCSI_TASK_TERMINATED: /* 0x0048 */ /* Linux handles an unsolicited DID_RESET better @@ -881,7 +881,7 @@ mptscsih_io_done(MPT_ADAPTER *ioc, MPT_FRAME_HDR *mf, MPT_FRAME_HDR *mr) case MPI_IOCSTATUS_SCSI_DATA_OVERRUN: /* 0x0044 */ scsi_set_resid(sc, 0); - /* Fall through */ + fallthrough; case MPI_IOCSTATUS_SCSI_RECOVERED_ERROR: /* 0x0040 */ case MPI_IOCSTATUS_SUCCESS: /* 0x0000 */ sc->result = (DID_OK << 16) | scsi_status; diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c index a9d9c1cdf546..a5983d515db0 100644 --- a/drivers/mfd/db8500-prcmu.c +++ b/drivers/mfd/db8500-prcmu.c @@ -1515,10 +1515,10 @@ static unsigned long dsiclk_rate(u8 n) switch (divsel) { case PRCM_DSI_PLLOUT_SEL_PHI_4: div *= 2; - /* Fall through */ + fallthrough; case PRCM_DSI_PLLOUT_SEL_PHI_2: div *= 2; - /* Fall through */ + fallthrough; case PRCM_DSI_PLLOUT_SEL_PHI: return pll_rate(PRCM_PLLDSI_FREQ, clock_rate(PRCMU_HDMICLK), PLL_RAW) / div; diff --git a/drivers/mfd/iqs62x.c b/drivers/mfd/iqs62x.c index af764bc87d7c..761b4ef3a381 100644 --- a/drivers/mfd/iqs62x.c +++ b/drivers/mfd/iqs62x.c @@ -136,7 +136,7 @@ static int iqs62x_dev_init(struct iqs62x_core *iqs62x) if (val & IQS620_PROX_SETTINGS_4_SAR_EN) iqs62x->ui_sel = IQS62X_UI_SAR1; - /* fall through */ + fallthrough; case IQS621_PROD_NUM: ret = regmap_write(iqs62x->regmap, IQS620_GLBL_EVENT_MASK, @@ -470,7 +470,7 @@ static irqreturn_t iqs62x_irq(int irq, void *context) case IQS62X_EVENT_UI_LO: event_data.ui_data = get_unaligned_le16(&event_map[i]); - /* fall through */ + fallthrough; case IQS62X_EVENT_UI_HI: case IQS62X_EVENT_NONE: @@ -491,7 +491,7 @@ static irqreturn_t iqs62x_irq(int irq, void *context) case IQS62X_EVENT_HYST: event_map[i] <<= iqs62x->dev_desc->hyst_shift; - /* fall through */ + fallthrough; case IQS62X_EVENT_WHEEL: case IQS62X_EVENT_HALL: diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index c3651f06684f..fc00aaccb5f7 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -126,10 +126,6 @@ static int mfd_match_of_node_to_dev(struct platform_device *pdev, const __be32 *reg; u64 of_node_addr; - /* Skip devices 'disabled' by Device Tree */ - if (!of_device_is_available(np)) - return -ENODEV; - /* Skip if OF node has previously been allocated to a device */ list_for_each_entry(of_entry, &mfd_of_node_list, list) if (of_entry->np == np) @@ -212,6 +208,12 @@ static int mfd_add_device(struct device *parent, int id, if (IS_ENABLED(CONFIG_OF) && parent->of_node && cell->of_compatible) { for_each_child_of_node(parent->of_node, np) { if (of_device_is_compatible(np, cell->of_compatible)) { + /* Ignore 'disabled' devices error free */ + if (!of_device_is_available(np)) { + ret = 0; + goto fail_alias; + } + ret = mfd_match_of_node_to_dev(pdev, np, cell); if (ret == -EAGAIN) continue; @@ -370,8 +372,6 @@ static int mfd_remove_devices_fn(struct device *dev, void *data) regulator_bulk_unregister_supply_alias(dev, cell->parent_supplies, cell->num_parent_supplies); - kfree(cell); - platform_device_unregister(pdev); return 0; } diff --git a/drivers/mfd/mxs-lradc.c b/drivers/mfd/mxs-lradc.c index 5bef142c4835..111d11fd25aa 100644 --- a/drivers/mfd/mxs-lradc.c +++ b/drivers/mfd/mxs-lradc.c @@ -172,7 +172,7 @@ static int mxs_lradc_probe(struct platform_device *pdev) MXS_LRADC_TOUCHSCREEN_5WIRE; break; } - /* fall through - to an error message for i.MX23 */ + fallthrough; /* to an error message for i.MX23 */ default: dev_err(&pdev->dev, "Unsupported number of touchscreen wires (%d)\n" diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c index 1e6431cb8536..2a3a240b4619 100644 --- a/drivers/mfd/omap-usb-host.c +++ b/drivers/mfd/omap-usb-host.c @@ -308,7 +308,7 @@ static int usbhs_runtime_resume(struct device *dev) i, r); } } - /* Fall through - as HSIC mode needs utmi_clk */ + fallthrough; /* as HSIC mode needs utmi_clk */ case OMAP_EHCI_PORT_MODE_TLL: if (!IS_ERR(omap->utmi_clk[i])) { @@ -344,7 +344,7 @@ static int usbhs_runtime_suspend(struct device *dev) if (!IS_ERR(omap->hsic480m_clk[i])) clk_disable_unprepare(omap->hsic480m_clk[i]); - /* Fall through - as utmi_clks were used in HSIC mode */ + fallthrough; /* as utmi_clks were used in HSIC mode */ case OMAP_EHCI_PORT_MODE_TLL: if (!IS_ERR(omap->utmi_clk[i])) diff --git a/drivers/mfd/rave-sp.c b/drivers/mfd/rave-sp.c index abaab541df19..545196c85b5c 100644 --- a/drivers/mfd/rave-sp.c +++ b/drivers/mfd/rave-sp.c @@ -270,7 +270,7 @@ static void *stuff(unsigned char *dest, const unsigned char *src, size_t n) case RAVE_SP_ETX: case RAVE_SP_DLE: *dest++ = RAVE_SP_DLE; - /* FALLTHROUGH */ + fallthrough; default: *dest++ = byte; } @@ -541,7 +541,7 @@ static int rave_sp_receive_buf(struct serdev_device *serdev, * deframer buffer */ - /* FALLTHROUGH */ + fallthrough; case RAVE_SP_EXPECT_ESCAPED_DATA: if (deframer->length == sizeof(deframer->data)) { diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c index 75859e492984..df5cebb372a5 100644 --- a/drivers/mfd/syscon.c +++ b/drivers/mfd/syscon.c @@ -95,7 +95,7 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_clk) break; default: pr_err("Failed to retrieve valid hwlock: %d\n", ret); - /* fall-through */ + fallthrough; case -EPROBE_DEFER: goto err_regmap; } diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index cde9a2fc1325..ed8d38b09925 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -90,10 +90,10 @@ static int at25_ee_read(void *priv, unsigned int offset, switch (at25->addrlen) { default: /* case 3 */ *cp++ = offset >> 16; - /* fall through */ + fallthrough; case 2: *cp++ = offset >> 8; - /* fall through */ + fallthrough; case 1: case 0: /* can't happen: for better codegen */ *cp++ = offset >> 0; @@ -178,10 +178,10 @@ static int at25_ee_write(void *priv, unsigned int off, void *val, size_t count) switch (at25->addrlen) { default: /* case 3 */ *cp++ = offset >> 16; - /* fall through */ + fallthrough; case 2: *cp++ = offset >> 8; - /* fall through */ + fallthrough; case 1: case 0: /* can't happen: for better codegen */ *cp++ = offset >> 0; @@ -278,7 +278,7 @@ static int at25_fw_to_chip(struct device *dev, struct spi_eeprom *chip) switch (val) { case 9: chip->flags |= EE_INSTR_BIT3_IS_ADDR; - /* fall through */ + fallthrough; case 8: chip->flags |= EE_ADDR1; break; diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c index 7c38c4f7f9c0..a8004911c977 100644 --- a/drivers/misc/habanalabs/common/command_buffer.c +++ b/drivers/misc/habanalabs/common/command_buffer.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <linux/slab.h> +#include <linux/uaccess.h> #include <linux/genalloc.h> static void cb_fini(struct hl_device *hdev, struct hl_cb *cb) @@ -300,7 +301,7 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma) struct hl_device *hdev = hpriv->hdev; struct hl_cb *cb; phys_addr_t address; - u32 handle; + u32 handle, user_cb_size; int rc; handle = vma->vm_pgoff; @@ -314,7 +315,8 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma) } /* Validation check */ - if ((vma->vm_end - vma->vm_start) != ALIGN(cb->size, PAGE_SIZE)) { + user_cb_size = vma->vm_end - vma->vm_start; + if (user_cb_size != ALIGN(cb->size, PAGE_SIZE)) { dev_err(hdev->dev, "CB mmap failed, mmap size 0x%lx != 0x%x cb size\n", vma->vm_end - vma->vm_start, cb->size); @@ -322,6 +324,16 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma) goto put_cb; } + if (!access_ok((void __user *) (uintptr_t) vma->vm_start, + user_cb_size)) { + dev_err(hdev->dev, + "user pointer is invalid - 0x%lx\n", + vma->vm_start); + + rc = -EINVAL; + goto put_cb; + } + spin_lock(&cb->lock); if (cb->mmap) { diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index b9840e368eb5..2e3fcbc794db 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -808,6 +808,14 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, /* currently it is guaranteed to have only one chunk */ chunk = &cs_chunk_array[0]; + + if (chunk->queue_index >= hdev->asic_prop.max_queues) { + dev_err(hdev->dev, "Queue index %d is invalid\n", + chunk->queue_index); + rc = -EINVAL; + goto free_cs_chunk_array; + } + q_idx = chunk->queue_index; hw_queue_prop = &hdev->asic_prop.hw_queues_props[q_idx]; q_type = hw_queue_prop->type; diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c index c50c6fc9e905..37701e4f9d5a 100644 --- a/drivers/misc/habanalabs/common/debugfs.c +++ b/drivers/misc/habanalabs/common/debugfs.c @@ -19,7 +19,7 @@ static struct dentry *hl_debug_root; static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, - u8 i2c_reg, u32 *val) + u8 i2c_reg, long *val) { struct armcp_packet pkt; int rc; @@ -36,7 +36,7 @@ static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, pkt.i2c_reg = i2c_reg; rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - 0, (long *) val); + 0, val); if (rc) dev_err(hdev->dev, "Failed to read from I2C, error %d\n", rc); @@ -827,7 +827,7 @@ static ssize_t hl_i2c_data_read(struct file *f, char __user *buf, struct hl_dbg_device_entry *entry = file_inode(f)->i_private; struct hl_device *hdev = entry->hdev; char tmp_buf[32]; - u32 val; + long val; ssize_t rc; if (*ppos) @@ -842,7 +842,7 @@ static ssize_t hl_i2c_data_read(struct file *f, char __user *buf, return rc; } - sprintf(tmp_buf, "0x%02x\n", val); + sprintf(tmp_buf, "0x%02lx\n", val); rc = simple_read_from_buffer(buf, count, ppos, tmp_buf, strlen(tmp_buf)); diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index be16b75bdfdb..24b01cce0a38 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -288,7 +288,7 @@ static int device_early_init(struct hl_device *hdev) for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++) { snprintf(workq_name, 32, "hl-free-jobs-%u", i); hdev->cq_wq[i] = create_singlethread_workqueue(workq_name); - if (hdev->cq_wq == NULL) { + if (hdev->cq_wq[i] == NULL) { dev_err(hdev->dev, "Failed to allocate CQ workqueue\n"); rc = -ENOMEM; goto free_cq_wq; @@ -1069,7 +1069,7 @@ again: goto out_err; } - hl_set_max_power(hdev, hdev->max_power); + hl_set_max_power(hdev); } else { rc = hdev->asic_funcs->soft_reset_late_init(hdev); if (rc) { @@ -1318,6 +1318,11 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass) goto out_disabled; } + /* Need to call this again because the max power might change, + * depending on card type for certain ASICs + */ + hl_set_max_power(hdev); + /* * hl_hwmon_init() must be called after device_late_init(), because only * there we get the information from the device about which diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c index f70302cdab1b..f52bc690dfc5 100644 --- a/drivers/misc/habanalabs/common/firmware_if.c +++ b/drivers/misc/habanalabs/common/firmware_if.c @@ -13,6 +13,7 @@ #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/slab.h> +#define FW_FILE_MAX_SIZE 0x1400000 /* maximum size of 20MB */ /** * hl_fw_load_fw_to_device() - Load F/W code to device's memory. * @@ -48,6 +49,14 @@ int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name, dev_dbg(hdev->dev, "%s firmware size == %zu\n", fw_name, fw_size); + if (fw_size > FW_FILE_MAX_SIZE) { + dev_err(hdev->dev, + "FW file size %zu exceeds maximum of %u bytes\n", + fw_size, FW_FILE_MAX_SIZE); + rc = -EINVAL; + goto out; + } + fw_data = (const u64 *) fw->data; memcpy_toio(dst, fw_data, fw_size); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 018d9d67e8e6..edbd627b29d2 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -1462,6 +1462,8 @@ struct hl_device_idle_busy_ts { * details. * @in_reset: is device in reset flow. * @curr_pll_profile: current PLL profile. + * @card_type: Various ASICs have several card types. This indicates the card + * type of the current device. * @cs_active_cnt: number of active command submissions on this device (active * means already in H/W queues) * @major: habanalabs kernel driver major. @@ -1566,6 +1568,7 @@ struct hl_device { u64 clock_gating_mask; atomic_t in_reset; enum hl_pll_frequency curr_pll_profile; + enum armcp_card_types card_type; int cs_active_cnt; u32 major; u32 high_pll; @@ -1651,7 +1654,7 @@ struct hl_ioctl_desc { * * Return: true if the area is inside the valid range, false otherwise. */ -static inline bool hl_mem_area_inside_range(u64 address, u32 size, +static inline bool hl_mem_area_inside_range(u64 address, u64 size, u64 range_start_address, u64 range_end_address) { u64 end_address = address + size; @@ -1858,7 +1861,7 @@ int hl_get_pwm_info(struct hl_device *hdev, void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr, long value); u64 hl_get_max_power(struct hl_device *hdev); -void hl_set_max_power(struct hl_device *hdev, u64 value); +void hl_set_max_power(struct hl_device *hdev); int hl_set_voltage(struct hl_device *hdev, int sensor_index, u32 attr, long value); int hl_set_current(struct hl_device *hdev, diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index dce9273e557a..5ff4688683fd 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -66,6 +66,11 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, num_pgs = (args->alloc.mem_size + (page_size - 1)) >> page_shift; total_size = num_pgs << page_shift; + if (!total_size) { + dev_err(hdev->dev, "Cannot allocate 0 bytes\n"); + return -EINVAL; + } + contiguous = args->flags & HL_MEM_CONTIGUOUS; if (contiguous) { @@ -93,7 +98,7 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, phys_pg_pack->contiguous = contiguous; phys_pg_pack->pages = kvmalloc_array(num_pgs, sizeof(u64), GFP_KERNEL); - if (!phys_pg_pack->pages) { + if (ZERO_OR_NULL_PTR(phys_pg_pack->pages)) { rc = -ENOMEM; goto pages_arr_err; } @@ -683,7 +688,7 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx, phys_pg_pack->pages = kvmalloc_array(total_npages, sizeof(u64), GFP_KERNEL); - if (!phys_pg_pack->pages) { + if (ZERO_OR_NULL_PTR(phys_pg_pack->pages)) { rc = -ENOMEM; goto page_pack_arr_mem_err; } diff --git a/drivers/misc/habanalabs/common/mmu.c b/drivers/misc/habanalabs/common/mmu.c index edcc11d5eaf1..3fc0f497fab3 100644 --- a/drivers/misc/habanalabs/common/mmu.c +++ b/drivers/misc/habanalabs/common/mmu.c @@ -450,7 +450,7 @@ int hl_mmu_init(struct hl_device *hdev) hdev->mmu_shadow_hop0 = kvmalloc_array(prop->max_asid, prop->mmu_hop_table_size, GFP_KERNEL | __GFP_ZERO); - if (!hdev->mmu_shadow_hop0) { + if (ZERO_OR_NULL_PTR(hdev->mmu_shadow_hop0)) { rc = -ENOMEM; goto err_pool_add; } diff --git a/drivers/misc/habanalabs/common/pci.c b/drivers/misc/habanalabs/common/pci.c index 7bd3737571f3..2770f03b6cbb 100644 --- a/drivers/misc/habanalabs/common/pci.c +++ b/drivers/misc/habanalabs/common/pci.c @@ -227,7 +227,7 @@ int hl_pci_set_inbound_region(struct hl_device *hdev, u8 region, } /* Point to the specified address */ - rc = hl_pci_iatu_write(hdev, offset + 0x14, + rc |= hl_pci_iatu_write(hdev, offset + 0x14, lower_32_bits(pci_region->addr)); rc |= hl_pci_iatu_write(hdev, offset + 0x18, upper_32_bits(pci_region->addr)); @@ -369,15 +369,17 @@ int hl_pci_init(struct hl_device *hdev) rc = hdev->asic_funcs->init_iatu(hdev); if (rc) { dev_err(hdev->dev, "Failed to initialize iATU\n"); - goto disable_device; + goto unmap_pci_bars; } rc = hl_pci_set_dma_mask(hdev); if (rc) - goto disable_device; + goto unmap_pci_bars; return 0; +unmap_pci_bars: + hl_pci_bars_unmap(hdev); disable_device: pci_clear_master(pdev); pci_disable_device(pdev); diff --git a/drivers/misc/habanalabs/common/sysfs.c b/drivers/misc/habanalabs/common/sysfs.c index b3cb0ac4721c..5ae484cc84cd 100644 --- a/drivers/misc/habanalabs/common/sysfs.c +++ b/drivers/misc/habanalabs/common/sysfs.c @@ -81,7 +81,7 @@ u64 hl_get_max_power(struct hl_device *hdev) return result; } -void hl_set_max_power(struct hl_device *hdev, u64 value) +void hl_set_max_power(struct hl_device *hdev) { struct armcp_packet pkt; int rc; @@ -90,7 +90,7 @@ void hl_set_max_power(struct hl_device *hdev, u64 value) pkt.ctl = cpu_to_le32(ARMCP_PACKET_MAX_POWER_SET << ARMCP_PKT_CTL_OPCODE_SHIFT); - pkt.value = cpu_to_le64(value); + pkt.value = cpu_to_le64(hdev->max_power); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL); @@ -316,7 +316,7 @@ static ssize_t max_power_store(struct device *dev, } hdev->max_power = value; - hl_set_max_power(hdev, value); + hl_set_max_power(hdev); out: return count; @@ -422,6 +422,7 @@ int hl_sysfs_init(struct hl_device *hdev) hdev->pm_mng_profile = PM_AUTO; else hdev->pm_mng_profile = PM_MANUAL; + hdev->max_power = hdev->asic_prop.max_power_default; hdev->asic_funcs->add_device_attr(hdev, &hl_dev_clks_attr_group); diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 00a0a7238d81..4009b7df4caf 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -154,6 +154,29 @@ static const u16 gaudi_packet_sizes[MAX_PACKET_ID] = { [PACKET_LOAD_AND_EXE] = sizeof(struct packet_load_and_exe) }; +static inline bool validate_packet_id(enum packet_id id) +{ + switch (id) { + case PACKET_WREG_32: + case PACKET_WREG_BULK: + case PACKET_MSG_LONG: + case PACKET_MSG_SHORT: + case PACKET_CP_DMA: + case PACKET_REPEAT: + case PACKET_MSG_PROT: + case PACKET_FENCE: + case PACKET_LIN_DMA: + case PACKET_NOP: + case PACKET_STOP: + case PACKET_ARB_POINT: + case PACKET_WAIT: + case PACKET_LOAD_AND_EXE: + return true; + default: + return false; + } +} + static const char * const gaudi_tpc_interrupts_cause[GAUDI_NUM_OF_TPC_INTR_CAUSE] = { "tpc_address_exceed_slm", @@ -433,7 +456,7 @@ static int gaudi_get_fixed_properties(struct hl_device *hdev) prop->num_of_events = GAUDI_EVENT_SIZE; prop->tpc_enabled_mask = TPC_ENABLED_MASK; - prop->max_power_default = MAX_POWER_DEFAULT; + prop->max_power_default = MAX_POWER_DEFAULT_PCI; prop->cb_pool_cb_cnt = GAUDI_CB_POOL_CB_CNT; prop->cb_pool_cb_size = GAUDI_CB_POOL_CB_SIZE; @@ -2485,6 +2508,7 @@ static void gaudi_set_clock_gating(struct hl_device *hdev) { struct gaudi_device *gaudi = hdev->asic_specific; u32 qman_offset; + bool enable; int i; /* In case we are during debug session, don't enable the clock gate @@ -2494,46 +2518,43 @@ static void gaudi_set_clock_gating(struct hl_device *hdev) return; for (i = GAUDI_PCI_DMA_1, qman_offset = 0 ; i < GAUDI_HBM_DMA_1 ; i++) { - if (!(hdev->clock_gating_mask & - (BIT_ULL(gaudi_dma_assignment[i])))) - continue; + enable = !!(hdev->clock_gating_mask & + (BIT_ULL(gaudi_dma_assignment[i]))); qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET; - WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); + WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, + enable ? QMAN_CGM1_PWR_GATE_EN : 0); WREG32(mmDMA0_QM_CGM_CFG + qman_offset, - QMAN_UPPER_CP_CGM_PWR_GATE_EN); + enable ? QMAN_UPPER_CP_CGM_PWR_GATE_EN : 0); } for (i = GAUDI_HBM_DMA_1 ; i < GAUDI_DMA_MAX ; i++) { - if (!(hdev->clock_gating_mask & - (BIT_ULL(gaudi_dma_assignment[i])))) - continue; + enable = !!(hdev->clock_gating_mask & + (BIT_ULL(gaudi_dma_assignment[i]))); qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET; - WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); + WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, + enable ? QMAN_CGM1_PWR_GATE_EN : 0); WREG32(mmDMA0_QM_CGM_CFG + qman_offset, - QMAN_COMMON_CP_CGM_PWR_GATE_EN); + enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0); } - if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_0))) { - WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); - WREG32(mmMME0_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN); - } + enable = !!(hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_0))); + WREG32(mmMME0_QM_CGM_CFG1, enable ? QMAN_CGM1_PWR_GATE_EN : 0); + WREG32(mmMME0_QM_CGM_CFG, enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0); - if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_2))) { - WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); - WREG32(mmMME2_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN); - } + enable = !!(hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_2))); + WREG32(mmMME2_QM_CGM_CFG1, enable ? QMAN_CGM1_PWR_GATE_EN : 0); + WREG32(mmMME2_QM_CGM_CFG, enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0); for (i = 0, qman_offset = 0 ; i < TPC_NUMBER_OF_ENGINES ; i++) { - if (!(hdev->clock_gating_mask & - (BIT_ULL(GAUDI_ENGINE_ID_TPC_0 + i)))) - continue; + enable = !!(hdev->clock_gating_mask & + (BIT_ULL(GAUDI_ENGINE_ID_TPC_0 + i))); WREG32(mmTPC0_QM_CGM_CFG1 + qman_offset, - QMAN_CGM1_PWR_GATE_EN); + enable ? QMAN_CGM1_PWR_GATE_EN : 0); WREG32(mmTPC0_QM_CGM_CFG + qman_offset, - QMAN_COMMON_CP_CGM_PWR_GATE_EN); + enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0); qman_offset += TPC_QMAN_OFFSET; } @@ -3772,6 +3793,12 @@ static int gaudi_validate_cb(struct hl_device *hdev, PACKET_HEADER_PACKET_ID_MASK) >> PACKET_HEADER_PACKET_ID_SHIFT); + if (!validate_packet_id(pkt_id)) { + dev_err(hdev->dev, "Invalid packet id %u\n", pkt_id); + rc = -EINVAL; + break; + } + pkt_size = gaudi_packet_sizes[pkt_id]; cb_parsed_length += pkt_size; if (cb_parsed_length > parser->user_cb_size) { @@ -3995,6 +4022,12 @@ static int gaudi_patch_cb(struct hl_device *hdev, PACKET_HEADER_PACKET_ID_MASK) >> PACKET_HEADER_PACKET_ID_SHIFT); + if (!validate_packet_id(pkt_id)) { + dev_err(hdev->dev, "Invalid packet id %u\n", pkt_id); + rc = -EINVAL; + break; + } + pkt_size = gaudi_packet_sizes[pkt_id]; cb_parsed_length += pkt_size; if (cb_parsed_length > parser->user_cb_size) { @@ -5215,7 +5248,7 @@ static int gaudi_extract_ecc_info(struct hl_device *hdev, *memory_wrapper_idx = 0xFF; /* Iterate through memory wrappers, a single bit must be set */ - for (i = 0 ; i > num_mem_regs ; i++) { + for (i = 0 ; i < num_mem_regs ; i++) { err_addr += i * 4; err_word = RREG32(err_addr); if (err_word) { @@ -6022,6 +6055,15 @@ static int gaudi_armcp_info_get(struct hl_device *hdev) strncpy(prop->armcp_info.card_name, GAUDI_DEFAULT_CARD_NAME, CARD_NAME_MAX_LEN); + hdev->card_type = le32_to_cpu(hdev->asic_prop.armcp_info.card_type); + + if (hdev->card_type == armcp_card_type_pci) + prop->max_power_default = MAX_POWER_DEFAULT_PCI; + else if (hdev->card_type == armcp_card_type_pmc) + prop->max_power_default = MAX_POWER_DEFAULT_PMC; + + hdev->max_power = prop->max_power_default; + return 0; } diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h index 5dc99f6f0296..82137c3f3e2e 100644 --- a/drivers/misc/habanalabs/gaudi/gaudiP.h +++ b/drivers/misc/habanalabs/gaudi/gaudiP.h @@ -41,7 +41,8 @@ #define GAUDI_MAX_CLK_FREQ 2200000000ull /* 2200 MHz */ -#define MAX_POWER_DEFAULT 200000 /* 200W */ +#define MAX_POWER_DEFAULT_PCI 200000 /* 200W */ +#define MAX_POWER_DEFAULT_PMC 350000 /* 350W */ #define GAUDI_CPU_TIMEOUT_USEC 15000000 /* 15s */ diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c index 5673ee49819e..881531d4d9da 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c +++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c @@ -527,7 +527,7 @@ static int gaudi_config_etf(struct hl_device *hdev, } static bool gaudi_etr_validate_address(struct hl_device *hdev, u64 addr, - u32 size, bool *is_host) + u64 size, bool *is_host) { struct asic_fixed_properties *prop = &hdev->asic_prop; struct gaudi_device *gaudi = hdev->asic_specific; @@ -539,6 +539,12 @@ static bool gaudi_etr_validate_address(struct hl_device *hdev, u64 addr, return false; } + if (addr > (addr + size)) { + dev_err(hdev->dev, + "ETR buffer size %llu overflow\n", size); + return false; + } + /* PMMU and HPMMU addresses are equal, check only one of them */ if ((gaudi->hw_cap_initialized & HW_CAP_MMU) && hl_mem_area_inside_range(addr, size, diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 85030759b2af..33cd2ae653d2 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -139,6 +139,25 @@ static u16 goya_packet_sizes[MAX_PACKET_ID] = { [PACKET_STOP] = sizeof(struct packet_stop) }; +static inline bool validate_packet_id(enum packet_id id) +{ + switch (id) { + case PACKET_WREG_32: + case PACKET_WREG_BULK: + case PACKET_MSG_LONG: + case PACKET_MSG_SHORT: + case PACKET_CP_DMA: + case PACKET_MSG_PROT: + case PACKET_FENCE: + case PACKET_LIN_DMA: + case PACKET_NOP: + case PACKET_STOP: + return true; + default: + return false; + } +} + static u64 goya_mmu_regs[GOYA_MMU_REGS_NUM] = { mmDMA_QM_0_GLBL_NON_SECURE_PROPS, mmDMA_QM_1_GLBL_NON_SECURE_PROPS, @@ -3455,6 +3474,12 @@ static int goya_validate_cb(struct hl_device *hdev, PACKET_HEADER_PACKET_ID_MASK) >> PACKET_HEADER_PACKET_ID_SHIFT); + if (!validate_packet_id(pkt_id)) { + dev_err(hdev->dev, "Invalid packet id %u\n", pkt_id); + rc = -EINVAL; + break; + } + pkt_size = goya_packet_sizes[pkt_id]; cb_parsed_length += pkt_size; if (cb_parsed_length > parser->user_cb_size) { @@ -3690,6 +3715,12 @@ static int goya_patch_cb(struct hl_device *hdev, PACKET_HEADER_PACKET_ID_MASK) >> PACKET_HEADER_PACKET_ID_SHIFT); + if (!validate_packet_id(pkt_id)) { + dev_err(hdev->dev, "Invalid packet id %u\n", pkt_id); + rc = -EINVAL; + break; + } + pkt_size = goya_packet_sizes[pkt_id]; cb_parsed_length += pkt_size; if (cb_parsed_length > parser->user_cb_size) { diff --git a/drivers/misc/habanalabs/goya/goya_coresight.c b/drivers/misc/habanalabs/goya/goya_coresight.c index b03912483de0..4027a6a334d7 100644 --- a/drivers/misc/habanalabs/goya/goya_coresight.c +++ b/drivers/misc/habanalabs/goya/goya_coresight.c @@ -362,11 +362,17 @@ static int goya_config_etf(struct hl_device *hdev, } static int goya_etr_validate_address(struct hl_device *hdev, u64 addr, - u32 size) + u64 size) { struct asic_fixed_properties *prop = &hdev->asic_prop; u64 range_start, range_end; + if (addr > (addr + size)) { + dev_err(hdev->dev, + "ETR buffer size %llu overflow\n", size); + return false; + } + if (hdev->mmu_enable) { range_start = prop->dmmu.start_addr; range_end = prop->dmmu.end_addr; diff --git a/drivers/misc/mei/hdcp/mei_hdcp.c b/drivers/misc/mei/hdcp/mei_hdcp.c index d1d3e025ca0e..9ae9669e46ea 100644 --- a/drivers/misc/mei/hdcp/mei_hdcp.c +++ b/drivers/misc/mei/hdcp/mei_hdcp.c @@ -546,38 +546,46 @@ static int mei_hdcp_verify_mprime(struct device *dev, struct hdcp_port_data *data, struct hdcp2_rep_stream_ready *stream_ready) { - struct wired_cmd_repeater_auth_stream_req_in - verify_mprime_in = { { 0 } }; + struct wired_cmd_repeater_auth_stream_req_in *verify_mprime_in; struct wired_cmd_repeater_auth_stream_req_out verify_mprime_out = { { 0 } }; struct mei_cl_device *cldev; ssize_t byte; + size_t cmd_size; if (!dev || !stream_ready || !data) return -EINVAL; cldev = to_mei_cl_device(dev); - verify_mprime_in.header.api_version = HDCP_API_VERSION; - verify_mprime_in.header.command_id = WIRED_REPEATER_AUTH_STREAM_REQ; - verify_mprime_in.header.status = ME_HDCP_STATUS_SUCCESS; - verify_mprime_in.header.buffer_len = + cmd_size = struct_size(verify_mprime_in, streams, data->k); + if (cmd_size == SIZE_MAX) + return -EINVAL; + + verify_mprime_in = kzalloc(cmd_size, GFP_KERNEL); + if (!verify_mprime_in) + return -ENOMEM; + + verify_mprime_in->header.api_version = HDCP_API_VERSION; + verify_mprime_in->header.command_id = WIRED_REPEATER_AUTH_STREAM_REQ; + verify_mprime_in->header.status = ME_HDCP_STATUS_SUCCESS; + verify_mprime_in->header.buffer_len = WIRED_CMD_BUF_LEN_REPEATER_AUTH_STREAM_REQ_MIN_IN; - verify_mprime_in.port.integrated_port_type = data->port_type; - verify_mprime_in.port.physical_port = (u8)data->fw_ddi; - verify_mprime_in.port.attached_transcoder = (u8)data->fw_tc; + verify_mprime_in->port.integrated_port_type = data->port_type; + verify_mprime_in->port.physical_port = (u8)data->fw_ddi; + verify_mprime_in->port.attached_transcoder = (u8)data->fw_tc; + + memcpy(verify_mprime_in->m_prime, stream_ready->m_prime, HDCP_2_2_MPRIME_LEN); + drm_hdcp_cpu_to_be24(verify_mprime_in->seq_num_m, data->seq_num_m); - memcpy(verify_mprime_in.m_prime, stream_ready->m_prime, - HDCP_2_2_MPRIME_LEN); - drm_hdcp_cpu_to_be24(verify_mprime_in.seq_num_m, data->seq_num_m); - memcpy(verify_mprime_in.streams, data->streams, + memcpy(verify_mprime_in->streams, data->streams, array_size(data->k, sizeof(*data->streams))); - verify_mprime_in.k = cpu_to_be16(data->k); + verify_mprime_in->k = cpu_to_be16(data->k); - byte = mei_cldev_send(cldev, (u8 *)&verify_mprime_in, - sizeof(verify_mprime_in)); + byte = mei_cldev_send(cldev, (u8 *)verify_mprime_in, cmd_size); + kfree(verify_mprime_in); if (byte < 0) { dev_dbg(dev, "mei_cldev_send failed. %zd\n", byte); return byte; diff --git a/drivers/misc/mic/scif/scif_api.c b/drivers/misc/mic/scif/scif_api.c index 9cc6b2a6cf22..304d6c833712 100644 --- a/drivers/misc/mic/scif/scif_api.c +++ b/drivers/misc/mic/scif/scif_api.c @@ -178,7 +178,7 @@ int scif_close(scif_epd_t epd) case SCIFEP_ZOMBIE: dev_err(scif_info.mdev.this_device, "SCIFAPI close: zombie state unexpected\n"); - /* fall through */ + fallthrough; case SCIFEP_DISCONNECTED: spin_unlock(&ep->lock); scif_unregister_all_windows(epd); @@ -645,7 +645,7 @@ int __scif_connect(scif_epd_t epd, struct scif_port_id *dst, bool non_block) ep->port.port = err; ep->port.node = scif_info.nodeid; ep->conn_async_state = ASYNC_CONN_IDLE; - /* Fall through */ + fallthrough; case SCIFEP_BOUND: /* * If a non-blocking connect has been already initiated diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c index de8f61efaef5..2da3b474f486 100644 --- a/drivers/misc/mic/scif/scif_rma.c +++ b/drivers/misc/mic/scif/scif_rma.c @@ -657,7 +657,7 @@ int scif_unregister_window(struct scif_window *window) window->unreg_state = OP_IN_PROGRESS; send_msg = true; } - /* fall through */ + fallthrough; case OP_IN_PROGRESS: { scif_get_window(window, 1); diff --git a/drivers/misc/sgi-gru/grukservices.c b/drivers/misc/sgi-gru/grukservices.c index f6e600bfac5d..0ea923fe6371 100644 --- a/drivers/misc/sgi-gru/grukservices.c +++ b/drivers/misc/sgi-gru/grukservices.c @@ -622,7 +622,7 @@ static int send_noop_message(void *cb, struct gru_message_queue_desc *mqd, break; case CBSS_PAGE_OVERFLOW: STAT(mesq_noop_page_overflow); - /* fall through */ + fallthrough; default: BUG(); } @@ -780,7 +780,7 @@ static int send_message_failure(void *cb, struct gru_message_queue_desc *mqd, break; case CBSS_PAGE_OVERFLOW: STAT(mesq_page_overflow); - /* fall through */ + fallthrough; default: BUG(); } diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c index d5e097cd556d..8a495dc82f16 100644 --- a/drivers/misc/sgi-xp/xpc_main.c +++ b/drivers/misc/sgi-xp/xpc_main.c @@ -1173,7 +1173,7 @@ xpc_system_die(struct notifier_block *nb, unsigned long event, void *_die_args) if (!xpc_kdebug_ignore) break; - /* fall through */ + fallthrough; case DIE_MCA_MONARCH_ENTER: case DIE_INIT_MONARCH_ENTER: xpc_arch_ops.offline_heartbeat(); @@ -1184,7 +1184,7 @@ xpc_system_die(struct notifier_block *nb, unsigned long event, void *_die_args) if (!xpc_kdebug_ignore) break; - /* fall through */ + fallthrough; case DIE_MCA_MONARCH_LEAVE: case DIE_INIT_MONARCH_LEAVE: xpc_arch_ops.online_heartbeat(); diff --git a/drivers/misc/sgi-xp/xpc_partition.c b/drivers/misc/sgi-xp/xpc_partition.c index 21a04bc97d40..099a53bdbb7d 100644 --- a/drivers/misc/sgi-xp/xpc_partition.c +++ b/drivers/misc/sgi-xp/xpc_partition.c @@ -441,10 +441,10 @@ xpc_discovery(void) switch (region_size) { case 128: max_regions *= 2; - /* fall through */ + fallthrough; case 64: max_regions *= 2; - /* fall through */ + fallthrough; case 32: max_regions *= 2; region_size = 16; diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index 98c60f11b76b..7791bde81a36 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -574,7 +574,7 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, xpc_wakeup_channel_mgr(part); } - /* fall through */ + fallthrough; case XPC_ACTIVATE_MQ_MSG_MARK_ENGAGED_UV: spin_lock_irqsave(&part_uv->flags_lock, irq_flags); part_uv->flags |= XPC_P_ENGAGED_UV; diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index ce43f7573d80..c8fae6611b73 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -191,7 +191,7 @@ int mmc_of_parse(struct mmc_host *host) switch (bus_width) { case 8: host->caps |= MMC_CAP_8_BIT_DATA; - /* fall through - Hosts capable of 8-bit can also do 4 bits */ + fallthrough; /* Hosts capable of 8-bit can also do 4 bits */ case 4: host->caps |= MMC_CAP_4_BIT_DATA; break; diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index 300901415aa2..3fc3bbea8536 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -2418,7 +2418,7 @@ static void atmci_get_cap(struct atmel_mci *host) case 0x600: case 0x500: host->caps.has_odd_clk_div = 1; - /* Fall through */ + fallthrough; case 0x400: case 0x300: host->caps.has_dma_conf_reg = 1; @@ -2426,16 +2426,16 @@ static void atmci_get_cap(struct atmel_mci *host) host->caps.has_cfg_reg = 1; host->caps.has_cstor_reg = 1; host->caps.has_highspeed = 1; - /* Fall through */ + fallthrough; case 0x200: host->caps.has_rwproof = 1; host->caps.need_blksz_mul_4 = 0; host->caps.need_notbusy_for_read_ops = 1; - /* Fall through */ + fallthrough; case 0x100: host->caps.has_bad_data_ordering = 0; host->caps.need_reset_after_xfer = 0; - /* Fall through */ + fallthrough; case 0x0: break; default: diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c index f01fecd75833..e50a08bce7ef 100644 --- a/drivers/mmc/host/davinci_mmc.c +++ b/drivers/mmc/host/davinci_mmc.c @@ -300,7 +300,7 @@ static void mmc_davinci_start_command(struct mmc_davinci_host *host, * then it's harmless for us to allow it. */ cmd_reg |= MMCCMD_BSYEXP; - /* FALLTHROUGH */ + fallthrough; case MMC_RSP_R1: /* 48 bits, CRC */ cmd_reg |= MMCCMD_RSPFMT_R1456; break; diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c index 50977ff18074..db1a84b2ba61 100644 --- a/drivers/mmc/host/dw_mmc-k3.c +++ b/drivers/mmc/host/dw_mmc-k3.c @@ -238,7 +238,7 @@ static void dw_mci_hs_set_timing(struct dw_mci *host, int timing, if (smpl_phase >= USE_DLY_MIN_SMPL && smpl_phase <= USE_DLY_MAX_SMPL) use_smpl_dly = 1; - /* fallthrough */ + fallthrough; case MMC_TIMING_UHS_SDR50: if (smpl_phase >= ENABLE_SHIFT_MIN_SMPL && smpl_phase <= ENABLE_SHIFT_MAX_SMPL) diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 35ae5737c622..0fba940544ca 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -2030,7 +2030,7 @@ static void dw_mci_tasklet_func(unsigned long priv) } prev_state = state = STATE_SENDING_DATA; - /* fall through */ + fallthrough; case STATE_SENDING_DATA: /* @@ -2088,7 +2088,7 @@ static void dw_mci_tasklet_func(unsigned long priv) } prev_state = state = STATE_DATA_BUSY; - /* fall through */ + fallthrough; case STATE_DATA_BUSY: if (!dw_mci_clear_pending_data_complete(host)) { @@ -2141,7 +2141,7 @@ static void dw_mci_tasklet_func(unsigned long priv) */ prev_state = state = STATE_SENDING_STOP; - /* fall through */ + fallthrough; case STATE_SENDING_STOP: if (!dw_mci_clear_pending_cmd_complete(host)) diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index 447552ac25c4..81d71010b474 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -739,7 +739,7 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid) break; jz_mmc_prepare_data_transfer(host); - /* fall through */ + fallthrough; case JZ4740_MMC_STATE_TRANSFER_DATA: if (host->use_dma) { @@ -774,7 +774,7 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid) break; } jz4740_mmc_write_irq_reg(host, JZ_MMC_IRQ_DATA_TRAN_DONE); - /* fall through */ + fallthrough; case JZ4740_MMC_STATE_SEND_STOP: if (!req->stop) diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c index 9b2cf7afc246..703d5834f9a5 100644 --- a/drivers/mmc/host/meson-mx-sdio.c +++ b/drivers/mmc/host/meson-mx-sdio.c @@ -294,7 +294,7 @@ static void meson_mx_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) switch (ios->power_mode) { case MMC_POWER_OFF: vdd = 0; - /* fall through */ + fallthrough; case MMC_POWER_UP: if (!IS_ERR(mmc->supply.vmmc)) { host->error = mmc_regulator_set_ocr(mmc, diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 4e2583f69a63..b0c27944db7f 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -22,6 +22,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> +#include <linux/reset.h> #include <linux/mmc/card.h> #include <linux/mmc/core.h> @@ -419,6 +420,7 @@ struct msdc_host { struct pinctrl_state *pins_uhs; struct delayed_work req_timeout; int irq; /* host interrupt */ + struct reset_control *reset; struct clk *src_clk; /* msdc source clock */ struct clk *h_clk; /* msdc h_clk */ @@ -1592,6 +1594,12 @@ static void msdc_init_hw(struct msdc_host *host) u32 val; u32 tune_reg = host->dev_comp->pad_tune_reg; + if (host->reset) { + reset_control_assert(host->reset); + usleep_range(10, 50); + reset_control_deassert(host->reset); + } + /* Configure to MMC/SD mode, clock free running */ sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_MODE | MSDC_CFG_CKPDN); @@ -2390,6 +2398,11 @@ static int msdc_drv_probe(struct platform_device *pdev) if (IS_ERR(host->src_clk_cg)) host->src_clk_cg = NULL; + host->reset = devm_reset_control_get_optional_exclusive(&pdev->dev, + "hrst"); + if (IS_ERR(host->reset)) + return PTR_ERR(host->reset); + host->irq = platform_get_irq(pdev, 0); if (host->irq < 0) { ret = -EINVAL; diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 15e21894bd44..904f5237d8f7 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -685,7 +685,7 @@ static int renesas_sdhi_write16_hook(struct tmio_mmc_host *host, int addr) case HOST_MODE: if (host->pdata->flags & TMIO_MMC_HAVE_CBSY) bit = TMIO_STAT_CMD_BUSY; - /* fallthrough */ + fallthrough; case CTL_SD_CARD_CLK_CTL: return renesas_sdhi_wait_idle(host, bit); } diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index 48ecbd0b180d..962f074ca174 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -535,6 +535,11 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_qcom_sd = { .caps = MMC_CAP_NONREMOVABLE, }; +struct amd_sdhci_host { + bool tuned_clock; + bool dll_enabled; +}; + /* AMD sdhci reset dll register. */ #define SDHCI_AMD_RESET_DLL_REGISTER 0x908 @@ -555,26 +560,66 @@ static void sdhci_acpi_amd_hs400_dll(struct sdhci_host *host) } /* - * For AMD Platform it is required to disable the tuning - * bit first controller to bring to HS Mode from HS200 - * mode, later enable to tune to HS400 mode. + * The initialization sequence for HS400 is: + * HS->HS200->Perform Tuning->HS->HS400 + * + * The re-tuning sequence is: + * HS400->DDR52->HS->HS200->Perform Tuning->HS->HS400 + * + * The AMD eMMC Controller can only use the tuned clock while in HS200 and HS400 + * mode. If we switch to a different mode, we need to disable the tuned clock. + * If we have previously performed tuning and switch back to HS200 or + * HS400, we can re-enable the tuned clock. + * */ static void amd_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) { struct sdhci_host *host = mmc_priv(mmc); + struct sdhci_acpi_host *acpi_host = sdhci_priv(host); + struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host); unsigned int old_timing = host->timing; + u16 val; sdhci_set_ios(mmc, ios); - if (old_timing == MMC_TIMING_MMC_HS200 && - ios->timing == MMC_TIMING_MMC_HS) - sdhci_writew(host, 0x9, SDHCI_HOST_CONTROL2); - if (old_timing != MMC_TIMING_MMC_HS400 && - ios->timing == MMC_TIMING_MMC_HS400) { - sdhci_writew(host, 0x80, SDHCI_HOST_CONTROL2); - sdhci_acpi_amd_hs400_dll(host); + + if (old_timing != host->timing && amd_host->tuned_clock) { + if (host->timing == MMC_TIMING_MMC_HS400 || + host->timing == MMC_TIMING_MMC_HS200) { + val = sdhci_readw(host, SDHCI_HOST_CONTROL2); + val |= SDHCI_CTRL_TUNED_CLK; + sdhci_writew(host, val, SDHCI_HOST_CONTROL2); + } else { + val = sdhci_readw(host, SDHCI_HOST_CONTROL2); + val &= ~SDHCI_CTRL_TUNED_CLK; + sdhci_writew(host, val, SDHCI_HOST_CONTROL2); + } + + /* DLL is only required for HS400 */ + if (host->timing == MMC_TIMING_MMC_HS400 && + !amd_host->dll_enabled) { + sdhci_acpi_amd_hs400_dll(host); + amd_host->dll_enabled = true; + } } } +static int amd_sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode) +{ + int err; + struct sdhci_host *host = mmc_priv(mmc); + struct sdhci_acpi_host *acpi_host = sdhci_priv(host); + struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host); + + amd_host->tuned_clock = false; + + err = sdhci_execute_tuning(mmc, opcode); + + if (!err && !host->tuning_err) + amd_host->tuned_clock = true; + + return err; +} + static const struct sdhci_ops sdhci_acpi_ops_amd = { .set_clock = sdhci_set_clock, .set_bus_width = sdhci_set_bus_width, @@ -602,6 +647,7 @@ static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev, host->mmc_host_ops.select_drive_strength = amd_select_drive_strength; host->mmc_host_ops.set_ios = amd_set_ios; + host->mmc_host_ops.execute_tuning = amd_sdhci_execute_tuning; return 0; } @@ -613,6 +659,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_amd_emmc = { SDHCI_QUIRK_32BIT_ADMA_SIZE, .quirks2 = SDHCI_QUIRK2_BROKEN_64_BIT_DMA, .probe_slot = sdhci_acpi_emmc_amd_probe_slot, + .priv_size = sizeof(struct amd_sdhci_host), }; struct sdhci_acpi_uid_slot { diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index a76b4513fbec..d738907a622f 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1556,7 +1556,7 @@ static int sdhci_esdhc_imx_probe_nondt(struct platform_device *pdev, "failed to request card-detect gpio!\n"); return err; } - /* fall through */ + fallthrough; case ESDHC_CD_CONTROLLER: /* we have a working card_detect back */ diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index bb6802448b2f..af413805bbf1 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -232,6 +232,14 @@ static void sdhci_pci_dumpregs(struct mmc_host *mmc) sdhci_dumpregs(mmc_priv(mmc)); } +static void sdhci_cqhci_reset(struct sdhci_host *host, u8 mask) +{ + if ((host->mmc->caps2 & MMC_CAP2_CQE) && (mask & SDHCI_RESET_ALL) && + host->mmc->cqe_private) + cqhci_deactivate(host->mmc); + sdhci_reset(host, mask); +} + /*****************************************************************************\ * * * Hardware specific quirk handling * @@ -718,7 +726,7 @@ static const struct sdhci_ops sdhci_intel_glk_ops = { .set_power = sdhci_intel_set_power, .enable_dma = sdhci_pci_enable_dma, .set_bus_width = sdhci_set_bus_width, - .reset = sdhci_reset, + .reset = sdhci_cqhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, .irq = sdhci_cqhci_irq, diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c index 9194bb73e601..080ced1e63f0 100644 --- a/drivers/mmc/host/sdhci-s3c.c +++ b/drivers/mmc/host/sdhci-s3c.c @@ -609,7 +609,7 @@ static int sdhci_s3c_probe(struct platform_device *pdev) switch (pdata->max_width) { case 8: host->mmc->caps |= MMC_CAP_8_BIT_DATA; - /* Fall through */ + fallthrough; case 4: host->mmc->caps |= MMC_CAP_4_BIT_DATA; break; diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index a910cb461ed7..bafa2e41c8b6 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -470,7 +470,7 @@ static int sdhci_sprd_voltage_switch(struct mmc_host *mmc, struct mmc_ios *ios) break; default: - /* fall-through */ + fallthrough; case MMC_SIGNAL_VOLTAGE_330: ret = pinctrl_select_state(sprd_host->pinctrl, sprd_host->pins_default); diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 0a3f9d024f2a..13fbf70b5fde 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -110,6 +110,12 @@ #define NVQUIRK_DIS_CARD_CLK_CONFIG_TAP BIT(8) #define NVQUIRK_CQHCI_DCMD_R1B_CMD_TIMING BIT(9) +/* + * NVQUIRK_HAS_TMCLK is for SoC's having separate timeout clock for Tegra + * SDMMC hardware data timeout. + */ +#define NVQUIRK_HAS_TMCLK BIT(10) + /* SDMMC CQE Base Address for Tegra Host Ver 4.1 and Higher */ #define SDHCI_TEGRA_CQE_BASE_ADDR 0xF000 @@ -140,6 +146,7 @@ struct sdhci_tegra_autocal_offsets { struct sdhci_tegra { const struct sdhci_tegra_soc_data *soc_data; struct gpio_desc *power_gpio; + struct clk *tmclk; bool ddr_signaling; bool pad_calib_required; bool pad_control_available; @@ -1418,7 +1425,6 @@ static const struct sdhci_ops tegra210_sdhci_ops = { static const struct sdhci_pltfm_data sdhci_tegra210_pdata = { .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | - SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | SDHCI_QUIRK_SINGLE_POWER_WRITE | SDHCI_QUIRK_NO_HISPD_BIT | SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC | @@ -1434,7 +1440,8 @@ static const struct sdhci_tegra_soc_data soc_data_tegra210 = { NVQUIRK_HAS_PADCALIB | NVQUIRK_DIS_CARD_CLK_CONFIG_TAP | NVQUIRK_ENABLE_SDR50 | - NVQUIRK_ENABLE_SDR104, + NVQUIRK_ENABLE_SDR104 | + NVQUIRK_HAS_TMCLK, .min_tap_delay = 106, .max_tap_delay = 185, }; @@ -1456,7 +1463,6 @@ static const struct sdhci_ops tegra186_sdhci_ops = { static const struct sdhci_pltfm_data sdhci_tegra186_pdata = { .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | - SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | SDHCI_QUIRK_SINGLE_POWER_WRITE | SDHCI_QUIRK_NO_HISPD_BIT | SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC | @@ -1473,6 +1479,7 @@ static const struct sdhci_tegra_soc_data soc_data_tegra186 = { NVQUIRK_DIS_CARD_CLK_CONFIG_TAP | NVQUIRK_ENABLE_SDR50 | NVQUIRK_ENABLE_SDR104 | + NVQUIRK_HAS_TMCLK | NVQUIRK_CQHCI_DCMD_R1B_CMD_TIMING, .min_tap_delay = 84, .max_tap_delay = 136, @@ -1485,7 +1492,8 @@ static const struct sdhci_tegra_soc_data soc_data_tegra194 = { NVQUIRK_HAS_PADCALIB | NVQUIRK_DIS_CARD_CLK_CONFIG_TAP | NVQUIRK_ENABLE_SDR50 | - NVQUIRK_ENABLE_SDR104, + NVQUIRK_ENABLE_SDR104 | + NVQUIRK_HAS_TMCLK, .min_tap_delay = 96, .max_tap_delay = 139, }; @@ -1613,6 +1621,43 @@ static int sdhci_tegra_probe(struct platform_device *pdev) goto err_power_req; } + /* + * Tegra210 has a separate SDMMC_LEGACY_TM clock used for host + * timeout clock and SW can choose TMCLK or SDCLK for hardware + * data timeout through the bit USE_TMCLK_FOR_DATA_TIMEOUT of + * the register SDHCI_TEGRA_VENDOR_SYS_SW_CTRL. + * + * USE_TMCLK_FOR_DATA_TIMEOUT bit default is set to 1 and SDMMC uses + * 12Mhz TMCLK which is advertised in host capability register. + * With TMCLK of 12Mhz provides maximum data timeout period that can + * be achieved is 11s better than using SDCLK for data timeout. + * + * So, TMCLK is set to 12Mhz and kept enabled all the time on SoC's + * supporting separate TMCLK. + */ + + if (soc_data->nvquirks & NVQUIRK_HAS_TMCLK) { + clk = devm_clk_get(&pdev->dev, "tmclk"); + if (IS_ERR(clk)) { + rc = PTR_ERR(clk); + if (rc == -EPROBE_DEFER) + goto err_power_req; + + dev_warn(&pdev->dev, "failed to get tmclk: %d\n", rc); + clk = NULL; + } + + clk_set_rate(clk, 12000000); + rc = clk_prepare_enable(clk); + if (rc) { + dev_err(&pdev->dev, + "failed to enable tmclk: %d\n", rc); + goto err_power_req; + } + + tegra_host->tmclk = clk; + } + clk = devm_clk_get(mmc_dev(host->mmc), NULL); if (IS_ERR(clk)) { rc = PTR_ERR(clk); @@ -1656,6 +1701,7 @@ err_add_host: err_rst_get: clk_disable_unprepare(pltfm_host->clk); err_clk_get: + clk_disable_unprepare(tegra_host->tmclk); err_power_req: err_parse_dt: sdhci_pltfm_free(pdev); @@ -1673,6 +1719,7 @@ static int sdhci_tegra_remove(struct platform_device *pdev) reset_control_assert(tegra_host->rst); usleep_range(2000, 4000); clk_disable_unprepare(pltfm_host->clk); + clk_disable_unprepare(tegra_host->tmclk); sdhci_pltfm_free(pdev); diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c index e6e9e286cc34..03ce57ef4585 100644 --- a/drivers/mmc/host/sdhci-xenon-phy.c +++ b/drivers/mmc/host/sdhci-xenon-phy.c @@ -527,7 +527,7 @@ static bool xenon_emmc_phy_slow_mode(struct sdhci_host *host, ret = true; break; } - /* fall through */ + fallthrough; default: reg &= ~XENON_TIMING_ADJUST_SLOW_MODE; ret = false; diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 3ad394b40eb1..592a55a34b58 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -2825,7 +2825,7 @@ int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode) case MMC_TIMING_UHS_SDR50: if (host->flags & SDHCI_SDR50_NEEDS_TUNING) break; - /* FALLTHROUGH */ + fallthrough; default: goto out; diff --git a/drivers/mmc/host/tifm_sd.c b/drivers/mmc/host/tifm_sd.c index 5987656e0474..fd8b72d3e02c 100644 --- a/drivers/mmc/host/tifm_sd.c +++ b/drivers/mmc/host/tifm_sd.c @@ -335,7 +335,7 @@ static unsigned int tifm_sd_op_flags(struct mmc_command *cmd) break; case MMC_RSP_R1B: rc |= TIFM_MMCSD_RSP_BUSY; - /* fall-through */ + fallthrough; case MMC_RSP_R1: rc |= TIFM_MMCSD_RSP_R1; break; diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c index 369b8dee2e3d..7666c90054ae 100644 --- a/drivers/mmc/host/usdhi6rol0.c +++ b/drivers/mmc/host/usdhi6rol0.c @@ -1343,7 +1343,7 @@ static int usdhi6_stop_cmd(struct usdhi6_host *host) host->wait = USDHI6_WAIT_FOR_STOP; return 0; } - /* fall through - Unsupported STOP command. */ + fallthrough; /* Unsupported STOP command */ default: dev_err(mmc_dev(host->mmc), "unsupported stop CMD%d for CMD%d\n", @@ -1691,7 +1691,7 @@ static void usdhi6_timeout_work(struct work_struct *work) switch (host->wait) { default: dev_err(mmc_dev(host->mmc), "Invalid state %u\n", host->wait); - /* fall through - mrq can be NULL, but is impossible. */ + fallthrough; /* mrq can be NULL, but is impossible */ case USDHI6_WAIT_FOR_CMD: usdhi6_error_code(host); if (mrq) @@ -1713,7 +1713,7 @@ static void usdhi6_timeout_work(struct work_struct *work) host->offset, data->blocks, data->blksz, data->sg_len, sg_dma_len(sg), sg->offset); usdhi6_sg_unmap(host, true); - /* fall through - page unmapped in USDHI6_WAIT_FOR_DATA_END. */ + fallthrough; /* page unmapped in USDHI6_WAIT_FOR_DATA_END */ case USDHI6_WAIT_FOR_DATA_END: usdhi6_error_code(host); data->error = -ETIMEDOUT; diff --git a/drivers/mux/adgs1408.c b/drivers/mux/adgs1408.c index 12466b06692c..22ed051eb1a4 100644 --- a/drivers/mux/adgs1408.c +++ b/drivers/mux/adgs1408.c @@ -93,7 +93,7 @@ static int adgs1408_probe(struct spi_device *spi) mux->idle_state = idle_state; break; } - /* fall through */ + fallthrough; default: dev_err(dev, "invalid idle-state %d\n", idle_state); return -EINVAL; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 1368d1d6a114..c3dbe64e628e 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -473,6 +473,10 @@ config NET_SB1000 source "drivers/net/phy/Kconfig" +source "drivers/net/mdio/Kconfig" + +source "drivers/net/pcs/Kconfig" + source "drivers/net/plip/Kconfig" source "drivers/net/ppp/Kconfig" diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 94b60800887a..72e18d505d1a 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -21,6 +21,8 @@ obj-$(CONFIG_MDIO) += mdio.o obj-$(CONFIG_NET) += Space.o loopback.o obj-$(CONFIG_NETCONSOLE) += netconsole.o obj-y += phy/ +obj-y += mdio/ +obj-y += pcs/ obj-$(CONFIG_RIONET) += rionet.o obj-$(CONFIG_NET_TEAM) += team/ obj-$(CONFIG_TUN) += tun.o diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index 18428e104445..1c6c27f35ac4 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -301,7 +301,7 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) dev->irq = cops_irq(ioaddr, board); if (dev->irq) break; - /* fall through - Once no IRQ found on this port. */ + fallthrough; /* Once no IRQ found on this port */ case 1: retval = -EINVAL; goto err_out; diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 14a5fb378145..98df38fe553c 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -363,13 +363,13 @@ static int __init arcrimi_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_err("Too many arguments\n"); - /* Fall through */ + fallthrough; case 3: /* Node ID */ node = ints[3]; - /* Fall through */ + fallthrough; case 2: /* IRQ */ irq = ints[2]; - /* Fall through */ + fallthrough; case 1: /* IO address */ io = ints[1]; } diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index cd27fdc1059b..f983c4ce6b07 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -197,22 +197,22 @@ static int __init com20020isa_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_info("Too many arguments\n"); - /* Fall through */ + fallthrough; case 6: /* Timeout */ timeout = ints[6]; - /* Fall through */ + fallthrough; case 5: /* CKP value */ clockp = ints[5]; - /* Fall through */ + fallthrough; case 4: /* Backplane flag */ backplane = ints[4]; - /* Fall through */ + fallthrough; case 3: /* Node ID */ node = ints[3]; - /* Fall through */ + fallthrough; case 2: /* IRQ */ irq = ints[2]; - /* Fall through */ + fallthrough; case 1: /* IO address */ io = ints[1]; } diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 186bbf87bc84..cf214b730671 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -363,10 +363,10 @@ static int __init com90io_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_err("Too many arguments\n"); - /* Fall through */ + fallthrough; case 2: /* IRQ */ irq = ints[2]; - /* Fall through */ + fallthrough; case 1: /* IO address */ io = ints[1]; } diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index bd75d06ad7df..3dc3d533cb19 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -693,13 +693,13 @@ static int __init com90xx_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_err("Too many arguments\n"); - /* Fall through */ + fallthrough; case 3: /* Mem address */ shmem = ints[3]; - /* Fall through */ + fallthrough; case 2: /* IRQ */ irq = ints[2]; - /* Fall through */ + fallthrough; case 1: /* IO address */ io = ints[1]; } diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 31e43a2197a3..aa001b16765a 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -130,7 +130,7 @@ static inline struct bonding *__get_bond_by_port(struct port *port) /** * __get_first_agg - get the first aggregator in the bond - * @bond: the bond we're looking at + * @port: the port we're looking at * * Return the aggregator of the first slave in @bond, or %NULL if it can't be * found. @@ -1149,7 +1149,7 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) port->actor_oper_port_state &= ~LACP_STATE_EXPIRED; port->sm_rx_state = AD_RX_PORT_DISABLED; - /* Fall Through */ + fallthrough; case AD_RX_PORT_DISABLED: port->sm_vars &= ~AD_PORT_MATCHED; break; @@ -1588,7 +1588,7 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best, if (__agg_active_ports(curr) < __agg_active_ports(best)) return best; - /*FALLTHROUGH*/ + fallthrough; case BOND_AD_STABLE: case BOND_AD_BANDWIDTH: if (__get_agg_bandwidth(curr) > __get_agg_bandwidth(best)) @@ -1626,7 +1626,7 @@ static int agg_device_up(const struct aggregator *agg) /** * ad_agg_selection_logic - select an aggregation group for a team - * @aggregator: the aggregator we're looking at + * @agg: the aggregator we're looking at * @update_slave_arr: Does slave array need update? * * It is assumed that only one aggregator may be selected for a team. @@ -1810,7 +1810,7 @@ static void ad_initialize_agg(struct aggregator *aggregator) /** * ad_initialize_port - initialize a given port's parameters - * @aggregator: the aggregator we're looking at + * @port: the port we're looking at * @lacp_fast: boolean. whether fast periodic should be used */ static void ad_initialize_port(struct port *port, int lacp_fast) @@ -1967,6 +1967,7 @@ static void ad_marker_response_received(struct bond_marker *marker, /** * bond_3ad_initiate_agg_selection - initate aggregator selection * @bond: bonding struct + * @timeout: timeout value to set * * Set the aggregation selection timer, to initiate an agg selection in * the very near future. Called during first initialization, and during @@ -2259,7 +2260,7 @@ void bond_3ad_update_ad_actor_settings(struct bonding *bond) /** * bond_3ad_state_machine_handler - handle state machines timeout - * @bond: bonding struct to work on + * @work: work context to fetch bonding struct to work on from * * The state machine handling concept in this module is to check every tick * which state machine should operate any function. The execution order is @@ -2500,7 +2501,7 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave) /** * bond_3ad_handle_link_change - handle a slave's link status change indication * @slave: slave struct to work on - * @status: whether the link is now up or down + * @link: whether the link is now up or down * * Handle reselection of aggregator (if needed) for this port. */ @@ -2551,7 +2552,7 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) /** * bond_3ad_set_carrier - set link state for bonding master - * @bond - bonding structure + * @bond: bonding structure * * if we have an active aggregator, we're up, if not, we're down. * Presumes that we cannot have an active aggregator if there are @@ -2664,7 +2665,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, /** * bond_3ad_update_lacp_rate - change the lacp rate - * @bond - bonding struct + * @bond: bonding struct * * When modify lacp_rate parameter via sysfs, * update actor_oper_port_state of each port. diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 095ea51d1853..4e1b7deb724b 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1206,8 +1206,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav /** * alb_set_mac_address - * @bond: - * @addr: + * @bond: bonding we're working on + * @addr: MAC address to set * * In TLB mode all slaves are configured to the bond's hw address, but set * their dev_addr field to different addresses (based on their permanent hw diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5ad43aaf76e5..42ef25ec0af5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -322,6 +322,7 @@ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, /** * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called + * @proto: network protocol ID * @vid: vlan id being added */ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, @@ -355,6 +356,7 @@ unwind: /** * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves * @bond_dev: bonding net device that got called + * @proto: network protocol ID * @vid: vlan id being removed */ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, @@ -948,7 +950,7 @@ static bool bond_should_notify_peers(struct bonding *bond) /** * change_active_interface - change the active slave into the specified one * @bond: our bonding struct - * @new: the new slave to make the active one + * @new_active: the new slave to make the active one * * Set the new slave to the bond's settings and unset them on the old * curr_active_slave. @@ -2205,7 +2207,8 @@ static int bond_release_and_destroy(struct net_device *bond_dev, int ret; ret = __bond_release_one(bond_dev, slave_dev, false, true); - if (ret == 0 && !bond_has_slaves(bond)) { + if (ret == 0 && !bond_has_slaves(bond) && + bond_dev->reg_state != NETREG_UNREGISTERING) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; netdev_info(bond_dev, "Destroying bond\n"); bond_remove_proc_entry(bond); @@ -2271,7 +2274,7 @@ static int bond_miimon_inspect(struct bonding *bond) "active " : "backup ") : "", bond->params.downdelay * bond->params.miimon); } - /*FALLTHRU*/ + fallthrough; case BOND_LINK_FAIL: if (link_state) { /* recovered before downdelay expired */ @@ -2307,7 +2310,7 @@ static int bond_miimon_inspect(struct bonding *bond) bond->params.updelay * bond->params.miimon); } - /*FALLTHRU*/ + fallthrough; case BOND_LINK_BACK: if (!link_state) { bond_propose_link_state(slave, BOND_LINK_DOWN); @@ -2945,6 +2948,9 @@ static int bond_ab_arp_inspect(struct bonding *bond) if (bond_time_in_interval(bond, last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; + } else if (slave->link == BOND_LINK_BACK) { + bond_propose_link_state(slave, BOND_LINK_FAIL); + commit++; } continue; } @@ -3053,6 +3059,19 @@ static void bond_ab_arp_commit(struct bonding *bond) continue; + case BOND_LINK_FAIL: + bond_set_slave_link_state(slave, BOND_LINK_FAIL, + BOND_SLAVE_NOTIFY_NOW); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); + + /* A slave has just been enslaved and has become + * the current active slave. + */ + if (rtnl_dereference(bond->curr_active_slave)) + RCU_INIT_POINTER(bond->current_arp_slave, NULL); + continue; + default: slave_err(bond->dev, slave->dev, "impossible: link_new_state %d on slave\n", @@ -3103,8 +3122,6 @@ static bool bond_ab_arp_probe(struct bonding *bond) return should_notify_rtnl; } - bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER); - bond_for_each_slave_rcu(bond, slave, iter) { if (!found && !before && bond_slave_is_up(slave)) before = slave; @@ -3305,7 +3322,7 @@ static int bond_slave_netdev_event(unsigned long event, if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave); - /* Fallthrough */ + fallthrough; case NETDEV_DOWN: /* Refresh slave-array if applicable! * If the setup does not use miimon or arpmon (mode-specific!), @@ -3743,7 +3760,7 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd return -EINVAL; mii->phy_id = 0; - /* Fall Through */ + fallthrough; case SIOCGMIIREG: /* We do this again just in case we were called by SIOCGMIIREG * instead of SIOCGMIIPHY. @@ -4552,13 +4569,23 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } +static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed) +{ + if (speed == 0 || speed == SPEED_UNKNOWN) + speed = slave->speed; + else + speed = min(speed, slave->speed); + + return speed; +} + static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, struct ethtool_link_ksettings *cmd) { struct bonding *bond = netdev_priv(bond_dev); - unsigned long speed = 0; struct list_head *iter; struct slave *slave; + u32 speed = 0; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; @@ -4570,8 +4597,13 @@ static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, */ bond_for_each_slave(bond, slave, iter) { if (bond_slave_can_tx(slave)) { - if (slave->speed != SPEED_UNKNOWN) - speed += slave->speed; + if (slave->speed != SPEED_UNKNOWN) { + if (BOND_MODE(bond) == BOND_MODE_BROADCAST) + speed = bond_mode_bcast_speed(slave, + speed); + else + speed += slave->speed; + } if (cmd->base.duplex == DUPLEX_UNKNOWN && slave->duplex != DUPLEX_UNKNOWN) cmd->base.duplex = slave->duplex; diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 9df2007b5e56..38e9f80ed1ef 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -898,7 +898,7 @@ static void at91_irq_err_state(struct net_device *dev, CAN_ERR_CRTL_TX_WARNING : CAN_ERR_CRTL_RX_WARNING; } - /* fall through */ + fallthrough; case CAN_STATE_ERROR_WARNING: /* * from: ERROR_ACTIVE, ERROR_WARNING @@ -948,7 +948,7 @@ static void at91_irq_err_state(struct net_device *dev, netdev_dbg(dev, "Error Active\n"); cf->can_id |= CAN_ERR_PROT; cf->data[2] = CAN_ERR_PROT_ACTIVE; - /* fall through */ + fallthrough; case CAN_STATE_ERROR_WARNING: reg_idr = AT91_IRQ_ERRA | AT91_IRQ_WARN | AT91_IRQ_BOFF; reg_ier = AT91_IRQ_ERRP; diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index 6ad83a881039..9469d4421afe 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -659,7 +659,7 @@ static int pciefd_can_probe(struct pciefd_board *pciefd) pciefd_can_writereg(priv, CANFD_CLK_SEL_80MHZ, PCIEFD_REG_CAN_CLK_SEL); - /* fall through */ + fallthrough; case CANFD_CLK_SEL_80MHZ: priv->ucan.can.clock.freq = 80 * 1000 * 1000; break; diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c index d7222ba46622..d7c2ec529b8f 100644 --- a/drivers/net/can/sja1000/sja1000_platform.c +++ b/drivers/net/can/sja1000/sja1000_platform.c @@ -150,7 +150,7 @@ static void sp_populate_of(struct sja1000_priv *priv, struct device_node *of) priv->read_reg = sp_read_reg16; priv->write_reg = sp_write_reg16; break; - case 1: /* fallthrough */ + case 1: default: priv->read_reg = sp_read_reg8; priv->write_reg = sp_write_reg8; diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 91cdc0a2b1a7..b4a39f0449ba 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -153,7 +153,7 @@ static void slc_bump(struct slcan *sl) switch (*cmd) { case 'r': cf.can_id = CAN_RTR_FLAG; - /* fallthrough */ + fallthrough; case 't': /* store dlc ASCII value and terminate SFF CAN ID string */ cf.can_dlc = sl->rbuff[SLC_CMD_LEN + SLC_SFF_ID_LEN]; @@ -163,7 +163,7 @@ static void slc_bump(struct slcan *sl) break; case 'R': cf.can_id = CAN_RTR_FLAG; - /* fallthrough */ + fallthrough; case 'T': cf.can_id |= CAN_EFF_FLAG; /* store dlc ASCII value and terminate EFF CAN ID string */ diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 5009ff294941..d17608870f2d 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -864,7 +864,7 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id) if (new_state >= CAN_STATE_ERROR_WARNING && new_state <= CAN_STATE_BUS_OFF) priv->can.can_stats.error_warning++; - /* fall through */ + fallthrough; case CAN_STATE_ERROR_WARNING: if (new_state >= CAN_STATE_ERROR_PASSIVE && new_state <= CAN_STATE_BUS_OFF) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index d2539c95adb6..66d0198e7834 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -415,7 +415,7 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, new_state = CAN_STATE_ERROR_WARNING; break; } - /* fall through */ + fallthrough; case CAN_STATE_ERROR_WARNING: if (n & PCAN_USB_ERROR_BUS_HEAVY) { diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 0b7766b715fd..d91df34e7fa8 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -345,7 +345,7 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb, default: netdev_warn(netdev, "tx urb submitting failed err=%d\n", err); - /* fall through */ + fallthrough; case -ENOENT: /* cable unplugged */ stats->tx_dropped++; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 53cb2f72bdd0..1689ab387612 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -133,10 +133,10 @@ static int pcan_msg_add_rec(struct pcan_usb_pro_msg *pm, int id, ...) switch (id) { case PCAN_USBPRO_TXMSG8: i += 4; - /* fall through */ + fallthrough; case PCAN_USBPRO_TXMSG4: i += 4; - /* fall through */ + fallthrough; case PCAN_USBPRO_TXMSG0: *pc++ = va_arg(ap, int); *pc++ = va_arg(ap, int); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 6500179c2ca2..6a5796c32721 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -17,8 +17,6 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include <linux/delay.h> #include <linux/export.h> #include <linux/gpio.h> @@ -767,8 +765,11 @@ static int b53_switch_reset(struct b53_device *dev) usleep_range(1000, 2000); } while (timeout-- > 0); - if (timeout == 0) + if (timeout == 0) { + dev_err(dev->dev, + "Timeout waiting for SW_RST to clear!\n"); return -ETIMEDOUT; + } } b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt); @@ -976,6 +977,54 @@ int b53_get_sset_count(struct dsa_switch *ds, int port, int sset) } EXPORT_SYMBOL(b53_get_sset_count); +enum b53_devlink_resource_id { + B53_DEVLINK_PARAM_ID_VLAN_TABLE, +}; + +static u64 b53_devlink_vlan_table_get(void *priv) +{ + struct b53_device *dev = priv; + struct b53_vlan *vl; + unsigned int i; + u64 count = 0; + + for (i = 0; i < dev->num_vlans; i++) { + vl = &dev->vlans[i]; + if (vl->members) + count++; + } + + return count; +} + +int b53_setup_devlink_resources(struct dsa_switch *ds) +{ + struct devlink_resource_size_params size_params; + struct b53_device *dev = ds->priv; + int err; + + devlink_resource_size_params_init(&size_params, dev->num_vlans, + dev->num_vlans, + 1, DEVLINK_RESOURCE_UNIT_ENTRY); + + err = dsa_devlink_resource_register(ds, "VLAN", dev->num_vlans, + B53_DEVLINK_PARAM_ID_VLAN_TABLE, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &size_params); + if (err) + goto out; + + dsa_devlink_resource_occ_get_register(ds, + B53_DEVLINK_PARAM_ID_VLAN_TABLE, + b53_devlink_vlan_table_get, dev); + + return 0; +out: + dsa_devlink_resources_unregister(ds); + return err; +} +EXPORT_SYMBOL(b53_setup_devlink_resources); + static int b53_setup(struct dsa_switch *ds) { struct b53_device *dev = ds->priv; @@ -991,8 +1040,10 @@ static int b53_setup(struct dsa_switch *ds) b53_reset_mib(dev); ret = b53_apply_config(dev); - if (ret) + if (ret) { dev_err(ds->dev, "failed to apply configuration\n"); + return ret; + } /* Configure IMP/CPU port, disable all other ports. Enabled * ports will be configured with .port_enable @@ -1011,7 +1062,12 @@ static int b53_setup(struct dsa_switch *ds) */ ds->vlan_filtering_is_global = true; - return ret; + return b53_setup_devlink_resources(ds); +} + +static void b53_teardown(struct dsa_switch *ds) +{ + dsa_devlink_resources_unregister(ds); } static void b53_force_link(struct b53_device *dev, int port, int link) @@ -1061,7 +1117,7 @@ static void b53_force_port_config(struct b53_device *dev, int port, switch (speed) { case 2000: reg |= PORT_OVERRIDE_SPEED_2000M; - /* fallthrough */ + fallthrough; case SPEED_1000: reg |= PORT_OVERRIDE_SPEED_1000M; break; @@ -1554,6 +1610,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, return ret; switch (ret) { + case -ETIMEDOUT: + return ret; case -ENOSPC: dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n", addr, vid); @@ -2138,6 +2196,7 @@ static int b53_get_max_mtu(struct dsa_switch *ds, int port) static const struct dsa_switch_ops b53_switch_ops = { .get_tag_protocol = b53_get_tag_protocol, .setup = b53_setup, + .teardown = b53_teardown, .get_strings = b53_get_strings, .get_ethtool_stats = b53_get_ethtool_stats, .get_sset_count = b53_get_sset_count, @@ -2618,8 +2677,9 @@ int b53_switch_detect(struct b53_device *dev) dev->chip_id = id32; break; default: - pr_err("unsupported switch detected (BCM53%02x/BCM%x)\n", - id8, id32); + dev_err(dev->dev, + "unsupported switch detected (BCM53%02x/BCM%x)\n", + id8, id32); return -ENODEV; } } @@ -2649,7 +2709,8 @@ int b53_switch_register(struct b53_device *dev) if (ret) return ret; - pr_info("found switch: %s, rev %i\n", dev->name, dev->core_rev); + dev_info(dev->dev, "found switch: %s, rev %i\n", + dev->name, dev->core_rev); return dsa_register_switch(dev->ds); } diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index e942c60e4365..c55c0a9f1b47 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -328,6 +328,7 @@ void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state); void b53_br_fast_age(struct dsa_switch *ds, int port); int b53_br_egress_floods(struct dsa_switch *ds, int port, bool unicast, bool multicast); +int b53_setup_devlink_resources(struct dsa_switch *ds); void b53_port_event(struct dsa_switch *ds, int port); void b53_phylink_validate(struct dsa_switch *ds, int port, unsigned long *supported, diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c index 629bf14128a2..5ae3d9783b68 100644 --- a/drivers/net/dsa/b53/b53_serdes.c +++ b/drivers/net/dsa/b53/b53_serdes.c @@ -170,7 +170,7 @@ void b53_serdes_phylink_validate(struct b53_device *dev, int port, switch (lane) { case 0: phylink_set(supported, 2500baseX_Full); - /* fallthrough */ + fallthrough; case 1: phylink_set(supported, 1000baseX_Full); break; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index bafddb35f3a9..723820603107 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -14,6 +14,7 @@ #include <linux/phy_fixed.h> #include <linux/phylink.h> #include <linux/mii.h> +#include <linux/clk.h> #include <linux/of.h> #include <linux/of_irq.h> #include <linux/of_address.h> @@ -31,6 +32,49 @@ #include "b53/b53_priv.h" #include "b53/b53_regs.h" +/* Return the number of active ports, not counting the IMP (CPU) port */ +static unsigned int bcm_sf2_num_active_ports(struct dsa_switch *ds) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + unsigned int port, count = 0; + + for (port = 0; port < ARRAY_SIZE(priv->port_sts); port++) { + if (dsa_is_cpu_port(ds, port)) + continue; + if (priv->port_sts[port].enabled) + count++; + } + + return count; +} + +static void bcm_sf2_recalc_clock(struct dsa_switch *ds) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + unsigned long new_rate; + unsigned int ports_active; + /* Frequenty in Mhz */ + const unsigned long rate_table[] = { + 59220000, + 60820000, + 62500000, + 62500000, + }; + + ports_active = bcm_sf2_num_active_ports(ds); + if (ports_active == 0 || !priv->clk_mdiv) + return; + + /* If we overflow our table, just use the recommended operational + * frequency + */ + if (ports_active > ARRAY_SIZE(rate_table)) + new_rate = 90000000; + else + new_rate = rate_table[ports_active - 1]; + clk_set_rate(priv->clk_mdiv, new_rate); +} + static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); @@ -82,6 +126,8 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) reg &= ~(RX_DIS | TX_DIS); core_writel(priv, reg, CORE_G_PCTL_PORT(port)); } + + priv->port_sts[port].enabled = true; } static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable) @@ -167,6 +213,10 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port, if (!dsa_is_user_port(ds, port)) return 0; + priv->port_sts[port].enabled = true; + + bcm_sf2_recalc_clock(ds); + /* Clear the memory power down */ reg = core_readl(priv, CORE_MEM_PSM_VDD_CTRL); reg &= ~P_TXQ_PSM_VDD(port); @@ -260,6 +310,10 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port) reg = core_readl(priv, CORE_MEM_PSM_VDD_CTRL); reg |= P_TXQ_PSM_VDD(port); core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL); + + priv->port_sts[port].enabled = false; + + bcm_sf2_recalc_clock(ds); } @@ -435,9 +489,11 @@ static void bcm_sf2_identify_ports(struct bcm_sf2_priv *priv, static int bcm_sf2_mdio_register(struct dsa_switch *ds) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - struct device_node *dn; + struct device_node *dn, *child; + struct phy_device *phydev; + struct property *prop; static int index; - int err; + int err, reg; /* Find our integrated MDIO bus node */ dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio"); @@ -480,6 +536,31 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) priv->slave_mii_bus->parent = ds->dev->parent; priv->slave_mii_bus->phy_mask = ~priv->indir_phy_mask; + /* We need to make sure that of_phy_connect() will not work by + * removing the 'phandle' and 'linux,phandle' properties and + * unregister the existing PHY device that was already registered. + */ + for_each_available_child_of_node(dn, child) { + if (of_property_read_u32(child, "reg", ®) || + reg >= PHY_MAX_ADDR) + continue; + + if (!(priv->indir_phy_mask & BIT(reg))) + continue; + + prop = of_find_property(child, "phandle", NULL); + if (prop) + of_remove_property(child, prop); + + prop = of_find_property(child, "linux,phandle", NULL); + if (prop) + of_remove_property(child, prop); + + phydev = of_phy_find_device(child); + if (phydev) + phy_device_remove(phydev); + } + err = mdiobus_register(priv->slave_mii_bus); if (err && dn) of_node_put(dn); @@ -566,7 +647,7 @@ static void bcm_sf2_sw_mac_config(struct dsa_switch *ds, int port, switch (state->interface) { case PHY_INTERFACE_MODE_RGMII: id_mode_dis = 1; - /* fallthrough */ + fallthrough; case PHY_INTERFACE_MODE_RGMII_TXID: port_mode = EXT_GPHY; break; @@ -750,6 +831,9 @@ static int bcm_sf2_sw_suspend(struct dsa_switch *ds) bcm_sf2_port_disable(ds, port); } + if (!priv->wol_ports_mask) + clk_disable_unprepare(priv->clk); + return 0; } @@ -758,6 +842,9 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds) struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); int ret; + if (!priv->wol_ports_mask) + clk_prepare_enable(priv->clk); + ret = bcm_sf2_sw_rst(priv); if (ret) { pr_err("%s: failed to software reset switch\n", __func__); @@ -849,7 +936,12 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds) b53_configure_vlan(ds); bcm_sf2_enable_acb(ds); - return 0; + return b53_setup_devlink_resources(ds); +} + +static void bcm_sf2_sw_teardown(struct dsa_switch *ds) +{ + dsa_devlink_resources_unregister(ds); } /* The SWITCH_CORE register space is managed by b53 but operates on a page + @@ -986,6 +1078,7 @@ static int bcm_sf2_sw_get_sset_count(struct dsa_switch *ds, int port, static const struct dsa_switch_ops bcm_sf2_ops = { .get_tag_protocol = b53_get_tag_protocol, .setup = bcm_sf2_sw_setup, + .teardown = bcm_sf2_sw_teardown, .get_strings = bcm_sf2_sw_get_strings, .get_ethtool_stats = bcm_sf2_sw_get_ethtool_stats, .get_sset_count = bcm_sf2_sw_get_sset_count, @@ -1189,10 +1282,24 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) base++; } + priv->clk = devm_clk_get_optional(&pdev->dev, "sw_switch"); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); + + clk_prepare_enable(priv->clk); + + priv->clk_mdiv = devm_clk_get_optional(&pdev->dev, "sw_switch_mdiv"); + if (IS_ERR(priv->clk_mdiv)) { + ret = PTR_ERR(priv->clk_mdiv); + goto out_clk; + } + + clk_prepare_enable(priv->clk_mdiv); + ret = bcm_sf2_sw_rst(priv); if (ret) { pr_err("unable to software reset switch: %d\n", ret); - return ret; + goto out_clk_mdiv; } bcm_sf2_gphy_enable_set(priv->dev->ds, true); @@ -1200,7 +1307,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) ret = bcm_sf2_mdio_register(ds); if (ret) { pr_err("failed to register MDIO bus\n"); - return ret; + goto out_clk_mdiv; } bcm_sf2_gphy_enable_set(priv->dev->ds, false); @@ -1267,6 +1374,10 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) out_mdio: bcm_sf2_mdio_unregister(priv); +out_clk_mdiv: + clk_disable_unprepare(priv->clk_mdiv); +out_clk: + clk_disable_unprepare(priv->clk); return ret; } @@ -1280,6 +1391,8 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev) dsa_unregister_switch(priv->dev->ds); bcm_sf2_cfp_exit(priv->dev->ds); bcm_sf2_mdio_unregister(priv); + clk_disable_unprepare(priv->clk_mdiv); + clk_disable_unprepare(priv->clk); if (priv->type == BCM7278_DEVICE_ID && !IS_ERR(priv->rcdev)) reset_control_assert(priv->rcdev); diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index de386dd96d66..1ed901a68536 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -45,6 +45,7 @@ struct bcm_sf2_hw_params { struct bcm_sf2_port_status { unsigned int link; + bool enabled; }; struct bcm_sf2_cfp_priv { @@ -93,6 +94,9 @@ struct bcm_sf2_priv { /* Mask of ports enabled for Wake-on-LAN */ u32 wol_ports_mask; + struct clk *clk; + struct clk *clk_mdiv; + /* MoCA port location */ int moca_port; diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index eb600b3dbf26..b588614d1e5e 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -28,6 +28,53 @@ static struct dsa_loop_mib_entry dsa_loop_mibs[] = { static struct phy_device *phydevs[PHY_MAX_ADDR]; +enum dsa_loop_devlink_resource_id { + DSA_LOOP_DEVLINK_PARAM_ID_VTU, +}; + +static u64 dsa_loop_devlink_vtu_get(void *priv) +{ + struct dsa_loop_priv *ps = priv; + unsigned int i, count = 0; + struct dsa_loop_vlan *vl; + + for (i = 0; i < ARRAY_SIZE(ps->vlans); i++) { + vl = &ps->vlans[i]; + if (vl->members) + count++; + } + + return count; +} + +static int dsa_loop_setup_devlink_resources(struct dsa_switch *ds) +{ + struct devlink_resource_size_params size_params; + struct dsa_loop_priv *ps = ds->priv; + int err; + + devlink_resource_size_params_init(&size_params, ARRAY_SIZE(ps->vlans), + ARRAY_SIZE(ps->vlans), + 1, DEVLINK_RESOURCE_UNIT_ENTRY); + + err = dsa_devlink_resource_register(ds, "VTU", ARRAY_SIZE(ps->vlans), + DSA_LOOP_DEVLINK_PARAM_ID_VTU, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &size_params); + if (err) + goto out; + + dsa_devlink_resource_occ_get_register(ds, + DSA_LOOP_DEVLINK_PARAM_ID_VTU, + dsa_loop_devlink_vtu_get, ps); + + return 0; + +out: + dsa_devlink_resources_unregister(ds); + return err; +} + static enum dsa_tag_protocol dsa_loop_get_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -48,7 +95,12 @@ static int dsa_loop_setup(struct dsa_switch *ds) dev_dbg(ds->dev, "%s\n", __func__); - return 0; + return dsa_loop_setup_devlink_resources(ds); +} + +static void dsa_loop_teardown(struct dsa_switch *ds) +{ + dsa_devlink_resources_unregister(ds); } static int dsa_loop_get_sset_count(struct dsa_switch *ds, int port, int sset) @@ -243,6 +295,7 @@ static int dsa_loop_port_max_mtu(struct dsa_switch *ds, int port) static const struct dsa_switch_ops dsa_loop_driver = { .get_tag_protocol = dsa_loop_get_protocol, .setup = dsa_loop_setup, + .teardown = dsa_loop_teardown, .get_strings = dsa_loop_get_strings, .get_ethtool_stats = dsa_loop_get_ethtool_stats, .get_sset_count = dsa_loop_get_sset_count, @@ -290,6 +343,7 @@ static int dsa_loop_drv_probe(struct mdio_device *mdiodev) ds->dev = &mdiodev->dev; ds->ops = &dsa_loop_driver; ds->priv = ps; + ds->configure_vlan_while_not_filtering = true; ps->bus = mdiodev->bus; dev_set_drvdata(&mdiodev->dev, ds); diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index dc999406ce86..b62dd64470a8 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1083,7 +1083,7 @@ static phy_interface_t ksz9477_get_interface(struct ksz_device *dev, int port) interface = PHY_INTERFACE_MODE_GMII; if (gbit) break; - /* fall through */ + fallthrough; case 0: interface = PHY_INTERFACE_MODE_MII; break; @@ -1235,6 +1235,9 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || dev->interface == PHY_INTERFACE_MODE_RGMII_TXID) data8 |= PORT_RGMII_ID_EG_ENABLE; + /* On KSZ9893, disable RGMII in-band status support */ + if (dev->features & IS_9893) + data8 &= ~PORT_MII_MAC_MODE; p->phydev.speed = SPEED_1000; break; } @@ -1265,6 +1268,8 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) for (i = 0; i < dev->port_cnt; i++) { if (dsa_is_cpu_port(ds, i) && (dev->cpu_ports & (1 << i))) { phy_interface_t interface; + const char *prev_msg; + const char *prev_mode; dev->cpu_port = i; dev->host_mask = (1 << dev->cpu_port); @@ -1277,11 +1282,19 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) interface = ksz9477_get_interface(dev, i); if (!dev->interface) dev->interface = interface; - if (interface && interface != dev->interface) - dev_info(dev->dev, - "use %s instead of %s\n", - phy_modes(dev->interface), - phy_modes(interface)); + if (interface && interface != dev->interface) { + prev_msg = " instead of "; + prev_mode = phy_modes(interface); + } else { + prev_msg = ""; + prev_mode = ""; + } + dev_info(dev->dev, + "Port%d: using phy mode %s%s%s\n", + i, + phy_modes(dev->interface), + prev_msg, + prev_mode); /* enable cpu port */ ksz9477_port_setup(dev, i, true); @@ -1426,10 +1439,12 @@ static int ksz9477_switch_detect(struct ksz_device *dev) /* Default capability is gigabit capable. */ dev->features = GBIT_SUPPORT; + dev_dbg(dev->dev, "Switch detect: ID=%08x%02x\n", id32, data8); id_hi = (u8)(id32 >> 16); id_lo = (u8)(id32 >> 8); if ((id_lo & 0xf) == 3) { /* Chip is from KSZ9893 design. */ + dev_info(dev->dev, "Found KSZ9893\n"); dev->features |= IS_9893; /* Chip does not support gigabit. */ @@ -1438,6 +1453,7 @@ static int ksz9477_switch_detect(struct ksz_device *dev) dev->mib_port_cnt = 3; dev->phy_port_cnt = 2; } else { + dev_info(dev->dev, "Found KSZ9477 or compatible\n"); /* Chip uses new XMII register definitions. */ dev->features |= NEW_XMII; diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 8d53b12d40a8..a31738662d95 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -400,8 +400,9 @@ int ksz_switch_register(struct ksz_device *dev, if (dev->reset_gpio) { gpiod_set_value_cansleep(dev->reset_gpio, 1); - mdelay(10); + usleep_range(10000, 12000); gpiod_set_value_cansleep(dev->reset_gpio, 0); + usleep_range(100, 1000); } mutex_init(&dev->dev_mutex); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 8dcb8a49ab67..1aaf47a0da2b 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -566,7 +566,7 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface) case P5_INTF_SEL_PHY_P0: /* MT7530_P5_MODE_GPHY_P0: 2nd GMAC -> P5 -> P0 */ val |= MHWTRAP_PHY0_SEL; - /* fall through */ + fallthrough; case P5_INTF_SEL_PHY_P4: /* MT7530_P5_MODE_GPHY_P4: 2nd GMAC -> P5 -> P4 */ val &= ~MHWTRAP_P5_MAC_SEL & ~MHWTRAP_P5_DIS; @@ -1326,14 +1326,17 @@ mt7530_setup(struct dsa_switch *ds) if (phy_node->parent == priv->dev->of_node->parent) { ret = of_get_phy_mode(mac_np, &interface); - if (ret && ret != -ENODEV) + if (ret && ret != -ENODEV) { + of_node_put(mac_np); return ret; + } id = of_mdio_parse_addr(ds->dev, phy_node); if (id == 0) priv->p5_intf_sel = P5_INTF_SEL_PHY_P0; if (id == 4) priv->p5_intf_sel = P5_INTF_SEL_PHY_P4; } + of_node_put(mac_np); of_node_put(phy_node); break; } @@ -1501,7 +1504,7 @@ unsupported: phylink_set(mask, 100baseT_Full); if (state->interface != PHY_INTERFACE_MODE_MII) { - phylink_set(mask, 1000baseT_Half); + /* This switch only supports 1G full-duplex. */ phylink_set(mask, 1000baseT_Full); if (port == 5) phylink_set(mask, 1000baseX_Full); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 7a71c9902e73..15b97a4f8d93 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -875,7 +875,7 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, break; case STATS_TYPE_BANK1: reg = bank1_select; - /* fall through */ + fallthrough; case STATS_TYPE_BANK0: reg |= s->reg | histogram; mv88e6xxx_g1_stats_read(chip, reg, &low); @@ -3329,12 +3329,6 @@ static int mv88e6xxx_mdio_register(struct mv88e6xxx_chip *chip, return 0; } -static const struct of_device_id mv88e6xxx_mdio_external_match[] = { - { .compatible = "marvell,mv88e6xxx-mdio-external", - .data = (void *)true }, - { }, -}; - static void mv88e6xxx_mdios_unregister(struct mv88e6xxx_chip *chip) { @@ -3354,7 +3348,6 @@ static void mv88e6xxx_mdios_unregister(struct mv88e6xxx_chip *chip) static int mv88e6xxx_mdios_register(struct mv88e6xxx_chip *chip, struct device_node *np) { - const struct of_device_id *match; struct device_node *child; int err; @@ -3372,8 +3365,8 @@ static int mv88e6xxx_mdios_register(struct mv88e6xxx_chip *chip, * bus. */ for_each_available_child_of_node(np, child) { - match = of_match_node(mv88e6xxx_mdio_external_match, child); - if (match) { + if (of_device_is_compatible( + child, "marvell,mv88e6xxx-mdio-external")) { err = mv88e6xxx_mdio_register(chip, child, true); if (err) { mv88e6xxx_mdios_unregister(chip); diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c index a4c488b12e8f..094d17a1d037 100644 --- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c +++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c @@ -211,49 +211,20 @@ int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port, -EFAULT : 0; } -/* Get the start of the PTP header in this skb */ -static u8 *parse_ptp_header(struct sk_buff *skb, unsigned int type) -{ - u8 *data = skb_mac_header(skb); - unsigned int offset = 0; - - if (type & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (type & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return NULL; - } - - /* Ensure that the entire header is present in this packet. */ - if (skb->len + ETH_HLEN < offset + 34) - return NULL; - - return data + offset; -} - /* Returns a pointer to the PTP header if the caller should time stamp, * or NULL if the caller should not. */ -static u8 *mv88e6xxx_should_tstamp(struct mv88e6xxx_chip *chip, int port, - struct sk_buff *skb, unsigned int type) +static struct ptp_header *mv88e6xxx_should_tstamp(struct mv88e6xxx_chip *chip, + int port, struct sk_buff *skb, + unsigned int type) { struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; - u8 *hdr; + struct ptp_header *hdr; if (!chip->info->ptp_support) return NULL; - hdr = parse_ptp_header(skb, type); + hdr = ptp_parse_header(skb, type); if (!hdr) return NULL; @@ -275,12 +246,11 @@ static int mv88e6xxx_ts_valid(u16 status) static int seq_match(struct sk_buff *skb, u16 ts_seqid) { unsigned int type = SKB_PTP_TYPE(skb); - u8 *hdr = parse_ptp_header(skb, type); - __be16 *seqid; + struct ptp_header *hdr; - seqid = (__be16 *)(hdr + OFF_PTP_SEQUENCE_ID); + hdr = ptp_parse_header(skb, type); - return ts_seqid == ntohs(*seqid); + return ts_seqid == ntohs(hdr->sequence_id); } static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip, @@ -357,9 +327,9 @@ static void mv88e6xxx_rxtstamp_work(struct mv88e6xxx_chip *chip, &ps->rx_queue2); } -static int is_pdelay_resp(u8 *msgtype) +static int is_pdelay_resp(const struct ptp_header *hdr) { - return (*msgtype & 0xf) == 3; + return (hdr->tsmt & 0xf) == 3; } bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, @@ -367,7 +337,7 @@ bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, { struct mv88e6xxx_port_hwtstamp *ps; struct mv88e6xxx_chip *chip; - u8 *hdr; + struct ptp_header *hdr; chip = ds->priv; ps = &chip->port_hwtstamp[port]; @@ -503,8 +473,7 @@ bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, { struct mv88e6xxx_chip *chip = ds->priv; struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; - __be16 *seq_ptr; - u8 *hdr; + struct ptp_header *hdr; if (!(skb_shinfo(clone)->tx_flags & SKBTX_HW_TSTAMP)) return false; @@ -513,15 +482,13 @@ bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, if (!hdr) return false; - seq_ptr = (__be16 *)(hdr + OFF_PTP_SEQUENCE_ID); - if (test_and_set_bit_lock(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, &ps->state)) return false; ps->tx_skb = clone; ps->tx_tstamp_start = jiffies; - ps->tx_seq_id = be16_to_cpup(seq_ptr); + ps->tx_seq_id = be16_to_cpu(hdr->sequence_id); ptp_schedule_worker(chip->ptp_clock, 0); return true; diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index f121619d81fe..e19718d4a7d4 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -8,8 +8,9 @@ config NET_DSA_MSCC_FELIX select MSCC_OCELOT_SWITCH_LIB select NET_DSA_TAG_OCELOT select FSL_ENETC_MDIO + select PCS_LYNX help - This driver supports network switches from the the Vitesse / + This driver supports network switches from the Vitesse / Microsemi / Microchip Ocelot family of switching cores that are connected to their host CPU via Ethernet. The following switches are supported: diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index c69d9592a2b7..a1e1d3824110 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -19,6 +19,7 @@ #include <linux/of_net.h> #include <linux/pci.h> #include <linux/of.h> +#include <linux/pcs-lynx.h> #include <net/pkt_sched.h> #include <net/dsa.h> #include "felix.h" @@ -196,27 +197,16 @@ static void felix_phylink_validate(struct dsa_switch *ds, int port, felix->info->phylink_validate(ocelot, port, supported, state); } -static int felix_phylink_mac_pcs_get_state(struct dsa_switch *ds, int port, - struct phylink_link_state *state) -{ - struct ocelot *ocelot = ds->priv; - struct felix *felix = ocelot_to_felix(ocelot); - - if (felix->info->pcs_link_state) - felix->info->pcs_link_state(ocelot, port, state); - - return 0; -} - static void felix_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int link_an_mode, const struct phylink_link_state *state) { struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); + struct dsa_port *dp = dsa_to_port(ds, port); - if (felix->info->pcs_config) - felix->info->pcs_config(ocelot, port, link_an_mode, state); + if (felix->pcs[port]) + phylink_set_pcs(dp->pl, &felix->pcs[port]->pcs); } static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port, @@ -306,10 +296,6 @@ static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, ocelot_fields_write(ocelot, port, QSYS_SWITCH_PORT_MODE_PORT_ENA, 1); - if (felix->info->pcs_link_up) - felix->info->pcs_link_up(ocelot, port, link_an_mode, interface, - speed, duplex); - if (felix->info->port_sched_speed_set) felix->info->port_sched_speed_set(ocelot, port, speed); } @@ -400,6 +386,7 @@ static int felix_parse_ports_node(struct felix *felix, if (err < 0) { dev_err(dev, "Unsupported PHY mode %s on port %d\n", phy_modes(phy_mode), port); + of_node_put(child); return err; } @@ -626,11 +613,6 @@ static int felix_setup(struct dsa_switch *ds) ds->mtu_enforcement_ingress = true; ds->configure_vlan_while_not_filtering = true; - /* It looks like the MAC/PCS interrupt register - PM0_IEVENT (0x8040) - * isn't instantiated for the Felix PF. - * In-band AN may take a few ms to complete, so we need to poll. - */ - ds->pcs_poll = true; return 0; } @@ -786,7 +768,6 @@ const struct dsa_switch_ops felix_switch_ops = { .get_sset_count = felix_get_sset_count, .get_ts_info = felix_get_ts_info, .phylink_validate = felix_phylink_validate, - .phylink_mac_link_state = felix_phylink_mac_pcs_get_state, .phylink_mac_config = felix_phylink_mac_config, .phylink_mac_link_down = felix_phylink_mac_link_down, .phylink_mac_link_up = felix_phylink_mac_link_up, diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 98f14621ac23..9bceb994b7db 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -28,15 +28,6 @@ struct felix_info { int imdio_pci_bar; int (*mdio_bus_alloc)(struct ocelot *ocelot); void (*mdio_bus_free)(struct ocelot *ocelot); - void (*pcs_config)(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - const struct phylink_link_state *state); - void (*pcs_link_up)(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - phy_interface_t interface, - int speed, int duplex); - void (*pcs_link_state)(struct ocelot *ocelot, int port, - struct phylink_link_state *state); void (*phylink_validate)(struct ocelot *ocelot, int port, unsigned long *supported, struct phylink_link_state *state); @@ -59,20 +50,11 @@ struct felix { const struct felix_info *info; struct ocelot ocelot; struct mii_bus *imdio; - struct phy_device **pcs; + struct lynx_pcs **pcs; resource_size_t switch_base; resource_size_t imdio_base; }; -void vsc9959_pcs_link_state(struct ocelot *ocelot, int port, - struct phylink_link_state *state); -void vsc9959_pcs_config(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - const struct phylink_link_state *state); -void vsc9959_pcs_link_up(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - phy_interface_t interface, - int speed, int duplex); void vsc9959_mdio_bus_free(struct ocelot *ocelot); #endif diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 9b720c8ddfc3..126a53a811f7 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -9,6 +9,7 @@ #include <soc/mscc/ocelot_sys.h> #include <soc/mscc/ocelot.h> #include <linux/packing.h> +#include <linux/pcs-lynx.h> #include <net/pkt_sched.h> #include <linux/iopoll.h> #include <linux/mdio.h> @@ -766,347 +767,6 @@ static int vsc9959_reset(struct ocelot *ocelot) return 0; } -/* We enable SGMII AN only when the PHY has managed = "in-band-status" in the - * device tree. If we are in MLO_AN_PHY mode, we program directly state->speed - * into the PCS, which is retrieved out-of-band over MDIO. This also has the - * benefit of working with SGMII fixed-links, like downstream switches, where - * both link partners attempt to operate as AN slaves and therefore AN never - * completes. But it also has the disadvantage that some PHY chips don't pass - * traffic if SGMII AN is enabled but not completed (acknowledged by us), so - * setting MLO_AN_INBAND is actually required for those. - */ -static void vsc9959_pcs_config_sgmii(struct phy_device *pcs, - unsigned int link_an_mode, - const struct phylink_link_state *state) -{ - int bmsr, bmcr; - - /* Some PHYs like VSC8234 don't like it when AN restarts on - * their system side and they restart line side AN too, going - * into an endless link up/down loop. Don't restart PCS AN if - * link is up already. - * We do check that AN is enabled just in case this is the 1st - * call, PCS detects a carrier but AN is disabled from power on - * or by boot loader. - */ - bmcr = phy_read(pcs, MII_BMCR); - if (bmcr < 0) - return; - - bmsr = phy_read(pcs, MII_BMSR); - if (bmsr < 0) - return; - - if ((bmcr & BMCR_ANENABLE) && (bmsr & BMSR_LSTATUS)) - return; - - /* SGMII spec requires tx_config_Reg[15:0] to be exactly 0x4001 - * for the MAC PCS in order to acknowledge the AN. - */ - phy_write(pcs, MII_ADVERTISE, ADVERTISE_SGMII | - ADVERTISE_LPACK); - - phy_write(pcs, ENETC_PCS_IF_MODE, - ENETC_PCS_IF_MODE_SGMII_EN | - ENETC_PCS_IF_MODE_USE_SGMII_AN); - - /* Adjust link timer for SGMII */ - phy_write(pcs, ENETC_PCS_LINK_TIMER1, - ENETC_PCS_LINK_TIMER1_VAL); - phy_write(pcs, ENETC_PCS_LINK_TIMER2, - ENETC_PCS_LINK_TIMER2_VAL); - - phy_set_bits(pcs, MII_BMCR, BMCR_ANENABLE); -} - -static void vsc9959_pcs_config_usxgmii(struct phy_device *pcs, - unsigned int link_an_mode, - const struct phylink_link_state *state) -{ - /* Configure device ability for the USXGMII Replicator */ - phy_write_mmd(pcs, MDIO_MMD_VEND2, MII_ADVERTISE, - MDIO_USXGMII_2500FULL | - MDIO_USXGMII_LINK | - ADVERTISE_SGMII | - ADVERTISE_LPACK); -} - -void vsc9959_pcs_config(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - const struct phylink_link_state *state) -{ - struct felix *felix = ocelot_to_felix(ocelot); - struct phy_device *pcs = felix->pcs[port]; - - if (!pcs) - return; - - /* The PCS does not implement the BMSR register fully, so capability - * detection via genphy_read_abilities does not work. Since we can get - * the PHY config word from the LPA register though, there is still - * value in using the generic phy_resolve_aneg_linkmode function. So - * populate the supported and advertising link modes manually here. - */ - linkmode_set_bit_array(phy_basic_ports_array, - ARRAY_SIZE(phy_basic_ports_array), - pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, pcs->supported); - if (pcs->interface == PHY_INTERFACE_MODE_2500BASEX || - pcs->interface == PHY_INTERFACE_MODE_USXGMII) - linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseX_Full_BIT, - pcs->supported); - if (pcs->interface != PHY_INTERFACE_MODE_2500BASEX) - linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - pcs->supported); - phy_advertise_supported(pcs); - - if (!phylink_autoneg_inband(link_an_mode)) - return; - - switch (pcs->interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_QSGMII: - vsc9959_pcs_config_sgmii(pcs, link_an_mode, state); - break; - case PHY_INTERFACE_MODE_2500BASEX: - phydev_err(pcs, "AN not supported on 3.125GHz SerDes lane\n"); - break; - case PHY_INTERFACE_MODE_USXGMII: - vsc9959_pcs_config_usxgmii(pcs, link_an_mode, state); - break; - default: - dev_err(ocelot->dev, "Unsupported link mode %s\n", - phy_modes(pcs->interface)); - } -} - -static void vsc9959_pcs_link_up_sgmii(struct phy_device *pcs, - unsigned int link_an_mode, - int speed, int duplex) -{ - u16 if_mode = ENETC_PCS_IF_MODE_SGMII_EN; - - switch (speed) { - case SPEED_1000: - if_mode |= ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_1000); - break; - case SPEED_100: - if_mode |= ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_100); - break; - case SPEED_10: - if_mode |= ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_10); - break; - default: - phydev_err(pcs, "Invalid PCS speed %d\n", speed); - return; - } - - if (duplex == DUPLEX_HALF) - if_mode |= ENETC_PCS_IF_MODE_DUPLEX_HALF; - - phy_write(pcs, ENETC_PCS_IF_MODE, if_mode); - phy_clear_bits(pcs, MII_BMCR, BMCR_ANENABLE); -} - -/* 2500Base-X is SerDes protocol 7 on Felix and 6 on ENETC. It is a SerDes lane - * clocked at 3.125 GHz which encodes symbols with 8b/10b and does not have - * auto-negotiation of any link parameters. Electrically it is compatible with - * a single lane of XAUI. - * The hardware reference manual wants to call this mode SGMII, but it isn't - * really, since the fundamental features of SGMII: - * - Downgrading the link speed by duplicating symbols - * - Auto-negotiation - * are not there. - * The speed is configured at 1000 in the IF_MODE and BMCR MDIO registers - * because the clock frequency is actually given by a PLL configured in the - * Reset Configuration Word (RCW). - * Since there is no difference between fixed speed SGMII w/o AN and 802.3z w/o - * AN, we call this PHY interface type 2500Base-X. In case a PHY negotiates a - * lower link speed on line side, the system-side interface remains fixed at - * 2500 Mbps and we do rate adaptation through pause frames. - */ -static void vsc9959_pcs_link_up_2500basex(struct phy_device *pcs, - unsigned int link_an_mode, - int speed, int duplex) -{ - u16 if_mode = ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_2500) | - ENETC_PCS_IF_MODE_SGMII_EN; - - if (duplex == DUPLEX_HALF) - if_mode |= ENETC_PCS_IF_MODE_DUPLEX_HALF; - - phy_write(pcs, ENETC_PCS_IF_MODE, if_mode); - phy_clear_bits(pcs, MII_BMCR, BMCR_ANENABLE); -} - -void vsc9959_pcs_link_up(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - phy_interface_t interface, - int speed, int duplex) -{ - struct felix *felix = ocelot_to_felix(ocelot); - struct phy_device *pcs = felix->pcs[port]; - - if (!pcs) - return; - - if (phylink_autoneg_inband(link_an_mode)) - return; - - switch (interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_QSGMII: - vsc9959_pcs_link_up_sgmii(pcs, link_an_mode, speed, duplex); - break; - case PHY_INTERFACE_MODE_2500BASEX: - vsc9959_pcs_link_up_2500basex(pcs, link_an_mode, speed, - duplex); - break; - case PHY_INTERFACE_MODE_USXGMII: - phydev_err(pcs, "USXGMII only supports in-band AN for now\n"); - break; - default: - dev_err(ocelot->dev, "Unsupported link mode %s\n", - phy_modes(pcs->interface)); - } -} - -static void vsc9959_pcs_link_state_resolve(struct phy_device *pcs, - struct phylink_link_state *state) -{ - state->an_complete = pcs->autoneg_complete; - state->an_enabled = pcs->autoneg; - state->link = pcs->link; - state->duplex = pcs->duplex; - state->speed = pcs->speed; - /* SGMII AN does not negotiate flow control, but that's ok, - * since phylink already knows that, and does: - * link_state.pause |= pl->phy_state.pause; - */ - state->pause = MLO_PAUSE_NONE; - - phydev_dbg(pcs, - "mode=%s/%s/%s adv=%*pb lpa=%*pb link=%u an_enabled=%u an_complete=%u\n", - phy_modes(pcs->interface), - phy_speed_to_str(pcs->speed), - phy_duplex_to_str(pcs->duplex), - __ETHTOOL_LINK_MODE_MASK_NBITS, pcs->advertising, - __ETHTOOL_LINK_MODE_MASK_NBITS, pcs->lp_advertising, - pcs->link, pcs->autoneg, pcs->autoneg_complete); -} - -static void vsc9959_pcs_link_state_sgmii(struct phy_device *pcs, - struct phylink_link_state *state) -{ - int err; - - err = genphy_update_link(pcs); - if (err < 0) - return; - - if (pcs->autoneg_complete) { - u16 lpa = phy_read(pcs, MII_LPA); - - mii_lpa_to_linkmode_lpa_sgmii(pcs->lp_advertising, lpa); - - phy_resolve_aneg_linkmode(pcs); - } -} - -static void vsc9959_pcs_link_state_2500basex(struct phy_device *pcs, - struct phylink_link_state *state) -{ - int err; - - err = genphy_update_link(pcs); - if (err < 0) - return; - - pcs->speed = SPEED_2500; - pcs->asym_pause = true; - pcs->pause = true; -} - -static void vsc9959_pcs_link_state_usxgmii(struct phy_device *pcs, - struct phylink_link_state *state) -{ - int status, lpa; - - status = phy_read_mmd(pcs, MDIO_MMD_VEND2, MII_BMSR); - if (status < 0) - return; - - pcs->autoneg = true; - pcs->autoneg_complete = !!(status & BMSR_ANEGCOMPLETE); - pcs->link = !!(status & BMSR_LSTATUS); - - if (!pcs->link || !pcs->autoneg_complete) - return; - - lpa = phy_read_mmd(pcs, MDIO_MMD_VEND2, MII_LPA); - if (lpa < 0) - return; - - switch (lpa & MDIO_USXGMII_SPD_MASK) { - case MDIO_USXGMII_10: - pcs->speed = SPEED_10; - break; - case MDIO_USXGMII_100: - pcs->speed = SPEED_100; - break; - case MDIO_USXGMII_1000: - pcs->speed = SPEED_1000; - break; - case MDIO_USXGMII_2500: - pcs->speed = SPEED_2500; - break; - default: - break; - } - - if (lpa & MDIO_USXGMII_FULL_DUPLEX) - pcs->duplex = DUPLEX_FULL; - else - pcs->duplex = DUPLEX_HALF; -} - -void vsc9959_pcs_link_state(struct ocelot *ocelot, int port, - struct phylink_link_state *state) -{ - struct felix *felix = ocelot_to_felix(ocelot); - struct phy_device *pcs = felix->pcs[port]; - - if (!pcs) - return; - - pcs->speed = SPEED_UNKNOWN; - pcs->duplex = DUPLEX_UNKNOWN; - pcs->pause = 0; - pcs->asym_pause = 0; - - switch (pcs->interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_QSGMII: - vsc9959_pcs_link_state_sgmii(pcs, state); - break; - case PHY_INTERFACE_MODE_2500BASEX: - vsc9959_pcs_link_state_2500basex(pcs, state); - break; - case PHY_INTERFACE_MODE_USXGMII: - vsc9959_pcs_link_state_usxgmii(pcs, state); - break; - default: - return; - } - - vsc9959_pcs_link_state_resolve(pcs, state); -} - static void vsc9959_phylink_validate(struct ocelot *ocelot, int port, unsigned long *supported, struct phylink_link_state *state) @@ -1195,7 +855,7 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) int rc; felix->pcs = devm_kcalloc(dev, felix->info->num_ports, - sizeof(struct phy_device *), + sizeof(struct lynx_pcs *), GFP_KERNEL); if (!felix->pcs) { dev_err(dev, "failed to allocate array for PCS PHYs\n"); @@ -1246,18 +906,26 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) for (port = 0; port < felix->info->num_ports; port++) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - struct phy_device *pcs; - bool is_c45 = false; + struct mdio_device *pcs; + struct lynx_pcs *lynx; + + if (dsa_is_unused_port(felix->ds, port)) + continue; - if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_USXGMII) - is_c45 = true; + if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_INTERNAL) + continue; - pcs = get_phy_device(felix->imdio, port, is_c45); + pcs = mdio_device_create(felix->imdio, port); if (IS_ERR(pcs)) continue; - pcs->interface = ocelot_port->phy_mode; - felix->pcs[port] = pcs; + lynx = lynx_pcs_create(pcs); + if (!lynx) { + mdio_device_free(pcs); + continue; + } + + felix->pcs[port] = lynx; dev_info(dev, "Found PCS at internal MDIO address %d\n", port); } @@ -1271,12 +939,13 @@ void vsc9959_mdio_bus_free(struct ocelot *ocelot) int port; for (port = 0; port < ocelot->num_phys_ports; port++) { - struct phy_device *pcs = felix->pcs[port]; + struct lynx_pcs *pcs = felix->pcs[port]; if (!pcs) continue; - put_device(&pcs->mdio.dev); + mdio_device_free(pcs->mdio); + lynx_pcs_destroy(pcs); } mdiobus_unregister(felix->imdio); } @@ -1499,9 +1168,6 @@ static const struct felix_info felix_info_vsc9959 = { .imdio_pci_bar = 0, .mdio_bus_alloc = vsc9959_mdio_bus_alloc, .mdio_bus_free = vsc9959_mdio_bus_free, - .pcs_config = vsc9959_pcs_config, - .pcs_link_up = vsc9959_pcs_link_up, - .pcs_link_state = vsc9959_pcs_link_state, .phylink_validate = vsc9959_phylink_validate, .prevalidate_phy_mode = vsc9959_prevalidate_phy_mode, .port_setup_tc = vsc9959_port_setup_tc, diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 625b1891d955..2d6a5f5758f8 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -7,6 +7,7 @@ #include <soc/mscc/ocelot_sys.h> #include <soc/mscc/ocelot.h> #include <linux/of_platform.h> +#include <linux/pcs-lynx.h> #include <linux/packing.h> #include <linux/iopoll.h> #include "felix.h" @@ -960,18 +961,27 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) for (port = 0; port < felix->info->num_ports; port++) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - struct phy_device *pcs; int addr = port + 4; + struct mdio_device *pcs; + struct lynx_pcs *lynx; + + if (dsa_is_unused_port(felix->ds, port)) + continue; if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_INTERNAL) continue; - pcs = get_phy_device(felix->imdio, addr, false); + pcs = mdio_device_create(felix->imdio, addr); if (IS_ERR(pcs)) continue; - pcs->interface = ocelot_port->phy_mode; - felix->pcs[port] = pcs; + lynx = lynx_pcs_create(pcs); + if (!lynx) { + mdio_device_free(pcs); + continue; + } + + felix->pcs[port] = lynx; dev_info(dev, "Found PCS at internal MDIO address %d\n", addr); } @@ -1013,9 +1023,6 @@ static const struct felix_info seville_info_vsc9953 = { .num_ports = 10, .mdio_bus_alloc = vsc9953_mdio_bus_alloc, .mdio_bus_free = vsc9959_mdio_bus_free, - .pcs_config = vsc9959_pcs_config, - .pcs_link_up = vsc9959_pcs_link_up, - .pcs_link_state = vsc9959_pcs_link_state, .phylink_validate = vsc9953_phylink_validate, .prevalidate_phy_mode = vsc9953_prevalidate_phy_mode, .xmit_template_populate = vsc9953_xmit_template_populate, diff --git a/drivers/net/dsa/realtek-smi-core.h b/drivers/net/dsa/realtek-smi-core.h index 9a63b51e1d82..6f2dab7e33d6 100644 --- a/drivers/net/dsa/realtek-smi-core.h +++ b/drivers/net/dsa/realtek-smi-core.h @@ -25,6 +25,9 @@ struct rtl8366_mib_counter { const char *name; }; +/** + * struct rtl8366_vlan_mc - Virtual LAN member configuration + */ struct rtl8366_vlan_mc { u16 vid; u16 untag; @@ -119,7 +122,6 @@ int realtek_smi_setup_mdio(struct realtek_smi *smi); int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used); int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, u32 untag, u32 fid); -int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val); int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port, unsigned int vid); int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable); diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c index 8f40fbf70a82..2dcde7a91721 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -36,12 +36,113 @@ int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used) } EXPORT_SYMBOL_GPL(rtl8366_mc_is_used); +/** + * rtl8366_obtain_mc() - retrieve or allocate a VLAN member configuration + * @smi: the Realtek SMI device instance + * @vid: the VLAN ID to look up or allocate + * @vlanmc: the pointer will be assigned to a pointer to a valid member config + * if successful + * @return: index of a new member config or negative error number + */ +static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, + struct rtl8366_vlan_mc *vlanmc) +{ + struct rtl8366_vlan_4k vlan4k; + int ret; + int i; + + /* Try to find an existing member config entry for this VID */ + for (i = 0; i < smi->num_vlan_mc; i++) { + ret = smi->ops->get_vlan_mc(smi, i, vlanmc); + if (ret) { + dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + + if (vid == vlanmc->vid) + return i; + } + + /* We have no MC entry for this VID, try to find an empty one */ + for (i = 0; i < smi->num_vlan_mc; i++) { + ret = smi->ops->get_vlan_mc(smi, i, vlanmc); + if (ret) { + dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + + if (vlanmc->vid == 0 && vlanmc->member == 0) { + /* Update the entry from the 4K table */ + ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + if (ret) { + dev_err(smi->dev, "error looking for 4K VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + + vlanmc->vid = vid; + vlanmc->member = vlan4k.member; + vlanmc->untag = vlan4k.untag; + vlanmc->fid = vlan4k.fid; + ret = smi->ops->set_vlan_mc(smi, i, vlanmc); + if (ret) { + dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + + dev_dbg(smi->dev, "created new MC at index %d for VID %d\n", + i, vid); + return i; + } + } + + /* MC table is full, try to find an unused entry and replace it */ + for (i = 0; i < smi->num_vlan_mc; i++) { + int used; + + ret = rtl8366_mc_is_used(smi, i, &used); + if (ret) + return ret; + + if (!used) { + /* Update the entry from the 4K table */ + ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + if (ret) + return ret; + + vlanmc->vid = vid; + vlanmc->member = vlan4k.member; + vlanmc->untag = vlan4k.untag; + vlanmc->fid = vlan4k.fid; + ret = smi->ops->set_vlan_mc(smi, i, vlanmc); + if (ret) { + dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + dev_dbg(smi->dev, "recycled MC at index %i for VID %d\n", + i, vid); + return i; + } + } + + dev_err(smi->dev, "all VLAN member configurations are in use\n"); + return -ENOSPC; +} + int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, u32 untag, u32 fid) { + struct rtl8366_vlan_mc vlanmc; struct rtl8366_vlan_4k vlan4k; + int mc; int ret; - int i; + + if (!smi->ops->is_vlan_valid(smi, vid)) + return -EINVAL; dev_dbg(smi->dev, "setting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", @@ -63,133 +164,58 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, "resulting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", vid, vlan4k.member, vlan4k.untag); - /* Try to find an existing MC entry for this VID */ - for (i = 0; i < smi->num_vlan_mc; i++) { - struct rtl8366_vlan_mc vlanmc; - - ret = smi->ops->get_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - - if (vid == vlanmc.vid) { - /* update the MC entry */ - vlanmc.member |= member; - vlanmc.untag |= untag; - vlanmc.fid = fid; - - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); + /* Find or allocate a member config for this VID */ + ret = rtl8366_obtain_mc(smi, vid, &vlanmc); + if (ret < 0) + return ret; + mc = ret; - dev_dbg(smi->dev, - "resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n", - vid, vlanmc.member, vlanmc.untag); + /* Update the MC entry */ + vlanmc.member |= member; + vlanmc.untag |= untag; + vlanmc.fid = fid; - break; - } - } + /* Commit updates to the MC entry */ + ret = smi->ops->set_vlan_mc(smi, mc, &vlanmc); + if (ret) + dev_err(smi->dev, "failed to commit changes to VLAN MC index %d for VID %d\n", + mc, vid); + else + dev_dbg(smi->dev, + "resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n", + vid, vlanmc.member, vlanmc.untag); return ret; } EXPORT_SYMBOL_GPL(rtl8366_set_vlan); -int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val) -{ - struct rtl8366_vlan_mc vlanmc; - int ret; - int index; - - ret = smi->ops->get_mc_index(smi, port, &index); - if (ret) - return ret; - - ret = smi->ops->get_vlan_mc(smi, index, &vlanmc); - if (ret) - return ret; - - *val = vlanmc.vid; - return 0; -} -EXPORT_SYMBOL_GPL(rtl8366_get_pvid); - int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port, unsigned int vid) { struct rtl8366_vlan_mc vlanmc; - struct rtl8366_vlan_4k vlan4k; + int mc; int ret; - int i; - - /* Try to find an existing MC entry for this VID */ - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->get_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - - if (vid == vlanmc.vid) { - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - ret = smi->ops->set_mc_index(smi, port, i); - return ret; - } - } - - /* We have no MC entry for this VID, try to find an empty one */ - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->get_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - - if (vlanmc.vid == 0 && vlanmc.member == 0) { - /* Update the entry from the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); - if (ret) - return ret; - - vlanmc.vid = vid; - vlanmc.member = vlan4k.member; - vlanmc.untag = vlan4k.untag; - vlanmc.fid = vlan4k.fid; - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - - ret = smi->ops->set_mc_index(smi, port, i); - return ret; - } - } - - /* MC table is full, try to find an unused entry and replace it */ - for (i = 0; i < smi->num_vlan_mc; i++) { - int used; - - ret = rtl8366_mc_is_used(smi, i, &used); - if (ret) - return ret; - - if (!used) { - /* Update the entry from the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); - if (ret) - return ret; + if (!smi->ops->is_vlan_valid(smi, vid)) + return -EINVAL; - vlanmc.vid = vid; - vlanmc.member = vlan4k.member; - vlanmc.untag = vlan4k.untag; - vlanmc.fid = vlan4k.fid; - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; + /* Find or allocate a member config for this VID */ + ret = rtl8366_obtain_mc(smi, vid, &vlanmc); + if (ret < 0) + return ret; + mc = ret; - ret = smi->ops->set_mc_index(smi, port, i); - return ret; - } + ret = smi->ops->set_mc_index(smi, port, mc); + if (ret) { + dev_err(smi->dev, "set PVID: failed to set MC index %d for port %d\n", + mc, port); + return ret; } - dev_err(smi->dev, - "all VLAN member configurations are in use\n"); + dev_dbg(smi->dev, "set PVID: the PVID for port %d set to %d using existing MC index %d\n", + port, vid, mc); - return -ENOSPC; + return 0; } EXPORT_SYMBOL_GPL(rtl8366_set_pvid); @@ -389,7 +415,8 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, if (!smi->ops->is_vlan_valid(smi, vid)) return; - dev_info(smi->dev, "add VLAN on port %d, %s, %s\n", + dev_info(smi->dev, "add VLAN %d on port %d, %s, %s\n", + vlan->vid_begin, port, untagged ? "untagged" : "tagged", pvid ? " PVID" : "no PVID"); @@ -398,34 +425,26 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, dev_err(smi->dev, "port is DSA or CPU port\n"); for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { - int pvid_val = 0; - - dev_info(smi->dev, "add VLAN %04x\n", vid); member |= BIT(port); if (untagged) untag |= BIT(port); - /* To ensure that we have a valid MC entry for this VLAN, - * initialize the port VLAN ID here. - */ - ret = rtl8366_get_pvid(smi, port, &pvid_val); - if (ret < 0) { - dev_err(smi->dev, "could not lookup PVID for port %d\n", - port); - return; - } - if (pvid_val == 0) { - ret = rtl8366_set_pvid(smi, port, vid); - if (ret < 0) - return; - } - ret = rtl8366_set_vlan(smi, vid, member, untag, 0); if (ret) dev_err(smi->dev, "failed to set up VLAN %04x", vid); + + ret = rtl8366_set_pvid(smi, port, vid); + if (ret) + dev_err(smi->dev, + "failed to set PVID on port %d to VLAN %04x", + port, vid); + + if (!ret) + dev_dbg(smi->dev, "VLAN add: added VLAN %d with PVID on port %d\n", + vid, port); } } EXPORT_SYMBOL_GPL(rtl8366_vlan_add); diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index 48f1ff746799..ddc24f5e4123 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -35,7 +35,7 @@ #define RTL8366RB_SGCR_MAX_LENGTH_1522 RTL8366RB_SGCR_MAX_LENGTH(0x0) #define RTL8366RB_SGCR_MAX_LENGTH_1536 RTL8366RB_SGCR_MAX_LENGTH(0x1) #define RTL8366RB_SGCR_MAX_LENGTH_1552 RTL8366RB_SGCR_MAX_LENGTH(0x2) -#define RTL8366RB_SGCR_MAX_LENGTH_9216 RTL8366RB_SGCR_MAX_LENGTH(0x3) +#define RTL8366RB_SGCR_MAX_LENGTH_16000 RTL8366RB_SGCR_MAX_LENGTH(0x3) #define RTL8366RB_SGCR_EN_VLAN BIT(13) #define RTL8366RB_SGCR_EN_VLAN_4KTB BIT(14) @@ -969,8 +969,10 @@ static enum dsa_tag_protocol rtl8366_get_tag_protocol(struct dsa_switch *ds, return DSA_TAG_PROTO_RTL4_A; } -static void rtl8366rb_adjust_link(struct dsa_switch *ds, int port, - struct phy_device *phydev) +static void +rtl8366rb_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, + phy_interface_t interface, struct phy_device *phydev, + int speed, int duplex, bool tx_pause, bool rx_pause) { struct realtek_smi *smi = ds->priv; int ret; @@ -978,25 +980,52 @@ static void rtl8366rb_adjust_link(struct dsa_switch *ds, int port, if (port != smi->cpu_port) return; - dev_info(smi->dev, "adjust link on CPU port (%d)\n", port); + dev_dbg(smi->dev, "MAC link up on CPU port (%d)\n", port); /* Force the fixed CPU port into 1Gbit mode, no autonegotiation */ ret = regmap_update_bits(smi->map, RTL8366RB_MAC_FORCE_CTRL_REG, BIT(port), BIT(port)); - if (ret) + if (ret) { + dev_err(smi->dev, "failed to force 1Gbit on CPU port\n"); return; + } ret = regmap_update_bits(smi->map, RTL8366RB_PAACR2, 0xFF00U, RTL8366RB_PAACR_CPU_PORT << 8); - if (ret) + if (ret) { + dev_err(smi->dev, "failed to set PAACR on CPU port\n"); return; + } /* Enable the CPU port */ ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), 0); - if (ret) + if (ret) { + dev_err(smi->dev, "failed to enable the CPU port\n"); + return; + } +} + +static void +rtl8366rb_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, + phy_interface_t interface) +{ + struct realtek_smi *smi = ds->priv; + int ret; + + if (port != smi->cpu_port) return; + + dev_dbg(smi->dev, "MAC link down on CPU port (%d)\n", port); + + /* Disable the CPU port */ + ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), + BIT(port)); + if (ret) { + dev_err(smi->dev, "failed to disable the CPU port\n"); + return; + } } static void rb8366rb_set_port_led(struct realtek_smi *smi, @@ -1077,6 +1106,40 @@ rtl8366rb_port_disable(struct dsa_switch *ds, int port) rb8366rb_set_port_led(smi, port, false); } +static int rtl8366rb_change_mtu(struct dsa_switch *ds, int port, int new_mtu) +{ + struct realtek_smi *smi = ds->priv; + u32 len; + + /* The first setting, 1522 bytes, is max IP packet 1500 bytes, + * plus ethernet header, 1518 bytes, plus CPU tag, 4 bytes. + * This function should consider the parameter an SDU, so the + * MTU passed for this setting is 1518 bytes. The same logic + * of subtracting the DSA tag of 4 bytes apply to the other + * settings. + */ + if (new_mtu <= 1518) + len = RTL8366RB_SGCR_MAX_LENGTH_1522; + else if (new_mtu > 1518 && new_mtu <= 1532) + len = RTL8366RB_SGCR_MAX_LENGTH_1536; + else if (new_mtu > 1532 && new_mtu <= 1548) + len = RTL8366RB_SGCR_MAX_LENGTH_1552; + else + len = RTL8366RB_SGCR_MAX_LENGTH_16000; + + return regmap_update_bits(smi->map, RTL8366RB_SGCR, + RTL8366RB_SGCR_MAX_LENGTH_MASK, + len); +} + +static int rtl8366rb_max_mtu(struct dsa_switch *ds, int port) +{ + /* The max MTU is 16000 bytes, so we subtract the CPU tag + * and the max presented to the system is 15996 bytes. + */ + return 15996; +} + static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid, struct rtl8366_vlan_4k *vlan4k) { @@ -1405,7 +1468,8 @@ static int rtl8366rb_detect(struct realtek_smi *smi) static const struct dsa_switch_ops rtl8366rb_switch_ops = { .get_tag_protocol = rtl8366_get_tag_protocol, .setup = rtl8366rb_setup, - .adjust_link = rtl8366rb_adjust_link, + .phylink_mac_link_up = rtl8366rb_mac_link_up, + .phylink_mac_link_down = rtl8366rb_mac_link_down, .get_strings = rtl8366_get_strings, .get_ethtool_stats = rtl8366_get_ethtool_stats, .get_sset_count = rtl8366_get_sset_count, @@ -1415,6 +1479,8 @@ static const struct dsa_switch_ops rtl8366rb_switch_ops = { .port_vlan_del = rtl8366_vlan_del, .port_enable = rtl8366rb_port_enable, .port_disable = rtl8366rb_port_disable, + .port_change_mtu = rtl8366rb_change_mtu, + .port_max_mtu = rtl8366rb_max_mtu, }; static const struct realtek_smi_ops rtl8366rb_smi_ops = { diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index c3f6f124e5f0..5a28dfb36ec3 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3415,7 +3415,7 @@ static int sja1105_check_device_id(struct sja1105_private *priv) sja1105_unpack(prod_id, &part_no, 19, 4, SJA1105_SIZE_DEVICE_ID); - for (match = sja1105_dt_ids; match->compatible; match++) { + for (match = sja1105_dt_ids; match->compatible[0]; match++) { const struct sja1105_info *info = match->data; /* Is what's been probed in our match table at all? */ diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c index 139d0120f511..667f38c9e4c6 100644 --- a/drivers/net/ethernet/3com/3c509.c +++ b/drivers/net/ethernet/3com/3c509.c @@ -1259,14 +1259,14 @@ el3_up(struct net_device *dev) pr_cont("Forcing 3c5x9b full-duplex mode"); break; } - /* fall through */ + fallthrough; case 8: /* set full-duplex mode based on eeprom config setting */ if ((sw_info & 0x000f) && (sw_info & 0x8000)) { pr_cont("Setting 3c5x9b full-duplex mode (from EEPROM configuration bit)"); break; } - /* fall through */ + fallthrough; default: /* xcvr=(0 || 4) OR user has an old 3c5x9 non "B" model */ pr_cont("Setting 3c5x9/3c5x9B half-duplex mode"); diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index ef1c3151fbb2..f66e7fb9a2bb 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -951,7 +951,7 @@ static struct net_device_stats *el3_get_stats(struct net_device *dev) static void update_stats(struct net_device *dev) { unsigned int ioaddr = dev->base_addr; - u8 rx, tx, up; + u8 up; pr_debug("%s: updating the statistics.\n", dev->name); @@ -972,8 +972,8 @@ static void update_stats(struct net_device *dev) dev->stats.tx_packets += (up&0x30) << 4; /* Rx packets */ inb(ioaddr + 7); /* Tx deferrals */ inb(ioaddr + 8); - rx = inw(ioaddr + 10); - tx = inw(ioaddr + 12); + /* rx */ inw(ioaddr + 10); + /* tx */ inw(ioaddr + 12); EL3WINDOW(4); /* BadSSD */ inb(ioaddr + 12); @@ -1046,7 +1046,7 @@ static int el3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) switch(cmd) { case SIOCGMIIPHY: /* Get the address of the PHY in use. */ data->phy_id = phy; - /* fall through */ + fallthrough; case SIOCGMIIREG: /* Read the specified MII register. */ { int saved_window; diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index d3b30bacc94e..f11474cac59f 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -789,8 +789,8 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev) * it with zeros to ETH_ZLEN for us. */ if (skb_shinfo(skb)->nr_frags == 0) { - skb_dma = pci_map_single(tp->tx_pdev, skb->data, skb->len, - PCI_DMA_TODEVICE); + skb_dma = dma_map_single(&tp->tx_pdev->dev, skb->data, + skb->len, DMA_TO_DEVICE); txd->flags = TYPHOON_FRAG_DESC | TYPHOON_DESC_VALID; txd->len = cpu_to_le16(skb->len); txd->frag.addr = cpu_to_le32(skb_dma); @@ -800,8 +800,8 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev) int i, len; len = skb_headlen(skb); - skb_dma = pci_map_single(tp->tx_pdev, skb->data, len, - PCI_DMA_TODEVICE); + skb_dma = dma_map_single(&tp->tx_pdev->dev, skb->data, len, + DMA_TO_DEVICE); txd->flags = TYPHOON_FRAG_DESC | TYPHOON_DESC_VALID; txd->len = cpu_to_le16(len); txd->frag.addr = cpu_to_le32(skb_dma); @@ -818,8 +818,8 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev) len = skb_frag_size(frag); frag_addr = skb_frag_address(frag); - skb_dma = pci_map_single(tp->tx_pdev, frag_addr, len, - PCI_DMA_TODEVICE); + skb_dma = dma_map_single(&tp->tx_pdev->dev, frag_addr, + len, DMA_TO_DEVICE); txd->flags = TYPHOON_FRAG_DESC | TYPHOON_DESC_VALID; txd->len = cpu_to_le16(len); txd->frag.addr = cpu_to_le32(skb_dma); @@ -1349,12 +1349,12 @@ typhoon_download_firmware(struct typhoon *tp) image_data = typhoon_fw->data; fHdr = (struct typhoon_file_header *) image_data; - /* Cannot just map the firmware image using pci_map_single() as + /* Cannot just map the firmware image using dma_map_single() as * the firmware is vmalloc()'d and may not be physically contiguous, - * so we allocate some consistent memory to copy the sections into. + * so we allocate some coherent memory to copy the sections into. */ err = -ENOMEM; - dpage = pci_alloc_consistent(pdev, PAGE_SIZE, &dpage_dma); + dpage = dma_alloc_coherent(&pdev->dev, PAGE_SIZE, &dpage_dma, GFP_ATOMIC); if (!dpage) { netdev_err(tp->dev, "no DMA mem for firmware\n"); goto err_out; @@ -1460,7 +1460,7 @@ err_out_irq: iowrite32(irqMasked, ioaddr + TYPHOON_REG_INTR_MASK); iowrite32(irqEnabled, ioaddr + TYPHOON_REG_INTR_ENABLE); - pci_free_consistent(pdev, PAGE_SIZE, dpage, dpage_dma); + dma_free_coherent(&pdev->dev, PAGE_SIZE, dpage, dpage_dma); err_out: return err; @@ -1527,8 +1527,8 @@ typhoon_clean_tx(struct typhoon *tp, struct transmit_ring *txRing, */ skb_dma = (dma_addr_t) le32_to_cpu(tx->frag.addr); dma_len = le16_to_cpu(tx->len); - pci_unmap_single(tp->pdev, skb_dma, dma_len, - PCI_DMA_TODEVICE); + dma_unmap_single(&tp->pdev->dev, skb_dma, dma_len, + DMA_TO_DEVICE); } tx->flags = 0; @@ -1609,8 +1609,8 @@ typhoon_alloc_rx_skb(struct typhoon *tp, u32 idx) skb_reserve(skb, 2); #endif - dma_addr = pci_map_single(tp->pdev, skb->data, - PKT_BUF_SZ, PCI_DMA_FROMDEVICE); + dma_addr = dma_map_single(&tp->pdev->dev, skb->data, PKT_BUF_SZ, + DMA_FROM_DEVICE); /* Since no card does 64 bit DAC, the high bits will never * change from zero. @@ -1665,20 +1665,19 @@ typhoon_rx(struct typhoon *tp, struct basic_ring *rxRing, volatile __le32 * read if (pkt_len < rx_copybreak && (new_skb = netdev_alloc_skb(tp->dev, pkt_len + 2)) != NULL) { skb_reserve(new_skb, 2); - pci_dma_sync_single_for_cpu(tp->pdev, dma_addr, - PKT_BUF_SZ, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&tp->pdev->dev, dma_addr, + PKT_BUF_SZ, DMA_FROM_DEVICE); skb_copy_to_linear_data(new_skb, skb->data, pkt_len); - pci_dma_sync_single_for_device(tp->pdev, dma_addr, - PKT_BUF_SZ, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&tp->pdev->dev, dma_addr, + PKT_BUF_SZ, + DMA_FROM_DEVICE); skb_put(new_skb, pkt_len); typhoon_recycle_rx_skb(tp, idx); } else { new_skb = skb; skb_put(new_skb, pkt_len); - pci_unmap_single(tp->pdev, dma_addr, PKT_BUF_SZ, - PCI_DMA_FROMDEVICE); + dma_unmap_single(&tp->pdev->dev, dma_addr, PKT_BUF_SZ, + DMA_FROM_DEVICE); typhoon_alloc_rx_skb(tp, idx); } new_skb->protocol = eth_type_trans(new_skb, tp->dev); @@ -1792,8 +1791,8 @@ typhoon_free_rx_rings(struct typhoon *tp) for (i = 0; i < RXENT_ENTRIES; i++) { struct rxbuff_ent *rxb = &tp->rxbuffers[i]; if (rxb->skb) { - pci_unmap_single(tp->pdev, rxb->dma_addr, PKT_BUF_SZ, - PCI_DMA_FROMDEVICE); + dma_unmap_single(&tp->pdev->dev, rxb->dma_addr, + PKT_BUF_SZ, DMA_FROM_DEVICE); dev_kfree_skb(rxb->skb); rxb->skb = NULL; } @@ -2306,7 +2305,7 @@ typhoon_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto error_out_disable; } - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err < 0) { err_msg = "No usable DMA configuration"; goto error_out_mwi; @@ -2355,8 +2354,8 @@ typhoon_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* allocate pci dma space for rx and tx descriptor rings */ - shared = pci_alloc_consistent(pdev, sizeof(struct typhoon_shared), - &shared_dma); + shared = dma_alloc_coherent(&pdev->dev, sizeof(struct typhoon_shared), + &shared_dma, GFP_KERNEL); if (!shared) { err_msg = "could not allocate DMA memory"; err = -ENOMEM; @@ -2509,8 +2508,8 @@ error_out_reset: typhoon_reset(ioaddr, NoWait); error_out_dma: - pci_free_consistent(pdev, sizeof(struct typhoon_shared), - shared, shared_dma); + dma_free_coherent(&pdev->dev, sizeof(struct typhoon_shared), shared, + shared_dma); error_out_remap: pci_iounmap(pdev, ioaddr); error_out_regions: @@ -2537,8 +2536,8 @@ typhoon_remove_one(struct pci_dev *pdev) pci_restore_state(pdev); typhoon_reset(tp->ioaddr, NoWait); pci_iounmap(pdev, tp->ioaddr); - pci_free_consistent(pdev, sizeof(struct typhoon_shared), - tp->shared, tp->shared_dma); + dma_free_coherent(&pdev->dev, sizeof(struct typhoon_shared), + tp->shared, tp->shared_dma); pci_release_regions(pdev); pci_clear_mwi(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index aeae7966a082..2488bfdb9133 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -610,7 +610,7 @@ static int axnet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) switch (cmd) { case SIOCGMIIPHY: data->phy_id = info->phy_id; - /* Fall through */ + fallthrough; case SIOCGMIIREG: /* Read MII PHY register. */ data->val_out = mdio_read(mii_addr, data->phy_id, data->reg_num & 0x1f); return 0; @@ -657,8 +657,10 @@ static void block_input(struct net_device *dev, int count, outb_p(E8390_RREAD+E8390_START, nic_base + AXNET_CMD); insw(nic_base + AXNET_DATAPORT,buf,count>>1); - if (count & 0x01) - buf[count-1] = inb(nic_base + AXNET_DATAPORT), xfer_count++; + if (count & 0x01) { + buf[count-1] = inb(nic_base + AXNET_DATAPORT); + xfer_count++; + } } @@ -898,6 +900,7 @@ static int ax_close(struct net_device *dev) /** * axnet_tx_timeout - handle transmit time out condition * @dev: network device which has apparently fallen asleep + * @txqueue: unused * * Called by kernel when device never acknowledges a transmit has * completed (or failed) - i.e. never posted a Tx related interrupt. @@ -1269,10 +1272,12 @@ static void ei_tx_intr(struct net_device *dev) ei_local->txing = 1; NS8390_trigger_send(dev, ei_local->tx2, ei_local->tx_start_page + 6); netif_trans_update(dev); - ei_local->tx2 = -1, + ei_local->tx2 = -1; ei_local->lasttx = 2; + } else { + ei_local->lasttx = 20; + ei_local->txing = 0; } - else ei_local->lasttx = 20, ei_local->txing = 0; } else if (ei_local->tx2 < 0) { @@ -1288,9 +1293,10 @@ static void ei_tx_intr(struct net_device *dev) netif_trans_update(dev); ei_local->tx1 = -1; ei_local->lasttx = 1; + } else { + ei_local->lasttx = 10; + ei_local->txing = 0; } - else - ei_local->lasttx = 10, ei_local->txing = 0; } // else // netdev_warn(dev, "unexpected TX-done interrupt, lasttx=%d\n", diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c index babc92e2692e..1f48d7f6365c 100644 --- a/drivers/net/ethernet/8390/lib8390.c +++ b/drivers/net/ethernet/8390/lib8390.c @@ -597,10 +597,12 @@ static void ei_tx_intr(struct net_device *dev) ei_local->txing = 1; NS8390_trigger_send(dev, ei_local->tx2, ei_local->tx_start_page + 6); netif_trans_update(dev); - ei_local->tx2 = -1, + ei_local->tx2 = -1; ei_local->lasttx = 2; - } else - ei_local->lasttx = 20, ei_local->txing = 0; + } else { + ei_local->lasttx = 20; + ei_local->txing = 0; + } } else if (ei_local->tx2 < 0) { if (ei_local->lasttx != 2 && ei_local->lasttx != -2) pr_err("%s: bogus last_tx_buffer %d, tx2=%d\n", @@ -612,8 +614,10 @@ static void ei_tx_intr(struct net_device *dev) netif_trans_update(dev); ei_local->tx1 = -1; ei_local->lasttx = 1; - } else - ei_local->lasttx = 10, ei_local->txing = 0; + } else { + ei_local->lasttx = 10; + ei_local->txing = 0; + } } /* else netdev_warn(dev, "unexpected TX-done interrupt, lasttx=%d\n", ei_local->lasttx); diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index 645efac6310d..9d3b1e0e425c 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -1108,7 +1108,7 @@ static int ei_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) switch (cmd) { case SIOCGMIIPHY: data->phy_id = info->phy_id; - /* fall through */ + fallthrough; case SIOCGMIIREG: /* Read MII PHY register. */ data->val_out = mdio_read(mii_addr, data->phy_id, data->reg_num & 0x1f); return 0; @@ -1178,8 +1178,10 @@ static void dma_block_input(struct net_device *dev, int count, outb_p(E8390_RREAD+E8390_START, nic_base + PCNET_CMD); insw(nic_base + PCNET_DATAPORT,buf,count>>1); - if (count & 0x01) - buf[count-1] = inb(nic_base + PCNET_DATAPORT), xfer_count++; + if (count & 0x01) { + buf[count-1] = inb(nic_base + PCNET_DATAPORT); + xfer_count++; + } /* This was for the ALPHA version only, but enough people have been encountering problems that it is still here. */ diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index ba0055bb1614..555299737b51 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -886,7 +886,9 @@ static int netdev_open(struct net_device *dev) tx_ring_size = ((sizeof(starfire_tx_desc) * TX_RING_SIZE + QUEUE_ALIGN - 1) / QUEUE_ALIGN) * QUEUE_ALIGN; rx_ring_size = sizeof(struct starfire_rx_desc) * RX_RING_SIZE; np->queue_mem_size = tx_done_q_size + rx_done_q_size + tx_ring_size + rx_ring_size; - np->queue_mem = pci_alloc_consistent(np->pci_dev, np->queue_mem_size, &np->queue_mem_dma); + np->queue_mem = dma_alloc_coherent(&np->pci_dev->dev, + np->queue_mem_size, + &np->queue_mem_dma, GFP_ATOMIC); if (np->queue_mem == NULL) { free_irq(irq, dev); return -ENOMEM; @@ -1136,9 +1138,11 @@ static void init_ring(struct net_device *dev) np->rx_info[i].skb = skb; if (skb == NULL) break; - np->rx_info[i].mapping = pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(np->pci_dev, - np->rx_info[i].mapping)) { + np->rx_info[i].mapping = dma_map_single(&np->pci_dev->dev, + skb->data, + np->rx_buf_sz, + DMA_FROM_DEVICE); + if (dma_mapping_error(&np->pci_dev->dev, np->rx_info[i].mapping)) { dev_kfree_skb(skb); np->rx_info[i].skb = NULL; break; @@ -1217,18 +1221,19 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev) status |= skb_first_frag_len(skb) | (skb_num_frags(skb) << 16); np->tx_info[entry].mapping = - pci_map_single(np->pci_dev, skb->data, skb_first_frag_len(skb), PCI_DMA_TODEVICE); + dma_map_single(&np->pci_dev->dev, skb->data, + skb_first_frag_len(skb), + DMA_TO_DEVICE); } else { const skb_frag_t *this_frag = &skb_shinfo(skb)->frags[i - 1]; status |= skb_frag_size(this_frag); np->tx_info[entry].mapping = - pci_map_single(np->pci_dev, + dma_map_single(&np->pci_dev->dev, skb_frag_address(this_frag), skb_frag_size(this_frag), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); } - if (pci_dma_mapping_error(np->pci_dev, - np->tx_info[entry].mapping)) { + if (dma_mapping_error(&np->pci_dev->dev, np->tx_info[entry].mapping)) { dev->stats.tx_dropped++; goto err_out; } @@ -1271,18 +1276,16 @@ err_out: entry = prev_tx % TX_RING_SIZE; np->tx_info[entry].skb = NULL; if (i > 0) { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, np->tx_info[entry].mapping, - skb_first_frag_len(skb), - PCI_DMA_TODEVICE); + skb_first_frag_len(skb), DMA_TO_DEVICE); np->tx_info[entry].mapping = 0; entry = (entry + np->tx_info[entry].used_slots) % TX_RING_SIZE; for (j = 1; j < i; j++) { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, np->tx_info[entry].mapping, - skb_frag_size( - &skb_shinfo(skb)->frags[j-1]), - PCI_DMA_TODEVICE); + skb_frag_size(&skb_shinfo(skb)->frags[j - 1]), + DMA_TO_DEVICE); entry++; } } @@ -1356,20 +1359,20 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) u16 entry = (tx_status & 0x7fff) / sizeof(starfire_tx_desc); struct sk_buff *skb = np->tx_info[entry].skb; np->tx_info[entry].skb = NULL; - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, np->tx_info[entry].mapping, skb_first_frag_len(skb), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); np->tx_info[entry].mapping = 0; np->dirty_tx += np->tx_info[entry].used_slots; entry = (entry + np->tx_info[entry].used_slots) % TX_RING_SIZE; { int i; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, np->tx_info[entry].mapping, skb_frag_size(&skb_shinfo(skb)->frags[i]), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); np->dirty_tx++; entry++; } @@ -1461,16 +1464,18 @@ static int __netdev_rx(struct net_device *dev, int *quota) if (pkt_len < rx_copybreak && (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ - pci_dma_sync_single_for_cpu(np->pci_dev, - np->rx_info[entry].mapping, - pkt_len, PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&np->pci_dev->dev, + np->rx_info[entry].mapping, + pkt_len, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, np->rx_info[entry].skb->data, pkt_len); - pci_dma_sync_single_for_device(np->pci_dev, - np->rx_info[entry].mapping, - pkt_len, PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&np->pci_dev->dev, + np->rx_info[entry].mapping, + pkt_len, DMA_FROM_DEVICE); skb_put(skb, pkt_len); } else { - pci_unmap_single(np->pci_dev, np->rx_info[entry].mapping, np->rx_buf_sz, PCI_DMA_FROMDEVICE); + dma_unmap_single(&np->pci_dev->dev, + np->rx_info[entry].mapping, + np->rx_buf_sz, DMA_FROM_DEVICE); skb = np->rx_info[entry].skb; skb_put(skb, pkt_len); np->rx_info[entry].skb = NULL; @@ -1588,9 +1593,9 @@ static void refill_rx_ring(struct net_device *dev) if (skb == NULL) break; /* Better luck next round. */ np->rx_info[entry].mapping = - pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(np->pci_dev, - np->rx_info[entry].mapping)) { + dma_map_single(&np->pci_dev->dev, skb->data, + np->rx_buf_sz, DMA_FROM_DEVICE); + if (dma_mapping_error(&np->pci_dev->dev, np->rx_info[entry].mapping)) { dev_kfree_skb(skb); np->rx_info[entry].skb = NULL; break; @@ -1963,7 +1968,9 @@ static int netdev_close(struct net_device *dev) for (i = 0; i < RX_RING_SIZE; i++) { np->rx_ring[i].rxaddr = cpu_to_dma(0xBADF00D0); /* An invalid address. */ if (np->rx_info[i].skb != NULL) { - pci_unmap_single(np->pci_dev, np->rx_info[i].mapping, np->rx_buf_sz, PCI_DMA_FROMDEVICE); + dma_unmap_single(&np->pci_dev->dev, + np->rx_info[i].mapping, + np->rx_buf_sz, DMA_FROM_DEVICE); dev_kfree_skb(np->rx_info[i].skb); } np->rx_info[i].skb = NULL; @@ -1973,9 +1980,8 @@ static int netdev_close(struct net_device *dev) struct sk_buff *skb = np->tx_info[i].skb; if (skb == NULL) continue; - pci_unmap_single(np->pci_dev, - np->tx_info[i].mapping, - skb_first_frag_len(skb), PCI_DMA_TODEVICE); + dma_unmap_single(&np->pci_dev->dev, np->tx_info[i].mapping, + skb_first_frag_len(skb), DMA_TO_DEVICE); np->tx_info[i].mapping = 0; dev_kfree_skb(skb); np->tx_info[i].skb = NULL; @@ -2018,7 +2024,8 @@ static void starfire_remove_one(struct pci_dev *pdev) unregister_netdev(dev); if (np->queue_mem) - pci_free_consistent(pdev, np->queue_mem_size, np->queue_mem, np->queue_mem_dma); + dma_free_coherent(&pdev->dev, np->queue_mem_size, + np->queue_mem, np->queue_mem_dma); /* XXX: add wakeup code -- requires firmware for MagicPacket */ diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c index 6234fcd844ee..696517eae77f 100644 --- a/drivers/net/ethernet/alacritech/slicoss.c +++ b/drivers/net/ethernet/alacritech/slicoss.c @@ -1712,13 +1712,13 @@ static bool slic_is_fiber(unsigned short subdev) { switch (subdev) { /* Mojave */ - case PCI_SUBDEVICE_ID_ALACRITECH_1000X1F: /* fallthrough */ - case PCI_SUBDEVICE_ID_ALACRITECH_SES1001F: /* fallthrough */ + case PCI_SUBDEVICE_ID_ALACRITECH_1000X1F: + case PCI_SUBDEVICE_ID_ALACRITECH_SES1001F: fallthrough; /* Oasis */ - case PCI_SUBDEVICE_ID_ALACRITECH_SEN2002XF: /* fallthrough */ - case PCI_SUBDEVICE_ID_ALACRITECH_SEN2001XF: /* fallthrough */ - case PCI_SUBDEVICE_ID_ALACRITECH_SEN2104EF: /* fallthrough */ - case PCI_SUBDEVICE_ID_ALACRITECH_SEN2102EF: /* fallthrough */ + case PCI_SUBDEVICE_ID_ALACRITECH_SEN2002XF: + case PCI_SUBDEVICE_ID_ALACRITECH_SEN2001XF: + case PCI_SUBDEVICE_ID_ALACRITECH_SEN2104EF: + case PCI_SUBDEVICE_ID_ALACRITECH_SEN2102EF: return true; } return false; diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index ac86fcae1582..8470c836fa18 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -547,7 +547,7 @@ static int acenic_probe_one(struct pci_dev *pdev, ap->name); break; } - /* Fall through */ + fallthrough; case PCI_VENDOR_ID_SGI: printk(KERN_INFO "%s: SGI AceNIC ", ap->name); break; diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h index b818a169c193..86869baa7b8e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h +++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h @@ -117,6 +117,8 @@ enum ena_admin_completion_policy_type { enum ena_admin_get_stats_type { ENA_ADMIN_GET_STATS_TYPE_BASIC = 0, ENA_ADMIN_GET_STATS_TYPE_EXTENDED = 1, + /* extra HW stats for specific network interface */ + ENA_ADMIN_GET_STATS_TYPE_ENI = 2, }; enum ena_admin_get_stats_scope { @@ -410,10 +412,43 @@ struct ena_admin_basic_stats { u32 tx_drops_high; }; +/* ENI Statistics Command. */ +struct ena_admin_eni_stats { + /* The number of packets shaped due to inbound aggregate BW + * allowance being exceeded + */ + u64 bw_in_allowance_exceeded; + + /* The number of packets shaped due to outbound aggregate BW + * allowance being exceeded + */ + u64 bw_out_allowance_exceeded; + + /* The number of packets shaped due to PPS allowance being exceeded */ + u64 pps_allowance_exceeded; + + /* The number of packets shaped due to connection tracking + * allowance being exceeded and leading to failure in establishment + * of new connections + */ + u64 conntrack_allowance_exceeded; + + /* The number of packets shaped due to linklocal packet rate + * allowance being exceeded + */ + u64 linklocal_allowance_exceeded; +}; + struct ena_admin_acq_get_stats_resp { struct ena_admin_acq_common_desc acq_common_desc; - struct ena_admin_basic_stats basic_stats; + union { + u64 raw[7]; + + struct ena_admin_basic_stats basic_stats; + + struct ena_admin_eni_stats eni_stats; + } u; }; struct ena_admin_get_set_feature_common_desc { diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 435bf05a853c..452e66b39a17 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -2167,6 +2167,21 @@ static int ena_get_dev_stats(struct ena_com_dev *ena_dev, return ret; } +int ena_com_get_eni_stats(struct ena_com_dev *ena_dev, + struct ena_admin_eni_stats *stats) +{ + struct ena_com_stats_ctx ctx; + int ret; + + memset(&ctx, 0x0, sizeof(ctx)); + ret = ena_get_dev_stats(ena_dev, &ctx, ENA_ADMIN_GET_STATS_TYPE_ENI); + if (likely(ret == 0)) + memcpy(stats, &ctx.get_resp.u.eni_stats, + sizeof(ctx.get_resp.u.eni_stats)); + + return ret; +} + int ena_com_get_dev_basic_stats(struct ena_com_dev *ena_dev, struct ena_admin_basic_stats *stats) { @@ -2176,8 +2191,8 @@ int ena_com_get_dev_basic_stats(struct ena_com_dev *ena_dev, memset(&ctx, 0x0, sizeof(ctx)); ret = ena_get_dev_stats(ena_dev, &ctx, ENA_ADMIN_GET_STATS_TYPE_BASIC); if (likely(ret == 0)) - memcpy(stats, &ctx.get_resp.basic_stats, - sizeof(ctx.get_resp.basic_stats)); + memcpy(stats, &ctx.get_resp.u.basic_stats, + sizeof(ctx.get_resp.u.basic_stats)); return ret; } diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h index 4287d47b2b0b..e4aafeda0cae 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_com.h @@ -616,6 +616,15 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev, int ena_com_get_dev_basic_stats(struct ena_com_dev *ena_dev, struct ena_admin_basic_stats *stats); +/* ena_com_get_eni_stats - Get extended network interface statistics + * @ena_dev: ENA communication layer struct + * @stats: stats return value + * + * @return: 0 on Success and negative value otherwise. + */ +int ena_com_get_eni_stats(struct ena_com_dev *ena_dev, + struct ena_admin_eni_stats *stats); + /* ena_com_set_dev_mtu - Configure the device mtu. * @ena_dev: ENA communication layer struct * @mtu: mtu value diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index 430275bc0d04..1e6457dd662a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -41,12 +41,17 @@ struct ena_stats { #define ENA_STAT_ENA_COM_ENTRY(stat) { \ .name = #stat, \ - .stat_offset = offsetof(struct ena_com_stats_admin, stat) \ + .stat_offset = offsetof(struct ena_com_stats_admin, stat) / sizeof(u64) \ } #define ENA_STAT_ENTRY(stat, stat_type) { \ .name = #stat, \ - .stat_offset = offsetof(struct ena_stats_##stat_type, stat) \ + .stat_offset = offsetof(struct ena_stats_##stat_type, stat) / sizeof(u64) \ +} + +#define ENA_STAT_HW_ENTRY(stat, stat_type) { \ + .name = #stat, \ + .stat_offset = offsetof(struct ena_admin_##stat_type, stat) / sizeof(u64) \ } #define ENA_STAT_RX_ENTRY(stat) \ @@ -58,6 +63,9 @@ struct ena_stats { #define ENA_STAT_GLOBAL_ENTRY(stat) \ ENA_STAT_ENTRY(stat, dev) +#define ENA_STAT_ENI_ENTRY(stat) \ + ENA_STAT_HW_ENTRY(stat, eni_stats) + static const struct ena_stats ena_stats_global_strings[] = { ENA_STAT_GLOBAL_ENTRY(tx_timeout), ENA_STAT_GLOBAL_ENTRY(suspend), @@ -68,6 +76,14 @@ static const struct ena_stats ena_stats_global_strings[] = { ENA_STAT_GLOBAL_ENTRY(admin_q_pause), }; +static const struct ena_stats ena_stats_eni_strings[] = { + ENA_STAT_ENI_ENTRY(bw_in_allowance_exceeded), + ENA_STAT_ENI_ENTRY(bw_out_allowance_exceeded), + ENA_STAT_ENI_ENTRY(pps_allowance_exceeded), + ENA_STAT_ENI_ENTRY(conntrack_allowance_exceeded), + ENA_STAT_ENI_ENTRY(linklocal_allowance_exceeded), +}; + static const struct ena_stats ena_stats_tx_strings[] = { ENA_STAT_TX_ENTRY(cnt), ENA_STAT_TX_ENTRY(bytes), @@ -100,6 +116,11 @@ static const struct ena_stats ena_stats_rx_strings[] = { ENA_STAT_RX_ENTRY(bad_req_id), ENA_STAT_RX_ENTRY(empty_rx_ring), ENA_STAT_RX_ENTRY(csum_unchecked), + ENA_STAT_RX_ENTRY(xdp_aborted), + ENA_STAT_RX_ENTRY(xdp_drop), + ENA_STAT_RX_ENTRY(xdp_pass), + ENA_STAT_RX_ENTRY(xdp_tx), + ENA_STAT_RX_ENTRY(xdp_invalid), }; static const struct ena_stats ena_stats_ena_com_strings[] = { @@ -110,10 +131,12 @@ static const struct ena_stats ena_stats_ena_com_strings[] = { ENA_STAT_ENA_COM_ENTRY(no_completion), }; -#define ENA_STATS_ARRAY_GLOBAL ARRAY_SIZE(ena_stats_global_strings) -#define ENA_STATS_ARRAY_TX ARRAY_SIZE(ena_stats_tx_strings) -#define ENA_STATS_ARRAY_RX ARRAY_SIZE(ena_stats_rx_strings) -#define ENA_STATS_ARRAY_ENA_COM ARRAY_SIZE(ena_stats_ena_com_strings) +#define ENA_STATS_ARRAY_GLOBAL ARRAY_SIZE(ena_stats_global_strings) +#define ENA_STATS_ARRAY_TX ARRAY_SIZE(ena_stats_tx_strings) +#define ENA_STATS_ARRAY_RX ARRAY_SIZE(ena_stats_rx_strings) +#define ENA_STATS_ARRAY_ENA_COM ARRAY_SIZE(ena_stats_ena_com_strings) +#define ENA_STATS_ARRAY_ENI(adapter) \ + (ARRAY_SIZE(ena_stats_eni_strings) * (adapter)->eni_stats_supported) static void ena_safe_update_stat(u64 *src, u64 *dst, struct u64_stats_sync *syncp) @@ -134,29 +157,30 @@ static void ena_queue_stats(struct ena_adapter *adapter, u64 **data) u64 *ptr; int i, j; - for (i = 0; i < adapter->num_io_queues; i++) { + for (i = 0; i < adapter->num_io_queues + adapter->xdp_num_queues; i++) { /* Tx stats */ ring = &adapter->tx_ring[i]; for (j = 0; j < ENA_STATS_ARRAY_TX; j++) { ena_stats = &ena_stats_tx_strings[j]; - ptr = (u64 *)((uintptr_t)&ring->tx_stats + - (uintptr_t)ena_stats->stat_offset); + ptr = (u64 *)&ring->tx_stats + ena_stats->stat_offset; ena_safe_update_stat(ptr, (*data)++, &ring->syncp); } + /* XDP TX queues don't have a RX queue counterpart */ + if (!ENA_IS_XDP_INDEX(adapter, i)) { + /* Rx stats */ + ring = &adapter->rx_ring[i]; - /* Rx stats */ - ring = &adapter->rx_ring[i]; - - for (j = 0; j < ENA_STATS_ARRAY_RX; j++) { - ena_stats = &ena_stats_rx_strings[j]; + for (j = 0; j < ENA_STATS_ARRAY_RX; j++) { + ena_stats = &ena_stats_rx_strings[j]; - ptr = (u64 *)((uintptr_t)&ring->rx_stats + - (uintptr_t)ena_stats->stat_offset); + ptr = (u64 *)&ring->rx_stats + + ena_stats->stat_offset; - ena_safe_update_stat(ptr, (*data)++, &ring->syncp); + ena_safe_update_stat(ptr, (*data)++, &ring->syncp); + } } } } @@ -170,18 +194,17 @@ static void ena_dev_admin_queue_stats(struct ena_adapter *adapter, u64 **data) for (i = 0; i < ENA_STATS_ARRAY_ENA_COM; i++) { ena_stats = &ena_stats_ena_com_strings[i]; - ptr = (u64 *)((uintptr_t)&adapter->ena_dev->admin_queue.stats + - (uintptr_t)ena_stats->stat_offset); + ptr = (u64 *)&adapter->ena_dev->admin_queue.stats + + ena_stats->stat_offset; *(*data)++ = *ptr; } } -static void ena_get_ethtool_stats(struct net_device *netdev, - struct ethtool_stats *stats, - u64 *data) +static void ena_get_stats(struct ena_adapter *adapter, + u64 *data, + bool eni_stats_needed) { - struct ena_adapter *adapter = netdev_priv(netdev); const struct ena_stats *ena_stats; u64 *ptr; int i; @@ -189,16 +212,48 @@ static void ena_get_ethtool_stats(struct net_device *netdev, for (i = 0; i < ENA_STATS_ARRAY_GLOBAL; i++) { ena_stats = &ena_stats_global_strings[i]; - ptr = (u64 *)((uintptr_t)&adapter->dev_stats + - (uintptr_t)ena_stats->stat_offset); + ptr = (u64 *)&adapter->dev_stats + ena_stats->stat_offset; ena_safe_update_stat(ptr, data++, &adapter->syncp); } + if (eni_stats_needed) { + ena_update_hw_stats(adapter); + for (i = 0; i < ENA_STATS_ARRAY_ENI(adapter); i++) { + ena_stats = &ena_stats_eni_strings[i]; + + ptr = (u64 *)&adapter->eni_stats + + ena_stats->stat_offset; + + ena_safe_update_stat(ptr, data++, &adapter->syncp); + } + } + ena_queue_stats(adapter, &data); ena_dev_admin_queue_stats(adapter, &data); } +static void ena_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, + u64 *data) +{ + struct ena_adapter *adapter = netdev_priv(netdev); + + ena_get_stats(adapter, data, adapter->eni_stats_supported); +} + +static int ena_get_sw_stats_count(struct ena_adapter *adapter) +{ + return adapter->num_io_queues * (ENA_STATS_ARRAY_TX + ENA_STATS_ARRAY_RX) + + adapter->xdp_num_queues * ENA_STATS_ARRAY_TX + + ENA_STATS_ARRAY_GLOBAL + ENA_STATS_ARRAY_ENA_COM; +} + +static int ena_get_hw_stats_count(struct ena_adapter *adapter) +{ + return ENA_STATS_ARRAY_ENI(adapter); +} + int ena_get_sset_count(struct net_device *netdev, int sset) { struct ena_adapter *adapter = netdev_priv(netdev); @@ -206,31 +261,38 @@ int ena_get_sset_count(struct net_device *netdev, int sset) if (sset != ETH_SS_STATS) return -EOPNOTSUPP; - return adapter->num_io_queues * (ENA_STATS_ARRAY_TX + ENA_STATS_ARRAY_RX) - + ENA_STATS_ARRAY_GLOBAL + ENA_STATS_ARRAY_ENA_COM; + return ena_get_sw_stats_count(adapter) + ena_get_hw_stats_count(adapter); } static void ena_queue_strings(struct ena_adapter *adapter, u8 **data) { const struct ena_stats *ena_stats; + bool is_xdp; int i, j; - for (i = 0; i < adapter->num_io_queues; i++) { + for (i = 0; i < adapter->num_io_queues + adapter->xdp_num_queues; i++) { + is_xdp = ENA_IS_XDP_INDEX(adapter, i); /* Tx stats */ for (j = 0; j < ENA_STATS_ARRAY_TX; j++) { ena_stats = &ena_stats_tx_strings[j]; snprintf(*data, ETH_GSTRING_LEN, - "queue_%u_tx_%s", i, ena_stats->name); + "queue_%u_%s_%s", i, + is_xdp ? "xdp_tx" : "tx", ena_stats->name); (*data) += ETH_GSTRING_LEN; } - /* Rx stats */ - for (j = 0; j < ENA_STATS_ARRAY_RX; j++) { - ena_stats = &ena_stats_rx_strings[j]; - snprintf(*data, ETH_GSTRING_LEN, - "queue_%u_rx_%s", i, ena_stats->name); - (*data) += ETH_GSTRING_LEN; + if (!is_xdp) { + /* RX stats, in XDP there isn't a RX queue + * counterpart + */ + for (j = 0; j < ENA_STATS_ARRAY_RX; j++) { + ena_stats = &ena_stats_rx_strings[j]; + + snprintf(*data, ETH_GSTRING_LEN, + "queue_%u_rx_%s", i, ena_stats->name); + (*data) += ETH_GSTRING_LEN; + } } } } @@ -249,25 +311,43 @@ static void ena_com_dev_strings(u8 **data) } } -static void ena_get_strings(struct net_device *netdev, u32 sset, u8 *data) +static void ena_get_strings(struct ena_adapter *adapter, + u8 *data, + bool eni_stats_needed) { - struct ena_adapter *adapter = netdev_priv(netdev); const struct ena_stats *ena_stats; int i; - if (sset != ETH_SS_STATS) - return; - for (i = 0; i < ENA_STATS_ARRAY_GLOBAL; i++) { ena_stats = &ena_stats_global_strings[i]; memcpy(data, ena_stats->name, ETH_GSTRING_LEN); data += ETH_GSTRING_LEN; } + if (eni_stats_needed) { + for (i = 0; i < ENA_STATS_ARRAY_ENI(adapter); i++) { + ena_stats = &ena_stats_eni_strings[i]; + memcpy(data, ena_stats->name, ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + } + ena_queue_strings(adapter, &data); ena_com_dev_strings(&data); } +static void ena_get_ethtool_strings(struct net_device *netdev, + u32 sset, + u8 *data) +{ + struct ena_adapter *adapter = netdev_priv(netdev); + + if (sset != ETH_SS_STATS) + return; + + ena_get_strings(adapter, data, adapter->eni_stats_supported); +} + static int ena_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *link_ksettings) { @@ -847,7 +927,7 @@ static const struct ethtool_ops ena_ethtool_ops = { .get_ringparam = ena_get_ringparam, .set_ringparam = ena_set_ringparam, .get_sset_count = ena_get_sset_count, - .get_strings = ena_get_strings, + .get_strings = ena_get_ethtool_strings, .get_ethtool_stats = ena_get_ethtool_stats, .get_rxnfc = ena_get_rxnfc, .set_rxnfc = ena_set_rxnfc, @@ -875,7 +955,7 @@ static void ena_dump_stats_ex(struct ena_adapter *adapter, u8 *buf) int strings_num; int i, rc; - strings_num = ena_get_sset_count(netdev, ETH_SS_STATS); + strings_num = ena_get_sw_stats_count(adapter); if (strings_num <= 0) { netif_err(adapter, drv, netdev, "Can't get stats num\n"); return; @@ -895,13 +975,13 @@ static void ena_dump_stats_ex(struct ena_adapter *adapter, u8 *buf) GFP_ATOMIC); if (!data_buf) { netif_err(adapter, drv, netdev, - "failed to allocate data buf\n"); + "Failed to allocate data buf\n"); devm_kfree(&adapter->pdev->dev, strings_buf); return; } - ena_get_strings(netdev, ETH_SS_STATS, strings_buf); - ena_get_ethtool_stats(netdev, NULL, data_buf); + ena_get_strings(adapter, strings_buf, false); + ena_get_stats(adapter, data_buf, false); /* If there is a buffer, dump stats, otherwise print them to dmesg */ if (buf) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 2a6c9725e092..b52e8d0c7951 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -365,6 +365,7 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, { struct bpf_prog *xdp_prog; u32 verdict = XDP_PASS; + u64 *xdp_stat; rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_bpf_prog); @@ -374,17 +375,31 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, verdict = bpf_prog_run_xdp(xdp_prog, xdp); - if (verdict == XDP_TX) + if (verdict == XDP_TX) { ena_xdp_xmit_buff(rx_ring->netdev, xdp, rx_ring->qid + rx_ring->adapter->num_io_queues, rx_info); - else if (unlikely(verdict == XDP_ABORTED)) + + xdp_stat = &rx_ring->rx_stats.xdp_tx; + } else if (unlikely(verdict == XDP_ABORTED)) { trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict); - else if (unlikely(verdict > XDP_TX)) + xdp_stat = &rx_ring->rx_stats.xdp_aborted; + } else if (unlikely(verdict == XDP_DROP)) { + xdp_stat = &rx_ring->rx_stats.xdp_drop; + } else if (unlikely(verdict == XDP_PASS)) { + xdp_stat = &rx_ring->rx_stats.xdp_pass; + } else { bpf_warn_invalid_xdp_action(verdict); + xdp_stat = &rx_ring->rx_stats.xdp_invalid; + } + + u64_stats_update_begin(&rx_ring->syncp); + (*xdp_stat)++; + u64_stats_update_end(&rx_ring->syncp); out: rcu_read_unlock(); + return verdict; } @@ -2180,13 +2195,10 @@ static void ena_del_napi_in_range(struct ena_adapter *adapter, int i; for (i = first_index; i < first_index + count; i++) { - /* Check if napi was initialized before */ - if (!ENA_IS_XDP_INDEX(adapter, i) || - adapter->ena_napi[i].xdp_ring) - netif_napi_del(&adapter->ena_napi[i].napi); - else - WARN_ON(ENA_IS_XDP_INDEX(adapter, i) && - adapter->ena_napi[i].xdp_ring); + netif_napi_del(&adapter->ena_napi[i].napi); + + WARN_ON(!ENA_IS_XDP_INDEX(adapter, i) && + adapter->ena_napi[i].xdp_ring); } } @@ -3181,6 +3193,19 @@ err: ena_com_delete_debug_area(adapter->ena_dev); } +int ena_update_hw_stats(struct ena_adapter *adapter) +{ + int rc = 0; + + rc = ena_com_get_eni_stats(adapter->ena_dev, &adapter->eni_stats); + if (rc) { + dev_info_once(&adapter->pdev->dev, "Failed to get ENI stats\n"); + return rc; + } + + return 0; +} + static void ena_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { @@ -3601,16 +3626,14 @@ static void ena_fw_reset_device(struct work_struct *work) { struct ena_adapter *adapter = container_of(work, struct ena_adapter, reset_task); - struct pci_dev *pdev = adapter->pdev; - if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { - dev_err(&pdev->dev, - "device reset schedule while reset bit is off\n"); - return; - } rtnl_lock(); - ena_destroy_device(adapter, false); - ena_restore_device(adapter); + + if (likely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { + ena_destroy_device(adapter, false); + ena_restore_device(adapter); + } + rtnl_unlock(); } @@ -3692,7 +3715,7 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, } u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.missed_tx = missed_tx; + tx_ring->tx_stats.missed_tx += missed_tx; u64_stats_update_end(&tx_ring->syncp); return rc; @@ -4301,6 +4324,11 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ena_config_debug_area(adapter); + if (!ena_update_hw_stats(adapter)) + adapter->eni_stats_supported = true; + else + adapter->eni_stats_supported = false; + memcpy(adapter->netdev->perm_addr, adapter->mac_addr, netdev->addr_len); netif_carrier_off(netdev); @@ -4389,8 +4417,11 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown) netdev->rx_cpu_rmap = NULL; } #endif /* CONFIG_RFS_ACCEL */ - del_timer_sync(&adapter->timer_service); + /* Make sure timer and reset routine won't be called after + * freeing device resources. + */ + del_timer_sync(&adapter->timer_service); cancel_work_sync(&adapter->reset_task); rtnl_lock(); /* lock released inside the below if-else block */ @@ -4558,6 +4589,9 @@ static void ena_keep_alive_wd(void *adapter_data, tx_drops = ((u64)desc->tx_drops_high << 32) | desc->tx_drops_low; u64_stats_update_begin(&adapter->syncp); + /* These stats are accumulated by the device, so the counters indicate + * all drops since last reset. + */ adapter->dev_stats.rx_drops = rx_drops; adapter->dev_stats.tx_drops = tx_drops; u64_stats_update_end(&adapter->syncp); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 0c8504006247..52abb6a4f87e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -261,6 +261,11 @@ struct ena_stats_rx { u64 bad_req_id; u64 empty_rx_ring; u64 csum_unchecked; + u64 xdp_aborted; + u64 xdp_drop; + u64 xdp_pass; + u64 xdp_tx; + u64 xdp_invalid; }; struct ena_ring { @@ -405,6 +410,8 @@ struct ena_adapter { struct u64_stats_sync syncp; struct ena_stats_dev dev_stats; + struct ena_admin_eni_stats eni_stats; + bool eni_stats_supported; /* last queue index that was checked for uncompleted tx packets */ u32 last_monitored_tx_qid; @@ -422,6 +429,8 @@ void ena_dump_stats_to_dmesg(struct ena_adapter *adapter); void ena_dump_stats_to_buf(struct ena_adapter *adapter, u8 *buf); +int ena_update_hw_stats(struct ena_adapter *adapter); + int ena_update_queue_sizes(struct ena_adapter *adapter, u32 new_tx_size, u32 new_rx_size); diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index b6c43b58ed3d..960d483e8997 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1475,7 +1475,7 @@ static int amd8111e_ioctl(struct net_device *dev , struct ifreq *ifr, int cmd) case SIOCGMIIPHY: data->phy_id = lp->ext_phy_addr; - /* fallthru */ + fallthrough; case SIOCGMIIREG: spin_lock_irq(&lp->lock); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 43294a148f8a..4ba75551cb17 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1538,7 +1538,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, /* PTP v2, UDP, any kind of event packet */ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); - /* Fall through - to PTP v1, UDP, any kind of event packet */ + fallthrough; /* to PTP v1, UDP, any kind of event packet */ case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); @@ -1549,7 +1549,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, /* PTP v2, UDP, Sync packet */ case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); - /* Fall through - to PTP v1, UDP, Sync packet */ + fallthrough; /* to PTP v1, UDP, Sync packet */ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); @@ -1560,7 +1560,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, /* PTP v2, UDP, Delay_req packet */ case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); - /* Fall through - to PTP v1, UDP, Delay_req packet */ + fallthrough; /* to PTP v1, UDP, Delay_req packet */ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 46c3c1ca38d6..859ded0c06b0 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -166,6 +166,7 @@ enum xgbe_port_mode { XGBE_PORT_MODE_10GBASE_T, XGBE_PORT_MODE_10GBASE_R, XGBE_PORT_MODE_SFP, + XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG, XGBE_PORT_MODE_MAX, }; @@ -1634,6 +1635,7 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata) if (ad_reg & 0x80) { switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: mode = XGBE_MODE_KR; break; default: @@ -1643,6 +1645,7 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata) } else if (ad_reg & 0x20) { switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: mode = XGBE_MODE_KX_1000; break; case XGBE_PORT_MODE_1000BASE_X: @@ -1782,6 +1785,7 @@ static void xgbe_phy_an_advertising(struct xgbe_prv_data *pdata, switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: XGBE_SET_ADV(dlks, 10000baseKR_Full); break; case XGBE_PORT_MODE_BACKPLANE_2500: @@ -1874,6 +1878,7 @@ static enum xgbe_an_mode xgbe_phy_an_mode(struct xgbe_prv_data *pdata) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: return XGBE_AN_MODE_CL73; + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: case XGBE_PORT_MODE_BACKPLANE_2500: return XGBE_AN_MODE_NONE; case XGBE_PORT_MODE_1000BASE_T: @@ -2156,6 +2161,7 @@ static enum xgbe_mode xgbe_phy_switch_mode(struct xgbe_prv_data *pdata) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: return xgbe_phy_switch_bp_mode(pdata); case XGBE_PORT_MODE_BACKPLANE_2500: return xgbe_phy_switch_bp_2500_mode(pdata); @@ -2251,6 +2257,7 @@ static enum xgbe_mode xgbe_phy_get_mode(struct xgbe_prv_data *pdata, switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: return xgbe_phy_get_bp_mode(speed); case XGBE_PORT_MODE_BACKPLANE_2500: return xgbe_phy_get_bp_2500_mode(speed); @@ -2426,6 +2433,7 @@ static bool xgbe_phy_use_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: return xgbe_phy_use_bp_mode(pdata, mode); case XGBE_PORT_MODE_BACKPLANE_2500: return xgbe_phy_use_bp_2500_mode(pdata, mode); @@ -2515,6 +2523,7 @@ static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: return xgbe_phy_valid_speed_bp_mode(speed); case XGBE_PORT_MODE_BACKPLANE_2500: return xgbe_phy_valid_speed_bp_2500_mode(speed); @@ -2792,6 +2801,7 @@ static bool xgbe_phy_port_mode_mismatch(struct xgbe_prv_data *pdata) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000)) return false; @@ -2844,6 +2854,7 @@ static bool xgbe_phy_conn_type_mismatch(struct xgbe_prv_data *pdata) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: case XGBE_PORT_MODE_BACKPLANE_2500: if (phy_data->conn_type == XGBE_CONN_TYPE_BACKPLANE) return false; @@ -3160,6 +3171,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) /* Backplane support */ case XGBE_PORT_MODE_BACKPLANE: XGBE_SET_SUP(lks, Autoneg); + fallthrough; + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: XGBE_SET_SUP(lks, Pause); XGBE_SET_SUP(lks, Asym_Pause); XGBE_SET_SUP(lks, Backplane); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index d35a338120cf..643f5e646740 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -18,6 +18,7 @@ #include <linux/of_platform.h> #include <linux/of_net.h> #include <linux/of_mdio.h> +#include <linux/mdio/mdio-xgene.h> #include <linux/module.h> #include <net/ip.h> #include <linux/prefetch.h> @@ -26,7 +27,6 @@ #include "xgene_enet_hw.h" #include "xgene_enet_cle.h" #include "xgene_enet_ring2.h" -#include "../../../phy/mdio-xgene.h" #define ETHER_MIN_PACKET 64 #define ETHER_STD_PACKET 1518 diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 16a944707ba9..8941ac4df9e3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -1631,8 +1631,8 @@ static int hw_atl_b0_get_mac_temp(struct aq_hw_s *self, u32 *temp) hw_atl_ts_reset_set(self, 0); } - err = readx_poll_timeout_atomic(hw_atl_b0_ts_ready_and_latch_high_get, - self, val, val == 1, 10000U, 500000U); + err = readx_poll_timeout(hw_atl_b0_ts_ready_and_latch_high_get, self, + val, val == 1, 10000U, 500000U); if (err) return err; diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c index 0187dbf3b87d..54cdafdd067d 100644 --- a/drivers/net/ethernet/arc/emac_mdio.c +++ b/drivers/net/ethernet/arc/emac_mdio.c @@ -153,6 +153,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv) if (IS_ERR(data->reset_gpio)) { error = PTR_ERR(data->reset_gpio); dev_err(priv->dev, "Failed to request gpio: %d\n", error); + mdiobus_free(bus); return error; } diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index decab9a8e4a8..c7288e1fa3a2 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -826,16 +826,16 @@ static inline void atl1c_clean_buffer(struct pci_dev *pdev, return; if (buffer_info->dma) { if (buffer_info->flags & ATL1C_PCIMAP_FROMDEVICE) - pci_driection = PCI_DMA_FROMDEVICE; + pci_driection = DMA_FROM_DEVICE; else - pci_driection = PCI_DMA_TODEVICE; + pci_driection = DMA_TO_DEVICE; if (buffer_info->flags & ATL1C_PCIMAP_SINGLE) - pci_unmap_single(pdev, buffer_info->dma, - buffer_info->length, pci_driection); + dma_unmap_single(&pdev->dev, buffer_info->dma, + buffer_info->length, pci_driection); else if (buffer_info->flags & ATL1C_PCIMAP_PAGE) - pci_unmap_page(pdev, buffer_info->dma, - buffer_info->length, pci_driection); + dma_unmap_page(&pdev->dev, buffer_info->dma, + buffer_info->length, pci_driection); } if (buffer_info->skb) dev_consume_skb_any(buffer_info->skb); @@ -933,9 +933,8 @@ static void atl1c_free_ring_resources(struct atl1c_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; - pci_free_consistent(pdev, adapter->ring_header.size, - adapter->ring_header.desc, - adapter->ring_header.dma); + dma_free_coherent(&pdev->dev, adapter->ring_header.size, + adapter->ring_header.desc, adapter->ring_header.dma); adapter->ring_header.desc = NULL; /* Note: just free tdp_ring.buffer_info, @@ -1717,10 +1716,9 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter) ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); buffer_info->skb = skb; buffer_info->length = adapter->rx_buffer_len; - mapping = pci_map_single(pdev, vir_addr, - buffer_info->length, - PCI_DMA_FROMDEVICE); - if (unlikely(pci_dma_mapping_error(pdev, mapping))) { + mapping = dma_map_single(&pdev->dev, vir_addr, + buffer_info->length, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(&pdev->dev, mapping))) { dev_kfree_skb(skb); buffer_info->skb = NULL; buffer_info->length = 0; @@ -1831,8 +1829,8 @@ rrs_checked: rfd_index = (rrs->word0 >> RRS_RX_RFD_INDEX_SHIFT) & RRS_RX_RFD_INDEX_MASK; buffer_info = &rfd_ring->buffer_info[rfd_index]; - pci_unmap_single(pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_FROMDEVICE); + dma_unmap_single(&pdev->dev, buffer_info->dma, + buffer_info->length, DMA_FROM_DEVICE); skb = buffer_info->skb; } else { /* TODO */ @@ -2106,10 +2104,10 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter, buffer_info = atl1c_get_tx_buffer(adapter, use_tpd); buffer_info->length = map_len; - buffer_info->dma = pci_map_single(adapter->pdev, - skb->data, hdr_len, PCI_DMA_TODEVICE); - if (unlikely(pci_dma_mapping_error(adapter->pdev, - buffer_info->dma))) + buffer_info->dma = dma_map_single(&adapter->pdev->dev, + skb->data, hdr_len, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))) goto err_dma; ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE, @@ -2131,10 +2129,10 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter, buffer_info = atl1c_get_tx_buffer(adapter, use_tpd); buffer_info->length = buf_len - mapped_len; buffer_info->dma = - pci_map_single(adapter->pdev, skb->data + mapped_len, - buffer_info->length, PCI_DMA_TODEVICE); - if (unlikely(pci_dma_mapping_error(adapter->pdev, - buffer_info->dma))) + dma_map_single(&adapter->pdev->dev, + skb->data + mapped_len, + buffer_info->length, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))) goto err_dma; ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); @@ -2542,8 +2540,8 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) || - (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)) != 0)) { + if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || + (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 223ef846123e..fb78f6c31708 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -654,11 +654,13 @@ static void atl1e_clean_tx_ring(struct atl1e_adapter *adapter) tx_buffer = &tx_ring->tx_buffer[index]; if (tx_buffer->dma) { if (tx_buffer->flags & ATL1E_TX_PCIMAP_SINGLE) - pci_unmap_single(pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_single(&pdev->dev, tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); else if (tx_buffer->flags & ATL1E_TX_PCIMAP_PAGE) - pci_unmap_page(pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_page(&pdev->dev, tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); tx_buffer->dma = 0; } } @@ -774,8 +776,8 @@ static void atl1e_free_ring_resources(struct atl1e_adapter *adapter) atl1e_clean_rx_ring(adapter); if (adapter->ring_vir_addr) { - pci_free_consistent(pdev, adapter->ring_size, - adapter->ring_vir_addr, adapter->ring_dma); + dma_free_coherent(&pdev->dev, adapter->ring_size, + adapter->ring_vir_addr, adapter->ring_dma); adapter->ring_vir_addr = NULL; } @@ -810,11 +812,12 @@ static int atl1e_setup_ring_resources(struct atl1e_adapter *adapter) /* real ring DMA buffer */ size = adapter->ring_size; - adapter->ring_vir_addr = pci_zalloc_consistent(pdev, adapter->ring_size, - &adapter->ring_dma); + adapter->ring_vir_addr = dma_alloc_coherent(&pdev->dev, + adapter->ring_size, + &adapter->ring_dma, GFP_KERNEL); if (adapter->ring_vir_addr == NULL) { netdev_err(adapter->netdev, - "pci_alloc_consistent failed, size = D%d\n", size); + "dma_alloc_coherent failed, size = D%d\n", size); return -ENOMEM; } @@ -870,8 +873,8 @@ static int atl1e_setup_ring_resources(struct atl1e_adapter *adapter) return 0; failed: if (adapter->ring_vir_addr != NULL) { - pci_free_consistent(pdev, adapter->ring_size, - adapter->ring_vir_addr, adapter->ring_dma); + dma_free_coherent(&pdev->dev, adapter->ring_size, + adapter->ring_vir_addr, adapter->ring_dma); adapter->ring_vir_addr = NULL; } return err; @@ -1233,11 +1236,15 @@ static bool atl1e_clean_tx_irq(struct atl1e_adapter *adapter) tx_buffer = &tx_ring->tx_buffer[next_to_clean]; if (tx_buffer->dma) { if (tx_buffer->flags & ATL1E_TX_PCIMAP_SINGLE) - pci_unmap_single(adapter->pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_single(&adapter->pdev->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); else if (tx_buffer->flags & ATL1E_TX_PCIMAP_PAGE) - pci_unmap_page(adapter->pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_page(&adapter->pdev->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); tx_buffer->dma = 0; } @@ -1710,8 +1717,9 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter, tx_buffer = atl1e_get_tx_buffer(adapter, use_tpd); tx_buffer->length = map_len; - tx_buffer->dma = pci_map_single(adapter->pdev, - skb->data, hdr_len, PCI_DMA_TODEVICE); + tx_buffer->dma = dma_map_single(&adapter->pdev->dev, + skb->data, hdr_len, + DMA_TO_DEVICE); if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) return -ENOSPC; @@ -1739,8 +1747,9 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter, ((buf_len - mapped_len) >= MAX_TX_BUF_LEN) ? MAX_TX_BUF_LEN : (buf_len - mapped_len); tx_buffer->dma = - pci_map_single(adapter->pdev, skb->data + mapped_len, - map_len, PCI_DMA_TODEVICE); + dma_map_single(&adapter->pdev->dev, + skb->data + mapped_len, map_len, + DMA_TO_DEVICE); if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) { /* We need to unwind the mappings we've done */ @@ -1749,8 +1758,10 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter, while (adapter->tx_ring.next_to_use != ring_end) { tpd = atl1e_get_tpd(adapter); tx_buffer = atl1e_get_tx_buffer(adapter, tpd); - pci_unmap_single(adapter->pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_single(&adapter->pdev->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); } /* Reset the tx rings next pointer */ adapter->tx_ring.next_to_use = ring_start; @@ -2300,8 +2311,8 @@ static int atl1e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) || - (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)) != 0)) { + if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || + (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index b35fcfcd692d..60f8aa79deb2 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -1050,11 +1050,11 @@ static s32 atl1_setup_ring_resources(struct atl1_adapter *adapter) + sizeof(struct stats_msg_block) + 40; - ring_header->desc = pci_alloc_consistent(pdev, ring_header->size, - &ring_header->dma); + ring_header->desc = dma_alloc_coherent(&pdev->dev, ring_header->size, + &ring_header->dma, GFP_KERNEL); if (unlikely(!ring_header->desc)) { if (netif_msg_drv(adapter)) - dev_err(&pdev->dev, "pci_alloc_consistent failed\n"); + dev_err(&pdev->dev, "dma_alloc_coherent failed\n"); goto err_nomem; } @@ -1136,8 +1136,8 @@ static void atl1_clean_rx_ring(struct atl1_adapter *adapter) for (i = 0; i < rfd_ring->count; i++) { buffer_info = &rfd_ring->buffer_info[i]; if (buffer_info->dma) { - pci_unmap_page(pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_FROMDEVICE); + dma_unmap_page(&pdev->dev, buffer_info->dma, + buffer_info->length, DMA_FROM_DEVICE); buffer_info->dma = 0; } if (buffer_info->skb) { @@ -1175,8 +1175,8 @@ static void atl1_clean_tx_ring(struct atl1_adapter *adapter) for (i = 0; i < tpd_ring->count; i++) { buffer_info = &tpd_ring->buffer_info[i]; if (buffer_info->dma) { - pci_unmap_page(pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_TODEVICE); + dma_unmap_page(&pdev->dev, buffer_info->dma, + buffer_info->length, DMA_TO_DEVICE); buffer_info->dma = 0; } } @@ -1217,8 +1217,8 @@ static void atl1_free_ring_resources(struct atl1_adapter *adapter) atl1_clean_rx_ring(adapter); kfree(tpd_ring->buffer_info); - pci_free_consistent(pdev, ring_header->size, ring_header->desc, - ring_header->dma); + dma_free_coherent(&pdev->dev, ring_header->size, ring_header->desc, + ring_header->dma); tpd_ring->buffer_info = NULL; tpd_ring->desc = NULL; @@ -1866,9 +1866,9 @@ static u16 atl1_alloc_rx_buffers(struct atl1_adapter *adapter) buffer_info->length = (u16) adapter->rx_buffer_len; page = virt_to_page(skb->data); offset = offset_in_page(skb->data); - buffer_info->dma = pci_map_page(pdev, page, offset, + buffer_info->dma = dma_map_page(&pdev->dev, page, offset, adapter->rx_buffer_len, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma); rfd_desc->buf_len = cpu_to_le16(adapter->rx_buffer_len); rfd_desc->coalese = 0; @@ -1992,8 +1992,8 @@ rrd_ok: } /* Good Receive */ - pci_unmap_page(adapter->pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_FROMDEVICE); + dma_unmap_page(&adapter->pdev->dev, buffer_info->dma, + buffer_info->length, DMA_FROM_DEVICE); buffer_info->dma = 0; skb = buffer_info->skb; length = le16_to_cpu(rrd->xsz.xsum_sz.pkt_size); @@ -2062,8 +2062,8 @@ static int atl1_intr_tx(struct atl1_adapter *adapter) while (cmb_tpd_next_to_clean != sw_tpd_next_to_clean) { buffer_info = &tpd_ring->buffer_info[sw_tpd_next_to_clean]; if (buffer_info->dma) { - pci_unmap_page(adapter->pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_TODEVICE); + dma_unmap_page(&adapter->pdev->dev, buffer_info->dma, + buffer_info->length, DMA_TO_DEVICE); buffer_info->dma = 0; } @@ -2210,9 +2210,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, buffer_info->length = hdr_len; page = virt_to_page(skb->data); offset = offset_in_page(skb->data); - buffer_info->dma = pci_map_page(adapter->pdev, page, + buffer_info->dma = dma_map_page(&adapter->pdev->dev, page, offset, hdr_len, - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); if (++next_to_use == tpd_ring->count) next_to_use = 0; @@ -2235,9 +2235,10 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, (hdr_len + i * ATL1_MAX_TX_BUF_LEN)); offset = offset_in_page(skb->data + (hdr_len + i * ATL1_MAX_TX_BUF_LEN)); - buffer_info->dma = pci_map_page(adapter->pdev, - page, offset, buffer_info->length, - PCI_DMA_TODEVICE); + buffer_info->dma = dma_map_page(&adapter->pdev->dev, + page, offset, + buffer_info->length, + DMA_TO_DEVICE); if (++next_to_use == tpd_ring->count) next_to_use = 0; } @@ -2247,8 +2248,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, buffer_info->length = buf_len; page = virt_to_page(skb->data); offset = offset_in_page(skb->data); - buffer_info->dma = pci_map_page(adapter->pdev, page, - offset, buf_len, PCI_DMA_TODEVICE); + buffer_info->dma = dma_map_page(&adapter->pdev->dev, page, + offset, buf_len, + DMA_TO_DEVICE); if (++next_to_use == tpd_ring->count) next_to_use = 0; } @@ -2922,7 +2924,7 @@ static int atl1_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { dev_err(&pdev->dev, "no usable DMA configuration\n"); goto err_dma; diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index c915852b8892..e2526c0fb7cf 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -281,8 +281,8 @@ static s32 atl2_setup_ring_resources(struct atl2_adapter *adapter) adapter->txs_ring_size * 4 + 7 + /* dword align */ adapter->rxd_ring_size * 1536 + 127; /* 128bytes align */ - adapter->ring_vir_addr = pci_alloc_consistent(pdev, size, - &adapter->ring_dma); + adapter->ring_vir_addr = dma_alloc_coherent(&pdev->dev, size, + &adapter->ring_dma, GFP_KERNEL); if (!adapter->ring_vir_addr) return -ENOMEM; @@ -663,8 +663,8 @@ static int atl2_request_irq(struct atl2_adapter *adapter) static void atl2_free_ring_resources(struct atl2_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; - pci_free_consistent(pdev, adapter->ring_size, adapter->ring_vir_addr, - adapter->ring_dma); + dma_free_coherent(&pdev->dev, adapter->ring_size, + adapter->ring_vir_addr, adapter->ring_dma); } /** @@ -1328,8 +1328,8 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * until the kernel has the proper infrastructure to support 64-bit DMA * on these devices. */ - if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) && - pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) { + if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) && + dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32))) { printk(KERN_ERR "atl2: No usable DMA configuration, aborting\n"); err = -EIO; goto err_dma; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index dfed9ade6950..0fdd19d99d99 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -20,6 +20,7 @@ #include <linux/phy.h> #include <linux/phy_fixed.h> #include <net/dsa.h> +#include <linux/clk.h> #include <net/ip.h> #include <net/ipv6.h> @@ -186,6 +187,11 @@ static int bcm_sysport_set_features(struct net_device *dev, netdev_features_t features) { struct bcm_sysport_priv *priv = netdev_priv(dev); + int ret; + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; /* Read CRC forward */ if (!priv->is_lite) @@ -197,6 +203,8 @@ static int bcm_sysport_set_features(struct net_device *dev, bcm_sysport_set_rx_csum(dev, features); bcm_sysport_set_tx_csum(dev, features); + clk_disable_unprepare(priv->clk); + return 0; } @@ -1940,6 +1948,8 @@ static int bcm_sysport_open(struct net_device *dev) unsigned int i; int ret; + clk_prepare_enable(priv->clk); + /* Reset UniMAC */ umac_reset(priv); @@ -1970,7 +1980,8 @@ static int bcm_sysport_open(struct net_device *dev) 0, priv->phy_interface); if (!phydev) { netdev_err(dev, "could not attach to PHY\n"); - return -ENODEV; + ret = -ENODEV; + goto out_clk_disable; } /* Reset house keeping link status */ @@ -2048,6 +2059,8 @@ out_free_irq0: free_irq(priv->irq0, dev); out_phy_disconnect: phy_disconnect(phydev); +out_clk_disable: + clk_disable_unprepare(priv->clk); return ret; } @@ -2106,6 +2119,8 @@ static int bcm_sysport_stop(struct net_device *dev) /* Disconnect from PHY */ phy_disconnect(dev->phydev); + clk_disable_unprepare(priv->clk); + return 0; } @@ -2487,12 +2502,18 @@ static int bcm_sysport_probe(struct platform_device *pdev) /* Initialize private members */ priv = netdev_priv(dev); + priv->clk = devm_clk_get_optional(&pdev->dev, "sw_sysport"); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); + /* Allocate number of TX rings */ priv->tx_rings = devm_kcalloc(&pdev->dev, txq, sizeof(struct bcm_sysport_tx_ring), GFP_KERNEL); - if (!priv->tx_rings) - return -ENOMEM; + if (!priv->tx_rings) { + ret = -ENOMEM; + goto err_free_netdev; + } priv->is_lite = params->is_lite; priv->num_rx_desc_words = params->num_rx_desc_words; @@ -2564,6 +2585,10 @@ static int bcm_sysport_probe(struct platform_device *pdev) if (!ret) device_set_wakeup_capable(&pdev->dev, 1); + priv->wol_clk = devm_clk_get_optional(&pdev->dev, "sw_sysportwol"); + if (IS_ERR(priv->wol_clk)) + return PTR_ERR(priv->wol_clk); + /* Set the needed headroom once and for all */ BUILD_BUG_ON(sizeof(struct bcm_tsb) != 8); dev->needed_headroom += sizeof(struct bcm_tsb); @@ -2588,6 +2613,8 @@ static int bcm_sysport_probe(struct platform_device *pdev) goto err_deregister_notifier; } + clk_prepare_enable(priv->clk); + priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK; dev_info(&pdev->dev, "Broadcom SYSTEMPORT%s " REV_FMT @@ -2596,6 +2623,8 @@ static int bcm_sysport_probe(struct platform_device *pdev) (priv->rev >> 8) & 0xff, priv->rev & 0xff, priv->irq0, priv->irq1, txq, rxq); + clk_disable_unprepare(priv->clk); + return 0; err_deregister_notifier: @@ -2749,8 +2778,12 @@ static int __maybe_unused bcm_sysport_suspend(struct device *d) bcm_sysport_fini_rx_ring(priv); /* Get prepared for Wake-on-LAN */ - if (device_may_wakeup(d) && priv->wolopts) + if (device_may_wakeup(d) && priv->wolopts) { + clk_prepare_enable(priv->wol_clk); ret = bcm_sysport_suspend_to_wol(priv); + } + + clk_disable_unprepare(priv->clk); return ret; } @@ -2765,6 +2798,10 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) if (!netif_running(dev)) return 0; + clk_prepare_enable(priv->clk); + if (priv->wolopts) + clk_disable_unprepare(priv->wol_clk); + umac_reset(priv); /* Disable the UniMAC RX/TX */ @@ -2844,6 +2881,7 @@ out_free_rx_ring: out_free_tx_rings: for (i = 0; i < dev->num_tx_queues; i++) bcm_sysport_fini_tx_ring(priv, i); + clk_disable_unprepare(priv->clk); return ret; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 6d80735fbc7f..3a5cb6f128f5 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -770,6 +770,8 @@ struct bcm_sysport_priv { u32 wolopts; u8 sopass[SOPASS_MAX]; unsigned int wol_irq_disabled:1; + struct clk *clk; + struct clk *wol_clk; /* MIB related fields */ struct bcm_sysport_mib mib; diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 34d18302b1a3..a5fd161ab5ee 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -217,7 +217,7 @@ static int bgmac_probe(struct bcma_device *core) /* BCM 471X/535X family */ case BCMA_CHIP_ID_BCM4716: bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; - /* fallthrough */ + fallthrough; case BCMA_CHIP_ID_BCM47162: bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL2; bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 6795b6d95f54..f37f1c58f368 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -131,7 +131,7 @@ static void bgmac_nicpm_speed_set(struct net_device *net_dev) switch (bgmac->net_dev->phydev->speed) { default: netdev_err(net_dev, "Unsupported speed. Defaulting to 1000Mb\n"); - /* fall through */ + fallthrough; case SPEED_1000: val |= NICPM_IOMUX_CTRL_SPD_1000M << NICPM_IOMUX_CTRL_SPD_SHIFT; break; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index c8cc14eadbb4..3e8a179f39db 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -1337,13 +1337,13 @@ bnx2_set_mac_link(struct bnx2 *bp) val |= BNX2_EMAC_MODE_PORT_MII_10M; break; } - /* fall through */ + fallthrough; case SPEED_100: val |= BNX2_EMAC_MODE_PORT_MII; break; case SPEED_2500: val |= BNX2_EMAC_MODE_25G_MODE; - /* fall through */ + fallthrough; case SPEED_1000: val |= BNX2_EMAC_MODE_PORT_GMII; break; @@ -1995,26 +1995,26 @@ bnx2_remote_phy_event(struct bnx2 *bp) switch (speed) { case BNX2_LINK_STATUS_10HALF: bp->duplex = DUPLEX_HALF; - /* fall through */ + fallthrough; case BNX2_LINK_STATUS_10FULL: bp->line_speed = SPEED_10; break; case BNX2_LINK_STATUS_100HALF: bp->duplex = DUPLEX_HALF; - /* fall through */ + fallthrough; case BNX2_LINK_STATUS_100BASE_T4: case BNX2_LINK_STATUS_100FULL: bp->line_speed = SPEED_100; break; case BNX2_LINK_STATUS_1000HALF: bp->duplex = DUPLEX_HALF; - /* fall through */ + fallthrough; case BNX2_LINK_STATUS_1000FULL: bp->line_speed = SPEED_1000; break; case BNX2_LINK_STATUS_2500HALF: bp->duplex = DUPLEX_HALF; - /* fall through */ + fallthrough; case BNX2_LINK_STATUS_2500FULL: bp->line_speed = SPEED_2500; break; @@ -7856,7 +7856,7 @@ bnx2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIPHY: data->phy_id = bp->phy_addr; - /* fallthru */ + fallthrough; case SIOCGMIIREG: { u32 mii_regval; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index e3d92e4f2193..2c0ccd4fba9b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -4229,8 +4229,8 @@ void bnx2x_get_c2s_mapping(struct bnx2x *bp, u8 *c2s_map, u8 *c2s_default) /** * bnx2x_setup_tc - routine to configure net_device for multi tc * - * @netdev: net device to configure - * @tc: number of traffic classes to enable + * @dev: net device to configure + * @num_tc: number of traffic classes to enable * * callback connected to the ndo_setup_tc function pointer */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 7e4c93be4451..d8b1824c334d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -825,9 +825,9 @@ static inline void bnx2x_del_all_napi_cnic(struct bnx2x *bp) int i; for_each_rx_queue_cnic(bp, i) { - napi_hash_del(&bnx2x_fp(bp, i, napi)); - netif_napi_del(&bnx2x_fp(bp, i, napi)); + __netif_napi_del(&bnx2x_fp(bp, i, napi)); } + synchronize_net(); } static inline void bnx2x_del_all_napi(struct bnx2x *bp) @@ -835,9 +835,9 @@ static inline void bnx2x_del_all_napi(struct bnx2x *bp) int i; for_each_eth_queue(bp, i) { - napi_hash_del(&bnx2x_fp(bp, i, napi)); - netif_napi_del(&bnx2x_fp(bp, i, napi)); + __netif_napi_del(&bnx2x_fp(bp, i, napi)); } + synchronize_net(); } int bnx2x_set_int_mode(struct bnx2x *bp); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 1426c691c7c4..4e85e7dbc2be 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -4712,14 +4712,14 @@ static void bnx2x_sync_link(struct link_params *params, LINK_STATUS_SPEED_AND_DUPLEX_MASK) { case LINK_10THD: vars->duplex = DUPLEX_HALF; - /* Fall thru */ + fallthrough; case LINK_10TFD: vars->line_speed = SPEED_10; break; case LINK_100TXHD: vars->duplex = DUPLEX_HALF; - /* Fall thru */ + fallthrough; case LINK_100T4: case LINK_100TXFD: vars->line_speed = SPEED_100; @@ -4727,14 +4727,14 @@ static void bnx2x_sync_link(struct link_params *params, case LINK_1000THD: vars->duplex = DUPLEX_HALF; - /* Fall thru */ + fallthrough; case LINK_1000TFD: vars->line_speed = SPEED_1000; break; case LINK_2500THD: vars->duplex = DUPLEX_HALF; - /* Fall thru */ + fallthrough; case LINK_2500TFD: vars->line_speed = SPEED_2500; break; @@ -6339,7 +6339,7 @@ int bnx2x_set_led(struct link_params *params, */ if (!vars->link_up) break; - /* fall through */ + fallthrough; case LED_MODE_ON: if (((params->phy[EXT_PHY1].type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) || @@ -12508,13 +12508,13 @@ static void bnx2x_phy_def_cfg(struct link_params *params, switch (link_config & PORT_FEATURE_LINK_SPEED_MASK) { case PORT_FEATURE_LINK_SPEED_10M_HALF: phy->req_duplex = DUPLEX_HALF; - /* fall through */ + fallthrough; case PORT_FEATURE_LINK_SPEED_10M_FULL: phy->req_line_speed = SPEED_10; break; case PORT_FEATURE_LINK_SPEED_100M_HALF: phy->req_duplex = DUPLEX_HALF; - /* fall through */ + fallthrough; case PORT_FEATURE_LINK_SPEED_100M_FULL: phy->req_line_speed = SPEED_100; break; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 7f24d2689fdd..3c543dd7a8f3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -8600,11 +8600,11 @@ int bnx2x_set_int_mode(struct bnx2x *bp) bp->num_queues, 1 + bp->num_cnic_queues); - /* fall through */ + fallthrough; case BNX2X_INT_MODE_MSI: bnx2x_enable_msi(bp); - /* fall through */ + fallthrough; case BNX2X_INT_MODE_INTX: bp->num_ethernet_queues = 1; bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 80d250a6d048..e26f4da5a6d7 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -3258,7 +3258,7 @@ static int bnx2x_mcast_validate_e2(struct bnx2x *bp, /* DEL command deletes all currently configured MACs */ case BNX2X_MCAST_CMD_DEL: o->set_registry_size(o, 0); - /* fall through */ + fallthrough; /* RESTORE command will restore the entire multicast configuration */ case BNX2X_MCAST_CMD_RESTORE: @@ -3592,7 +3592,7 @@ static int bnx2x_mcast_validate_e1(struct bnx2x *bp, /* DEL command deletes all currently configured MACs */ case BNX2X_MCAST_CMD_DEL: o->set_registry_size(o, 0); - /* fall through */ + fallthrough; /* RESTORE command will restore the entire multicast configuration */ case BNX2X_MCAST_CMD_RESTORE: diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index b4476f44e386..9c2f51f23035 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1809,7 +1809,7 @@ get_vf: DP(BNX2X_MSG_IOV, "got VF [%d:%d] RSS update ramrod\n", vf->abs_vfid, qidx); bnx2x_vf_handle_rss_update_eqe(bp, vf); - /* fall through */ + fallthrough; case EVENT_RING_OPCODE_VF_FLR: /* Do nothing for now */ return 0; @@ -2207,7 +2207,7 @@ int bnx2x_vf_free(struct bnx2x *bp, struct bnx2x_virtf *vf) rc = bnx2x_vf_close(bp, vf); if (rc) goto op_err; - /* Fall through - to release resources */ + fallthrough; /* to release resources */ case VF_ACQUIRED: DP(BNX2X_MSG_IOV, "about to free resources\n"); bnx2x_vf_free_resc(bp, vf); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 31fb5a28e1c4..53f64ca673c3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1141,6 +1141,9 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay) { + if (!(test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))) + return; + if (BNXT_PF(bp)) queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay); else @@ -1157,10 +1160,12 @@ static void bnxt_queue_sp_work(struct bnxt *bp) static void bnxt_cancel_sp_work(struct bnxt *bp) { - if (BNXT_PF(bp)) + if (BNXT_PF(bp)) { flush_workqueue(bnxt_pf_wq); - else + } else { cancel_work_sync(&bp->sp_task); + cancel_delayed_work_sync(&bp->fw_reset_task); + } } static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) @@ -1923,7 +1928,7 @@ u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx) break; case BNXT_FW_HEALTH_REG_TYPE_GRC: reg_off = fw_health->mapped_regs[reg_idx]; - /* fall through */ + fallthrough; case BNXT_FW_HEALTH_REG_TYPE_BAR0: val = readl(bp->bar0 + reg_off); break; @@ -1966,11 +1971,11 @@ static int bnxt_async_event_process(struct bnxt *bp, } set_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, &bp->sp_event); } - /* fall through */ + fallthrough; case ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CHANGE: case ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE: set_bit(BNXT_LINK_CFG_CHANGE_SP_EVENT, &bp->sp_event); - /* fall through */ + fallthrough; case ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE: set_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event); break; @@ -6102,6 +6107,21 @@ static int bnxt_get_func_stat_ctxs(struct bnxt *bp) return cp + ulp_stat; } +/* Check if a default RSS map needs to be setup. This function is only + * used on older firmware that does not require reserving RX rings. + */ +static void bnxt_check_rss_tbl_no_rmgr(struct bnxt *bp) +{ + struct bnxt_hw_resc *hw_resc = &bp->hw_resc; + + /* The RSS map is valid for RX rings set to resv_rx_rings */ + if (hw_resc->resv_rx_rings != bp->rx_nr_rings) { + hw_resc->resv_rx_rings = bp->rx_nr_rings; + if (!netif_is_rxfh_configured(bp->dev)) + bnxt_set_dflt_rss_indir_tbl(bp); + } +} + static bool bnxt_need_reserve_rings(struct bnxt *bp) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; @@ -6110,22 +6130,28 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp) int rx = bp->rx_nr_rings, stat; int vnic = 1, grp = rx; - if (bp->hwrm_spec_code < 0x10601) - return false; - - if (hw_resc->resv_tx_rings != bp->tx_nr_rings) + if (hw_resc->resv_tx_rings != bp->tx_nr_rings && + bp->hwrm_spec_code >= 0x10601) return true; + /* Old firmware does not need RX ring reservations but we still + * need to setup a default RSS map when needed. With new firmware + * we go through RX ring reservations first and then set up the + * RSS map for the successfully reserved RX rings when needed. + */ + if (!BNXT_NEW_RM(bp)) { + bnxt_check_rss_tbl_no_rmgr(bp); + return false; + } if ((bp->flags & BNXT_FLAG_RFS) && !(bp->flags & BNXT_FLAG_CHIP_P5)) vnic = rx + 1; if (bp->flags & BNXT_FLAG_AGG_RINGS) rx <<= 1; stat = bnxt_get_func_stat_ctxs(bp); - if (BNXT_NEW_RM(bp) && - (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp || - hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat || - (hw_resc->resv_hw_ring_grps != grp && - !(bp->flags & BNXT_FLAG_CHIP_P5)))) + if (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp || + hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat || + (hw_resc->resv_hw_ring_grps != grp && + !(bp->flags & BNXT_FLAG_CHIP_P5))) return true; if ((bp->flags & BNXT_FLAG_CHIP_P5) && BNXT_PF(bp) && hw_resc->resv_irqs != nq) @@ -6214,6 +6240,9 @@ static int __bnxt_reserve_rings(struct bnxt *bp) if (!tx || !rx || !cp || !grp || !vnic || !stat) return -ENOMEM; + if (!netif_is_rxfh_configured(bp->dev)) + bnxt_set_dflt_rss_indir_tbl(bp); + return rc; } @@ -8495,9 +8524,6 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) rc = bnxt_init_int_mode(bp); bnxt_ulp_irq_restart(bp, rc); } - if (!netif_is_rxfh_configured(bp->dev)) - bnxt_set_dflt_rss_indir_tbl(bp); - if (rc) { netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc); return rc; @@ -8608,10 +8634,9 @@ static void bnxt_del_napi(struct bnxt *bp) for (i = 0; i < bp->cp_nr_rings; i++) { struct bnxt_napi *bnapi = bp->bnapi[i]; - napi_hash_del(&bnapi->napi); - netif_napi_del(&bnapi->napi); + __netif_napi_del(&bnapi->napi); } - /* We called napi_hash_del() before netif_napi_del(), we need + /* We called __netif_napi_del(), we need * to respect an RCU grace period before freeing napi structures. */ synchronize_net(); @@ -9284,16 +9309,19 @@ static ssize_t bnxt_show_temp(struct device *dev, struct hwrm_temp_monitor_query_input req = {0}; struct hwrm_temp_monitor_query_output *resp; struct bnxt *bp = dev_get_drvdata(dev); - u32 temp = 0; + u32 len = 0; resp = bp->hwrm_cmd_resp_addr; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); - if (!_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) - temp = resp->temp * 1000; /* display millidegree */ + if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) + len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */ mutex_unlock(&bp->hwrm_cmd_lock); - return sprintf(buf, "%u\n", temp); + if (len) + return len; + + return sprintf(buf, "unknown\n"); } static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0); @@ -9475,15 +9503,15 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) } } - bnxt_enable_napi(bp); - bnxt_debug_dev_init(bp); - rc = bnxt_init_nic(bp, irq_re_init); if (rc) { netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); - goto open_err; + goto open_err_irq; } + bnxt_enable_napi(bp); + bnxt_debug_dev_init(bp); + if (link_re_init) { mutex_lock(&bp->link_lock); rc = bnxt_update_phy_setting(bp); @@ -9514,10 +9542,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) bnxt_vf_reps_open(bp); return 0; -open_err: - bnxt_debug_dev_exit(bp); - bnxt_disable_napi(bp); - open_err_irq: bnxt_del_napi(bp); @@ -9765,7 +9789,7 @@ static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIPHY: mdio->phy_id = bp->link_info.phy_addr; - /* fallthru */ + fallthrough; case SIOCGMIIREG: { u16 mii_regval = 0; @@ -11022,7 +11046,7 @@ static void bnxt_fw_reset_writel(struct bnxt *bp, int reg_idx) writel(reg_off & BNXT_GRC_BASE_MASK, bp->bar0 + BNXT_GRCPF_REG_WINDOW_BASE_OUT + 4); reg_off = (reg_off & BNXT_GRC_OFFSET_MASK) + 0x2000; - /* fall through */ + fallthrough; case BNXT_FW_HEALTH_REG_TYPE_BAR0: writel(val, bp->bar0 + reg_off); break; @@ -11135,7 +11159,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) } bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW; } - /* fall through */ + fallthrough; case BNXT_FW_RESET_STATE_RESET_FW: bnxt_reset_all(bp); bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV; @@ -11158,7 +11182,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) } pci_set_master(bp->pdev); bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW; - /* fall through */ + fallthrough; case BNXT_FW_RESET_STATE_POLL_FW: bp->hwrm_cmd_timeout = SHORT_HWRM_CMD_TIMEOUT; rc = __bnxt_hwrm_ver_get(bp, true); @@ -11173,7 +11197,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) } bp->hwrm_cmd_timeout = DFLT_HWRM_CMD_TIMEOUT; bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING; - /* fall through */ + fallthrough; case BNXT_FW_RESET_STATE_OPENING: while (!rtnl_trylock()) { bnxt_queue_fw_reset_work(bp, HZ / 10); @@ -11761,6 +11785,7 @@ static void bnxt_remove_one(struct pci_dev *pdev) unregister_netdev(dev); bnxt_dl_unregister(bp); bnxt_shutdown_tc(bp); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); bnxt_cancel_sp_work(bp); bp->sp_event = 0; @@ -12200,6 +12225,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (BNXT_CHIP_P5(bp)) bp->flags |= BNXT_FLAG_CHIP_P5; + rc = bnxt_alloc_rss_indir_tbl(bp); + if (rc) + goto init_err_pci_clean; + rc = bnxt_fw_init_one_p2(bp); if (rc) goto init_err_pci_clean; @@ -12304,11 +12333,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ bp->tx_nr_rings_per_tc = bp->tx_nr_rings; - rc = bnxt_alloc_rss_indir_tbl(bp); - if (rc) - goto init_err_pci_clean; - bnxt_set_dflt_rss_indir_tbl(bp); - if (BNXT_PF(bp)) { if (!bnxt_pf_wq) { bnxt_pf_wq = @@ -12339,6 +12363,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) (long)pci_resource_start(pdev, 0), dev->dev_addr); pcie_print_link_status(pdev); + pci_save_state(pdev); return 0; init_err_cleanup: @@ -12536,6 +12561,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) "Cannot re-enable PCI device after reset.\n"); } else { pci_set_master(pdev); + pci_restore_state(pdev); + pci_save_state(pdev); err = bnxt_hwrm_func_reset(bp); if (!err) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 64da654f1038..d0928334bdc8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -472,20 +472,13 @@ static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp) static int bnxt_get_num_ring_stats(struct bnxt *bp) { int rx, tx, cmn; - bool sh = false; - - if (bp->flags & BNXT_FLAG_SHARED_RINGS) - sh = true; rx = NUM_RING_RX_HW_STATS + NUM_RING_RX_SW_STATS + bnxt_get_num_tpa_ring_stats(bp); tx = NUM_RING_TX_HW_STATS; cmn = NUM_RING_CMN_SW_STATS; - if (sh) - return (rx + tx + cmn) * bp->cp_nr_rings; - else - return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings + - cmn * bp->cp_nr_rings; + return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings + + cmn * bp->cp_nr_rings; } static int bnxt_get_num_stats(struct bnxt *bp) @@ -806,7 +799,7 @@ static void bnxt_get_channels(struct net_device *dev, int max_tx_sch_inputs; /* Get the most up-to-date max_tx_sch_inputs. */ - if (BNXT_NEW_RM(bp)) + if (netif_running(dev) && BNXT_NEW_RM(bp)) bnxt_hwrm_func_resc_qcaps(bp, false); max_tx_sch_inputs = hw_resc->max_tx_sch_inputs; @@ -1073,7 +1066,7 @@ static int bnxt_grxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd) if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4) cmd->data |= RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; - /* fall through */ + fallthrough; case SCTP_V4_FLOW: case AH_ESP_V4_FLOW: case AH_V4_FLOW: @@ -1092,7 +1085,7 @@ static int bnxt_grxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd) if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6) cmd->data |= RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; - /* fall through */ + fallthrough; case SCTP_V6_FLOW: case AH_ESP_V6_FLOW: case AH_V6_FLOW: @@ -2323,6 +2316,9 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data) if (rc != 0) return rc; + if (!dir_entries || !entry_length) + return -EIO; + /* Insert 2 bytes of directory info (count and size of entries) */ if (len < 2) return -EINVAL; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 2704a4709bc7..fcc262064766 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -201,10 +201,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, break; default: bpf_warn_invalid_xdp_action(act); - /* Fall thru */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(bp->dev, xdp_prog, act); - /* Fall thru */ + fallthrough; case XDP_DROP: bnxt_reuse_rx_data(rxr, cons, page); break; diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index c5cca63b8571..84536292b031 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -3311,7 +3311,7 @@ static int cnic_ctl(void *data, struct cnic_ctl_info *info) } case CNIC_CTL_FCOE_STATS_GET_CMD: ulp_type = CNIC_ULP_FCOE; - /* fall through */ + fallthrough; case CNIC_CTL_ISCSI_STATS_GET_CMD: cnic_hold(dev); cnic_copy_ulp_stats(dev, ulp_type); @@ -4044,7 +4044,7 @@ static void cnic_cm_process_kcqe(struct cnic_dev *dev, struct kcqe *kcqe) l4kcqe->status, l5kcqe->completion_status); opcode = L4_KCQE_OPCODE_VALUE_CLOSE_COMP; } - /* Fall through */ + fallthrough; case L4_KCQE_OPCODE_VALUE_RESET_RECEIVED: case L4_KCQE_OPCODE_VALUE_CLOSE_COMP: case L4_KCQE_OPCODE_VALUE_RESET_COMP: diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 1fecc25767bd..be85dad2e3bc 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1185,10 +1185,10 @@ static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv) continue; case BCMGENET_STAT_RUNT: offset += BCMGENET_STAT_OFFSET; - /* fall through */ + fallthrough; case BCMGENET_STAT_MIB_TX: offset += BCMGENET_STAT_OFFSET; - /* fall through */ + fallthrough; case BCMGENET_STAT_MIB_RX: val = bcmgenet_umac_readl(priv, UMAC_MIB_START + j + offset); @@ -1364,7 +1364,7 @@ static int bcmgenet_validate_flow(struct net_device *dev, case ETHER_FLOW: eth_mask = &cmd->fs.m_u.ether_spec; /* don't allow mask which isn't valid */ - if (VALIDATE_MASK(eth_mask->h_source) || + if (VALIDATE_MASK(eth_mask->h_dest) || VALIDATE_MASK(eth_mask->h_source) || VALIDATE_MASK(eth_mask->h_proto)) { netdev_err(dev, "rxnfc: Unsupported mask\n"); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 511d553a4d11..6fb6c3556285 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -192,7 +192,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) switch (priv->phy_interface) { case PHY_INTERFACE_MODE_INTERNAL: phy_name = "internal PHY"; - /* fall through */ + fallthrough; case PHY_INTERFACE_MODE_MOCA: /* Irrespective of the actually configured PHY speed (100 or * 1000) GENETv4 only has an internal GPHY so we will just end diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index ebff1fc0d8ce..5143cdd0eeca 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -715,7 +715,7 @@ static int tg3_ape_lock(struct tg3 *tp, int locknum) case TG3_APE_LOCK_GPIO: if (tg3_asic_rev(tp) == ASIC_REV_5761) return 0; - /* fall through */ + fallthrough; case TG3_APE_LOCK_GRC: case TG3_APE_LOCK_MEM: if (!tp->pci_fn) @@ -776,7 +776,7 @@ static void tg3_ape_unlock(struct tg3 *tp, int locknum) case TG3_APE_LOCK_GPIO: if (tg3_asic_rev(tp) == ASIC_REV_5761) return; - /* fall through */ + fallthrough; case TG3_APE_LOCK_GRC: case TG3_APE_LOCK_MEM: if (!tp->pci_fn) @@ -1586,7 +1586,7 @@ static int tg3_mdio_init(struct tg3 *tp) phydev->dev_flags |= PHY_BRCM_EXT_IBND_RX_ENABLE; if (tg3_flag(tp, RGMII_EXT_IBND_TX_EN)) phydev->dev_flags |= PHY_BRCM_EXT_IBND_TX_ENABLE; - /* fall through */ + fallthrough; case PHY_ID_RTL8211C: phydev->interface = PHY_INTERFACE_MODE_RGMII; break; @@ -2114,7 +2114,7 @@ static int tg3_phy_init(struct tg3 *tp) phy_support_asym_pause(phydev); break; } - /* fall through */ + fallthrough; case PHY_INTERFACE_MODE_MII: phy_set_max_speed(phydev, SPEED_100); phy_support_asym_pause(phydev); @@ -4390,7 +4390,7 @@ static int tg3_phy_autoneg_cfg(struct tg3 *tp, u32 advertise, u32 flowctrl) MII_TG3_DSP_TAP26_RMRXSTO | MII_TG3_DSP_TAP26_OPCSINPT; tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, val); - /* Fall through */ + fallthrough; case ASIC_REV_5720: case ASIC_REV_5762: if (!tg3_phydsp_read(tp, MII_TG3_DSP_CH34TP2, &val)) @@ -4538,7 +4538,7 @@ static int tg3_phy_pull_config(struct tg3 *tp) tp->link_config.speed = SPEED_1000; break; } - /* Fall through */ + fallthrough; default: goto done; } @@ -5209,7 +5209,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp, if (ap->flags & (MR_AN_ENABLE | MR_RESTART_AN)) ap->state = ANEG_STATE_AN_ENABLE; - /* fall through */ + fallthrough; case ANEG_STATE_AN_ENABLE: ap->flags &= ~(MR_AN_COMPLETE | MR_PAGE_RX); if (ap->flags & MR_AN_ENABLE) { @@ -5239,7 +5239,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp, ret = ANEG_TIMER_ENAB; ap->state = ANEG_STATE_RESTART; - /* fall through */ + fallthrough; case ANEG_STATE_RESTART: delta = ap->cur_time - ap->link_time; if (delta > ANEG_STATE_SETTLE_TIME) @@ -5282,7 +5282,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp, ap->state = ANEG_STATE_ACK_DETECT; - /* fall through */ + fallthrough; case ANEG_STATE_ACK_DETECT: if (ap->ack_match != 0) { if ((ap->rxconfig & ~ANEG_CFG_ACK) == @@ -7221,8 +7221,8 @@ static inline void tg3_reset_task_schedule(struct tg3 *tp) static inline void tg3_reset_task_cancel(struct tg3 *tp) { - cancel_work_sync(&tp->reset_task); - tg3_flag_clear(tp, RESET_TASK_PENDING); + if (test_and_clear_bit(TG3_FLAG_RESET_TASK_PENDING, tp->tg3_flags)) + cancel_work_sync(&tp->reset_task); tg3_flag_clear(tp, TX_RECOVERY_PENDING); } @@ -10720,40 +10720,40 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy) switch (limit) { case 16: tw32(MAC_RCV_RULE_15, 0); tw32(MAC_RCV_VALUE_15, 0); - /* fall through */ + fallthrough; case 15: tw32(MAC_RCV_RULE_14, 0); tw32(MAC_RCV_VALUE_14, 0); - /* fall through */ + fallthrough; case 14: tw32(MAC_RCV_RULE_13, 0); tw32(MAC_RCV_VALUE_13, 0); - /* fall through */ + fallthrough; case 13: tw32(MAC_RCV_RULE_12, 0); tw32(MAC_RCV_VALUE_12, 0); - /* fall through */ + fallthrough; case 12: tw32(MAC_RCV_RULE_11, 0); tw32(MAC_RCV_VALUE_11, 0); - /* fall through */ + fallthrough; case 11: tw32(MAC_RCV_RULE_10, 0); tw32(MAC_RCV_VALUE_10, 0); - /* fall through */ + fallthrough; case 10: tw32(MAC_RCV_RULE_9, 0); tw32(MAC_RCV_VALUE_9, 0); - /* fall through */ + fallthrough; case 9: tw32(MAC_RCV_RULE_8, 0); tw32(MAC_RCV_VALUE_8, 0); - /* fall through */ + fallthrough; case 8: tw32(MAC_RCV_RULE_7, 0); tw32(MAC_RCV_VALUE_7, 0); - /* fall through */ + fallthrough; case 7: tw32(MAC_RCV_RULE_6, 0); tw32(MAC_RCV_VALUE_6, 0); - /* fall through */ + fallthrough; case 6: tw32(MAC_RCV_RULE_5, 0); tw32(MAC_RCV_VALUE_5, 0); - /* fall through */ + fallthrough; case 5: tw32(MAC_RCV_RULE_4, 0); tw32(MAC_RCV_VALUE_4, 0); - /* fall through */ + fallthrough; case 4: /* tw32(MAC_RCV_RULE_3, 0); tw32(MAC_RCV_VALUE_3, 0); */ case 3: @@ -11209,18 +11209,27 @@ static void tg3_reset_task(struct work_struct *work) tg3_halt(tp, RESET_KIND_SHUTDOWN, 0); err = tg3_init_hw(tp, true); - if (err) + if (err) { + tg3_full_unlock(tp); + tp->irq_sync = 0; + tg3_napi_enable(tp); + /* Clear this flag so that tg3_reset_task_cancel() will not + * call cancel_work_sync() and wait forever. + */ + tg3_flag_clear(tp, RESET_TASK_PENDING); + dev_close(tp->dev); goto out; + } tg3_netif_start(tp); -out: tg3_full_unlock(tp); if (!err) tg3_phy_start(tp); tg3_flag_clear(tp, RESET_TASK_PENDING); +out: rtnl_unlock(); } @@ -13998,7 +14007,7 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIPHY: data->phy_id = tp->phy_addr; - /* fall through */ + fallthrough; case SIOCGMIIREG: { u32 mii_regval; @@ -17136,7 +17145,7 @@ static u32 tg3_calc_dma_bndry(struct tg3 *tp, u32 val) val |= DMA_RWCTRL_WRITE_BNDRY_64_PCIE; break; } - /* fallthrough */ + fallthrough; case 128: default: val &= ~DMA_RWCTRL_WRITE_BNDRY_DISAB_PCIE; @@ -17151,28 +17160,28 @@ static u32 tg3_calc_dma_bndry(struct tg3 *tp, u32 val) DMA_RWCTRL_WRITE_BNDRY_16); break; } - /* fallthrough */ + fallthrough; case 32: if (goal == BOUNDARY_SINGLE_CACHELINE) { val |= (DMA_RWCTRL_READ_BNDRY_32 | DMA_RWCTRL_WRITE_BNDRY_32); break; } - /* fallthrough */ + fallthrough; case 64: if (goal == BOUNDARY_SINGLE_CACHELINE) { val |= (DMA_RWCTRL_READ_BNDRY_64 | DMA_RWCTRL_WRITE_BNDRY_64); break; } - /* fallthrough */ + fallthrough; case 128: if (goal == BOUNDARY_SINGLE_CACHELINE) { val |= (DMA_RWCTRL_READ_BNDRY_128 | DMA_RWCTRL_WRITE_BNDRY_128); break; } - /* fallthrough */ + fallthrough; case 256: val |= (DMA_RWCTRL_READ_BNDRY_256 | DMA_RWCTRL_WRITE_BNDRY_256); diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c index 49358d42a0e2..b9dd06b12945 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c +++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c @@ -321,7 +321,7 @@ bfa_ioc_sm_getattr(struct bfa_ioc *ioc, enum ioc_event event) case IOC_E_PFFAILED: case IOC_E_HWERROR: del_timer(&ioc->ioc_timer); - /* fall through */ + fallthrough; case IOC_E_TIMEOUT: ioc->cbfn->enable_cbfn(ioc->bfa, BFA_STATUS_IOC_FAILURE); bfa_fsm_set_state(ioc, bfa_ioc_sm_fail); @@ -780,7 +780,7 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf *iocpf, enum iocpf_event event) case IOCPF_E_INITFAIL: del_timer(&ioc->iocpf_timer); - /* fall through */ + fallthrough; case IOCPF_E_TIMEOUT: bfa_nw_ioc_hw_sem_release(ioc); @@ -849,7 +849,7 @@ bfa_iocpf_sm_disabling(struct bfa_iocpf *iocpf, enum iocpf_event event) case IOCPF_E_FAIL: del_timer(&ioc->iocpf_timer); - /* fall through*/ + fallthrough; case IOCPF_E_TIMEOUT: bfa_ioc_set_cur_ioc_fwstate(ioc, BFI_IOC_FAIL); diff --git a/drivers/net/ethernet/brocade/bna/bna_enet.c b/drivers/net/ethernet/brocade/bna/bna_enet.c index 40107a9bd120..a2c983f56b00 100644 --- a/drivers/net/ethernet/brocade/bna/bna_enet.c +++ b/drivers/net/ethernet/brocade/bna/bna_enet.c @@ -1084,7 +1084,7 @@ bna_enet_sm_cfg_wait(struct bna_enet *enet, case ENET_E_CHLD_STOPPED: bna_enet_rx_start(enet); - /* Fall through */ + fallthrough; case ENET_E_FWRESP_PAUSE: if (enet->flags & BNA_ENET_F_PAUSE_CHANGED) { enet->flags &= ~BNA_ENET_F_PAUSE_CHANGED; diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c index b5ecbfe13ab0..2623a0da4682 100644 --- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c +++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c @@ -1636,7 +1636,7 @@ bna_bfi_rx_enet_start(struct bna_rx *rx) &q1->qpt); cfg_req->q_cfg[i].qs.rx_buffer_size = htons((u16)q1->buffer_size); - /* Fall through */ + fallthrough; case BNA_RXP_SINGLE: /* Large/Single RxQ */ diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 31ebf3ee7ec0..283918aeb741 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -460,7 +460,7 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd) case HWTSTAMP_TX_ONESTEP_SYNC: if (gem_ptp_set_one_step_sync(bp, 1) != 0) return -ERANGE; - /* fall through */ + fallthrough; case HWTSTAMP_TX_ON: tx_bd_control = TSTAMP_ALL_FRAMES; break; diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.c b/drivers/net/ethernet/cavium/common/cavium_ptp.c index 81ff9ac73f9a..9fd717b9cf69 100644 --- a/drivers/net/ethernet/cavium/common/cavium_ptp.c +++ b/drivers/net/ethernet/cavium/common/cavium_ptp.c @@ -86,7 +86,7 @@ EXPORT_SYMBOL(cavium_ptp_put); /** * cavium_ptp_adjfine() - Adjust ptp frequency - * @ptp: PTP clock info + * @ptp_info: PTP clock info * @scaled_ppm: how much to adjust by, in parts per million, but with a * 16 bit binary fractional field */ @@ -134,7 +134,7 @@ static int cavium_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm) /** * cavium_ptp_adjtime() - Adjust ptp time - * @ptp: PTP clock info + * @ptp_info: PTP clock info * @delta: how much to adjust by, in nanosecs */ static int cavium_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) @@ -155,7 +155,7 @@ static int cavium_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) /** * cavium_ptp_gettime() - Get hardware clock time with adjustment - * @ptp: PTP clock info + * @ptp_info: PTP clock info * @ts: timespec */ static int cavium_ptp_gettime(struct ptp_clock_info *ptp_info, @@ -177,7 +177,7 @@ static int cavium_ptp_gettime(struct ptp_clock_info *ptp_info, /** * cavium_ptp_settime() - Set hardware clock time. Reset adjustment - * @ptp: PTP clock info + * @ptp_info: PTP clock info * @ts: timespec */ static int cavium_ptp_settime(struct ptp_clock_info *ptp_info, @@ -199,7 +199,7 @@ static int cavium_ptp_settime(struct ptp_clock_info *ptp_info, /** * cavium_ptp_enable() - Request to enable or disable an ancillary feature. - * @ptp: PTP clock info + * @ptp_info: PTP clock info * @rq: request * @on: is it on */ diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index e73bc211779a..8e0ed01e7f03 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -977,15 +977,14 @@ static void octeon_destroy_resources(struct octeon_device *oct) schedule_timeout_uninterruptible(HZ / 10); - /* fallthrough */ + fallthrough; case OCT_DEV_HOST_OK: - /* fallthrough */ case OCT_DEV_CONSOLE_INIT_DONE: /* Remove any consoles */ octeon_remove_consoles(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_IO_QUEUES_DONE: if (lio_wait_for_instr_fetch(oct)) dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n"); @@ -1027,7 +1026,7 @@ static void octeon_destroy_resources(struct octeon_device *oct) octeon_free_sc_done_list(oct); octeon_free_sc_zombie_list(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_INTR_SET_DONE: /* Disable interrupts */ oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR); @@ -1062,17 +1061,17 @@ static void octeon_destroy_resources(struct octeon_device *oct) kfree(oct->irq_name_storage); oct->irq_name_storage = NULL; - /* fallthrough */ + fallthrough; case OCT_DEV_MSIX_ALLOC_VECTOR_DONE: if (OCTEON_CN23XX_PF(oct)) octeon_free_ioq_vector(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_MBOX_SETUP_DONE: if (OCTEON_CN23XX_PF(oct)) oct->fn_list.free_mbox(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_IN_RESET: case OCT_DEV_DROQ_INIT_DONE: /* Wait for any pending operations */ @@ -1095,11 +1094,11 @@ static void octeon_destroy_resources(struct octeon_device *oct) } } - /* fallthrough */ + fallthrough; case OCT_DEV_RESP_LIST_INIT_DONE: octeon_delete_response_list(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_INSTR_QUEUE_INIT_DONE: for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) { if (!(oct->io_qmask.iq & BIT_ULL(i))) @@ -1110,16 +1109,16 @@ static void octeon_destroy_resources(struct octeon_device *oct) if (oct->sriov_info.sriov_enabled) pci_disable_sriov(oct->pci_dev); #endif - /* fallthrough */ + fallthrough; case OCT_DEV_SC_BUFF_POOL_INIT_DONE: octeon_free_sc_buffer_pool(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_DISPATCH_INIT_DONE: octeon_delete_dispatch_list(oct); cancel_delayed_work_sync(&oct->nic_poll_work.work); - /* fallthrough */ + fallthrough; case OCT_DEV_PCI_MAP_DONE: refcount = octeon_deregister_device(oct); @@ -1137,13 +1136,13 @@ static void octeon_destroy_resources(struct octeon_device *oct) octeon_unmap_pci_barx(oct, 0); octeon_unmap_pci_barx(oct, 1); - /* fallthrough */ + fallthrough; case OCT_DEV_PCI_ENABLE_DONE: pci_clear_master(oct->pci_dev); /* Disable the device, releasing the PCI INT */ pci_disable_device(oct->pci_dev); - /* fallthrough */ + fallthrough; case OCT_DEV_BEGIN_STATE: /* Nothing to be done here either */ break; @@ -2168,7 +2167,7 @@ static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) case SIOCSHWTSTAMP: if (lio->oct_dev->ptp_enable) return hwtstamp_ioctl(netdev, ifr); - /* fall through */ + fallthrough; default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 90ef21086f27..8c5879e31240 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -460,9 +460,8 @@ static void octeon_destroy_resources(struct octeon_device *oct) schedule_timeout_uninterruptible(HZ / 10); - /* fallthrough */ + fallthrough; case OCT_DEV_HOST_OK: - /* fallthrough */ case OCT_DEV_IO_QUEUES_DONE: if (lio_wait_for_instr_fetch(oct)) dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n"); @@ -504,7 +503,7 @@ static void octeon_destroy_resources(struct octeon_device *oct) octeon_free_sc_done_list(oct); octeon_free_sc_zombie_list(oct); - /* fall through */ + fallthrough; case OCT_DEV_INTR_SET_DONE: /* Disable interrupts */ oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR); @@ -533,15 +532,15 @@ static void octeon_destroy_resources(struct octeon_device *oct) else cn23xx_vf_ask_pf_to_do_flr(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_MSIX_ALLOC_VECTOR_DONE: octeon_free_ioq_vector(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_MBOX_SETUP_DONE: oct->fn_list.free_mbox(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_IN_RESET: case OCT_DEV_DROQ_INIT_DONE: mdelay(100); @@ -551,11 +550,11 @@ static void octeon_destroy_resources(struct octeon_device *oct) octeon_delete_droq(oct, i); } - /* fallthrough */ + fallthrough; case OCT_DEV_RESP_LIST_INIT_DONE: octeon_delete_response_list(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_INSTR_QUEUE_INIT_DONE: for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) { if (!(oct->io_qmask.iq & BIT_ULL(i))) @@ -563,27 +562,27 @@ static void octeon_destroy_resources(struct octeon_device *oct) octeon_delete_instr_queue(oct, i); } - /* fallthrough */ + fallthrough; case OCT_DEV_SC_BUFF_POOL_INIT_DONE: octeon_free_sc_buffer_pool(oct); - /* fallthrough */ + fallthrough; case OCT_DEV_DISPATCH_INIT_DONE: octeon_delete_dispatch_list(oct); cancel_delayed_work_sync(&oct->nic_poll_work.work); - /* fallthrough */ + fallthrough; case OCT_DEV_PCI_MAP_DONE: octeon_unmap_pci_barx(oct, 0); octeon_unmap_pci_barx(oct, 1); - /* fallthrough */ + fallthrough; case OCT_DEV_PCI_ENABLE_DONE: pci_clear_master(oct->pci_dev); /* Disable the device, releasing the PCI INT */ pci_disable_device(oct->pci_dev); - /* fallthrough */ + fallthrough; case OCT_DEV_BEGIN_STATE: /* Nothing to be done here either */ break; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index 017169023cca..cf4fe5b17f8a 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -280,13 +280,10 @@ int octeon_init_droq(struct octeon_device *oct, dev_dbg(&oct->pci_dev->dev, "droq[%d]: num_desc: %d\n", q_no, droq->max_count); - droq->recv_buf_list = (struct octeon_recv_buffer *) - vzalloc_node(array_size(droq->max_count, OCT_DROQ_RECVBUF_SIZE), - numa_node); + droq->recv_buf_list = vzalloc_node(array_size(droq->max_count, OCT_DROQ_RECVBUF_SIZE), + numa_node); if (!droq->recv_buf_list) - droq->recv_buf_list = (struct octeon_recv_buffer *) - vzalloc(array_size(droq->max_count, - OCT_DROQ_RECVBUF_SIZE)); + droq->recv_buf_list = vzalloc(array_size(droq->max_count, OCT_DROQ_RECVBUF_SIZE)); if (!droq->recv_buf_list) { dev_err(&oct->pci_dev->dev, "Output queue recv buf list alloc failed\n"); goto init_droq_fail; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index 83dabcffc789..c7bdac79299a 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -522,7 +522,7 @@ static int nicvf_get_rss_hash_opts(struct nicvf *nic, case SCTP_V4_FLOW: case SCTP_V6_FLOW: info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - /* Fall through */ + fallthrough; case IPV4_FLOW: case IPV6_FLOW: info->data |= RXH_IP_SRC | RXH_IP_DST; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index c1378b5c780c..063e560d9c1b 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -594,10 +594,10 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, return true; default: bpf_warn_invalid_xdp_action(action); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(nic->netdev, prog, action); - /* fall through */ + fallthrough; case XDP_DROP: /* Check if it's a recycled page, if not * unmap the DMA mapping. diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig index f6f3ef9a93cf..87cc0ef68b31 100644 --- a/drivers/net/ethernet/chelsio/Kconfig +++ b/drivers/net/ethernet/chelsio/Kconfig @@ -134,4 +134,6 @@ config CHELSIO_LIB help Common library for Chelsio drivers. +source "drivers/net/ethernet/chelsio/inline_crypto/Kconfig" + endif # NET_VENDOR_CHELSIO diff --git a/drivers/net/ethernet/chelsio/Makefile b/drivers/net/ethernet/chelsio/Makefile index c0f978d2e8a7..1a6fd8b2bb7d 100644 --- a/drivers/net/ethernet/chelsio/Makefile +++ b/drivers/net/ethernet/chelsio/Makefile @@ -8,3 +8,4 @@ obj-$(CONFIG_CHELSIO_T3) += cxgb3/ obj-$(CONFIG_CHELSIO_T4) += cxgb4/ obj-$(CONFIG_CHELSIO_T4VF) += cxgb4vf/ obj-$(CONFIG_CHELSIO_LIB) += libcxgb/ +obj-$(CONFIG_CHELSIO_INLINE_CRYPTO) += inline_crypto/ diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c index 99736796e1a0..0e4a0f413960 100644 --- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c +++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c @@ -997,17 +997,17 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_disable_pdev; } - if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) { pci_using_dac = 1; - if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) { - pr_err("%s: unable to obtain 64-bit DMA for " - "consistent allocations\n", pci_name(pdev)); + if (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + pr_err("%s: unable to obtain 64-bit DMA for coherent allocations\n", + pci_name(pdev)); err = -ENODEV; goto out_disable_pdev; } - } else if ((err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) != 0) { + } else if ((err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) != 0) { pr_err("%s: no usable DMA configuration\n", pci_name(pdev)); goto out_disable_pdev; } diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c index 47b5c8e2104b..21016de20b2d 100644 --- a/drivers/net/ethernet/chelsio/cxgb/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb/sge.c @@ -509,9 +509,8 @@ static void free_freelQ_buffers(struct pci_dev *pdev, struct freelQ *q) while (q->credits--) { struct freelQ_ce *ce = &q->centries[cidx]; - pci_unmap_single(pdev, dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), - PCI_DMA_FROMDEVICE); + dma_unmap_single(&pdev->dev, dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), DMA_FROM_DEVICE); dev_kfree_skb(ce->skb); ce->skb = NULL; if (++cidx == q->size) @@ -529,8 +528,8 @@ static void free_rx_resources(struct sge *sge) if (sge->respQ.entries) { size = sizeof(struct respQ_e) * sge->respQ.size; - pci_free_consistent(pdev, size, sge->respQ.entries, - sge->respQ.dma_addr); + dma_free_coherent(&pdev->dev, size, sge->respQ.entries, + sge->respQ.dma_addr); } for (i = 0; i < SGE_FREELQ_N; i++) { @@ -542,8 +541,8 @@ static void free_rx_resources(struct sge *sge) } if (q->entries) { size = sizeof(struct freelQ_e) * q->size; - pci_free_consistent(pdev, size, q->entries, - q->dma_addr); + dma_free_coherent(&pdev->dev, size, q->entries, + q->dma_addr); } } } @@ -564,7 +563,8 @@ static int alloc_rx_resources(struct sge *sge, struct sge_params *p) q->size = p->freelQ_size[i]; q->dma_offset = sge->rx_pkt_pad ? 0 : NET_IP_ALIGN; size = sizeof(struct freelQ_e) * q->size; - q->entries = pci_alloc_consistent(pdev, size, &q->dma_addr); + q->entries = dma_alloc_coherent(&pdev->dev, size, + &q->dma_addr, GFP_KERNEL); if (!q->entries) goto err_no_mem; @@ -601,7 +601,8 @@ static int alloc_rx_resources(struct sge *sge, struct sge_params *p) sge->respQ.credits = 0; size = sizeof(struct respQ_e) * sge->respQ.size; sge->respQ.entries = - pci_alloc_consistent(pdev, size, &sge->respQ.dma_addr); + dma_alloc_coherent(&pdev->dev, size, &sge->respQ.dma_addr, + GFP_KERNEL); if (!sge->respQ.entries) goto err_no_mem; return 0; @@ -624,9 +625,10 @@ static void free_cmdQ_buffers(struct sge *sge, struct cmdQ *q, unsigned int n) ce = &q->centries[cidx]; while (n--) { if (likely(dma_unmap_len(ce, dma_len))) { - pci_unmap_single(pdev, dma_unmap_addr(ce, dma_addr), + dma_unmap_single(&pdev->dev, + dma_unmap_addr(ce, dma_addr), dma_unmap_len(ce, dma_len), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); if (q->sop) q->sop = 0; } @@ -663,8 +665,8 @@ static void free_tx_resources(struct sge *sge) } if (q->entries) { size = sizeof(struct cmdQ_e) * q->size; - pci_free_consistent(pdev, size, q->entries, - q->dma_addr); + dma_free_coherent(&pdev->dev, size, q->entries, + q->dma_addr); } } } @@ -689,7 +691,8 @@ static int alloc_tx_resources(struct sge *sge, struct sge_params *p) q->stop_thres = 0; spin_lock_init(&q->lock); size = sizeof(struct cmdQ_e) * q->size; - q->entries = pci_alloc_consistent(pdev, size, &q->dma_addr); + q->entries = dma_alloc_coherent(&pdev->dev, size, + &q->dma_addr, GFP_KERNEL); if (!q->entries) goto err_no_mem; @@ -837,8 +840,8 @@ static void refill_free_list(struct sge *sge, struct freelQ *q) break; skb_reserve(skb, q->dma_offset); - mapping = pci_map_single(pdev, skb->data, dma_len, - PCI_DMA_FROMDEVICE); + mapping = dma_map_single(&pdev->dev, skb->data, dma_len, + DMA_FROM_DEVICE); skb_reserve(skb, sge->rx_pkt_pad); ce->skb = skb; @@ -1049,15 +1052,15 @@ static inline struct sk_buff *get_packet(struct adapter *adapter, goto use_orig_buf; skb_put(skb, len); - pci_dma_sync_single_for_cpu(pdev, - dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), - PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&pdev->dev, + dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), + DMA_FROM_DEVICE); skb_copy_from_linear_data(ce->skb, skb->data, len); - pci_dma_sync_single_for_device(pdev, - dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&pdev->dev, + dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), + DMA_FROM_DEVICE); recycle_fl_buf(fl, fl->cidx); return skb; } @@ -1068,8 +1071,8 @@ use_orig_buf: return NULL; } - pci_unmap_single(pdev, dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), PCI_DMA_FROMDEVICE); + dma_unmap_single(&pdev->dev, dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), DMA_FROM_DEVICE); skb = ce->skb; prefetch(skb->data); @@ -1091,8 +1094,9 @@ static void unexpected_offload(struct adapter *adapter, struct freelQ *fl) struct freelQ_ce *ce = &fl->centries[fl->cidx]; struct sk_buff *skb = ce->skb; - pci_dma_sync_single_for_cpu(adapter->pdev, dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&adapter->pdev->dev, + dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), DMA_FROM_DEVICE); pr_err("%s: unexpected offload packet, cmd %u\n", adapter->name, *skb->data); recycle_fl_buf(fl, fl->cidx); @@ -1209,8 +1213,8 @@ static inline void write_tx_descs(struct adapter *adapter, struct sk_buff *skb, e = e1 = &q->entries[pidx]; ce = &q->centries[pidx]; - mapping = pci_map_single(adapter->pdev, skb->data, - skb_headlen(skb), PCI_DMA_TODEVICE); + mapping = dma_map_single(&adapter->pdev->dev, skb->data, + skb_headlen(skb), DMA_TO_DEVICE); desc_mapping = mapping; desc_len = skb_headlen(skb); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 42c6e9379882..387c357e1b8e 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -2543,7 +2543,7 @@ static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd) !(data->phy_id & 0xe0e0)) data->phy_id = mdio_phy_id_c45(data->phy_id >> 8, data->phy_id & 0x1f); - /* FALLTHRU */ + fallthrough; case SIOCGMIIPHY: return mdio_mii_ioctl(&pi->phy.mdio, data, cmd); case SIOCCHIOCTL: diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.c b/drivers/net/ethernet/chelsio/cxgb3/l2t.c index b3e4118a15e7..9749d1239f58 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.c @@ -136,7 +136,7 @@ again: if (e->state == L2T_STATE_STALE) e->state = L2T_STATE_VALID; spin_unlock_bh(&e->lock); - /* fall through */ + fallthrough; case L2T_STATE_VALID: /* fast-path, send the packet on */ return cxgb3_ofld_send(dev, skb); case L2T_STATE_RESOLVING: diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index 6dabbf1502c7..ee6188dea705 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -2372,10 +2372,7 @@ no_mem: if (fl->use_pages) { void *addr = fl->sdesc[fl->cidx].pg_chunk.va; - prefetch(addr); -#if L1_CACHE_BYTES < 128 - prefetch(addr + L1_CACHE_BYTES); -#endif + net_prefetch(addr); __refill_fl(adap, fl); if (lro > 0) { lro_add_page(adap, qs, fl, diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c index 0a9f2c596624..311fed38c101 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c @@ -2195,7 +2195,7 @@ static int t3_sge_write_context(struct adapter *adapter, unsigned int id, /** * clear_sge_ctxt - completely clear an SGE context - * @adapter: the adapter + * @adap: the adapter * @id: the context id * @type: the context type * @@ -2966,7 +2966,7 @@ static void ulp_config(struct adapter *adap, const struct tp_params *p) /** * t3_set_proto_sram - set the contents of the protocol sram - * @adapter: the adapter + * @adap: the adapter * @data: the protocol image * * Write the contents of the protocol SRAM. diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 9cb8b229c1b3..abab82ad3f63 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -146,6 +146,11 @@ enum { CXGB4_ETHTOOL_FLASH_BOOTCFG = 4 }; +enum cxgb4_netdev_tls_ops { + CXGB4_TLSDEV_OPS = 1, + CXGB4_XFRMDEV_OPS +}; + struct cxgb4_bootcfg_data { __le16 signature; __u8 reserved[2]; @@ -1196,6 +1201,9 @@ struct adapter { struct cxgb4_tc_u32_table *tc_u32; struct chcr_ktls chcr_ktls; struct chcr_stats_debug chcr_stats; +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) + struct ch_ipsec_stats_debug ch_ipsec_stats; +#endif /* TC flower offload */ bool tc_flower_initialized; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 05f33b7e3677..42112e8ad687 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3542,14 +3542,17 @@ static int chcr_stats_show(struct seq_file *seq, void *v) atomic_read(&adap->chcr_stats.error)); seq_printf(seq, "Fallback: %10u \n", atomic_read(&adap->chcr_stats.fallback)); - seq_printf(seq, "IPSec PDU: %10u\n", - atomic_read(&adap->chcr_stats.ipsec_cnt)); seq_printf(seq, "TLS PDU Tx: %10u\n", atomic_read(&adap->chcr_stats.tls_pdu_tx)); seq_printf(seq, "TLS PDU Rx: %10u\n", atomic_read(&adap->chcr_stats.tls_pdu_rx)); seq_printf(seq, "TLS Keys (DDR) Count: %10u\n", atomic_read(&adap->chcr_stats.tls_key)); +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) + seq_puts(seq, "\nChelsio Inline IPsec Crypto Accelerator Stats\n"); + seq_printf(seq, "IPSec PDU: %10u\n", + atomic_read(&adap->ch_ipsec_stats.ipsec_cnt)); +#endif #ifdef CONFIG_CHELSIO_TLS_DEVICE seq_puts(seq, "\nChelsio KTLS Crypto Accelerator Stats\n"); seq_printf(seq, "Tx TLS offload refcount: %20u\n", diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 650db92cb11c..f6c1ec140e09 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -604,17 +604,14 @@ int cxgb4_get_free_ftid(struct net_device *dev, u8 family, bool hash_en, /* If the new rule wants to get inserted into * HPFILTER region, but its prio is greater * than the rule with the highest prio in HASH - * region, then reject the rule. - */ - if (t->tc_hash_tids_max_prio && - tc_prio > t->tc_hash_tids_max_prio) - break; - - /* If there's not enough slots available - * in HPFILTER region, then move on to - * normal FILTER region immediately. + * region, or if there's not enough slots + * available in HPFILTER region, then skip + * trying to insert this rule into HPFILTER + * region and directly go to the next region. */ - if (ftid + n > t->nhpftids) { + if ((t->tc_hash_tids_max_prio && + tc_prio > t->tc_hash_tids_max_prio) || + (ftid + n) > t->nhpftids) { ftid = t->nhpftids; continue; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index de078a5bf23e..27530c0e2d14 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -6396,6 +6396,49 @@ static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs) } #endif /* CONFIG_PCI_IOV */ +#if defined(CONFIG_CHELSIO_TLS_DEVICE) || IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) + +static int chcr_offload_state(struct adapter *adap, + enum cxgb4_netdev_tls_ops op_val) +{ + switch (op_val) { +#if defined(CONFIG_CHELSIO_TLS_DEVICE) + case CXGB4_TLSDEV_OPS: + if (!adap->uld[CXGB4_ULD_CRYPTO].handle) { + dev_dbg(adap->pdev_dev, "chcr driver is not loaded\n"); + return -EOPNOTSUPP; + } + if (!adap->uld[CXGB4_ULD_CRYPTO].tlsdev_ops) { + dev_dbg(adap->pdev_dev, + "chcr driver has no registered tlsdev_ops\n"); + return -EOPNOTSUPP; + } + break; +#endif /* CONFIG_CHELSIO_TLS_DEVICE */ +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) + case CXGB4_XFRMDEV_OPS: + if (!adap->uld[CXGB4_ULD_IPSEC].handle) { + dev_dbg(adap->pdev_dev, "chipsec driver is not loaded\n"); + return -EOPNOTSUPP; + } + if (!adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops) { + dev_dbg(adap->pdev_dev, + "chipsec driver has no registered xfrmdev_ops\n"); + return -EOPNOTSUPP; + } + break; +#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ + default: + dev_dbg(adap->pdev_dev, + "driver has no support for offload %d\n", op_val); + return -EOPNOTSUPP; + } + + return 0; +} + +#endif /* CONFIG_CHELSIO_TLS_DEVICE || CONFIG_CHELSIO_IPSEC_INLINE */ + #if defined(CONFIG_CHELSIO_TLS_DEVICE) static int cxgb4_ktls_dev_add(struct net_device *netdev, struct sock *sk, @@ -6404,21 +6447,12 @@ static int cxgb4_ktls_dev_add(struct net_device *netdev, struct sock *sk, u32 tcp_sn) { struct adapter *adap = netdev2adap(netdev); - int ret = 0; + int ret; mutex_lock(&uld_mutex); - if (!adap->uld[CXGB4_ULD_CRYPTO].handle) { - dev_err(adap->pdev_dev, "chcr driver is not loaded\n"); - ret = -EOPNOTSUPP; - goto out_unlock; - } - - if (!adap->uld[CXGB4_ULD_CRYPTO].tlsdev_ops) { - dev_err(adap->pdev_dev, - "chcr driver has no registered tlsdev_ops()\n"); - ret = -EOPNOTSUPP; + ret = chcr_offload_state(adap, CXGB4_TLSDEV_OPS); + if (ret) goto out_unlock; - } ret = cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_ENABLE); if (ret) @@ -6444,25 +6478,125 @@ static void cxgb4_ktls_dev_del(struct net_device *netdev, struct adapter *adap = netdev2adap(netdev); mutex_lock(&uld_mutex); - if (!adap->uld[CXGB4_ULD_CRYPTO].handle) { - dev_err(adap->pdev_dev, "chcr driver is not loaded\n"); + if (chcr_offload_state(adap, CXGB4_TLSDEV_OPS)) goto out_unlock; + + adap->uld[CXGB4_ULD_CRYPTO].tlsdev_ops->tls_dev_del(netdev, tls_ctx, + direction); + cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE); + +out_unlock: + mutex_unlock(&uld_mutex); +} + +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) + +static int cxgb4_xfrm_add_state(struct xfrm_state *x) +{ + struct adapter *adap = netdev2adap(x->xso.dev); + int ret; + + if (!mutex_trylock(&uld_mutex)) { + dev_dbg(adap->pdev_dev, + "crypto uld critical resource is under use\n"); + return -EBUSY; } + ret = chcr_offload_state(adap, CXGB4_XFRMDEV_OPS); + if (ret) + goto out_unlock; - if (!adap->uld[CXGB4_ULD_CRYPTO].tlsdev_ops) { - dev_err(adap->pdev_dev, - "chcr driver has no registered tlsdev_ops\n"); + ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_add(x); + +out_unlock: + mutex_unlock(&uld_mutex); + + return ret; +} + +static void cxgb4_xfrm_del_state(struct xfrm_state *x) +{ + struct adapter *adap = netdev2adap(x->xso.dev); + + if (!mutex_trylock(&uld_mutex)) { + dev_dbg(adap->pdev_dev, + "crypto uld critical resource is under use\n"); + return; + } + if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS)) goto out_unlock; + + adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_delete(x); + +out_unlock: + mutex_unlock(&uld_mutex); +} + +static void cxgb4_xfrm_free_state(struct xfrm_state *x) +{ + struct adapter *adap = netdev2adap(x->xso.dev); + + if (!mutex_trylock(&uld_mutex)) { + dev_dbg(adap->pdev_dev, + "crypto uld critical resource is under use\n"); + return; } + if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS)) + goto out_unlock; - adap->uld[CXGB4_ULD_CRYPTO].tlsdev_ops->tls_dev_del(netdev, tls_ctx, - direction); - cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE); + adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_free(x); + +out_unlock: + mutex_unlock(&uld_mutex); +} + +static bool cxgb4_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x) +{ + struct adapter *adap = netdev2adap(x->xso.dev); + bool ret = false; + + if (!mutex_trylock(&uld_mutex)) { + dev_dbg(adap->pdev_dev, + "crypto uld critical resource is under use\n"); + return ret; + } + if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS)) + goto out_unlock; + + ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_offload_ok(skb, x); out_unlock: mutex_unlock(&uld_mutex); + return ret; } +static void cxgb4_advance_esn_state(struct xfrm_state *x) +{ + struct adapter *adap = netdev2adap(x->xso.dev); + + if (!mutex_trylock(&uld_mutex)) { + dev_dbg(adap->pdev_dev, + "crypto uld critical resource is under use\n"); + return; + } + if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS)) + goto out_unlock; + + adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_advance_esn(x); + +out_unlock: + mutex_unlock(&uld_mutex); +} + +static const struct xfrmdev_ops cxgb4_xfrmdev_ops = { + .xdo_dev_state_add = cxgb4_xfrm_add_state, + .xdo_dev_state_delete = cxgb4_xfrm_del_state, + .xdo_dev_state_free = cxgb4_xfrm_free_state, + .xdo_dev_offload_ok = cxgb4_ipsec_offload_ok, + .xdo_dev_state_advance_esn = cxgb4_advance_esn_state, +}; + +#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ + static const struct tlsdev_ops cxgb4_ktls_ops = { .tls_dev_add = cxgb4_ktls_dev_add, .tls_dev_del = cxgb4_ktls_dev_del, @@ -6728,7 +6862,15 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* initialize the refcount */ refcount_set(&pi->adapter->chcr_ktls.ktls_refcount, 0); } -#endif +#endif /* CONFIG_CHELSIO_TLS_DEVICE */ +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) + if (pi->adapter->params.crypto & FW_CAPS_CONFIG_IPSEC_INLINE) { + netdev->hw_enc_features |= NETIF_F_HW_ESP; + netdev->features |= NETIF_F_HW_ESP; + netdev->xfrmdev_ops = &cxgb4_xfrmdev_ops; + } +#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ + netdev->priv_flags |= IFF_UNICAST_FLT; /* MTU range: 81 - 9600 */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c index e3510e9b21f3..9a6d65243334 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c @@ -62,6 +62,7 @@ static struct thermal_zone_device_ops cxgb4_thermal_ops = { int cxgb4_thermal_init(struct adapter *adap) { struct ch_thermal *ch_thermal = &adap->ch_thermal; + char ch_tz_name[THERMAL_NAME_LENGTH]; int num_trip = CXGB4_NUM_TRIPS; u32 param, val; int ret; @@ -82,7 +83,8 @@ int cxgb4_thermal_init(struct adapter *adap) ch_thermal->trip_type = THERMAL_TRIP_CRITICAL; } - ch_thermal->tzdev = thermal_zone_device_register("cxgb4", num_trip, + snprintf(ch_tz_name, sizeof(ch_tz_name), "cxgb4_%s", adap->name); + ch_thermal->tzdev = thermal_zone_device_register(ch_tz_name, num_trip, 0, adap, &cxgb4_thermal_ops, NULL, 0, 0); @@ -105,7 +107,9 @@ int cxgb4_thermal_init(struct adapter *adap) int cxgb4_thermal_remove(struct adapter *adap) { - if (adap->ch_thermal.tzdev) + if (adap->ch_thermal.tzdev) { thermal_zone_device_unregister(adap->ch_thermal.tzdev); + adap->ch_thermal.tzdev = NULL; + } return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h index a963fd0b4540..421ae87aa7db 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h @@ -302,6 +302,7 @@ enum cxgb4_uld { CXGB4_ULD_ISCSI, CXGB4_ULD_ISCSIT, CXGB4_ULD_CRYPTO, + CXGB4_ULD_IPSEC, CXGB4_ULD_TLS, CXGB4_ULD_MAX }; @@ -368,7 +369,6 @@ struct chcr_stats_debug { atomic_t complete; atomic_t error; atomic_t fallback; - atomic_t ipsec_cnt; atomic_t tls_pdu_tx; atomic_t tls_pdu_rx; atomic_t tls_key; @@ -394,6 +394,12 @@ struct chcr_stats_debug { #endif }; +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) +struct ch_ipsec_stats_debug { + atomic_t ipsec_cnt; +}; +#endif + #define OCQ_WIN_OFFSET(pdev, vres) \ (pci_resource_len((pdev), 2) - roundup_pow_of_two((vres)->ocq.size)) @@ -473,6 +479,9 @@ struct cxgb4_uld_info { #if IS_ENABLED(CONFIG_TLS_DEVICE) const struct tlsdev_ops *tlsdev_ops; #endif +#if IS_ENABLED(CONFIG_XFRM_OFFLOAD) + const struct xfrmdev_ops *xfrmdev_ops; +#endif }; void cxgb4_uld_enable(struct adapter *adap); diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index c4864125fe02..a10a6862a9a4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -231,7 +231,7 @@ again: if (e->state == L2T_STATE_STALE) e->state = L2T_STATE_VALID; spin_unlock_bh(&e->lock); - /* fall through */ + fallthrough; case L2T_STATE_VALID: /* fast-path, send the packet on */ return t4_ofld_send(adap, skb); case L2T_STATE_RESOLVING: diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index d2b587d1670a..fddd70ee6436 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -1416,9 +1416,9 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) pi = netdev_priv(dev); adap = pi->adapter; ssi = skb_shinfo(skb); -#ifdef CONFIG_CHELSIO_IPSEC_INLINE +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) if (xfrm_offload(skb) && !ssi->gso_size) - return adap->uld[CXGB4_ULD_CRYPTO].tx_handler(skb, dev); + return adap->uld[CXGB4_ULD_IPSEC].tx_handler(skb, dev); #endif /* CHELSIO_IPSEC_INLINE */ #ifdef CONFIG_CHELSIO_TLS_DEVICE @@ -2553,19 +2553,22 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) pkt_len = ETH_HLEN + sizeof(CXGB4_SELFTEST_LB_STR); - flits = DIV_ROUND_UP(pkt_len + sizeof(struct cpl_tx_pkt) + - sizeof(*wr), sizeof(__be64)); + flits = DIV_ROUND_UP(pkt_len + sizeof(*cpl) + sizeof(*wr), + sizeof(__be64)); ndesc = flits_to_desc(flits); lb = &pi->ethtool_lb; lb->loopback = 1; q = &adap->sge.ethtxq[pi->first_qset]; + __netif_tx_lock(q->txq, smp_processor_id()); reclaim_completed_tx(adap, &q->q, -1, true); credits = txq_avail(&q->q) - ndesc; - if (unlikely(credits < 0)) + if (unlikely(credits < 0)) { + __netif_tx_unlock(q->txq); return -ENOMEM; + } wr = (void *)&q->q.desc[q->q.pidx]; memset(wr, 0, sizeof(struct tx_desc)); @@ -2598,6 +2601,7 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) init_completion(&lb->completion); txq_advance(&q->q, ndesc); cxgb4_ring_tx_db(adap, &q->q, ndesc); + __netif_tx_unlock(q->txq); /* wait for the pkt to return */ ret = wait_for_completion_timeout(&lb->completion, 10 * HZ); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 8a56491bb034..98d01a7497ec 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4745,9 +4745,11 @@ static void le_intr_handler(struct adapter *adap) static struct intr_info t6_le_intr_info[] = { { T6_LIPMISS_F, "LE LIP miss", -1, 0 }, { T6_LIP0_F, "LE 0 LIP error", -1, 0 }, + { CMDTIDERR_F, "LE cmd tid error", -1, 1 }, { TCAMINTPERR_F, "LE parity error", -1, 1 }, { T6_UNKNOWNCMD_F, "LE unknown command", -1, 1 }, { SSRAMINTPERR_F, "LE request queue parity error", -1, 1 }, + { HASHTBLMEMCRCERR_F, "LE hash table mem crc error", -1, 0 }, { 0 } }; @@ -7656,13 +7658,13 @@ int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port, switch (nmac) { case 5: memcpy(mac + 24, c.nmac3, sizeof(c.nmac3)); - /* Fall through */ + fallthrough; case 4: memcpy(mac + 18, c.nmac2, sizeof(c.nmac2)); - /* Fall through */ + fallthrough; case 3: memcpy(mac + 12, c.nmac1, sizeof(c.nmac1)); - /* Fall through */ + fallthrough; case 2: memcpy(mac + 6, c.nmac0, sizeof(c.nmac0)); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 065c01c654ff..b11a172b5174 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -3017,6 +3017,14 @@ #define REV_V(x) ((x) << REV_S) #define REV_G(x) (((x) >> REV_S) & REV_M) +#define HASHTBLMEMCRCERR_S 27 +#define HASHTBLMEMCRCERR_V(x) ((x) << HASHTBLMEMCRCERR_S) +#define HASHTBLMEMCRCERR_F HASHTBLMEMCRCERR_V(1U) + +#define CMDTIDERR_S 22 +#define CMDTIDERR_V(x) ((x) << CMDTIDERR_S) +#define CMDTIDERR_F CMDTIDERR_V(1U) + #define T6_UNKNOWNCMD_S 3 #define T6_UNKNOWNCMD_V(x) ((x) << T6_UNKNOWNCMD_S) #define T6_UNKNOWNCMD_F T6_UNKNOWNCMD_V(1U) diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index dbe8ee7e0e21..e2fe78e2e242 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -517,7 +517,7 @@ static int fwevtq_handler(struct sge_rspq *rspq, const __be64 *rsp, } cpl = (void *)p; } - /* Fall through */ + fallthrough; case CPL_SGE_EGR_UPDATE: { /* diff --git a/drivers/net/ethernet/chelsio/inline_crypto/Kconfig b/drivers/net/ethernet/chelsio/inline_crypto/Kconfig new file mode 100644 index 000000000000..be70b59b6f80 --- /dev/null +++ b/drivers/net/ethernet/chelsio/inline_crypto/Kconfig @@ -0,0 +1,37 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Chelsio inline crypto configuration +# + +config CHELSIO_INLINE_CRYPTO + bool "Chelsio Inline Crypto support" + depends on CHELSIO_T4 + default y + help + Enable support for inline crypto. + Allows enable/disable from list of inline crypto drivers. + +if CHELSIO_INLINE_CRYPTO + +config CRYPTO_DEV_CHELSIO_TLS + tristate "Chelsio Crypto Inline TLS Driver" + depends on TLS_TOE + help + Support Chelsio Inline TLS with Chelsio crypto accelerator. + Enable inline TLS support for Tx and Rx. + + To compile this driver as a module, choose M here: the module + will be called chtls. + +config CHELSIO_IPSEC_INLINE + tristate "Chelsio IPSec XFRM Tx crypto offload" + depends on XFRM_OFFLOAD + depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD + help + Support Chelsio Inline IPsec with Chelsio crypto accelerator. + Enable inline IPsec support for Tx. + + To compile this driver as a module, choose M here: the module + will be called ch_ipsec. + +endif # CHELSIO_INLINE_CRYPTO diff --git a/drivers/net/ethernet/chelsio/inline_crypto/Makefile b/drivers/net/ethernet/chelsio/inline_crypto/Makefile new file mode 100644 index 000000000000..9a86ee8f1f38 --- /dev/null +++ b/drivers/net/ethernet/chelsio/inline_crypto/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_CRYPTO_DEV_CHELSIO_TLS) += chtls/ +obj-$(CONFIG_CHELSIO_IPSEC_INLINE) += ch_ipsec/ diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/Makefile b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/Makefile new file mode 100644 index 000000000000..efdcaaebc455 --- /dev/null +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +ccflags-y := -I $(srctree)/drivers/net/ethernet/chelsio/cxgb4 \ + -I $(srctree)/drivers/crypto/chelsio + +obj-$(CONFIG_CHELSIO_IPSEC_INLINE) += ch_ipsec.o +ch_ipsec-objs := chcr_ipsec.o + + diff --git a/drivers/crypto/chelsio/chcr_ipsec.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c index 967babd67a51..0e7d25169407 100644 --- a/drivers/crypto/chelsio/chcr_ipsec.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c @@ -60,9 +60,7 @@ #include <crypto/scatterwalk.h> #include <crypto/internal/hash.h> -#include "chcr_core.h" -#include "chcr_algo.h" -#include "chcr_crypto.h" +#include "chcr_ipsec.h" /* * Max Tx descriptor space we allow for an Ethernet packet to be inlined @@ -71,11 +69,16 @@ #define MAX_IMM_TX_PKT_LEN 256 #define GCM_ESP_IV_SIZE 8 +static LIST_HEAD(uld_ctx_list); +static DEFINE_MUTEX(dev_mutex); + static int chcr_xfrm_add_state(struct xfrm_state *x); static void chcr_xfrm_del_state(struct xfrm_state *x); static void chcr_xfrm_free_state(struct xfrm_state *x); static bool chcr_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x); static void chcr_advance_esn_state(struct xfrm_state *x); +static int ch_ipsec_uld_state_change(void *handle, enum cxgb4_state new_state); +static void *ch_ipsec_uld_add(const struct cxgb4_lld_info *infop); static const struct xfrmdev_ops chcr_xfrmdev_ops = { .xdo_dev_state_add = chcr_xfrm_add_state, @@ -85,21 +88,56 @@ static const struct xfrmdev_ops chcr_xfrmdev_ops = { .xdo_dev_state_advance_esn = chcr_advance_esn_state, }; -/* Add offload xfrms to Chelsio Interface */ -void chcr_add_xfrmops(const struct cxgb4_lld_info *lld) +static struct cxgb4_uld_info ch_ipsec_uld_info = { + .name = CHIPSEC_DRV_MODULE_NAME, + .nrxq = MAX_ULD_QSETS, + /* Max ntxq will be derived from fw config file*/ + .rxq_size = 1024, + .add = ch_ipsec_uld_add, + .state_change = ch_ipsec_uld_state_change, + .tx_handler = chcr_ipsec_xmit, + .xfrmdev_ops = &chcr_xfrmdev_ops, +}; + +static void *ch_ipsec_uld_add(const struct cxgb4_lld_info *infop) { - struct net_device *netdev = NULL; - int i; - - for (i = 0; i < lld->nports; i++) { - netdev = lld->ports[i]; - if (!netdev) - continue; - netdev->xfrmdev_ops = &chcr_xfrmdev_ops; - netdev->hw_enc_features |= NETIF_F_HW_ESP; - netdev->features |= NETIF_F_HW_ESP; - netdev_change_features(netdev); + struct ipsec_uld_ctx *u_ctx; + + pr_info_once("%s - version %s\n", CHIPSEC_DRV_DESC, + CHIPSEC_DRV_VERSION); + u_ctx = kzalloc(sizeof(*u_ctx), GFP_KERNEL); + if (!u_ctx) { + u_ctx = ERR_PTR(-ENOMEM); + goto out; } + u_ctx->lldi = *infop; +out: + return u_ctx; +} + +static int ch_ipsec_uld_state_change(void *handle, enum cxgb4_state new_state) +{ + struct ipsec_uld_ctx *u_ctx = handle; + + pr_info("new_state %u\n", new_state); + switch (new_state) { + case CXGB4_STATE_UP: + pr_info("%s: Up\n", pci_name(u_ctx->lldi.pdev)); + mutex_lock(&dev_mutex); + list_add_tail(&u_ctx->entry, &uld_ctx_list); + mutex_unlock(&dev_mutex); + break; + case CXGB4_STATE_START_RECOVERY: + case CXGB4_STATE_DOWN: + case CXGB4_STATE_DETACH: + pr_info("%s: Down\n", pci_name(u_ctx->lldi.pdev)); + list_del(&u_ctx->entry); + break; + default: + break; + } + + return 0; } static inline int chcr_ipsec_setauthsize(struct xfrm_state *x, @@ -538,7 +576,7 @@ inline void *chcr_crypto_wreq(struct sk_buff *skb, unsigned int kctx_len = sa_entry->kctx_len; int qid = q->q.cntxt_id; - atomic_inc(&adap->chcr_stats.ipsec_cnt); + atomic_inc(&adap->ch_ipsec_stats.ipsec_cnt); flits = calc_tx_sec_flits(skb, sa_entry, &immediate); ndesc = DIV_ROUND_UP(flits, 2); @@ -752,3 +790,35 @@ out_free: dev_kfree_skb_any(skb); cxgb4_ring_tx_db(adap, &q->q, ndesc); return NETDEV_TX_OK; } + +static int __init chcr_ipsec_init(void) +{ + cxgb4_register_uld(CXGB4_ULD_IPSEC, &ch_ipsec_uld_info); + + return 0; +} + +static void __exit chcr_ipsec_exit(void) +{ + struct ipsec_uld_ctx *u_ctx, *tmp; + struct adapter *adap; + + mutex_lock(&dev_mutex); + list_for_each_entry_safe(u_ctx, tmp, &uld_ctx_list, entry) { + adap = pci_get_drvdata(u_ctx->lldi.pdev); + atomic_set(&adap->ch_ipsec_stats.ipsec_cnt, 0); + list_del(&u_ctx->entry); + kfree(u_ctx); + } + mutex_unlock(&dev_mutex); + cxgb4_unregister_uld(CXGB4_ULD_IPSEC); +} + +module_init(chcr_ipsec_init); +module_exit(chcr_ipsec_exit); + +MODULE_DESCRIPTION("Crypto IPSEC for Chelsio Terminator cards."); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Chelsio Communications"); +MODULE_VERSION(CHIPSEC_DRV_VERSION); + diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.h new file mode 100644 index 000000000000..1d110d2edd64 --- /dev/null +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2018 Chelsio Communications, Inc. */ + +#ifndef __CHCR_IPSEC_H__ +#define __CHCR_IPSEC_H__ + +#include <crypto/algapi.h> +#include "t4_hw.h" +#include "cxgb4.h" +#include "t4_msg.h" +#include "cxgb4_uld.h" + +#include "chcr_core.h" +#include "chcr_algo.h" +#include "chcr_crypto.h" + +#define CHIPSEC_DRV_MODULE_NAME "ch_ipsec" +#define CHIPSEC_DRV_VERSION "1.0.0.0-ko" +#define CHIPSEC_DRV_DESC "Chelsio T6 Crypto Ipsec offload Driver" + +struct ipsec_uld_ctx { + struct list_head entry; + struct cxgb4_lld_info lldi; +}; + +struct chcr_ipsec_req { + struct ulp_txpkt ulptx; + struct ulptx_idata sc_imm; + struct cpl_tx_sec_pdu sec_cpl; + struct _key_ctx key_ctx; +}; + +struct chcr_ipsec_wr { + struct fw_ulptx_wr wreq; + struct chcr_ipsec_req req; +}; + +#define ESN_IV_INSERT_OFFSET 12 +struct chcr_ipsec_aadiv { + __be32 spi; + u8 seq_no[8]; + u8 iv[8]; +}; + +struct ipsec_sa_entry { + int hmac_ctrl; + u16 esn; + u16 resv; + unsigned int enckey_len; + unsigned int kctx_len; + unsigned int authsize; + __be32 key_ctx_hdr; + char salt[MAX_SALT]; + char key[2 * AES_MAX_KEY_SIZE]; +}; + +#endif /* __CHCR_IPSEC_H__ */ + diff --git a/drivers/crypto/chelsio/chtls/Makefile b/drivers/net/ethernet/chelsio/inline_crypto/chtls/Makefile index bc11495acdb3..bc11495acdb3 100644 --- a/drivers/crypto/chelsio/chtls/Makefile +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/Makefile diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h index 459442704eb1..2d3dfdd2a716 100644 --- a/drivers/crypto/chelsio/chtls/chtls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h @@ -32,6 +32,94 @@ #include "chcr_core.h" #include "chcr_crypto.h" +#define CHTLS_DRV_VERSION "1.0.0.0-ko" + +#define TLS_KEYCTX_RXFLIT_CNT_S 24 +#define TLS_KEYCTX_RXFLIT_CNT_V(x) ((x) << TLS_KEYCTX_RXFLIT_CNT_S) + +#define TLS_KEYCTX_RXPROT_VER_S 20 +#define TLS_KEYCTX_RXPROT_VER_M 0xf +#define TLS_KEYCTX_RXPROT_VER_V(x) ((x) << TLS_KEYCTX_RXPROT_VER_S) + +#define TLS_KEYCTX_RXCIPH_MODE_S 16 +#define TLS_KEYCTX_RXCIPH_MODE_M 0xf +#define TLS_KEYCTX_RXCIPH_MODE_V(x) ((x) << TLS_KEYCTX_RXCIPH_MODE_S) + +#define TLS_KEYCTX_RXAUTH_MODE_S 12 +#define TLS_KEYCTX_RXAUTH_MODE_M 0xf +#define TLS_KEYCTX_RXAUTH_MODE_V(x) ((x) << TLS_KEYCTX_RXAUTH_MODE_S) + +#define TLS_KEYCTX_RXCIAU_CTRL_S 11 +#define TLS_KEYCTX_RXCIAU_CTRL_V(x) ((x) << TLS_KEYCTX_RXCIAU_CTRL_S) + +#define TLS_KEYCTX_RX_SEQCTR_S 9 +#define TLS_KEYCTX_RX_SEQCTR_M 0x3 +#define TLS_KEYCTX_RX_SEQCTR_V(x) ((x) << TLS_KEYCTX_RX_SEQCTR_S) + +#define TLS_KEYCTX_RX_VALID_S 8 +#define TLS_KEYCTX_RX_VALID_V(x) ((x) << TLS_KEYCTX_RX_VALID_S) + +#define TLS_KEYCTX_RXCK_SIZE_S 3 +#define TLS_KEYCTX_RXCK_SIZE_M 0x7 +#define TLS_KEYCTX_RXCK_SIZE_V(x) ((x) << TLS_KEYCTX_RXCK_SIZE_S) + +#define TLS_KEYCTX_RXMK_SIZE_S 0 +#define TLS_KEYCTX_RXMK_SIZE_M 0x7 +#define TLS_KEYCTX_RXMK_SIZE_V(x) ((x) << TLS_KEYCTX_RXMK_SIZE_S) + +#define KEYCTX_TX_WR_IV_S 55 +#define KEYCTX_TX_WR_IV_M 0x1ffULL +#define KEYCTX_TX_WR_IV_V(x) ((x) << KEYCTX_TX_WR_IV_S) +#define KEYCTX_TX_WR_IV_G(x) \ + (((x) >> KEYCTX_TX_WR_IV_S) & KEYCTX_TX_WR_IV_M) + +#define KEYCTX_TX_WR_AAD_S 47 +#define KEYCTX_TX_WR_AAD_M 0xffULL +#define KEYCTX_TX_WR_AAD_V(x) ((x) << KEYCTX_TX_WR_AAD_S) +#define KEYCTX_TX_WR_AAD_G(x) (((x) >> KEYCTX_TX_WR_AAD_S) & \ + KEYCTX_TX_WR_AAD_M) + +#define KEYCTX_TX_WR_AADST_S 39 +#define KEYCTX_TX_WR_AADST_M 0xffULL +#define KEYCTX_TX_WR_AADST_V(x) ((x) << KEYCTX_TX_WR_AADST_S) +#define KEYCTX_TX_WR_AADST_G(x) \ + (((x) >> KEYCTX_TX_WR_AADST_S) & KEYCTX_TX_WR_AADST_M) + +#define KEYCTX_TX_WR_CIPHER_S 30 +#define KEYCTX_TX_WR_CIPHER_M 0x1ffULL +#define KEYCTX_TX_WR_CIPHER_V(x) ((x) << KEYCTX_TX_WR_CIPHER_S) +#define KEYCTX_TX_WR_CIPHER_G(x) \ + (((x) >> KEYCTX_TX_WR_CIPHER_S) & KEYCTX_TX_WR_CIPHER_M) + +#define KEYCTX_TX_WR_CIPHERST_S 23 +#define KEYCTX_TX_WR_CIPHERST_M 0x7f +#define KEYCTX_TX_WR_CIPHERST_V(x) ((x) << KEYCTX_TX_WR_CIPHERST_S) +#define KEYCTX_TX_WR_CIPHERST_G(x) \ + (((x) >> KEYCTX_TX_WR_CIPHERST_S) & KEYCTX_TX_WR_CIPHERST_M) + +#define KEYCTX_TX_WR_AUTH_S 14 +#define KEYCTX_TX_WR_AUTH_M 0x1ff +#define KEYCTX_TX_WR_AUTH_V(x) ((x) << KEYCTX_TX_WR_AUTH_S) +#define KEYCTX_TX_WR_AUTH_G(x) \ + (((x) >> KEYCTX_TX_WR_AUTH_S) & KEYCTX_TX_WR_AUTH_M) + +#define KEYCTX_TX_WR_AUTHST_S 7 +#define KEYCTX_TX_WR_AUTHST_M 0x7f +#define KEYCTX_TX_WR_AUTHST_V(x) ((x) << KEYCTX_TX_WR_AUTHST_S) +#define KEYCTX_TX_WR_AUTHST_G(x) \ + (((x) >> KEYCTX_TX_WR_AUTHST_S) & KEYCTX_TX_WR_AUTHST_M) + +#define KEYCTX_TX_WR_AUTHIN_S 0 +#define KEYCTX_TX_WR_AUTHIN_M 0x7f +#define KEYCTX_TX_WR_AUTHIN_V(x) ((x) << KEYCTX_TX_WR_AUTHIN_S) +#define KEYCTX_TX_WR_AUTHIN_G(x) \ + (((x) >> KEYCTX_TX_WR_AUTHIN_S) & KEYCTX_TX_WR_AUTHIN_M) + +struct sge_opaque_hdr { + void *dev; + dma_addr_t addr[MAX_SKB_FRAGS + 1]; +}; + #define MAX_IVS_PAGE 256 #define TLS_KEY_CONTEXT_SZ 64 #define CIPHER_BLOCK_SIZE 16 diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 05520dccd906..05520dccd906 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h index 47ba81e42f5d..47ba81e42f5d 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h diff --git a/drivers/crypto/chelsio/chtls/chtls_hw.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c index f1820aca0d33..f1820aca0d33 100644 --- a/drivers/crypto/chelsio/chtls/chtls_hw.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index 2e9acae1cba3..2e9acae1cba3 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c index 66d247efd561..9098b3eed4da 100644 --- a/drivers/crypto/chelsio/chtls/chtls_main.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c @@ -638,4 +638,4 @@ module_exit(chtls_unregister); MODULE_DESCRIPTION("Chelsio TLS Inline driver"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Chelsio Communications"); -MODULE_VERSION(DRV_VERSION); +MODULE_VERSION(CHTLS_DRV_VERSION); diff --git a/drivers/net/ethernet/cirrus/cs89x0.h b/drivers/net/ethernet/cirrus/cs89x0.h index 91423b70bb45..210f9ec9af4b 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.h +++ b/drivers/net/ethernet/cirrus/cs89x0.h @@ -459,7 +459,3 @@ #define PNP_CNF_INT 0x70 #define PNP_CNF_DMA 0x74 #define PNP_CNF_MEM 0x48 - -#define BIT0 1 -#define BIT15 0x8000 - diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 6bc7e7ba38c3..4f0329d8778f 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -272,7 +272,7 @@ static netdev_features_t enic_features_check(struct sk_buff *skb, case ntohs(ETH_P_IPV6): if (!(enic->vxlan.flags & ENIC_VXLAN_INNER_IPV6)) goto out; - /* Fall through */ + fallthrough; case ntohs(ETH_P_IP): break; default: @@ -326,11 +326,11 @@ static void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf) struct enic *enic = vnic_dev_priv(wq->vdev); if (buf->sop) - pci_unmap_single(enic->pdev, buf->dma_addr, - buf->len, PCI_DMA_TODEVICE); + dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len, + DMA_TO_DEVICE); else - pci_unmap_page(enic->pdev, buf->dma_addr, - buf->len, PCI_DMA_TODEVICE); + dma_unmap_page(&enic->pdev->dev, buf->dma_addr, buf->len, + DMA_TO_DEVICE); if (buf->os_buf) dev_kfree_skb_any(buf->os_buf); @@ -574,8 +574,8 @@ static int enic_queue_wq_skb_vlan(struct enic *enic, struct vnic_wq *wq, dma_addr_t dma_addr; int err = 0; - dma_addr = pci_map_single(enic->pdev, skb->data, head_len, - PCI_DMA_TODEVICE); + dma_addr = dma_map_single(&enic->pdev->dev, skb->data, head_len, + DMA_TO_DEVICE); if (unlikely(enic_dma_map_check(enic, dma_addr))) return -ENOMEM; @@ -605,8 +605,8 @@ static int enic_queue_wq_skb_csum_l4(struct enic *enic, struct vnic_wq *wq, dma_addr_t dma_addr; int err = 0; - dma_addr = pci_map_single(enic->pdev, skb->data, head_len, - PCI_DMA_TODEVICE); + dma_addr = dma_map_single(&enic->pdev->dev, skb->data, head_len, + DMA_TO_DEVICE); if (unlikely(enic_dma_map_check(enic, dma_addr))) return -ENOMEM; @@ -693,8 +693,9 @@ static int enic_queue_wq_skb_tso(struct enic *enic, struct vnic_wq *wq, */ while (frag_len_left) { len = min(frag_len_left, (unsigned int)WQ_ENET_MAX_DESC_LEN); - dma_addr = pci_map_single(enic->pdev, skb->data + offset, len, - PCI_DMA_TODEVICE); + dma_addr = dma_map_single(&enic->pdev->dev, + skb->data + offset, len, + DMA_TO_DEVICE); if (unlikely(enic_dma_map_check(enic, dma_addr))) return -ENOMEM; enic_queue_wq_desc_tso(wq, skb, dma_addr, len, mss, hdr_len, @@ -752,8 +753,8 @@ static inline int enic_queue_wq_skb_encap(struct enic *enic, struct vnic_wq *wq, dma_addr_t dma_addr; int err = 0; - dma_addr = pci_map_single(enic->pdev, skb->data, head_len, - PCI_DMA_TODEVICE); + dma_addr = dma_map_single(&enic->pdev->dev, skb->data, head_len, + DMA_TO_DEVICE); if (unlikely(enic_dma_map_check(enic, dma_addr))) return -ENOMEM; @@ -1222,8 +1223,8 @@ static void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf) if (!buf->os_buf) return; - pci_unmap_single(enic->pdev, buf->dma_addr, - buf->len, PCI_DMA_FROMDEVICE); + dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len, + DMA_FROM_DEVICE); dev_kfree_skb_any(buf->os_buf); buf->os_buf = NULL; } @@ -1248,8 +1249,8 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq) if (!skb) return -ENOMEM; - dma_addr = pci_map_single(enic->pdev, skb->data, len, - PCI_DMA_FROMDEVICE); + dma_addr = dma_map_single(&enic->pdev->dev, skb->data, len, + DMA_FROM_DEVICE); if (unlikely(enic_dma_map_check(enic, dma_addr))) { dev_kfree_skb(skb); return -ENOMEM; @@ -1281,8 +1282,8 @@ static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb, new_skb = netdev_alloc_skb_ip_align(netdev, len); if (!new_skb) return false; - pci_dma_sync_single_for_cpu(enic->pdev, buf->dma_addr, len, - DMA_FROM_DEVICE); + dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr, len, + DMA_FROM_DEVICE); memcpy(new_skb->data, (*skb)->data, len); *skb = new_skb; @@ -1331,8 +1332,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, enic->rq_truncated_pkts++; } - pci_unmap_single(enic->pdev, buf->dma_addr, buf->len, - PCI_DMA_FROMDEVICE); + dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len, + DMA_FROM_DEVICE); dev_kfree_skb_any(skb); buf->os_buf = NULL; @@ -1346,8 +1347,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) { buf->os_buf = NULL; - pci_unmap_single(enic->pdev, buf->dma_addr, buf->len, - PCI_DMA_FROMDEVICE); + dma_unmap_single(&enic->pdev->dev, buf->dma_addr, + buf->len, DMA_FROM_DEVICE); } prefetch(skb->data - NET_IP_ALIGN); @@ -1420,8 +1421,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, /* Buffer overflow */ - pci_unmap_single(enic->pdev, buf->dma_addr, buf->len, - PCI_DMA_FROMDEVICE); + dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len, + DMA_FROM_DEVICE); dev_kfree_skb_any(skb); buf->os_buf = NULL; } @@ -2178,9 +2179,9 @@ int __enic_set_rsskey(struct enic *enic) dma_addr_t rss_key_buf_pa; int i, kidx, bidx, err; - rss_key_buf_va = pci_zalloc_consistent(enic->pdev, - sizeof(union vnic_rss_key), - &rss_key_buf_pa); + rss_key_buf_va = dma_alloc_coherent(&enic->pdev->dev, + sizeof(union vnic_rss_key), + &rss_key_buf_pa, GFP_ATOMIC); if (!rss_key_buf_va) return -ENOMEM; @@ -2195,8 +2196,8 @@ int __enic_set_rsskey(struct enic *enic) sizeof(union vnic_rss_key)); spin_unlock_bh(&enic->devcmd_lock); - pci_free_consistent(enic->pdev, sizeof(union vnic_rss_key), - rss_key_buf_va, rss_key_buf_pa); + dma_free_coherent(&enic->pdev->dev, sizeof(union vnic_rss_key), + rss_key_buf_va, rss_key_buf_pa); return err; } @@ -2215,8 +2216,9 @@ static int enic_set_rsscpu(struct enic *enic, u8 rss_hash_bits) unsigned int i; int err; - rss_cpu_buf_va = pci_alloc_consistent(enic->pdev, - sizeof(union vnic_rss_cpu), &rss_cpu_buf_pa); + rss_cpu_buf_va = dma_alloc_coherent(&enic->pdev->dev, + sizeof(union vnic_rss_cpu), + &rss_cpu_buf_pa, GFP_ATOMIC); if (!rss_cpu_buf_va) return -ENOMEM; @@ -2229,8 +2231,8 @@ static int enic_set_rsscpu(struct enic *enic, u8 rss_hash_bits) sizeof(union vnic_rss_cpu)); spin_unlock_bh(&enic->devcmd_lock); - pci_free_consistent(enic->pdev, sizeof(union vnic_rss_cpu), - rss_cpu_buf_va, rss_cpu_buf_pa); + dma_free_coherent(&enic->pdev->dev, sizeof(union vnic_rss_cpu), + rss_cpu_buf_va, rss_cpu_buf_pa); return err; } @@ -2527,13 +2529,15 @@ static void enic_dev_deinit(struct enic *enic) { unsigned int i; - for (i = 0; i < enic->rq_count; i++) { - napi_hash_del(&enic->napi[i]); - netif_napi_del(&enic->napi[i]); - } + for (i = 0; i < enic->rq_count; i++) + __netif_napi_del(&enic->napi[i]); + if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX) for (i = 0; i < enic->wq_count; i++) - netif_napi_del(&enic->napi[enic_cq_wq(enic, i)]); + __netif_napi_del(&enic->napi[enic_cq_wq(enic, i)]); + + /* observe RCU grace period after __netif_napi_del() calls */ + synchronize_net(); enic_free_vnic_resources(enic); enic_clear_intr_mode(enic); @@ -2699,21 +2703,21 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * fail to 32-bit. */ - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(47)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(47)); if (err) { - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { dev_err(dev, "No usable DMA configuration, aborting\n"); goto err_out_release_regions; } - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { dev_err(dev, "Unable to obtain %u-bit DMA " "for consistent allocations, aborting\n", 32); goto err_out_release_regions; } } else { - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(47)); + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(47)); if (err) { dev_err(dev, "Unable to obtain %u-bit DMA " "for consistent allocations, aborting\n", 47); diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c index 901e44b0b795..45015931b335 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_dev.c +++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c @@ -193,9 +193,10 @@ int vnic_dev_alloc_desc_ring(struct vnic_dev *vdev, struct vnic_dev_ring *ring, { vnic_dev_desc_ring_size(ring, desc_count, desc_size); - ring->descs_unaligned = pci_alloc_consistent(vdev->pdev, - ring->size_unaligned, - &ring->base_addr_unaligned); + ring->descs_unaligned = dma_alloc_coherent(&vdev->pdev->dev, + ring->size_unaligned, + &ring->base_addr_unaligned, + GFP_KERNEL); if (!ring->descs_unaligned) { vdev_err(vdev, "Failed to allocate ring (size=%d), aborting\n", @@ -218,10 +219,9 @@ int vnic_dev_alloc_desc_ring(struct vnic_dev *vdev, struct vnic_dev_ring *ring, void vnic_dev_free_desc_ring(struct vnic_dev *vdev, struct vnic_dev_ring *ring) { if (ring->descs) { - pci_free_consistent(vdev->pdev, - ring->size_unaligned, - ring->descs_unaligned, - ring->base_addr_unaligned); + dma_free_coherent(&vdev->pdev->dev, ring->size_unaligned, + ring->descs_unaligned, + ring->base_addr_unaligned); ring->descs = NULL; } } @@ -551,9 +551,9 @@ int vnic_dev_fw_info(struct vnic_dev *vdev, int err = 0; if (!vdev->fw_info) { - vdev->fw_info = pci_zalloc_consistent(vdev->pdev, - sizeof(struct vnic_devcmd_fw_info), - &vdev->fw_info_pa); + vdev->fw_info = dma_alloc_coherent(&vdev->pdev->dev, + sizeof(struct vnic_devcmd_fw_info), + &vdev->fw_info_pa, GFP_ATOMIC); if (!vdev->fw_info) return -ENOMEM; @@ -603,8 +603,9 @@ int vnic_dev_stats_dump(struct vnic_dev *vdev, struct vnic_stats **stats) int wait = 1000; if (!vdev->stats) { - vdev->stats = pci_alloc_consistent(vdev->pdev, - sizeof(struct vnic_stats), &vdev->stats_pa); + vdev->stats = dma_alloc_coherent(&vdev->pdev->dev, + sizeof(struct vnic_stats), + &vdev->stats_pa, GFP_ATOMIC); if (!vdev->stats) return -ENOMEM; } @@ -852,9 +853,9 @@ int vnic_dev_notify_set(struct vnic_dev *vdev, u16 intr) return -EINVAL; } - notify_addr = pci_alloc_consistent(vdev->pdev, - sizeof(struct vnic_devcmd_notify), - ¬ify_pa); + notify_addr = dma_alloc_coherent(&vdev->pdev->dev, + sizeof(struct vnic_devcmd_notify), + ¬ify_pa, GFP_ATOMIC); if (!notify_addr) return -ENOMEM; @@ -882,10 +883,9 @@ static int vnic_dev_notify_unsetcmd(struct vnic_dev *vdev) int vnic_dev_notify_unset(struct vnic_dev *vdev) { if (vdev->notify) { - pci_free_consistent(vdev->pdev, - sizeof(struct vnic_devcmd_notify), - vdev->notify, - vdev->notify_pa); + dma_free_coherent(&vdev->pdev->dev, + sizeof(struct vnic_devcmd_notify), + vdev->notify, vdev->notify_pa); } return vnic_dev_notify_unsetcmd(vdev); @@ -1046,18 +1046,17 @@ void vnic_dev_unregister(struct vnic_dev *vdev) { if (vdev) { if (vdev->notify) - pci_free_consistent(vdev->pdev, - sizeof(struct vnic_devcmd_notify), - vdev->notify, - vdev->notify_pa); + dma_free_coherent(&vdev->pdev->dev, + sizeof(struct vnic_devcmd_notify), + vdev->notify, vdev->notify_pa); if (vdev->stats) - pci_free_consistent(vdev->pdev, - sizeof(struct vnic_stats), - vdev->stats, vdev->stats_pa); + dma_free_coherent(&vdev->pdev->dev, + sizeof(struct vnic_stats), + vdev->stats, vdev->stats_pa); if (vdev->fw_info) - pci_free_consistent(vdev->pdev, - sizeof(struct vnic_devcmd_fw_info), - vdev->fw_info, vdev->fw_info_pa); + dma_free_coherent(&vdev->pdev->dev, + sizeof(struct vnic_devcmd_fw_info), + vdev->fw_info, vdev->fw_info_pa); if (vdev->devcmd2) vnic_dev_deinit_devcmd2(vdev); @@ -1127,7 +1126,7 @@ int vnic_dev_init_prov2(struct vnic_dev *vdev, u8 *buf, u32 len) void *prov_buf; int ret; - prov_buf = pci_alloc_consistent(vdev->pdev, len, &prov_pa); + prov_buf = dma_alloc_coherent(&vdev->pdev->dev, len, &prov_pa, GFP_ATOMIC); if (!prov_buf) return -ENOMEM; @@ -1137,7 +1136,7 @@ int vnic_dev_init_prov2(struct vnic_dev *vdev, u8 *buf, u32 len) ret = vnic_dev_cmd(vdev, CMD_INIT_PROV_INFO2, &a0, &a1, wait); - pci_free_consistent(vdev->pdev, len, prov_buf, prov_pa); + dma_free_coherent(&vdev->pdev->dev, len, prov_buf, prov_pa); return ret; } @@ -1217,7 +1216,8 @@ int vnic_dev_classifier(struct vnic_dev *vdev, u8 cmd, u16 *entry, tlv_size = sizeof(struct filter) + sizeof(struct filter_action) + 2 * sizeof(struct filter_tlv); - tlv_va = pci_alloc_consistent(vdev->pdev, tlv_size, &tlv_pa); + tlv_va = dma_alloc_coherent(&vdev->pdev->dev, tlv_size, + &tlv_pa, GFP_ATOMIC); if (!tlv_va) return -ENOMEM; tlv = tlv_va; @@ -1240,7 +1240,7 @@ int vnic_dev_classifier(struct vnic_dev *vdev, u8 cmd, u16 *entry, ret = vnic_dev_cmd(vdev, CMD_ADD_FILTER, &a0, &a1, wait); *entry = (u16)a0; - pci_free_consistent(vdev->pdev, tlv_size, tlv_va, tlv_pa); + dma_free_coherent(&vdev->pdev->dev, tlv_size, tlv_va, tlv_pa); } else if (cmd == CLSF_DEL) { a0 = *entry; ret = vnic_dev_cmd(vdev, CMD_DEL_FILTER, &a0, &a1, wait); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 66e67b24a887..9dcf47f576c6 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -539,12 +539,6 @@ static int gmac_init(struct net_device *netdev) return 0; } -static void gmac_uninit(struct net_device *netdev) -{ - if (netdev->phydev) - phy_disconnect(netdev->phydev); -} - static int gmac_setup_txqs(struct net_device *netdev) { struct gemini_ethernet_port *port = netdev_priv(netdev); @@ -1768,15 +1762,6 @@ static int gmac_open(struct net_device *netdev) struct gemini_ethernet_port *port = netdev_priv(netdev); int err; - if (!netdev->phydev) { - err = gmac_setup_phy(netdev); - if (err) { - netif_err(port, ifup, netdev, - "PHY init failed: %d\n", err); - return err; - } - } - err = request_irq(netdev->irq, gmac_irq, IRQF_SHARED, netdev->name, netdev); if (err) { @@ -2209,7 +2194,6 @@ static void gmac_get_drvinfo(struct net_device *netdev, static const struct net_device_ops gmac_351x_ops = { .ndo_init = gmac_init, - .ndo_uninit = gmac_uninit, .ndo_open = gmac_open, .ndo_stop = gmac_stop, .ndo_start_xmit = gmac_start_xmit, @@ -2295,8 +2279,10 @@ static irqreturn_t gemini_port_irq(int irq, void *data) static void gemini_port_remove(struct gemini_ethernet_port *port) { - if (port->netdev) + if (port->netdev) { + phy_disconnect(port->netdev->phydev); unregister_netdev(port->netdev); + } clk_disable_unprepare(port->pclk); geth_cleanup_freeq(port->geth); } @@ -2389,7 +2375,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) dev_info(dev, "probe %s ID %d\n", dev_name(dev), id); - netdev = alloc_etherdev_mq(sizeof(*port), TX_QUEUE_NUM); + netdev = devm_alloc_etherdev_mqs(dev, sizeof(*port), TX_QUEUE_NUM, TX_QUEUE_NUM); if (!netdev) { dev_err(dev, "Can't allocate ethernet device #%d\n", id); return -ENOMEM; @@ -2446,8 +2432,8 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->reset = devm_reset_control_get_exclusive(dev, NULL); if (IS_ERR(port->reset)) { dev_err(dev, "no reset\n"); - clk_disable_unprepare(port->pclk); - return PTR_ERR(port->reset); + ret = PTR_ERR(port->reset); + goto unprepare; } reset_control_reset(port->reset); usleep_range(100, 500); @@ -2502,26 +2488,28 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) IRQF_SHARED, port_names[port->id], port); + if (ret) + goto unprepare; + + ret = gmac_setup_phy(netdev); if (ret) { - clk_disable_unprepare(port->pclk); - return ret; + netdev_err(netdev, + "PHY init failed\n"); + goto unprepare; } ret = register_netdev(netdev); - if (!ret) { - netdev_info(netdev, - "irq %d, DMA @ 0x%pap, GMAC @ 0x%pap\n", - port->irq, &dmares->start, - &gmacres->start); - ret = gmac_setup_phy(netdev); - if (ret) - netdev_info(netdev, - "PHY init failed, deferring to ifup time\n"); - return 0; - } + if (ret) + goto unprepare; - port->netdev = NULL; - free_netdev(netdev); + netdev_info(netdev, + "irq %d, DMA @ 0x%pap, GMAC @ 0x%pap\n", + port->irq, &dmares->start, + &gmacres->start); + return 0; + +unprepare: + clk_disable_unprepare(port->pclk); return ret; } @@ -2530,7 +2518,7 @@ static int gemini_ethernet_port_remove(struct platform_device *pdev) struct gemini_ethernet_port *port = platform_get_drvdata(pdev); gemini_port_remove(port); - free_netdev(port->netdev); + return 0; } diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 7f7705138262..5c6c8c5ec747 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -385,7 +385,7 @@ static void dm9000_set_io(struct board_info *db, int byte_width) case 3: dev_dbg(db->dev, ": 3 byte IO, falling back to 16bit\n"); - /* fall through */ + fallthrough; case 2: db->dumpblk = dm9000_dumpblk_16bit; db->outblk = dm9000_outblk_16bit; diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 0ccd9994ad45..f9dd1aa9f2da 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -3203,7 +3203,7 @@ srom_map_media(struct net_device *dev) case SROM_10BASETF: if (!lp->params.fdx) return -1; lp->fdx = true; - /* fall through */ + fallthrough; case SROM_10BASET: if (lp->params.fdx && !lp->fdx) return -1; @@ -3225,7 +3225,7 @@ srom_map_media(struct net_device *dev) case SROM_100BASETF: if (!lp->params.fdx) return -1; lp->fdx = true; - /* fall through */ + fallthrough; case SROM_100BASET: if (lp->params.fdx && !lp->fdx) return -1; @@ -3239,7 +3239,7 @@ srom_map_media(struct net_device *dev) case SROM_100BASEFF: if (!lp->params.fdx) return -1; lp->fdx = true; - /* fall through */ + fallthrough; case SROM_100BASEF: if (lp->params.fdx && !lp->fdx) return -1; diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 9db23527275a..3a8659c5da06 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -911,7 +911,7 @@ static int private_ioctl (struct net_device *dev, struct ifreq *rq, int cmd) data->phy_id = 1; else return -ENODEV; - /* Fall through */ + fallthrough; case SIOCGMIIREG: /* Read MII PHY register. */ if (data->phy_id == 32 && (tp->flags & HAS_NWAY)) { diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 5dcc66f60144..5a43be327f58 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -1443,7 +1443,7 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) switch(cmd) { case SIOCGMIIPHY: /* Get address of MII PHY in use. */ data->phy_id = ((struct netdev_private *)netdev_priv(dev))->phys[0] & 0x1f; - /* Fall Through */ + fallthrough; case SIOCGMIIREG: /* Read MII PHY register. */ spin_lock_irq(&np->lock); diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index be6d8a9ada27..e8e563d6e86b 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -7,7 +7,6 @@ */ -#define DRV_NAME "DL2000/TC902x-based linux driver" #include "dl2k.h" #include <linux/dma-mapping.h> diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index db98274501a0..3143df9a398c 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -508,7 +508,7 @@ static netdev_tx_t dnet_start_xmit(struct sk_buff *skb, struct net_device *dev) struct dnet *bp = netdev_priv(dev); u32 tx_status, irq_enable; - unsigned int len, i, tx_cmd, wrsz; + unsigned int i, tx_cmd, wrsz; unsigned long flags; unsigned int *bufp; @@ -518,9 +518,6 @@ static netdev_tx_t dnet_start_xmit(struct sk_buff *skb, struct net_device *dev) skb->len, skb->head, skb->data); dnet_print_skb(skb); - /* frame size (words) */ - len = (skb->len + 3) >> 2; - spin_lock_irqsave(&bp->lock, flags); tx_status = dnet_readl(bp, TX_STATUS); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index d6ed1d943762..99cc1c46fb30 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -571,7 +571,7 @@ static u32 convert_to_et_setting(struct be_adapter *adapter, u32 if_speeds) break; } } - /* fall through */ + fallthrough; case PHY_TYPE_SFP_PLUS_10GB: case PHY_TYPE_XFP_10GB: case PHY_TYPE_SFP_1GB: diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 43570f4911ea..fdff3b4723ba 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -945,7 +945,7 @@ static void dpaa_fq_setup(struct dpaa_priv *priv, break; case FQ_TYPE_TX_CONF_MQ: priv->conf_fqs[conf_cnt++] = &fq->fq_base; - /* fall through */ + fallthrough; case FQ_TYPE_TX_CONFIRM: dpaa_setup_ingress(priv, fq, &fq_cbs->tx_defq); break; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 9db2a02fb531..1268996b7030 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -375,7 +375,7 @@ static int dpaa_get_hash_opts(struct net_device *dev, case UDP_V6_FLOW: if (priv->keygen_in_use) cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - /* Fall through */ + fallthrough; case IPV4_FLOW: case IPV6_FLOW: case SCTP_V4_FLOW: diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c index 83dee575c2fa..84de0644168d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c @@ -17,12 +17,12 @@ static int dpaa2_eth_dcbnl_ieee_getpfc(struct net_device *net_dev, return 0; } -static inline bool is_prio_enabled(u8 pfc_en, u8 tc) +static inline bool dpaa2_eth_is_prio_enabled(u8 pfc_en, u8 tc) { return !!(pfc_en & (1 << tc)); } -static int set_pfc_cn(struct dpaa2_eth_priv *priv, u8 pfc_en) +static int dpaa2_eth_set_pfc_cn(struct dpaa2_eth_priv *priv, u8 pfc_en) { struct dpni_congestion_notification_cfg cfg = {0}; int i, err; @@ -33,7 +33,7 @@ static int set_pfc_cn(struct dpaa2_eth_priv *priv, u8 pfc_en) cfg.message_ctx = 0ULL; for (i = 0; i < dpaa2_eth_tc_count(priv); i++) { - if (is_prio_enabled(pfc_en, i)) { + if (dpaa2_eth_is_prio_enabled(pfc_en, i)) { cfg.threshold_entry = DPAA2_ETH_CN_THRESH_ENTRY(priv); cfg.threshold_exit = DPAA2_ETH_CN_THRESH_EXIT(priv); } else { @@ -93,7 +93,7 @@ static int dpaa2_eth_dcbnl_ieee_setpfc(struct net_device *net_dev, } /* Configure congestion notifications for the enabled priorities */ - err = set_pfc_cn(priv, pfc->pfc_en); + err = dpaa2_eth_set_pfc_cn(priv, pfc->pfc_en); if (err) return err; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 457106e761be..ceaf76158e23 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -40,9 +40,9 @@ static void *dpaa2_iova_to_virt(struct iommu_domain *domain, return phys_to_virt(phys_addr); } -static void validate_rx_csum(struct dpaa2_eth_priv *priv, - u32 fd_status, - struct sk_buff *skb) +static void dpaa2_eth_validate_rx_csum(struct dpaa2_eth_priv *priv, + u32 fd_status, + struct sk_buff *skb) { skb_checksum_none_assert(skb); @@ -62,9 +62,9 @@ static void validate_rx_csum(struct dpaa2_eth_priv *priv, /* Free a received FD. * Not to be used for Tx conf FDs or on any other paths. */ -static void free_rx_fd(struct dpaa2_eth_priv *priv, - const struct dpaa2_fd *fd, - void *vaddr) +static void dpaa2_eth_free_rx_fd(struct dpaa2_eth_priv *priv, + const struct dpaa2_fd *fd, + void *vaddr) { struct device *dev = priv->net_dev->dev.parent; dma_addr_t addr = dpaa2_fd_get_addr(fd); @@ -100,9 +100,9 @@ free_buf: } /* Build a linear skb based on a single-buffer frame descriptor */ -static struct sk_buff *build_linear_skb(struct dpaa2_eth_channel *ch, - const struct dpaa2_fd *fd, - void *fd_vaddr) +static struct sk_buff *dpaa2_eth_build_linear_skb(struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, + void *fd_vaddr) { struct sk_buff *skb = NULL; u16 fd_offset = dpaa2_fd_get_offset(fd); @@ -121,9 +121,9 @@ static struct sk_buff *build_linear_skb(struct dpaa2_eth_channel *ch, } /* Build a non linear (fragmented) skb based on a S/G table */ -static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - struct dpaa2_sg_entry *sgt) +static struct sk_buff *dpaa2_eth_build_frag_skb(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_sg_entry *sgt) { struct sk_buff *skb = NULL; struct device *dev = priv->net_dev->dev.parent; @@ -204,7 +204,8 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv, /* Free buffers acquired from the buffer pool or which were meant to * be released in the pool */ -static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count) +static void dpaa2_eth_free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, + int count) { struct device *dev = priv->net_dev->dev.parent; void *vaddr; @@ -218,9 +219,9 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count) } } -static void xdp_release_buf(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - dma_addr_t addr) +static void dpaa2_eth_xdp_release_buf(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + dma_addr_t addr) { int retries = 0; int err; @@ -238,7 +239,7 @@ static void xdp_release_buf(struct dpaa2_eth_priv *priv, } if (err) { - free_bufs(priv, ch->xdp.drop_bufs, ch->xdp.drop_cnt); + dpaa2_eth_free_bufs(priv, ch->xdp.drop_bufs, ch->xdp.drop_cnt); ch->buf_count -= ch->xdp.drop_cnt; } @@ -274,9 +275,9 @@ static int dpaa2_eth_xdp_flush(struct dpaa2_eth_priv *priv, return total_enqueued; } -static void xdp_tx_flush(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - struct dpaa2_eth_fq *fq) +static void dpaa2_eth_xdp_tx_flush(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_eth_fq *fq) { struct rtnl_link_stats64 *percpu_stats; struct dpaa2_fd *fds; @@ -295,17 +296,17 @@ static void xdp_tx_flush(struct dpaa2_eth_priv *priv, ch->stats.xdp_tx++; } for (i = enqueued; i < fq->xdp_tx_fds.num; i++) { - xdp_release_buf(priv, ch, dpaa2_fd_get_addr(&fds[i])); + dpaa2_eth_xdp_release_buf(priv, ch, dpaa2_fd_get_addr(&fds[i])); percpu_stats->tx_errors++; ch->stats.xdp_tx_err++; } fq->xdp_tx_fds.num = 0; } -static void xdp_enqueue(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - struct dpaa2_fd *fd, - void *buf_start, u16 queue_id) +static void dpaa2_eth_xdp_enqueue(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_fd *fd, + void *buf_start, u16 queue_id) { struct dpaa2_faead *faead; struct dpaa2_fd *dest_fd; @@ -333,13 +334,13 @@ static void xdp_enqueue(struct dpaa2_eth_priv *priv, if (fq->xdp_tx_fds.num < DEV_MAP_BULK_SIZE) return; - xdp_tx_flush(priv, ch, fq); + dpaa2_eth_xdp_tx_flush(priv, ch, fq); } -static u32 run_xdp(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - struct dpaa2_eth_fq *rx_fq, - struct dpaa2_fd *fd, void *vaddr) +static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_eth_fq *rx_fq, + struct dpaa2_fd *fd, void *vaddr) { dma_addr_t addr = dpaa2_fd_get_addr(fd); struct bpf_prog *xdp_prog; @@ -372,16 +373,16 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv, case XDP_PASS: break; case XDP_TX: - xdp_enqueue(priv, ch, fd, vaddr, rx_fq->flowid); + dpaa2_eth_xdp_enqueue(priv, ch, fd, vaddr, rx_fq->flowid); break; default: bpf_warn_invalid_xdp_action(xdp_act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act); - /* fall through */ + fallthrough; case XDP_DROP: - xdp_release_buf(priv, ch, addr); + dpaa2_eth_xdp_release_buf(priv, ch, addr); ch->stats.xdp_drop++; break; case XDP_REDIRECT: @@ -441,7 +442,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, percpu_extras = this_cpu_ptr(priv->percpu_extras); if (fd_format == dpaa2_fd_single) { - xdp_act = run_xdp(priv, ch, fq, (struct dpaa2_fd *)fd, vaddr); + xdp_act = dpaa2_eth_run_xdp(priv, ch, fq, (struct dpaa2_fd *)fd, vaddr); if (xdp_act != XDP_PASS) { percpu_stats->rx_packets++; percpu_stats->rx_bytes += dpaa2_fd_get_len(fd); @@ -450,13 +451,13 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); - skb = build_linear_skb(ch, fd, vaddr); + skb = dpaa2_eth_build_linear_skb(ch, fd, vaddr); } else if (fd_format == dpaa2_fd_sg) { WARN_ON(priv->xdp_prog); dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); - skb = build_frag_skb(priv, ch, buf_data); + skb = dpaa2_eth_build_frag_skb(priv, ch, buf_data); free_pages((unsigned long)vaddr, 0); percpu_extras->rx_sg_frames++; percpu_extras->rx_sg_bytes += dpaa2_fd_get_len(fd); @@ -485,7 +486,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, /* Check if we need to validate the L4 csum */ if (likely(dpaa2_fd_get_frc(fd) & DPAA2_FD_FRC_FASV)) { status = le32_to_cpu(fas->status); - validate_rx_csum(priv, status, skb); + dpaa2_eth_validate_rx_csum(priv, status, skb); } skb->protocol = eth_type_trans(skb, priv->net_dev); @@ -499,7 +500,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, return; err_build_skb: - free_rx_fd(priv, fd, vaddr); + dpaa2_eth_free_rx_fd(priv, fd, vaddr); err_frame_format: percpu_stats->rx_dropped++; } @@ -510,8 +511,8 @@ err_frame_format: * * Observance of NAPI budget is not our concern, leaving that to the caller. */ -static int consume_frames(struct dpaa2_eth_channel *ch, - struct dpaa2_eth_fq **src) +static int dpaa2_eth_consume_frames(struct dpaa2_eth_channel *ch, + struct dpaa2_eth_fq **src) { struct dpaa2_eth_priv *priv = ch->priv; struct dpaa2_eth_fq *fq = NULL; @@ -560,7 +561,7 @@ static int consume_frames(struct dpaa2_eth_channel *ch, } /* Configure the egress frame annotation for timestamp update */ -static void enable_tx_tstamp(struct dpaa2_fd *fd, void *buf_start) +static void dpaa2_eth_enable_tx_tstamp(struct dpaa2_fd *fd, void *buf_start) { struct dpaa2_faead *faead; u32 ctrl, frc; @@ -582,9 +583,9 @@ static void enable_tx_tstamp(struct dpaa2_fd *fd, void *buf_start) } /* Create a frame descriptor based on a fragmented skb */ -static int build_sg_fd(struct dpaa2_eth_priv *priv, - struct sk_buff *skb, - struct dpaa2_fd *fd) +static int dpaa2_eth_build_sg_fd(struct dpaa2_eth_priv *priv, + struct sk_buff *skb, + struct dpaa2_fd *fd) { struct device *dev = priv->net_dev->dev.parent; void *sgt_buf = NULL; @@ -673,7 +674,7 @@ static int build_sg_fd(struct dpaa2_eth_priv *priv, dpaa2_fd_set_ctrl(fd, FD_CTRL_PTA); if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) - enable_tx_tstamp(fd, sgt_buf); + dpaa2_eth_enable_tx_tstamp(fd, sgt_buf); return 0; @@ -692,9 +693,9 @@ dma_map_sg_failed: * enough for the HW requirements, thus instead of realloc-ing the skb we * create a SG frame descriptor with only one entry. */ -static int build_sg_fd_single_buf(struct dpaa2_eth_priv *priv, - struct sk_buff *skb, - struct dpaa2_fd *fd) +static int dpaa2_eth_build_sg_fd_single_buf(struct dpaa2_eth_priv *priv, + struct sk_buff *skb, + struct dpaa2_fd *fd) { struct device *dev = priv->net_dev->dev.parent; struct dpaa2_eth_sgt_cache *sgt_cache; @@ -751,7 +752,7 @@ static int build_sg_fd_single_buf(struct dpaa2_eth_priv *priv, dpaa2_fd_set_ctrl(fd, FD_CTRL_PTA); if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) - enable_tx_tstamp(fd, sgt_buf); + dpaa2_eth_enable_tx_tstamp(fd, sgt_buf); return 0; @@ -767,9 +768,9 @@ data_map_failed: } /* Create a frame descriptor based on a linear skb */ -static int build_single_fd(struct dpaa2_eth_priv *priv, - struct sk_buff *skb, - struct dpaa2_fd *fd) +static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv, + struct sk_buff *skb, + struct dpaa2_fd *fd) { struct device *dev = priv->net_dev->dev.parent; u8 *buffer_start, *aligned_start; @@ -807,7 +808,7 @@ static int build_single_fd(struct dpaa2_eth_priv *priv, dpaa2_fd_set_ctrl(fd, FD_CTRL_PTA); if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) - enable_tx_tstamp(fd, buffer_start); + dpaa2_eth_enable_tx_tstamp(fd, buffer_start); return 0; } @@ -819,9 +820,9 @@ static int build_single_fd(struct dpaa2_eth_priv *priv, * This can be called either from dpaa2_eth_tx_conf() or on the error path of * dpaa2_eth_tx(). */ -static void free_tx_fd(const struct dpaa2_eth_priv *priv, - struct dpaa2_eth_fq *fq, - const struct dpaa2_fd *fd, bool in_napi) +static void dpaa2_eth_free_tx_fd(const struct dpaa2_eth_priv *priv, + struct dpaa2_eth_fq *fq, + const struct dpaa2_fd *fd, bool in_napi) { struct device *dev = priv->net_dev->dev.parent; dma_addr_t fd_addr, sg_addr; @@ -954,17 +955,17 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) memset(&fd, 0, sizeof(fd)); if (skb_is_nonlinear(skb)) { - err = build_sg_fd(priv, skb, &fd); + err = dpaa2_eth_build_sg_fd(priv, skb, &fd); percpu_extras->tx_sg_frames++; percpu_extras->tx_sg_bytes += skb->len; } else if (skb_headroom(skb) < needed_headroom) { - err = build_sg_fd_single_buf(priv, skb, &fd); + err = dpaa2_eth_build_sg_fd_single_buf(priv, skb, &fd); percpu_extras->tx_sg_frames++; percpu_extras->tx_sg_bytes += skb->len; percpu_extras->tx_converted_sg_frames++; percpu_extras->tx_converted_sg_bytes += skb->len; } else { - err = build_single_fd(priv, skb, &fd); + err = dpaa2_eth_build_single_fd(priv, skb, &fd); } if (unlikely(err)) { @@ -1010,7 +1011,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) if (unlikely(err < 0)) { percpu_stats->tx_errors++; /* Clean up everything, including freeing the skb */ - free_tx_fd(priv, fq, &fd, false); + dpaa2_eth_free_tx_fd(priv, fq, &fd, false); netdev_tx_completed_queue(nq, 1, fd_len); } else { percpu_stats->tx_packets++; @@ -1045,7 +1046,7 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv, /* Check frame errors in the FD field */ fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK; - free_tx_fd(priv, fq, fd, true); + dpaa2_eth_free_tx_fd(priv, fq, fd, true); if (likely(!fd_errors)) return; @@ -1059,7 +1060,7 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv, percpu_stats->tx_errors++; } -static int set_rx_csum(struct dpaa2_eth_priv *priv, bool enable) +static int dpaa2_eth_set_rx_csum(struct dpaa2_eth_priv *priv, bool enable) { int err; @@ -1082,7 +1083,7 @@ static int set_rx_csum(struct dpaa2_eth_priv *priv, bool enable) return 0; } -static int set_tx_csum(struct dpaa2_eth_priv *priv, bool enable) +static int dpaa2_eth_set_tx_csum(struct dpaa2_eth_priv *priv, bool enable) { int err; @@ -1106,8 +1107,8 @@ static int set_tx_csum(struct dpaa2_eth_priv *priv, bool enable) /* Perform a single release command to add buffers * to the specified buffer pool */ -static int add_bufs(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, u16 bpid) +static int dpaa2_eth_add_bufs(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, u16 bpid) { struct device *dev = priv->net_dev->dev.parent; u64 buf_array[DPAA2_ETH_BUFS_PER_CMD]; @@ -1155,7 +1156,7 @@ release_bufs: * not much else we can do about it */ if (err) { - free_bufs(priv, buf_array, i); + dpaa2_eth_free_bufs(priv, buf_array, i); return 0; } @@ -1173,7 +1174,7 @@ err_alloc: return 0; } -static int seed_pool(struct dpaa2_eth_priv *priv, u16 bpid) +static int dpaa2_eth_seed_pool(struct dpaa2_eth_priv *priv, u16 bpid) { int i, j; int new_count; @@ -1181,7 +1182,7 @@ static int seed_pool(struct dpaa2_eth_priv *priv, u16 bpid) for (j = 0; j < priv->num_channels; j++) { for (i = 0; i < DPAA2_ETH_NUM_BUFS; i += DPAA2_ETH_BUFS_PER_CMD) { - new_count = add_bufs(priv, priv->channel[j], bpid); + new_count = dpaa2_eth_add_bufs(priv, priv->channel[j], bpid); priv->channel[j]->buf_count += new_count; if (new_count < DPAA2_ETH_BUFS_PER_CMD) { @@ -1197,7 +1198,7 @@ static int seed_pool(struct dpaa2_eth_priv *priv, u16 bpid) * Drain the specified number of buffers from the DPNI's private buffer pool. * @count must not exceeed DPAA2_ETH_BUFS_PER_CMD */ -static void drain_bufs(struct dpaa2_eth_priv *priv, int count) +static void dpaa2_eth_drain_bufs(struct dpaa2_eth_priv *priv, int count) { u64 buf_array[DPAA2_ETH_BUFS_PER_CMD]; int retries = 0; @@ -1213,17 +1214,17 @@ static void drain_bufs(struct dpaa2_eth_priv *priv, int count) netdev_err(priv->net_dev, "dpaa2_io_service_acquire() failed\n"); return; } - free_bufs(priv, buf_array, ret); + dpaa2_eth_free_bufs(priv, buf_array, ret); retries = 0; } while (ret); } -static void drain_pool(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_drain_pool(struct dpaa2_eth_priv *priv) { int i; - drain_bufs(priv, DPAA2_ETH_BUFS_PER_CMD); - drain_bufs(priv, 1); + dpaa2_eth_drain_bufs(priv, DPAA2_ETH_BUFS_PER_CMD); + dpaa2_eth_drain_bufs(priv, 1); for (i = 0; i < priv->num_channels; i++) priv->channel[i]->buf_count = 0; @@ -1232,9 +1233,9 @@ static void drain_pool(struct dpaa2_eth_priv *priv) /* Function is called from softirq context only, so we don't need to guard * the access to percpu count */ -static int refill_pool(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - u16 bpid) +static int dpaa2_eth_refill_pool(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + u16 bpid) { int new_count; @@ -1242,7 +1243,7 @@ static int refill_pool(struct dpaa2_eth_priv *priv, return 0; do { - new_count = add_bufs(priv, ch, bpid); + new_count = dpaa2_eth_add_bufs(priv, ch, bpid); if (unlikely(!new_count)) { /* Out of memory; abort for now, we'll try later on */ break; @@ -1272,7 +1273,7 @@ static void dpaa2_eth_sgt_cache_drain(struct dpaa2_eth_priv *priv) } } -static int pull_channel(struct dpaa2_eth_channel *ch) +static int dpaa2_eth_pull_channel(struct dpaa2_eth_channel *ch) { int err; int dequeues = -1; @@ -1319,14 +1320,14 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget) ch->rx_list = &rx_list; do { - err = pull_channel(ch); + err = dpaa2_eth_pull_channel(ch); if (unlikely(err)) break; /* Refill pool if appropriate */ - refill_pool(priv, ch, priv->bpid); + dpaa2_eth_refill_pool(priv, ch, priv->bpid); - store_cleaned = consume_frames(ch, &fq); + store_cleaned = dpaa2_eth_consume_frames(ch, &fq); if (store_cleaned <= 0) break; if (fq->type == DPAA2_RX_FQ) { @@ -1375,12 +1376,12 @@ out: if (ch->xdp.res & XDP_REDIRECT) xdp_do_flush_map(); else if (rx_cleaned && ch->xdp.res & XDP_TX) - xdp_tx_flush(priv, ch, &priv->fq[flowid]); + dpaa2_eth_xdp_tx_flush(priv, ch, &priv->fq[flowid]); return work_done; } -static void enable_ch_napi(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_enable_ch_napi(struct dpaa2_eth_priv *priv) { struct dpaa2_eth_channel *ch; int i; @@ -1391,7 +1392,7 @@ static void enable_ch_napi(struct dpaa2_eth_priv *priv) } } -static void disable_ch_napi(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_disable_ch_napi(struct dpaa2_eth_priv *priv) { struct dpaa2_eth_channel *ch; int i; @@ -1465,7 +1466,7 @@ set_cgtd: priv->rx_cgtd_enabled = td.enable; } -static int link_state_update(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_link_state_update(struct dpaa2_eth_priv *priv) { struct dpni_link_state state = {0}; bool tx_pause; @@ -1517,7 +1518,7 @@ static int dpaa2_eth_open(struct net_device *net_dev) struct dpaa2_eth_priv *priv = netdev_priv(net_dev); int err; - err = seed_pool(priv, priv->bpid); + err = dpaa2_eth_seed_pool(priv, priv->bpid); if (err) { /* Not much to do; the buffer pool, though not filled up, * may still contain some buffers which would enable us @@ -1541,7 +1542,7 @@ static int dpaa2_eth_open(struct net_device *net_dev) */ netif_carrier_off(net_dev); } - enable_ch_napi(priv); + dpaa2_eth_enable_ch_napi(priv); err = dpni_enable(priv->mc_io, 0, priv->mc_token); if (err < 0) { @@ -1553,7 +1554,7 @@ static int dpaa2_eth_open(struct net_device *net_dev) /* If the DPMAC object has already processed the link up * interrupt, we have to learn the link state ourselves. */ - err = link_state_update(priv); + err = dpaa2_eth_link_state_update(priv); if (err < 0) { netdev_err(net_dev, "Can't update link state\n"); goto link_state_err; @@ -1566,13 +1567,13 @@ static int dpaa2_eth_open(struct net_device *net_dev) link_state_err: enable_err: - disable_ch_napi(priv); - drain_pool(priv); + dpaa2_eth_disable_ch_napi(priv); + dpaa2_eth_drain_pool(priv); return err; } /* Total number of in-flight frames on ingress queues */ -static u32 ingress_fq_count(struct dpaa2_eth_priv *priv) +static u32 dpaa2_eth_ingress_fq_count(struct dpaa2_eth_priv *priv) { struct dpaa2_eth_fq *fq; u32 fcnt = 0, bcnt = 0, total = 0; @@ -1591,13 +1592,13 @@ static u32 ingress_fq_count(struct dpaa2_eth_priv *priv) return total; } -static void wait_for_ingress_fq_empty(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_wait_for_ingress_fq_empty(struct dpaa2_eth_priv *priv) { int retries = 10; u32 pending; do { - pending = ingress_fq_count(priv); + pending = dpaa2_eth_ingress_fq_count(priv); if (pending) msleep(100); } while (pending && --retries); @@ -1605,7 +1606,7 @@ static void wait_for_ingress_fq_empty(struct dpaa2_eth_priv *priv) #define DPNI_TX_PENDING_VER_MAJOR 7 #define DPNI_TX_PENDING_VER_MINOR 13 -static void wait_for_egress_fq_empty(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_wait_for_egress_fq_empty(struct dpaa2_eth_priv *priv) { union dpni_statistics stats; int retries = 10; @@ -1651,7 +1652,7 @@ static int dpaa2_eth_stop(struct net_device *net_dev) * on WRIOP. After it finishes, wait until all remaining frames on Rx * and Tx conf queues are consumed on NAPI poll. */ - wait_for_egress_fq_empty(priv); + dpaa2_eth_wait_for_egress_fq_empty(priv); do { dpni_disable(priv->mc_io, 0, priv->mc_token); @@ -1667,11 +1668,11 @@ static int dpaa2_eth_stop(struct net_device *net_dev) */ } - wait_for_ingress_fq_empty(priv); - disable_ch_napi(priv); + dpaa2_eth_wait_for_ingress_fq_empty(priv); + dpaa2_eth_disable_ch_napi(priv); /* Empty the buffer pool */ - drain_pool(priv); + dpaa2_eth_drain_pool(priv); /* Empty the Scatter-Gather Buffer cache */ dpaa2_eth_sgt_cache_drain(priv); @@ -1725,8 +1726,8 @@ static void dpaa2_eth_get_stats(struct net_device *net_dev, /* Copy mac unicast addresses from @net_dev to @priv. * Its sole purpose is to make dpaa2_eth_set_rx_mode() more readable. */ -static void add_uc_hw_addr(const struct net_device *net_dev, - struct dpaa2_eth_priv *priv) +static void dpaa2_eth_add_uc_hw_addr(const struct net_device *net_dev, + struct dpaa2_eth_priv *priv) { struct netdev_hw_addr *ha; int err; @@ -1744,8 +1745,8 @@ static void add_uc_hw_addr(const struct net_device *net_dev, /* Copy mac multicast addresses from @net_dev to @priv * Its sole purpose is to make dpaa2_eth_set_rx_mode() more readable. */ -static void add_mc_hw_addr(const struct net_device *net_dev, - struct dpaa2_eth_priv *priv) +static void dpaa2_eth_add_mc_hw_addr(const struct net_device *net_dev, + struct dpaa2_eth_priv *priv) { struct netdev_hw_addr *ha; int err; @@ -1810,7 +1811,7 @@ static void dpaa2_eth_set_rx_mode(struct net_device *net_dev) err = dpni_clear_mac_filters(mc_io, 0, mc_token, 1, 0); if (err) netdev_warn(net_dev, "Can't clear uc filters\n"); - add_uc_hw_addr(net_dev, priv); + dpaa2_eth_add_uc_hw_addr(net_dev, priv); /* Finally, clear uc promisc and set mc promisc as requested. */ err = dpni_set_unicast_promisc(mc_io, 0, mc_token, 0); @@ -1833,8 +1834,8 @@ static void dpaa2_eth_set_rx_mode(struct net_device *net_dev) err = dpni_clear_mac_filters(mc_io, 0, mc_token, 1, 1); if (err) netdev_warn(net_dev, "Can't clear mac filters\n"); - add_mc_hw_addr(net_dev, priv); - add_uc_hw_addr(net_dev, priv); + dpaa2_eth_add_mc_hw_addr(net_dev, priv); + dpaa2_eth_add_uc_hw_addr(net_dev, priv); /* Now we can clear both ucast and mcast promisc, without risking * to drop legitimate frames anymore. @@ -1868,14 +1869,14 @@ static int dpaa2_eth_set_features(struct net_device *net_dev, if (changed & NETIF_F_RXCSUM) { enable = !!(features & NETIF_F_RXCSUM); - err = set_rx_csum(priv, enable); + err = dpaa2_eth_set_rx_csum(priv, enable); if (err) return err; } if (changed & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { enable = !!(features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)); - err = set_tx_csum(priv, enable); + err = dpaa2_eth_set_tx_csum(priv, enable); if (err) return err; } @@ -1944,7 +1945,7 @@ static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu) return true; } -static int set_rx_mfl(struct dpaa2_eth_priv *priv, int mtu, bool has_xdp) +static int dpaa2_eth_set_rx_mfl(struct dpaa2_eth_priv *priv, int mtu, bool has_xdp) { int mfl, err; @@ -1978,7 +1979,7 @@ static int dpaa2_eth_change_mtu(struct net_device *dev, int new_mtu) if (!xdp_mtu_valid(priv, new_mtu)) return -EINVAL; - err = set_rx_mfl(priv, new_mtu, true); + err = dpaa2_eth_set_rx_mfl(priv, new_mtu, true); if (err) return err; @@ -1987,7 +1988,7 @@ out: return 0; } -static int update_rx_buffer_headroom(struct dpaa2_eth_priv *priv, bool has_xdp) +static int dpaa2_eth_update_rx_buffer_headroom(struct dpaa2_eth_priv *priv, bool has_xdp) { struct dpni_buffer_layout buf_layout = {0}; int err; @@ -2013,7 +2014,7 @@ static int update_rx_buffer_headroom(struct dpaa2_eth_priv *priv, bool has_xdp) return 0; } -static int setup_xdp(struct net_device *dev, struct bpf_prog *prog) +static int dpaa2_eth_setup_xdp(struct net_device *dev, struct bpf_prog *prog) { struct dpaa2_eth_priv *priv = netdev_priv(dev); struct dpaa2_eth_channel *ch; @@ -2039,10 +2040,10 @@ static int setup_xdp(struct net_device *dev, struct bpf_prog *prog) * so we are sure no old format buffers will be used from now on. */ if (need_update) { - err = set_rx_mfl(priv, dev->mtu, !!prog); + err = dpaa2_eth_set_rx_mfl(priv, dev->mtu, !!prog); if (err) goto out_err; - err = update_rx_buffer_headroom(priv, !!prog); + err = dpaa2_eth_update_rx_buffer_headroom(priv, !!prog); if (err) goto out_err; } @@ -2079,7 +2080,7 @@ static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: - return setup_xdp(dev, xdp->prog); + return dpaa2_eth_setup_xdp(dev, xdp->prog); default: return -EINVAL; } @@ -2316,7 +2317,7 @@ static const struct net_device_ops dpaa2_eth_ops = { .ndo_setup_tc = dpaa2_eth_setup_tc, }; -static void cdan_cb(struct dpaa2_io_notification_ctx *ctx) +static void dpaa2_eth_cdan_cb(struct dpaa2_io_notification_ctx *ctx) { struct dpaa2_eth_channel *ch; @@ -2329,7 +2330,7 @@ static void cdan_cb(struct dpaa2_io_notification_ctx *ctx) } /* Allocate and configure a DPCON object */ -static struct fsl_mc_device *setup_dpcon(struct dpaa2_eth_priv *priv) +static struct fsl_mc_device *dpaa2_eth_setup_dpcon(struct dpaa2_eth_priv *priv) { struct fsl_mc_device *dpcon; struct device *dev = priv->net_dev->dev.parent; @@ -2373,16 +2374,15 @@ free: return ERR_PTR(err); } -static void free_dpcon(struct dpaa2_eth_priv *priv, - struct fsl_mc_device *dpcon) +static void dpaa2_eth_free_dpcon(struct dpaa2_eth_priv *priv, + struct fsl_mc_device *dpcon) { dpcon_disable(priv->mc_io, 0, dpcon->mc_handle); dpcon_close(priv->mc_io, 0, dpcon->mc_handle); fsl_mc_object_free(dpcon); } -static struct dpaa2_eth_channel * -alloc_channel(struct dpaa2_eth_priv *priv) +static struct dpaa2_eth_channel *dpaa2_eth_alloc_channel(struct dpaa2_eth_priv *priv) { struct dpaa2_eth_channel *channel; struct dpcon_attr attr; @@ -2393,7 +2393,7 @@ alloc_channel(struct dpaa2_eth_priv *priv) if (!channel) return NULL; - channel->dpcon = setup_dpcon(priv); + channel->dpcon = dpaa2_eth_setup_dpcon(priv); if (IS_ERR(channel->dpcon)) { err = PTR_ERR(channel->dpcon); goto err_setup; @@ -2413,23 +2413,23 @@ alloc_channel(struct dpaa2_eth_priv *priv) return channel; err_get_attr: - free_dpcon(priv, channel->dpcon); + dpaa2_eth_free_dpcon(priv, channel->dpcon); err_setup: kfree(channel); return ERR_PTR(err); } -static void free_channel(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *channel) +static void dpaa2_eth_free_channel(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *channel) { - free_dpcon(priv, channel->dpcon); + dpaa2_eth_free_dpcon(priv, channel->dpcon); kfree(channel); } /* DPIO setup: allocate and configure QBMan channels, setup core affinity * and register data availability notifications */ -static int setup_dpio(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_setup_dpio(struct dpaa2_eth_priv *priv) { struct dpaa2_io_notification_ctx *nctx; struct dpaa2_eth_channel *channel; @@ -2449,7 +2449,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv) cpumask_clear(&priv->dpio_cpumask); for_each_online_cpu(i) { /* Try to allocate a channel */ - channel = alloc_channel(priv); + channel = dpaa2_eth_alloc_channel(priv); if (IS_ERR_OR_NULL(channel)) { err = PTR_ERR_OR_ZERO(channel); if (err != -EPROBE_DEFER) @@ -2462,7 +2462,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv) nctx = &channel->nctx; nctx->is_cdan = 1; - nctx->cb = cdan_cb; + nctx->cb = dpaa2_eth_cdan_cb; nctx->id = channel->ch_id; nctx->desired_cpu = i; @@ -2510,14 +2510,14 @@ static int setup_dpio(struct dpaa2_eth_priv *priv) err_set_cdan: dpaa2_io_service_deregister(channel->dpio, nctx, dev); err_service_reg: - free_channel(priv, channel); + dpaa2_eth_free_channel(priv, channel); err_alloc_ch: if (err == -EPROBE_DEFER) { for (i = 0; i < priv->num_channels; i++) { channel = priv->channel[i]; nctx = &channel->nctx; dpaa2_io_service_deregister(channel->dpio, nctx, dev); - free_channel(priv, channel); + dpaa2_eth_free_channel(priv, channel); } priv->num_channels = 0; return err; @@ -2534,7 +2534,7 @@ err_alloc_ch: return 0; } -static void free_dpio(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_free_dpio(struct dpaa2_eth_priv *priv) { struct device *dev = priv->net_dev->dev.parent; struct dpaa2_eth_channel *ch; @@ -2544,12 +2544,12 @@ static void free_dpio(struct dpaa2_eth_priv *priv) for (i = 0; i < priv->num_channels; i++) { ch = priv->channel[i]; dpaa2_io_service_deregister(ch->dpio, &ch->nctx, dev); - free_channel(priv, ch); + dpaa2_eth_free_channel(priv, ch); } } -static struct dpaa2_eth_channel *get_affine_channel(struct dpaa2_eth_priv *priv, - int cpu) +static struct dpaa2_eth_channel *dpaa2_eth_get_affine_channel(struct dpaa2_eth_priv *priv, + int cpu) { struct device *dev = priv->net_dev->dev.parent; int i; @@ -2566,7 +2566,7 @@ static struct dpaa2_eth_channel *get_affine_channel(struct dpaa2_eth_priv *priv, return priv->channel[0]; } -static void set_fq_affinity(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_set_fq_affinity(struct dpaa2_eth_priv *priv) { struct device *dev = priv->net_dev->dev.parent; struct dpaa2_eth_fq *fq; @@ -2597,13 +2597,13 @@ static void set_fq_affinity(struct dpaa2_eth_priv *priv) default: dev_err(dev, "Unknown FQ type: %d\n", fq->type); } - fq->channel = get_affine_channel(priv, fq->target_cpu); + fq->channel = dpaa2_eth_get_affine_channel(priv, fq->target_cpu); } update_xps(priv); } -static void setup_fqs(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_setup_fqs(struct dpaa2_eth_priv *priv) { int i, j; @@ -2627,11 +2627,11 @@ static void setup_fqs(struct dpaa2_eth_priv *priv) } /* For each FQ, decide on which core to process incoming frames */ - set_fq_affinity(priv); + dpaa2_eth_set_fq_affinity(priv); } /* Allocate and configure one buffer pool for each interface */ -static int setup_dpbp(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_setup_dpbp(struct dpaa2_eth_priv *priv) { int err; struct fsl_mc_device *dpbp_dev; @@ -2690,15 +2690,15 @@ err_open: return err; } -static void free_dpbp(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_free_dpbp(struct dpaa2_eth_priv *priv) { - drain_pool(priv); + dpaa2_eth_drain_pool(priv); dpbp_disable(priv->mc_io, 0, priv->dpbp_dev->mc_handle); dpbp_close(priv->mc_io, 0, priv->dpbp_dev->mc_handle); fsl_mc_object_free(priv->dpbp_dev); } -static int set_buffer_layout(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_set_buffer_layout(struct dpaa2_eth_priv *priv) { struct device *dev = priv->net_dev->dev.parent; struct dpni_buffer_layout buf_layout = {0}; @@ -2815,7 +2815,7 @@ static inline int dpaa2_eth_enqueue_fq_multiple(struct dpaa2_eth_priv *priv, return 0; } -static void set_enqueue_mode(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_set_enqueue_mode(struct dpaa2_eth_priv *priv) { if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_ENQUEUE_FQID_VER_MAJOR, DPNI_ENQUEUE_FQID_VER_MINOR) < 0) @@ -2824,7 +2824,7 @@ static void set_enqueue_mode(struct dpaa2_eth_priv *priv) priv->enqueue = dpaa2_eth_enqueue_fq_multiple; } -static int set_pause(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_set_pause(struct dpaa2_eth_priv *priv) { struct device *dev = priv->net_dev->dev.parent; struct dpni_link_cfg link_cfg = {0}; @@ -2851,7 +2851,7 @@ static int set_pause(struct dpaa2_eth_priv *priv) return 0; } -static void update_tx_fqids(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_update_tx_fqids(struct dpaa2_eth_priv *priv) { struct dpni_queue_id qid = {0}; struct dpaa2_eth_fq *fq; @@ -2893,7 +2893,7 @@ out_err: } /* Configure ingress classification based on VLAN PCP */ -static int set_vlan_qos(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_set_vlan_qos(struct dpaa2_eth_priv *priv) { struct device *dev = priv->net_dev->dev.parent; struct dpkg_profile_cfg kg_cfg = {0}; @@ -3005,7 +3005,7 @@ out_free_tbl: } /* Configure the DPNI object this interface is associated with */ -static int setup_dpni(struct fsl_mc_device *ls_dev) +static int dpaa2_eth_setup_dpni(struct fsl_mc_device *ls_dev) { struct device *dev = &ls_dev->dev; struct dpaa2_eth_priv *priv; @@ -3053,20 +3053,20 @@ static int setup_dpni(struct fsl_mc_device *ls_dev) goto close; } - err = set_buffer_layout(priv); + err = dpaa2_eth_set_buffer_layout(priv); if (err) goto close; - set_enqueue_mode(priv); + dpaa2_eth_set_enqueue_mode(priv); /* Enable pause frame support */ if (dpaa2_eth_has_pause_support(priv)) { - err = set_pause(priv); + err = dpaa2_eth_set_pause(priv); if (err) goto close; } - err = set_vlan_qos(priv); + err = dpaa2_eth_set_vlan_qos(priv); if (err && err != -EOPNOTSUPP) goto close; @@ -3086,7 +3086,7 @@ close: return err; } -static void free_dpni(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_free_dpni(struct dpaa2_eth_priv *priv) { int err; @@ -3098,8 +3098,8 @@ static void free_dpni(struct dpaa2_eth_priv *priv) dpni_close(priv->mc_io, 0, priv->mc_token); } -static int setup_rx_flow(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_fq *fq) +static int dpaa2_eth_setup_rx_flow(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_fq *fq) { struct device *dev = priv->net_dev->dev.parent; struct dpni_queue queue; @@ -3150,8 +3150,8 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv, return 0; } -static int setup_tx_flow(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_fq *fq) +static int dpaa2_eth_setup_tx_flow(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_fq *fq) { struct device *dev = priv->net_dev->dev.parent; struct dpni_queue queue; @@ -3266,7 +3266,7 @@ static const struct dpaa2_eth_dist_fields dist_fields[] = { }; /* Configure the Rx hash key using the legacy API */ -static int config_legacy_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key) +static int dpaa2_eth_config_legacy_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key) { struct device *dev = priv->net_dev->dev.parent; struct dpni_rx_tc_dist_cfg dist_cfg; @@ -3291,7 +3291,7 @@ static int config_legacy_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key) } /* Configure the Rx hash key using the new API */ -static int config_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key) +static int dpaa2_eth_config_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key) { struct device *dev = priv->net_dev->dev.parent; struct dpni_rx_dist_cfg dist_cfg; @@ -3317,7 +3317,7 @@ static int config_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key) } /* Configure the Rx flow classification key */ -static int config_cls_key(struct dpaa2_eth_priv *priv, dma_addr_t key) +static int dpaa2_eth_config_cls_key(struct dpaa2_eth_priv *priv, dma_addr_t key) { struct device *dev = priv->net_dev->dev.parent; struct dpni_rx_dist_cfg dist_cfg; @@ -3452,11 +3452,11 @@ static int dpaa2_eth_set_dist_key(struct net_device *net_dev, if (type == DPAA2_ETH_RX_DIST_HASH) { if (dpaa2_eth_has_legacy_dist(priv)) - err = config_legacy_hash_key(priv, key_iova); + err = dpaa2_eth_config_legacy_hash_key(priv, key_iova); else - err = config_hash_key(priv, key_iova); + err = dpaa2_eth_config_hash_key(priv, key_iova); } else { - err = config_cls_key(priv, key_iova); + err = dpaa2_eth_config_cls_key(priv, key_iova); } dma_unmap_single(dev, key_iova, DPAA2_CLASSIFIER_DMA_SIZE, @@ -3531,7 +3531,7 @@ out: /* Bind the DPNI to its needed objects and resources: buffer pool, DPIOs, * frame queues and channels */ -static int bind_dpni(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_bind_dpni(struct dpaa2_eth_priv *priv) { struct net_device *net_dev = priv->net_dev; struct device *dev = net_dev->dev.parent; @@ -3579,10 +3579,10 @@ static int bind_dpni(struct dpaa2_eth_priv *priv) for (i = 0; i < priv->num_fqs; i++) { switch (priv->fq[i].type) { case DPAA2_RX_FQ: - err = setup_rx_flow(priv, &priv->fq[i]); + err = dpaa2_eth_setup_rx_flow(priv, &priv->fq[i]); break; case DPAA2_TX_CONF_FQ: - err = setup_tx_flow(priv, &priv->fq[i]); + err = dpaa2_eth_setup_tx_flow(priv, &priv->fq[i]); break; default: dev_err(dev, "Invalid FQ type %d\n", priv->fq[i].type); @@ -3603,7 +3603,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv) } /* Allocate rings for storing incoming frame descriptors */ -static int alloc_rings(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_alloc_rings(struct dpaa2_eth_priv *priv) { struct net_device *net_dev = priv->net_dev; struct device *dev = net_dev->dev.parent; @@ -3630,7 +3630,7 @@ err_ring: return -ENOMEM; } -static void free_rings(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_free_rings(struct dpaa2_eth_priv *priv) { int i; @@ -3638,7 +3638,7 @@ static void free_rings(struct dpaa2_eth_priv *priv) dpaa2_io_store_destroy(priv->channel[i]->store); } -static int set_mac_addr(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_set_mac_addr(struct dpaa2_eth_priv *priv) { struct net_device *net_dev = priv->net_dev; struct device *dev = net_dev->dev.parent; @@ -3703,7 +3703,7 @@ static int set_mac_addr(struct dpaa2_eth_priv *priv) return 0; } -static int netdev_init(struct net_device *net_dev) +static int dpaa2_eth_netdev_init(struct net_device *net_dev) { struct device *dev = net_dev->dev.parent; struct dpaa2_eth_priv *priv = netdev_priv(net_dev); @@ -3716,7 +3716,7 @@ static int netdev_init(struct net_device *net_dev) net_dev->netdev_ops = &dpaa2_eth_ops; net_dev->ethtool_ops = &dpaa2_ethtool_ops; - err = set_mac_addr(priv); + err = dpaa2_eth_set_mac_addr(priv); if (err) return err; @@ -3771,13 +3771,13 @@ static int netdev_init(struct net_device *net_dev) return 0; } -static int poll_link_state(void *arg) +static int dpaa2_eth_poll_link_state(void *arg) { struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)arg; int err; while (!kthread_should_stop()) { - err = link_state_update(priv); + err = dpaa2_eth_link_state_update(priv); if (unlikely(err)) return err; @@ -3847,11 +3847,11 @@ static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg) } if (status & DPNI_IRQ_EVENT_LINK_CHANGED) - link_state_update(netdev_priv(net_dev)); + dpaa2_eth_link_state_update(netdev_priv(net_dev)); if (status & DPNI_IRQ_EVENT_ENDPOINT_CHANGED) { - set_mac_addr(netdev_priv(net_dev)); - update_tx_fqids(priv); + dpaa2_eth_set_mac_addr(netdev_priv(net_dev)); + dpaa2_eth_update_tx_fqids(priv); rtnl_lock(); if (priv->mac) @@ -3864,7 +3864,7 @@ static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg) return IRQ_HANDLED; } -static int setup_irqs(struct fsl_mc_device *ls_dev) +static int dpaa2_eth_setup_irqs(struct fsl_mc_device *ls_dev) { int err = 0; struct fsl_mc_device_irq *irq; @@ -3910,7 +3910,7 @@ free_mc_irq: return err; } -static void add_ch_napi(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_add_ch_napi(struct dpaa2_eth_priv *priv) { int i; struct dpaa2_eth_channel *ch; @@ -3923,7 +3923,7 @@ static void add_ch_napi(struct dpaa2_eth_priv *priv) } } -static void del_ch_napi(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_del_ch_napi(struct dpaa2_eth_priv *priv) { int i; struct dpaa2_eth_channel *ch; @@ -3970,26 +3970,26 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) } /* MC objects initialization and configuration */ - err = setup_dpni(dpni_dev); + err = dpaa2_eth_setup_dpni(dpni_dev); if (err) goto err_dpni_setup; - err = setup_dpio(priv); + err = dpaa2_eth_setup_dpio(priv); if (err) goto err_dpio_setup; - setup_fqs(priv); + dpaa2_eth_setup_fqs(priv); - err = setup_dpbp(priv); + err = dpaa2_eth_setup_dpbp(priv); if (err) goto err_dpbp_setup; - err = bind_dpni(priv); + err = dpaa2_eth_bind_dpni(priv); if (err) goto err_bind; /* Add a NAPI context for each channel */ - add_ch_napi(priv); + dpaa2_eth_add_ch_napi(priv); /* Percpu statistics */ priv->percpu_stats = alloc_percpu(*priv->percpu_stats); @@ -4012,21 +4012,21 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) goto err_alloc_sgt_cache; } - err = netdev_init(net_dev); + err = dpaa2_eth_netdev_init(net_dev); if (err) goto err_netdev_init; /* Configure checksum offload based on current interface flags */ - err = set_rx_csum(priv, !!(net_dev->features & NETIF_F_RXCSUM)); + err = dpaa2_eth_set_rx_csum(priv, !!(net_dev->features & NETIF_F_RXCSUM)); if (err) goto err_csum; - err = set_tx_csum(priv, !!(net_dev->features & - (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))); + err = dpaa2_eth_set_tx_csum(priv, + !!(net_dev->features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))); if (err) goto err_csum; - err = alloc_rings(priv); + err = dpaa2_eth_alloc_rings(priv); if (err) goto err_alloc_rings; @@ -4039,10 +4039,10 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) } #endif - err = setup_irqs(dpni_dev); + err = dpaa2_eth_setup_irqs(dpni_dev); if (err) { netdev_warn(net_dev, "Failed to set link interrupt, fall back to polling\n"); - priv->poll_thread = kthread_run(poll_link_state, priv, + priv->poll_thread = kthread_run(dpaa2_eth_poll_link_state, priv, "%s_poll_link", net_dev->name); if (IS_ERR(priv->poll_thread)) { dev_err(dev, "Error starting polling thread\n"); @@ -4076,7 +4076,7 @@ err_connect_mac: else fsl_mc_free_irqs(dpni_dev); err_poll_thread: - free_rings(priv); + dpaa2_eth_free_rings(priv); err_alloc_rings: err_csum: err_netdev_init: @@ -4086,13 +4086,13 @@ err_alloc_sgt_cache: err_alloc_percpu_extras: free_percpu(priv->percpu_stats); err_alloc_percpu_stats: - del_ch_napi(priv); + dpaa2_eth_del_ch_napi(priv); err_bind: - free_dpbp(priv); + dpaa2_eth_free_dpbp(priv); err_dpbp_setup: - free_dpio(priv); + dpaa2_eth_free_dpio(priv); err_dpio_setup: - free_dpni(priv); + dpaa2_eth_free_dpni(priv); err_dpni_setup: fsl_mc_portal_free(priv->mc_io); err_portal_alloc: @@ -4126,15 +4126,15 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) else fsl_mc_free_irqs(ls_dev); - free_rings(priv); + dpaa2_eth_free_rings(priv); free_percpu(priv->sgt_cache); free_percpu(priv->percpu_stats); free_percpu(priv->percpu_extras); - del_ch_napi(priv); - free_dpbp(priv); - free_dpio(priv); - free_dpni(priv); + dpaa2_eth_del_ch_napi(priv); + dpaa2_eth_free_dpbp(priv); + dpaa2_eth_free_dpio(priv); + dpaa2_eth_free_dpni(priv); fsl_mc_portal_free(priv->mc_io); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 8356f1fbbee1..26bd99b76765 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -316,8 +316,8 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, dpaa2_mac_get_ethtool_stats(priv->mac, data + i); } -static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask, - void *key, void *mask, u64 *fields) +static int dpaa2_eth_prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask, + void *key, void *mask, u64 *fields) { int off; @@ -345,9 +345,9 @@ static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask, return 0; } -static int prep_uip_rule(struct ethtool_usrip4_spec *uip_value, - struct ethtool_usrip4_spec *uip_mask, - void *key, void *mask, u64 *fields) +static int dpaa2_eth_prep_uip_rule(struct ethtool_usrip4_spec *uip_value, + struct ethtool_usrip4_spec *uip_mask, + void *key, void *mask, u64 *fields) { int off; u32 tmp_value, tmp_mask; @@ -400,9 +400,9 @@ static int prep_uip_rule(struct ethtool_usrip4_spec *uip_value, return 0; } -static int prep_l4_rule(struct ethtool_tcpip4_spec *l4_value, - struct ethtool_tcpip4_spec *l4_mask, - void *key, void *mask, u8 l4_proto, u64 *fields) +static int dpaa2_eth_prep_l4_rule(struct ethtool_tcpip4_spec *l4_value, + struct ethtool_tcpip4_spec *l4_mask, + void *key, void *mask, u8 l4_proto, u64 *fields) { int off; @@ -451,9 +451,9 @@ static int prep_l4_rule(struct ethtool_tcpip4_spec *l4_value, return 0; } -static int prep_ext_rule(struct ethtool_flow_ext *ext_value, - struct ethtool_flow_ext *ext_mask, - void *key, void *mask, u64 *fields) +static int dpaa2_eth_prep_ext_rule(struct ethtool_flow_ext *ext_value, + struct ethtool_flow_ext *ext_mask, + void *key, void *mask, u64 *fields) { int off; @@ -470,9 +470,9 @@ static int prep_ext_rule(struct ethtool_flow_ext *ext_value, return 0; } -static int prep_mac_ext_rule(struct ethtool_flow_ext *ext_value, - struct ethtool_flow_ext *ext_mask, - void *key, void *mask, u64 *fields) +static int dpaa2_eth_prep_mac_ext_rule(struct ethtool_flow_ext *ext_value, + struct ethtool_flow_ext *ext_mask, + void *key, void *mask, u64 *fields) { int off; @@ -486,32 +486,32 @@ static int prep_mac_ext_rule(struct ethtool_flow_ext *ext_value, return 0; } -static int prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, void *mask, - u64 *fields) +static int dpaa2_eth_prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, + void *mask, u64 *fields) { int err; switch (fs->flow_type & 0xFF) { case ETHER_FLOW: - err = prep_eth_rule(&fs->h_u.ether_spec, &fs->m_u.ether_spec, - key, mask, fields); + err = dpaa2_eth_prep_eth_rule(&fs->h_u.ether_spec, &fs->m_u.ether_spec, + key, mask, fields); break; case IP_USER_FLOW: - err = prep_uip_rule(&fs->h_u.usr_ip4_spec, - &fs->m_u.usr_ip4_spec, key, mask, fields); + err = dpaa2_eth_prep_uip_rule(&fs->h_u.usr_ip4_spec, + &fs->m_u.usr_ip4_spec, key, mask, fields); break; case TCP_V4_FLOW: - err = prep_l4_rule(&fs->h_u.tcp_ip4_spec, &fs->m_u.tcp_ip4_spec, - key, mask, IPPROTO_TCP, fields); + err = dpaa2_eth_prep_l4_rule(&fs->h_u.tcp_ip4_spec, &fs->m_u.tcp_ip4_spec, + key, mask, IPPROTO_TCP, fields); break; case UDP_V4_FLOW: - err = prep_l4_rule(&fs->h_u.udp_ip4_spec, &fs->m_u.udp_ip4_spec, - key, mask, IPPROTO_UDP, fields); + err = dpaa2_eth_prep_l4_rule(&fs->h_u.udp_ip4_spec, &fs->m_u.udp_ip4_spec, + key, mask, IPPROTO_UDP, fields); break; case SCTP_V4_FLOW: - err = prep_l4_rule(&fs->h_u.sctp_ip4_spec, - &fs->m_u.sctp_ip4_spec, key, mask, - IPPROTO_SCTP, fields); + err = dpaa2_eth_prep_l4_rule(&fs->h_u.sctp_ip4_spec, + &fs->m_u.sctp_ip4_spec, key, mask, + IPPROTO_SCTP, fields); break; default: return -EOPNOTSUPP; @@ -521,14 +521,14 @@ static int prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, void *mask, return err; if (fs->flow_type & FLOW_EXT) { - err = prep_ext_rule(&fs->h_ext, &fs->m_ext, key, mask, fields); + err = dpaa2_eth_prep_ext_rule(&fs->h_ext, &fs->m_ext, key, mask, fields); if (err) return err; } if (fs->flow_type & FLOW_MAC_EXT) { - err = prep_mac_ext_rule(&fs->h_ext, &fs->m_ext, key, mask, - fields); + err = dpaa2_eth_prep_mac_ext_rule(&fs->h_ext, &fs->m_ext, key, + mask, fields); if (err) return err; } @@ -536,9 +536,9 @@ static int prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, void *mask, return 0; } -static int do_cls_rule(struct net_device *net_dev, - struct ethtool_rx_flow_spec *fs, - bool add) +static int dpaa2_eth_do_cls_rule(struct net_device *net_dev, + struct ethtool_rx_flow_spec *fs, + bool add) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct device *dev = net_dev->dev.parent; @@ -561,7 +561,7 @@ static int do_cls_rule(struct net_device *net_dev, return -ENOMEM; /* Fill the key and mask memory areas */ - err = prep_cls_rule(fs, key_buf, key_buf + rule_cfg.key_size, &fields); + err = dpaa2_eth_prep_cls_rule(fs, key_buf, key_buf + rule_cfg.key_size, &fields); if (err) goto free_mem; @@ -629,7 +629,7 @@ free_mem: return err; } -static int num_rules(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_num_cls_rules(struct dpaa2_eth_priv *priv) { int i, rules = 0; @@ -640,9 +640,9 @@ static int num_rules(struct dpaa2_eth_priv *priv) return rules; } -static int update_cls_rule(struct net_device *net_dev, - struct ethtool_rx_flow_spec *new_fs, - unsigned int location) +static int dpaa2_eth_update_cls_rule(struct net_device *net_dev, + struct ethtool_rx_flow_spec *new_fs, + unsigned int location) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct dpaa2_eth_cls_rule *rule; @@ -658,13 +658,14 @@ static int update_cls_rule(struct net_device *net_dev, /* If a rule is present at the specified location, delete it. */ if (rule->in_use) { - err = do_cls_rule(net_dev, &rule->fs, false); + err = dpaa2_eth_do_cls_rule(net_dev, &rule->fs, false); if (err) return err; rule->in_use = 0; - if (!dpaa2_eth_fs_mask_enabled(priv) && !num_rules(priv)) + if (!dpaa2_eth_fs_mask_enabled(priv) && + !dpaa2_eth_num_cls_rules(priv)) priv->rx_cls_fields = 0; } @@ -672,7 +673,7 @@ static int update_cls_rule(struct net_device *net_dev, if (!new_fs) return err; - err = do_cls_rule(net_dev, new_fs, true); + err = dpaa2_eth_do_cls_rule(net_dev, new_fs, true); if (err) return err; @@ -702,7 +703,7 @@ static int dpaa2_eth_get_rxnfc(struct net_device *net_dev, break; case ETHTOOL_GRXCLSRLCNT: rxnfc->rule_cnt = 0; - rxnfc->rule_cnt = num_rules(priv); + rxnfc->rule_cnt = dpaa2_eth_num_cls_rules(priv); rxnfc->data = max_rules; break; case ETHTOOL_GRXCLSRULE: @@ -744,10 +745,10 @@ static int dpaa2_eth_set_rxnfc(struct net_device *net_dev, err = dpaa2_eth_set_hash(net_dev, rxnfc->data); break; case ETHTOOL_SRXCLSRLINS: - err = update_cls_rule(net_dev, &rxnfc->fs, rxnfc->fs.location); + err = dpaa2_eth_update_cls_rule(net_dev, &rxnfc->fs, rxnfc->fs.location); break; case ETHTOOL_SRXCLSRLDEL: - err = update_cls_rule(net_dev, NULL, rxnfc->fs.location); + err = dpaa2_eth_update_cls_rule(net_dev, NULL, rxnfc->fs.location); break; default: err = -EOPNOTSUPP; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 9934421814b4..c043afb38b6e 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1960,8 +1960,7 @@ failed_clk_ref: mutex_unlock(&fep->ptp_clk_mutex); } failed_clk_ptp: - if (fep->clk_enet_out) - clk_disable_unprepare(fep->clk_enet_out); + clk_disable_unprepare(fep->clk_enet_out); return ret; } @@ -3715,11 +3714,11 @@ failed_mii_init: failed_irq: failed_init: fec_ptp_stop(pdev); - if (fep->reg_phy) - regulator_disable(fep->reg_phy); failed_reset: pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + if (fep->reg_phy) + regulator_disable(fep->reg_phy); failed_regulator: clk_disable_unprepare(fep->clk_ahb); failed_clk_ahb: diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 645764abdaae..bb9887f98841 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -528,7 +528,7 @@ static void setup_sgmii_internal_phy(struct fman_mac *memac, case 100: tmp_reg16 |= IF_MODE_SGMII_SPEED_100M; break; - case 1000: /* fallthrough */ + case 1000: default: tmp_reg16 |= IF_MODE_SGMII_SPEED_1G; break; diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index c27df153f895..624b2eb6f01d 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -1344,10 +1344,10 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params) switch (port->port_type) { case FMAN_PORT_TYPE_RX: set_rx_dflt_cfg(port, params); - /* fall through */ + fallthrough; case FMAN_PORT_TYPE_TX: set_tx_dflt_cfg(port, params, &port->dts_params); - /* fall through */ + fallthrough; default: set_dflt_cfg(port, params); } diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index bf846b42bc74..78e008b81374 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -562,10 +562,13 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) BD_ENET_TX_TC); CBDS_SC(bdp, BD_ENET_TX_READY); - if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0) - bdp++, curidx++; - else - bdp = fep->tx_bd_base, curidx = 0; + if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0) { + bdp++; + curidx++; + } else { + bdp = fep->tx_bd_base; + curidx = 0; + } len = skb_frag_size(frag); CBDW_BUFADDR(bdp, skb_frag_dma_map(fep->dev, frag, 0, len, diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index b513b8c5c3b5..41dd3d0f3452 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -750,8 +750,10 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) continue; err = gfar_parse_group(child, priv, model); - if (err) + if (err) { + of_node_put(child); goto err_grp_init; + } } } else { /* SQ_SG_MODE */ err = gfar_parse_group(np, priv, model); diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index db791f60b884..714b501be7d0 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1348,7 +1348,7 @@ static int adjust_enet_interface(struct ucc_geth_private *ugeth) switch (ugeth->max_speed) { case SPEED_10: upsmr |= UCC_GETH_UPSMR_R10M; - /* FALLTHROUGH */ + fallthrough; case SPEED_100: if (ugeth->phy_interface != PHY_INTERFACE_MODE_RTBI) upsmr |= UCC_GETH_UPSMR_RMM; diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 08339278c722..e017b7c34140 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -438,7 +438,7 @@ EXPORT_SYMBOL(hnae_ae_register); /** * hnae_ae_unregister - unregisters a HNAE AE engine - * @cdev: the device to unregister + * @hdev: the device to unregister */ void hnae_ae_unregister(struct hnae_ae_dev *hdev) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index b43dec0560a8..b98244f75ab9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -13,8 +13,6 @@ #include "hns_dsaf_ppe.h" #include "hns_dsaf_rcb.h" -#define AE_NAME_PORT_ID_IDX 6 - static struct hns_mac_cb *hns_get_mac_cb(struct hnae_handle *handle) { struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index 0a3dbab2dfc9..d832cd018c1c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -130,7 +130,7 @@ static void hns_xgmac_lf_rf_control_init(struct mac_driver *mac_drv) /** *hns_xgmac_enable - enable xgmac port - *@drv: mac driver + *@mac_drv: mac driver *@mode: mode of mac port */ static void hns_xgmac_enable(void *mac_drv, enum mac_commom_mode mode) @@ -490,7 +490,6 @@ static void hns_xgmac_get_link_status(void *mac_drv, u32 *link_stat) /** *hns_xgmac_get_regs - dump xgmac regs *@mac_drv: mac driver - *@cmd:ethtool cmd *@data:data for value of regs */ static void hns_xgmac_get_regs(void *mac_drv, void *data) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 23f278e46975..b658b9de81d7 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -557,10 +557,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, va = (unsigned char *)desc_cb->buf + desc_cb->page_offset; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); skb = *out_skb = napi_alloc_skb(&ring_data->napi, HNS_RX_HEAD_SIZE); @@ -1832,8 +1829,7 @@ static int hns_nic_uc_unsync(struct net_device *netdev, /** * nic_set_multicast_list - set mutl mac address - * @netdev: net device - * @p: mac address + * @ndev: net device * * return void */ @@ -2282,8 +2278,10 @@ static int hns_nic_dev_probe(struct platform_device *pdev) priv->enet_ver = AE_VERSION_1; else if (acpi_dev_found(hns_enet_acpi_match[1].id)) priv->enet_ver = AE_VERSION_2; - else - return -ENXIO; + else { + ret = -ENXIO; + goto out_read_prop_fail; + } /* try to find port-idx-in-ae first */ ret = acpi_node_get_property_reference(dev->fwnode, @@ -2299,7 +2297,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev) priv->fwnode = args.fwnode; } else { dev_err(dev, "cannot read cfg data from OF or acpi\n"); - return -ENXIO; + ret = -ENXIO; + goto out_read_prop_fail; } ret = device_property_read_u32(dev, "port-idx-in-ae", &port_id); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 49624acf2473..4eb50296f653 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -305,7 +305,7 @@ static int __lb_setup(struct net_device *ndev, break; case MAC_LOOP_PHY_NONE: ret = hns_nic_config_phy_loopback(phy_dev, 0x0); - /* fall through */ + fallthrough; case MAC_LOOP_NONE: if (!ret && h->dev->ops->set_loopback) { if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 87776ce3539b..93825a433915 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -21,6 +21,7 @@ #include <net/pkt_cls.h> #include <net/tcp.h> #include <net/vxlan.h> +#include <net/geneve.h> #include "hnae3.h" #include "hns3_enet.h" @@ -622,20 +623,6 @@ void hns3_request_update_promisc_mode(struct hnae3_handle *handle) ops->request_update_promisc_mode(handle); } -int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags) -{ - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; - - if (h->ae_algo->ops->set_promisc_mode) { - return h->ae_algo->ops->set_promisc_mode(h, - promisc_flags & HNAE3_UPE, - promisc_flags & HNAE3_MPE); - } - - return 0; -} - void hns3_enable_vlan_filter(struct net_device *netdev, bool enable) { struct hns3_nic_priv *priv = netdev_priv(netdev); @@ -780,7 +767,7 @@ static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto, * and it is udp packet, which has a dest port as the IANA assigned. * the hardware is expected to do the checksum offload, but the * hardware will not do the checksum offload when udp dest port is - * 4789. + * 4789 or 6081. */ static bool hns3_tunnel_csum_bug(struct sk_buff *skb) { @@ -789,7 +776,8 @@ static bool hns3_tunnel_csum_bug(struct sk_buff *skb) l4.hdr = skb_transport_header(skb); if (!(!skb->encapsulation && - l4.udp->dest == htons(IANA_VXLAN_UDP_PORT))) + (l4.udp->dest == htons(IANA_VXLAN_UDP_PORT) || + l4.udp->dest == htons(GENEVE_UDP_PORT)))) return false; skb_checksum_help(skb); @@ -2746,7 +2734,7 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, case HNS3_OL4_TYPE_MAC_IN_UDP: case HNS3_OL4_TYPE_NVGRE: skb->csum_level = 1; - /* fall through */ + fallthrough; case HNS3_OL4_TYPE_NO_TUN: l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S); @@ -3091,10 +3079,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring) * lines. In such a case, single fetch would suffice to cache in the * relevant part of the header. */ - prefetch(ring->va); -#if L1_CACHE_BYTES < 128 - prefetch(ring->va + L1_CACHE_BYTES); -#endif + net_prefetch(ring->va); if (!skb) { ret = hns3_alloc_skb(ring, length, ring->va); @@ -3671,12 +3656,10 @@ static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv, ring = &priv->ring[q->tqp_index]; desc_num = priv->ae_handle->kinfo.num_tx_desc; ring->queue_index = q->tqp_index; - ring->io_base = (u8 __iomem *)q->io_base + HNS3_TX_REG_OFFSET; } else { ring = &priv->ring[q->tqp_index + queue_num]; desc_num = priv->ae_handle->kinfo.num_rx_desc; ring->queue_index = q->tqp_index; - ring->io_base = q->io_base; } hnae3_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 9922c5fd7f94..98ca6ead0b7d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -42,13 +42,8 @@ enum hns3_nic_state { #define HNS3_RING_TX_RING_PKTNUM_RECORD_REG 0x0006C #define HNS3_RING_TX_RING_EBD_OFFSET_REG 0x00070 #define HNS3_RING_TX_RING_BD_ERR_REG 0x00074 -#define HNS3_RING_PREFETCH_EN_REG 0x0007C -#define HNS3_RING_CFG_VF_NUM_REG 0x00080 -#define HNS3_RING_ASID_REG 0x0008C #define HNS3_RING_EN_REG 0x00090 -#define HNS3_TX_REG_OFFSET 0x40 - #define HNS3_RX_HEAD_SIZE 256 #define HNS3_TX_TIMEOUT (5 * HZ) @@ -380,7 +375,6 @@ struct ring_stats { }; struct hns3_enet_ring { - u8 __iomem *io_base; /* base io address for the ring */ struct hns3_desc *desc; /* dma map address space */ struct hns3_desc_cb *desc_cb; struct hns3_enet_ring *next; @@ -607,7 +601,6 @@ void hns3_set_vector_coalesce_rl(struct hns3_enet_tqp_vector *tqp_vector, u32 rl_value); void hns3_enable_vlan_filter(struct net_device *netdev, bool enable); -int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags); void hns3_request_update_promisc_mode(struct hnae3_handle *handle); #ifdef CONFIG_HNS3_DCB diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 36575e72a915..40d68a4ff83d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3061,7 +3061,7 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) * by first decoding the types of errors. */ set_bit(HNAE3_UNKNOWN_RESET, &hdev->reset_request); - /* fall through */ + fallthrough; case HCLGE_VECTOR0_EVENT_RST: hclge_reset_task_schedule(hdev); break; @@ -3686,12 +3686,10 @@ static int hclge_reset_prepare_up(struct hclge_dev *hdev) switch (hdev->reset_type) { case HNAE3_FUNC_RESET: - /* fall through */ case HNAE3_FLR_RESET: ret = hclge_set_all_vf_rst(hdev, false); break; case HNAE3_GLOBAL_RESET: - /* fall through */ case HNAE3_IMP_RESET: ret = hclge_set_rst_done(hdev); break; @@ -3946,6 +3944,9 @@ static void hclge_periodic_service_task(struct hclge_dev *hdev) { unsigned long delta = round_jiffies_relative(HZ); + if (test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) + return; + /* Always handle the link updating to make sure link state is * updated when it is triggered by mbx. */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 9bbdd4557c27..3975332a1a10 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -266,7 +266,7 @@ struct hclge_mac { u32 fec_mode; /* active fec mode */ u32 user_fec_mode; u32 fec_ability; - int link; /* store the link status of mac & phy (if phy exit) */ + int link; /* store the link status of mac & phy (if phy exists) */ struct phy_device *phydev; struct mii_bus *mdio_bus; phy_interface_t phy_if; @@ -749,7 +749,6 @@ struct hclge_dev { u16 num_tx_desc; /* desc num of per tx queue */ u16 num_rx_desc; /* desc num of per rx queue */ u8 hw_tc_map; - u8 tc_num_last_time; enum hclge_fc_mode fc_mode_last_time; u8 support_sfp_query; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index e972138a14ad..20dd50dd765a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1788,10 +1788,10 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev) { #define HCLGEVF_RESET_SYNC_TIME 100 - struct hclge_vf_to_pf_msg send_msg; - int ret = 0; - if (hdev->reset_type == HNAE3_VF_FUNC_RESET) { + struct hclge_vf_to_pf_msg send_msg; + int ret; + hclgevf_build_send_msg(&send_msg, HCLGE_MBX_RESET, 0); ret = hclgevf_send_mbx_msg(hdev, &send_msg, true, NULL, 0); if (ret) { @@ -1806,10 +1806,10 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev) /* inform hardware that preparatory work is done */ msleep(HCLGEVF_RESET_SYNC_TIME); hclgevf_reset_handshake(hdev, true); - dev_info(&hdev->pdev->dev, "prepare reset(%d) wait done, ret:%d\n", - hdev->reset_type, ret); + dev_info(&hdev->pdev->dev, "prepare reset(%d) wait done\n", + hdev->reset_type); - return ret; + return 0; } static void hclgevf_dump_rst_info(struct hclgevf_dev *hdev) @@ -2186,6 +2186,9 @@ static void hclgevf_periodic_service_task(struct hclgevf_dev *hdev) unsigned long delta = round_jiffies_relative(HZ); struct hnae3_handle *handle = &hdev->nic; + if (test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) + return; + if (time_is_after_jiffies(hdev->last_serv_processed + HZ)) { delta = jiffies - hdev->last_serv_processed; diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile index 67b59d0ba769..2f89119c9b69 100644 --- a/drivers/net/ethernet/huawei/hinic/Makefile +++ b/drivers/net/ethernet/huawei/hinic/Makefile @@ -4,4 +4,5 @@ obj-$(CONFIG_HINIC) += hinic.o hinic-y := hinic_main.o hinic_tx.o hinic_rx.o hinic_port.o hinic_hw_dev.o \ hinic_hw_io.o hinic_hw_qp.o hinic_hw_cmdq.o hinic_hw_wq.o \ hinic_hw_mgmt.o hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o \ - hinic_common.o hinic_ethtool.o hinic_devlink.o hinic_hw_mbox.o hinic_sriov.o + hinic_common.o hinic_ethtool.o hinic_devlink.o hinic_hw_mbox.o \ + hinic_sriov.o hinic_debugfs.o diff --git a/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c new file mode 100644 index 000000000000..19eb839177ec --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + */ + +#include <linux/debugfs.h> +#include <linux/device.h> + +#include "hinic_debugfs.h" + +static struct dentry *hinic_dbgfs_root; + +enum sq_dbg_info { + GLB_SQ_ID, + SQ_PI, + SQ_CI, + SQ_FI, + SQ_MSIX_ENTRY, +}; + +static char *sq_fields[] = {"glb_sq_id", "sq_pi", "sq_ci", "sq_fi", "sq_msix_entry"}; + +static u64 hinic_dbg_get_sq_info(struct hinic_dev *nic_dev, struct hinic_sq *sq, int idx) +{ + struct hinic_wq *wq = sq->wq; + + switch (idx) { + case GLB_SQ_ID: + return nic_dev->hwdev->func_to_io.global_qpn + sq->qid; + case SQ_PI: + return atomic_read(&wq->prod_idx) & wq->mask; + case SQ_CI: + return atomic_read(&wq->cons_idx) & wq->mask; + case SQ_FI: + return be16_to_cpu(*(__be16 *)(sq->hw_ci_addr)) & wq->mask; + case SQ_MSIX_ENTRY: + return sq->msix_entry; + } + + return 0; +} + +enum rq_dbg_info { + GLB_RQ_ID, + RQ_HW_PI, + RQ_SW_CI, + RQ_SW_PI, + RQ_MSIX_ENTRY, +}; + +static char *rq_fields[] = {"glb_rq_id", "rq_hw_pi", "rq_sw_ci", "rq_sw_pi", "rq_msix_entry"}; + +static u64 hinic_dbg_get_rq_info(struct hinic_dev *nic_dev, struct hinic_rq *rq, int idx) +{ + struct hinic_wq *wq = rq->wq; + + switch (idx) { + case GLB_RQ_ID: + return nic_dev->hwdev->func_to_io.global_qpn + rq->qid; + case RQ_HW_PI: + return be16_to_cpu(*(__be16 *)(rq->pi_virt_addr)) & wq->mask; + case RQ_SW_CI: + return atomic_read(&wq->cons_idx) & wq->mask; + case RQ_SW_PI: + return atomic_read(&wq->prod_idx) & wq->mask; + case RQ_MSIX_ENTRY: + return rq->msix_entry; + } + + return 0; +} + +enum func_tbl_info { + VALID, + RX_MODE, + MTU, + RQ_DEPTH, + QUEUE_NUM, +}; + +static char *func_table_fields[] = {"valid", "rx_mode", "mtu", "rq_depth", "cfg_q_num"}; + +static int hinic_dbg_get_func_table(struct hinic_dev *nic_dev, int idx) +{ + struct tag_sml_funcfg_tbl *funcfg_table_elem; + struct hinic_cmd_lt_rd *read_data; + u16 out_size = sizeof(*read_data); + int err; + + read_data = kzalloc(sizeof(*read_data), GFP_KERNEL); + if (!read_data) + return ~0; + + read_data->node = TBL_ID_FUNC_CFG_SM_NODE; + read_data->inst = TBL_ID_FUNC_CFG_SM_INST; + read_data->entry_size = HINIC_FUNCTION_CONFIGURE_TABLE_SIZE; + read_data->lt_index = HINIC_HWIF_FUNC_IDX(nic_dev->hwdev->hwif); + read_data->len = HINIC_FUNCTION_CONFIGURE_TABLE_SIZE; + + err = hinic_port_msg_cmd(nic_dev->hwdev, HINIC_PORT_CMD_RD_LINE_TBL, read_data, + sizeof(*read_data), read_data, &out_size); + if (err || out_size != sizeof(*read_data) || read_data->status) { + netif_err(nic_dev, drv, nic_dev->netdev, + "Failed to get func table, err: %d, status: 0x%x, out size: 0x%x\n", + err, read_data->status, out_size); + kfree(read_data); + return ~0; + } + + funcfg_table_elem = (struct tag_sml_funcfg_tbl *)read_data->data; + + switch (idx) { + case VALID: + return funcfg_table_elem->dw0.bs.valid; + case RX_MODE: + return funcfg_table_elem->dw0.bs.nic_rx_mode; + case MTU: + return funcfg_table_elem->dw1.bs.mtu; + case RQ_DEPTH: + return funcfg_table_elem->dw13.bs.cfg_rq_depth; + case QUEUE_NUM: + return funcfg_table_elem->dw13.bs.cfg_q_num; + } + + kfree(read_data); + + return ~0; +} + +static ssize_t hinic_dbg_cmd_read(struct file *filp, char __user *buffer, size_t count, + loff_t *ppos) +{ + struct hinic_debug_priv *dbg; + char ret_buf[20]; + int *desc; + u64 out; + int ret; + + desc = filp->private_data; + dbg = container_of(desc, struct hinic_debug_priv, field_id[*desc]); + + switch (dbg->type) { + case HINIC_DBG_SQ_INFO: + out = hinic_dbg_get_sq_info(dbg->dev, dbg->object, *desc); + break; + + case HINIC_DBG_RQ_INFO: + out = hinic_dbg_get_rq_info(dbg->dev, dbg->object, *desc); + break; + + case HINIC_DBG_FUNC_TABLE: + out = hinic_dbg_get_func_table(dbg->dev, *desc); + break; + + default: + netif_warn(dbg->dev, drv, dbg->dev->netdev, "Invalid hinic debug cmd: %d\n", + dbg->type); + return -EINVAL; + } + + ret = snprintf(ret_buf, sizeof(ret_buf), "0x%llx\n", out); + + return simple_read_from_buffer(buffer, count, ppos, ret_buf, ret); +} + +static const struct file_operations hinic_dbg_cmd_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = hinic_dbg_cmd_read, +}; + +static int create_dbg_files(struct hinic_dev *dev, enum hinic_dbg_type type, void *data, + struct dentry *root, struct hinic_debug_priv **dbg, char **field, + int nfile) +{ + struct hinic_debug_priv *tmp; + int i; + + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + tmp->dev = dev; + tmp->object = data; + tmp->type = type; + tmp->root = root; + + for (i = 0; i < nfile; i++) { + tmp->field_id[i] = i; + debugfs_create_file(field[i], 0400, root, &tmp->field_id[i], &hinic_dbg_cmd_fops); + } + + *dbg = tmp; + + return 0; +} + +static void rem_dbg_files(struct hinic_debug_priv *dbg) +{ + if (dbg->type != HINIC_DBG_FUNC_TABLE) + debugfs_remove_recursive(dbg->root); + + kfree(dbg); +} + +int hinic_sq_debug_add(struct hinic_dev *dev, u16 sq_id) +{ + struct hinic_sq *sq; + struct dentry *root; + char sub_dir[16]; + + sq = dev->txqs[sq_id].sq; + + sprintf(sub_dir, "0x%x", sq_id); + + root = debugfs_create_dir(sub_dir, dev->sq_dbgfs); + + return create_dbg_files(dev, HINIC_DBG_SQ_INFO, sq, root, &sq->dbg, sq_fields, + ARRAY_SIZE(sq_fields)); +} + +void hinic_sq_debug_rem(struct hinic_sq *sq) +{ + if (sq->dbg) + rem_dbg_files(sq->dbg); +} + +int hinic_rq_debug_add(struct hinic_dev *dev, u16 rq_id) +{ + struct hinic_rq *rq; + struct dentry *root; + char sub_dir[16]; + + rq = dev->rxqs[rq_id].rq; + + sprintf(sub_dir, "0x%x", rq_id); + + root = debugfs_create_dir(sub_dir, dev->rq_dbgfs); + + return create_dbg_files(dev, HINIC_DBG_RQ_INFO, rq, root, &rq->dbg, rq_fields, + ARRAY_SIZE(rq_fields)); +} + +void hinic_rq_debug_rem(struct hinic_rq *rq) +{ + if (rq->dbg) + rem_dbg_files(rq->dbg); +} + +int hinic_func_table_debug_add(struct hinic_dev *dev) +{ + if (HINIC_IS_VF(dev->hwdev->hwif)) + return 0; + + return create_dbg_files(dev, HINIC_DBG_FUNC_TABLE, dev, dev->func_tbl_dbgfs, &dev->dbg, + func_table_fields, ARRAY_SIZE(func_table_fields)); +} + +void hinic_func_table_debug_rem(struct hinic_dev *dev) +{ + if (!HINIC_IS_VF(dev->hwdev->hwif) && dev->dbg) + rem_dbg_files(dev->dbg); +} + +void hinic_sq_dbgfs_init(struct hinic_dev *nic_dev) +{ + nic_dev->sq_dbgfs = debugfs_create_dir("SQs", nic_dev->dbgfs_root); +} + +void hinic_sq_dbgfs_uninit(struct hinic_dev *nic_dev) +{ + debugfs_remove_recursive(nic_dev->sq_dbgfs); +} + +void hinic_rq_dbgfs_init(struct hinic_dev *nic_dev) +{ + nic_dev->rq_dbgfs = debugfs_create_dir("RQs", nic_dev->dbgfs_root); +} + +void hinic_rq_dbgfs_uninit(struct hinic_dev *nic_dev) +{ + debugfs_remove_recursive(nic_dev->rq_dbgfs); +} + +void hinic_func_tbl_dbgfs_init(struct hinic_dev *nic_dev) +{ + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + nic_dev->func_tbl_dbgfs = debugfs_create_dir("func_table", nic_dev->dbgfs_root); +} + +void hinic_func_tbl_dbgfs_uninit(struct hinic_dev *nic_dev) +{ + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + debugfs_remove_recursive(nic_dev->func_tbl_dbgfs); +} + +void hinic_dbg_init(struct hinic_dev *nic_dev) +{ + nic_dev->dbgfs_root = debugfs_create_dir(pci_name(nic_dev->hwdev->hwif->pdev), + hinic_dbgfs_root); +} + +void hinic_dbg_uninit(struct hinic_dev *nic_dev) +{ + debugfs_remove_recursive(nic_dev->dbgfs_root); + nic_dev->dbgfs_root = NULL; +} + +void hinic_dbg_register_debugfs(const char *debugfs_dir_name) +{ + hinic_dbgfs_root = debugfs_create_dir(debugfs_dir_name, NULL); +} + +void hinic_dbg_unregister_debugfs(void) +{ + debugfs_remove_recursive(hinic_dbgfs_root); + hinic_dbgfs_root = NULL; +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_debugfs.h b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.h new file mode 100644 index 000000000000..e9e00cfa1329 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + */ + +#ifndef HINIC_DEBUGFS_H +#define HINIC_DEBUGFS_H + +#include "hinic_dev.h" + +#define TBL_ID_FUNC_CFG_SM_NODE 11 +#define TBL_ID_FUNC_CFG_SM_INST 1 + +#define HINIC_FUNCTION_CONFIGURE_TABLE_SIZE 64 +#define HINIC_FUNCTION_CONFIGURE_TABLE 1 + +struct hinic_cmd_lt_rd { + u8 status; + u8 version; + u8 rsvd0[6]; + + unsigned char node; + unsigned char inst; + unsigned char entry_size; + unsigned char rsvd; + unsigned int lt_index; + unsigned int offset; + unsigned int len; + unsigned char data[100]; +}; + +struct tag_sml_funcfg_tbl { + union { + struct { + u32 rsvd0 :8; + u32 nic_rx_mode :5; + u32 rsvd1 :18; + u32 valid :1; + } bs; + + u32 value; + } dw0; + + union { + struct { + u32 vlan_id :12; + u32 vlan_mode :3; + u32 fast_recycled_mode :1; + u32 mtu :16; + } bs; + + u32 value; + } dw1; + + u32 dw2; + u32 dw3; + u32 dw4; + u32 dw5; + u32 dw6; + u32 dw7; + u32 dw8; + u32 dw9; + u32 dw10; + u32 dw11; + u32 dw12; + + union { + struct { + u32 rsvd2 :15; + u32 cfg_q_num :9; + u32 cfg_rq_depth :6; + u32 vhd_type :2; + } bs; + + u32 value; + } dw13; + + u32 dw14; + u32 dw15; +}; + +int hinic_sq_debug_add(struct hinic_dev *dev, u16 sq_id); + +void hinic_sq_debug_rem(struct hinic_sq *sq); + +int hinic_rq_debug_add(struct hinic_dev *dev, u16 rq_id); + +void hinic_rq_debug_rem(struct hinic_rq *rq); + +int hinic_func_table_debug_add(struct hinic_dev *dev); + +void hinic_func_table_debug_rem(struct hinic_dev *dev); + +void hinic_sq_dbgfs_init(struct hinic_dev *nic_dev); + +void hinic_sq_dbgfs_uninit(struct hinic_dev *nic_dev); + +void hinic_rq_dbgfs_init(struct hinic_dev *nic_dev); + +void hinic_rq_dbgfs_uninit(struct hinic_dev *nic_dev); + +void hinic_func_tbl_dbgfs_init(struct hinic_dev *nic_dev); + +void hinic_func_tbl_dbgfs_uninit(struct hinic_dev *nic_dev); + +void hinic_dbg_init(struct hinic_dev *nic_dev); + +void hinic_dbg_uninit(struct hinic_dev *nic_dev); + +void hinic_dbg_register_debugfs(const char *debugfs_dir_name); + +void hinic_dbg_unregister_debugfs(void); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h index 0a1e20edf7cf..fb3e89141a0d 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h @@ -58,6 +58,20 @@ struct hinic_intr_coal_info { u8 resend_timer_cfg; }; +enum hinic_dbg_type { + HINIC_DBG_SQ_INFO, + HINIC_DBG_RQ_INFO, + HINIC_DBG_FUNC_TABLE, +}; + +struct hinic_debug_priv { + struct hinic_dev *dev; + void *object; + enum hinic_dbg_type type; + struct dentry *root; + int field_id[64]; +}; + struct hinic_dev { struct net_device *netdev; struct hinic_hwdev *hwdev; @@ -97,6 +111,12 @@ struct hinic_dev { int lb_test_rx_idx; int lb_pkt_len; u8 *lb_test_rx_buf; + + struct dentry *dbgfs_root; + struct dentry *sq_dbgfs; + struct dentry *rq_dbgfs; + struct dentry *func_tbl_dbgfs; + struct hinic_debug_priv *dbg; struct devlink *devlink; bool cable_unplugged; bool module_unrecognized; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c index 29e88e25a4a4..4e4029d5c8e1 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c @@ -373,7 +373,7 @@ static int wait_for_api_cmd_completion(struct hinic_api_cmd_chain *chain) * @chain: chain for the command * @dest: destination node on the card that will receive the command * @cmd: command data - * @size: the command size + * @cmd_size: the command size * * Return 0 - Success, negative - Failure **/ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 0c737765d113..239685152f6e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -465,6 +465,7 @@ int hinic_hwdev_ifup(struct hinic_hwdev *hwdev, u16 sq_depth, u16 rq_depth) func_to_io->hwdev = hwdev; func_to_io->sq_depth = sq_depth; func_to_io->rq_depth = rq_depth; + func_to_io->global_qpn = base_qpn; err = hinic_io_init(func_to_io, hwif, nic_cap->max_qps, num_ceqs, ceq_msix_entries); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index 701eb81e09a7..416492e48274 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -96,6 +96,8 @@ enum hinic_port_cmd { HINIC_PORT_CMD_RSS_TEMP_MGR = 49, + HINIC_PORT_CMD_RD_LINE_TBL = 57, + HINIC_PORT_CMD_RSS_CFG = 66, HINIC_PORT_CMD_FWCTXT_INIT = 69, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c index ca8cb68a8d20..b30733f4a59e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c @@ -106,7 +106,7 @@ enum eq_arm_state { * @aeqs: pointer to Async eqs of the chip * @event: aeq event to register callback for it * @handle: private data will be used by the callback - * @hw_handler: callback function + * @hwe_handler: callback function **/ void hinic_aeq_register_hw_cb(struct hinic_aeqs *aeqs, enum hinic_aeq_type event, void *handle, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c index 3e3fa742e476..4ef4008e65bd 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c @@ -305,6 +305,7 @@ static int init_qp(struct hinic_func_to_io *func_to_io, func_to_io->sq_db[q_id] = db_base; + qp->sq.qid = q_id; err = hinic_init_sq(&qp->sq, hwif, &func_to_io->sq_wq[q_id], sq_msix_entry, CI_ADDR(func_to_io->ci_addr_base, q_id), @@ -314,6 +315,7 @@ static int init_qp(struct hinic_func_to_io *func_to_io, goto err_sq_init; } + qp->rq.qid = q_id; err = hinic_init_rq(&qp->rq, hwif, &func_to_io->rq_wq[q_id], rq_msix_entry); if (err) { @@ -361,8 +363,8 @@ static void destroy_qp(struct hinic_func_to_io *func_to_io, * @func_to_io: func to io channel that holds the IO components * @base_qpn: base qp number * @num_qps: number queue pairs to create - * @sq_msix_entry: msix entries for sq - * @rq_msix_entry: msix entries for rq + * @sq_msix_entries: msix entries for sq + * @rq_msix_entries: msix entries for rq * * Return 0 - Success, negative - Failure **/ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h index ee6d60762d84..52159a90278a 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h @@ -59,6 +59,7 @@ struct hinic_nic_cfg { struct hinic_func_to_io { struct hinic_hwif *hwif; struct hinic_hwdev *hwdev; + u16 global_qpn; struct hinic_ceqs ceqs; struct hinic_wqs wqs; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h index ca3e2d060284..0dfa51ad5855 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h @@ -81,6 +81,8 @@ struct hinic_sq { struct hinic_wq *wq; + u16 qid; + u32 irq; u16 msix_entry; @@ -90,6 +92,7 @@ struct hinic_sq { void __iomem *db_base; struct sk_buff **saved_skb; + struct hinic_debug_priv *dbg; }; struct hinic_rq { @@ -97,6 +100,8 @@ struct hinic_rq { struct hinic_wq *wq; + u16 qid; + struct cpumask affinity_mask; u32 irq; u16 msix_entry; @@ -110,6 +115,7 @@ struct hinic_rq { u16 *pi_virt_addr; dma_addr_t pi_dma_addr; + struct hinic_debug_priv *dbg; }; struct hinic_qp { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 501056fd32ee..797c55a1d9c6 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -24,6 +24,7 @@ #include <linux/delay.h> #include <linux/err.h> +#include "hinic_debugfs.h" #include "hinic_hw_qp.h" #include "hinic_hw_dev.h" #include "hinic_devlink.h" @@ -153,6 +154,8 @@ static int create_txqs(struct hinic_dev *nic_dev) if (!nic_dev->txqs) return -ENOMEM; + hinic_sq_dbgfs_init(nic_dev); + for (i = 0; i < num_txqs; i++) { struct hinic_sq *sq = hinic_hwdev_get_sq(nic_dev->hwdev, i); @@ -162,13 +165,27 @@ static int create_txqs(struct hinic_dev *nic_dev) "Failed to init Txq\n"); goto err_init_txq; } + + err = hinic_sq_debug_add(nic_dev, i); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to add SQ%d debug\n", i); + goto err_add_sq_dbg; + } + } return 0; +err_add_sq_dbg: + hinic_clean_txq(&nic_dev->txqs[i]); err_init_txq: - for (j = 0; j < i; j++) + for (j = 0; j < i; j++) { + hinic_sq_debug_rem(nic_dev->txqs[j].sq); hinic_clean_txq(&nic_dev->txqs[j]); + } + + hinic_sq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->txqs); return err; @@ -186,8 +203,12 @@ static void free_txqs(struct hinic_dev *nic_dev) if (!nic_dev->txqs) return; - for (i = 0; i < num_txqs; i++) + for (i = 0; i < num_txqs; i++) { + hinic_sq_debug_rem(nic_dev->txqs[i].sq); hinic_clean_txq(&nic_dev->txqs[i]); + } + + hinic_sq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->txqs); nic_dev->txqs = NULL; @@ -213,6 +234,8 @@ static int create_rxqs(struct hinic_dev *nic_dev) if (!nic_dev->rxqs) return -ENOMEM; + hinic_rq_dbgfs_init(nic_dev); + for (i = 0; i < num_rxqs; i++) { struct hinic_rq *rq = hinic_hwdev_get_rq(nic_dev->hwdev, i); @@ -222,13 +245,26 @@ static int create_rxqs(struct hinic_dev *nic_dev) "Failed to init rxq\n"); goto err_init_rxq; } + + err = hinic_rq_debug_add(nic_dev, i); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to add RQ%d debug\n", i); + goto err_add_rq_dbg; + } } return 0; +err_add_rq_dbg: + hinic_clean_rxq(&nic_dev->rxqs[i]); err_init_rxq: - for (j = 0; j < i; j++) + for (j = 0; j < i; j++) { + hinic_rq_debug_rem(nic_dev->rxqs[j].rq); hinic_clean_rxq(&nic_dev->rxqs[j]); + } + + hinic_rq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->rxqs); return err; @@ -246,8 +282,12 @@ static void free_rxqs(struct hinic_dev *nic_dev) if (!nic_dev->rxqs) return; - for (i = 0; i < num_rxqs; i++) + for (i = 0; i < num_rxqs; i++) { + hinic_rq_debug_rem(nic_dev->rxqs[i].rq); hinic_clean_rxq(&nic_dev->rxqs[i]); + } + + hinic_rq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->rxqs); nic_dev->rxqs = NULL; @@ -1260,6 +1300,16 @@ static int nic_dev_init(struct pci_dev *pdev) goto err_init_intr; } + hinic_dbg_init(nic_dev); + + hinic_func_tbl_dbgfs_init(nic_dev); + + err = hinic_func_table_debug_add(nic_dev); + if (err) { + dev_err(&pdev->dev, "Failed to add func_table debug\n"); + goto err_add_func_table_dbg; + } + err = register_netdev(netdev); if (err) { dev_err(&pdev->dev, "Failed to register netdev\n"); @@ -1269,6 +1319,10 @@ static int nic_dev_init(struct pci_dev *pdev) return 0; err_reg_netdev: + hinic_func_table_debug_rem(nic_dev); +err_add_func_table_dbg: + hinic_func_tbl_dbgfs_uninit(nic_dev); + hinic_dbg_uninit(nic_dev); hinic_free_intr_coalesce(nic_dev); err_init_intr: err_set_pfc: @@ -1391,6 +1445,12 @@ static void hinic_remove(struct pci_dev *pdev) unregister_netdev(netdev); + hinic_func_table_debug_rem(nic_dev); + + hinic_func_tbl_dbgfs_uninit(nic_dev); + + hinic_dbg_uninit(nic_dev); + hinic_free_intr_coalesce(nic_dev); hinic_port_del_mac(nic_dev, netdev->dev_addr, 0); @@ -1445,4 +1505,17 @@ static struct pci_driver hinic_driver = { .sriov_configure = hinic_pci_sriov_configure, }; -module_pci_driver(hinic_driver); +static int __init hinic_module_init(void) +{ + hinic_dbg_register_debugfs(HINIC_DRV_NAME); + return pci_register_driver(&hinic_driver); +} + +static void __exit hinic_module_exit(void) +{ + pci_unregister_driver(&hinic_driver); + hinic_dbg_unregister_debugfs(); +} + +module_init(hinic_module_init); +module_exit(hinic_module_exit); diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 0273fb7a9d01..3153d62cc73e 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3247,7 +3247,7 @@ static int ehea_mem_notifier(struct notifier_block *nb, switch (action) { case MEM_CANCEL_OFFLINE: pr_info("memory offlining canceled"); - /* Fall through - re-add canceled memory block */ + fallthrough; /* re-add canceled memory block */ case MEM_ONLINE: pr_info("memory is going online"); diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 06248a7db7f2..c00b9097eeea 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2319,7 +2319,7 @@ static int emac_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd) switch (cmd) { case SIOCGMIIPHY: data->phy_id = dev->phy.address; - /* Fall through */ + fallthrough; case SIOCGMIIREG: data->val_out = emac_mdio_read(ndev, dev->phy.address, data->reg_num); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5afb3c9c52d2..6b619c190239 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -104,8 +104,7 @@ static int send_login(struct ibmvnic_adapter *adapter); static void send_cap_queries(struct ibmvnic_adapter *adapter); static int init_sub_crqs(struct ibmvnic_adapter *); static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter); -static int ibmvnic_init(struct ibmvnic_adapter *); -static int ibmvnic_reset_init(struct ibmvnic_adapter *); +static int ibmvnic_reset_init(struct ibmvnic_adapter *, bool reset); static void release_crq_queue(struct ibmvnic_adapter *); static int __ibmvnic_set_mac(struct net_device *, u8 *); static int init_crq_queue(struct ibmvnic_adapter *adapter); @@ -297,8 +296,7 @@ static void deactivate_rx_pools(struct ibmvnic_adapter *adapter) { int i; - for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - i++) + for (i = 0; i < adapter->num_active_rx_pools; i++) adapter->rx_pool[i].active = 0; } @@ -306,6 +304,7 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, struct ibmvnic_rx_pool *pool) { int count = pool->size - atomic_read(&pool->available); + u64 handle = adapter->rx_scrq[pool->index]->handle; struct device *dev = &adapter->vdev->dev; int buffers_added = 0; unsigned long lpar_rc; @@ -314,7 +313,6 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, unsigned int offset; dma_addr_t dma_addr; unsigned char *dst; - u64 *handle_array; int shift = 0; int index; int i; @@ -322,10 +320,6 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, if (!pool->active) return; - handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + - be32_to_cpu(adapter->login_rsp_buf-> - off_rxadd_subcrqs)); - for (i = 0; i < count; ++i) { skb = alloc_skb(pool->buff_size, GFP_ATOMIC); if (!skb) { @@ -369,8 +363,7 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, #endif sub_crq.rx_add.len = cpu_to_be32(pool->buff_size << shift); - lpar_rc = send_subcrq(adapter, handle_array[pool->index], - &sub_crq); + lpar_rc = send_subcrq(adapter, handle, &sub_crq); if (lpar_rc != H_SUCCESS) goto failure; @@ -407,8 +400,7 @@ static void replenish_pools(struct ibmvnic_adapter *adapter) int i; adapter->replenish_task_cycles++; - for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - i++) { + for (i = 0; i < adapter->num_active_rx_pools; i++) { if (adapter->rx_pool[i].active) replenish_rx_pool(adapter, &adapter->rx_pool[i]); } @@ -475,22 +467,23 @@ static int init_stats_token(struct ibmvnic_adapter *adapter) static int reset_rx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_rx_pool *rx_pool; + u64 buff_size; int rx_scrqs; int i, j, rc; - u64 *size_array; - size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + - be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); + if (!adapter->rx_pool) + return -1; - rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + buff_size = adapter->cur_rx_buf_sz; + rx_scrqs = adapter->num_active_rx_pools; for (i = 0; i < rx_scrqs; i++) { rx_pool = &adapter->rx_pool[i]; netdev_dbg(adapter->netdev, "Re-setting rx_pool[%d]\n", i); - if (rx_pool->buff_size != be64_to_cpu(size_array[i])) { + if (rx_pool->buff_size != buff_size) { free_long_term_buff(adapter, &rx_pool->long_term_buff); - rx_pool->buff_size = be64_to_cpu(size_array[i]); + rx_pool->buff_size = buff_size; rc = alloc_long_term_buff(adapter, &rx_pool->long_term_buff, rx_pool->size * @@ -558,13 +551,11 @@ static int init_rx_pools(struct net_device *netdev) struct device *dev = &adapter->vdev->dev; struct ibmvnic_rx_pool *rx_pool; int rxadd_subcrqs; - u64 *size_array; + u64 buff_size; int i, j; - rxadd_subcrqs = - be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + - be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); + rxadd_subcrqs = adapter->num_active_rx_scrqs; + buff_size = adapter->cur_rx_buf_sz; adapter->rx_pool = kcalloc(rxadd_subcrqs, sizeof(struct ibmvnic_rx_pool), @@ -582,11 +573,11 @@ static int init_rx_pools(struct net_device *netdev) netdev_dbg(adapter->netdev, "Initializing rx_pool[%d], %lld buffs, %lld bytes each\n", i, adapter->req_rx_add_entries_per_subcrq, - be64_to_cpu(size_array[i])); + buff_size); rx_pool->size = adapter->req_rx_add_entries_per_subcrq; rx_pool->index = i; - rx_pool->buff_size = be64_to_cpu(size_array[i]); + rx_pool->buff_size = buff_size; rx_pool->active = 1; rx_pool->free_map = kcalloc(rx_pool->size, sizeof(int), @@ -649,7 +640,10 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter) int tx_scrqs; int i, rc; - tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + if (!adapter->tx_pool) + return -1; + + tx_scrqs = adapter->num_active_tx_pools; for (i = 0; i < tx_scrqs; i++) { rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]); if (rc) @@ -738,7 +732,7 @@ static int init_tx_pools(struct net_device *netdev) int tx_subcrqs; int i, rc; - tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + tx_subcrqs = adapter->num_active_tx_scrqs; adapter->tx_pool = kcalloc(tx_subcrqs, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL); if (!adapter->tx_pool) @@ -974,7 +968,7 @@ static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state) return -1; } - if (adapter->init_done_rc == 1) { + if (adapter->init_done_rc == PARTIALSUCCESS) { /* Partuial success, delay and re-send */ mdelay(1000); resend = true; @@ -1524,9 +1518,9 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) unsigned int offset; int num_entries = 1; unsigned char *dst; - u64 *handle_array; int index = 0; u8 proto = 0; + u64 handle; netdev_tx_t ret = NETDEV_TX_OK; if (test_bit(0, &adapter->resetting)) { @@ -1553,8 +1547,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_scrq = adapter->tx_scrq[queue_num]; txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb)); - handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + - be32_to_cpu(adapter->login_rsp_buf->off_txsubm_subcrqs)); + handle = tx_scrq->handle; index = tx_pool->free_map[tx_pool->consumer_index]; @@ -1666,14 +1659,14 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) ret = NETDEV_TX_OK; goto tx_err_out; } - lpar_rc = send_subcrq_indirect(adapter, handle_array[queue_num], + lpar_rc = send_subcrq_indirect(adapter, handle, (u64)tx_buff->indir_dma, (u64)num_entries); dma_unmap_single(dev, tx_buff->indir_dma, sizeof(tx_buff->indir_arr), DMA_TO_DEVICE); } else { tx_buff->num_entries = num_entries; - lpar_rc = send_subcrq(adapter, handle_array[queue_num], + lpar_rc = send_subcrq(adapter, handle, &tx_crq); } if (lpar_rc != H_SUCCESS) { @@ -1868,7 +1861,7 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, return rc; } - rc = ibmvnic_reset_init(adapter); + rc = ibmvnic_reset_init(adapter, true); if (rc) return IBMVNIC_INIT_FAILED; @@ -1986,7 +1979,7 @@ static int do_reset(struct ibmvnic_adapter *adapter, goto out; } - rc = ibmvnic_reset_init(adapter); + rc = ibmvnic_reset_init(adapter, true); if (rc) { rc = IBMVNIC_INIT_FAILED; goto out; @@ -2011,7 +2004,10 @@ static int do_reset(struct ibmvnic_adapter *adapter, adapter->req_rx_add_entries_per_subcrq != old_num_rx_slots || adapter->req_tx_entries_per_subcrq != - old_num_tx_slots) { + old_num_tx_slots || + !adapter->rx_pool || + !adapter->tso_pool || + !adapter->tx_pool) { release_rx_pools(adapter); release_tx_pools(adapter); release_napi(adapter); @@ -2024,10 +2020,14 @@ static int do_reset(struct ibmvnic_adapter *adapter, } else { rc = reset_tx_pools(adapter); if (rc) + netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n", + rc); goto out; rc = reset_rx_pools(adapter); if (rc) + netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n", + rc); goto out; } ibmvnic_disable_irqs(adapter); @@ -2093,7 +2093,7 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, return rc; } - rc = ibmvnic_init(adapter); + rc = ibmvnic_reset_init(adapter, false); if (rc) return rc; @@ -3568,8 +3568,7 @@ static int ibmvnic_send_crq(struct ibmvnic_adapter *adapter, if (rc) { if (rc == H_CLOSED) { dev_warn(dev, "CRQ Queue closed\n"); - if (test_bit(0, &adapter->resetting)) - ibmvnic_reset(adapter, VNIC_RESET_FATAL); + /* do not reset, report the fail, wait for passive init from server */ } dev_warn(dev, "Send error (rc=%d)\n", rc); @@ -3580,14 +3579,31 @@ static int ibmvnic_send_crq(struct ibmvnic_adapter *adapter, static int ibmvnic_send_crq_init(struct ibmvnic_adapter *adapter) { + struct device *dev = &adapter->vdev->dev; union ibmvnic_crq crq; + int retries = 100; + int rc; memset(&crq, 0, sizeof(crq)); crq.generic.first = IBMVNIC_CRQ_INIT_CMD; crq.generic.cmd = IBMVNIC_CRQ_INIT; netdev_dbg(adapter->netdev, "Sending CRQ init\n"); - return ibmvnic_send_crq(adapter, &crq); + do { + rc = ibmvnic_send_crq(adapter, &crq); + if (rc != H_CLOSED) + break; + retries--; + msleep(50); + + } while (retries > 0); + + if (rc) { + dev_err(dev, "Failed to send init request, rc = %d\n", rc); + return rc; + } + + return 0; } static int send_version_xchg(struct ibmvnic_adapter *adapter) @@ -4292,6 +4308,11 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, struct net_device *netdev = adapter->netdev; struct ibmvnic_login_rsp_buffer *login_rsp = adapter->login_rsp_buf; struct ibmvnic_login_buffer *login = adapter->login_buf; + u64 *tx_handle_array; + u64 *rx_handle_array; + int num_tx_pools; + int num_rx_pools; + u64 *size_array; int i; dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, @@ -4326,6 +4347,30 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, ibmvnic_remove(adapter->vdev); return -EIO; } + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); + /* variable buffer sizes are not supported, so just read the + * first entry. + */ + adapter->cur_rx_buf_sz = be64_to_cpu(size_array[0]); + + num_tx_pools = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + num_rx_pools = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + + tx_handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf->off_txsubm_subcrqs)); + rx_handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_subcrqs)); + + for (i = 0; i < num_tx_pools; i++) + adapter->tx_scrq[i]->handle = tx_handle_array[i]; + + for (i = 0; i < num_rx_pools; i++) + adapter->rx_scrq[i]->handle = rx_handle_array[i]; + + adapter->num_active_tx_scrqs = num_tx_pools; + adapter->num_active_rx_scrqs = num_rx_pools; + release_login_rsp_buffer(adapter); release_login_buffer(adapter); complete(&adapter->init_done); @@ -4971,7 +5016,7 @@ map_failed: return retrc; } -static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) +static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset) { struct device *dev = &adapter->vdev->dev; unsigned long timeout = msecs_to_jiffies(30000); @@ -4980,12 +5025,19 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) adapter->from_passive_init = false; - old_num_rx_queues = adapter->req_rx_queues; - old_num_tx_queues = adapter->req_tx_queues; + if (reset) { + old_num_rx_queues = adapter->req_rx_queues; + old_num_tx_queues = adapter->req_tx_queues; + reinit_completion(&adapter->init_done); + } - reinit_completion(&adapter->init_done); adapter->init_done_rc = 0; - ibmvnic_send_crq_init(adapter); + rc = ibmvnic_send_crq_init(adapter); + if (rc) { + dev_err(dev, "Send crq init failed with error %d\n", rc); + return rc; + } + if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { dev_err(dev, "Initialization sequence timed out\n"); return -1; @@ -4996,13 +5048,8 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) return adapter->init_done_rc; } - if (adapter->from_passive_init) { - adapter->state = VNIC_OPEN; - adapter->from_passive_init = false; - return -1; - } - - if (test_bit(0, &adapter->resetting) && !adapter->wait_for_reset && + if (reset && + test_bit(0, &adapter->resetting) && !adapter->wait_for_reset && adapter->reset_reason != VNIC_RESET_MOBILITY) { if (adapter->req_rx_queues != old_num_rx_queues || adapter->req_tx_queues != old_num_tx_queues) { @@ -5030,48 +5077,6 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) return rc; } -static int ibmvnic_init(struct ibmvnic_adapter *adapter) -{ - struct device *dev = &adapter->vdev->dev; - unsigned long timeout = msecs_to_jiffies(30000); - int rc; - - adapter->from_passive_init = false; - - adapter->init_done_rc = 0; - ibmvnic_send_crq_init(adapter); - if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { - dev_err(dev, "Initialization sequence timed out\n"); - return -1; - } - - if (adapter->init_done_rc) { - release_crq_queue(adapter); - return adapter->init_done_rc; - } - - if (adapter->from_passive_init) { - adapter->state = VNIC_OPEN; - adapter->from_passive_init = false; - return -1; - } - - rc = init_sub_crqs(adapter); - if (rc) { - dev_err(dev, "Initialization of sub crqs failed\n"); - release_crq_queue(adapter); - return rc; - } - - rc = init_sub_crq_irqs(adapter); - if (rc) { - dev_err(dev, "Failed to initialize sub crq irqs\n"); - release_crq_queue(adapter); - } - - return rc; -} - static struct device_attribute dev_attr_failover; static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) @@ -5134,7 +5139,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) goto ibmvnic_init_fail; } - rc = ibmvnic_init(adapter); + rc = ibmvnic_reset_init(adapter, false); if (rc && rc != EAGAIN) goto ibmvnic_init_fail; } while (rc == EAGAIN); @@ -5284,8 +5289,7 @@ static unsigned long ibmvnic_get_desired_dma(struct vio_dev *vdev) for (i = 0; i < adapter->req_tx_queues + adapter->req_rx_queues; i++) ret += 4 * PAGE_SIZE; /* the scrq message queue */ - for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - i++) + for (i = 0; i < adapter->num_active_rx_pools; i++) ret += adapter->rx_pool[i].size * IOMMU_PAGE_ALIGN(adapter->rx_pool[i].buff_size, tbl); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index f8416e1d4cf0..8da98794eda9 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -875,6 +875,7 @@ struct ibmvnic_sub_crq_queue { struct ibmvnic_adapter *adapter; atomic_t used; char name[32]; + u64 handle; }; struct ibmvnic_long_term_buff { @@ -1075,6 +1076,7 @@ struct ibmvnic_adapter { u32 num_active_rx_napi; u32 num_active_tx_scrqs; u32 num_active_tx_pools; + u32 cur_rx_buf_sz; struct tasklet_struct tasklet; enum vnic_state state; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 63dde3bcf5bc..664e8ccc88d2 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -4079,7 +4079,6 @@ void e1000e_reset(struct e1000_adapter *adapter) case e1000_pch_lpt: case e1000_pch_spt: case e1000_pch_cnp: - fallthrough; case e1000_pch_tgp: case e1000_pch_adp: fc->refresh_time = 0xFFFF; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index d88dd41a9442..99b8252eb969 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -310,10 +310,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, rx_buffer->page_offset; /* prefetch first cache line of first page */ - prefetch(page_addr); -#if L1_CACHE_BYTES < 128 - prefetch((void *)((u8 *)page_addr + L1_CACHE_BYTES)); -#endif + net_prefetch(page_addr); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index a62ddd626929..c0c8efe42fce 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -981,7 +981,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes { #define I40E_AQC_SET_VSI_PROMISC_BROADCAST 0x04 #define I40E_AQC_SET_VSI_DEFAULT 0x08 #define I40E_AQC_SET_VSI_PROMISC_VLAN 0x10 -#define I40E_AQC_SET_VSI_PROMISC_TX 0x8000 +#define I40E_AQC_SET_VSI_PROMISC_RX_ONLY 0x8000 __le16 seid; __le16 vlan_tag; #define I40E_AQC_SET_VSI_VLAN_VALID 0x8000 diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index afad5e9f80e0..6ab52cbd697a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1967,6 +1967,21 @@ i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags, } /** + * i40e_is_aq_api_ver_ge + * @aq: pointer to AdminQ info containing HW API version to compare + * @maj: API major value + * @min: API minor value + * + * Assert whether current HW API version is greater/equal than provided. + **/ +static bool i40e_is_aq_api_ver_ge(struct i40e_adminq_info *aq, u16 maj, + u16 min) +{ + return (aq->api_maj_ver > maj || + (aq->api_maj_ver == maj && aq->api_min_ver >= min)); +} + +/** * i40e_aq_add_vsi * @hw: pointer to the hw struct * @vsi_ctx: pointer to a vsi context struct @@ -2091,18 +2106,16 @@ i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, if (set) { flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST; - if (rx_only_promisc && - (((hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver >= 5)) || - (hw->aq.api_maj_ver > 1))) - flags |= I40E_AQC_SET_VSI_PROMISC_TX; + if (rx_only_promisc && i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY; } cmd->promiscuous_flags = cpu_to_le16(flags); cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST); - if (((hw->aq.api_maj_ver >= 1) && (hw->aq.api_min_ver >= 5)) || - (hw->aq.api_maj_ver > 1)) - cmd->valid_flags |= cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_TX); + if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + cmd->valid_flags |= + cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY); cmd->seid = cpu_to_le16(seid); status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); @@ -2199,11 +2212,17 @@ enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); - if (enable) + if (enable) { flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST; + if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY; + } cmd->promiscuous_flags = cpu_to_le16(flags); cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST); + if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + cmd->valid_flags |= + cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY); cmd->seid = cpu_to_le16(seid); cmd->vlan_tag = cpu_to_le16(vid | I40E_AQC_SET_VSI_VLAN_VALID); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 825c104ecba1..dc1577156bb6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1967,7 +1967,7 @@ static int i40e_set_ringparam(struct net_device *netdev, (new_rx_count == vsi->rx_rings[0]->count)) return 0; - /* If there is a AF_XDP UMEM attached to any of Rx rings, + /* If there is a AF_XDP page pool attached to any of Rx rings, * disallow changing the number of descriptors -- regardless * if the netdev is running or not. */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b5399357a667..05c6d3ea11e6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3122,12 +3122,12 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring) } /** - * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled + * i40e_xsk_pool - Retrieve the AF_XDP buffer pool if XDP and ZC is enabled * @ring: The Tx or Rx ring * - * Returns the UMEM or NULL. + * Returns the AF_XDP buffer pool or NULL. **/ -static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) +static struct xsk_buff_pool *i40e_xsk_pool(struct i40e_ring *ring) { bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi); int qid = ring->queue_index; @@ -3138,7 +3138,7 @@ static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps)) return NULL; - return xdp_get_umem_from_qid(ring->vsi->netdev, qid); + return xsk_get_pool_from_qid(ring->vsi->netdev, qid); } /** @@ -3157,7 +3157,7 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) u32 qtx_ctl = 0; if (ring_is_xdp(ring)) - ring->xsk_umem = i40e_xsk_umem(ring); + ring->xsk_pool = i40e_xsk_pool(ring); /* some ATR related tx ring init */ if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) { @@ -3280,12 +3280,13 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); kfree(ring->rx_bi); - ring->xsk_umem = i40e_xsk_umem(ring); - if (ring->xsk_umem) { + ring->xsk_pool = i40e_xsk_pool(ring); + if (ring->xsk_pool) { ret = i40e_alloc_rx_bi_zc(ring); if (ret) return ret; - ring->rx_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem); + ring->rx_buf_len = + xsk_pool_get_rx_frame_size(ring->xsk_pool); /* For AF_XDP ZC, we disallow packets to span on * multiple buffers, thus letting us skip that * handling in the fast-path. @@ -3368,8 +3369,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); - if (ring->xsk_umem) { - xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq); + if (ring->xsk_pool) { + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)); } else { ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); @@ -3380,7 +3381,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) */ dev_info(&vsi->back->pdev->dev, "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n", - ring->xsk_umem ? "UMEM enabled " : "", + ring->xsk_pool ? "AF_XDP ZC enabled " : "", ring->queue_index, pf_q); } @@ -12644,7 +12645,7 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, */ if (need_reset && prog) for (i = 0; i < vsi->num_queue_pairs; i++) - if (vsi->xdp_rings[i]->xsk_umem) + if (vsi->xdp_rings[i]->xsk_pool) (void)i40e_xsk_wakeup(vsi->netdev, i, XDP_WAKEUP_RX); @@ -12923,8 +12924,8 @@ static int i40e_xdp(struct net_device *dev, switch (xdp->command) { case XDP_SETUP_PROG: return i40e_xdp_setup(vsi, xdp->prog); - case XDP_SETUP_XSK_UMEM: - return i40e_xsk_umem_setup(vsi, xdp->xsk.umem, + case XDP_SETUP_XSK_POOL: + return i40e_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; @@ -15463,6 +15464,9 @@ static void i40e_remove(struct pci_dev *pdev) i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0); i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0); + while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + usleep_range(1000, 2000); + /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 3e5c566ceb01..91ab824926b9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -636,7 +636,7 @@ void i40e_clean_tx_ring(struct i40e_ring *tx_ring) unsigned long bi_size; u16 i; - if (ring_is_xdp(tx_ring) && tx_ring->xsk_umem) { + if (ring_is_xdp(tx_ring) && tx_ring->xsk_pool) { i40e_xsk_clean_tx_ring(tx_ring); } else { /* ring already cleared, nothing to do */ @@ -1335,7 +1335,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) rx_ring->skb = NULL; } - if (rx_ring->xsk_umem) { + if (rx_ring->xsk_pool) { i40e_xsk_clean_rx_ring(rx_ring); goto skip_free; } @@ -1369,7 +1369,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) } skip_free: - if (rx_ring->xsk_umem) + if (rx_ring->xsk_pool) i40e_clear_rx_bi_zc(rx_ring); else i40e_clear_rx_bi(rx_ring); @@ -1992,10 +1992,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(xdp->data); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data); + /* Note, we get here by enabling legacy-rx via: * * ethtool --set-priv-flags <dev> legacy-rx on @@ -2078,10 +2076,8 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * likely have a consumer accessing first few bytes of meta * data, and then actual data. */ - prefetch(xdp->data_meta); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data_meta + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data_meta); + /* build an skb around the page buffer */ skb = build_skb(xdp->data_hard_start, truesize); if (unlikely(!skb)) @@ -2579,7 +2575,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ i40e_for_each_ring(ring, q_vector->tx) { - bool wd = ring->xsk_umem ? + bool wd = ring->xsk_pool ? i40e_clean_xdp_tx_irq(vsi, ring) : i40e_clean_tx_irq(vsi, ring, budget); @@ -2607,7 +2603,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) budget_per_ring = budget; i40e_for_each_ring(ring, q_vector->rx) { - int cleaned = ring->xsk_umem ? + int cleaned = ring->xsk_pool ? i40e_clean_rx_irq_zc(ring, budget_per_ring) : i40e_clean_rx_irq(ring, budget_per_ring); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 4036893d6825..703b644fd71f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -388,7 +388,7 @@ struct i40e_ring { struct i40e_channel *ch; struct xdp_rxq_info xdp_rxq; - struct xdp_umem *xsk_umem; + struct xsk_buff_pool *xsk_pool; } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 8ce57b507a21..2a1153d8957b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -29,14 +29,16 @@ static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx) } /** - * i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid + * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a + * certain ring/qid * @vsi: Current VSI - * @umem: UMEM - * @qid: Rx ring to associate UMEM to + * @pool: buffer pool + * @qid: Rx ring to associate buffer pool with * * Returns 0 on success, <0 on failure **/ -static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, +static int i40e_xsk_pool_enable(struct i40e_vsi *vsi, + struct xsk_buff_pool *pool, u16 qid) { struct net_device *netdev = vsi->netdev; @@ -53,7 +55,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, qid >= netdev->real_num_tx_queues) return -EINVAL; - err = xsk_buff_dma_map(umem, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR); + err = xsk_pool_dma_map(pool, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR); if (err) return err; @@ -80,21 +82,22 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, } /** - * i40e_xsk_umem_disable - Disassociate a UMEM from a certain ring/qid + * i40e_xsk_pool_disable - Disassociate an AF_XDP buffer pool from a + * certain ring/qid * @vsi: Current VSI - * @qid: Rx ring to associate UMEM to + * @qid: Rx ring to associate buffer pool with * * Returns 0 on success, <0 on failure **/ -static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) +static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid) { struct net_device *netdev = vsi->netdev; - struct xdp_umem *umem; + struct xsk_buff_pool *pool; bool if_running; int err; - umem = xdp_get_umem_from_qid(netdev, qid); - if (!umem) + pool = xsk_get_pool_from_qid(netdev, qid); + if (!pool) return -EINVAL; if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi); @@ -106,7 +109,7 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) } clear_bit(qid, vsi->af_xdp_zc_qps); - xsk_buff_dma_unmap(umem, I40E_RX_DMA_ATTR); + xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR); if (if_running) { err = i40e_queue_pair_enable(vsi, qid); @@ -118,20 +121,21 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) } /** - * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid + * i40e_xsk_pool_setup - Enable/disassociate an AF_XDP buffer pool to/from + * a ring/qid * @vsi: Current VSI - * @umem: UMEM to enable/associate to a ring, or NULL to disable - * @qid: Rx ring to (dis)associate UMEM (from)to + * @pool: Buffer pool to enable/associate to a ring, or NULL to disable + * @qid: Rx ring to (dis)associate buffer pool (from)to * - * This function enables or disables a UMEM to a certain ring. + * This function enables or disables a buffer pool to a certain ring. * * Returns 0 on success, <0 on failure **/ -int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, +int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) { - return umem ? i40e_xsk_umem_enable(vsi, umem, qid) : - i40e_xsk_umem_disable(vsi, qid); + return pool ? i40e_xsk_pool_enable(vsi, pool, qid) : + i40e_xsk_pool_disable(vsi, qid); } /** @@ -191,7 +195,7 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) rx_desc = I40E_RX_DESC(rx_ring, ntu); bi = i40e_rx_bi(rx_ring, ntu); do { - xdp = xsk_buff_alloc(rx_ring->xsk_umem); + xdp = xsk_buff_alloc(rx_ring->xsk_pool); if (!xdp) { ok = false; goto no_buffers; @@ -310,7 +314,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); (*bi)->data_end = (*bi)->data + size; - xsk_buff_dma_sync_for_cpu(*bi); + xsk_buff_dma_sync_for_cpu(*bi, rx_ring->xsk_pool); xdp_res = i40e_run_xdp_zc(rx_ring, *bi); if (xdp_res) { @@ -358,11 +362,11 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) i40e_finalize_xdp_rx(rx_ring, xdp_xmit); i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); - if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) { + if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_umem); + xsk_set_rx_need_wakeup(rx_ring->xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_umem); + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); return (int)total_rx_packets; } @@ -385,11 +389,11 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) dma_addr_t dma; while (budget-- > 0) { - if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) + if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc)) break; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma, + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc.len); tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use]; @@ -416,7 +420,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) I40E_TXD_QW1_CMD_SHIFT); i40e_xdp_ring_update_tail(xdp_ring); - xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + xsk_tx_release(xdp_ring->xsk_pool); i40e_update_tx_stats(xdp_ring, sent_frames, total_bytes); } @@ -448,7 +452,7 @@ static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring, **/ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring) { - struct xdp_umem *umem = tx_ring->xsk_umem; + struct xsk_buff_pool *bp = tx_ring->xsk_pool; u32 i, completed_frames, xsk_frames = 0; u32 head_idx = i40e_get_head(tx_ring); struct i40e_tx_buffer *tx_bi; @@ -488,13 +492,13 @@ skip: tx_ring->next_to_clean -= tx_ring->count; if (xsk_frames) - xsk_umem_complete_tx(umem, xsk_frames); + xsk_tx_completed(bp, xsk_frames); i40e_arm_wb(tx_ring, vsi, completed_frames); out_xmit: - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); + if (xsk_uses_need_wakeup(tx_ring->xsk_pool)) + xsk_set_tx_need_wakeup(tx_ring->xsk_pool); return i40e_xmit_zc(tx_ring, I40E_DESC_UNUSED(tx_ring)); } @@ -526,7 +530,7 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) if (queue_id >= vsi->num_queue_pairs) return -ENXIO; - if (!vsi->xdp_rings[queue_id]->xsk_umem) + if (!vsi->xdp_rings[queue_id]->xsk_pool) return -ENXIO; ring = vsi->xdp_rings[queue_id]; @@ -565,7 +569,7 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring) void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring) { u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; - struct xdp_umem *umem = tx_ring->xsk_umem; + struct xsk_buff_pool *bp = tx_ring->xsk_pool; struct i40e_tx_buffer *tx_bi; u32 xsk_frames = 0; @@ -585,14 +589,15 @@ void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring) } if (xsk_frames) - xsk_umem_complete_tx(umem, xsk_frames); + xsk_tx_completed(bp, xsk_frames); } /** - * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have AF_XDP UMEM attached + * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have an AF_XDP + * buffer pool attached * @vsi: vsi * - * Returns true if any of the Rx rings has an AF_XDP UMEM attached + * Returns true if any of the Rx rings has an AF_XDP buffer pool attached **/ bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi) { @@ -600,7 +605,7 @@ bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi) int i; for (i = 0; i < vsi->num_queue_pairs; i++) { - if (xdp_get_umem_from_qid(netdev, i)) + if (xsk_get_pool_from_qid(netdev, i)) return true; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index c524c142127f..7adfd8539247 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -5,12 +5,12 @@ #define _I40E_XSK_H_ struct i40e_vsi; -struct xdp_umem; +struct xsk_buff_pool; struct zero_copy_allocator; int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair); int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair); -int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, +int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool, u16 qid); bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count); int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index ca041b39ffda..256fa07d54d5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1309,10 +1309,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring, return NULL; /* prefetch first cache line of first page */ va = page_address(rx_buffer->page) + rx_buffer->page_offset; - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* allocate a skb to store the frags */ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, @@ -1376,10 +1373,8 @@ static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring, return NULL; /* prefetch first cache line of first page */ va = page_address(rx_buffer->page) + rx_buffer->page_offset; - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); + /* build an skb around the page buffer */ skb = build_skb(va - IAVF_SKB_PAD, truesize); if (unlikely(!skb)) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index fe140ff38f74..65583f0a1797 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -321,9 +321,9 @@ struct ice_vsi { struct ice_ring **xdp_rings; /* XDP ring array */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ - struct xdp_umem **xsk_umems; - u16 num_xsk_umems_used; - u16 num_xsk_umems; + struct xsk_buff_pool **xsk_pools; + u16 num_xsk_pools_used; + u16 num_xsk_pools; } ____cacheline_internodealigned_in_smp; /* struct that defines an interrupt vector */ @@ -507,25 +507,25 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring) } /** - * ice_xsk_umem - get XDP UMEM bound to a ring + * ice_xsk_pool - get XSK buffer pool bound to a ring * @ring - ring to use * - * Returns a pointer to xdp_umem structure if there is an UMEM present, + * Returns a pointer to xdp_umem structure if there is a buffer pool present, * NULL otherwise. */ -static inline struct xdp_umem *ice_xsk_umem(struct ice_ring *ring) +static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring) { - struct xdp_umem **umems = ring->vsi->xsk_umems; + struct xsk_buff_pool **pools = ring->vsi->xsk_pools; u16 qid = ring->q_index; if (ice_ring_is_xdp(ring)) qid -= ring->vsi->num_xdp_txq; - if (qid >= ring->vsi->num_xsk_umems || !umems || !umems[qid] || + if (qid >= ring->vsi->num_xsk_pools || !pools || !pools[qid] || !ice_is_xdp_ena_vsi(ring->vsi)) return NULL; - return umems[qid]; + return pools[qid]; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 87008476d8fe..fe4320e2d1f2 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -308,12 +308,12 @@ int ice_setup_rx_ctx(struct ice_ring *ring) xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index); - ring->xsk_umem = ice_xsk_umem(ring); - if (ring->xsk_umem) { + ring->xsk_pool = ice_xsk_pool(ring); + if (ring->xsk_pool) { xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); ring->rx_buf_len = - xsk_umem_get_rx_frame_size(ring->xsk_umem); + xsk_pool_get_rx_frame_size(ring->xsk_pool); /* For AF_XDP ZC, we disallow packets to span on * multiple buffers, thus letting us skip that * handling in the fast-path. @@ -324,7 +324,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) NULL); if (err) return err; - xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); @@ -417,9 +417,9 @@ int ice_setup_rx_ctx(struct ice_ring *ring) ring->tail = hw->hw_addr + QRX_TAIL(pf_q); writel(0, ring->tail); - if (ring->xsk_umem) { - if (!xsk_buff_can_alloc(ring->xsk_umem, num_bufs)) { - dev_warn(dev, "UMEM does not provide enough addresses to fill %d buffers on Rx ring %d\n", + if (ring->xsk_pool) { + if (!xsk_buff_can_alloc(ring->xsk_pool, num_bufs)) { + dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n", num_bufs, ring->q_index); dev_warn(dev, "Change Rx ring/fill queue size to avoid performance issues\n"); @@ -428,7 +428,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) err = ice_alloc_rx_bufs_zc(ring, num_bufs); if (err) - dev_info(dev, "Failed to allocate some buffers on UMEM enabled Rx ring %d (pf_q %d)\n", + dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n", ring->q_index, pf_q); return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index f2682776f8c8..feeb5cdccdc5 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1743,7 +1743,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) return ret; for (i = 0; i < vsi->num_xdp_txq; i++) - vsi->xdp_rings[i]->xsk_umem = ice_xsk_umem(vsi->xdp_rings[i]); + vsi->xdp_rings[i]->xsk_pool = ice_xsk_pool(vsi->xdp_rings[i]); return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4634b48949bb..2297ee7dba26 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2273,7 +2273,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_umem = ice_xsk_umem(xdp_ring); + xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring); } return 0; @@ -2517,13 +2517,13 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (if_running) ret = ice_up(vsi); - if (!ret && prog && vsi->xsk_umems) { + if (!ret && prog && vsi->xsk_pools) { int i; ice_for_each_rxq(vsi, i) { struct ice_ring *rx_ring = vsi->rx_rings[i]; - if (rx_ring->xsk_umem) + if (rx_ring->xsk_pool) napi_schedule(&rx_ring->q_vector->napi); } } @@ -2549,8 +2549,8 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); - case XDP_SETUP_XSK_UMEM: - return ice_xsk_umem_setup(vsi, xdp->xsk.umem, + case XDP_SETUP_XSK_POOL: + return ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 9d0d6b0025cf..eae75260fe20 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -145,7 +145,7 @@ void ice_clean_tx_ring(struct ice_ring *tx_ring) { u16 i; - if (ice_ring_is_xdp(tx_ring) && tx_ring->xsk_umem) { + if (ice_ring_is_xdp(tx_ring) && tx_ring->xsk_pool) { ice_xsk_clean_xdp_ring(tx_ring); goto tx_skip_free; } @@ -375,7 +375,7 @@ void ice_clean_rx_ring(struct ice_ring *rx_ring) if (!rx_ring->rx_buf) return; - if (rx_ring->xsk_umem) { + if (rx_ring->xsk_pool) { ice_xsk_clean_rx_ring(rx_ring); goto rx_skip_free; } @@ -919,10 +919,7 @@ ice_build_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * likely have a consumer accessing first few bytes of meta * data, and then actual data. */ - prefetch(xdp->data_meta); -#if L1_CACHE_BYTES < 128 - prefetch((void *)(xdp->data + L1_CACHE_BYTES)); -#endif + net_prefetch(xdp->data_meta); /* build an skb around the page buffer */ skb = build_skb(xdp->data_hard_start, truesize); if (unlikely(!skb)) @@ -964,10 +961,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(xdp->data); -#if L1_CACHE_BYTES < 128 - prefetch((void *)(xdp->data + L1_CACHE_BYTES)); -#endif /* L1_CACHE_BYTES */ + net_prefetch(xdp->data); /* allocate a skb to store the frags */ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE, @@ -1616,7 +1610,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ ice_for_each_ring(ring, q_vector->tx) { - bool wd = ring->xsk_umem ? + bool wd = ring->xsk_pool ? ice_clean_tx_irq_zc(ring, budget) : ice_clean_tx_irq(ring, budget); @@ -1646,7 +1640,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * comparison in the irq context instead of many inside the * ice_clean_rx_irq function and makes the codebase cleaner. */ - cleaned = ring->xsk_umem ? + cleaned = ring->xsk_pool ? ice_clean_rx_irq_zc(ring, budget_per_ring) : ice_clean_rx_irq(ring, budget_per_ring); work_done += cleaned; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 51b4df7a59d2..e9f60d550fcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -295,7 +295,7 @@ struct ice_ring { struct rcu_head rcu; /* to avoid race on free */ struct bpf_prog *xdp_prog; - struct xdp_umem *xsk_umem; + struct xsk_buff_pool *xsk_pool; /* CL3 - 3rd cacheline starts here */ struct xdp_rxq_info xdp_rxq; /* CLX - the below items are only accessed infrequently and should be diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 20ac5fca68c6..797886524054 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -236,7 +236,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) goto free_buf; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_umem = ice_xsk_umem(xdp_ring); + xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring); } err = ice_setup_rx_ctx(rx_ring); @@ -260,21 +260,21 @@ free_buf: } /** - * ice_xsk_alloc_umems - allocate a UMEM region for an XDP socket - * @vsi: VSI to allocate the UMEM on + * ice_xsk_alloc_pools - allocate a buffer pool for an XDP socket + * @vsi: VSI to allocate the buffer pool on * * Returns 0 on success, negative on error */ -static int ice_xsk_alloc_umems(struct ice_vsi *vsi) +static int ice_xsk_alloc_pools(struct ice_vsi *vsi) { - if (vsi->xsk_umems) + if (vsi->xsk_pools) return 0; - vsi->xsk_umems = kcalloc(vsi->num_xsk_umems, sizeof(*vsi->xsk_umems), + vsi->xsk_pools = kcalloc(vsi->num_xsk_pools, sizeof(*vsi->xsk_pools), GFP_KERNEL); - if (!vsi->xsk_umems) { - vsi->num_xsk_umems = 0; + if (!vsi->xsk_pools) { + vsi->num_xsk_pools = 0; return -ENOMEM; } @@ -282,73 +282,73 @@ static int ice_xsk_alloc_umems(struct ice_vsi *vsi) } /** - * ice_xsk_remove_umem - Remove an UMEM for a certain ring/qid + * ice_xsk_remove_pool - Remove an buffer pool for a certain ring/qid * @vsi: VSI from which the VSI will be removed - * @qid: Ring/qid associated with the UMEM + * @qid: Ring/qid associated with the buffer pool */ -static void ice_xsk_remove_umem(struct ice_vsi *vsi, u16 qid) +static void ice_xsk_remove_pool(struct ice_vsi *vsi, u16 qid) { - vsi->xsk_umems[qid] = NULL; - vsi->num_xsk_umems_used--; + vsi->xsk_pools[qid] = NULL; + vsi->num_xsk_pools_used--; - if (vsi->num_xsk_umems_used == 0) { - kfree(vsi->xsk_umems); - vsi->xsk_umems = NULL; - vsi->num_xsk_umems = 0; + if (vsi->num_xsk_pools_used == 0) { + kfree(vsi->xsk_pools); + vsi->xsk_pools = NULL; + vsi->num_xsk_pools = 0; } } /** - * ice_xsk_umem_disable - disable a UMEM region + * ice_xsk_pool_disable - disable a buffer pool region * @vsi: Current VSI * @qid: queue ID * * Returns 0 on success, negative on failure */ -static int ice_xsk_umem_disable(struct ice_vsi *vsi, u16 qid) +static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid) { - if (!vsi->xsk_umems || qid >= vsi->num_xsk_umems || - !vsi->xsk_umems[qid]) + if (!vsi->xsk_pools || qid >= vsi->num_xsk_pools || + !vsi->xsk_pools[qid]) return -EINVAL; - xsk_buff_dma_unmap(vsi->xsk_umems[qid], ICE_RX_DMA_ATTR); - ice_xsk_remove_umem(vsi, qid); + xsk_pool_dma_unmap(vsi->xsk_pools[qid], ICE_RX_DMA_ATTR); + ice_xsk_remove_pool(vsi, qid); return 0; } /** - * ice_xsk_umem_enable - enable a UMEM region + * ice_xsk_pool_enable - enable a buffer pool region * @vsi: Current VSI - * @umem: pointer to a requested UMEM region + * @pool: pointer to a requested buffer pool region * @qid: queue ID * * Returns 0 on success, negative on failure */ static int -ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) +ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) { int err; if (vsi->type != ICE_VSI_PF) return -EINVAL; - if (!vsi->num_xsk_umems) - vsi->num_xsk_umems = min_t(u16, vsi->num_rxq, vsi->num_txq); - if (qid >= vsi->num_xsk_umems) + if (!vsi->num_xsk_pools) + vsi->num_xsk_pools = min_t(u16, vsi->num_rxq, vsi->num_txq); + if (qid >= vsi->num_xsk_pools) return -EINVAL; - err = ice_xsk_alloc_umems(vsi); + err = ice_xsk_alloc_pools(vsi); if (err) return err; - if (vsi->xsk_umems && vsi->xsk_umems[qid]) + if (vsi->xsk_pools && vsi->xsk_pools[qid]) return -EBUSY; - vsi->xsk_umems[qid] = umem; - vsi->num_xsk_umems_used++; + vsi->xsk_pools[qid] = pool; + vsi->num_xsk_pools_used++; - err = xsk_buff_dma_map(vsi->xsk_umems[qid], ice_pf_to_dev(vsi->back), + err = xsk_pool_dma_map(vsi->xsk_pools[qid], ice_pf_to_dev(vsi->back), ICE_RX_DMA_ATTR); if (err) return err; @@ -357,17 +357,17 @@ ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) } /** - * ice_xsk_umem_setup - enable/disable a UMEM region depending on its state + * ice_xsk_pool_setup - enable/disable a buffer pool region depending on its state * @vsi: Current VSI - * @umem: UMEM to enable/associate to a ring, NULL to disable + * @pool: buffer pool to enable/associate to a ring, NULL to disable * @qid: queue ID * * Returns 0 on success, negative on failure */ -int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) +int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) { - bool if_running, umem_present = !!umem; - int ret = 0, umem_failure = 0; + bool if_running, pool_present = !!pool; + int ret = 0, pool_failure = 0; if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi); @@ -375,26 +375,26 @@ int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) ret = ice_qp_dis(vsi, qid); if (ret) { netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret); - goto xsk_umem_if_up; + goto xsk_pool_if_up; } } - umem_failure = umem_present ? ice_xsk_umem_enable(vsi, umem, qid) : - ice_xsk_umem_disable(vsi, qid); + pool_failure = pool_present ? ice_xsk_pool_enable(vsi, pool, qid) : + ice_xsk_pool_disable(vsi, qid); -xsk_umem_if_up: +xsk_pool_if_up: if (if_running) { ret = ice_qp_ena(vsi, qid); - if (!ret && umem_present) + if (!ret && pool_present) napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi); else if (ret) netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret); } - if (umem_failure) { - netdev_err(vsi->netdev, "Could not %sable UMEM, error = %d\n", - umem_present ? "en" : "dis", umem_failure); - return umem_failure; + if (pool_failure) { + netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n", + pool_present ? "en" : "dis", pool_failure); + return pool_failure; } return ret; @@ -425,7 +425,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) rx_buf = &rx_ring->rx_buf[ntu]; do { - rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_umem); + rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool); if (!rx_buf->xdp) { ret = true; break; @@ -595,7 +595,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; rx_buf->xdp->data_end = rx_buf->xdp->data + size; - xsk_buff_dma_sync_for_cpu(rx_buf->xdp); + xsk_buff_dma_sync_for_cpu(rx_buf->xdp, rx_ring->xsk_pool); xdp_res = ice_run_xdp_zc(rx_ring, rx_buf->xdp); if (xdp_res) { @@ -645,11 +645,11 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) ice_finalize_xdp_rx(rx_ring, xdp_xmit); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); - if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) { + if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_umem); + xsk_set_rx_need_wakeup(rx_ring->xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_umem); + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); return (int)total_rx_packets; } @@ -682,11 +682,11 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use]; - if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) + if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc)) break; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma, + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc.len); tx_buf->bytecount = desc.len; @@ -703,7 +703,7 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) if (tx_desc) { ice_xdp_ring_update_tail(xdp_ring); - xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + xsk_tx_release(xdp_ring->xsk_pool); } return budget > 0 && work_done; @@ -777,10 +777,10 @@ bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget) xdp_ring->next_to_clean = ntc; if (xsk_frames) - xsk_umem_complete_tx(xdp_ring->xsk_umem, xsk_frames); + xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) - xsk_set_tx_need_wakeup(xdp_ring->xsk_umem); + if (xsk_uses_need_wakeup(xdp_ring->xsk_pool)) + xsk_set_tx_need_wakeup(xdp_ring->xsk_pool); ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes); xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK); @@ -814,7 +814,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, if (queue_id >= vsi->num_txq) return -ENXIO; - if (!vsi->xdp_rings[queue_id]->xsk_umem) + if (!vsi->xdp_rings[queue_id]->xsk_pool) return -ENXIO; ring = vsi->xdp_rings[queue_id]; @@ -833,20 +833,20 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, } /** - * ice_xsk_any_rx_ring_ena - Checks if Rx rings have AF_XDP UMEM attached + * ice_xsk_any_rx_ring_ena - Checks if Rx rings have AF_XDP buff pool attached * @vsi: VSI to be checked * - * Returns true if any of the Rx rings has an AF_XDP UMEM attached + * Returns true if any of the Rx rings has an AF_XDP buff pool attached */ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi) { int i; - if (!vsi->xsk_umems) + if (!vsi->xsk_pools) return false; - for (i = 0; i < vsi->num_xsk_umems; i++) { - if (vsi->xsk_umems[i]) + for (i = 0; i < vsi->num_xsk_pools; i++) { + if (vsi->xsk_pools[i]) return true; } @@ -854,7 +854,7 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi) } /** - * ice_xsk_clean_rx_ring - clean UMEM queues connected to a given Rx ring + * ice_xsk_clean_rx_ring - clean buffer pool queues connected to a given Rx ring * @rx_ring: ring to be cleaned */ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) @@ -872,7 +872,7 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) } /** - * ice_xsk_clean_xdp_ring - Clean the XDP Tx ring and its UMEM queues + * ice_xsk_clean_xdp_ring - Clean the XDP Tx ring and its buffer pool queues * @xdp_ring: XDP_Tx ring */ void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) @@ -896,5 +896,5 @@ void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) } if (xsk_frames) - xsk_umem_complete_tx(xdp_ring->xsk_umem, xsk_frames); + xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index fc1a06b4df36..fad783690134 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -9,7 +9,8 @@ struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS -int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid); +int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, + u16 qid); int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget); bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); @@ -19,8 +20,8 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring); #else static inline int -ice_xsk_umem_setup(struct ice_vsi __always_unused *vsi, - struct xdp_umem __always_unused *umem, +ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, + struct xsk_buff_pool __always_unused *pool, u16 __always_unused qid) { return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 4f05f6efe6af..e1e37d0b7703 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -718,7 +718,6 @@ static void igb_cache_ring_register(struct igb_adapter *adapter) case e1000_i354: case e1000_i210: case e1000_i211: - fallthrough; default: for (; i < adapter->num_rx_queues; i++) adapter->rx_ring[i]->reg_idx = rbase_offset + i; @@ -8047,10 +8046,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); @@ -8104,10 +8100,7 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* build an skb around the page buffer */ skb = build_skb(va - IGB_SKB_PAD, truesize); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 7a6f2a0d413f..c6968fdb6caa 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1550,10 +1550,7 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* build an skb around the page buffer */ skb = build_skb(va - IGC_SKB_PAD, truesize); @@ -1589,10 +1586,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGC_RX_HDR_LEN); @@ -5142,6 +5136,8 @@ static int igc_probe(struct pci_dev *pdev, device_set_wakeup_enable(&adapter->pdev->dev, adapter->flags & IGC_FLAG_WOL_SUPPORTED); + igc_ptp_init(adapter); + /* reset the hardware with the new settings */ igc_reset(adapter); @@ -5158,9 +5154,6 @@ static int igc_probe(struct pci_dev *pdev, /* carrier off reporting is important to ethtool even BEFORE open */ netif_carrier_off(netdev); - /* do hw tstamp init after resetting */ - igc_ptp_init(adapter); - /* Check if Media Autosense is enabled */ adapter->ei = *ei; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index e67d4655b47e..36c999250fcc 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -496,8 +496,6 @@ void igc_ptp_init(struct igc_adapter *adapter) adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; - igc_ptp_reset(adapter); - adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, &adapter->pdev->dev); if (IS_ERR(adapter->ptp_clock)) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 1e8a809233a0..de0fc6ecf491 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -350,7 +350,7 @@ struct ixgbe_ring { struct ixgbe_rx_queue_stats rx_stats; }; struct xdp_rxq_info xdp_rxq; - struct xdp_umem *xsk_umem; + struct xsk_buff_pool *xsk_pool; u16 ring_idx; /* {rx,tx,xdp}_ring back reference idx */ u16 rx_buf_len; } ____cacheline_internodealigned_in_smp; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index e67b1a59ecb7..0fcd82036d4e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -193,7 +193,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, } /* alloc the udl from per cpu ddp pool */ - ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_KERNEL, &ddp->udp); + ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_ATOMIC, &ddp->udp); if (!ddp->udl) { e_err(drv, "failed allocated ddp context\n"); goto out_noddp_unmap; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 2e35c5706cf1..df389a11d3af 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1029,10 +1029,10 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx) WRITE_ONCE(adapter->rx_ring[ring->queue_index], NULL); adapter->q_vector[v_idx] = NULL; - napi_hash_del(&q_vector->napi); - netif_napi_del(&q_vector->napi); + __netif_napi_del(&q_vector->napi); /* + * after a call to __netif_napi_del() napi may still be used and * ixgbe_get_stats64() might access the rings on this vector, * we must wait a grace period before freeing it. */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 2f8a4cfc5fa1..0b675c34ce49 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2095,10 +2095,8 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(xdp->data); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data); + /* Note, we get here by enabling legacy-rx via: * * ethtool --set-priv-flags <dev> legacy-rx on @@ -2161,10 +2159,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, * likely have a consumer accessing first few bytes of meta * data, and then actual data. */ - prefetch(xdp->data_meta); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data_meta + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data_meta); /* build an skb to around the page buffer */ skb = build_skb(xdp->data_hard_start, truesize); @@ -3156,7 +3151,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) #endif ixgbe_for_each_ring(ring, q_vector->tx) { - bool wd = ring->xsk_umem ? + bool wd = ring->xsk_pool ? ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) : ixgbe_clean_tx_irq(q_vector, ring, budget); @@ -3176,7 +3171,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) per_ring_budget = budget; ixgbe_for_each_ring(ring, q_vector->rx) { - int cleaned = ring->xsk_umem ? + int cleaned = ring->xsk_pool ? ixgbe_clean_rx_irq_zc(q_vector, ring, per_ring_budget) : ixgbe_clean_rx_irq(q_vector, ring, @@ -3471,9 +3466,9 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, u32 txdctl = IXGBE_TXDCTL_ENABLE; u8 reg_idx = ring->reg_idx; - ring->xsk_umem = NULL; + ring->xsk_pool = NULL; if (ring_is_xdp(ring)) - ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); + ring->xsk_pool = ixgbe_xsk_pool(adapter, ring); /* disable queue to avoid issues while updating state */ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0); @@ -3713,8 +3708,8 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; /* configure the packet buffer length */ - if (rx_ring->xsk_umem) { - u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_umem); + if (rx_ring->xsk_pool) { + u32 xsk_buf_len = xsk_pool_get_rx_frame_size(rx_ring->xsk_pool); /* If the MAC support setting RXDCTL.RLPML, the * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and @@ -4059,12 +4054,12 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, u8 reg_idx = ring->reg_idx; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); - if (ring->xsk_umem) { + ring->xsk_pool = ixgbe_xsk_pool(adapter, ring); + if (ring->xsk_pool) { WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL)); - xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); } else { WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL)); @@ -4119,8 +4114,8 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, #endif } - if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) { - u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem); + if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) { + u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | IXGBE_RXDCTL_RLPML_EN); @@ -4142,7 +4137,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); ixgbe_rx_desc_queue_enable(adapter, ring); - if (ring->xsk_umem) + if (ring->xsk_pool) ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring)); else ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring)); @@ -5292,7 +5287,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) u16 i = rx_ring->next_to_clean; struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i]; - if (rx_ring->xsk_umem) { + if (rx_ring->xsk_pool) { ixgbe_xsk_clean_rx_ring(rx_ring); goto skip_free; } @@ -5984,7 +5979,7 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) u16 i = tx_ring->next_to_clean; struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; - if (tx_ring->xsk_umem) { + if (tx_ring->xsk_pool) { ixgbe_xsk_clean_tx_ring(tx_ring); goto out; } @@ -10146,7 +10141,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) */ if (need_reset && prog) for (i = 0; i < adapter->num_rx_queues; i++) - if (adapter->xdp_ring[i]->xsk_umem) + if (adapter->xdp_ring[i]->xsk_pool) (void)ixgbe_xsk_wakeup(adapter->netdev, i, XDP_WAKEUP_RX); @@ -10160,8 +10155,8 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: return ixgbe_xdp_setup(dev, xdp->prog); - case XDP_SETUP_XSK_UMEM: - return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem, + case XDP_SETUP_XSK_POOL: + return ixgbe_xsk_pool_setup(adapter, xdp->xsk.pool, xdp->xsk.queue_id); default: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h index 7887ae4aaf4f..2aeec78029bc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -28,9 +28,10 @@ void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, u64 qmask); void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring); void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring); -struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, - struct ixgbe_ring *ring); -int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, +struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring); +int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter, + struct xsk_buff_pool *pool, u16 qid); void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index ec7121f352e2..3771857cf887 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -8,8 +8,8 @@ #include "ixgbe.h" #include "ixgbe_txrx_common.h" -struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, - struct ixgbe_ring *ring) +struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) { bool xdp_on = READ_ONCE(adapter->xdp_prog); int qid = ring->ring_idx; @@ -17,11 +17,11 @@ struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, if (!xdp_on || !test_bit(qid, adapter->af_xdp_zc_qps)) return NULL; - return xdp_get_umem_from_qid(adapter->netdev, qid); + return xsk_get_pool_from_qid(adapter->netdev, qid); } -static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, - struct xdp_umem *umem, +static int ixgbe_xsk_pool_enable(struct ixgbe_adapter *adapter, + struct xsk_buff_pool *pool, u16 qid) { struct net_device *netdev = adapter->netdev; @@ -35,7 +35,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, qid >= netdev->real_num_tx_queues) return -EINVAL; - err = xsk_buff_dma_map(umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR); + err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR); if (err) return err; @@ -59,13 +59,13 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, return 0; } -static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) +static int ixgbe_xsk_pool_disable(struct ixgbe_adapter *adapter, u16 qid) { - struct xdp_umem *umem; + struct xsk_buff_pool *pool; bool if_running; - umem = xdp_get_umem_from_qid(adapter->netdev, qid); - if (!umem) + pool = xsk_get_pool_from_qid(adapter->netdev, qid); + if (!pool) return -EINVAL; if_running = netif_running(adapter->netdev) && @@ -75,7 +75,7 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) ixgbe_txrx_ring_disable(adapter, qid); clear_bit(qid, adapter->af_xdp_zc_qps); - xsk_buff_dma_unmap(umem, IXGBE_RX_DMA_ATTR); + xsk_pool_dma_unmap(pool, IXGBE_RX_DMA_ATTR); if (if_running) ixgbe_txrx_ring_enable(adapter, qid); @@ -83,11 +83,12 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) return 0; } -int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, +int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter, + struct xsk_buff_pool *pool, u16 qid) { - return umem ? ixgbe_xsk_umem_enable(adapter, umem, qid) : - ixgbe_xsk_umem_disable(adapter, qid); + return pool ? ixgbe_xsk_pool_enable(adapter, pool, qid) : + ixgbe_xsk_pool_disable(adapter, qid); } static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, @@ -149,7 +150,7 @@ bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) i -= rx_ring->count; do { - bi->xdp = xsk_buff_alloc(rx_ring->xsk_umem); + bi->xdp = xsk_buff_alloc(rx_ring->xsk_pool); if (!bi->xdp) { ok = false; break; @@ -286,7 +287,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, } bi->xdp->data_end = bi->xdp->data + size; - xsk_buff_dma_sync_for_cpu(bi->xdp); + xsk_buff_dma_sync_for_cpu(bi->xdp, rx_ring->xsk_pool); xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp); if (xdp_res) { @@ -344,11 +345,11 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, q_vector->rx.total_packets += total_rx_packets; q_vector->rx.total_bytes += total_rx_bytes; - if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) { + if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_umem); + xsk_set_rx_need_wakeup(rx_ring->xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_umem); + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); return (int)total_rx_packets; } @@ -373,6 +374,7 @@ void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring) static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) { + struct xsk_buff_pool *pool = xdp_ring->xsk_pool; union ixgbe_adv_tx_desc *tx_desc = NULL; struct ixgbe_tx_buffer *tx_bi; bool work_done = true; @@ -387,12 +389,11 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) break; } - if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) + if (!xsk_tx_peek_desc(pool, &desc)) break; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma, - desc.len); + dma = xsk_buff_raw_get_dma(pool, desc.addr); + xsk_buff_raw_dma_sync_for_device(pool, dma, desc.len); tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use]; tx_bi->bytecount = desc.len; @@ -418,7 +419,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) if (tx_desc) { ixgbe_xdp_ring_update_tail(xdp_ring); - xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + xsk_tx_release(pool); } return !!budget && work_done; @@ -439,7 +440,7 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, { u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; unsigned int total_packets = 0, total_bytes = 0; - struct xdp_umem *umem = tx_ring->xsk_umem; + struct xsk_buff_pool *pool = tx_ring->xsk_pool; union ixgbe_adv_tx_desc *tx_desc; struct ixgbe_tx_buffer *tx_bi; u32 xsk_frames = 0; @@ -484,10 +485,10 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, q_vector->tx.total_packets += total_packets; if (xsk_frames) - xsk_umem_complete_tx(umem, xsk_frames); + xsk_tx_completed(pool, xsk_frames); - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); + if (xsk_uses_need_wakeup(pool)) + xsk_set_tx_need_wakeup(pool); return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit); } @@ -511,7 +512,7 @@ int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) if (test_bit(__IXGBE_TX_DISABLED, &ring->state)) return -ENETDOWN; - if (!ring->xsk_umem) + if (!ring->xsk_pool) return -ENXIO; if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { @@ -526,7 +527,7 @@ int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring) { u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; - struct xdp_umem *umem = tx_ring->xsk_umem; + struct xsk_buff_pool *pool = tx_ring->xsk_pool; struct ixgbe_tx_buffer *tx_bi; u32 xsk_frames = 0; @@ -546,5 +547,5 @@ void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring) } if (xsk_frames) - xsk_umem_complete_tx(umem, xsk_frames); + xsk_tx_completed(pool, xsk_frames); } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index a428113e6d54..50afec43e001 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -866,10 +866,8 @@ struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(xdp->data); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data); + /* Note, we get here by enabling legacy-rx via: * * ethtool --set-priv-flags <dev> legacy-rx on @@ -947,10 +945,7 @@ static struct sk_buff *ixgbevf_build_skb(struct ixgbevf_ring *rx_ring, * have a consumer accessing first few bytes of meta data, * and then actual data. */ - prefetch(xdp->data_meta); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data_meta + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data_meta); /* build an skb around the page buffer */ skb = build_skb(xdp->data_hard_start, truesize); diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index ef4f35ba077d..a599e44a36a8 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -92,6 +92,12 @@ config MVPP2 This driver supports the network interface units in the Marvell ARMADA 375, 7K and 8K SoCs. +config MVPP2_PTP + bool "Marvell Armada 8K Enable PTP support" + depends on NETWORK_PHY_TIMESTAMPING + depends on (PTP_1588_CLOCK = y && MVPP2 = y) || \ + (PTP_1588_CLOCK && MVPP2 = m) + config PXA168_ETH tristate "Marvell pxa168 ethernet support" depends on HAS_IOMEM diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 832bbb8b05c8..f75e05e899bb 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -330,7 +330,6 @@ #define MVNETA_SKB_HEADROOM ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) #define MVNETA_SKB_PAD (SKB_DATA_ALIGN(sizeof(struct skb_shared_info) + \ MVNETA_SKB_HEADROOM)) -#define MVNETA_SKB_SIZE(len) (SKB_DATA_ALIGN(len) + MVNETA_SKB_PAD) #define MVNETA_MAX_RX_BUF_SIZE (PAGE_SIZE - MVNETA_SKB_PAD) #define IS_TSO_HEADER(txq, addr) \ @@ -2205,10 +2204,10 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, break; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(pp->dev, prog, act); - /* fall through */ + fallthrough; case XDP_DROP: mvneta_xdp_put_buff(pp, rxq, xdp, sync, true); ret = MVNETA_XDP_DROPPED; @@ -2227,8 +2226,7 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, struct mvneta_rx_desc *rx_desc, struct mvneta_rx_queue *rxq, struct xdp_buff *xdp, int *size, - struct page *page, - struct mvneta_stats *stats) + struct page *page) { unsigned char *data = page_address(page); int data_len = -MVNETA_MH_SIZE, len; @@ -2236,7 +2234,7 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, enum dma_data_direction dma_dir; struct skb_shared_info *sinfo; - if (MVNETA_SKB_SIZE(rx_desc->data_size) > PAGE_SIZE) { + if (rx_desc->data_size > MVNETA_MAX_RX_BUF_SIZE) { len = MVNETA_MAX_RX_BUF_SIZE; data_len += len; } else { @@ -2381,7 +2379,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, desc_status = rx_desc->status; mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf, - &size, page, &ps); + &size, page); } else { if (unlikely(!xdp_buf.data_hard_start)) continue; diff --git a/drivers/net/ethernet/marvell/mvpp2/Makefile b/drivers/net/ethernet/marvell/mvpp2/Makefile index 51f65a202c6e..9bd8e7964b40 100644 --- a/drivers/net/ethernet/marvell/mvpp2/Makefile +++ b/drivers/net/ethernet/marvell/mvpp2/Makefile @@ -4,4 +4,5 @@ # obj-$(CONFIG_MVPP2) := mvpp2.o -mvpp2-objs := mvpp2_main.o mvpp2_prs.o mvpp2_cls.o mvpp2_debugfs.o +mvpp2-y := mvpp2_main.o mvpp2_prs.o mvpp2_cls.o mvpp2_debugfs.o +mvpp2-$(CONFIG_MVPP2_PTP) += mvpp2_tai.o diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 32753cc771bf..834775843067 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/phylink.h> #include <net/flow_offload.h> @@ -461,8 +462,12 @@ #define MVPP22_CTRL4_DP_CLK_SEL BIT(5) #define MVPP22_CTRL4_SYNC_BYPASS_DIS BIT(6) #define MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE BIT(7) +#define MVPP22_GMAC_INT_SUM_STAT 0xa0 +#define MVPP22_GMAC_INT_SUM_STAT_INTERNAL BIT(1) +#define MVPP22_GMAC_INT_SUM_STAT_PTP BIT(2) #define MVPP22_GMAC_INT_SUM_MASK 0xa4 #define MVPP22_GMAC_INT_SUM_MASK_LINK_STAT BIT(1) +#define MVPP22_GMAC_INT_SUM_MASK_PTP BIT(2) /* Per-port XGMAC registers. PPv2.2 only, only for GOP port 0, * relative to port->base. @@ -488,9 +493,13 @@ #define MVPP22_XLG_CTRL3_MACMODESELECT_MASK (7 << 13) #define MVPP22_XLG_CTRL3_MACMODESELECT_GMAC (0 << 13) #define MVPP22_XLG_CTRL3_MACMODESELECT_10G (1 << 13) +#define MVPP22_XLG_EXT_INT_STAT 0x158 +#define MVPP22_XLG_EXT_INT_STAT_XLG BIT(1) +#define MVPP22_XLG_EXT_INT_STAT_PTP BIT(7) #define MVPP22_XLG_EXT_INT_MASK 0x15c #define MVPP22_XLG_EXT_INT_MASK_XLG BIT(1) #define MVPP22_XLG_EXT_INT_MASK_GIG BIT(2) +#define MVPP22_XLG_EXT_INT_MASK_PTP BIT(7) #define MVPP22_XLG_CTRL4_REG 0x184 #define MVPP22_XLG_CTRL4_FWD_FC BIT(5) #define MVPP22_XLG_CTRL4_FWD_PFC BIT(6) @@ -501,6 +510,70 @@ #define MVPP22_SMI_MISC_CFG_REG 0x1204 #define MVPP22_SMI_POLLING_EN BIT(10) +/* TAI registers, PPv2.2 only, relative to priv->iface_base */ +#define MVPP22_TAI_INT_CAUSE 0x1400 +#define MVPP22_TAI_INT_MASK 0x1404 +#define MVPP22_TAI_CR0 0x1408 +#define MVPP22_TAI_CR1 0x140c +#define MVPP22_TAI_TCFCR0 0x1410 +#define MVPP22_TAI_TCFCR1 0x1414 +#define MVPP22_TAI_TCFCR2 0x1418 +#define MVPP22_TAI_FATWR 0x141c +#define MVPP22_TAI_TOD_STEP_NANO_CR 0x1420 +#define MVPP22_TAI_TOD_STEP_FRAC_HIGH 0x1424 +#define MVPP22_TAI_TOD_STEP_FRAC_LOW 0x1428 +#define MVPP22_TAI_TAPDC_HIGH 0x142c +#define MVPP22_TAI_TAPDC_LOW 0x1430 +#define MVPP22_TAI_TGTOD_SEC_HIGH 0x1434 +#define MVPP22_TAI_TGTOD_SEC_MED 0x1438 +#define MVPP22_TAI_TGTOD_SEC_LOW 0x143c +#define MVPP22_TAI_TGTOD_NANO_HIGH 0x1440 +#define MVPP22_TAI_TGTOD_NANO_LOW 0x1444 +#define MVPP22_TAI_TGTOD_FRAC_HIGH 0x1448 +#define MVPP22_TAI_TGTOD_FRAC_LOW 0x144c +#define MVPP22_TAI_TLV_SEC_HIGH 0x1450 +#define MVPP22_TAI_TLV_SEC_MED 0x1454 +#define MVPP22_TAI_TLV_SEC_LOW 0x1458 +#define MVPP22_TAI_TLV_NANO_HIGH 0x145c +#define MVPP22_TAI_TLV_NANO_LOW 0x1460 +#define MVPP22_TAI_TLV_FRAC_HIGH 0x1464 +#define MVPP22_TAI_TLV_FRAC_LOW 0x1468 +#define MVPP22_TAI_TCV0_SEC_HIGH 0x146c +#define MVPP22_TAI_TCV0_SEC_MED 0x1470 +#define MVPP22_TAI_TCV0_SEC_LOW 0x1474 +#define MVPP22_TAI_TCV0_NANO_HIGH 0x1478 +#define MVPP22_TAI_TCV0_NANO_LOW 0x147c +#define MVPP22_TAI_TCV0_FRAC_HIGH 0x1480 +#define MVPP22_TAI_TCV0_FRAC_LOW 0x1484 +#define MVPP22_TAI_TCV1_SEC_HIGH 0x1488 +#define MVPP22_TAI_TCV1_SEC_MED 0x148c +#define MVPP22_TAI_TCV1_SEC_LOW 0x1490 +#define MVPP22_TAI_TCV1_NANO_HIGH 0x1494 +#define MVPP22_TAI_TCV1_NANO_LOW 0x1498 +#define MVPP22_TAI_TCV1_FRAC_HIGH 0x149c +#define MVPP22_TAI_TCV1_FRAC_LOW 0x14a0 +#define MVPP22_TAI_TCSR 0x14a4 +#define MVPP22_TAI_TUC_LSB 0x14a8 +#define MVPP22_TAI_GFM_SEC_HIGH 0x14ac +#define MVPP22_TAI_GFM_SEC_MED 0x14b0 +#define MVPP22_TAI_GFM_SEC_LOW 0x14b4 +#define MVPP22_TAI_GFM_NANO_HIGH 0x14b8 +#define MVPP22_TAI_GFM_NANO_LOW 0x14bc +#define MVPP22_TAI_GFM_FRAC_HIGH 0x14c0 +#define MVPP22_TAI_GFM_FRAC_LOW 0x14c4 +#define MVPP22_TAI_PCLK_DA_HIGH 0x14c8 +#define MVPP22_TAI_PCLK_DA_LOW 0x14cc +#define MVPP22_TAI_CTCR 0x14d0 +#define MVPP22_TAI_PCLK_CCC_HIGH 0x14d4 +#define MVPP22_TAI_PCLK_CCC_LOW 0x14d8 +#define MVPP22_TAI_DTC_HIGH 0x14dc +#define MVPP22_TAI_DTC_LOW 0x14e0 +#define MVPP22_TAI_CCC_HIGH 0x14e4 +#define MVPP22_TAI_CCC_LOW 0x14e8 +#define MVPP22_TAI_ICICE 0x14f4 +#define MVPP22_TAI_ICICC_LOW 0x14f8 +#define MVPP22_TAI_TUC_MSB 0x14fc + #define MVPP22_GMAC_BASE(port) (0x7000 + (port) * 0x1000 + 0xe00) #define MVPP2_CAUSE_TXQ_SENT_DESC_ALL_MASK 0xff @@ -527,6 +600,46 @@ #define MVPP22_XPCS_CFG0_PCS_MODE(n) ((n) << 3) #define MVPP22_XPCS_CFG0_ACTIVE_LANE(n) ((n) << 5) +/* PTP registers. PPv2.2 only */ +#define MVPP22_PTP_BASE(port) (0x7800 + (port * 0x1000)) +#define MVPP22_PTP_INT_CAUSE 0x00 +#define MVPP22_PTP_INT_CAUSE_QUEUE1 BIT(6) +#define MVPP22_PTP_INT_CAUSE_QUEUE0 BIT(5) +#define MVPP22_PTP_INT_MASK 0x04 +#define MVPP22_PTP_INT_MASK_QUEUE1 BIT(6) +#define MVPP22_PTP_INT_MASK_QUEUE0 BIT(5) +#define MVPP22_PTP_GCR 0x08 +#define MVPP22_PTP_GCR_RX_RESET BIT(13) +#define MVPP22_PTP_GCR_TX_RESET BIT(1) +#define MVPP22_PTP_GCR_TSU_ENABLE BIT(0) +#define MVPP22_PTP_TX_Q0_R0 0x0c +#define MVPP22_PTP_TX_Q0_R1 0x10 +#define MVPP22_PTP_TX_Q0_R2 0x14 +#define MVPP22_PTP_TX_Q1_R0 0x18 +#define MVPP22_PTP_TX_Q1_R1 0x1c +#define MVPP22_PTP_TX_Q1_R2 0x20 +#define MVPP22_PTP_TPCR 0x24 +#define MVPP22_PTP_V1PCR 0x28 +#define MVPP22_PTP_V2PCR 0x2c +#define MVPP22_PTP_Y1731PCR 0x30 +#define MVPP22_PTP_NTPTSPCR 0x34 +#define MVPP22_PTP_NTPRXPCR 0x38 +#define MVPP22_PTP_NTPTXPCR 0x3c +#define MVPP22_PTP_WAMPPCR 0x40 +#define MVPP22_PTP_NAPCR 0x44 +#define MVPP22_PTP_FAPCR 0x48 +#define MVPP22_PTP_CAPCR 0x50 +#define MVPP22_PTP_ATAPCR 0x54 +#define MVPP22_PTP_ACTAPCR 0x58 +#define MVPP22_PTP_CATAPCR 0x5c +#define MVPP22_PTP_CACTAPCR 0x60 +#define MVPP22_PTP_AITAPCR 0x64 +#define MVPP22_PTP_CAITAPCR 0x68 +#define MVPP22_PTP_CITAPCR 0x6c +#define MVPP22_PTP_NTP_OFF_HIGH 0x70 +#define MVPP22_PTP_NTP_OFF_LOW 0x74 +#define MVPP22_PTP_TX_PIPE_STATUS_DELAY 0x78 + /* System controller registers. Accessed through a regmap. */ #define GENCONF_SOFT_RESET1 0x1108 #define GENCONF_SOFT_RESET1_GOP BIT(6) @@ -692,6 +805,43 @@ enum mvpp2_prs_l3_cast { MVPP2_PRS_L3_BROAD_CAST }; +/* PTP descriptor constants. The low bits of the descriptor are stored + * separately from the high bits. + */ +#define MVPP22_PTP_DESC_MASK_LOW 0xfff + +/* PTPAction */ +enum mvpp22_ptp_action { + MVPP22_PTP_ACTION_NONE = 0, + MVPP22_PTP_ACTION_FORWARD = 1, + MVPP22_PTP_ACTION_CAPTURE = 3, + /* The following have not been verified */ + MVPP22_PTP_ACTION_ADDTIME = 4, + MVPP22_PTP_ACTION_ADDCORRECTEDTIME = 5, + MVPP22_PTP_ACTION_CAPTUREADDTIME = 6, + MVPP22_PTP_ACTION_CAPTUREADDCORRECTEDTIME = 7, + MVPP22_PTP_ACTION_ADDINGRESSTIME = 8, + MVPP22_PTP_ACTION_CAPTUREADDINGRESSTIME = 9, + MVPP22_PTP_ACTION_CAPTUREINGRESSTIME = 10, +}; + +/* PTPPacketFormat */ +enum mvpp22_ptp_packet_format { + MVPP22_PTP_PKT_FMT_PTPV2 = 0, + MVPP22_PTP_PKT_FMT_PTPV1 = 1, + MVPP22_PTP_PKT_FMT_Y1731 = 2, + MVPP22_PTP_PKT_FMT_NTPTS = 3, + MVPP22_PTP_PKT_FMT_NTPRX = 4, + MVPP22_PTP_PKT_FMT_NTPTX = 5, + MVPP22_PTP_PKT_FMT_TWAMP = 6, +}; + +#define MVPP22_PTP_ACTION(x) (((x) & 15) << 0) +#define MVPP22_PTP_PACKETFORMAT(x) (((x) & 7) << 4) +#define MVPP22_PTP_MACTIMESTAMPINGEN BIT(11) +#define MVPP22_PTP_TIMESTAMPENTRYID(x) (((x) & 31) << 12) +#define MVPP22_PTP_TIMESTAMPQUEUESELECT BIT(18) + /* BM constants */ #define MVPP2_BM_JUMBO_BUF_NUM 512 #define MVPP2_BM_LONG_BUF_NUM 1024 @@ -759,6 +909,8 @@ enum mvpp2_prs_l3_cast { #define MVPP2_DESC_DMA_MASK DMA_BIT_MASK(40) +struct mvpp2_tai; + /* Definitions */ struct mvpp2_dbgfs_entries; @@ -794,6 +946,7 @@ struct mvpp2 { /* List of pointers to port structures */ int port_count; struct mvpp2_port *port_list[MVPP2_MAX_PORTS]; + struct mvpp2_tai *tai; /* Number of Tx threads used */ unsigned int nthreads; @@ -907,6 +1060,11 @@ struct mvpp2_ethtool_fs { struct ethtool_rxnfc rxnfc; }; +struct mvpp2_hwtstamp_queue { + struct sk_buff *skb[32]; + u8 next; +}; + struct mvpp2_port { u8 id; @@ -915,7 +1073,7 @@ struct mvpp2_port { */ int gop_id; - int link_irq; + int port_irq; struct mvpp2 *priv; @@ -967,6 +1125,7 @@ struct mvpp2_port { phy_interface_t phy_interface; struct phylink *phylink; struct phylink_config phylink_config; + struct phylink_pcs phylink_pcs; struct phy *comphy; struct mvpp2_bm_pool *pool_long; @@ -989,6 +1148,11 @@ struct mvpp2_port { * them from 0 */ int rss_ctx[MVPP22_N_RSS_TABLES]; + + bool hwtstamp; + bool rx_hwtstamp; + enum hwtstamp_tx_types tx_hwtstamp_type; + struct mvpp2_hwtstamp_queue tx_hwtstamp_queue[2]; }; /* The mvpp2_tx_desc and mvpp2_rx_desc structures describe the @@ -1057,7 +1221,8 @@ struct mvpp22_tx_desc { u8 packet_offset; u8 phys_txq; __le16 data_size; - __le64 reserved1; + __le32 ptp_descriptor; + __le32 reserved2; __le64 buf_dma_addr_ptp; __le64 buf_cookie_misc; }; @@ -1068,7 +1233,7 @@ struct mvpp22_rx_desc { __le16 reserved1; __le16 data_size; __le32 reserved2; - __le32 reserved3; + __le32 timestamp; __le64 buf_dma_addr_key_hash; __le64 buf_cookie_misc; }; @@ -1248,4 +1413,36 @@ void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name); void mvpp2_dbgfs_cleanup(struct mvpp2 *priv); +#ifdef CONFIG_MVPP2_PTP +int mvpp22_tai_probe(struct device *dev, struct mvpp2 *priv); +void mvpp22_tai_tstamp(struct mvpp2_tai *tai, u32 tstamp, + struct skb_shared_hwtstamps *hwtstamp); +void mvpp22_tai_start(struct mvpp2_tai *tai); +void mvpp22_tai_stop(struct mvpp2_tai *tai); +int mvpp22_tai_ptp_clock_index(struct mvpp2_tai *tai); +#else +static inline int mvpp22_tai_probe(struct device *dev, struct mvpp2 *priv) +{ + return 0; +} +static inline void mvpp22_tai_tstamp(struct mvpp2_tai *tai, u32 tstamp, + struct skb_shared_hwtstamps *hwtstamp) +{ +} +static inline void mvpp22_tai_start(struct mvpp2_tai *tai) +{ +} +static inline void mvpp22_tai_stop(struct mvpp2_tai *tai) +{ +} +static inline int mvpp22_tai_ptp_clock_index(struct mvpp2_tai *tai) +{ + return -1; +} +#endif + +static inline bool mvpp22_rx_hwtstamping(struct mvpp2_port *port) +{ + return IS_ENABLED(CONFIG_MVPP2_PTP) && port->rx_hwtstamp; +} #endif diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index d4a4e241333d..41d935d1aaf6 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1638,7 +1638,7 @@ int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info) hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP; if (info->data & RXH_L4_B_2_3) hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP; - /* Fallthrough */ + fallthrough; case MVPP22_FLOW_IP4: case MVPP22_FLOW_IP6: if (info->data & RXH_L2DA) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 2a8a5842eaef..87b1c9cfdc77 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -28,6 +28,7 @@ #include <linux/phy.h> #include <linux/phylink.h> #include <linux/phy/phy.h> +#include <linux/ptp_classify.h> #include <linux/clk.h> #include <linux/hrtimer.h> #include <linux/ktime.h> @@ -57,13 +58,7 @@ static struct { /* The prototype is added here to be used in start_dev when using ACPI. This * will be removed once phylink is used for all modes (dt+ACPI). */ -static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode, - const struct phylink_link_state *state); -static void mvpp2_mac_link_up(struct phylink_config *config, - struct phy_device *phy, - unsigned int mode, phy_interface_t interface, - int speed, int duplex, - bool tx_pause, bool rx_pause); +static void mvpp2_acpi_start(struct mvpp2_port *port); /* Queue modes */ #define MVPP2_QDIST_SINGLE_MODE 0 @@ -1385,6 +1380,10 @@ static void mvpp22_gop_setup_irq(struct mvpp2_port *port) { u32 val; + mvpp2_modify(port->base + MVPP22_GMAC_INT_SUM_MASK, + MVPP22_GMAC_INT_SUM_MASK_PTP, + MVPP22_GMAC_INT_SUM_MASK_PTP); + if (port->phylink || phy_interface_mode_is_rgmii(port->phy_interface) || phy_interface_mode_is_8023z(port->phy_interface) || @@ -1398,6 +1397,10 @@ static void mvpp22_gop_setup_irq(struct mvpp2_port *port) val = readl(port->base + MVPP22_XLG_INT_MASK); val |= MVPP22_XLG_INT_MASK_LINK; writel(val, port->base + MVPP22_XLG_INT_MASK); + + mvpp2_modify(port->base + MVPP22_XLG_EXT_INT_MASK, + MVPP22_XLG_EXT_INT_MASK_PTP, + MVPP22_XLG_EXT_INT_MASK_PTP); } mvpp22_gop_unmask_irq(port); @@ -1485,8 +1488,8 @@ static void mvpp2_port_loopback_set(struct mvpp2_port *port, else val &= ~MVPP2_GMAC_GMII_LB_EN_MASK; - if (phy_interface_mode_is_8023z(port->phy_interface) || - port->phy_interface == PHY_INTERFACE_MODE_SGMII) + if (phy_interface_mode_is_8023z(state->interface) || + state->interface == PHY_INTERFACE_MODE_SGMII) val |= MVPP2_GMAC_PCS_LB_EN_MASK; else val &= ~MVPP2_GMAC_PCS_LB_EN_MASK; @@ -2980,44 +2983,67 @@ static irqreturn_t mvpp2_isr(int irq, void *dev_id) return IRQ_HANDLED; } -/* Per-port interrupt for link status changes */ -static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id) +static void mvpp2_isr_handle_ptp_queue(struct mvpp2_port *port, int nq) { - struct mvpp2_port *port = (struct mvpp2_port *)dev_id; - struct net_device *dev = port->dev; - bool event = false, link = false; - u32 val; + struct skb_shared_hwtstamps shhwtstamps; + struct mvpp2_hwtstamp_queue *queue; + struct sk_buff *skb; + void __iomem *ptp_q; + unsigned int id; + u32 r0, r1, r2; - mvpp22_gop_mask_irq(port); + ptp_q = port->priv->iface_base + MVPP22_PTP_BASE(port->gop_id); + if (nq) + ptp_q += MVPP22_PTP_TX_Q1_R0 - MVPP22_PTP_TX_Q0_R0; - if (mvpp2_port_supports_xlg(port) && - mvpp2_is_xlg(port->phy_interface)) { - val = readl(port->base + MVPP22_XLG_INT_STAT); - if (val & MVPP22_XLG_INT_STAT_LINK) { - event = true; - val = readl(port->base + MVPP22_XLG_STATUS); - if (val & MVPP22_XLG_STATUS_LINK_UP) - link = true; - } - } else if (phy_interface_mode_is_rgmii(port->phy_interface) || - phy_interface_mode_is_8023z(port->phy_interface) || - port->phy_interface == PHY_INTERFACE_MODE_SGMII) { - val = readl(port->base + MVPP22_GMAC_INT_STAT); - if (val & MVPP22_GMAC_INT_STAT_LINK) { - event = true; - val = readl(port->base + MVPP2_GMAC_STATUS0); - if (val & MVPP2_GMAC_STATUS0_LINK_UP) - link = true; + queue = &port->tx_hwtstamp_queue[nq]; + + while (1) { + r0 = readl_relaxed(ptp_q + MVPP22_PTP_TX_Q0_R0) & 0xffff; + if (!r0) + break; + + r1 = readl_relaxed(ptp_q + MVPP22_PTP_TX_Q0_R1) & 0xffff; + r2 = readl_relaxed(ptp_q + MVPP22_PTP_TX_Q0_R2) & 0xffff; + + id = (r0 >> 1) & 31; + + skb = queue->skb[id]; + queue->skb[id] = NULL; + if (skb) { + u32 ts = r2 << 19 | r1 << 3 | r0 >> 13; + + mvpp22_tai_tstamp(port->priv->tai, ts, &shhwtstamps); + skb_tstamp_tx(skb, &shhwtstamps); + dev_kfree_skb_any(skb); } } +} + +static void mvpp2_isr_handle_ptp(struct mvpp2_port *port) +{ + void __iomem *ptp; + u32 val; + + ptp = port->priv->iface_base + MVPP22_PTP_BASE(port->gop_id); + val = readl(ptp + MVPP22_PTP_INT_CAUSE); + if (val & MVPP22_PTP_INT_CAUSE_QUEUE0) + mvpp2_isr_handle_ptp_queue(port, 0); + if (val & MVPP22_PTP_INT_CAUSE_QUEUE1) + mvpp2_isr_handle_ptp_queue(port, 1); +} + +static void mvpp2_isr_handle_link(struct mvpp2_port *port, bool link) +{ + struct net_device *dev = port->dev; if (port->phylink) { phylink_mac_change(port->phylink, link); - goto handled; + return; } - if (!netif_running(dev) || !event) - goto handled; + if (!netif_running(dev)) + return; if (link) { mvpp2_interrupts_enable(port); @@ -3034,8 +3060,65 @@ static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id) mvpp2_interrupts_disable(port); } +} + +static void mvpp2_isr_handle_xlg(struct mvpp2_port *port) +{ + bool link; + u32 val; + + val = readl(port->base + MVPP22_XLG_INT_STAT); + if (val & MVPP22_XLG_INT_STAT_LINK) { + val = readl(port->base + MVPP22_XLG_STATUS); + link = (val & MVPP22_XLG_STATUS_LINK_UP); + mvpp2_isr_handle_link(port, link); + } +} + +static void mvpp2_isr_handle_gmac_internal(struct mvpp2_port *port) +{ + bool link; + u32 val; + + if (phy_interface_mode_is_rgmii(port->phy_interface) || + phy_interface_mode_is_8023z(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { + val = readl(port->base + MVPP22_GMAC_INT_STAT); + if (val & MVPP22_GMAC_INT_STAT_LINK) { + val = readl(port->base + MVPP2_GMAC_STATUS0); + link = (val & MVPP2_GMAC_STATUS0_LINK_UP); + mvpp2_isr_handle_link(port, link); + } + } +} + +/* Per-port interrupt for link status changes */ +static irqreturn_t mvpp2_port_isr(int irq, void *dev_id) +{ + struct mvpp2_port *port = (struct mvpp2_port *)dev_id; + u32 val; + + mvpp22_gop_mask_irq(port); + + if (mvpp2_port_supports_xlg(port) && + mvpp2_is_xlg(port->phy_interface)) { + /* Check the external status register */ + val = readl(port->base + MVPP22_XLG_EXT_INT_STAT); + if (val & MVPP22_XLG_EXT_INT_STAT_XLG) + mvpp2_isr_handle_xlg(port); + if (val & MVPP22_XLG_EXT_INT_STAT_PTP) + mvpp2_isr_handle_ptp(port); + } else { + /* If it's not the XLG, we must be using the GMAC. + * Check the summary status. + */ + val = readl(port->base + MVPP22_GMAC_INT_SUM_STAT); + if (val & MVPP22_GMAC_INT_SUM_STAT_INTERNAL) + mvpp2_isr_handle_gmac_internal(port); + if (val & MVPP22_GMAC_INT_SUM_STAT_PTP) + mvpp2_isr_handle_ptp(port); + } -handled: mvpp22_gop_unmask_irq(port); return IRQ_HANDLED; } @@ -3427,7 +3510,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, unsigned int frag_size; dma_addr_t dma_addr; phys_addr_t phys_addr; - u32 rx_status; + u32 rx_status, timestamp; int pool, rx_bytes, err, ret; void *data; @@ -3505,6 +3588,15 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, goto err_drop_frame; } + /* If we have RX hardware timestamping enabled, grab the + * timestamp from the queue and convert. + */ + if (mvpp22_rx_hwtstamping(port)) { + timestamp = le32_to_cpu(rx_desc->pp22.timestamp); + mvpp22_tai_tstamp(port->priv->tai, timestamp, + skb_hwtstamps(skb)); + } + err = mvpp2_rx_refill(port, bm_pool, pp, pool); if (err) { netdev_err(port->dev, "failed to refill BM pools\n"); @@ -3579,6 +3671,92 @@ tx_desc_unmap_put(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, mvpp2_txq_desc_put(txq); } +static void mvpp2_txdesc_clear_ptp(struct mvpp2_port *port, + struct mvpp2_tx_desc *desc) +{ + /* We only need to clear the low bits */ + if (port->priv->hw_version != MVPP21) + desc->pp22.ptp_descriptor &= + cpu_to_le32(~MVPP22_PTP_DESC_MASK_LOW); +} + +static bool mvpp2_tx_hw_tstamp(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + struct sk_buff *skb) +{ + struct mvpp2_hwtstamp_queue *queue; + unsigned int mtype, type, i; + struct ptp_header *hdr; + u64 ptpdesc; + + if (port->priv->hw_version == MVPP21 || + port->tx_hwtstamp_type == HWTSTAMP_TX_OFF) + return false; + + type = ptp_classify_raw(skb); + if (!type) + return false; + + hdr = ptp_parse_header(skb, type); + if (!hdr) + return false; + + ptpdesc = MVPP22_PTP_MACTIMESTAMPINGEN | + MVPP22_PTP_ACTION_CAPTURE; + queue = &port->tx_hwtstamp_queue[0]; + + switch (type & PTP_CLASS_VMASK) { + case PTP_CLASS_V1: + ptpdesc |= MVPP22_PTP_PACKETFORMAT(MVPP22_PTP_PKT_FMT_PTPV1); + break; + + case PTP_CLASS_V2: + ptpdesc |= MVPP22_PTP_PACKETFORMAT(MVPP22_PTP_PKT_FMT_PTPV2); + mtype = hdr->tsmt & 15; + /* Direct PTP Sync messages to queue 1 */ + if (mtype == 0) { + ptpdesc |= MVPP22_PTP_TIMESTAMPQUEUESELECT; + queue = &port->tx_hwtstamp_queue[1]; + } + break; + } + + /* Take a reference on the skb and insert into our queue */ + i = queue->next; + queue->next = (i + 1) & 31; + if (queue->skb[i]) + dev_kfree_skb_any(queue->skb[i]); + queue->skb[i] = skb_get(skb); + + ptpdesc |= MVPP22_PTP_TIMESTAMPENTRYID(i); + + /* + * 3:0 - PTPAction + * 6:4 - PTPPacketFormat + * 7 - PTP_CF_WraparoundCheckEn + * 9:8 - IngressTimestampSeconds[1:0] + * 10 - Reserved + * 11 - MACTimestampingEn + * 17:12 - PTP_TimestampQueueEntryID[5:0] + * 18 - PTPTimestampQueueSelect + * 19 - UDPChecksumUpdateEn + * 27:20 - TimestampOffset + * PTP, NTPTransmit, OWAMP/TWAMP - L3 to PTP header + * NTPTs, Y.1731 - L3 to timestamp entry + * 35:28 - UDP Checksum Offset + * + * stored in tx descriptor bits 75:64 (11:0) and 191:168 (35:12) + */ + tx_desc->pp22.ptp_descriptor &= + cpu_to_le32(~MVPP22_PTP_DESC_MASK_LOW); + tx_desc->pp22.ptp_descriptor |= + cpu_to_le32(ptpdesc & MVPP22_PTP_DESC_MASK_LOW); + tx_desc->pp22.buf_dma_addr_ptp &= cpu_to_le64(~0xffffff0000000000ULL); + tx_desc->pp22.buf_dma_addr_ptp |= cpu_to_le64((ptpdesc >> 12) << 40); + + return true; +} + /* Handle tx fragmentation processing */ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, struct mvpp2_tx_queue *aggr_txq, @@ -3595,6 +3773,7 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, void *addr = skb_frag_address(frag); tx_desc = mvpp2_txq_next_desc_get(aggr_txq); + mvpp2_txdesc_clear_ptp(port, tx_desc); mvpp2_txdesc_txq_set(port, tx_desc, txq->id); mvpp2_txdesc_size_set(port, tx_desc, skb_frag_size(frag)); @@ -3644,6 +3823,7 @@ static inline void mvpp2_tso_put_hdr(struct sk_buff *skb, struct mvpp2_tx_desc *tx_desc = mvpp2_txq_next_desc_get(aggr_txq); dma_addr_t addr; + mvpp2_txdesc_clear_ptp(port, tx_desc); mvpp2_txdesc_txq_set(port, tx_desc, txq->id); mvpp2_txdesc_size_set(port, tx_desc, hdr_sz); @@ -3668,6 +3848,7 @@ static inline int mvpp2_tso_put_data(struct sk_buff *skb, struct mvpp2_tx_desc *tx_desc = mvpp2_txq_next_desc_get(aggr_txq); dma_addr_t buf_dma_addr; + mvpp2_txdesc_clear_ptp(port, tx_desc); mvpp2_txdesc_txq_set(port, tx_desc, txq->id); mvpp2_txdesc_size_set(port, tx_desc, sz); @@ -3784,6 +3965,9 @@ static netdev_tx_t mvpp2_tx(struct sk_buff *skb, struct net_device *dev) /* Get a descriptor for the first part of the packet */ tx_desc = mvpp2_txq_next_desc_get(aggr_txq); + if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) || + !mvpp2_tx_hw_tstamp(port, tx_desc, skb)) + mvpp2_txdesc_clear_ptp(port, tx_desc); mvpp2_txdesc_txq_set(port, tx_desc, txq->id); mvpp2_txdesc_size_set(port, tx_desc, skb_headlen(skb)); @@ -4007,17 +4191,7 @@ static void mvpp2_start_dev(struct mvpp2_port *port) if (port->phylink) { phylink_start(port->phylink); } else { - /* Phylink isn't used as of now for ACPI, so the MAC has to be - * configured manually when the interface is started. This will - * be removed as soon as the phylink ACPI support lands in. - */ - struct phylink_link_state state = { - .interface = port->phy_interface, - }; - mvpp2_mac_config(&port->phylink_config, MLO_AN_INBAND, &state); - mvpp2_mac_link_up(&port->phylink_config, NULL, - MLO_AN_INBAND, port->phy_interface, - SPEED_UNKNOWN, DUPLEX_UNKNOWN, false, false); + mvpp2_acpi_start(port); } netif_tx_start_all_queues(port->dev); @@ -4227,12 +4401,13 @@ static int mvpp2_open(struct net_device *dev) valid = true; } - if (priv->hw_version == MVPP22 && port->link_irq) { - err = request_irq(port->link_irq, mvpp2_link_status_isr, 0, + if (priv->hw_version == MVPP22 && port->port_irq) { + err = request_irq(port->port_irq, mvpp2_port_isr, 0, dev->name, port); if (err) { - netdev_err(port->dev, "cannot request link IRQ %d\n", - port->link_irq); + netdev_err(port->dev, + "cannot request port link/ptp IRQ %d\n", + port->port_irq); goto err_free_irq; } @@ -4243,7 +4418,7 @@ static int mvpp2_open(struct net_device *dev) valid = true; } else { - port->link_irq = 0; + port->port_irq = 0; } if (!valid) { @@ -4287,8 +4462,8 @@ static int mvpp2_stop(struct net_device *dev) if (port->phylink) phylink_disconnect_phy(port->phylink); - if (port->link_irq) - free_irq(port->link_irq, port); + if (port->port_irq) + free_irq(port->port_irq, port); mvpp2_irqs_deinit(port); if (!port->has_tx_irqs) { @@ -4548,10 +4723,124 @@ mvpp2_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_dropped = dev->stats.tx_dropped; } +static int mvpp2_set_ts_config(struct mvpp2_port *port, struct ifreq *ifr) +{ + struct hwtstamp_config config; + void __iomem *ptp; + u32 gcr, int_mask; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + if (config.flags) + return -EINVAL; + + if (config.tx_type != HWTSTAMP_TX_OFF && + config.tx_type != HWTSTAMP_TX_ON) + return -ERANGE; + + ptp = port->priv->iface_base + MVPP22_PTP_BASE(port->gop_id); + + int_mask = gcr = 0; + if (config.tx_type != HWTSTAMP_TX_OFF) { + gcr |= MVPP22_PTP_GCR_TSU_ENABLE | MVPP22_PTP_GCR_TX_RESET; + int_mask |= MVPP22_PTP_INT_MASK_QUEUE1 | + MVPP22_PTP_INT_MASK_QUEUE0; + } + + /* It seems we must also release the TX reset when enabling the TSU */ + if (config.rx_filter != HWTSTAMP_FILTER_NONE) + gcr |= MVPP22_PTP_GCR_TSU_ENABLE | MVPP22_PTP_GCR_RX_RESET | + MVPP22_PTP_GCR_TX_RESET; + + if (gcr & MVPP22_PTP_GCR_TSU_ENABLE) + mvpp22_tai_start(port->priv->tai); + + if (config.rx_filter != HWTSTAMP_FILTER_NONE) { + config.rx_filter = HWTSTAMP_FILTER_ALL; + mvpp2_modify(ptp + MVPP22_PTP_GCR, + MVPP22_PTP_GCR_RX_RESET | + MVPP22_PTP_GCR_TX_RESET | + MVPP22_PTP_GCR_TSU_ENABLE, gcr); + port->rx_hwtstamp = true; + } else { + port->rx_hwtstamp = false; + mvpp2_modify(ptp + MVPP22_PTP_GCR, + MVPP22_PTP_GCR_RX_RESET | + MVPP22_PTP_GCR_TX_RESET | + MVPP22_PTP_GCR_TSU_ENABLE, gcr); + } + + mvpp2_modify(ptp + MVPP22_PTP_INT_MASK, + MVPP22_PTP_INT_MASK_QUEUE1 | + MVPP22_PTP_INT_MASK_QUEUE0, int_mask); + + if (!(gcr & MVPP22_PTP_GCR_TSU_ENABLE)) + mvpp22_tai_stop(port->priv->tai); + + port->tx_hwtstamp_type = config.tx_type; + + if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) + return -EFAULT; + + return 0; +} + +static int mvpp2_get_ts_config(struct mvpp2_port *port, struct ifreq *ifr) +{ + struct hwtstamp_config config; + + memset(&config, 0, sizeof(config)); + + config.tx_type = port->tx_hwtstamp_type; + config.rx_filter = port->rx_hwtstamp ? + HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; + + if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) + return -EFAULT; + + return 0; +} + +static int mvpp2_ethtool_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct mvpp2_port *port = netdev_priv(dev); + + if (!port->hwtstamp) + return -EOPNOTSUPP; + + info->phc_index = mvpp22_tai_ptp_clock_index(port->priv->tai); + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = BIT(HWTSTAMP_TX_OFF) | + BIT(HWTSTAMP_TX_ON); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_ALL); + + return 0; +} + static int mvpp2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct mvpp2_port *port = netdev_priv(dev); + switch (cmd) { + case SIOCSHWTSTAMP: + if (port->hwtstamp) + return mvpp2_set_ts_config(port, ifr); + break; + + case SIOCGHWTSTAMP: + if (port->hwtstamp) + return mvpp2_get_ts_config(port, ifr); + break; + } + if (!port->phylink) return -ENOTSUPP; @@ -5021,6 +5310,7 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { ETHTOOL_COALESCE_MAX_FRAMES, .nway_reset = mvpp2_ethtool_nway_reset, .get_link = ethtool_op_get_link, + .get_ts_info = mvpp2_ethtool_get_ts_info, .set_coalesce = mvpp2_ethtool_set_coalesce, .get_coalesce = mvpp2_ethtool_get_coalesce, .get_drvinfo = mvpp2_ethtool_get_drvinfo, @@ -5392,6 +5682,155 @@ static struct mvpp2_port *mvpp2_phylink_to_port(struct phylink_config *config) return container_of(config, struct mvpp2_port, phylink_config); } +static struct mvpp2_port *mvpp2_pcs_to_port(struct phylink_pcs *pcs) +{ + return container_of(pcs, struct mvpp2_port, phylink_pcs); +} + +static void mvpp2_xlg_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct mvpp2_port *port = mvpp2_pcs_to_port(pcs); + u32 val; + + state->speed = SPEED_10000; + state->duplex = 1; + state->an_complete = 1; + + val = readl(port->base + MVPP22_XLG_STATUS); + state->link = !!(val & MVPP22_XLG_STATUS_LINK_UP); + + state->pause = 0; + val = readl(port->base + MVPP22_XLG_CTRL0_REG); + if (val & MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN) + state->pause |= MLO_PAUSE_TX; + if (val & MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN) + state->pause |= MLO_PAUSE_RX; +} + +static int mvpp2_xlg_pcs_config(struct phylink_pcs *pcs, + unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) +{ + return 0; +} + +static const struct phylink_pcs_ops mvpp2_phylink_xlg_pcs_ops = { + .pcs_get_state = mvpp2_xlg_pcs_get_state, + .pcs_config = mvpp2_xlg_pcs_config, +}; + +static void mvpp2_gmac_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct mvpp2_port *port = mvpp2_pcs_to_port(pcs); + u32 val; + + val = readl(port->base + MVPP2_GMAC_STATUS0); + + state->an_complete = !!(val & MVPP2_GMAC_STATUS0_AN_COMPLETE); + state->link = !!(val & MVPP2_GMAC_STATUS0_LINK_UP); + state->duplex = !!(val & MVPP2_GMAC_STATUS0_FULL_DUPLEX); + + switch (port->phy_interface) { + case PHY_INTERFACE_MODE_1000BASEX: + state->speed = SPEED_1000; + break; + case PHY_INTERFACE_MODE_2500BASEX: + state->speed = SPEED_2500; + break; + default: + if (val & MVPP2_GMAC_STATUS0_GMII_SPEED) + state->speed = SPEED_1000; + else if (val & MVPP2_GMAC_STATUS0_MII_SPEED) + state->speed = SPEED_100; + else + state->speed = SPEED_10; + } + + state->pause = 0; + if (val & MVPP2_GMAC_STATUS0_RX_PAUSE) + state->pause |= MLO_PAUSE_RX; + if (val & MVPP2_GMAC_STATUS0_TX_PAUSE) + state->pause |= MLO_PAUSE_TX; +} + +static int mvpp2_gmac_pcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) +{ + struct mvpp2_port *port = mvpp2_pcs_to_port(pcs); + u32 mask, val, an, old_an, changed; + + mask = MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS | + MVPP2_GMAC_IN_BAND_AUTONEG | + MVPP2_GMAC_AN_SPEED_EN | + MVPP2_GMAC_FLOW_CTRL_AUTONEG | + MVPP2_GMAC_AN_DUPLEX_EN; + + if (phylink_autoneg_inband(mode)) { + mask |= MVPP2_GMAC_CONFIG_MII_SPEED | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX; + val = MVPP2_GMAC_IN_BAND_AUTONEG; + + if (interface == PHY_INTERFACE_MODE_SGMII) { + /* SGMII mode receives the speed and duplex from PHY */ + val |= MVPP2_GMAC_AN_SPEED_EN | + MVPP2_GMAC_AN_DUPLEX_EN; + } else { + /* 802.3z mode has fixed speed and duplex */ + val |= MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX; + + /* The FLOW_CTRL_AUTONEG bit selects either the hardware + * automatically or the bits in MVPP22_GMAC_CTRL_4_REG + * manually controls the GMAC pause modes. + */ + if (permit_pause_to_mac) + val |= MVPP2_GMAC_FLOW_CTRL_AUTONEG; + + /* Configure advertisement bits */ + mask |= MVPP2_GMAC_FC_ADV_EN | MVPP2_GMAC_FC_ADV_ASM_EN; + if (phylink_test(advertising, Pause)) + val |= MVPP2_GMAC_FC_ADV_EN; + if (phylink_test(advertising, Asym_Pause)) + val |= MVPP2_GMAC_FC_ADV_ASM_EN; + } + } else { + val = 0; + } + + old_an = an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); + an = (an & ~mask) | val; + changed = an ^ old_an; + if (changed) + writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + + /* We are only interested in the advertisement bits changing */ + return changed & (MVPP2_GMAC_FC_ADV_EN | MVPP2_GMAC_FC_ADV_ASM_EN); +} + +static void mvpp2_gmac_pcs_an_restart(struct phylink_pcs *pcs) +{ + struct mvpp2_port *port = mvpp2_pcs_to_port(pcs); + u32 val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); + + writel(val | MVPP2_GMAC_IN_BAND_RESTART_AN, + port->base + MVPP2_GMAC_AUTONEG_CONFIG); + writel(val & ~MVPP2_GMAC_IN_BAND_RESTART_AN, + port->base + MVPP2_GMAC_AUTONEG_CONFIG); +} + +static const struct phylink_pcs_ops mvpp2_phylink_gmac_pcs_ops = { + .pcs_get_state = mvpp2_gmac_pcs_get_state, + .pcs_config = mvpp2_gmac_pcs_config, + .pcs_an_restart = mvpp2_gmac_pcs_an_restart, +}; + static void mvpp2_phylink_validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state) @@ -5437,7 +5876,7 @@ static void mvpp2_phylink_validate(struct phylink_config *config, } if (state->interface != PHY_INTERFACE_MODE_NA) break; - /* Fall-through */ + fallthrough; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: @@ -5451,7 +5890,7 @@ static void mvpp2_phylink_validate(struct phylink_config *config, phylink_set(mask, 1000baseX_Full); if (state->interface != PHY_INTERFACE_MODE_NA) break; - /* Fall-through */ + fallthrough; case PHY_INTERFACE_MODE_1000BASEX: case PHY_INTERFACE_MODE_2500BASEX: if (port->comphy || @@ -5480,89 +5919,6 @@ empty_set: bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static void mvpp22_xlg_pcs_get_state(struct mvpp2_port *port, - struct phylink_link_state *state) -{ - u32 val; - - state->speed = SPEED_10000; - state->duplex = 1; - state->an_complete = 1; - - val = readl(port->base + MVPP22_XLG_STATUS); - state->link = !!(val & MVPP22_XLG_STATUS_LINK_UP); - - state->pause = 0; - val = readl(port->base + MVPP22_XLG_CTRL0_REG); - if (val & MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN) - state->pause |= MLO_PAUSE_TX; - if (val & MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN) - state->pause |= MLO_PAUSE_RX; -} - -static void mvpp2_gmac_pcs_get_state(struct mvpp2_port *port, - struct phylink_link_state *state) -{ - u32 val; - - val = readl(port->base + MVPP2_GMAC_STATUS0); - - state->an_complete = !!(val & MVPP2_GMAC_STATUS0_AN_COMPLETE); - state->link = !!(val & MVPP2_GMAC_STATUS0_LINK_UP); - state->duplex = !!(val & MVPP2_GMAC_STATUS0_FULL_DUPLEX); - - switch (port->phy_interface) { - case PHY_INTERFACE_MODE_1000BASEX: - state->speed = SPEED_1000; - break; - case PHY_INTERFACE_MODE_2500BASEX: - state->speed = SPEED_2500; - break; - default: - if (val & MVPP2_GMAC_STATUS0_GMII_SPEED) - state->speed = SPEED_1000; - else if (val & MVPP2_GMAC_STATUS0_MII_SPEED) - state->speed = SPEED_100; - else - state->speed = SPEED_10; - } - - state->pause = 0; - if (val & MVPP2_GMAC_STATUS0_RX_PAUSE) - state->pause |= MLO_PAUSE_RX; - if (val & MVPP2_GMAC_STATUS0_TX_PAUSE) - state->pause |= MLO_PAUSE_TX; -} - -static void mvpp2_phylink_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) -{ - struct mvpp2_port *port = mvpp2_phylink_to_port(config); - - if (port->priv->hw_version == MVPP22 && port->gop_id == 0) { - u32 mode = readl(port->base + MVPP22_XLG_CTRL3_REG); - mode &= MVPP22_XLG_CTRL3_MACMODESELECT_MASK; - - if (mode == MVPP22_XLG_CTRL3_MACMODESELECT_10G) { - mvpp22_xlg_pcs_get_state(port, state); - return; - } - } - - mvpp2_gmac_pcs_get_state(port, state); -} - -static void mvpp2_mac_an_restart(struct phylink_config *config) -{ - struct mvpp2_port *port = mvpp2_phylink_to_port(config); - u32 val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - - writel(val | MVPP2_GMAC_IN_BAND_RESTART_AN, - port->base + MVPP2_GMAC_AUTONEG_CONFIG); - writel(val & ~MVPP2_GMAC_IN_BAND_RESTART_AN, - port->base + MVPP2_GMAC_AUTONEG_CONFIG); -} - static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, const struct phylink_link_state *state) { @@ -5586,23 +5942,16 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, const struct phylink_link_state *state) { - u32 old_an, an; u32 old_ctrl0, ctrl0; u32 old_ctrl2, ctrl2; u32 old_ctrl4, ctrl4; - old_an = an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); old_ctrl0 = ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG); old_ctrl2 = ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG); old_ctrl4 = ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG); - an &= ~(MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN | - MVPP2_GMAC_FC_ADV_ASM_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG | - MVPP2_GMAC_AN_DUPLEX_EN | MVPP2_GMAC_IN_BAND_AUTONEG | - MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS); ctrl0 &= ~MVPP2_GMAC_PORT_TYPE_MASK; - ctrl2 &= ~(MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PORT_RESET_MASK | - MVPP2_GMAC_PCS_ENABLE_MASK); + ctrl2 &= ~(MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK); /* Configure port type */ if (phy_interface_mode_is_8023z(state->interface)) { @@ -5624,12 +5973,6 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; } - /* Configure advertisement bits */ - if (phylink_test(state->advertising, Pause)) - an |= MVPP2_GMAC_FC_ADV_EN; - if (phylink_test(state->advertising, Asym_Pause)) - an |= MVPP2_GMAC_FC_ADV_ASM_EN; - /* Configure negotiation style */ if (!phylink_autoneg_inband(mode)) { /* Phy or fixed speed - no in-band AN, nothing to do, leave the @@ -5638,14 +5981,6 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { /* SGMII in-band mode receives the speed and duplex from * the PHY. Flow control information is not received. */ - an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | - MVPP2_GMAC_FORCE_LINK_PASS | - MVPP2_GMAC_CONFIG_MII_SPEED | - MVPP2_GMAC_CONFIG_GMII_SPEED | - MVPP2_GMAC_CONFIG_FULL_DUPLEX); - an |= MVPP2_GMAC_IN_BAND_AUTONEG | - MVPP2_GMAC_AN_SPEED_EN | - MVPP2_GMAC_AN_DUPLEX_EN; } else if (phy_interface_mode_is_8023z(state->interface)) { /* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can * they negotiate duplex: they are always operating with a fixed @@ -5653,42 +5988,6 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, * speed and full duplex here. */ ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK; - an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | - MVPP2_GMAC_FORCE_LINK_PASS | - MVPP2_GMAC_CONFIG_MII_SPEED | - MVPP2_GMAC_CONFIG_GMII_SPEED | - MVPP2_GMAC_CONFIG_FULL_DUPLEX); - an |= MVPP2_GMAC_IN_BAND_AUTONEG | - MVPP2_GMAC_CONFIG_GMII_SPEED | - MVPP2_GMAC_CONFIG_FULL_DUPLEX; - - if (state->pause & MLO_PAUSE_AN && state->an_enabled) - an |= MVPP2_GMAC_FLOW_CTRL_AUTONEG; - } - -/* Some fields of the auto-negotiation register require the port to be down when - * their value is updated. - */ -#define MVPP2_GMAC_AN_PORT_DOWN_MASK \ - (MVPP2_GMAC_IN_BAND_AUTONEG | \ - MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS | \ - MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED | \ - MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_CONFIG_FULL_DUPLEX | \ - MVPP2_GMAC_AN_DUPLEX_EN) - - if ((old_ctrl0 ^ ctrl0) & MVPP2_GMAC_PORT_TYPE_MASK || - (old_ctrl2 ^ ctrl2) & MVPP2_GMAC_INBAND_AN_MASK || - (old_an ^ an) & MVPP2_GMAC_AN_PORT_DOWN_MASK) { - /* Force link down */ - old_an &= ~MVPP2_GMAC_FORCE_LINK_PASS; - old_an |= MVPP2_GMAC_FORCE_LINK_DOWN; - writel(old_an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); - - /* Set the GMAC in a reset state - do this in a way that - * ensures we clear it below. - */ - old_ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK; - writel(old_ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); } if (old_ctrl0 != ctrl0) @@ -5697,41 +5996,85 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); if (old_ctrl4 != ctrl4) writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG); - if (old_an != an) - writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); - - if (old_ctrl2 & MVPP2_GMAC_PORT_RESET_MASK) { - while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) & - MVPP2_GMAC_PORT_RESET_MASK) - continue; - } } -static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode, - const struct phylink_link_state *state) +static int mvpp2__mac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) { struct mvpp2_port *port = mvpp2_phylink_to_port(config); - bool change_interface = port->phy_interface != state->interface; /* Check for invalid configuration */ - if (mvpp2_is_xlg(state->interface) && port->gop_id != 0) { + if (mvpp2_is_xlg(interface) && port->gop_id != 0) { netdev_err(port->dev, "Invalid mode on %s\n", port->dev->name); - return; + return -EINVAL; + } + + if (port->phy_interface != interface || + phylink_autoneg_inband(mode)) { + /* Force the link down when changing the interface or if in + * in-band mode to ensure we do not change the configuration + * while the hardware is indicating link is up. We force both + * XLG and GMAC down to ensure that they're both in a known + * state. + */ + mvpp2_modify(port->base + MVPP2_GMAC_AUTONEG_CONFIG, + MVPP2_GMAC_FORCE_LINK_PASS | + MVPP2_GMAC_FORCE_LINK_DOWN, + MVPP2_GMAC_FORCE_LINK_DOWN); + + if (mvpp2_port_supports_xlg(port)) + mvpp2_modify(port->base + MVPP22_XLG_CTRL0_REG, + MVPP22_XLG_CTRL0_FORCE_LINK_PASS | + MVPP22_XLG_CTRL0_FORCE_LINK_DOWN, + MVPP22_XLG_CTRL0_FORCE_LINK_DOWN); } /* Make sure the port is disabled when reconfiguring the mode */ mvpp2_port_disable(port); - if (port->priv->hw_version == MVPP22 && change_interface) { - mvpp22_gop_mask_irq(port); + if (port->phy_interface != interface) { + /* Place GMAC into reset */ + mvpp2_modify(port->base + MVPP2_GMAC_CTRL_2_REG, + MVPP2_GMAC_PORT_RESET_MASK, + MVPP2_GMAC_PORT_RESET_MASK); - port->phy_interface = state->interface; + if (port->priv->hw_version == MVPP22) { + mvpp22_gop_mask_irq(port); - /* Reconfigure the serdes lanes */ - phy_power_off(port->comphy); - mvpp22_mode_reconfigure(port); + phy_power_off(port->comphy); + } } + /* Select the appropriate PCS operations depending on the + * configured interface mode. We will only switch to a mode + * that the validate() checks have already passed. + */ + if (mvpp2_is_xlg(interface)) + port->phylink_pcs.ops = &mvpp2_phylink_xlg_pcs_ops; + else + port->phylink_pcs.ops = &mvpp2_phylink_gmac_pcs_ops; + + return 0; +} + +static int mvpp2_mac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct mvpp2_port *port = mvpp2_phylink_to_port(config); + int ret; + + ret = mvpp2__mac_prepare(config, mode, interface); + if (ret == 0) + phylink_set_pcs(port->phylink, &port->phylink_pcs); + + return ret; +} + +static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ + struct mvpp2_port *port = mvpp2_phylink_to_port(config); + /* mac (re)configuration */ if (mvpp2_is_xlg(state->interface)) mvpp2_xlg_config(port, mode, state); @@ -5742,11 +6085,51 @@ static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode, if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK) mvpp2_port_loopback_set(port, state); +} + +static int mvpp2_mac_finish(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct mvpp2_port *port = mvpp2_phylink_to_port(config); + + if (port->priv->hw_version == MVPP22 && + port->phy_interface != interface) { + port->phy_interface = interface; - if (port->priv->hw_version == MVPP22 && change_interface) + /* Reconfigure the serdes lanes */ + mvpp22_mode_reconfigure(port); + + /* Unmask interrupts */ mvpp22_gop_unmask_irq(port); + } + + if (!mvpp2_is_xlg(interface)) { + /* Release GMAC reset and wait */ + mvpp2_modify(port->base + MVPP2_GMAC_CTRL_2_REG, + MVPP2_GMAC_PORT_RESET_MASK, 0); + + while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) & + MVPP2_GMAC_PORT_RESET_MASK) + continue; + } mvpp2_port_enable(port); + + /* Allow the link to come up if in in-band mode, otherwise the + * link is forced via mac_link_down()/mac_link_up() + */ + if (phylink_autoneg_inband(mode)) { + if (mvpp2_is_xlg(interface)) + mvpp2_modify(port->base + MVPP22_XLG_CTRL0_REG, + MVPP22_XLG_CTRL0_FORCE_LINK_PASS | + MVPP22_XLG_CTRL0_FORCE_LINK_DOWN, 0); + else + mvpp2_modify(port->base + MVPP2_GMAC_AUTONEG_CONFIG, + MVPP2_GMAC_FORCE_LINK_PASS | + MVPP2_GMAC_FORCE_LINK_DOWN, 0); + } + + return 0; } static void mvpp2_mac_link_up(struct phylink_config *config, @@ -5843,13 +6226,36 @@ static void mvpp2_mac_link_down(struct phylink_config *config, static const struct phylink_mac_ops mvpp2_phylink_ops = { .validate = mvpp2_phylink_validate, - .mac_pcs_get_state = mvpp2_phylink_mac_pcs_get_state, - .mac_an_restart = mvpp2_mac_an_restart, + .mac_prepare = mvpp2_mac_prepare, .mac_config = mvpp2_mac_config, + .mac_finish = mvpp2_mac_finish, .mac_link_up = mvpp2_mac_link_up, .mac_link_down = mvpp2_mac_link_down, }; +/* Work-around for ACPI */ +static void mvpp2_acpi_start(struct mvpp2_port *port) +{ + /* Phylink isn't used as of now for ACPI, so the MAC has to be + * configured manually when the interface is started. This will + * be removed as soon as the phylink ACPI support lands in. + */ + struct phylink_link_state state = { + .interface = port->phy_interface, + }; + mvpp2__mac_prepare(&port->phylink_config, MLO_AN_INBAND, + port->phy_interface); + mvpp2_mac_config(&port->phylink_config, MLO_AN_INBAND, &state); + port->phylink_pcs.ops->pcs_config(&port->phylink_pcs, MLO_AN_INBAND, + port->phy_interface, + state.advertising, false); + mvpp2_mac_finish(&port->phylink_config, MLO_AN_INBAND, + port->phy_interface); + mvpp2_mac_link_up(&port->phylink_config, NULL, + MLO_AN_INBAND, port->phy_interface, + SPEED_UNKNOWN, DUPLEX_UNKNOWN, false, false); +} + /* Ports initialization */ static int mvpp2_port_probe(struct platform_device *pdev, struct fwnode_handle *port_fwnode, @@ -5937,16 +6343,16 @@ static int mvpp2_port_probe(struct platform_device *pdev, goto err_free_netdev; if (port_node) - port->link_irq = of_irq_get_byname(port_node, "link"); + port->port_irq = of_irq_get_byname(port_node, "link"); else - port->link_irq = fwnode_irq_get(port_fwnode, port->nqvecs + 1); - if (port->link_irq == -EPROBE_DEFER) { + port->port_irq = fwnode_irq_get(port_fwnode, port->nqvecs + 1); + if (port->port_irq == -EPROBE_DEFER) { err = -EPROBE_DEFER; goto err_deinit_qvecs; } - if (port->link_irq <= 0) + if (port->port_irq <= 0) /* the link irq is optional */ - port->link_irq = 0; + port->port_irq = 0; if (fwnode_property_read_bool(port_fwnode, "marvell,loopback")) port->flags |= MVPP2_F_LOOPBACK; @@ -5983,6 +6389,12 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->stats_base = port->priv->iface_base + MVPP22_MIB_COUNTERS_OFFSET + port->gop_id * MVPP22_MIB_COUNTERS_PORT_SZ; + + /* We may want a property to describe whether we should use + * MAC hardware timestamping. + */ + if (priv->tai) + port->hwtstamp = true; } /* Alloc per-cpu and ethtool stats */ @@ -6110,8 +6522,8 @@ err_free_txq_pcpu: err_free_stats: free_percpu(port->stats); err_free_irq: - if (port->link_irq) - irq_dispose_mapping(port->link_irq); + if (port->port_irq) + irq_dispose_mapping(port->port_irq); err_deinit_qvecs: mvpp2_queue_vectors_deinit(port); err_free_netdev: @@ -6132,8 +6544,8 @@ static void mvpp2_port_remove(struct mvpp2_port *port) for (i = 0; i < port->ntxqs; i++) free_percpu(port->txqs[i]->pcpu); mvpp2_queue_vectors_deinit(port); - if (port->link_irq) - irq_dispose_mapping(port->link_irq); + if (port->port_irq) + irq_dispose_mapping(port->port_irq); free_netdev(port->dev); } @@ -6545,6 +6957,10 @@ static int mvpp2_probe(struct platform_device *pdev) goto err_axi_clk; } + err = mvpp22_tai_probe(&pdev->dev, priv); + if (err < 0) + goto err_axi_clk; + /* Initialize ports */ fwnode_for_each_available_child_node(fwnode, port_fwnode) { err = mvpp2_port_probe(pdev, port_fwnode, priv); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_tai.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_tai.c new file mode 100644 index 000000000000..95862aff49f1 --- /dev/null +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_tai.c @@ -0,0 +1,457 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Marvell PP2.2 TAI support + * + * Note: + * Do NOT use the event capture support. + * Do Not even set the MPP muxes to allow PTP_EVENT_REQ to be used. + * It will disrupt the operation of this driver, and there is nothing + * that this driver can do to prevent that. Even using PTP_EVENT_REQ + * as an output will be seen as a trigger input, which can't be masked. + * When ever a trigger input is seen, the action in the TCFCR0_TCF + * field will be performed - whether it is a set, increment, decrement + * read, or frequency update. + * + * Other notes (useful, not specified in the documentation): + * - PTP_PULSE_OUT (PTP_EVENT_REQ MPP) + * It looks like the hardware can't generate a pulse at nsec=0. (The + * output doesn't trigger if the nsec field is zero.) + * Note: when configured as an output via the register at 0xfX441120, + * the input is still very much alive, and will trigger the current TCF + * function. + * - PTP_CLK_OUT (PTP_TRIG_GEN MPP) + * This generates a "PPS" signal determined by the CCC registers. It + * seems this is not aligned to the TOD counter in any way (it may be + * initially, but if you specify a non-round second interval, it won't, + * and you can't easily get it back.) + * - PTP_PCLK_OUT + * This generates a 50% duty cycle clock based on the TOD counter, and + * seems it can be set to any period of 1ns resolution. It is probably + * limited by the TOD step size. Its period is defined by the PCLK_CCC + * registers. Again, its alignment to the second is questionable. + * + * Consequently, we support none of these. + */ +#include <linux/io.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/slab.h> + +#include "mvpp2.h" + +#define CR0_SW_NRESET BIT(0) + +#define TCFCR0_PHASE_UPDATE_ENABLE BIT(8) +#define TCFCR0_TCF_MASK (7 << 2) +#define TCFCR0_TCF_UPDATE (0 << 2) +#define TCFCR0_TCF_FREQUPDATE (1 << 2) +#define TCFCR0_TCF_INCREMENT (2 << 2) +#define TCFCR0_TCF_DECREMENT (3 << 2) +#define TCFCR0_TCF_CAPTURE (4 << 2) +#define TCFCR0_TCF_NOP (7 << 2) +#define TCFCR0_TCF_TRIGGER BIT(0) + +#define TCSR_CAPTURE_1_VALID BIT(1) +#define TCSR_CAPTURE_0_VALID BIT(0) + +struct mvpp2_tai { + struct ptp_clock_info caps; + struct ptp_clock *ptp_clock; + void __iomem *base; + spinlock_t lock; + u64 period; // nanosecond period in 32.32 fixed point + /* This timestamp is updated every two seconds */ + struct timespec64 stamp; +}; + +static void mvpp2_tai_modify(void __iomem *reg, u32 mask, u32 set) +{ + u32 val; + + val = readl_relaxed(reg) & ~mask; + val |= set & mask; + writel(val, reg); +} + +static void mvpp2_tai_write(u32 val, void __iomem *reg) +{ + writel_relaxed(val & 0xffff, reg); +} + +static u32 mvpp2_tai_read(void __iomem *reg) +{ + return readl_relaxed(reg) & 0xffff; +} + +static struct mvpp2_tai *ptp_to_tai(struct ptp_clock_info *ptp) +{ + return container_of(ptp, struct mvpp2_tai, caps); +} + +static void mvpp22_tai_read_ts(struct timespec64 *ts, void __iomem *base) +{ + ts->tv_sec = (u64)mvpp2_tai_read(base + 0) << 32 | + mvpp2_tai_read(base + 4) << 16 | + mvpp2_tai_read(base + 8); + + ts->tv_nsec = mvpp2_tai_read(base + 12) << 16 | + mvpp2_tai_read(base + 16); + + /* Read and discard fractional part */ + readl_relaxed(base + 20); + readl_relaxed(base + 24); +} + +static void mvpp2_tai_write_tlv(const struct timespec64 *ts, u32 frac, + void __iomem *base) +{ + mvpp2_tai_write(ts->tv_sec >> 32, base + MVPP22_TAI_TLV_SEC_HIGH); + mvpp2_tai_write(ts->tv_sec >> 16, base + MVPP22_TAI_TLV_SEC_MED); + mvpp2_tai_write(ts->tv_sec, base + MVPP22_TAI_TLV_SEC_LOW); + mvpp2_tai_write(ts->tv_nsec >> 16, base + MVPP22_TAI_TLV_NANO_HIGH); + mvpp2_tai_write(ts->tv_nsec, base + MVPP22_TAI_TLV_NANO_LOW); + mvpp2_tai_write(frac >> 16, base + MVPP22_TAI_TLV_FRAC_HIGH); + mvpp2_tai_write(frac, base + MVPP22_TAI_TLV_FRAC_LOW); +} + +static void mvpp2_tai_op(u32 op, void __iomem *base) +{ + /* Trigger the operation. Note that an external unmaskable + * event on PTP_EVENT_REQ will also trigger this action. + */ + mvpp2_tai_modify(base + MVPP22_TAI_TCFCR0, + TCFCR0_TCF_MASK | TCFCR0_TCF_TRIGGER, + op | TCFCR0_TCF_TRIGGER); + mvpp2_tai_modify(base + MVPP22_TAI_TCFCR0, TCFCR0_TCF_MASK, + TCFCR0_TCF_NOP); +} + +/* The adjustment has a range of +0.5ns to -0.5ns in 2^32 steps, so has units + * of 2^-32 ns. + * + * units(s) = 1 / (2^32 * 10^9) + * fractional = abs_scaled_ppm / (2^16 * 10^6) + * + * What we want to achieve: + * freq_adjusted = freq_nominal * (1 + fractional) + * freq_delta = freq_adjusted - freq_nominal => positive = faster + * freq_delta = freq_nominal * (1 + fractional) - freq_nominal + * So: freq_delta = freq_nominal * fractional + * + * However, we are dealing with periods, so: + * period_adjusted = period_nominal / (1 + fractional) + * period_delta = period_nominal - period_adjusted => positive = faster + * period_delta = period_nominal * fractional / (1 + fractional) + * + * Hence: + * period_delta = period_nominal * abs_scaled_ppm / + * (2^16 * 10^6 + abs_scaled_ppm) + * + * To avoid overflow, we reduce both sides of the divide operation by a factor + * of 16. + */ +static u64 mvpp22_calc_frac_ppm(struct mvpp2_tai *tai, long abs_scaled_ppm) +{ + u64 val = tai->period * abs_scaled_ppm >> 4; + + return div_u64(val, (1000000 << 12) + (abs_scaled_ppm >> 4)); +} + +static s32 mvpp22_calc_max_adj(struct mvpp2_tai *tai) +{ + return 1000000; +} + +static int mvpp22_tai_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct mvpp2_tai *tai = ptp_to_tai(ptp); + unsigned long flags; + void __iomem *base; + bool neg_adj; + s32 frac; + u64 val; + + neg_adj = scaled_ppm < 0; + if (neg_adj) + scaled_ppm = -scaled_ppm; + + val = mvpp22_calc_frac_ppm(tai, scaled_ppm); + + /* Convert to a signed 32-bit adjustment */ + if (neg_adj) { + /* -S32_MIN warns, -val < S32_MIN fails, so go for the easy + * solution. + */ + if (val > 0x80000000) + return -ERANGE; + + frac = -val; + } else { + if (val > S32_MAX) + return -ERANGE; + + frac = val; + } + + base = tai->base; + spin_lock_irqsave(&tai->lock, flags); + mvpp2_tai_write(frac >> 16, base + MVPP22_TAI_TLV_FRAC_HIGH); + mvpp2_tai_write(frac, base + MVPP22_TAI_TLV_FRAC_LOW); + mvpp2_tai_op(TCFCR0_TCF_FREQUPDATE, base); + spin_unlock_irqrestore(&tai->lock, flags); + + return 0; +} + +static int mvpp22_tai_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct mvpp2_tai *tai = ptp_to_tai(ptp); + struct timespec64 ts; + unsigned long flags; + void __iomem *base; + u32 tcf; + + /* We can't deal with S64_MIN */ + if (delta == S64_MIN) + return -ERANGE; + + if (delta < 0) { + delta = -delta; + tcf = TCFCR0_TCF_DECREMENT; + } else { + tcf = TCFCR0_TCF_INCREMENT; + } + + ts = ns_to_timespec64(delta); + + base = tai->base; + spin_lock_irqsave(&tai->lock, flags); + mvpp2_tai_write_tlv(&ts, 0, base); + mvpp2_tai_op(tcf, base); + spin_unlock_irqrestore(&tai->lock, flags); + + return 0; +} + +static int mvpp22_tai_gettimex64(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct mvpp2_tai *tai = ptp_to_tai(ptp); + unsigned long flags; + void __iomem *base; + u32 tcsr; + int ret; + + base = tai->base; + spin_lock_irqsave(&tai->lock, flags); + /* XXX: the only way to read the PTP time is for the CPU to trigger + * an event. However, there is no way to distinguish between the CPU + * triggered event, and an external event on PTP_EVENT_REQ. So this + * is incompatible with external use of PTP_EVENT_REQ. + */ + ptp_read_system_prets(sts); + mvpp2_tai_modify(base + MVPP22_TAI_TCFCR0, + TCFCR0_TCF_MASK | TCFCR0_TCF_TRIGGER, + TCFCR0_TCF_CAPTURE | TCFCR0_TCF_TRIGGER); + ptp_read_system_postts(sts); + mvpp2_tai_modify(base + MVPP22_TAI_TCFCR0, TCFCR0_TCF_MASK, + TCFCR0_TCF_NOP); + + tcsr = readl(base + MVPP22_TAI_TCSR); + if (tcsr & TCSR_CAPTURE_1_VALID) { + mvpp22_tai_read_ts(ts, base + MVPP22_TAI_TCV1_SEC_HIGH); + ret = 0; + } else if (tcsr & TCSR_CAPTURE_0_VALID) { + mvpp22_tai_read_ts(ts, base + MVPP22_TAI_TCV0_SEC_HIGH); + ret = 0; + } else { + /* We don't seem to have a reading... */ + ret = -EBUSY; + } + spin_unlock_irqrestore(&tai->lock, flags); + + return ret; +} + +static int mvpp22_tai_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct mvpp2_tai *tai = ptp_to_tai(ptp); + unsigned long flags; + void __iomem *base; + + base = tai->base; + spin_lock_irqsave(&tai->lock, flags); + mvpp2_tai_write_tlv(ts, 0, base); + + /* Trigger an update to load the value from the TLV registers + * into the TOD counter. Note that an external unmaskable event on + * PTP_EVENT_REQ will also trigger this action. + */ + mvpp2_tai_modify(base + MVPP22_TAI_TCFCR0, + TCFCR0_PHASE_UPDATE_ENABLE | + TCFCR0_TCF_MASK | TCFCR0_TCF_TRIGGER, + TCFCR0_TCF_UPDATE | TCFCR0_TCF_TRIGGER); + mvpp2_tai_modify(base + MVPP22_TAI_TCFCR0, TCFCR0_TCF_MASK, + TCFCR0_TCF_NOP); + spin_unlock_irqrestore(&tai->lock, flags); + + return 0; +} + +static long mvpp22_tai_aux_work(struct ptp_clock_info *ptp) +{ + struct mvpp2_tai *tai = ptp_to_tai(ptp); + + mvpp22_tai_gettimex64(ptp, &tai->stamp, NULL); + + return msecs_to_jiffies(2000); +} + +static void mvpp22_tai_set_step(struct mvpp2_tai *tai) +{ + void __iomem *base = tai->base; + u32 nano, frac; + + nano = upper_32_bits(tai->period); + frac = lower_32_bits(tai->period); + + /* As the fractional nanosecond is a signed offset, if the MSB (sign) + * bit is set, we have to increment the whole nanoseconds. + */ + if (frac >= 0x80000000) + nano += 1; + + mvpp2_tai_write(nano, base + MVPP22_TAI_TOD_STEP_NANO_CR); + mvpp2_tai_write(frac >> 16, base + MVPP22_TAI_TOD_STEP_FRAC_HIGH); + mvpp2_tai_write(frac, base + MVPP22_TAI_TOD_STEP_FRAC_LOW); +} + +static void mvpp22_tai_init(struct mvpp2_tai *tai) +{ + void __iomem *base = tai->base; + + mvpp22_tai_set_step(tai); + + /* Release the TAI reset */ + mvpp2_tai_modify(base + MVPP22_TAI_CR0, CR0_SW_NRESET, CR0_SW_NRESET); +} + +int mvpp22_tai_ptp_clock_index(struct mvpp2_tai *tai) +{ + return ptp_clock_index(tai->ptp_clock); +} + +void mvpp22_tai_tstamp(struct mvpp2_tai *tai, u32 tstamp, + struct skb_shared_hwtstamps *hwtstamp) +{ + struct timespec64 ts; + int delta; + + /* The tstamp consists of 2 bits of seconds and 30 bits of nanoseconds. + * We use our stored timestamp (tai->stamp) to form a full timestamp, + * and we must read the seconds exactly once. + */ + ts.tv_sec = READ_ONCE(tai->stamp.tv_sec); + ts.tv_nsec = tstamp & 0x3fffffff; + + /* Calculate the delta in seconds between our stored timestamp and + * the value read from the queue. Allow timestamps one second in the + * past, otherwise consider them to be in the future. + */ + delta = ((tstamp >> 30) - (ts.tv_sec & 3)) & 3; + if (delta == 3) + delta -= 4; + ts.tv_sec += delta; + + memset(hwtstamp, 0, sizeof(*hwtstamp)); + hwtstamp->hwtstamp = timespec64_to_ktime(ts); +} + +void mvpp22_tai_start(struct mvpp2_tai *tai) +{ + long delay; + + delay = mvpp22_tai_aux_work(&tai->caps); + + ptp_schedule_worker(tai->ptp_clock, delay); +} + +void mvpp22_tai_stop(struct mvpp2_tai *tai) +{ + ptp_cancel_worker_sync(tai->ptp_clock); +} + +static void mvpp22_tai_remove(void *priv) +{ + struct mvpp2_tai *tai = priv; + + if (!IS_ERR(tai->ptp_clock)) + ptp_clock_unregister(tai->ptp_clock); +} + +int mvpp22_tai_probe(struct device *dev, struct mvpp2 *priv) +{ + struct mvpp2_tai *tai; + int ret; + + tai = devm_kzalloc(dev, sizeof(*tai), GFP_KERNEL); + if (!tai) + return -ENOMEM; + + spin_lock_init(&tai->lock); + + tai->base = priv->iface_base; + + /* The step size consists of three registers - a 16-bit nanosecond step + * size, and a 32-bit fractional nanosecond step size split over two + * registers. The fractional nanosecond step size has units of 2^-32ns. + * + * To calculate this, we calculate: + * (10^9 + freq / 2) / (freq * 2^-32) + * which gives us the nanosecond step to the nearest integer in 16.32 + * fixed point format, and the fractional part of the step size with + * the MSB inverted. With rounding of the fractional nanosecond, and + * simplification, this becomes: + * (10^9 << 32 + freq << 31 + (freq + 1) >> 1) / freq + * + * So: + * div = (10^9 << 32 + freq << 31 + (freq + 1) >> 1) / freq + * nano = upper_32_bits(div); + * frac = lower_32_bits(div) ^ 0x80000000; + * Will give the values for the registers. + * + * This is all seems perfect, but alas it is not when considering the + * whole story. The system is clocked from 25MHz, which is multiplied + * by a PLL to 1GHz, and then divided by three, giving 333333333Hz + * (recurring). This gives exactly 3ns, but using 333333333Hz with + * the above gives an error of 13*2^-32ns. + * + * Consequently, we use the period rather than calculating from the + * frequency. + */ + tai->period = 3ULL << 32; + + mvpp22_tai_init(tai); + + tai->caps.owner = THIS_MODULE; + strscpy(tai->caps.name, "Marvell PP2.2", sizeof(tai->caps.name)); + tai->caps.max_adj = mvpp22_calc_max_adj(tai); + tai->caps.adjfine = mvpp22_tai_adjfine; + tai->caps.adjtime = mvpp22_tai_adjtime; + tai->caps.gettimex64 = mvpp22_tai_gettimex64; + tai->caps.settime64 = mvpp22_tai_settime64; + tai->caps.do_aux_work = mvpp22_tai_aux_work; + + ret = devm_add_action(dev, mvpp22_tai_remove, tai); + if (ret) + return ret; + + tai->ptp_clock = ptp_clock_register(&tai->caps, dev); + if (IS_ERR(tai->ptp_clock)) + return PTR_ERR(tai->ptp_clock); + + priv->tai = tai; + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile index 1b25948c662b..0bc2410c8949 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_OCTEONTX2_AF) += octeontx2_af.o octeontx2_mbox-y := mbox.o octeontx2_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \ - rvu_reg.o rvu_npc.o rvu_debugfs.o + rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index a4e65da8d95b..8f17e26dca53 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -468,6 +468,35 @@ static void cgx_lmac_pause_frm_config(struct cgx *cgx, int lmac_id, bool enable) } } +void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable) +{ + struct cgx *cgx = cgxd; + u64 cfg; + + if (!cgx) + return; + + if (enable) { + /* Enable inbound PTP timestamping */ + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg |= CGX_GMP_GMI_RXX_FRM_CTL_PTP_MODE; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); + cfg |= CGX_SMUX_RX_FRM_CTL_PTP_MODE; + cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + } else { + /* Disable inbound PTP stamping */ + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_PTP_MODE; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); + cfg &= ~CGX_SMUX_RX_FRM_CTL_PTP_MODE; + cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + } +} + /* CGX Firmware interface low level support */ static int cgx_fwi_cmd_send(u64 req, u64 *resp, struct lmac *lmac) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 394f96591feb..27ca3291682b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -58,8 +58,10 @@ #define CGXX_SMUX_RX_FRM_CTL 0x20020 #define CGX_SMUX_RX_FRM_CTL_CTL_BCK BIT_ULL(3) +#define CGX_SMUX_RX_FRM_CTL_PTP_MODE BIT_ULL(12) #define CGXX_GMP_GMI_RXX_FRM_CTL 0x38028 #define CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK BIT_ULL(3) +#define CGX_GMP_GMI_RXX_FRM_CTL_PTP_MODE BIT_ULL(12) #define CGXX_SMUX_TX_CTL 0x20178 #define CGXX_SMUX_TX_PAUSE_PKT_TIME 0x20110 #define CGXX_SMUX_TX_PAUSE_PKT_INTERVAL 0x20120 @@ -139,4 +141,6 @@ int cgx_lmac_get_pause_frm(void *cgxd, int lmac_id, u8 *tx_pause, u8 *rx_pause); int cgx_lmac_set_pause_frm(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause); +void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable); + #endif /* CGX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 6dfd0f90cd70..4aaef0a2b51c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -127,6 +127,7 @@ M(ATTACH_RESOURCES, 0x002, attach_resources, rsrc_attach, msg_rsp) \ M(DETACH_RESOURCES, 0x003, detach_resources, rsrc_detach, msg_rsp) \ M(MSIX_OFFSET, 0x005, msix_offset, msg_req, msix_offset_rsp) \ M(VF_FLR, 0x006, vf_flr, msg_req, msg_rsp) \ +M(PTP_OP, 0x007, ptp_op, ptp_req, ptp_rsp) \ M(GET_HW_CAP, 0x008, get_hw_cap, msg_req, get_hw_cap_rsp) \ /* CGX mbox IDs (range 0x200 - 0x3FF) */ \ M(CGX_START_RXTX, 0x200, cgx_start_rxtx, msg_req, msg_rsp) \ @@ -143,6 +144,8 @@ M(CGX_STOP_LINKEVENTS, 0x208, cgx_stop_linkevents, msg_req, msg_rsp) \ M(CGX_GET_LINKINFO, 0x209, cgx_get_linkinfo, msg_req, cgx_link_info_msg) \ M(CGX_INTLBK_ENABLE, 0x20A, cgx_intlbk_enable, msg_req, msg_rsp) \ M(CGX_INTLBK_DISABLE, 0x20B, cgx_intlbk_disable, msg_req, msg_rsp) \ +M(CGX_PTP_RX_ENABLE, 0x20C, cgx_ptp_rx_enable, msg_req, msg_rsp) \ +M(CGX_PTP_RX_DISABLE, 0x20D, cgx_ptp_rx_disable, msg_req, msg_rsp) \ M(CGX_CFG_PAUSE_FRM, 0x20E, cgx_cfg_pause_frm, cgx_pause_frm_cfg, \ cgx_pause_frm_cfg) \ /* NPA mbox IDs (range 0x400 - 0x5FF) */ \ @@ -213,6 +216,8 @@ M(NIX_LSO_FORMAT_CFG, 0x8011, nix_lso_format_cfg, \ nix_lso_format_cfg, \ nix_lso_format_cfg_rsp) \ M(NIX_RXVLAN_ALLOC, 0x8012, nix_rxvlan_alloc, msg_req, msg_rsp) \ +M(NIX_LF_PTP_TX_ENABLE, 0x8013, nix_lf_ptp_tx_enable, msg_req, msg_rsp) \ +M(NIX_LF_PTP_TX_DISABLE, 0x8014, nix_lf_ptp_tx_disable, msg_req, msg_rsp) \ M(NIX_BP_ENABLE, 0x8016, nix_bp_enable, nix_bp_cfg_req, \ nix_bp_cfg_rsp) \ M(NIX_BP_DISABLE, 0x8017, nix_bp_disable, nix_bp_cfg_req, msg_rsp) \ @@ -858,4 +863,20 @@ struct npc_get_kex_cfg_rsp { u8 mkex_pfl_name[MKEX_NAME_LEN]; }; +enum ptp_op { + PTP_OP_ADJFINE = 0, + PTP_OP_GET_CLOCK = 1, +}; + +struct ptp_req { + struct mbox_msghdr hdr; + u8 op; + s64 scaled_ppm; +}; + +struct ptp_rsp { + struct mbox_msghdr hdr; + u64 clk; +}; + #endif /* MBOX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c new file mode 100644 index 000000000000..f69f4f35ae48 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell PTP driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ + +#include <linux/bitfield.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/pci.h> + +#include "ptp.h" +#include "mbox.h" +#include "rvu.h" + +#define DRV_NAME "Marvell PTP Driver" + +#define PCI_DEVID_OCTEONTX2_PTP 0xA00C +#define PCI_SUBSYS_DEVID_OCTX2_98xx_PTP 0xB100 +#define PCI_SUBSYS_DEVID_OCTX2_96XX_PTP 0xB200 +#define PCI_SUBSYS_DEVID_OCTX2_95XX_PTP 0xB300 +#define PCI_SUBSYS_DEVID_OCTX2_LOKI_PTP 0xB400 +#define PCI_SUBSYS_DEVID_OCTX2_95MM_PTP 0xB500 +#define PCI_DEVID_OCTEONTX2_RST 0xA085 + +#define PCI_PTP_BAR_NO 0 +#define PCI_RST_BAR_NO 0 + +#define PTP_CLOCK_CFG 0xF00ULL +#define PTP_CLOCK_CFG_PTP_EN BIT_ULL(0) +#define PTP_CLOCK_LO 0xF08ULL +#define PTP_CLOCK_HI 0xF10ULL +#define PTP_CLOCK_COMP 0xF18ULL + +#define RST_BOOT 0x1600ULL +#define RST_MUL_BITS GENMASK_ULL(38, 33) +#define CLOCK_BASE_RATE 50000000ULL + +static u64 get_clock_rate(void) +{ + u64 cfg, ret = CLOCK_BASE_RATE * 16; + struct pci_dev *pdev; + void __iomem *base; + + /* To get the input clock frequency with which PTP co-processor + * block is running the base frequency(50 MHz) needs to be multiplied + * with multiplier bits present in RST_BOOT register of RESET block. + * Hence below code gets the multiplier bits from the RESET PCI + * device present in the system. + */ + pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, + PCI_DEVID_OCTEONTX2_RST, NULL); + if (!pdev) + goto error; + + base = pci_ioremap_bar(pdev, PCI_RST_BAR_NO); + if (!base) + goto error_put_pdev; + + cfg = readq(base + RST_BOOT); + ret = CLOCK_BASE_RATE * FIELD_GET(RST_MUL_BITS, cfg); + + iounmap(base); + +error_put_pdev: + pci_dev_put(pdev); + +error: + return ret; +} + +struct ptp *ptp_get(void) +{ + struct pci_dev *pdev; + struct ptp *ptp; + + /* If the PTP pci device is found on the system and ptp + * driver is bound to it then the PTP pci device is returned + * to the caller(rvu driver). + */ + pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, + PCI_DEVID_OCTEONTX2_PTP, NULL); + if (!pdev) + return ERR_PTR(-ENODEV); + + ptp = pci_get_drvdata(pdev); + if (!ptp) + ptp = ERR_PTR(-EPROBE_DEFER); + if (IS_ERR(ptp)) + pci_dev_put(pdev); + + return ptp; +} + +void ptp_put(struct ptp *ptp) +{ + if (!ptp) + return; + + pci_dev_put(ptp->pdev); +} + +static int ptp_adjfine(struct ptp *ptp, long scaled_ppm) +{ + bool neg_adj = false; + u64 comp; + u64 adj; + s64 ppb; + + if (scaled_ppm < 0) { + neg_adj = true; + scaled_ppm = -scaled_ppm; + } + + /* The hardware adds the clock compensation value to the PTP clock + * on every coprocessor clock cycle. Typical convention is that it + * represent number of nanosecond betwen each cycle. In this + * convention compensation value is in 64 bit fixed-point + * representation where upper 32 bits are number of nanoseconds + * and lower is fractions of nanosecond. + * The scaled_ppm represent the ratio in "parts per million" by which + * the compensation value should be corrected. + * To calculate new compenstation value we use 64bit fixed point + * arithmetic on following formula + * comp = tbase + tbase * scaled_ppm / (1M * 2^16) + * where tbase is the basic compensation value calculated + * initialy in the probe function. + */ + comp = ((u64)1000000000ull << 32) / ptp->clock_rate; + /* convert scaled_ppm to ppb */ + ppb = 1 + scaled_ppm; + ppb *= 125; + ppb >>= 13; + adj = comp * ppb; + adj = div_u64(adj, 1000000000ull); + comp = neg_adj ? comp - adj : comp + adj; + + writeq(comp, ptp->reg_base + PTP_CLOCK_COMP); + + return 0; +} + +static int ptp_get_clock(struct ptp *ptp, u64 *clk) +{ + /* Return the current PTP clock */ + *clk = readq(ptp->reg_base + PTP_CLOCK_HI); + + return 0; +} + +static int ptp_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct device *dev = &pdev->dev; + struct ptp *ptp; + u64 clock_comp; + u64 clock_cfg; + int err; + + ptp = devm_kzalloc(dev, sizeof(*ptp), GFP_KERNEL); + if (!ptp) { + err = -ENOMEM; + goto error; + } + + ptp->pdev = pdev; + + err = pcim_enable_device(pdev); + if (err) + goto error_free; + + err = pcim_iomap_regions(pdev, 1 << PCI_PTP_BAR_NO, pci_name(pdev)); + if (err) + goto error_free; + + ptp->reg_base = pcim_iomap_table(pdev)[PCI_PTP_BAR_NO]; + + ptp->clock_rate = get_clock_rate(); + + /* Enable PTP clock */ + clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG); + clock_cfg |= PTP_CLOCK_CFG_PTP_EN; + writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG); + + clock_comp = ((u64)1000000000ull << 32) / ptp->clock_rate; + /* Initial compensation value to start the nanosecs counter */ + writeq(clock_comp, ptp->reg_base + PTP_CLOCK_COMP); + + pci_set_drvdata(pdev, ptp); + + return 0; + +error_free: + devm_kfree(dev, ptp); + +error: + /* For `ptp_get()` we need to differentiate between the case + * when the core has not tried to probe this device and the case when + * the probe failed. In the later case we pretend that the + * initialization was successful and keep the error in + * `dev->driver_data`. + */ + pci_set_drvdata(pdev, ERR_PTR(err)); + return 0; +} + +static void ptp_remove(struct pci_dev *pdev) +{ + struct ptp *ptp = pci_get_drvdata(pdev); + u64 clock_cfg; + + if (IS_ERR_OR_NULL(ptp)) + return; + + /* Disable PTP clock */ + clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG); + clock_cfg &= ~PTP_CLOCK_CFG_PTP_EN; + writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG); +} + +static const struct pci_device_id ptp_id_table[] = { + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_98xx_PTP) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_96XX_PTP) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_95XX_PTP) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_LOKI_PTP) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_95MM_PTP) }, + { 0, } +}; + +struct pci_driver ptp_driver = { + .name = DRV_NAME, + .id_table = ptp_id_table, + .probe = ptp_probe, + .remove = ptp_remove, +}; + +int rvu_mbox_handler_ptp_op(struct rvu *rvu, struct ptp_req *req, + struct ptp_rsp *rsp) +{ + int err = 0; + + /* This function is the PTP mailbox handler invoked when + * called by AF consumers/netdev drivers via mailbox mechanism. + * It is used by netdev driver to get the PTP clock and to set + * frequency adjustments. Since mailbox can be called without + * notion of whether the driver is bound to ptp device below + * validation is needed as first step. + */ + if (!rvu->ptp) + return -ENODEV; + + switch (req->op) { + case PTP_OP_ADJFINE: + err = ptp_adjfine(rvu->ptp, req->scaled_ppm); + break; + case PTP_OP_GET_CLOCK: + err = ptp_get_clock(rvu->ptp, &rsp->clk); + break; + default: + err = -EINVAL; + break; + } + + return err; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.h b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h new file mode 100644 index 000000000000..878bc395d28f --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell PTP driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ + +#ifndef PTP_H +#define PTP_H + +#include <linux/timecounter.h> +#include <linux/time64.h> +#include <linux/spinlock.h> + +struct ptp { + struct pci_dev *pdev; + void __iomem *reg_base; + u32 clock_rate; +}; + +struct ptp *ptp_get(void); +void ptp_put(struct ptp *ptp); + +extern struct pci_driver ptp_driver; + +#endif diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 557e4292c846..c3ef73ae782c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -18,6 +18,7 @@ #include "cgx.h" #include "rvu.h" #include "rvu_reg.h" +#include "ptp.h" #define DRV_NAME "octeontx2-af" #define DRV_STRING "Marvell OcteonTX2 RVU Admin Function Driver" @@ -2565,13 +2566,21 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); + rvu->ptp = ptp_get(); + if (IS_ERR(rvu->ptp)) { + err = PTR_ERR(rvu->ptp); + if (err == -EPROBE_DEFER) + goto err_release_regions; + rvu->ptp = NULL; + } + /* Map Admin function CSRs */ rvu->afreg_base = pcim_iomap(pdev, PCI_AF_REG_BAR_NUM, 0); rvu->pfreg_base = pcim_iomap(pdev, PCI_PF_REG_BAR_NUM, 0); if (!rvu->afreg_base || !rvu->pfreg_base) { dev_err(dev, "Unable to map admin function CSRs, aborting\n"); err = -ENOMEM; - goto err_release_regions; + goto err_put_ptp; } /* Store module params in rvu structure */ @@ -2586,7 +2595,7 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id) err = rvu_setup_hw_resources(rvu); if (err) - goto err_release_regions; + goto err_put_ptp; /* Init mailbox btw AF and PFs */ err = rvu_mbox_init(rvu, &rvu->afpf_wq_info, TYPE_AFPF, @@ -2626,6 +2635,8 @@ err_hwsetup: rvu_reset_all_blocks(rvu); rvu_free_hw_resources(rvu); rvu_clear_rvum_blk_revid(rvu); +err_put_ptp: + ptp_put(rvu->ptp); err_release_regions: pci_release_regions(pdev); err_disable_device: @@ -2651,6 +2662,7 @@ static void rvu_remove(struct pci_dev *pdev) rvu_reset_all_blocks(rvu); rvu_free_hw_resources(rvu); rvu_clear_rvum_blk_revid(rvu); + ptp_put(rvu->ptp); pci_release_regions(pdev); pci_disable_device(pdev); pci_set_drvdata(pdev, NULL); @@ -2676,9 +2688,19 @@ static int __init rvu_init_module(void) if (err < 0) return err; + err = pci_register_driver(&ptp_driver); + if (err < 0) + goto ptp_err; + err = pci_register_driver(&rvu_driver); if (err < 0) - pci_unregister_driver(&cgx_driver); + goto rvu_err; + + return 0; +rvu_err: + pci_unregister_driver(&ptp_driver); +ptp_err: + pci_unregister_driver(&cgx_driver); return err; } @@ -2686,6 +2708,7 @@ static int __init rvu_init_module(void) static void __exit rvu_cleanup_module(void) { pci_unregister_driver(&rvu_driver); + pci_unregister_driver(&ptp_driver); pci_unregister_driver(&cgx_driver); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index dcf25a092008..05da7a91944a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -289,6 +289,8 @@ struct rvu_fwdata { u64 reserved[FWDATA_RESERVED_MEM]; }; +struct ptp; + struct rvu { void __iomem *afreg_base; void __iomem *pfreg_base; @@ -337,6 +339,8 @@ struct rvu { /* Firmware data */ struct rvu_fwdata *fwdata; + struct ptp *ptp; + #ifdef CONFIG_DEBUG_FS struct rvu_debugfs rvu_dbg; #endif @@ -469,6 +473,7 @@ int rvu_npc_init(struct rvu *rvu); void rvu_npc_freemem(struct rvu *rvu); int rvu_npc_get_pkind(struct rvu *rvu, u16 pf); void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf); +int npc_config_ts_kpuaction(struct rvu *rvu, int pf, u16 pcifunc, bool en); void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan, u8 *mac_addr); void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index f3c82e489897..fe3389c144b5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -509,6 +509,45 @@ int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req, return 0; } +static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) +{ + int pf = rvu_get_pf(pcifunc); + u8 cgx_id, lmac_id; + void *cgxd; + + /* This msg is expected only from PFs that are mapped to CGX LMACs, + * if received from other PF/VF simply ACK, nothing to do. + */ + if ((pcifunc & RVU_PFVF_FUNC_MASK) || + !is_pf_cgxmapped(rvu, pf)) + return -ENODEV; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + + cgx_lmac_ptp_config(cgxd, lmac_id, enable); + /* If PTP is enabled then inform NPC that packets to be + * parsed by this PF will have their data shifted by 8 bytes + * and if PTP is disabled then no shift is required + */ + if (npc_config_ts_kpuaction(rvu, pf, pcifunc, enable)) + return -EINVAL; + + return 0; +} + +int rvu_mbox_handler_cgx_ptp_rx_enable(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_cgx_ptp_rx_cfg(rvu, req->hdr.pcifunc, true); +} + +int rvu_mbox_handler_cgx_ptp_rx_disable(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_cgx_ptp_rx_cfg(rvu, req->hdr.pcifunc, false); +} + static int rvu_cgx_config_linkevents(struct rvu *rvu, u16 pcifunc, bool en) { int pf = rvu_get_pf(pcifunc); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 36953d4f51c7..08181fc5f5d4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -737,7 +737,7 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, else if (req->ctype == NIX_AQ_CTYPE_MCE) memcpy(mask, &req->mce_mask, sizeof(struct nix_rx_mce_s)); - /* Fall through */ + fallthrough; case NIX_AQ_INSTOP_INIT: if (req->ctype == NIX_AQ_CTYPE_RQ) memcpy(ctx, &req->rq, sizeof(struct nix_rq_ctx_s)); @@ -3319,6 +3319,49 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) nix_ctx_free(rvu, pfvf); } +#define NIX_AF_LFX_TX_CFG_PTP_EN BIT_ULL(32) + +static int rvu_nix_lf_ptp_tx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_block *block; + int blkaddr; + int nixlf; + u64 cfg; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (blkaddr < 0) + return NIX_AF_ERR_AF_LF_INVALID; + + block = &hw->block[blkaddr]; + nixlf = rvu_get_lf(rvu, block, pcifunc, 0); + if (nixlf < 0) + return NIX_AF_ERR_AF_LF_INVALID; + + cfg = rvu_read64(rvu, blkaddr, NIX_AF_LFX_TX_CFG(nixlf)); + + if (enable) + cfg |= NIX_AF_LFX_TX_CFG_PTP_EN; + else + cfg &= ~NIX_AF_LFX_TX_CFG_PTP_EN; + + rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_CFG(nixlf), cfg); + + return 0; +} + +int rvu_mbox_handler_nix_lf_ptp_tx_enable(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_nix_lf_ptp_tx_cfg(rvu, req->hdr.pcifunc, true); +} + +int rvu_mbox_handler_nix_lf_ptp_tx_disable(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_nix_lf_ptp_tx_cfg(rvu, req->hdr.pcifunc, false); +} + int rvu_mbox_handler_nix_lso_format_cfg(struct rvu *rvu, struct nix_lso_format_cfg *req, struct nix_lso_format_cfg_rsp *rsp) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 0a214084406a..e2e585d4de9b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -27,6 +27,7 @@ #define NIXLF_PROMISC_ENTRY 2 #define NPC_PARSE_RESULT_DMAC_OFFSET 8 +#define NPC_HW_TSTAMP_OFFSET 8 static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr, u16 pcifunc); @@ -61,6 +62,36 @@ int rvu_npc_get_pkind(struct rvu *rvu, u16 pf) return -1; } +#define NPC_AF_ACTION0_PTR_ADVANCE GENMASK_ULL(27, 20) + +int npc_config_ts_kpuaction(struct rvu *rvu, int pf, u16 pcifunc, bool enable) +{ + int pkind, blkaddr; + u64 val; + + pkind = rvu_npc_get_pkind(rvu, pf); + if (pkind < 0) { + dev_err(rvu->dev, "%s: pkind not mapped\n", __func__); + return -EINVAL; + } + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, pcifunc); + if (blkaddr < 0) { + dev_err(rvu->dev, "%s: NPC block not implemented\n", __func__); + return -EINVAL; + } + + val = rvu_read64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind)); + val &= ~NPC_AF_ACTION0_PTR_ADVANCE; + /* If timestamp is enabled then configure NPC to shift 8 bytes */ + if (enable) + val |= FIELD_PREP(NPC_AF_ACTION0_PTR_ADVANCE, + NPC_HW_TSTAMP_OFFSET); + rvu_write64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind), val); + + return 0; +} + static int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf, int type) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 778df331c8ac..b2c6385707c9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -6,7 +6,8 @@ obj-$(CONFIG_OCTEONTX2_PF) += octeontx2_nicpf.o obj-$(CONFIG_OCTEONTX2_VF) += octeontx2_nicvf.o -octeontx2_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o +octeontx2_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ + otx2_ptp.o octeontx2_nicvf-y := otx2_vf.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 5975521a4c86..820fc660de66 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -365,6 +365,95 @@ int otx2_rss_init(struct otx2_nic *pfvf) return 0; } +/* Setup UDP segmentation algorithm in HW */ +static void otx2_setup_udp_segmentation(struct nix_lso_format_cfg *lso, bool v4) +{ + struct nix_lso_format *field; + + field = (struct nix_lso_format *)&lso->fields[0]; + lso->field_mask = GENMASK(18, 0); + + /* IP's Length field */ + field->layer = NIX_TXLAYER_OL3; + /* In ipv4, length field is at offset 2 bytes, for ipv6 it's 4 */ + field->offset = v4 ? 2 : 4; + field->sizem1 = 1; /* i.e 2 bytes */ + field->alg = NIX_LSOALG_ADD_PAYLEN; + field++; + + /* No ID field in IPv6 header */ + if (v4) { + /* Increment IPID */ + field->layer = NIX_TXLAYER_OL3; + field->offset = 4; + field->sizem1 = 1; /* i.e 2 bytes */ + field->alg = NIX_LSOALG_ADD_SEGNUM; + field++; + } + + /* Update length in UDP header */ + field->layer = NIX_TXLAYER_OL4; + field->offset = 4; + field->sizem1 = 1; + field->alg = NIX_LSOALG_ADD_PAYLEN; +} + +/* Setup segmentation algorithms in HW and retrieve algorithm index */ +void otx2_setup_segmentation(struct otx2_nic *pfvf) +{ + struct nix_lso_format_cfg_rsp *rsp; + struct nix_lso_format_cfg *lso; + struct otx2_hw *hw = &pfvf->hw; + int err; + + mutex_lock(&pfvf->mbox.lock); + + /* UDPv4 segmentation */ + lso = otx2_mbox_alloc_msg_nix_lso_format_cfg(&pfvf->mbox); + if (!lso) + goto fail; + + /* Setup UDP/IP header fields that HW should update per segment */ + otx2_setup_udp_segmentation(lso, true); + + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) + goto fail; + + rsp = (struct nix_lso_format_cfg_rsp *) + otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &lso->hdr); + if (IS_ERR(rsp)) + goto fail; + + hw->lso_udpv4_idx = rsp->lso_format_idx; + + /* UDPv6 segmentation */ + lso = otx2_mbox_alloc_msg_nix_lso_format_cfg(&pfvf->mbox); + if (!lso) + goto fail; + + /* Setup UDP/IP header fields that HW should update per segment */ + otx2_setup_udp_segmentation(lso, false); + + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) + goto fail; + + rsp = (struct nix_lso_format_cfg_rsp *) + otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &lso->hdr); + if (IS_ERR(rsp)) + goto fail; + + hw->lso_udpv6_idx = rsp->lso_format_idx; + mutex_unlock(&pfvf->mbox.lock); + return; +fail: + mutex_unlock(&pfvf->mbox.lock); + netdev_info(pfvf->netdev, + "Failed to get LSO index for UDP GSO offload, disabling\n"); + pfvf->netdev->hw_features &= ~NETIF_F_GSO_UDP_L4; +} + void otx2_config_irq_coalescing(struct otx2_nic *pfvf, int qidx) { /* Configure CQE interrupt coalescing parameters @@ -671,6 +760,13 @@ static int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) if (!sq->sg) return -ENOMEM; + if (pfvf->ptp) { + err = qmem_alloc(pfvf->dev, &sq->timestamps, qset->sqe_cnt, + sizeof(*sq->timestamps)); + if (err) + return err; + } + sq->head = 0; sq->sqe_per_sqb = (pfvf->hw.sqb_size / sq->sqe_size) - 1; sq->num_sqbs = (qset->sqe_cnt + sq->sqe_per_sqb) / sq->sqe_per_sqb; @@ -1226,8 +1322,8 @@ int otx2_config_npa(struct otx2_nic *pfvf) if (!hw->pool_cnt) return -EINVAL; - qset->pool = devm_kzalloc(pfvf->dev, sizeof(struct otx2_pool) * - hw->pool_cnt, GFP_KERNEL); + qset->pool = devm_kcalloc(pfvf->dev, hw->pool_cnt, + sizeof(struct otx2_pool), GFP_KERNEL); if (!qset->pool) return -ENOMEM; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 2fa29889522e..ac47762cce9b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -13,6 +13,9 @@ #include <linux/pci.h> #include <linux/iommu.h> +#include <linux/net_tstamp.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/timecounter.h> #include <mbox.h> #include "otx2_reg.h" @@ -174,9 +177,11 @@ struct otx2_hw { u16 rq_skid; u8 cq_time_wait; - /* For TSO segmentation */ + /* Segmentation */ u8 lso_tsov4_idx; u8 lso_tsov6_idx; + u8 lso_udpv4_idx; + u8 lso_udpv6_idx; u8 hw_tso; /* MSI-X */ @@ -209,6 +214,17 @@ struct refill_work { struct otx2_nic *pf; }; +struct otx2_ptp { + struct ptp_clock_info ptp_info; + struct ptp_clock *ptp_clock; + struct otx2_nic *nic; + + struct cyclecounter cycle_counter; + struct timecounter time_counter; +}; + +#define OTX2_HW_TIMESTAMP_LEN 8 + struct otx2_nic { void __iomem *reg_base; struct net_device *netdev; @@ -216,6 +232,8 @@ struct otx2_nic { u16 max_frs; u16 rbsize; /* Receive buffer size */ +#define OTX2_FLAG_RX_TSTAMP_ENABLED BIT_ULL(0) +#define OTX2_FLAG_TX_TSTAMP_ENABLED BIT_ULL(1) #define OTX2_FLAG_INTF_DOWN BIT_ULL(2) #define OTX2_FLAG_RX_PAUSE_ENABLED BIT_ULL(9) #define OTX2_FLAG_TX_PAUSE_ENABLED BIT_ULL(10) @@ -251,6 +269,9 @@ struct otx2_nic { /* Block address of NIX either BLKADDR_NIX0 or BLKADDR_NIX1 */ int nix_blkaddr; + + struct otx2_ptp *ptp; + struct hwtstamp_config tstamp; }; static inline bool is_otx2_lbkvf(struct pci_dev *pdev) @@ -561,6 +582,7 @@ void otx2_tx_timeout(struct net_device *netdev, unsigned int txq); void otx2_get_mac_from_af(struct net_device *netdev); void otx2_config_irq_coalescing(struct otx2_nic *pfvf, int qidx); int otx2_config_pause_frm(struct otx2_nic *pfvf); +void otx2_setup_segmentation(struct otx2_nic *pfvf); /* RVU block related APIs */ int otx2_attach_npa_nix(struct otx2_nic *pfvf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index d59f5a9c7273..0341d9694e8b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -13,8 +13,10 @@ #include <linux/stddef.h> #include <linux/etherdevice.h> #include <linux/log2.h> +#include <linux/net_tstamp.h> #include "otx2_common.h" +#include "otx2_ptp.h" #define DRV_NAME "octeontx2-nicpf" #define DRV_VF_NAME "octeontx2-nicvf" @@ -663,6 +665,31 @@ static u32 otx2_get_link(struct net_device *netdev) return pfvf->linfo.link_up; } +static int otx2_get_ts_info(struct net_device *netdev, + struct ethtool_ts_info *info) +{ + struct otx2_nic *pfvf = netdev_priv(netdev); + + if (!pfvf->ptp) + return ethtool_op_get_ts_info(netdev, info); + + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + info->phc_index = otx2_ptp_clock_index(pfvf); + + info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON); + + info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_ALL); + + return 0; +} + static const struct ethtool_ops otx2_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES, @@ -687,6 +714,7 @@ static const struct ethtool_ops otx2_ethtool_ops = { .set_msglevel = otx2_set_msglevel, .get_pauseparam = otx2_get_pauseparam, .set_pauseparam = otx2_set_pauseparam, + .get_ts_info = otx2_get_ts_info, }; void otx2_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 75a8c407e815..aac2845c1fb1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -21,6 +21,7 @@ #include "otx2_common.h" #include "otx2_txrx.h" #include "otx2_struct.h" +#include "otx2_ptp.h" #define DRV_NAME "octeontx2-nicpf" #define DRV_STRING "Marvell OcteonTX2 NIC Physical Function Driver" @@ -41,6 +42,9 @@ enum { TYPE_PFVF, }; +static int otx2_config_hw_tx_tstamp(struct otx2_nic *pfvf, bool enable); +static int otx2_config_hw_rx_tstamp(struct otx2_nic *pfvf, bool enable); + static int otx2_change_mtu(struct net_device *netdev, int new_mtu) { bool if_up = netif_running(netdev); @@ -1281,7 +1285,8 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) hw->pool_cnt = hw->rqpool_cnt + hw->sqpool_cnt; /* Get the size of receive buffers to allocate */ - pf->rbsize = RCV_FRAG_LEN(pf->netdev->mtu + OTX2_ETH_HLEN); + pf->rbsize = RCV_FRAG_LEN(OTX2_HW_TIMESTAMP_LEN + pf->netdev->mtu + + OTX2_ETH_HLEN); mutex_lock(&mbox->lock); /* NPA init */ @@ -1496,6 +1501,9 @@ int otx2_open(struct net_device *netdev) if (err) goto err_disable_napi; + /* Setup segmentation algorithms, if failed, clear offload capability */ + otx2_setup_segmentation(pf); + /* Initialize RSS */ err = otx2_rss_init(pf); if (err) @@ -1547,6 +1555,16 @@ int otx2_open(struct net_device *netdev) otx2_set_cints_affinity(pf); + /* When reinitializing enable time stamping if it is enabled before */ + if (pf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED) { + pf->flags &= ~OTX2_FLAG_TX_TSTAMP_ENABLED; + otx2_config_hw_tx_tstamp(pf, true); + } + if (pf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED) { + pf->flags &= ~OTX2_FLAG_RX_TSTAMP_ENABLED; + otx2_config_hw_rx_tstamp(pf, true); + } + pf->flags &= ~OTX2_FLAG_INTF_DOWN; /* 'intf_down' may be checked on any cpu */ smp_wmb(); @@ -1738,6 +1756,143 @@ static void otx2_reset_task(struct work_struct *work) rtnl_unlock(); } +static int otx2_config_hw_rx_tstamp(struct otx2_nic *pfvf, bool enable) +{ + struct msg_req *req; + int err; + + if (pfvf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED && enable) + return 0; + + mutex_lock(&pfvf->mbox.lock); + if (enable) + req = otx2_mbox_alloc_msg_cgx_ptp_rx_enable(&pfvf->mbox); + else + req = otx2_mbox_alloc_msg_cgx_ptp_rx_disable(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); + return -ENOMEM; + } + + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) { + mutex_unlock(&pfvf->mbox.lock); + return err; + } + + mutex_unlock(&pfvf->mbox.lock); + if (enable) + pfvf->flags |= OTX2_FLAG_RX_TSTAMP_ENABLED; + else + pfvf->flags &= ~OTX2_FLAG_RX_TSTAMP_ENABLED; + return 0; +} + +static int otx2_config_hw_tx_tstamp(struct otx2_nic *pfvf, bool enable) +{ + struct msg_req *req; + int err; + + if (pfvf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED && enable) + return 0; + + mutex_lock(&pfvf->mbox.lock); + if (enable) + req = otx2_mbox_alloc_msg_nix_lf_ptp_tx_enable(&pfvf->mbox); + else + req = otx2_mbox_alloc_msg_nix_lf_ptp_tx_disable(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); + return -ENOMEM; + } + + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) { + mutex_unlock(&pfvf->mbox.lock); + return err; + } + + mutex_unlock(&pfvf->mbox.lock); + if (enable) + pfvf->flags |= OTX2_FLAG_TX_TSTAMP_ENABLED; + else + pfvf->flags &= ~OTX2_FLAG_TX_TSTAMP_ENABLED; + return 0; +} + +static int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) +{ + struct otx2_nic *pfvf = netdev_priv(netdev); + struct hwtstamp_config config; + + if (!pfvf->ptp) + return -ENODEV; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* reserved for future extensions */ + if (config.flags) + return -EINVAL; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + otx2_config_hw_tx_tstamp(pfvf, false); + break; + case HWTSTAMP_TX_ON: + otx2_config_hw_tx_tstamp(pfvf, true); + break; + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + otx2_config_hw_rx_tstamp(pfvf, false); + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + otx2_config_hw_rx_tstamp(pfvf, true); + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + return -ERANGE; + } + + memcpy(&pfvf->tstamp, &config, sizeof(config)); + + return copy_to_user(ifr->ifr_data, &config, + sizeof(config)) ? -EFAULT : 0; +} + +static int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) +{ + struct otx2_nic *pfvf = netdev_priv(netdev); + struct hwtstamp_config *cfg = &pfvf->tstamp; + + switch (cmd) { + case SIOCSHWTSTAMP: + return otx2_config_hwtstamp(netdev, req); + case SIOCGHWTSTAMP: + return copy_to_user(req->ifr_data, cfg, + sizeof(*cfg)) ? -EFAULT : 0; + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops otx2_netdev_ops = { .ndo_open = otx2_open, .ndo_stop = otx2_stop, @@ -1748,6 +1903,7 @@ static const struct net_device_ops otx2_netdev_ops = { .ndo_set_features = otx2_set_features, .ndo_tx_timeout = otx2_tx_timeout, .ndo_get_stats64 = otx2_get_stats64, + .ndo_do_ioctl = otx2_ioctl, }; static int otx2_wq_init(struct otx2_nic *pf) @@ -1920,6 +2076,9 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Assign default mac address */ otx2_get_mac_from_af(netdev); + /* Don't check for error. Proceed without ptp */ + otx2_ptp_init(pf); + /* NPA's pool is a stack to which SW frees buffer pointers via Aura. * HW allocates buffer pointer from stack and uses it for DMA'ing * ingress packet. In some scenarios HW can free back allocated buffer @@ -1935,7 +2094,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->hw_features = (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXHASH | - NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6); + NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_L4); netdev->features |= netdev->hw_features; netdev->hw_features |= NETIF_F_LOOPBACK | NETIF_F_RXALL; @@ -1952,7 +2112,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) err = register_netdev(netdev); if (err) { dev_err(dev, "Failed to register netdevice\n"); - goto err_detach_rsrc; + goto err_ptp_destroy; } err = otx2_wq_init(pf); @@ -1972,6 +2132,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_unreg_netdev: unregister_netdev(netdev); +err_ptp_destroy: + otx2_ptp_destroy(pf); err_detach_rsrc: otx2_detach_resources(&pf->mbox); err_disable_mbox_intr: @@ -2113,6 +2275,11 @@ static void otx2_remove(struct pci_dev *pdev) pf = netdev_priv(netdev); + if (pf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED) + otx2_config_hw_tx_tstamp(pf, false); + if (pf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED) + otx2_config_hw_rx_tstamp(pf, false); + cancel_work_sync(&pf->reset_task); /* Disable link notifications */ otx2_cgx_config_linkevents(pf, false); @@ -2122,6 +2289,7 @@ static void otx2_remove(struct pci_dev *pdev) if (pf->otx2_wq) destroy_workqueue(pf->otx2_wq); + otx2_ptp_destroy(pf); otx2_detach_resources(&pf->mbox); otx2_disable_mbox_intr(pf); otx2_pfaf_mbox_destroy(pf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c new file mode 100644 index 000000000000..7bcf5246350f --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell OcteonTx2 PTP support for ethernet driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ + +#include "otx2_common.h" +#include "otx2_ptp.h" + +static int otx2_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm) +{ + struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, + ptp_info); + struct ptp_req *req; + int err; + + if (!ptp->nic) + return -ENODEV; + + req = otx2_mbox_alloc_msg_ptp_op(&ptp->nic->mbox); + if (!req) + return -ENOMEM; + + req->op = PTP_OP_ADJFINE; + req->scaled_ppm = scaled_ppm; + + err = otx2_sync_mbox_msg(&ptp->nic->mbox); + if (err) + return err; + + return 0; +} + +static u64 ptp_cc_read(const struct cyclecounter *cc) +{ + struct otx2_ptp *ptp = container_of(cc, struct otx2_ptp, cycle_counter); + struct ptp_req *req; + struct ptp_rsp *rsp; + int err; + + if (!ptp->nic) + return 0; + + req = otx2_mbox_alloc_msg_ptp_op(&ptp->nic->mbox); + if (!req) + return 0; + + req->op = PTP_OP_GET_CLOCK; + + err = otx2_sync_mbox_msg(&ptp->nic->mbox); + if (err) + return 0; + + rsp = (struct ptp_rsp *)otx2_mbox_get_rsp(&ptp->nic->mbox.mbox, 0, + &req->hdr); + if (IS_ERR(rsp)) + return 0; + + return rsp->clk; +} + +static int otx2_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) +{ + struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, + ptp_info); + struct otx2_nic *pfvf = ptp->nic; + + mutex_lock(&pfvf->mbox.lock); + timecounter_adjtime(&ptp->time_counter, delta); + mutex_unlock(&pfvf->mbox.lock); + + return 0; +} + +static int otx2_ptp_gettime(struct ptp_clock_info *ptp_info, + struct timespec64 *ts) +{ + struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, + ptp_info); + struct otx2_nic *pfvf = ptp->nic; + u64 nsec; + + mutex_lock(&pfvf->mbox.lock); + nsec = timecounter_read(&ptp->time_counter); + mutex_unlock(&pfvf->mbox.lock); + + *ts = ns_to_timespec64(nsec); + + return 0; +} + +static int otx2_ptp_settime(struct ptp_clock_info *ptp_info, + const struct timespec64 *ts) +{ + struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, + ptp_info); + struct otx2_nic *pfvf = ptp->nic; + u64 nsec; + + nsec = timespec64_to_ns(ts); + + mutex_lock(&pfvf->mbox.lock); + timecounter_init(&ptp->time_counter, &ptp->cycle_counter, nsec); + mutex_unlock(&pfvf->mbox.lock); + + return 0; +} + +static int otx2_ptp_enable(struct ptp_clock_info *ptp_info, + struct ptp_clock_request *rq, int on) +{ + return -EOPNOTSUPP; +} + +int otx2_ptp_init(struct otx2_nic *pfvf) +{ + struct otx2_ptp *ptp_ptr; + struct cyclecounter *cc; + struct ptp_req *req; + int err; + + mutex_lock(&pfvf->mbox.lock); + /* check if PTP block is available */ + req = otx2_mbox_alloc_msg_ptp_op(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); + return -ENOMEM; + } + + req->op = PTP_OP_GET_CLOCK; + + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) { + mutex_unlock(&pfvf->mbox.lock); + return err; + } + mutex_unlock(&pfvf->mbox.lock); + + ptp_ptr = kzalloc(sizeof(*ptp_ptr), GFP_KERNEL); + if (!ptp_ptr) { + err = -ENOMEM; + goto error; + } + + ptp_ptr->nic = pfvf; + + cc = &ptp_ptr->cycle_counter; + cc->read = ptp_cc_read; + cc->mask = CYCLECOUNTER_MASK(64); + cc->mult = 1; + cc->shift = 0; + + timecounter_init(&ptp_ptr->time_counter, &ptp_ptr->cycle_counter, + ktime_to_ns(ktime_get_real())); + + ptp_ptr->ptp_info = (struct ptp_clock_info) { + .owner = THIS_MODULE, + .name = "OcteonTX2 PTP", + .max_adj = 1000000000ull, + .n_ext_ts = 0, + .n_pins = 0, + .pps = 0, + .adjfine = otx2_ptp_adjfine, + .adjtime = otx2_ptp_adjtime, + .gettime64 = otx2_ptp_gettime, + .settime64 = otx2_ptp_settime, + .enable = otx2_ptp_enable, + }; + + ptp_ptr->ptp_clock = ptp_clock_register(&ptp_ptr->ptp_info, pfvf->dev); + if (IS_ERR_OR_NULL(ptp_ptr->ptp_clock)) { + err = ptp_ptr->ptp_clock ? + PTR_ERR(ptp_ptr->ptp_clock) : -ENODEV; + kfree(ptp_ptr); + goto error; + } + + pfvf->ptp = ptp_ptr; + +error: + return err; +} + +void otx2_ptp_destroy(struct otx2_nic *pfvf) +{ + struct otx2_ptp *ptp = pfvf->ptp; + + if (!ptp) + return; + + ptp_clock_unregister(ptp->ptp_clock); + kfree(ptp); + pfvf->ptp = NULL; +} + +int otx2_ptp_clock_index(struct otx2_nic *pfvf) +{ + if (!pfvf->ptp) + return -ENODEV; + + return ptp_clock_index(pfvf->ptp->ptp_clock); +} + +int otx2_ptp_tstamp2time(struct otx2_nic *pfvf, u64 tstamp, u64 *tsns) +{ + if (!pfvf->ptp) + return -ENODEV; + + *tsns = timecounter_cyc2time(&pfvf->ptp->time_counter, tstamp); + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h new file mode 100644 index 000000000000..706d63a43ae1 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 PTP support for ethernet driver */ + +#ifndef OTX2_PTP_H +#define OTX2_PTP_H + +int otx2_ptp_init(struct otx2_nic *pfvf); +void otx2_ptp_destroy(struct otx2_nic *pfvf); + +int otx2_ptp_clock_index(struct otx2_nic *pfvf); +int otx2_ptp_tstamp2time(struct otx2_nic *pfvf, u64 tstamp, u64 *tsns); + +#endif diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 3a5b34a2a7a6..faaa322265a0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -16,6 +16,7 @@ #include "otx2_common.h" #include "otx2_struct.h" #include "otx2_txrx.h" +#include "otx2_ptp.h" #define CQE_ADDR(CQ, idx) ((CQ)->cqe_base + ((CQ)->cqe_size * (idx))) @@ -81,8 +82,11 @@ static void otx2_snd_pkt_handler(struct otx2_nic *pfvf, int budget, int *tx_pkts, int *tx_bytes) { struct nix_send_comp_s *snd_comp = &cqe->comp; + struct skb_shared_hwtstamps ts; struct sk_buff *skb = NULL; + u64 timestamp, tsns; struct sg_list *sg; + int err; if (unlikely(snd_comp->status) && netif_msg_tx_err(pfvf)) net_err_ratelimited("%s: TX%d: Error in send CQ status:%x\n", @@ -94,6 +98,18 @@ static void otx2_snd_pkt_handler(struct otx2_nic *pfvf, if (unlikely(!skb)) return; + if (skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) { + timestamp = ((u64 *)sq->timestamps->base)[snd_comp->sqe_id]; + if (timestamp != 1) { + err = otx2_ptp_tstamp2time(pfvf, timestamp, &tsns); + if (!err) { + memset(&ts, 0, sizeof(ts)); + ts.hwtstamp = ns_to_ktime(tsns); + skb_tstamp_tx(skb, &ts); + } + } + } + *tx_bytes += skb->len; (*tx_pkts)++; otx2_dma_unmap_skb_frags(pfvf, sg); @@ -101,16 +117,47 @@ static void otx2_snd_pkt_handler(struct otx2_nic *pfvf, sg->skb = (u64)NULL; } +static void otx2_set_rxtstamp(struct otx2_nic *pfvf, + struct sk_buff *skb, void *data) +{ + u64 tsns; + int err; + + if (!(pfvf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED)) + return; + + /* The first 8 bytes is the timestamp */ + err = otx2_ptp_tstamp2time(pfvf, be64_to_cpu(*(__be64 *)data), &tsns); + if (err) + return; + + skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(tsns); +} + static void otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, - u64 iova, int len) + u64 iova, int len, struct nix_rx_parse_s *parse) { struct page *page; + int off = 0; void *va; va = phys_to_virt(otx2_iova_to_phys(pfvf->iommu_domain, iova)); + + if (likely(!skb_shinfo(skb)->nr_frags)) { + /* Check if data starts at some nonzero offset + * from the start of the buffer. For now the + * only possible offset is 8 bytes in the case + * where packet is prepended by a timestamp. + */ + if (parse->laptr) { + otx2_set_rxtstamp(pfvf, skb, va); + off = OTX2_HW_TIMESTAMP_LEN; + } + } + page = virt_to_page(va); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - va - page_address(page), len, pfvf->rbsize); + va - page_address(page) + off, len - off, pfvf->rbsize); otx2_dma_unmap_page(pfvf, iova - OTX2_HEAD_ROOM, pfvf->rbsize, DMA_FROM_DEVICE); @@ -239,7 +286,7 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, if (unlikely(!skb)) return; - otx2_skb_add_frag(pfvf, skb, cqe->sg.seg_addr, cqe->sg.seg_size); + otx2_skb_add_frag(pfvf, skb, cqe->sg.seg_addr, cqe->sg.seg_size, parse); cq->pool_ptrs++; otx2_set_rxhash(pfvf, cqe, skb); @@ -477,15 +524,55 @@ static void otx2_sqe_add_ext(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, */ ip_hdr(skb)->tot_len = htons(ext->lso_sb - skb_network_offset(skb)); - } else { + } else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { ext->lso_format = pfvf->hw.lso_tsov6_idx; + ipv6_hdr(skb)->payload_len = htons(ext->lso_sb - skb_network_offset(skb)); + } else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { + __be16 l3_proto = vlan_get_protocol(skb); + struct udphdr *udph = udp_hdr(skb); + u16 iplen; + + ext->lso_sb = skb_transport_offset(skb) + + sizeof(struct udphdr); + + /* HW adds payload size to length fields in IP and + * UDP headers while segmentation, hence adjust the + * lengths to just header sizes. + */ + iplen = htons(ext->lso_sb - skb_network_offset(skb)); + if (l3_proto == htons(ETH_P_IP)) { + ip_hdr(skb)->tot_len = iplen; + ext->lso_format = pfvf->hw.lso_udpv4_idx; + } else { + ipv6_hdr(skb)->payload_len = iplen; + ext->lso_format = pfvf->hw.lso_udpv6_idx; + } + + udph->len = htons(sizeof(struct udphdr)); } + } else if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + ext->tstmp = 1; } + *offset += sizeof(*ext); } +static void otx2_sqe_add_mem(struct otx2_snd_queue *sq, int *offset, + int alg, u64 iova) +{ + struct nix_sqe_mem_s *mem; + + mem = (struct nix_sqe_mem_s *)(sq->sqe_base + *offset); + mem->subdc = NIX_SUBDC_MEM; + mem->alg = alg; + mem->wmem = 1; /* wait for the memory operation */ + mem->addr = iova; + + *offset += sizeof(*mem); +} + /* Add SQE header subdescriptor structure */ static void otx2_sqe_add_hdr(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, struct nix_sqe_hdr_s *sqe_hdr, @@ -736,6 +823,21 @@ static int otx2_get_sqe_count(struct otx2_nic *pfvf, struct sk_buff *skb) return skb_shinfo(skb)->gso_segs; } +static void otx2_set_txtstamp(struct otx2_nic *pfvf, struct sk_buff *skb, + struct otx2_snd_queue *sq, int *offset) +{ + u64 iova; + + if (!skb_shinfo(skb)->gso_size && + skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + iova = sq->timestamps->iova + (sq->head * sizeof(u64)); + otx2_sqe_add_mem(sq, offset, NIX_SENDMEMALG_E_SETTSTMP, iova); + } else { + skb_tx_timestamp(skb); + } +} + bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, struct sk_buff *skb, u16 qidx) { @@ -789,6 +891,8 @@ bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, return false; } + otx2_set_txtstamp(pfvf, skb, sq, &offset); + sqe_hdr->sizem1 = (offset / 16) - 1; netdev_tx_sent_queue(txq, skb->len); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index da97f2d4416f..73af15685657 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -91,6 +91,7 @@ struct otx2_snd_queue { struct qmem *sqe; struct qmem *tso_hdrs; struct sg_list *sg; + struct qmem *timestamps; struct queue_stats stats; u16 sqb_count; u64 *sqb_ptrs; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 92a3db69a6cd..70e0d4ca6688 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -553,7 +553,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->hw_features = NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXHASH | - NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6; + NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_L4; netdev->features = netdev->hw_features; netdev->gso_max_segs = OTX2_MAX_GSO_SEGS; diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index eb8cf60ecf12..faac94b2d5ff 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1541,10 +1541,8 @@ static int pxa168_eth_remove(struct platform_device *pdev) } if (dev->phydev) phy_disconnect(dev->phydev); - if (pep->clk) { - clk_disable_unprepare(pep->clk); - } + clk_disable_unprepare(pep->clk); mdiobus_unregister(pep->smi_bus); mdiobus_free(pep->smi_bus); unregister_netdev(dev); diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index b792f6306a64..6a930351cb23 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -2448,7 +2448,7 @@ static int skge_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIPHY: data->phy_id = hw->phy_addr; - /* fallthru */ + fallthrough; case SIOCGMIIREG: { u16 val = 0; spin_lock_bh(&hw->phy_lock); diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index cec8124301c7..344864275ed5 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -1376,7 +1376,7 @@ static int sky2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIPHY: data->phy_id = PHY_ADDR_MARV; - /* fallthru */ + fallthrough; case SIOCGMIIREG: { u16 val = 0; @@ -2764,7 +2764,7 @@ static int sky2_status_intr(struct sky2_hw *hw, int to_do, u16 idx) case OP_RXCHKSVLAN: sky2_rx_tag(sky2, length); - /* fall through */ + fallthrough; case OP_RXCHKS: if (likely(dev->features & NETIF_F_RXCSUM)) sky2_rx_checksum(sky2, status); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 0870fe78ea38..6d2d60675ffd 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -228,7 +228,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode, if (!MTK_HAS_CAPS(mac->hw->soc->caps, MTK_GMAC1_TRGMII)) goto err_phy; - /* fall through */ + fallthrough; case PHY_INTERFACE_MODE_RGMII_TXID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_ID: @@ -501,11 +501,11 @@ static void mtk_validate(struct phylink_config *config, case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: phylink_set(mask, 1000baseT_Half); - /* fall through */ + fallthrough; case PHY_INTERFACE_MODE_SGMII: phylink_set(mask, 1000baseT_Full); phylink_set(mask, 1000baseX_Full); - /* fall through */ + fallthrough; case PHY_INTERFACE_MODE_MII: case PHY_INTERFACE_MODE_RMII: case PHY_INTERFACE_MODE_REVMII: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b50c567ef508..99d7737e8ad6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -705,7 +705,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud frags = ring->rx_info + (index << priv->log_rx_info); va = page_address(frags[0].page) + frags[0].page_offset; - prefetchw(va); + net_prefetchw(va); /* * make sure we read the CQE after we read the ownership bit */ diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 258c7a96f269..70cf24ba71e4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3031,6 +3031,17 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port) if (err) return err; + /* Ethernet and IB drivers will normally set the port type, + * but if they are not built set the type now to prevent + * devlink_port_type_warn() from firing. + */ + if (!IS_ENABLED(CONFIG_MLX4_EN) && + dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) + devlink_port_type_eth_set(&info->devlink_port, NULL); + else if (!IS_ENABLED(CONFIG_MLX4_INFINIBAND) && + dev->caps.port_type[port] == MLX4_PORT_TYPE_IB) + devlink_port_type_ib_set(&info->devlink_port, NULL); + info->dev = dev; info->port = port; if (!mlx4_is_slave(dev)) { diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c index d2986f1f2db0..d7444782bfdd 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mr.c +++ b/drivers/net/ethernet/mellanox/mlx4/mr.c @@ -114,7 +114,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order) goto err_out; for (i = 0; i <= buddy->max_order; ++i) { - s = BITS_TO_LONGS(1 << (buddy->max_order - i)); + s = BITS_TO_LONGS(1UL << (buddy->max_order - i)); buddy->bits[i] = kvmalloc_array(s, sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!buddy->bits[i]) goto err_out_free; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 10e6886c96ba..0b3eaa102751 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -24,7 +24,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ en_selftest.o en/port.o en/monitor_stats.o en/health.o \ - en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/umem.o \ + en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \ en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o # diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0cc2080fd847..4f33658da25a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -442,7 +442,7 @@ struct mlx5e_xdpsq { struct mlx5e_cq cq; /* read only */ - struct xdp_umem *umem; + struct xsk_buff_pool *xsk_pool; struct mlx5_wq_cyc wq; struct mlx5e_xdpsq_stats *stats; mlx5e_fp_xmit_xdp_frame_check xmit_xdp_frame_check; @@ -606,7 +606,7 @@ struct mlx5e_rq { struct page_pool *page_pool; /* AF_XDP zero-copy */ - struct xdp_umem *umem; + struct xsk_buff_pool *xsk_pool; struct work_struct recover_work; @@ -729,12 +729,13 @@ struct mlx5e_hv_vhca_stats_agent { #endif struct mlx5e_xsk { - /* UMEMs are stored separately from channels, because we don't want to - * lose them when channels are recreated. The kernel also stores UMEMs, - * but it doesn't distinguish between zero-copy and non-zero-copy UMEMs, - * so rely on our mechanism. + /* XSK buffer pools are stored separately from channels, + * because we don't want to lose them when channels are + * recreated. The kernel also stores buffer pool, but it doesn't + * distinguish between zero-copy and non-zero-copy UMEMs, so + * rely on our mechanism. */ - struct xdp_umem **umems; + struct xsk_buff_pool **pools; u16 refcnt; bool ever_used; }; @@ -893,7 +894,7 @@ struct mlx5e_xsk_param; struct mlx5e_rq_param; int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk, - struct xdp_umem *umem, struct mlx5e_rq *rq); + struct xsk_buff_pool *xsk_pool, struct mlx5e_rq *rq); int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time); void mlx5e_deactivate_rq(struct mlx5e_rq *rq); void mlx5e_close_rq(struct mlx5e_rq *rq); @@ -903,7 +904,7 @@ int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_sq_param *param, struct mlx5e_icosq *sq); void mlx5e_close_icosq(struct mlx5e_icosq *sq); int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, - struct mlx5e_sq_param *param, struct xdp_umem *umem, + struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool, struct mlx5e_xdpsq *sq, bool is_redirect); void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 0e6946fc121f..145592788de5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -201,7 +201,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) pi = mlx5e_xdpsq_get_next_pi(sq, MLX5_SEND_WQE_MAX_WQEBBS); session->wqe = MLX5E_TX_FETCH_WQE(sq, pi); - prefetchw(session->wqe->data); + net_prefetchw(session->wqe->data); session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; session->pkt_count = 0; @@ -322,7 +322,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd, struct mlx5e_xdpsq_stats *stats = sq->stats; - prefetchw(wqe); + net_prefetchw(wqe); if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || sq->hw_mtu < dma_len)) { stats->err++; @@ -445,7 +445,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); if (xsk_frames) - xsk_umem_complete_tx(sq->umem, xsk_frames); + xsk_tx_completed(sq->xsk_pool, xsk_frames); sq->stats->cqes += i; @@ -475,7 +475,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) } if (xsk_frames) - xsk_umem_complete_tx(sq->umem, xsk_frames); + xsk_tx_completed(sq->xsk_pool, xsk_frames); } int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, @@ -563,4 +563,3 @@ void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw) sq->xmit_xdp_frame = is_mpw ? mlx5e_xmit_xdp_frame_mpwqe : mlx5e_xmit_xdp_frame; } - diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c index 331ca2b0f8a4..3503e7711178 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c @@ -1,31 +1,31 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -/* Copyright (c) 2019 Mellanox Technologies. */ +/* Copyright (c) 2019-2020, Mellanox Technologies inc. All rights reserved. */ #include <net/xdp_sock_drv.h> -#include "umem.h" +#include "pool.h" #include "setup.h" #include "en/params.h" -static int mlx5e_xsk_map_umem(struct mlx5e_priv *priv, - struct xdp_umem *umem) +static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv, + struct xsk_buff_pool *pool) { struct device *dev = priv->mdev->device; - return xsk_buff_dma_map(umem, dev, 0); + return xsk_pool_dma_map(pool, dev, 0); } -static void mlx5e_xsk_unmap_umem(struct mlx5e_priv *priv, - struct xdp_umem *umem) +static void mlx5e_xsk_unmap_pool(struct mlx5e_priv *priv, + struct xsk_buff_pool *pool) { - return xsk_buff_dma_unmap(umem, 0); + return xsk_pool_dma_unmap(pool, 0); } -static int mlx5e_xsk_get_umems(struct mlx5e_xsk *xsk) +static int mlx5e_xsk_get_pools(struct mlx5e_xsk *xsk) { - if (!xsk->umems) { - xsk->umems = kcalloc(MLX5E_MAX_NUM_CHANNELS, - sizeof(*xsk->umems), GFP_KERNEL); - if (unlikely(!xsk->umems)) + if (!xsk->pools) { + xsk->pools = kcalloc(MLX5E_MAX_NUM_CHANNELS, + sizeof(*xsk->pools), GFP_KERNEL); + if (unlikely(!xsk->pools)) return -ENOMEM; } @@ -35,68 +35,68 @@ static int mlx5e_xsk_get_umems(struct mlx5e_xsk *xsk) return 0; } -static void mlx5e_xsk_put_umems(struct mlx5e_xsk *xsk) +static void mlx5e_xsk_put_pools(struct mlx5e_xsk *xsk) { if (!--xsk->refcnt) { - kfree(xsk->umems); - xsk->umems = NULL; + kfree(xsk->pools); + xsk->pools = NULL; } } -static int mlx5e_xsk_add_umem(struct mlx5e_xsk *xsk, struct xdp_umem *umem, u16 ix) +static int mlx5e_xsk_add_pool(struct mlx5e_xsk *xsk, struct xsk_buff_pool *pool, u16 ix) { int err; - err = mlx5e_xsk_get_umems(xsk); + err = mlx5e_xsk_get_pools(xsk); if (unlikely(err)) return err; - xsk->umems[ix] = umem; + xsk->pools[ix] = pool; return 0; } -static void mlx5e_xsk_remove_umem(struct mlx5e_xsk *xsk, u16 ix) +static void mlx5e_xsk_remove_pool(struct mlx5e_xsk *xsk, u16 ix) { - xsk->umems[ix] = NULL; + xsk->pools[ix] = NULL; - mlx5e_xsk_put_umems(xsk); + mlx5e_xsk_put_pools(xsk); } -static bool mlx5e_xsk_is_umem_sane(struct xdp_umem *umem) +static bool mlx5e_xsk_is_pool_sane(struct xsk_buff_pool *pool) { - return xsk_umem_get_headroom(umem) <= 0xffff && - xsk_umem_get_chunk_size(umem) <= 0xffff; + return xsk_pool_get_headroom(pool) <= 0xffff && + xsk_pool_get_chunk_size(pool) <= 0xffff; } -void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk) +void mlx5e_build_xsk_param(struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk) { - xsk->headroom = xsk_umem_get_headroom(umem); - xsk->chunk_size = xsk_umem_get_chunk_size(umem); + xsk->headroom = xsk_pool_get_headroom(pool); + xsk->chunk_size = xsk_pool_get_chunk_size(pool); } static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, - struct xdp_umem *umem, u16 ix) + struct xsk_buff_pool *pool, u16 ix) { struct mlx5e_params *params = &priv->channels.params; struct mlx5e_xsk_param xsk; struct mlx5e_channel *c; int err; - if (unlikely(mlx5e_xsk_get_umem(&priv->channels.params, &priv->xsk, ix))) + if (unlikely(mlx5e_xsk_get_pool(&priv->channels.params, &priv->xsk, ix))) return -EBUSY; - if (unlikely(!mlx5e_xsk_is_umem_sane(umem))) + if (unlikely(!mlx5e_xsk_is_pool_sane(pool))) return -EINVAL; - err = mlx5e_xsk_map_umem(priv, umem); + err = mlx5e_xsk_map_pool(priv, pool); if (unlikely(err)) return err; - err = mlx5e_xsk_add_umem(&priv->xsk, umem, ix); + err = mlx5e_xsk_add_pool(&priv->xsk, pool, ix); if (unlikely(err)) - goto err_unmap_umem; + goto err_unmap_pool; - mlx5e_build_xsk_param(umem, &xsk); + mlx5e_build_xsk_param(pool, &xsk); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { /* XSK objects will be created on open. */ @@ -112,9 +112,9 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, c = priv->channels.c[ix]; - err = mlx5e_open_xsk(priv, params, &xsk, umem, c); + err = mlx5e_open_xsk(priv, params, &xsk, pool, c); if (unlikely(err)) - goto err_remove_umem; + goto err_remove_pool; mlx5e_activate_xsk(c); @@ -132,11 +132,11 @@ err_deactivate: mlx5e_deactivate_xsk(c); mlx5e_close_xsk(c); -err_remove_umem: - mlx5e_xsk_remove_umem(&priv->xsk, ix); +err_remove_pool: + mlx5e_xsk_remove_pool(&priv->xsk, ix); -err_unmap_umem: - mlx5e_xsk_unmap_umem(priv, umem); +err_unmap_pool: + mlx5e_xsk_unmap_pool(priv, pool); return err; @@ -146,7 +146,7 @@ validate_closed: */ if (!mlx5e_validate_xsk_param(params, &xsk, priv->mdev)) { err = -EINVAL; - goto err_remove_umem; + goto err_remove_pool; } return 0; @@ -154,45 +154,45 @@ validate_closed: static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix) { - struct xdp_umem *umem = mlx5e_xsk_get_umem(&priv->channels.params, + struct xsk_buff_pool *pool = mlx5e_xsk_get_pool(&priv->channels.params, &priv->xsk, ix); struct mlx5e_channel *c; - if (unlikely(!umem)) + if (unlikely(!pool)) return -EINVAL; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) - goto remove_umem; + goto remove_pool; /* XSK RQ and SQ are only created if XDP program is set. */ if (!priv->channels.params.xdp_prog) - goto remove_umem; + goto remove_pool; c = priv->channels.c[ix]; mlx5e_xsk_redirect_rqt_to_drop(priv, ix); mlx5e_deactivate_xsk(c); mlx5e_close_xsk(c); -remove_umem: - mlx5e_xsk_remove_umem(&priv->xsk, ix); - mlx5e_xsk_unmap_umem(priv, umem); +remove_pool: + mlx5e_xsk_remove_pool(&priv->xsk, ix); + mlx5e_xsk_unmap_pool(priv, pool); return 0; } -static int mlx5e_xsk_enable_umem(struct mlx5e_priv *priv, struct xdp_umem *umem, +static int mlx5e_xsk_enable_pool(struct mlx5e_priv *priv, struct xsk_buff_pool *pool, u16 ix) { int err; mutex_lock(&priv->state_lock); - err = mlx5e_xsk_enable_locked(priv, umem, ix); + err = mlx5e_xsk_enable_locked(priv, pool, ix); mutex_unlock(&priv->state_lock); return err; } -static int mlx5e_xsk_disable_umem(struct mlx5e_priv *priv, u16 ix) +static int mlx5e_xsk_disable_pool(struct mlx5e_priv *priv, u16 ix) { int err; @@ -203,7 +203,7 @@ static int mlx5e_xsk_disable_umem(struct mlx5e_priv *priv, u16 ix) return err; } -int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid) +int mlx5e_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid) { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_params *params = &priv->channels.params; @@ -212,6 +212,6 @@ int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid) if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix))) return -EINVAL; - return umem ? mlx5e_xsk_enable_umem(priv, umem, ix) : - mlx5e_xsk_disable_umem(priv, ix); + return pool ? mlx5e_xsk_enable_pool(priv, pool, ix) : + mlx5e_xsk_disable_pool(priv, ix); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h new file mode 100644 index 000000000000..dca0010a0866 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019-2020, Mellanox Technologies inc. All rights reserved. */ + +#ifndef __MLX5_EN_XSK_POOL_H__ +#define __MLX5_EN_XSK_POOL_H__ + +#include "en.h" + +static inline struct xsk_buff_pool *mlx5e_xsk_get_pool(struct mlx5e_params *params, + struct mlx5e_xsk *xsk, u16 ix) +{ + if (!xsk || !xsk->pools) + return NULL; + + if (unlikely(ix >= params->num_channels)) + return NULL; + + return xsk->pools[ix]; +} + +struct mlx5e_xsk_param; +void mlx5e_build_xsk_param(struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk); + +/* .ndo_bpf callback. */ +int mlx5e_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid); + +#endif /* __MLX5_EN_XSK_POOL_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index a33a1f762c70..bb6669d2a916 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -48,8 +48,8 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, xdp->data_end = xdp->data + cqe_bcnt32; xdp_set_data_meta_invalid(xdp); - xsk_buff_dma_sync_for_cpu(xdp); - prefetch(xdp->data); + xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool); + net_prefetch(xdp->data); rcu_read_lock(); consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp); @@ -99,8 +99,8 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, xdp->data_end = xdp->data + cqe_bcnt; xdp_set_data_meta_invalid(xdp); - xsk_buff_dma_sync_for_cpu(xdp); - prefetch(xdp->data); + xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool); + net_prefetch(xdp->data); if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) { rq->stats->wqe_err++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h index d147b2f13b54..7f88ccf67fdd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h @@ -19,10 +19,10 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); -static inline int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, +static inline int mlx5e_xsk_page_alloc_pool(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info) { - dma_info->xsk = xsk_buff_alloc(rq->umem); + dma_info->xsk = xsk_buff_alloc(rq->xsk_pool); if (!dma_info->xsk) return -ENOMEM; @@ -38,13 +38,13 @@ static inline int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err) { - if (!xsk_umem_uses_need_wakeup(rq->umem)) + if (!xsk_uses_need_wakeup(rq->xsk_pool)) return alloc_err; if (unlikely(alloc_err)) - xsk_set_rx_need_wakeup(rq->umem); + xsk_set_rx_need_wakeup(rq->xsk_pool); else - xsk_clear_rx_need_wakeup(rq->umem); + xsk_clear_rx_need_wakeup(rq->xsk_pool); return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index dd9df519d383..662a1dafeaad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -45,7 +45,7 @@ static void mlx5e_build_xsk_cparam(struct mlx5e_priv *priv, } int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, - struct mlx5e_xsk_param *xsk, struct xdp_umem *umem, + struct mlx5e_xsk_param *xsk, struct xsk_buff_pool *pool, struct mlx5e_channel *c) { struct mlx5e_channel_param *cparam; @@ -64,7 +64,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, if (unlikely(err)) goto err_free_cparam; - err = mlx5e_open_rq(c, params, &cparam->rq, xsk, umem, &c->xskrq); + err = mlx5e_open_rq(c, params, &cparam->rq, xsk, pool, &c->xskrq); if (unlikely(err)) goto err_close_rx_cq; @@ -72,13 +72,13 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, if (unlikely(err)) goto err_close_rq; - /* Create a separate SQ, so that when the UMEM is disabled, we could + /* Create a separate SQ, so that when the buff pool is disabled, we could * close this SQ safely and stop receiving CQEs. In other case, e.g., if - * the XDPSQ was used instead, we might run into trouble when the UMEM + * the XDPSQ was used instead, we might run into trouble when the buff pool * is disabled and then reenabled, but the SQ continues receiving CQEs - * from the old UMEM. + * from the old buff pool. */ - err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, umem, &c->xsksq, true); + err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, pool, &c->xsksq, true); if (unlikely(err)) goto err_close_tx_cq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h index 0dd11b81c046..ca20f1ff5e39 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h @@ -12,7 +12,7 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5_core_dev *mdev); int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, - struct mlx5e_xsk_param *xsk, struct xdp_umem *umem, + struct mlx5e_xsk_param *xsk, struct xsk_buff_pool *pool, struct mlx5e_channel *c); void mlx5e_close_xsk(struct mlx5e_channel *c); void mlx5e_activate_xsk(struct mlx5e_channel *c); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 4d892f6cecb3..aa91cbdfe969 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -2,7 +2,7 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #include "tx.h" -#include "umem.h" +#include "pool.h" #include "en/xdp.h" #include "en/params.h" #include <net/xdp_sock_drv.h> @@ -66,7 +66,7 @@ static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq, bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) { - struct xdp_umem *umem = sq->umem; + struct xsk_buff_pool *pool = sq->xsk_pool; struct mlx5e_xdp_info xdpi; struct mlx5e_xdp_xmit_data xdptxd; bool work_done = true; @@ -87,7 +87,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) break; } - if (!xsk_umem_consume_tx(umem, &desc)) { + if (!xsk_tx_peek_desc(pool, &desc)) { /* TX will get stuck until something wakes it up by * triggering NAPI. Currently it's expected that the * application calls sendto() if there are consumed, but @@ -96,11 +96,11 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) break; } - xdptxd.dma_addr = xsk_buff_raw_get_dma(umem, desc.addr); - xdptxd.data = xsk_buff_raw_get_data(umem, desc.addr); + xdptxd.dma_addr = xsk_buff_raw_get_dma(pool, desc.addr); + xdptxd.data = xsk_buff_raw_get_data(pool, desc.addr); xdptxd.len = desc.len; - xsk_buff_raw_dma_sync_for_device(umem, xdptxd.dma_addr, xdptxd.len); + xsk_buff_raw_dma_sync_for_device(pool, xdptxd.dma_addr, xdptxd.len); ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe, mlx5e_xmit_xdp_frame, sq, &xdptxd, &xdpi, check_result); @@ -119,7 +119,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) mlx5e_xdp_mpwqe_complete(sq); mlx5e_xmit_xdp_doorbell(sq); - xsk_umem_consume_tx_done(umem); + xsk_tx_release(pool); } return !(budget && work_done); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h index 39fa0a705856..a05085035f23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h @@ -15,13 +15,13 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget); static inline void mlx5e_xsk_update_tx_wakeup(struct mlx5e_xdpsq *sq) { - if (!xsk_umem_uses_need_wakeup(sq->umem)) + if (!xsk_uses_need_wakeup(sq->xsk_pool)) return; if (sq->pc != sq->cc) - xsk_clear_tx_need_wakeup(sq->umem); + xsk_clear_tx_need_wakeup(sq->xsk_pool); else - xsk_set_tx_need_wakeup(sq->umem); + xsk_set_tx_need_wakeup(sq->xsk_pool); } #endif /* __MLX5_EN_XSK_TX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h deleted file mode 100644 index bada94973586..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ -/* Copyright (c) 2019 Mellanox Technologies. */ - -#ifndef __MLX5_EN_XSK_UMEM_H__ -#define __MLX5_EN_XSK_UMEM_H__ - -#include "en.h" - -static inline struct xdp_umem *mlx5e_xsk_get_umem(struct mlx5e_params *params, - struct mlx5e_xsk *xsk, u16 ix) -{ - if (!xsk || !xsk->umems) - return NULL; - - if (unlikely(ix >= params->num_channels)) - return NULL; - - return xsk->umems[ix]; -} - -struct mlx5e_xsk_param; -void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk); - -/* .ndo_bpf callback. */ -int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid); - -int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries); - -#endif /* __MLX5_EN_XSK_UMEM_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 08270987c506..5cb1e4839eb7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -32,7 +32,7 @@ #include "en.h" #include "en/port.h" -#include "en/xsk/umem.h" +#include "en/xsk/pool.h" #include "lib/clock.h" void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 83c9b2bbc4af..b416a8ee2eed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -33,7 +33,7 @@ #include <linux/mlx5/fs.h> #include "en.h" #include "en/params.h" -#include "en/xsk/umem.h" +#include "en/xsk/pool.h" struct mlx5e_ethtool_rule { struct list_head list; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index aebcf73f8546..26834625556d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -57,7 +57,7 @@ #include "en/monitor_stats.h" #include "en/health.h" #include "en/params.h" -#include "en/xsk/umem.h" +#include "en/xsk/pool.h" #include "en/xsk/setup.h" #include "en/xsk/rx.h" #include "en/xsk/tx.h" @@ -363,7 +363,7 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work) static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - struct xdp_umem *umem, + struct xsk_buff_pool *xsk_pool, struct mlx5e_rq_param *rqp, struct mlx5e_rq *rq) { @@ -389,9 +389,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->mdev = mdev; rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); rq->xdpsq = &c->rq_xdpsq; - rq->umem = umem; + rq->xsk_pool = xsk_pool; - if (rq->umem) + if (rq->xsk_pool) rq->stats = &c->priv->channel_stats[c->ix].xskrq; else rq->stats = &c->priv->channel_stats[c->ix].rq; @@ -477,7 +477,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (xsk) { err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); - xsk_buff_set_rxq_info(rq->umem, &rq->xdp_rxq); + xsk_pool_set_rxq_info(rq->xsk_pool, &rq->xdp_rxq); } else { /* Create a page_pool and register it with rxq */ pp_params.order = 0; @@ -816,11 +816,11 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq) int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk, - struct xdp_umem *umem, struct mlx5e_rq *rq) + struct xsk_buff_pool *xsk_pool, struct mlx5e_rq *rq) { int err; - err = mlx5e_alloc_rq(c, params, xsk, umem, param, rq); + err = mlx5e_alloc_rq(c, params, xsk, xsk_pool, param, rq); if (err) return err; @@ -925,7 +925,7 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa) static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, - struct xdp_umem *umem, + struct xsk_buff_pool *xsk_pool, struct mlx5e_sq_param *param, struct mlx5e_xdpsq *sq, bool is_redirect) @@ -941,9 +941,9 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); - sq->umem = umem; + sq->xsk_pool = xsk_pool; - sq->stats = sq->umem ? + sq->stats = sq->xsk_pool ? &c->priv->channel_stats[c->ix].xsksq : is_redirect ? &c->priv->channel_stats[c->ix].xdpsq : @@ -1408,13 +1408,13 @@ void mlx5e_close_icosq(struct mlx5e_icosq *sq) } int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, - struct mlx5e_sq_param *param, struct xdp_umem *umem, + struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool, struct mlx5e_xdpsq *sq, bool is_redirect) { struct mlx5e_create_sq_param csp = {}; int err; - err = mlx5e_alloc_xdpsq(c, params, umem, param, sq, is_redirect); + err = mlx5e_alloc_xdpsq(c, params, xsk_pool, param, sq, is_redirect); if (err) return err; @@ -1907,7 +1907,7 @@ static u8 mlx5e_enumerate_lag_port(struct mlx5_core_dev *mdev, int ix) static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_params *params, struct mlx5e_channel_param *cparam, - struct xdp_umem *umem, + struct xsk_buff_pool *xsk_pool, struct mlx5e_channel **cp) { int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix)); @@ -1946,9 +1946,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, if (unlikely(err)) goto err_napi_del; - if (umem) { - mlx5e_build_xsk_param(umem, &xsk); - err = mlx5e_open_xsk(priv, params, &xsk, umem, c); + if (xsk_pool) { + mlx5e_build_xsk_param(xsk_pool, &xsk); + err = mlx5e_open_xsk(priv, params, &xsk, xsk_pool, c); if (unlikely(err)) goto err_close_queues; } @@ -2309,12 +2309,12 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, mlx5e_build_channel_param(priv, &chs->params, cparam); for (i = 0; i < chs->num; i++) { - struct xdp_umem *umem = NULL; + struct xsk_buff_pool *xsk_pool = NULL; if (chs->params.xdp_prog) - umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, i); + xsk_pool = mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, i); - err = mlx5e_open_channel(priv, i, &chs->params, cparam, umem, &chs->c[i]); + err = mlx5e_open_channel(priv, i, &chs->params, cparam, xsk_pool, &chs->c[i]); if (err) goto err_close_channels; } @@ -3892,13 +3892,14 @@ static bool mlx5e_xsk_validate_mtu(struct net_device *netdev, u16 ix; for (ix = 0; ix < chs->params.num_channels; ix++) { - struct xdp_umem *umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, ix); + struct xsk_buff_pool *xsk_pool = + mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, ix); struct mlx5e_xsk_param xsk; - if (!umem) + if (!xsk_pool) continue; - mlx5e_build_xsk_param(umem, &xsk); + mlx5e_build_xsk_param(xsk_pool, &xsk); if (!mlx5e_validate_xsk_param(new_params, &xsk, mdev)) { u32 hr = mlx5e_get_linear_rq_headroom(new_params, &xsk); @@ -4423,8 +4424,8 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: return mlx5e_xdp_set(dev, xdp->prog); - case XDP_SETUP_XSK_UMEM: - return mlx5e_xsk_setup_umem(dev, xdp->xsk.umem, + case XDP_SETUP_XSK_POOL: + return mlx5e_xsk_setup_pool(dev, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index e13e5d1b3eae..135ee26881c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1210,16 +1210,22 @@ is_devlink_port_supported(const struct mlx5_core_dev *dev, static int register_devlink_port(struct mlx5_core_dev *dev, struct mlx5e_rep_priv *rpriv) { + struct mlx5_esw_offload *offloads = &dev->priv.eswitch->offloads; struct devlink *devlink = priv_to_devlink(dev); struct mlx5_eswitch_rep *rep = rpriv->rep; struct devlink_port_attrs attrs = {}; struct netdev_phys_item_id ppid = {}; unsigned int dl_port_index = 0; + u32 controller_num = 0; + bool external; u16 pfnum; if (!is_devlink_port_supported(dev, rpriv)) return 0; + external = mlx5_core_is_ecpf_esw_manager(dev); + if (external) + controller_num = offloads->host_number + 1; mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid); dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, rep->vport); pfnum = PCI_FUNC(dev->pdev->devfn); @@ -1232,12 +1238,13 @@ static int register_devlink_port(struct mlx5_core_dev *dev, } else if (rep->vport == MLX5_VPORT_PF) { memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len); rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len; - devlink_port_attrs_pci_pf_set(&rpriv->dl_port, pfnum); + devlink_port_attrs_pci_pf_set(&rpriv->dl_port, controller_num, + pfnum, external); } else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) { memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len); rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len; - devlink_port_attrs_pci_vf_set(&rpriv->dl_port, - pfnum, rep->vport - 1); + devlink_port_attrs_pci_vf_set(&rpriv->dl_port, controller_num, + pfnum, rep->vport - 1, external); } return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 65828af120b7..7aab69e991a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -30,7 +30,6 @@ * SOFTWARE. */ -#include <linux/prefetch.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/tcp.h> @@ -281,8 +280,8 @@ static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq, static inline int mlx5e_page_alloc(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info) { - if (rq->umem) - return mlx5e_xsk_page_alloc_umem(rq, dma_info); + if (rq->xsk_pool) + return mlx5e_xsk_page_alloc_pool(rq, dma_info); else return mlx5e_page_alloc_pool(rq, dma_info); } @@ -313,7 +312,7 @@ static inline void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, bool recycle) { - if (rq->umem) + if (rq->xsk_pool) /* The `recycle` parameter is ignored, and the page is always * put into the Reuse Ring, because there is no way to return * the page to the userspace when the interface goes down. @@ -400,14 +399,14 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk) int err; int i; - if (rq->umem) { + if (rq->xsk_pool) { int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags; /* Check in advance that we have enough frames, instead of * allocating one-by-one, failing and moving frames to the * Reuse Ring. */ - if (unlikely(!xsk_buff_can_alloc(rq->umem, pages_desired))) + if (unlikely(!xsk_buff_can_alloc(rq->xsk_pool, pages_desired))) return -ENOMEM; } @@ -505,8 +504,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) /* Check in advance that we have enough frames, instead of allocating * one-by-one, failing and moving frames to the Reuse Ring. */ - if (rq->umem && - unlikely(!xsk_buff_can_alloc(rq->umem, MLX5_MPWRQ_PAGES_PER_WQE))) { + if (rq->xsk_pool && + unlikely(!xsk_buff_can_alloc(rq->xsk_pool, MLX5_MPWRQ_PAGES_PER_WQE))) { err = -ENOMEM; goto err; } @@ -754,7 +753,7 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) * the driver when it refills the Fill Ring. * 2. Otherwise, busy poll by rescheduling the NAPI poll. */ - if (unlikely(alloc_err == -ENOMEM && rq->umem)) + if (unlikely(alloc_err == -ENOMEM && rq->xsk_pool)) return true; return false; @@ -1141,8 +1140,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, dma_sync_single_range_for_cpu(rq->pdev, di->addr, wi->offset, frag_size, DMA_FROM_DEVICE); - prefetchw(va); /* xdp_frame data area */ - prefetch(data); + net_prefetchw(va); /* xdp_frame data area */ + net_prefetch(data); rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp); @@ -1184,7 +1183,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, return NULL; } - prefetchw(skb->data); + net_prefetchw(skb->data); while (byte_cnt) { u16 frag_consumed_bytes = @@ -1399,7 +1398,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w return NULL; } - prefetchw(skb->data); + net_prefetchw(skb->data); if (unlikely(frag_offset >= PAGE_SIZE)) { di++; @@ -1452,8 +1451,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, dma_sync_single_range_for_cpu(rq->pdev, di->addr, head_offset, frag_size, DMA_FROM_DEVICE); - prefetchw(va); /* xdp_frame data area */ - prefetch(data); + net_prefetchw(va); /* xdp_frame data area */ + net_prefetch(data); rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 46790216ce86..ce8ab1f01876 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -30,7 +30,6 @@ * SOFTWARE. */ -#include <linux/prefetch.h> #include <linux/ip.h> #include <linux/udp.h> #include <net/udp.h> @@ -115,7 +114,7 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv) return NULL; } - prefetchw(skb->data); + net_prefetchw(skb->data); skb_reserve(skb, NET_IP_ALIGN); /* Reserve for ethernet and IP header */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 867d8120b8a5..7455fbd21a0a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -217,6 +217,7 @@ struct mlx5_esw_offload { atomic64_t num_flows; enum devlink_eswitch_encap_mode encap; struct ida vport_metadata_ida; + unsigned int host_number; /* ECPF supports one external host */ }; /* E-Switch MC FDB table hash node */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d2516922d867..b381cbca5852 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2110,6 +2110,24 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type return NOTIFY_OK; } +static int mlx5_esw_host_number_init(struct mlx5_eswitch *esw) +{ + const u32 *query_host_out; + + if (!mlx5_core_is_ecpf_esw_manager(esw->dev)) + return 0; + + query_host_out = mlx5_esw_query_functions(esw->dev); + if (IS_ERR(query_host_out)) + return PTR_ERR(query_host_out); + + /* Mark non local controller with non zero controller number. */ + esw->offloads.host_number = MLX5_GET(query_esw_functions_out, query_host_out, + host_params_context.host_number); + kvfree(query_host_out); + return 0; +} + int esw_offloads_enable(struct mlx5_eswitch *esw) { struct mlx5_vport *vport; @@ -2124,6 +2142,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) mutex_init(&esw->offloads.termtbl_mutex); mlx5_rdma_enable_roce(esw->dev); + err = mlx5_esw_host_number_init(esw); + if (err) + goto err_vport_metadata; + err = esw_set_passing_vport_metadata(esw, true); if (err) goto err_vport_metadata; diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c index 7a04c626a2aa..bcd166911d44 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c @@ -72,7 +72,7 @@ static int mlxfw_fsm_state_err(struct mlxfw_dev *mlxfw_dev, case MLXFW_FSM_STATE_ERR_BLOCKED_PENDING_RESET: MLXFW_ERR_MSG(mlxfw_dev, extack, "pending reset", err); break; - case MLXFW_FSM_STATE_ERR_OK: /* fall through */ + case MLXFW_FSM_STATE_ERR_OK: case MLXFW_FSM_STATE_ERR_MAX: MLXFW_ERR_MSG(mlxfw_dev, extack, "unknown error", err); break; @@ -155,7 +155,7 @@ mlxfw_fsm_reactivate_err(struct mlxfw_dev *mlxfw_dev, case MLXFW_FSM_REACTIVATE_STATUS_FW_ALREADY_ACTIVATED: MLXFW_REACT_ERR("fw already activated", err); break; - case MLXFW_FSM_REACTIVATE_STATUS_OK: /* fall through */ + case MLXFW_FSM_REACTIVATE_STATUS_OK: case MLXFW_FSM_REACTIVATE_STATUS_MAX: MLXFW_REACT_ERR("unexpected error", err); break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 08d101138fbe..ec45a03140d7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -2289,21 +2289,21 @@ int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module) /* Here we need to get the module width according to the module type. */ switch (module_type) { - case MLXSW_REG_PMTM_MODULE_TYPE_C2C8X: /* fall through */ - case MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_C2C8X: + case MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD: case MLXSW_REG_PMTM_MODULE_TYPE_OSFP: return 8; - case MLXSW_REG_PMTM_MODULE_TYPE_C2C4X: /* fall through */ - case MLXSW_REG_PMTM_MODULE_TYPE_BP_4X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_C2C4X: + case MLXSW_REG_PMTM_MODULE_TYPE_BP_4X: case MLXSW_REG_PMTM_MODULE_TYPE_QSFP: return 4; - case MLXSW_REG_PMTM_MODULE_TYPE_C2C2X: /* fall through */ - case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: /* fall through */ - case MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_C2C2X: + case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: + case MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD: case MLXSW_REG_PMTM_MODULE_TYPE_DSFP: return 2; - case MLXSW_REG_PMTM_MODULE_TYPE_C2C1X: /* fall through */ - case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_C2C1X: + case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: case MLXSW_REG_PMTM_MODULE_TYPE_SFP: return 1; default: diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index 44fa02cbb683..056eeb85be60 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -30,8 +30,8 @@ static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP: *qsfp = false; break; - case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: /* fall-through */ - case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: *qsfp = true; break; @@ -205,7 +205,7 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, modinfo->type = ETH_MODULE_SFF_8436; modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; break; - case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: if (module_id == MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28 || module_rev_id >= diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index 3fe878d7c94c..252e91072c5a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -12,8 +12,17 @@ #include "core.h" #include "core_env.h" -#define MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT 127 -#define MLXSW_HWMON_ATTR_COUNT (MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT * 4 + \ +#define MLXSW_HWMON_SENSORS_MAX_COUNT 64 +#define MLXSW_HWMON_MODULES_MAX_COUNT 64 +#define MLXSW_HWMON_GEARBOXES_MAX_COUNT 32 + +#define MLXSW_HWMON_ATTR_PER_SENSOR 3 +#define MLXSW_HWMON_ATTR_PER_MODULE 7 +#define MLXSW_HWMON_ATTR_PER_GEARBOX 4 + +#define MLXSW_HWMON_ATTR_COUNT (MLXSW_HWMON_SENSORS_MAX_COUNT * MLXSW_HWMON_ATTR_PER_SENSOR + \ + MLXSW_HWMON_MODULES_MAX_COUNT * MLXSW_HWMON_ATTR_PER_MODULE + \ + MLXSW_HWMON_GEARBOXES_MAX_COUNT * MLXSW_HWMON_ATTR_PER_GEARBOX + \ MLXSW_MFCR_TACHOS_MAX + MLXSW_MFCR_PWMS_MAX) struct mlxsw_hwmon_attr { @@ -205,25 +214,39 @@ static ssize_t mlxsw_hwmon_pwm_store(struct device *dev, return len; } -static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev, - struct device_attribute *attr, - char *buf) +static int mlxsw_hwmon_module_temp_get(struct device *dev, + struct device_attribute *attr, + int *p_temp) { struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = container_of(attr, struct mlxsw_hwmon_attr, dev_attr); struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; char mtmp_pl[MLXSW_REG_MTMP_LEN]; u8 module; - int temp; int err; module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; mlxsw_reg_mtmp_pack(mtmp_pl, MLXSW_REG_MTMP_MODULE_INDEX_MIN + module, false, false); err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl); + if (err) { + dev_err(dev, "Failed to query module temperature\n"); + return err; + } + mlxsw_reg_mtmp_unpack(mtmp_pl, p_temp, NULL, NULL); + + return 0; +} + +static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int err, temp; + + err = mlxsw_hwmon_module_temp_get(dev, attr, &temp); if (err) return err; - mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL); return sprintf(buf, "%d\n", temp); } @@ -259,8 +282,8 @@ static ssize_t mlxsw_hwmon_module_temp_fault_show(struct device *dev, */ fault = 1; break; - case MLXSW_REG_MTBR_NO_CONN: /* fall-through */ - case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */ + case MLXSW_REG_MTBR_NO_CONN: + case MLXSW_REG_MTBR_NO_TEMP_SENS: case MLXSW_REG_MTBR_INDEX_NA: default: fault = 0; @@ -270,48 +293,72 @@ static ssize_t mlxsw_hwmon_module_temp_fault_show(struct device *dev, return sprintf(buf, "%u\n", fault); } -static ssize_t -mlxsw_hwmon_module_temp_critical_show(struct device *dev, - struct device_attribute *attr, char *buf) +static int mlxsw_hwmon_module_temp_critical_get(struct device *dev, + struct device_attribute *attr, + int *p_temp) { struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = container_of(attr, struct mlxsw_hwmon_attr, dev_attr); struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; - int temp; u8 module; int err; module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module, - SFP_TEMP_HIGH_WARN, &temp); + SFP_TEMP_HIGH_WARN, p_temp); if (err) { dev_err(dev, "Failed to query module temperature thresholds\n"); return err; } - return sprintf(buf, "%u\n", temp); + return 0; } static ssize_t -mlxsw_hwmon_module_temp_emergency_show(struct device *dev, - struct device_attribute *attr, - char *buf) +mlxsw_hwmon_module_temp_critical_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int err, temp; + + err = mlxsw_hwmon_module_temp_critical_get(dev, attr, &temp); + if (err) + return err; + + return sprintf(buf, "%u\n", temp); +} + +static int mlxsw_hwmon_module_temp_emergency_get(struct device *dev, + struct device_attribute *attr, + int *p_temp) { struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = container_of(attr, struct mlxsw_hwmon_attr, dev_attr); struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; u8 module; - int temp; int err; module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module, - SFP_TEMP_HIGH_ALARM, &temp); + SFP_TEMP_HIGH_ALARM, p_temp); if (err) { dev_err(dev, "Failed to query module temperature thresholds\n"); return err; } + return 0; +} + +static ssize_t +mlxsw_hwmon_module_temp_emergency_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int err, temp; + + err = mlxsw_hwmon_module_temp_emergency_get(dev, attr, &temp); + if (err) + return err; + return sprintf(buf, "%u\n", temp); } @@ -341,6 +388,53 @@ mlxsw_hwmon_gbox_temp_label_show(struct device *dev, return sprintf(buf, "gearbox %03u\n", index); } +static ssize_t mlxsw_hwmon_temp_critical_alarm_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int err, temp, emergency_temp, critic_temp; + + err = mlxsw_hwmon_module_temp_get(dev, attr, &temp); + if (err) + return err; + + if (temp <= 0) + return sprintf(buf, "%d\n", false); + + err = mlxsw_hwmon_module_temp_emergency_get(dev, attr, &emergency_temp); + if (err) + return err; + + if (temp >= emergency_temp) + return sprintf(buf, "%d\n", false); + + err = mlxsw_hwmon_module_temp_critical_get(dev, attr, &critic_temp); + if (err) + return err; + + return sprintf(buf, "%d\n", temp >= critic_temp); +} + +static ssize_t mlxsw_hwmon_temp_emergency_alarm_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int err, temp, emergency_temp; + + err = mlxsw_hwmon_module_temp_get(dev, attr, &temp); + if (err) + return err; + + if (temp <= 0) + return sprintf(buf, "%d\n", false); + + err = mlxsw_hwmon_module_temp_emergency_get(dev, attr, &emergency_temp); + if (err) + return err; + + return sprintf(buf, "%d\n", temp >= emergency_temp); +} + enum mlxsw_hwmon_attr_type { MLXSW_HWMON_ATTR_TYPE_TEMP, MLXSW_HWMON_ATTR_TYPE_TEMP_MAX, @@ -354,6 +448,8 @@ enum mlxsw_hwmon_attr_type { MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG, MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL, MLXSW_HWMON_ATTR_TYPE_TEMP_GBOX_LABEL, + MLXSW_HWMON_ATTR_TYPE_TEMP_CRIT_ALARM, + MLXSW_HWMON_ATTR_TYPE_TEMP_EMERGENCY_ALARM, }; static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon, @@ -444,6 +540,20 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon, snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), "temp%u_label", num + 1); break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_CRIT_ALARM: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_temp_critical_alarm_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_crit_alarm", num + 1); + break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_EMERGENCY_ALARM: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_temp_emergency_alarm_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_emergency_alarm", num + 1); + break; default: WARN_ON(1); } @@ -566,6 +676,12 @@ static int mlxsw_hwmon_module_init(struct mlxsw_hwmon *mlxsw_hwmon) mlxsw_hwmon_attr_add(mlxsw_hwmon, MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL, i, i); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_CRIT_ALARM, + i, i); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_EMERGENCY_ALARM, + i, i); } return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 079b080de7f7..485e3e02eb70 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4174,7 +4174,6 @@ MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4); #define MLXSW_REG_PTYS_EXT_ETH_SPEED_SGMII_100M BIT(0) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_1000BASE_X_SGMII BIT(1) -#define MLXSW_REG_PTYS_EXT_ETH_SPEED_2_5GBASE_X_2_5GMII BIT(2) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_5GBASE_R BIT(3) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_XFI_XAUI_1_10G BIT(4) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_XLAUI_4_XLPPI_4_40G BIT(5) @@ -4197,7 +4196,6 @@ MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32); #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 BIT(2) #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 BIT(3) #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR BIT(4) -#define MLXSW_REG_PTYS_ETH_SPEED_20GBASE_KR2 BIT(5) #define MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 BIT(6) #define MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 BIT(7) #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR BIT(12) @@ -4210,10 +4208,6 @@ MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32); #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 BIT(20) #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 BIT(21) #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 BIT(22) -#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4 BIT(23) -#define MLXSW_REG_PTYS_ETH_SPEED_100BASE_TX BIT(24) -#define MLXSW_REG_PTYS_ETH_SPEED_100BASE_T BIT(25) -#define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_T BIT(26) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR BIT(27) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR BIT(28) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR BIT(29) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index fdf9aa8314b2..4186e29119c2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -517,8 +517,8 @@ enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 state) return MLXSW_REG_SPMS_STATE_FORWARDING; case BR_STATE_LEARNING: return MLXSW_REG_SPMS_STATE_LEARNING; - case BR_STATE_LISTENING: /* fall-through */ - case BR_STATE_DISABLED: /* fall-through */ + case BR_STATE_LISTENING: + case BR_STATE_DISABLED: case BR_STATE_BLOCKING: return MLXSW_REG_SPMS_STATE_DISCARDING; default: diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index f9ba59641b4d..5240bf11b6c4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -636,11 +636,11 @@ static inline unsigned int mlxsw_sp_kvdl_entry_size(enum mlxsw_sp_kvdl_entry_type type) { switch (type) { - case MLXSW_SP_KVDL_ENTRY_TYPE_ADJ: /* fall through */ - case MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET: /* fall through */ - case MLXSW_SP_KVDL_ENTRY_TYPE_PBS: /* fall through */ - case MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR: /* fall through */ - case MLXSW_SP_KVDL_ENTRY_TYPE_TNUMT: /* fall through */ + case MLXSW_SP_KVDL_ENTRY_TYPE_ADJ: + case MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET: + case MLXSW_SP_KVDL_ENTRY_TYPE_PBS: + case MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR: + case MLXSW_SP_KVDL_ENTRY_TYPE_TNUMT: default: return 1; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index 14c78f73bb65..f08cad5b5657 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -993,22 +993,12 @@ struct mlxsw_sp1_port_link_mode { static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = { { - .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_T, - .mask_ethtool = ETHTOOL_LINK_MODE_100baseT_Full_BIT, - .speed = SPEED_100, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII | MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX, .mask_ethtool = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, .speed = SPEED_1000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_T, - .mask_ethtool = ETHTOOL_LINK_MODE_10000baseT_Full_BIT, - .speed = SPEED_10000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 | MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4, .mask_ethtool = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, @@ -1023,11 +1013,6 @@ static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = { .speed = SPEED_10000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_20GBASE_KR2, - .mask_ethtool = ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT, - .speed = SPEED_20000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4, .mask_ethtool = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, .speed = SPEED_40000, @@ -1092,11 +1077,6 @@ static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = { .mask_ethtool = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, .speed = SPEED_100000, }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4, - .mask_ethtool = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, - .speed = SPEED_100000, - }, }; #define MLXSW_SP1_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp1_port_link_mode) @@ -1237,14 +1217,6 @@ mlxsw_sp2_mask_ethtool_1000base_x_sgmii[] = { ARRAY_SIZE(mlxsw_sp2_mask_ethtool_1000base_x_sgmii) static const enum ethtool_link_mode_bit_indices -mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii[] = { - ETHTOOL_LINK_MODE_2500baseX_Full_BIT, -}; - -#define MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN \ - ARRAY_SIZE(mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii) - -static const enum ethtool_link_mode_bit_indices mlxsw_sp2_mask_ethtool_5gbase_r[] = { ETHTOOL_LINK_MODE_5000baseT_Full_BIT, }; @@ -1408,16 +1380,6 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .speed = SPEED_1000, }, { - .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_2_5GBASE_X_2_5GMII, - .mask_ethtool = mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii, - .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN, - .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | - MLXSW_SP_PORT_MASK_WIDTH_2X | - MLXSW_SP_PORT_MASK_WIDTH_4X | - MLXSW_SP_PORT_MASK_WIDTH_8X, - .speed = SPEED_2500, - }, - { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_5GBASE_R, .mask_ethtool = mlxsw_sp2_mask_ethtool_5gbase_r, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_5GBASE_R_LEN, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 9650562fc0ef..ca8090a28dec 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -314,11 +314,9 @@ static int mlxsw_sp_ptp_parse(struct sk_buff *skb, u8 *p_message_type, u16 *p_sequence_id) { - unsigned int offset = 0; unsigned int ptp_class; - u8 *data; + struct ptp_header *hdr; - data = skb_mac_header(skb); ptp_class = ptp_classify_raw(skb); switch (ptp_class & PTP_CLASS_VMASK) { @@ -329,30 +327,14 @@ static int mlxsw_sp_ptp_parse(struct sk_buff *skb, return -ERANGE; } - if (ptp_class & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (ptp_class & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return -ERANGE; - } - - /* PTP header is 34 bytes. */ - if (skb->len < offset + 34) + hdr = ptp_parse_header(skb, ptp_class); + if (!hdr) return -EINVAL; - *p_message_type = data[offset] & 0x0f; - *p_domain_number = data[offset + 4]; - *p_sequence_id = (u16)(data[offset + 30]) << 8 | data[offset + 31]; + *p_message_type = ptp_get_msgtype(hdr, ptp_class); + *p_domain_number = hdr->domain_number; + *p_sequence_id = be16_to_cpu(hdr->sequence_id); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 0521e9d48c45..24f1fd1f8d56 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1164,7 +1164,7 @@ mlxsw_sp_router_ip2me_fib_entry_find(struct mlxsw_sp *mlxsw_sp, u32 tb_id, addr_len = 4; addr_prefix_len = 32; break; - case MLXSW_SP_L3_PROTO_IPV6: /* fall through */ + case MLXSW_SP_L3_PROTO_IPV6: default: WARN_ON(1); return NULL; @@ -4555,14 +4555,14 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP; return 0; } - /* fall through */ + fallthrough; case RTN_BROADCAST: fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; return 0; case RTN_BLACKHOLE: fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE; return 0; - case RTN_UNREACHABLE: /* fall through */ + case RTN_UNREACHABLE: case RTN_PROHIBIT: /* Packets hitting these routes need to be trapped, but * can do so with a lower priority than packets directed @@ -5990,7 +5990,7 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info); fib_info_put(fib_work->fen_info.fi); break; - case FIB_EVENT_NH_ADD: /* fall through */ + case FIB_EVENT_NH_ADD: case FIB_EVENT_NH_DEL: mlxsw_sp_nexthop4_event(mlxsw_sp, fib_work->event, fib_work->fnh_info.fib_nh); @@ -6050,7 +6050,7 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) rtnl_lock(); mutex_lock(&mlxsw_sp->router->lock); switch (fib_work->event) { - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_ADD: replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE; @@ -6089,7 +6089,7 @@ static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work, struct fib_nh_notifier_info *fnh_info; switch (fib_work->event) { - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_DEL: fen_info = container_of(info, struct fib_entry_notifier_info, info); @@ -6099,7 +6099,7 @@ static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work, */ fib_info_hold(fib_work->fen_info.fi); break; - case FIB_EVENT_NH_ADD: /* fall through */ + case FIB_EVENT_NH_ADD: case FIB_EVENT_NH_DEL: fnh_info = container_of(info, struct fib_nh_notifier_info, info); @@ -6116,8 +6116,8 @@ static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, int err; switch (fib_work->event) { - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ - case FIB_EVENT_ENTRY_APPEND: /* fall through */ + case FIB_EVENT_ENTRY_REPLACE: + case FIB_EVENT_ENTRY_APPEND: case FIB_EVENT_ENTRY_DEL: fen6_info = container_of(info, struct fib6_entry_notifier_info, info); @@ -6136,13 +6136,13 @@ mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event_work *fib_work, struct fib_notifier_info *info) { switch (fib_work->event) { - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ - case FIB_EVENT_ENTRY_ADD: /* fall through */ + case FIB_EVENT_ENTRY_REPLACE: + case FIB_EVENT_ENTRY_ADD: case FIB_EVENT_ENTRY_DEL: memcpy(&fib_work->men_info, info, sizeof(fib_work->men_info)); mr_cache_hold(fib_work->men_info.mfc); break; - case FIB_EVENT_VIF_ADD: /* fall through */ + case FIB_EVENT_VIF_ADD: case FIB_EVENT_VIF_DEL: memcpy(&fib_work->ven_info, info, sizeof(fib_work->ven_info)); dev_hold(fib_work->ven_info.dev); @@ -6215,13 +6215,13 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, router = container_of(nb, struct mlxsw_sp_router, fib_nb); switch (event) { - case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_ADD: case FIB_EVENT_RULE_DEL: err = mlxsw_sp_router_fib_rule_event(event, info, router->mlxsw_sp); return notifier_from_errno(err); - case FIB_EVENT_ENTRY_ADD: /* fall through */ - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_ADD: + case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_APPEND: if (router->aborted) { NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route"); @@ -7277,7 +7277,7 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev, goto out; switch (event) { - case NETDEV_CHANGEMTU: /* fall through */ + case NETDEV_CHANGEMTU: case NETDEV_CHANGEADDR: err = mlxsw_sp_router_port_change_event(mlxsw_sp, rif); break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 5c959a995199..1d18e41ab255 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -1523,12 +1523,12 @@ mlxsw_sp_span_trigger_ops_set(struct mlxsw_sp_span_trigger_entry *trigger_entry) enum mlxsw_sp_span_trigger_type type; switch (trigger_entry->trigger) { - case MLXSW_SP_SPAN_TRIGGER_INGRESS: /* fall-through */ + case MLXSW_SP_SPAN_TRIGGER_INGRESS: case MLXSW_SP_SPAN_TRIGGER_EGRESS: type = MLXSW_SP_SPAN_TRIGGER_TYPE_PORT; break; - case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP: /* fall-through */ - case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP: /* fall-through */ + case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP: + case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP: case MLXSW_SP_SPAN_TRIGGER_ECN: type = MLXSW_SP_SPAN_TRIGGER_TYPE_GLOBAL; break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index a26162b08b7d..72912afa6f72 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1297,7 +1297,7 @@ static int mlxsw_sp_port_fdb_tunnel_uc_op(struct mlxsw_sp *mlxsw_sp, uip = be32_to_cpu(addr->addr4); sfd_proto = MLXSW_REG_SFD_UC_TUNNEL_PROTOCOL_IPV4; break; - case MLXSW_SP_L3_PROTO_IPV6: /* fall through */ + case MLXSW_SP_L3_PROTO_IPV6: default: WARN_ON(1); return -EOPNOTSUPP; @@ -2870,7 +2870,7 @@ static void mlxsw_sp_switchdev_bridge_fdb_event_work(struct work_struct *work) fdb_info = &switchdev_work->fdb_info; mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, false); break; - case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */ + case SWITCHDEV_FDB_ADD_TO_BRIDGE: case SWITCHDEV_FDB_DEL_TO_BRIDGE: /* These events are only used to potentially update an existing * SPAN mirror. @@ -3116,9 +3116,9 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused, switchdev_work->event = event; switch (event) { - case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */ - case SWITCHDEV_FDB_DEL_TO_DEVICE: /* fall through */ - case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */ + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + case SWITCHDEV_FDB_ADD_TO_BRIDGE: case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = container_of(info, struct switchdev_notifier_fdb_info, @@ -3138,7 +3138,7 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused, */ dev_hold(dev); break; - case SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE: /* fall through */ + case SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE: case SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE: INIT_WORK(&switchdev_work->work, mlxsw_sp_switchdev_vxlan_fdb_event_work); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 2e41c5519c1b..433f14ade464 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -291,7 +291,7 @@ static void mlxsw_sp_rx_sample_listener(struct sk_buff *skb, u8 local_port, static const struct mlxsw_sp_trap_policer_item mlxsw_sp_trap_policer_items_arr[] = { { - .policer = MLXSW_SP_TRAP_POLICER(1, 10 * 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(1, 10 * 1024, 4096), }, { .policer = MLXSW_SP_TRAP_POLICER(2, 128, 128), @@ -303,25 +303,25 @@ mlxsw_sp_trap_policer_items_arr[] = { .policer = MLXSW_SP_TRAP_POLICER(4, 128, 128), }, { - .policer = MLXSW_SP_TRAP_POLICER(5, 16 * 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(5, 16 * 1024, 8192), }, { .policer = MLXSW_SP_TRAP_POLICER(6, 128, 128), }, { - .policer = MLXSW_SP_TRAP_POLICER(7, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(7, 1024, 512), }, { - .policer = MLXSW_SP_TRAP_POLICER(8, 20 * 1024, 1024), + .policer = MLXSW_SP_TRAP_POLICER(8, 20 * 1024, 8192), }, { .policer = MLXSW_SP_TRAP_POLICER(9, 128, 128), }, { - .policer = MLXSW_SP_TRAP_POLICER(10, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(10, 1024, 512), }, { - .policer = MLXSW_SP_TRAP_POLICER(11, 360, 128), + .policer = MLXSW_SP_TRAP_POLICER(11, 256, 128), }, { .policer = MLXSW_SP_TRAP_POLICER(12, 128, 128), @@ -330,19 +330,19 @@ mlxsw_sp_trap_policer_items_arr[] = { .policer = MLXSW_SP_TRAP_POLICER(13, 128, 128), }, { - .policer = MLXSW_SP_TRAP_POLICER(14, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(14, 1024, 512), }, { - .policer = MLXSW_SP_TRAP_POLICER(15, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(15, 1024, 512), }, { - .policer = MLXSW_SP_TRAP_POLICER(16, 24 * 1024, 4096), + .policer = MLXSW_SP_TRAP_POLICER(16, 24 * 1024, 16384), }, { - .policer = MLXSW_SP_TRAP_POLICER(17, 19 * 1024, 4096), + .policer = MLXSW_SP_TRAP_POLICER(17, 19 * 1024, 8192), }, { - .policer = MLXSW_SP_TRAP_POLICER(18, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(18, 1024, 512), }, { .policer = MLXSW_SP_TRAP_POLICER(19, 1024, 512), diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 6f9a725662fb..5023d91269f4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -551,16 +551,6 @@ struct mlxsw_sx_port_link_mode { static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { { - .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_T, - .supported = SUPPORTED_100baseT_Full, - .advertised = ADVERTISED_100baseT_Full, - .speed = 100, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_TX, - .speed = 100, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII | MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX, .supported = SUPPORTED_1000baseKX_Full, @@ -568,12 +558,6 @@ static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { .speed = 1000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_T, - .supported = SUPPORTED_10000baseT_Full, - .advertised = ADVERTISED_10000baseT_Full, - .speed = 10000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 | MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4, .supported = SUPPORTED_10000baseKX4_Full, @@ -590,12 +574,6 @@ static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { .speed = 10000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_20GBASE_KR2, - .supported = SUPPORTED_20000baseKR2_Full, - .advertised = ADVERTISED_20000baseKR2_Full, - .speed = 20000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4, .supported = SUPPORTED_40000baseCR4_Full, .advertised = ADVERTISED_40000baseCR4_Full, @@ -634,8 +612,7 @@ static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { { .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 | MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4, + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4, .speed = 100000, }, }; diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index c533d06fbe3a..dcde496da7fb 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -548,7 +548,7 @@ static int lan743x_ethtool_get_rxnfc(struct net_device *netdev, case TCP_V4_FLOW:case UDP_V4_FLOW: case TCP_V6_FLOW:case UDP_V6_FLOW: rxnfc->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - /* fall through */ + fallthrough; case IPV4_FLOW: case IPV6_FLOW: rxnfc->data |= RXH_IP_SRC | RXH_IP_DST; return 0; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 867c680f5917..5abb7d2b0a9e 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -859,7 +859,7 @@ void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state) switch (state) { case BR_STATE_FORWARDING: ocelot->bridge_fwd_mask |= BIT(port); - /* Fallthrough */ + fallthrough; case BR_STATE_LEARNING: port_cfg |= ANA_PORT_PORT_CFG_LEARN_ENA; break; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 4a5beafa0493..1634ca6d4a8f 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -3543,11 +3543,10 @@ static void myri10ge_free_slices(struct myri10ge_priv *mgp) ss->fw_stats, ss->fw_stats_bus); ss->fw_stats = NULL; } - napi_hash_del(&ss->napi); - netif_napi_del(&ss->napi); + __netif_napi_del(&ss->napi); } /* Wait till napi structs are no longer used, and then free ss. */ - synchronize_rcu(); + synchronize_net(); kfree(mgp->ss); mgp->ss = NULL; } diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index c2867fe995bc..3de8430ee8c5 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -3081,7 +3081,7 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) switch(cmd) { case SIOCGMIIPHY: /* Get address of MII PHY in use. */ data->phy_id = np->phy_addr_external; - /* Fall Through */ + fallthrough; case SIOCGMIIREG: /* Read MII PHY register. */ /* The phy_id is not enough to uniquely identify diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 4f1f90f5e178..78eba10300ae 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -3768,20 +3768,20 @@ vxge_hw_rts_rth_data0_data1_get(u32 j, u64 *data0, u64 *data1, VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_ENTRY_EN | VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_BUCKET_DATA( itable[j]); - /* fall through */ + fallthrough; case 2: *data0 |= VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_NUM(j)| VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_ENTRY_EN | VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_DATA( itable[j]); - /* fall through */ + fallthrough; case 3: *data1 = VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_NUM(j)| VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_ENTRY_EN | VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_DATA( itable[j]); - /* fall through */ + fallthrough; case 4: *data1 |= VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_BUCKET_NUM(j)| diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 1ded4e275086..7afdb3bc631c 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -4539,7 +4539,7 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) * due to the fact that HWTS is using the FCS as the location of the * timestamp. The HW FCS checking will still correctly determine if * there is a valid checksum, and the FCS is being removed by the driver - * anyway. So no fucntionality is being lost. Since it is always + * anyway. So no functionality is being lost. Since it is always * enabled, we now simply use the ioctl call to set whether or not the * driver should be paying attention to the HWTS. */ diff --git a/drivers/net/ethernet/netronome/nfp/crypto/tls.c b/drivers/net/ethernet/netronome/nfp/crypto/tls.c index 7c50e3dfb9d5..76c51da5b66f 100644 --- a/drivers/net/ethernet/netronome/nfp/crypto/tls.c +++ b/drivers/net/ethernet/netronome/nfp/crypto/tls.c @@ -296,7 +296,7 @@ nfp_net_tls_add(struct net_device *netdev, struct sock *sk, break; } #endif - /* fall through */ + fallthrough; case AF_INET: req_sz = sizeof(struct nfp_crypto_req_add_v4); ipv6 = false; diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index ff844e5cc41f..1cbe2c9f3959 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -297,7 +297,7 @@ nfp_fl_get_tun_from_act(struct nfp_app *app, case htons(GENEVE_UDP_PORT): if (priv->flower_ext_feats & NFP_FL_FEATS_GENEVE) return NFP_FL_TUNNEL_GENEVE; - /* FALLTHROUGH */ + fallthrough; default: return NFP_FL_TUNNEL_NONE; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c index a050cb898782..f21cf1f40f98 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c @@ -289,7 +289,7 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb) skb_stored = nfp_flower_lag_unprocessed_msg(app, skb); break; } - /* fall through */ + fallthrough; default: err_default: nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n", diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index bf516285510f..a2926b1b3cff 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -24,6 +24,7 @@ #define NFP_FLOWER_LAYER_VXLAN BIT(7) #define NFP_FLOWER_LAYER2_GRE BIT(0) +#define NFP_FLOWER_LAYER2_QINQ BIT(4) #define NFP_FLOWER_LAYER2_GENEVE BIT(5) #define NFP_FLOWER_LAYER2_GENEVE_OP BIT(6) #define NFP_FLOWER_LAYER2_TUN_IPV6 BIT(7) @@ -319,6 +320,22 @@ struct nfp_flower_mac_mpls { __be32 mpls_lse; }; +/* VLAN details (2W/8B) + * 3 2 1 + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | outer_tpid | outer_tci | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | inner_tpid | inner_tci | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + */ +struct nfp_flower_vlan { + __be16 outer_tpid; + __be16 outer_tci; + __be16 inner_tpid; + __be16 inner_tci; +}; + /* L4 ports (for UDP, TCP, SCTP) (1W/4B) * 3 2 1 * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 3bf9c1afa45e..caf12eec9945 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -30,6 +30,8 @@ struct nfp_app; #define NFP_FLOWER_MASK_ELEMENT_RS 1 #define NFP_FLOWER_MASK_HASH_BITS 10 +#define NFP_FLOWER_KEY_MAX_LW 32 + #define NFP_FL_META_FLAG_MANAGE_MASK BIT(7) #define NFP_FL_MASK_REUSE_TIME_NS 40000 @@ -44,6 +46,7 @@ struct nfp_app; #define NFP_FL_FEATS_FLOW_MOD BIT(5) #define NFP_FL_FEATS_PRE_TUN_RULES BIT(6) #define NFP_FL_FEATS_IPV6_TUN BIT(7) +#define NFP_FL_FEATS_VLAN_QINQ BIT(8) #define NFP_FL_FEATS_HOST_ACK BIT(31) #define NFP_FL_ENABLE_FLOW_MERGE BIT(0) @@ -57,7 +60,8 @@ struct nfp_app; NFP_FL_FEATS_VF_RLIM | \ NFP_FL_FEATS_FLOW_MOD | \ NFP_FL_FEATS_PRE_TUN_RULES | \ - NFP_FL_FEATS_IPV6_TUN) + NFP_FL_FEATS_IPV6_TUN | \ + NFP_FL_FEATS_VLAN_QINQ) struct nfp_fl_mask_id { struct circ_buf mask_id_free_list; diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index f7f01e2e3dce..255a4dff6288 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -10,7 +10,7 @@ static void nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext, struct nfp_flower_meta_tci *msk, - struct flow_rule *rule, u8 key_type) + struct flow_rule *rule, u8 key_type, bool qinq_sup) { u16 tmp_tci; @@ -24,7 +24,7 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext, msk->nfp_flow_key_layer = key_type; msk->mask_id = ~0; - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + if (!qinq_sup && flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { struct flow_match_vlan match; flow_rule_match_vlan(rule, &match); @@ -231,6 +231,50 @@ nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext, } static void +nfp_flower_fill_vlan(struct flow_dissector_key_vlan *key, + struct nfp_flower_vlan *frame, + bool outer_vlan) +{ + u16 tci; + + tci = NFP_FLOWER_MASK_VLAN_PRESENT; + tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, + key->vlan_priority) | + FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, + key->vlan_id); + + if (outer_vlan) { + frame->outer_tci = cpu_to_be16(tci); + frame->outer_tpid = key->vlan_tpid; + } else { + frame->inner_tci = cpu_to_be16(tci); + frame->inner_tpid = key->vlan_tpid; + } +} + +static void +nfp_flower_compile_vlan(struct nfp_flower_vlan *ext, + struct nfp_flower_vlan *msk, + struct flow_rule *rule) +{ + struct flow_match_vlan match; + + memset(ext, 0, sizeof(struct nfp_flower_vlan)); + memset(msk, 0, sizeof(struct nfp_flower_vlan)); + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + flow_rule_match_vlan(rule, &match); + nfp_flower_fill_vlan(match.key, ext, true); + nfp_flower_fill_vlan(match.mask, msk, true); + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { + flow_rule_match_cvlan(rule, &match); + nfp_flower_fill_vlan(match.key, ext, false); + nfp_flower_fill_vlan(match.mask, msk, false); + } +} + +static void nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext, struct nfp_flower_ipv4 *msk, struct flow_rule *rule) { @@ -433,7 +477,10 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, struct netlink_ext_ack *extack) { struct flow_rule *rule = flow_cls_offload_flow_rule(flow); + struct nfp_flower_priv *priv = app->priv; + bool qinq_sup; u32 port_id; + int ext_len; int err; u8 *ext; u8 *msk; @@ -446,9 +493,11 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, ext = nfp_flow->unmasked_data; msk = nfp_flow->mask_data; + qinq_sup = !!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ); + nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)ext, (struct nfp_flower_meta_tci *)msk, - rule, key_ls->key_layer); + rule, key_ls->key_layer, qinq_sup); ext += sizeof(struct nfp_flower_meta_tci); msk += sizeof(struct nfp_flower_meta_tci); @@ -547,6 +596,14 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, } } + if (NFP_FLOWER_LAYER2_QINQ & key_ls->key_layer_two) { + nfp_flower_compile_vlan((struct nfp_flower_vlan *)ext, + (struct nfp_flower_vlan *)msk, + rule); + ext += sizeof(struct nfp_flower_vlan); + msk += sizeof(struct nfp_flower_vlan); + } + if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN || key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE) { if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6) { @@ -589,5 +646,15 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, } } + /* Check that the flow key does not exceed the maximum limit. + * All structures in the key is multiples of 4 bytes, so use u32. + */ + ext_len = (u32 *)ext - (u32 *)nfp_flow->unmasked_data; + if (ext_len > NFP_FLOWER_KEY_MAX_LW) { + NL_SET_ERR_MSG_MOD(extack, + "unsupported offload: flow key too long"); + return -EOPNOTSUPP; + } + return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 4651fe417b7f..1c59aff2163c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -31,6 +31,7 @@ BIT(FLOW_DISSECTOR_KEY_PORTS) | \ BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_VLAN) | \ + BIT(FLOW_DISSECTOR_KEY_CVLAN) | \ BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \ BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \ @@ -66,7 +67,8 @@ NFP_FLOWER_LAYER_IPV6) #define NFP_FLOWER_PRE_TUN_RULE_FIELDS \ - (NFP_FLOWER_LAYER_PORT | \ + (NFP_FLOWER_LAYER_EXT_META | \ + NFP_FLOWER_LAYER_PORT | \ NFP_FLOWER_LAYER_MAC | \ NFP_FLOWER_LAYER_IPV4 | \ NFP_FLOWER_LAYER_IPV6) @@ -285,6 +287,30 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support VLAN PCP offload"); return -EOPNOTSUPP; } + if (priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ && + !(key_layer_two & NFP_FLOWER_LAYER2_QINQ)) { + key_layer |= NFP_FLOWER_LAYER_EXT_META; + key_size += sizeof(struct nfp_flower_ext_meta); + key_size += sizeof(struct nfp_flower_vlan); + key_layer_two |= NFP_FLOWER_LAYER2_QINQ; + } + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { + struct flow_match_vlan cvlan; + + if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support VLAN QinQ offload"); + return -EOPNOTSUPP; + } + + flow_rule_match_vlan(rule, &cvlan); + if (!(key_layer_two & NFP_FLOWER_LAYER2_QINQ)) { + key_layer |= NFP_FLOWER_LAYER_EXT_META; + key_size += sizeof(struct nfp_flower_ext_meta); + key_size += sizeof(struct nfp_flower_vlan); + key_layer_two |= NFP_FLOWER_LAYER2_QINQ; + } } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { @@ -784,7 +810,7 @@ nfp_flower_copy_pre_actions(char *act_dst, char *act_src, int len, case NFP_FL_ACTION_OPCODE_PRE_TUNNEL: if (tunnel_act) *tunnel_act = true; - /* fall through */ + fallthrough; case NFP_FL_ACTION_OPCODE_PRE_LAG: memcpy(act_dst + act_off, act_src + act_off, act_len); break; @@ -1066,6 +1092,7 @@ err_destroy_merge_flow: * nfp_flower_validate_pre_tun_rule() * @app: Pointer to the APP handle * @flow: Pointer to NFP flow representation of rule + * @key_ls: Pointer to NFP key layers structure * @extack: Netlink extended ACK report * * Verifies the flow as a pre-tunnel rule. @@ -1075,10 +1102,13 @@ err_destroy_merge_flow: static int nfp_flower_validate_pre_tun_rule(struct nfp_app *app, struct nfp_fl_payload *flow, + struct nfp_fl_key_ls *key_ls, struct netlink_ext_ack *extack) { + struct nfp_flower_priv *priv = app->priv; struct nfp_flower_meta_tci *meta_tci; struct nfp_flower_mac_mpls *mac; + u8 *ext = flow->unmasked_data; struct nfp_fl_act_head *act; u8 *mask = flow->mask_data; bool vlan = false; @@ -1086,20 +1116,25 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, u8 key_layer; meta_tci = (struct nfp_flower_meta_tci *)flow->unmasked_data; - if (meta_tci->tci & cpu_to_be16(NFP_FLOWER_MASK_VLAN_PRESENT)) { - u16 vlan_tci = be16_to_cpu(meta_tci->tci); - - vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; - flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); - vlan = true; - } else { - flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + key_layer = key_ls->key_layer; + if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ)) { + if (meta_tci->tci & cpu_to_be16(NFP_FLOWER_MASK_VLAN_PRESENT)) { + u16 vlan_tci = be16_to_cpu(meta_tci->tci); + + vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; + flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); + vlan = true; + } else { + flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + } } - key_layer = meta_tci->nfp_flow_key_layer; if (key_layer & ~NFP_FLOWER_PRE_TUN_RULE_FIELDS) { NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: too many match fields"); return -EOPNOTSUPP; + } else if (key_ls->key_layer_two & ~NFP_FLOWER_LAYER2_QINQ) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: non-vlan in extended match fields"); + return -EOPNOTSUPP; } if (!(key_layer & NFP_FLOWER_LAYER_MAC)) { @@ -1109,7 +1144,13 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, /* Skip fields known to exist. */ mask += sizeof(struct nfp_flower_meta_tci); + ext += sizeof(struct nfp_flower_meta_tci); + if (key_ls->key_layer_two) { + mask += sizeof(struct nfp_flower_ext_meta); + ext += sizeof(struct nfp_flower_ext_meta); + } mask += sizeof(struct nfp_flower_in_port); + ext += sizeof(struct nfp_flower_in_port); /* Ensure destination MAC address is fully matched. */ mac = (struct nfp_flower_mac_mpls *)mask; @@ -1118,6 +1159,8 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, return -EOPNOTSUPP; } + mask += sizeof(struct nfp_flower_mac_mpls); + ext += sizeof(struct nfp_flower_mac_mpls); if (key_layer & NFP_FLOWER_LAYER_IPV4 || key_layer & NFP_FLOWER_LAYER_IPV6) { /* Flags and proto fields have same offset in IPv4 and IPv6. */ @@ -1130,7 +1173,6 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, sizeof(struct nfp_flower_ipv4) : sizeof(struct nfp_flower_ipv6); - mask += sizeof(struct nfp_flower_mac_mpls); /* Ensure proto and flags are the only IP layer fields. */ for (i = 0; i < size; i++) @@ -1138,6 +1180,25 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: only flags and proto can be matched in ip header"); return -EOPNOTSUPP; } + ext += size; + mask += size; + } + + if ((priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ)) { + if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_QINQ) { + struct nfp_flower_vlan *vlan_tags; + u16 vlan_tci; + + vlan_tags = (struct nfp_flower_vlan *)ext; + + vlan_tci = be16_to_cpu(vlan_tags->outer_tci); + + vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; + flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); + vlan = true; + } else { + flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + } } /* Action must be a single egress or pop_vlan and egress. */ @@ -1220,7 +1281,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, goto err_destroy_flow; if (flow_pay->pre_tun_rule.dev) { - err = nfp_flower_validate_pre_tun_rule(app, flow_pay, extack); + err = nfp_flower_validate_pre_tun_rule(app, flow_pay, key_layer, extack); if (err) goto err_destroy_flow; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 2df3deedf9fd..7248d248f604 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -61,6 +61,7 @@ struct nfp_tun_active_tuns { * @flags: options part of the request * @tun_info.ipv6: dest IPv6 address of active route * @tun_info.egress_port: port the encapsulated packet egressed + * @tun_info.extra: reserved for future use * @tun_info: tunnels that have sent traffic in reported period */ struct nfp_tun_active_tuns_v6 { @@ -70,6 +71,7 @@ struct nfp_tun_active_tuns_v6 { struct route_ip_info_v6 { struct in6_addr ipv6; __be32 egress_port; + __be32 extra[2]; } tun_info[]; }; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c index b04b83687fe2..2643ea5948f4 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -137,7 +137,7 @@ static u16 nfp_swreg_to_unreg(swreg reg, bool is_dst) val; case NN_LM_MOD_DEC: lm_dec = true; - /* fall through */ + fallthrough; case NN_LM_MOD_INC: if (val) { pr_err("LM offset in inc/dev mode\n"); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 39ee23e8c0bf..21ea22694e47 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1940,10 +1940,10 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) continue; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(dp->netdev, xdp_prog, act); - /* fall through */ + fallthrough; case XDP_DROP: nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag, rxbuf->dma_addr); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index a486008eb80a..252fe06f58aa 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -340,12 +340,12 @@ static int matching_bar(struct nfp_bar *bar, u32 tgt, u32 act, u32 tok, switch (maptype) { case NFP_PCIE_BAR_PCIE2CPP_MapType_TARGET: bartok = -1; - /* FALLTHROUGH */ + fallthrough; case NFP_PCIE_BAR_PCIE2CPP_MapType_BULK: baract = NFP_CPP_ACTION_RW; if (act == 0) act = NFP_CPP_ACTION_RW; - /* FALLTHROUGH */ + fallthrough; case NFP_PCIE_BAR_PCIE2CPP_MapType_FIXED: break; default: diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c index 75f012444796..2260c2403a83 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c @@ -213,7 +213,7 @@ u64 nfp_rtsym_size(const struct nfp_rtsym *sym) return 0; default: pr_warn("rtsym '%s': unknown type: %d\n", sym->name, sym->type); - /* fall through */ + fallthrough; case NFP_RTSYM_TYPE_OBJECT: case NFP_RTSYM_TYPE_FUNCTION: return sym->size; diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c index a26966fa40b9..dceec80fd642 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c @@ -410,7 +410,7 @@ static void pch_gbe_check_copper_options(struct pch_gbe_adapter *adapter) case SPEED_1000 + HALF_DUPLEX: netdev_dbg(adapter->netdev, "Half Duplex is not supported at 1000 Mbps\n"); - /* fall through */ + fallthrough; case SPEED_1000 + FULL_DUPLEX: full_duplex_only: netdev_dbg(adapter->netdev, diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c index 647a1431b359..3da075307178 100644 --- a/drivers/net/ethernet/packetengines/yellowfin.c +++ b/drivers/net/ethernet/packetengines/yellowfin.c @@ -1356,7 +1356,7 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) switch(cmd) { case SIOCGMIIPHY: /* Get address of MII PHY in use. */ data->phy_id = np->phys[0] & 0x1f; - /* Fall Through */ + fallthrough; case SIOCGMIIREG: /* Read MII PHY register. */ data->val_out = mdio_read(ioaddr, data->phy_id & 0x1f, data->reg_num & 0x1f); diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h index f5a910c458ba..084a924431d5 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic.h +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -42,13 +42,11 @@ struct ionic { struct ionic_dev_bar bars[IONIC_BARS_MAX]; unsigned int num_bars; struct ionic_identity ident; - struct list_head lifs; - struct ionic_lif *master_lif; + struct ionic_lif *lif; unsigned int nnqs_per_lif; unsigned int neqs_per_lif; unsigned int ntxqs_per_lif; unsigned int nrxqs_per_lif; - DECLARE_BITMAP(lifbits, IONIC_LIFS_MAX); unsigned int nintrs; DECLARE_BITMAP(intrs, IONIC_INTR_CTRL_REGS_MAX); struct work_struct nb_work; @@ -66,9 +64,6 @@ struct ionic_admin_ctx { union ionic_adminq_comp comp; }; -int ionic_napi(struct napi_struct *napi, int budget, ionic_cq_cb cb, - ionic_cq_done_cb done_cb, void *done_arg); - int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait); int ionic_set_dma_mask(struct ionic *ionic); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index 85c686c16741..d1d6fb6669e5 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -294,21 +294,21 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_port_reset; } - err = ionic_lifs_size(ionic); + err = ionic_lif_size(ionic); if (err) { - dev_err(dev, "Cannot size LIFs: %d, aborting\n", err); + dev_err(dev, "Cannot size LIF: %d, aborting\n", err); goto err_out_port_reset; } - err = ionic_lifs_alloc(ionic); + err = ionic_lif_alloc(ionic); if (err) { - dev_err(dev, "Cannot allocate LIFs: %d, aborting\n", err); + dev_err(dev, "Cannot allocate LIF: %d, aborting\n", err); goto err_out_free_irqs; } - err = ionic_lifs_init(ionic); + err = ionic_lif_init(ionic->lif); if (err) { - dev_err(dev, "Cannot init LIFs: %d, aborting\n", err); + dev_err(dev, "Cannot init LIF: %d, aborting\n", err); goto err_out_free_lifs; } @@ -321,9 +321,9 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(dev, "Cannot enable existing VFs: %d\n", err); } - err = ionic_lifs_register(ionic); + err = ionic_lif_register(ionic->lif); if (err) { - dev_err(dev, "Cannot register LIFs: %d, aborting\n", err); + dev_err(dev, "Cannot register LIF: %d, aborting\n", err); goto err_out_deinit_lifs; } @@ -336,12 +336,13 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_out_deregister_lifs: - ionic_lifs_unregister(ionic); + ionic_lif_unregister(ionic->lif); err_out_deinit_lifs: ionic_vf_dealloc(ionic); - ionic_lifs_deinit(ionic); + ionic_lif_deinit(ionic->lif); err_out_free_lifs: - ionic_lifs_free(ionic); + ionic_lif_free(ionic->lif); + ionic->lif = NULL; err_out_free_irqs: ionic_bus_free_irq_vectors(ionic); err_out_port_reset: @@ -377,11 +378,12 @@ static void ionic_remove(struct pci_dev *pdev) if (!ionic) return; - if (ionic->master_lif) { + if (ionic->lif) { ionic_devlink_unregister(ionic); - ionic_lifs_unregister(ionic); - ionic_lifs_deinit(ionic); - ionic_lifs_free(ionic); + ionic_lif_unregister(ionic->lif); + ionic_lif_deinit(ionic->lif); + ionic_lif_free(ionic->lif); + ionic->lif = NULL; ionic_bus_free_irq_vectors(ionic); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c index 11621ccc1faf..683bbbf75115 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -76,7 +76,7 @@ static int q_tail_show(struct seq_file *seq, void *v) { struct ionic_queue *q = seq->private; - seq_printf(seq, "%d\n", q->tail->index); + seq_printf(seq, "%d\n", q->tail_idx); return 0; } @@ -86,7 +86,7 @@ static int q_head_show(struct seq_file *seq, void *v) { struct ionic_queue *q = seq->private; - seq_printf(seq, "%d\n", q->head->index); + seq_printf(seq, "%d\n", q->head_idx); return 0; } @@ -96,7 +96,7 @@ static int cq_tail_show(struct seq_file *seq, void *v) { struct ionic_cq *cq = seq->private; - seq_printf(seq, "%d\n", cq->tail->index); + seq_printf(seq, "%d\n", cq->tail_idx); return 0; } @@ -112,7 +112,8 @@ static const struct debugfs_reg32 intr_ctrl_regs[] = { void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) { - struct dentry *q_dentry, *cq_dentry, *intr_dentry, *stats_dentry; + struct dentry *qcq_dentry, *q_dentry, *cq_dentry; + struct dentry *intr_dentry, *stats_dentry; struct ionic_dev *idev = &lif->ionic->idev; struct debugfs_regset32 *intr_ctrl_regset; struct ionic_intr_info *intr = &qcq->intr; @@ -121,21 +122,21 @@ void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) struct ionic_queue *q = &qcq->q; struct ionic_cq *cq = &qcq->cq; - qcq->dentry = debugfs_create_dir(q->name, lif->dentry); + qcq_dentry = debugfs_create_dir(q->name, lif->dentry); + if (IS_ERR_OR_NULL(qcq_dentry)) + return; + qcq->dentry = qcq_dentry; - debugfs_create_x32("total_size", 0400, qcq->dentry, &qcq->total_size); - debugfs_create_x64("base_pa", 0400, qcq->dentry, &qcq->base_pa); + debugfs_create_x64("q_base_pa", 0400, qcq_dentry, &qcq->q_base_pa); + debugfs_create_x32("q_size", 0400, qcq_dentry, &qcq->q_size); + debugfs_create_x64("cq_base_pa", 0400, qcq_dentry, &qcq->cq_base_pa); + debugfs_create_x32("cq_size", 0400, qcq_dentry, &qcq->cq_size); + debugfs_create_x64("sg_base_pa", 0400, qcq_dentry, &qcq->sg_base_pa); + debugfs_create_x32("sg_size", 0400, qcq_dentry, &qcq->sg_size); q_dentry = debugfs_create_dir("q", qcq->dentry); debugfs_create_u32("index", 0400, q_dentry, &q->index); - debugfs_create_x64("base_pa", 0400, q_dentry, &q->base_pa); - if (qcq->flags & IONIC_QCQ_F_SG) { - debugfs_create_x64("sg_base_pa", 0400, q_dentry, - &q->sg_base_pa); - debugfs_create_u32("sg_desc_size", 0400, q_dentry, - &q->sg_desc_size); - } debugfs_create_u32("num_descs", 0400, q_dentry, &q->num_descs); debugfs_create_u32("desc_size", 0400, q_dentry, &q->desc_size); debugfs_create_u32("pid", 0400, q_dentry, &q->pid); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index d83eff0ae0ac..6068f51a11d9 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -21,8 +21,8 @@ static void ionic_watchdog_cb(struct timer_list *t) hb = ionic_heartbeat_check(ionic); - if (hb >= 0 && ionic->master_lif) - ionic_link_status_check_request(ionic->master_lif); + if (hb >= 0 && ionic->lif) + ionic_link_status_check_request(ionic->lif); } void ionic_init_devinfo(struct ionic *ionic) @@ -126,7 +126,7 @@ int ionic_heartbeat_check(struct ionic *ionic) /* is this a transition? */ if (fw_status != idev->last_fw_status && idev->last_fw_status != 0xff) { - struct ionic_lif *lif = ionic->master_lif; + struct ionic_lif *lif = ionic->lif; bool trigger = false; if (!fw_status || fw_status == 0xff) { @@ -467,9 +467,7 @@ int ionic_cq_init(struct ionic_lif *lif, struct ionic_cq *cq, struct ionic_intr_info *intr, unsigned int num_descs, size_t desc_size) { - struct ionic_cq_info *cur; unsigned int ring_size; - unsigned int i; if (desc_size == 0 || !is_power_of_2(num_descs)) return -EINVAL; @@ -482,22 +480,9 @@ int ionic_cq_init(struct ionic_lif *lif, struct ionic_cq *cq, cq->bound_intr = intr; cq->num_descs = num_descs; cq->desc_size = desc_size; - cq->tail = cq->info; + cq->tail_idx = 0; cq->done_color = 1; - cur = cq->info; - - for (i = 0; i < num_descs; i++) { - if (i + 1 == num_descs) { - cur->next = cq->info; - cur->last = true; - } else { - cur->next = cur + 1; - } - cur->index = i; - cur++; - } - return 0; } @@ -522,15 +507,18 @@ unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do, ionic_cq_cb cb, ionic_cq_done_cb done_cb, void *done_arg) { + struct ionic_cq_info *cq_info; unsigned int work_done = 0; if (work_to_do == 0) return 0; - while (cb(cq, cq->tail)) { - if (cq->tail->last) + cq_info = &cq->info[cq->tail_idx]; + while (cb(cq, cq_info)) { + if (cq->tail_idx == cq->num_descs - 1) cq->done_color = !cq->done_color; - cq->tail = cq->tail->next; + cq->tail_idx = (cq->tail_idx + 1) & (cq->num_descs - 1); + cq_info = &cq->info[cq->tail_idx]; DEBUG_STATS_CQE_CNT(cq); if (++work_done >= work_to_do) @@ -548,9 +536,7 @@ int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, unsigned int num_descs, size_t desc_size, size_t sg_desc_size, unsigned int pid) { - struct ionic_desc_info *cur; unsigned int ring_size; - unsigned int i; if (desc_size == 0 || !is_power_of_2(num_descs)) return -EINVAL; @@ -565,24 +551,12 @@ int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, q->num_descs = num_descs; q->desc_size = desc_size; q->sg_desc_size = sg_desc_size; - q->tail = q->info; - q->head = q->tail; + q->tail_idx = 0; + q->head_idx = 0; q->pid = pid; snprintf(q->name, sizeof(q->name), "L%d-%s%u", lif->index, name, index); - cur = q->info; - - for (i = 0; i < num_descs; i++) { - if (i + 1 == num_descs) - cur->next = q->info; - else - cur->next = cur + 1; - cur->index = i; - cur->left = num_descs - i; - cur++; - } - return 0; } @@ -614,19 +588,22 @@ void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, void *cb_arg) { struct device *dev = q->lif->ionic->dev; + struct ionic_desc_info *desc_info; struct ionic_lif *lif = q->lif; - q->head->cb = cb; - q->head->cb_arg = cb_arg; - q->head = q->head->next; + desc_info = &q->info[q->head_idx]; + desc_info->cb = cb; + desc_info->cb_arg = cb_arg; + + q->head_idx = (q->head_idx + 1) & (q->num_descs - 1); dev_dbg(dev, "lif=%d qname=%s qid=%d qtype=%d p_index=%d ringdb=%d\n", q->lif->index, q->name, q->hw_type, q->hw_index, - q->head->index, ring_doorbell); + q->head_idx, ring_doorbell); if (ring_doorbell) ionic_dbell_ring(lif->kern_dbpage, q->hw_type, - q->dbval | q->head->index); + q->dbval | q->head_idx); } static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) @@ -634,8 +611,8 @@ static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) unsigned int mask, tail, head; mask = q->num_descs - 1; - tail = q->tail->index; - head = q->head->index; + tail = q->tail_idx; + head = q->head_idx; return ((pos - tail) & mask) < ((head - tail) & mask); } @@ -646,20 +623,22 @@ void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, struct ionic_desc_info *desc_info; ionic_desc_cb cb; void *cb_arg; + u16 index; /* check for empty queue */ - if (q->tail->index == q->head->index) + if (q->tail_idx == q->head_idx) return; /* stop index must be for a descriptor that is not yet completed */ if (unlikely(!ionic_q_is_posted(q, stop_index))) dev_err(q->lif->ionic->dev, "ionic stop is not posted %s stop %u tail %u head %u\n", - q->name, stop_index, q->tail->index, q->head->index); + q->name, stop_index, q->tail_idx, q->head_idx); do { - desc_info = q->tail; - q->tail = desc_info->next; + desc_info = &q->info[q->tail_idx]; + index = q->tail_idx; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); cb = desc_info->cb; cb_arg = desc_info->cb_arg; @@ -669,5 +648,5 @@ void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, if (cb) cb(q, desc_info, cq_info, cb_arg); - } while (desc_info->index != stop_index); + } while (index != stop_index); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index d5cba502abca..4a35174e3ff1 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -149,10 +149,13 @@ struct ionic_dev { }; struct ionic_cq_info { - void *cq_desc; - struct ionic_cq_info *next; - unsigned int index; - bool last; + union { + void *cq_desc; + struct ionic_txq_comp *txcq; + struct ionic_rxq_comp *rxcq; + struct ionic_admin_comp *admincq; + struct ionic_notifyq_event *notifyq; + }; }; struct ionic_queue; @@ -169,11 +172,17 @@ struct ionic_page_info { }; struct ionic_desc_info { - void *desc; - void *sg_desc; - struct ionic_desc_info *next; - unsigned int index; - unsigned int left; + union { + void *desc; + struct ionic_txq_desc *txq_desc; + struct ionic_rxq_desc *rxq_desc; + struct ionic_admin_cmd *adminq_desc; + }; + union { + void *sg_desc; + struct ionic_txq_sg_desc *txq_sg_desc; + struct ionic_rxq_sg_desc *rxq_sgl_desc; + }; unsigned int npages; struct ionic_page_info pages[IONIC_RX_MAX_SG_ELEMS + 1]; ionic_desc_cb cb; @@ -183,25 +192,35 @@ struct ionic_desc_info { #define IONIC_QUEUE_NAME_MAX_SZ 32 struct ionic_queue { + struct device *dev; + struct ionic_lif *lif; + struct ionic_desc_info *info; + u16 head_idx; + u16 tail_idx; + unsigned int index; + unsigned int num_descs; u64 dbell_count; - u64 drop; u64 stop; u64 wake; - struct ionic_lif *lif; - struct ionic_desc_info *info; - struct ionic_desc_info *tail; - struct ionic_desc_info *head; + u64 drop; struct ionic_dev *idev; - unsigned int index; unsigned int type; unsigned int hw_index; unsigned int hw_type; u64 dbval; - void *base; - void *sg_base; + union { + void *base; + struct ionic_txq_desc *txq; + struct ionic_rxq_desc *rxq; + struct ionic_admin_cmd *adminq; + }; + union { + void *sg_base; + struct ionic_txq_sg_desc *txq_sgl; + struct ionic_rxq_sg_desc *rxq_sgl; + }; dma_addr_t base_pa; dma_addr_t sg_base_pa; - unsigned int num_descs; unsigned int desc_size; unsigned int sg_desc_size; unsigned int pid; @@ -221,17 +240,17 @@ struct ionic_intr_info { }; struct ionic_cq { - void *base; - dma_addr_t base_pa; struct ionic_lif *lif; struct ionic_cq_info *info; - struct ionic_cq_info *tail; struct ionic_queue *bound_q; struct ionic_intr_info *bound_intr; + u16 tail_idx; bool done_color; unsigned int num_descs; - u64 compl_count; unsigned int desc_size; + u64 compl_count; + void *base; + dma_addr_t base_pa; }; struct ionic; @@ -246,12 +265,12 @@ static inline void ionic_intr_init(struct ionic_dev *idev, static inline unsigned int ionic_q_space_avail(struct ionic_queue *q) { - unsigned int avail = q->tail->index; + unsigned int avail = q->tail_idx; - if (q->head->index >= avail) - avail += q->head->left - 1; + if (q->head_idx >= avail) + avail += q->num_descs - q->head_idx - 1; else - avail -= q->head->index + 1; + avail -= q->head_idx + 1; return avail; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index c4f4fd469fe3..8d9fb2e19cca 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -85,7 +85,7 @@ int ionic_devlink_register(struct ionic *ionic) dev_err(ionic->dev, "devlink_port_register failed: %d\n", err); else devlink_port_type_eth_set(&ionic->dl_port, - ionic->master_lif->netdev); + ionic->lif->netdev); return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index 3c57c331729f..0d14659fbdfd 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -298,8 +298,8 @@ static void ionic_get_pauseparam(struct net_device *netdev, pause_type = lif->ionic->idev.port_info->config.pause_type; if (pause_type) { - pause->rx_pause = pause_type & IONIC_PAUSE_F_RX ? 1 : 0; - pause->tx_pause = pause_type & IONIC_PAUSE_F_TX ? 1 : 0; + pause->rx_pause = (pause_type & IONIC_PAUSE_F_RX) ? 1 : 0; + pause->tx_pause = (pause_type & IONIC_PAUSE_F_TX) ? 1 : 0; } } @@ -454,7 +454,7 @@ static int ionic_set_coalesce(struct net_device *netdev, if (test_bit(IONIC_LIF_F_UP, lif->state)) { for (i = 0; i < lif->nxqs; i++) { - qcq = lif->rxqcqs[i].qcq; + qcq = lif->rxqcqs[i]; ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, qcq->intr.index, lif->rx_coalesce_hw); @@ -471,7 +471,7 @@ static int ionic_set_coalesce(struct net_device *netdev, if (test_bit(IONIC_LIF_F_UP, lif->state)) { for (i = 0; i < lif->nxqs; i++) { - qcq = lif->txqcqs[i].qcq; + qcq = lif->txqcqs[i]; ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, qcq->intr.index, lif->tx_coalesce_hw); @@ -493,18 +493,14 @@ static void ionic_get_ringparam(struct net_device *netdev, ring->rx_pending = lif->nrxq_descs; } -static void ionic_set_ringsize(struct ionic_lif *lif, void *arg) -{ - struct ethtool_ringparam *ring = arg; - - lif->ntxq_descs = ring->tx_pending; - lif->nrxq_descs = ring->rx_pending; -} - static int ionic_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) { struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_queue_params qparam; + int err; + + ionic_init_queue_params(lif, &qparam); if (ring->rx_mini_pending || ring->rx_jumbo_pending) { netdev_info(netdev, "Changing jumbo or mini descriptors not supported\n"); @@ -522,7 +518,28 @@ static int ionic_set_ringparam(struct net_device *netdev, ring->rx_pending == lif->nrxq_descs) return 0; - return ionic_reset_queues(lif, ionic_set_ringsize, ring); + if (ring->tx_pending != lif->ntxq_descs) + netdev_info(netdev, "Changing Tx ring size from %d to %d\n", + lif->ntxq_descs, ring->tx_pending); + + if (ring->rx_pending != lif->nrxq_descs) + netdev_info(netdev, "Changing Rx ring size from %d to %d\n", + lif->nrxq_descs, ring->rx_pending); + + /* if we're not running, just set the values and return */ + if (!netif_running(lif->netdev)) { + lif->ntxq_descs = ring->tx_pending; + lif->nrxq_descs = ring->rx_pending; + return 0; + } + + qparam.ntxq_descs = ring->tx_pending; + qparam.nrxq_descs = ring->rx_pending; + err = ionic_reconfigure_queues(lif, &qparam); + if (err) + netdev_info(netdev, "Ring reconfiguration failed, changes canceled: %d\n", err); + + return err; } static void ionic_get_channels(struct net_device *netdev, @@ -544,32 +561,15 @@ static void ionic_get_channels(struct net_device *netdev, } } -static void ionic_set_queuecount(struct ionic_lif *lif, void *arg) -{ - struct ethtool_channels *ch = arg; - - if (ch->combined_count) { - lif->nxqs = ch->combined_count; - if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { - clear_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); - lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; - lif->tx_coalesce_hw = lif->rx_coalesce_hw; - netdev_info(lif->netdev, "Sharing queue interrupts\n"); - } - } else { - lif->nxqs = ch->rx_count; - if (!test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { - set_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); - netdev_info(lif->netdev, "Splitting queue interrupts\n"); - } - } -} - static int ionic_set_channels(struct net_device *netdev, struct ethtool_channels *ch) { struct ionic_lif *lif = netdev_priv(netdev); - int new_cnt; + struct ionic_queue_params qparam; + int max_cnt; + int err; + + ionic_init_queue_params(lif, &qparam); if (ch->rx_count != ch->tx_count) { netdev_info(netdev, "The rx and tx count must be equal\n"); @@ -577,20 +577,63 @@ static int ionic_set_channels(struct net_device *netdev, } if (ch->combined_count && ch->rx_count) { - netdev_info(netdev, "Use either combined_count or rx/tx_count, not both\n"); + netdev_info(netdev, "Use either combined or rx and tx, not both\n"); return -EINVAL; } - if (ch->combined_count) - new_cnt = ch->combined_count; - else - new_cnt = ch->rx_count; + max_cnt = lif->ionic->ntxqs_per_lif; + if (ch->combined_count) { + if (ch->combined_count > max_cnt) + return -EINVAL; + + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + netdev_info(lif->netdev, "Sharing queue interrupts\n"); + else if (ch->combined_count == lif->nxqs) + return 0; + + if (lif->nxqs != ch->combined_count) + netdev_info(netdev, "Changing queue count from %d to %d\n", + lif->nxqs, ch->combined_count); - if (lif->nxqs != new_cnt) - netdev_info(netdev, "Changing queue count from %d to %d\n", - lif->nxqs, new_cnt); + qparam.nxqs = ch->combined_count; + qparam.intr_split = 0; + } else { + max_cnt /= 2; + if (ch->rx_count > max_cnt) + return -EINVAL; - return ionic_reset_queues(lif, ionic_set_queuecount, ch); + if (!test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + netdev_info(lif->netdev, "Splitting queue interrupts\n"); + else if (ch->rx_count == lif->nxqs) + return 0; + + if (lif->nxqs != ch->rx_count) + netdev_info(netdev, "Changing queue count from %d to %d\n", + lif->nxqs, ch->rx_count); + + qparam.nxqs = ch->rx_count; + qparam.intr_split = 1; + } + + /* if we're not running, just set the values and return */ + if (!netif_running(lif->netdev)) { + lif->nxqs = qparam.nxqs; + + if (qparam.intr_split) { + set_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + } else { + clear_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; + lif->tx_coalesce_hw = lif->rx_coalesce_hw; + } + return 0; + } + + err = ionic_reconfigure_queues(lif, &qparam); + if (err) + netdev_info(netdev, "Queue reconfiguration failed, changes canceled: %d\n", err); + + return err; } static u32 ionic_get_priv_flags(struct net_device *netdev) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 26988ad7ec97..ee683cb142a8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -36,6 +36,8 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif); static void ionic_lif_handle_fw_up(struct ionic_lif *lif); static void ionic_lif_set_netdev_info(struct ionic_lif *lif); +static void ionic_txrx_deinit(struct ionic_lif *lif); +static int ionic_txrx_init(struct ionic_lif *lif); static int ionic_start_queues(struct ionic_lif *lif); static void ionic_stop_queues(struct ionic_lif *lif); static void ionic_lif_queue_identify(struct ionic_lif *lif); @@ -297,6 +299,18 @@ static void ionic_lif_qcq_deinit(struct ionic_lif *lif, struct ionic_qcq *qcq) qcq->flags &= ~IONIC_QCQ_F_INITED; } +static void ionic_qcq_intr_free(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + if (!(qcq->flags & IONIC_QCQ_F_INTR) || qcq->intr.vector == 0) + return; + + irq_set_affinity_hint(qcq->intr.vector, NULL); + devm_free_irq(lif->ionic->dev, qcq->intr.vector, &qcq->napi); + qcq->intr.vector = 0; + ionic_intr_free(lif->ionic, qcq->intr.index); + qcq->intr.index = IONIC_INTR_INDEX_NOT_ASSIGNED; +} + static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq) { struct device *dev = lif->ionic->dev; @@ -306,51 +320,62 @@ static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq) ionic_debugfs_del_qcq(qcq); - dma_free_coherent(dev, qcq->total_size, qcq->base, qcq->base_pa); - qcq->base = NULL; - qcq->base_pa = 0; + if (qcq->q_base) { + dma_free_coherent(dev, qcq->q_size, qcq->q_base, qcq->q_base_pa); + qcq->q_base = NULL; + qcq->q_base_pa = 0; + } - if (qcq->flags & IONIC_QCQ_F_INTR) { - irq_set_affinity_hint(qcq->intr.vector, NULL); - devm_free_irq(dev, qcq->intr.vector, &qcq->napi); - qcq->intr.vector = 0; - ionic_intr_free(lif->ionic, qcq->intr.index); + if (qcq->cq_base) { + dma_free_coherent(dev, qcq->cq_size, qcq->cq_base, qcq->cq_base_pa); + qcq->cq_base = NULL; + qcq->cq_base_pa = 0; } - devm_kfree(dev, qcq->cq.info); - qcq->cq.info = NULL; - devm_kfree(dev, qcq->q.info); - qcq->q.info = NULL; - devm_kfree(dev, qcq); + if (qcq->sg_base) { + dma_free_coherent(dev, qcq->sg_size, qcq->sg_base, qcq->sg_base_pa); + qcq->sg_base = NULL; + qcq->sg_base_pa = 0; + } + + ionic_qcq_intr_free(lif, qcq); + + if (qcq->cq.info) { + devm_kfree(dev, qcq->cq.info); + qcq->cq.info = NULL; + } + if (qcq->q.info) { + devm_kfree(dev, qcq->q.info); + qcq->q.info = NULL; + } } static void ionic_qcqs_free(struct ionic_lif *lif) { struct device *dev = lif->ionic->dev; - unsigned int i; if (lif->notifyqcq) { ionic_qcq_free(lif, lif->notifyqcq); + devm_kfree(dev, lif->notifyqcq); lif->notifyqcq = NULL; } if (lif->adminqcq) { ionic_qcq_free(lif, lif->adminqcq); + devm_kfree(dev, lif->adminqcq); lif->adminqcq = NULL; } if (lif->rxqcqs) { - for (i = 0; i < lif->nxqs; i++) - if (lif->rxqcqs[i].stats) - devm_kfree(dev, lif->rxqcqs[i].stats); + devm_kfree(dev, lif->rxqstats); + lif->rxqstats = NULL; devm_kfree(dev, lif->rxqcqs); lif->rxqcqs = NULL; } if (lif->txqcqs) { - for (i = 0; i < lif->nxqs; i++) - if (lif->txqcqs[i].stats) - devm_kfree(dev, lif->txqcqs[i].stats); + devm_kfree(dev, lif->txqstats); + lif->txqstats = NULL; devm_kfree(dev, lif->txqcqs); lif->txqcqs = NULL; } @@ -368,6 +393,53 @@ static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, n_qcq->intr.index = src_qcq->intr.index; } +static int ionic_alloc_qcq_interrupt(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + int err; + + if (!(qcq->flags & IONIC_QCQ_F_INTR)) { + qcq->intr.index = IONIC_INTR_INDEX_NOT_ASSIGNED; + return 0; + } + + err = ionic_intr_alloc(lif, &qcq->intr); + if (err) { + netdev_warn(lif->netdev, "no intr for %s: %d\n", + qcq->q.name, err); + goto err_out; + } + + err = ionic_bus_get_irq(lif->ionic, qcq->intr.index); + if (err < 0) { + netdev_warn(lif->netdev, "no vector for %s: %d\n", + qcq->q.name, err); + goto err_out_free_intr; + } + qcq->intr.vector = err; + ionic_intr_mask_assert(lif->ionic->idev.intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_SET); + + err = ionic_request_irq(lif, qcq); + if (err) { + netdev_warn(lif->netdev, "irq request failed %d\n", err); + goto err_out_free_intr; + } + + /* try to get the irq on the local numa node first */ + qcq->intr.cpu = cpumask_local_spread(qcq->intr.index, + dev_to_node(lif->ionic->dev)); + if (qcq->intr.cpu != -1) + cpumask_set_cpu(qcq->intr.cpu, &qcq->intr.affinity_mask); + + netdev_dbg(lif->netdev, "%s: Interrupt index %d\n", qcq->q.name, qcq->intr.index); + return 0; + +err_out_free_intr: + ionic_intr_free(lif->ionic, qcq->intr.index); +err_out: + return err; +} + static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, unsigned int index, const char *name, unsigned int flags, @@ -377,7 +449,6 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, unsigned int pid, struct ionic_qcq **qcq) { struct ionic_dev *idev = &lif->ionic->idev; - u32 q_size, cq_size, sg_size, total_size; struct device *dev = lif->ionic->dev; void *q_base, *cq_base, *sg_base; dma_addr_t cq_base_pa = 0; @@ -388,21 +459,6 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, *qcq = NULL; - q_size = num_descs * desc_size; - cq_size = num_descs * cq_desc_size; - sg_size = num_descs * sg_desc_size; - - total_size = ALIGN(q_size, PAGE_SIZE) + ALIGN(cq_size, PAGE_SIZE); - /* Note: aligning q_size/cq_size is not enough due to cq_base - * address aligning as q_base could be not aligned to the page. - * Adding PAGE_SIZE. - */ - total_size += PAGE_SIZE; - if (flags & IONIC_QCQ_F_SG) { - total_size += ALIGN(sg_size, PAGE_SIZE); - total_size += PAGE_SIZE; - } - new = devm_kzalloc(dev, sizeof(*new), GFP_KERNEL); if (!new) { netdev_err(lif->netdev, "Cannot allocate queue structure\n"); @@ -417,7 +473,7 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, if (!new->q.info) { netdev_err(lif->netdev, "Cannot allocate queue info\n"); err = -ENOMEM; - goto err_out; + goto err_out_free_qcq; } new->q.type = type; @@ -426,41 +482,12 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, desc_size, sg_desc_size, pid); if (err) { netdev_err(lif->netdev, "Cannot initialize queue\n"); - goto err_out; + goto err_out_free_q_info; } - if (flags & IONIC_QCQ_F_INTR) { - err = ionic_intr_alloc(lif, &new->intr); - if (err) { - netdev_warn(lif->netdev, "no intr for %s: %d\n", - name, err); - goto err_out; - } - - err = ionic_bus_get_irq(lif->ionic, new->intr.index); - if (err < 0) { - netdev_warn(lif->netdev, "no vector for %s: %d\n", - name, err); - goto err_out_free_intr; - } - new->intr.vector = err; - ionic_intr_mask_assert(idev->intr_ctrl, new->intr.index, - IONIC_INTR_MASK_SET); - - err = ionic_request_irq(lif, new); - if (err) { - netdev_warn(lif->netdev, "irq request failed %d\n", err); - goto err_out_free_intr; - } - - new->intr.cpu = cpumask_local_spread(new->intr.index, - dev_to_node(dev)); - if (new->intr.cpu != -1) - cpumask_set_cpu(new->intr.cpu, - &new->intr.affinity_mask); - } else { - new->intr.index = IONIC_INTR_INDEX_NOT_ASSIGNED; - } + err = ionic_alloc_qcq_interrupt(lif, new); + if (err) + goto err_out; new->cq.info = devm_kcalloc(dev, num_descs, sizeof(*new->cq.info), GFP_KERNEL); @@ -473,46 +500,67 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, err = ionic_cq_init(lif, &new->cq, &new->intr, num_descs, cq_desc_size); if (err) { netdev_err(lif->netdev, "Cannot initialize completion queue\n"); - goto err_out_free_irq; + goto err_out_free_cq_info; } - new->base = dma_alloc_coherent(dev, total_size, &new->base_pa, - GFP_KERNEL); - if (!new->base) { + new->q_size = PAGE_SIZE + (num_descs * desc_size); + new->q_base = dma_alloc_coherent(dev, new->q_size, &new->q_base_pa, + GFP_KERNEL); + if (!new->q_base) { netdev_err(lif->netdev, "Cannot allocate queue DMA memory\n"); err = -ENOMEM; - goto err_out_free_irq; + goto err_out_free_cq_info; } + q_base = PTR_ALIGN(new->q_base, PAGE_SIZE); + q_base_pa = ALIGN(new->q_base_pa, PAGE_SIZE); + ionic_q_map(&new->q, q_base, q_base_pa); - new->total_size = total_size; - - q_base = new->base; - q_base_pa = new->base_pa; - - cq_base = (void *)ALIGN((uintptr_t)q_base + q_size, PAGE_SIZE); - cq_base_pa = ALIGN(q_base_pa + q_size, PAGE_SIZE); + new->cq_size = PAGE_SIZE + (num_descs * cq_desc_size); + new->cq_base = dma_alloc_coherent(dev, new->cq_size, &new->cq_base_pa, + GFP_KERNEL); + if (!new->cq_base) { + netdev_err(lif->netdev, "Cannot allocate cq DMA memory\n"); + err = -ENOMEM; + goto err_out_free_q; + } + cq_base = PTR_ALIGN(new->cq_base, PAGE_SIZE); + cq_base_pa = ALIGN(new->cq_base_pa, PAGE_SIZE); + ionic_cq_map(&new->cq, cq_base, cq_base_pa); + ionic_cq_bind(&new->cq, &new->q); if (flags & IONIC_QCQ_F_SG) { - sg_base = (void *)ALIGN((uintptr_t)cq_base + cq_size, - PAGE_SIZE); - sg_base_pa = ALIGN(cq_base_pa + cq_size, PAGE_SIZE); + new->sg_size = PAGE_SIZE + (num_descs * sg_desc_size); + new->sg_base = dma_alloc_coherent(dev, new->sg_size, &new->sg_base_pa, + GFP_KERNEL); + if (!new->sg_base) { + netdev_err(lif->netdev, "Cannot allocate sg DMA memory\n"); + err = -ENOMEM; + goto err_out_free_cq; + } + sg_base = PTR_ALIGN(new->sg_base, PAGE_SIZE); + sg_base_pa = ALIGN(new->sg_base_pa, PAGE_SIZE); ionic_q_sg_map(&new->q, sg_base, sg_base_pa); } - ionic_q_map(&new->q, q_base, q_base_pa); - ionic_cq_map(&new->cq, cq_base, cq_base_pa); - ionic_cq_bind(&new->cq, &new->q); - *qcq = new; return 0; +err_out_free_cq: + dma_free_coherent(dev, new->cq_size, new->cq_base, new->cq_base_pa); +err_out_free_q: + dma_free_coherent(dev, new->q_size, new->q_base, new->q_base_pa); +err_out_free_cq_info: + devm_kfree(dev, new->cq.info); err_out_free_irq: - if (flags & IONIC_QCQ_F_INTR) + if (flags & IONIC_QCQ_F_INTR) { devm_free_irq(dev, new->intr.vector, &new->napi); -err_out_free_intr: - if (flags & IONIC_QCQ_F_INTR) ionic_intr_free(lif->ionic, new->intr.index); + } +err_out_free_q_info: + devm_kfree(dev, new->q.info); +err_out_free_qcq: + devm_kfree(dev, new); err_out: dev_err(dev, "qcq alloc of %s%d failed %d\n", name, index, err); return err; @@ -521,10 +569,8 @@ err_out: static int ionic_qcqs_alloc(struct ionic_lif *lif) { struct device *dev = lif->ionic->dev; - unsigned int q_list_size; unsigned int flags; int err; - int i; flags = IONIC_QCQ_F_INTR; err = ionic_qcq_alloc(lif, IONIC_QTYPE_ADMINQ, 0, "admin", flags, @@ -544,63 +590,50 @@ static int ionic_qcqs_alloc(struct ionic_lif *lif) sizeof(union ionic_notifyq_comp), 0, lif->kern_pid, &lif->notifyqcq); if (err) - goto err_out_free_adminqcq; + goto err_out; ionic_debugfs_add_qcq(lif, lif->notifyqcq); /* Let the notifyq ride on the adminq interrupt */ ionic_link_qcq_interrupts(lif->adminqcq, lif->notifyqcq); } - q_list_size = sizeof(*lif->txqcqs) * lif->nxqs; err = -ENOMEM; - lif->txqcqs = devm_kzalloc(dev, q_list_size, GFP_KERNEL); + lif->txqcqs = devm_kcalloc(dev, lif->ionic->ntxqs_per_lif, + sizeof(struct ionic_qcq *), GFP_KERNEL); if (!lif->txqcqs) - goto err_out_free_notifyqcq; - for (i = 0; i < lif->nxqs; i++) { - lif->txqcqs[i].stats = devm_kzalloc(dev, - sizeof(struct ionic_q_stats), - GFP_KERNEL); - if (!lif->txqcqs[i].stats) - goto err_out_free_tx_stats; - } - - lif->rxqcqs = devm_kzalloc(dev, q_list_size, GFP_KERNEL); + goto err_out; + lif->rxqcqs = devm_kcalloc(dev, lif->ionic->nrxqs_per_lif, + sizeof(struct ionic_qcq *), GFP_KERNEL); if (!lif->rxqcqs) - goto err_out_free_tx_stats; - for (i = 0; i < lif->nxqs; i++) { - lif->rxqcqs[i].stats = devm_kzalloc(dev, - sizeof(struct ionic_q_stats), - GFP_KERNEL); - if (!lif->rxqcqs[i].stats) - goto err_out_free_rx_stats; - } + goto err_out; - return 0; + lif->txqstats = devm_kcalloc(dev, lif->ionic->ntxqs_per_lif, + sizeof(struct ionic_tx_stats), GFP_KERNEL); + if (!lif->txqstats) + goto err_out; + lif->rxqstats = devm_kcalloc(dev, lif->ionic->nrxqs_per_lif, + sizeof(struct ionic_rx_stats), GFP_KERNEL); + if (!lif->rxqstats) + goto err_out; -err_out_free_rx_stats: - for (i = 0; i < lif->nxqs; i++) - if (lif->rxqcqs[i].stats) - devm_kfree(dev, lif->rxqcqs[i].stats); - devm_kfree(dev, lif->rxqcqs); - lif->rxqcqs = NULL; -err_out_free_tx_stats: - for (i = 0; i < lif->nxqs; i++) - if (lif->txqcqs[i].stats) - devm_kfree(dev, lif->txqcqs[i].stats); - devm_kfree(dev, lif->txqcqs); - lif->txqcqs = NULL; -err_out_free_notifyqcq: - if (lif->notifyqcq) { - ionic_qcq_free(lif, lif->notifyqcq); - lif->notifyqcq = NULL; - } -err_out_free_adminqcq: - ionic_qcq_free(lif, lif->adminqcq); - lif->adminqcq = NULL; + return 0; +err_out: + ionic_qcqs_free(lif); return err; } +static void ionic_qcq_sanitize(struct ionic_qcq *qcq) +{ + qcq->q.tail_idx = 0; + qcq->q.head_idx = 0; + qcq->cq.tail_idx = 0; + qcq->cq.done_color = 1; + memset(qcq->q_base, 0, qcq->q_size); + memset(qcq->cq_base, 0, qcq->cq_size); + memset(qcq->sg_base, 0, qcq->sg_size); +} + static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) { struct device *dev = lif->ionic->dev; @@ -626,10 +659,10 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) unsigned int intr_index; int err; - if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + if (qcq->flags & IONIC_QCQ_F_INTR) intr_index = qcq->intr.index; else - intr_index = lif->rxqcqs[q->index].qcq->intr.index; + intr_index = lif->rxqcqs[q->index]->intr.index; ctx.cmd.q_init.intr_index = cpu_to_le16(intr_index); dev_dbg(dev, "txq_init.pid %d\n", ctx.cmd.q_init.pid); @@ -640,9 +673,7 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "txq_init.ver %d\n", ctx.cmd.q_init.ver); dev_dbg(dev, "txq_init.intr_index %d\n", ctx.cmd.q_init.intr_index); - q->tail = q->info; - q->head = q->tail; - cq->tail = cq->info; + ionic_qcq_sanitize(qcq); err = ionic_adminq_post_wait(lif, &ctx); if (err) @@ -697,9 +728,7 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "rxq_init.ver %d\n", ctx.cmd.q_init.ver); dev_dbg(dev, "rxq_init.intr_index %d\n", ctx.cmd.q_init.intr_index); - q->tail = q->info; - q->head = q->tail; - cq->tail = cq->info; + ionic_qcq_sanitize(qcq); err = ionic_adminq_post_wait(lif, &ctx); if (err) @@ -771,21 +800,6 @@ static bool ionic_notifyq_service(struct ionic_cq *cq, return true; } -static int ionic_notifyq_clean(struct ionic_lif *lif, int budget) -{ - struct ionic_dev *idev = &lif->ionic->idev; - struct ionic_cq *cq = &lif->notifyqcq->cq; - u32 work_done; - - work_done = ionic_cq_service(cq, budget, ionic_notifyq_service, - NULL, NULL); - if (work_done) - ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, - work_done, IONIC_INTR_CRED_RESET_COALESCE); - - return work_done; -} - static bool ionic_adminq_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) { @@ -801,15 +815,36 @@ static bool ionic_adminq_service(struct ionic_cq *cq, static int ionic_adminq_napi(struct napi_struct *napi, int budget) { + struct ionic_intr_info *intr = napi_to_cq(napi)->bound_intr; struct ionic_lif *lif = napi_to_cq(napi)->lif; + struct ionic_dev *idev = &lif->ionic->idev; + unsigned int flags = 0; int n_work = 0; int a_work = 0; + int work_done; + + if (lif->notifyqcq && lif->notifyqcq->flags & IONIC_QCQ_F_INITED) + n_work = ionic_cq_service(&lif->notifyqcq->cq, budget, + ionic_notifyq_service, NULL, NULL); + + if (lif->adminqcq && lif->adminqcq->flags & IONIC_QCQ_F_INITED) + a_work = ionic_cq_service(&lif->adminqcq->cq, budget, + ionic_adminq_service, NULL, NULL); - if (likely(lif->notifyqcq && lif->notifyqcq->flags & IONIC_QCQ_F_INITED)) - n_work = ionic_notifyq_clean(lif, budget); - a_work = ionic_napi(napi, budget, ionic_adminq_service, NULL, NULL); + work_done = max(n_work, a_work); + if (work_done < budget && napi_complete_done(napi, work_done)) { + flags |= IONIC_INTR_CRED_UNMASK; + DEBUG_STATS_INTR_REARM(intr); + } + + if (work_done || flags) { + flags |= IONIC_INTR_CRED_RESET_COALESCE; + ionic_intr_credits(idev->intr_ctrl, + intr->index, + n_work + a_work, flags); + } - return max(n_work, a_work); + return work_done; } void ionic_get_stats64(struct net_device *netdev, @@ -1315,6 +1350,35 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa) return ionic_addr_add(netdev, mac); } +static void ionic_stop_queues_reconfig(struct ionic_lif *lif) +{ + /* Stop and clean the queues before reconfiguration */ + mutex_lock(&lif->queue_lock); + netif_device_detach(lif->netdev); + ionic_stop_queues(lif); + ionic_txrx_deinit(lif); +} + +static int ionic_start_queues_reconfig(struct ionic_lif *lif) +{ + int err; + + /* Re-init the queues after reconfiguration */ + + /* The only way txrx_init can fail here is if communication + * with FW is suddenly broken. There's not much we can do + * at this point - error messages have already been printed, + * so we can continue on and the user can eventually do a + * DOWN and UP to try to reset and clear the issue. + */ + err = ionic_txrx_init(lif); + mutex_unlock(&lif->queue_lock); + ionic_link_status_check_request(lif); + netif_device_attach(lif->netdev); + + return err; +} + static int ionic_change_mtu(struct net_device *netdev, int new_mtu) { struct ionic_lif *lif = netdev_priv(netdev); @@ -1334,9 +1398,12 @@ static int ionic_change_mtu(struct net_device *netdev, int new_mtu) return err; netdev->mtu = new_mtu; - err = ionic_reset_queues(lif, NULL, NULL); + /* if we're not running, nothing more to do */ + if (!netif_running(netdev)) + return 0; - return err; + ionic_stop_queues_reconfig(lif); + return ionic_start_queues_reconfig(lif); } static void ionic_tx_timeout_work(struct work_struct *ws) @@ -1345,9 +1412,14 @@ static void ionic_tx_timeout_work(struct work_struct *ws) netdev_info(lif->netdev, "Tx Timeout recovery\n"); - rtnl_lock(); - ionic_reset_queues(lif, NULL, NULL); - rtnl_unlock(); + /* if we were stopped before this scheduled job was launched, + * don't bother the queues as they are already stopped. + */ + if (!netif_running(lif->netdev)) + return; + + ionic_stop_queues_reconfig(lif); + ionic_start_queues_reconfig(lif); } static void ionic_tx_timeout(struct net_device *netdev, unsigned int txqueue) @@ -1482,7 +1554,7 @@ static void ionic_txrx_disable(struct ionic_lif *lif) if (lif->txqcqs) { for (i = 0; i < lif->nxqs; i++) { - err = ionic_qcq_disable(lif->txqcqs[i].qcq); + err = ionic_qcq_disable(lif->txqcqs[i]); if (err == -ETIMEDOUT) break; } @@ -1490,7 +1562,7 @@ static void ionic_txrx_disable(struct ionic_lif *lif) if (lif->rxqcqs) { for (i = 0; i < lif->nxqs; i++) { - err = ionic_qcq_disable(lif->rxqcqs[i].qcq); + err = ionic_qcq_disable(lif->rxqcqs[i]); if (err == -ETIMEDOUT) break; } @@ -1502,18 +1574,18 @@ static void ionic_txrx_deinit(struct ionic_lif *lif) unsigned int i; if (lif->txqcqs) { - for (i = 0; i < lif->nxqs; i++) { - ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); - ionic_tx_flush(&lif->txqcqs[i].qcq->cq); - ionic_tx_empty(&lif->txqcqs[i].qcq->q); + for (i = 0; i < lif->nxqs && lif->txqcqs[i]; i++) { + ionic_lif_qcq_deinit(lif, lif->txqcqs[i]); + ionic_tx_flush(&lif->txqcqs[i]->cq); + ionic_tx_empty(&lif->txqcqs[i]->q); } } if (lif->rxqcqs) { - for (i = 0; i < lif->nxqs; i++) { - ionic_lif_qcq_deinit(lif, lif->rxqcqs[i].qcq); - ionic_rx_flush(&lif->rxqcqs[i].qcq->cq); - ionic_rx_empty(&lif->rxqcqs[i].qcq->q); + for (i = 0; i < lif->nxqs && lif->rxqcqs[i]; i++) { + ionic_lif_qcq_deinit(lif, lif->rxqcqs[i]); + ionic_rx_flush(&lif->rxqcqs[i]->cq); + ionic_rx_empty(&lif->rxqcqs[i]->q); } } lif->rx_mode = 0; @@ -1524,16 +1596,18 @@ static void ionic_txrx_free(struct ionic_lif *lif) unsigned int i; if (lif->txqcqs) { - for (i = 0; i < lif->nxqs; i++) { - ionic_qcq_free(lif, lif->txqcqs[i].qcq); - lif->txqcqs[i].qcq = NULL; + for (i = 0; i < lif->ionic->ntxqs_per_lif && lif->txqcqs[i]; i++) { + ionic_qcq_free(lif, lif->txqcqs[i]); + devm_kfree(lif->ionic->dev, lif->txqcqs[i]); + lif->txqcqs[i] = NULL; } } if (lif->rxqcqs) { - for (i = 0; i < lif->nxqs; i++) { - ionic_qcq_free(lif, lif->rxqcqs[i].qcq); - lif->rxqcqs[i].qcq = NULL; + for (i = 0; i < lif->ionic->nrxqs_per_lif && lif->rxqcqs[i]; i++) { + ionic_qcq_free(lif, lif->rxqcqs[i]); + devm_kfree(lif->ionic->dev, lif->rxqcqs[i]); + lif->rxqcqs[i] = NULL; } } } @@ -1561,17 +1635,16 @@ static int ionic_txrx_alloc(struct ionic_lif *lif) sizeof(struct ionic_txq_desc), sizeof(struct ionic_txq_comp), sg_desc_sz, - lif->kern_pid, &lif->txqcqs[i].qcq); + lif->kern_pid, &lif->txqcqs[i]); if (err) goto err_out; if (flags & IONIC_QCQ_F_INTR) ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, - lif->txqcqs[i].qcq->intr.index, + lif->txqcqs[i]->intr.index, lif->tx_coalesce_hw); - lif->txqcqs[i].qcq->stats = lif->txqcqs[i].stats; - ionic_debugfs_add_qcq(lif, lif->txqcqs[i].qcq); + ionic_debugfs_add_qcq(lif, lif->txqcqs[i]); } flags = IONIC_QCQ_F_RX_STATS | IONIC_QCQ_F_SG | IONIC_QCQ_F_INTR; @@ -1581,20 +1654,19 @@ static int ionic_txrx_alloc(struct ionic_lif *lif) sizeof(struct ionic_rxq_desc), sizeof(struct ionic_rxq_comp), sizeof(struct ionic_rxq_sg_desc), - lif->kern_pid, &lif->rxqcqs[i].qcq); + lif->kern_pid, &lif->rxqcqs[i]); if (err) goto err_out; ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, - lif->rxqcqs[i].qcq->intr.index, + lif->rxqcqs[i]->intr.index, lif->rx_coalesce_hw); if (!test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) - ionic_link_qcq_interrupts(lif->rxqcqs[i].qcq, - lif->txqcqs[i].qcq); + ionic_link_qcq_interrupts(lif->rxqcqs[i], + lif->txqcqs[i]); - lif->rxqcqs[i].qcq->stats = lif->rxqcqs[i].stats; - ionic_debugfs_add_qcq(lif, lif->rxqcqs[i].qcq); + ionic_debugfs_add_qcq(lif, lif->rxqcqs[i]); } return 0; @@ -1611,13 +1683,13 @@ static int ionic_txrx_init(struct ionic_lif *lif) int err; for (i = 0; i < lif->nxqs; i++) { - err = ionic_lif_txq_init(lif, lif->txqcqs[i].qcq); + err = ionic_lif_txq_init(lif, lif->txqcqs[i]); if (err) goto err_out; - err = ionic_lif_rxq_init(lif, lif->rxqcqs[i].qcq); + err = ionic_lif_rxq_init(lif, lif->rxqcqs[i]); if (err) { - ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); + ionic_lif_qcq_deinit(lif, lif->txqcqs[i]); goto err_out; } } @@ -1631,8 +1703,8 @@ static int ionic_txrx_init(struct ionic_lif *lif) err_out: while (i--) { - ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); - ionic_lif_qcq_deinit(lif, lif->rxqcqs[i].qcq); + ionic_lif_qcq_deinit(lif, lif->txqcqs[i]); + ionic_lif_qcq_deinit(lif, lif->rxqcqs[i]); } return err; @@ -1643,15 +1715,15 @@ static int ionic_txrx_enable(struct ionic_lif *lif) int i, err; for (i = 0; i < lif->nxqs; i++) { - ionic_rx_fill(&lif->rxqcqs[i].qcq->q); - err = ionic_qcq_enable(lif->rxqcqs[i].qcq); + ionic_rx_fill(&lif->rxqcqs[i]->q); + err = ionic_qcq_enable(lif->rxqcqs[i]); if (err) goto err_out; - err = ionic_qcq_enable(lif->txqcqs[i].qcq); + err = ionic_qcq_enable(lif->txqcqs[i]); if (err) { if (err != -ETIMEDOUT) - ionic_qcq_disable(lif->rxqcqs[i].qcq); + ionic_qcq_disable(lif->rxqcqs[i]); goto err_out; } } @@ -1660,10 +1732,10 @@ static int ionic_txrx_enable(struct ionic_lif *lif) err_out: while (i--) { - err = ionic_qcq_disable(lif->txqcqs[i].qcq); + err = ionic_qcq_disable(lif->txqcqs[i]); if (err == -ETIMEDOUT) break; - err = ionic_qcq_disable(lif->rxqcqs[i].qcq); + err = ionic_qcq_disable(lif->rxqcqs[i]); if (err == -ETIMEDOUT) break; } @@ -1688,7 +1760,7 @@ static int ionic_start_queues(struct ionic_lif *lif) return 0; } -int ionic_open(struct net_device *netdev) +static int ionic_open(struct net_device *netdev) { struct ionic_lif *lif = netdev_priv(netdev); int err; @@ -1734,7 +1806,7 @@ static void ionic_stop_queues(struct ionic_lif *lif) ionic_txrx_disable(lif); } -int ionic_stop(struct net_device *netdev) +static int ionic_stop(struct net_device *netdev) { struct ionic_lif *lif = netdev_priv(netdev); @@ -2016,35 +2088,210 @@ static const struct net_device_ops ionic_netdev_ops = { .ndo_get_vf_stats = ionic_get_vf_stats, }; -int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg) -{ - bool running; - int err = 0; +static void ionic_swap_queues(struct ionic_qcq *a, struct ionic_qcq *b) +{ + /* only swapping the queues, not the napi, flags, or other stuff */ + swap(a->q.num_descs, b->q.num_descs); + swap(a->q.base, b->q.base); + swap(a->q.base_pa, b->q.base_pa); + swap(a->q.info, b->q.info); + swap(a->q_base, b->q_base); + swap(a->q_base_pa, b->q_base_pa); + swap(a->q_size, b->q_size); + + swap(a->q.sg_base, b->q.sg_base); + swap(a->q.sg_base_pa, b->q.sg_base_pa); + swap(a->sg_base, b->sg_base); + swap(a->sg_base_pa, b->sg_base_pa); + swap(a->sg_size, b->sg_size); + + swap(a->cq.num_descs, b->cq.num_descs); + swap(a->cq.base, b->cq.base); + swap(a->cq.base_pa, b->cq.base_pa); + swap(a->cq.info, b->cq.info); + swap(a->cq_base, b->cq_base); + swap(a->cq_base_pa, b->cq_base_pa); + swap(a->cq_size, b->cq_size); +} + +int ionic_reconfigure_queues(struct ionic_lif *lif, + struct ionic_queue_params *qparam) +{ + struct ionic_qcq **tx_qcqs = NULL; + struct ionic_qcq **rx_qcqs = NULL; + unsigned int sg_desc_sz; + unsigned int flags; + int err = -ENOMEM; + unsigned int i; - mutex_lock(&lif->queue_lock); - running = netif_running(lif->netdev); - if (running) { - netif_device_detach(lif->netdev); - err = ionic_stop(lif->netdev); + /* allocate temporary qcq arrays to hold new queue structs */ + if (qparam->nxqs != lif->nxqs || qparam->ntxq_descs != lif->ntxq_descs) { + tx_qcqs = devm_kcalloc(lif->ionic->dev, lif->ionic->ntxqs_per_lif, + sizeof(struct ionic_qcq *), GFP_KERNEL); + if (!tx_qcqs) + goto err_out; + } + if (qparam->nxqs != lif->nxqs || qparam->nrxq_descs != lif->nrxq_descs) { + rx_qcqs = devm_kcalloc(lif->ionic->dev, lif->ionic->nrxqs_per_lif, + sizeof(struct ionic_qcq *), GFP_KERNEL); + if (!rx_qcqs) + goto err_out; + } + + /* allocate new desc_info and rings, but leave the interrupt setup + * until later so as to not mess with the still-running queues + */ + if (lif->qtype_info[IONIC_QTYPE_TXQ].version >= 1 && + lif->qtype_info[IONIC_QTYPE_TXQ].sg_desc_sz == + sizeof(struct ionic_txq_sg_desc_v1)) + sg_desc_sz = sizeof(struct ionic_txq_sg_desc_v1); + else + sg_desc_sz = sizeof(struct ionic_txq_sg_desc); + + if (tx_qcqs) { + for (i = 0; i < qparam->nxqs; i++) { + flags = lif->txqcqs[i]->flags & ~IONIC_QCQ_F_INTR; + err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags, + qparam->ntxq_descs, + sizeof(struct ionic_txq_desc), + sizeof(struct ionic_txq_comp), + sg_desc_sz, + lif->kern_pid, &tx_qcqs[i]); + if (err) + goto err_out; + } + } + + if (rx_qcqs) { + for (i = 0; i < qparam->nxqs; i++) { + flags = lif->rxqcqs[i]->flags & ~IONIC_QCQ_F_INTR; + err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags, + qparam->nrxq_descs, + sizeof(struct ionic_rxq_desc), + sizeof(struct ionic_rxq_comp), + sizeof(struct ionic_rxq_sg_desc), + lif->kern_pid, &rx_qcqs[i]); + if (err) + goto err_out; + } + } + + /* stop and clean the queues */ + ionic_stop_queues_reconfig(lif); + + if (qparam->nxqs != lif->nxqs) { + err = netif_set_real_num_tx_queues(lif->netdev, qparam->nxqs); if (err) - goto reset_out; + goto err_out_reinit_unlock; + err = netif_set_real_num_rx_queues(lif->netdev, qparam->nxqs); + if (err) { + netif_set_real_num_tx_queues(lif->netdev, lif->nxqs); + goto err_out_reinit_unlock; + } } - if (cb) - cb(lif, arg); + /* swap new desc_info and rings, keeping existing interrupt config */ + if (tx_qcqs) { + lif->ntxq_descs = qparam->ntxq_descs; + for (i = 0; i < qparam->nxqs; i++) + ionic_swap_queues(lif->txqcqs[i], tx_qcqs[i]); + } - if (running) { - err = ionic_open(lif->netdev); - netif_device_attach(lif->netdev); + if (rx_qcqs) { + lif->nrxq_descs = qparam->nrxq_descs; + for (i = 0; i < qparam->nxqs; i++) + ionic_swap_queues(lif->rxqcqs[i], rx_qcqs[i]); } -reset_out: - mutex_unlock(&lif->queue_lock); + /* if we need to change the interrupt layout, this is the time */ + if (qparam->intr_split != test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state) || + qparam->nxqs != lif->nxqs) { + if (qparam->intr_split) { + set_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + } else { + clear_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; + lif->tx_coalesce_hw = lif->rx_coalesce_hw; + } + + /* clear existing interrupt assignments */ + for (i = 0; i < lif->ionic->ntxqs_per_lif; i++) { + ionic_qcq_intr_free(lif, lif->txqcqs[i]); + ionic_qcq_intr_free(lif, lif->rxqcqs[i]); + } + + /* re-assign the interrupts */ + for (i = 0; i < qparam->nxqs; i++) { + lif->rxqcqs[i]->flags |= IONIC_QCQ_F_INTR; + err = ionic_alloc_qcq_interrupt(lif, lif->rxqcqs[i]); + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + lif->rxqcqs[i]->intr.index, + lif->rx_coalesce_hw); + + if (qparam->intr_split) { + lif->txqcqs[i]->flags |= IONIC_QCQ_F_INTR; + err = ionic_alloc_qcq_interrupt(lif, lif->txqcqs[i]); + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + lif->txqcqs[i]->intr.index, + lif->tx_coalesce_hw); + } else { + lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_link_qcq_interrupts(lif->rxqcqs[i], lif->txqcqs[i]); + } + } + } + + swap(lif->nxqs, qparam->nxqs); + +err_out_reinit_unlock: + /* re-init the queues, but don't loose an error code */ + if (err) + ionic_start_queues_reconfig(lif); + else + err = ionic_start_queues_reconfig(lif); + +err_out: + /* free old allocs without cleaning intr */ + for (i = 0; i < qparam->nxqs; i++) { + if (tx_qcqs && tx_qcqs[i]) { + tx_qcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, tx_qcqs[i]); + devm_kfree(lif->ionic->dev, tx_qcqs[i]); + tx_qcqs[i] = NULL; + } + if (rx_qcqs && rx_qcqs[i]) { + rx_qcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, rx_qcqs[i]); + devm_kfree(lif->ionic->dev, rx_qcqs[i]); + rx_qcqs[i] = NULL; + } + } + + /* free q array */ + if (rx_qcqs) { + devm_kfree(lif->ionic->dev, rx_qcqs); + rx_qcqs = NULL; + } + if (tx_qcqs) { + devm_kfree(lif->ionic->dev, tx_qcqs); + tx_qcqs = NULL; + } + + /* clean the unused dma and info allocations when new set is smaller + * than the full array, but leave the qcq shells in place + */ + for (i = lif->nxqs; i < lif->ionic->ntxqs_per_lif; i++) { + lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->txqcqs[i]); + + lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->rxqcqs[i]); + } return err; } -static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index) +int ionic_lif_alloc(struct ionic *ionic) { struct device *dev = ionic->dev; union ionic_lif_identity *lid; @@ -2055,7 +2302,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lid = kzalloc(sizeof(*lid), GFP_KERNEL); if (!lid) - return ERR_PTR(-ENOMEM); + return -ENOMEM; netdev = alloc_etherdev_mqs(sizeof(*lif), ionic->ntxqs_per_lif, ionic->ntxqs_per_lif); @@ -2069,7 +2316,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lif = netdev_priv(netdev); lif->netdev = netdev; - ionic->master_lif = lif; + ionic->lif = lif; netdev->netdev_ops = &ionic_netdev_ops; ionic_ethtool_set_ops(netdev); @@ -2079,7 +2326,8 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lif->identity = lid; lif->lif_type = IONIC_LIF_TYPE_CLASSIC; ionic_lif_identify(ionic, lif->lif_type, lif->identity); - lif->netdev->min_mtu = le32_to_cpu(lif->identity->eth.min_frame_size); + lif->netdev->min_mtu = max_t(unsigned int, ETH_MIN_MTU, + le32_to_cpu(lif->identity->eth.min_frame_size)); lif->netdev->max_mtu = le32_to_cpu(lif->identity->eth.max_frame_size) - ETH_HLEN - VLAN_HLEN; @@ -2087,7 +2335,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lif->nxqs = ionic->ntxqs_per_lif; lif->ionic = ionic; - lif->index = index; + lif->index = 0; lif->ntxq_descs = IONIC_DEF_TXRX_DESC; lif->nrxq_descs = IONIC_DEF_TXRX_DESC; lif->tx_budget = IONIC_TX_BUDGET_DEFAULT; @@ -2099,7 +2347,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; lif->tx_coalesce_hw = lif->rx_coalesce_hw; - snprintf(lif->name, sizeof(lif->name), "lif%u", index); + snprintf(lif->name, sizeof(lif->name), "lif%u", lif->index); spin_lock_init(&lif->adminq_lock); @@ -2119,7 +2367,8 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index ionic_debugfs_add_lif(lif); - /* allocate queues */ + /* allocate control queues and txrx queue arrays */ + ionic_lif_queue_identify(lif); err = ionic_qcqs_alloc(lif); if (err) goto err_out_free_lif_info; @@ -2138,9 +2387,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index } netdev_rss_key_fill(lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE); - list_add_tail(&lif->list, &ionic->lifs); - - return lif; + return 0; err_out_free_qcqs: ionic_qcqs_free(lif); @@ -2154,27 +2401,7 @@ err_out_free_netdev: err_out_free_lid: kfree(lid); - return ERR_PTR(err); -} - -int ionic_lifs_alloc(struct ionic *ionic) -{ - struct ionic_lif *lif; - - INIT_LIST_HEAD(&ionic->lifs); - - /* only build the first lif, others are for later features */ - set_bit(0, ionic->lifbits); - - lif = ionic_lif_alloc(ionic, 0); - if (IS_ERR_OR_NULL(lif)) { - clear_bit(0, ionic->lifbits); - return -ENOMEM; - } - - ionic_lif_queue_identify(lif); - - return 0; + return err; } static void ionic_lif_reset(struct ionic_lif *lif) @@ -2209,7 +2436,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif) ionic_txrx_deinit(lif); ionic_txrx_free(lif); } - ionic_lifs_deinit(ionic); + ionic_lif_deinit(lif); ionic_reset(ionic); ionic_qcqs_free(lif); @@ -2232,7 +2459,7 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) if (err) goto err_out; - err = ionic_lifs_init(ionic); + err = ionic_lif_init(lif); if (err) goto err_qcqs_free; @@ -2261,14 +2488,14 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) err_txrx_free: ionic_txrx_free(lif); err_lifs_deinit: - ionic_lifs_deinit(ionic); + ionic_lif_deinit(lif); err_qcqs_free: ionic_qcqs_free(lif); err_out: dev_err(ionic->dev, "FW Up: LIFs restart failed - err %d\n", err); } -static void ionic_lif_free(struct ionic_lif *lif) +void ionic_lif_free(struct ionic_lif *lif) { struct device *dev = lif->ionic->dev; @@ -2297,23 +2524,10 @@ static void ionic_lif_free(struct ionic_lif *lif) /* free netdev & lif */ ionic_debugfs_del_lif(lif); - list_del(&lif->list); free_netdev(lif->netdev); } -void ionic_lifs_free(struct ionic *ionic) -{ - struct list_head *cur, *tmp; - struct ionic_lif *lif; - - list_for_each_safe(cur, tmp, &ionic->lifs) { - lif = list_entry(cur, struct ionic_lif, list); - - ionic_lif_free(lif); - } -} - -static void ionic_lif_deinit(struct ionic_lif *lif) +void ionic_lif_deinit(struct ionic_lif *lif) { if (!test_and_clear_bit(IONIC_LIF_F_INITED, lif->state)) return; @@ -2334,17 +2548,6 @@ static void ionic_lif_deinit(struct ionic_lif *lif) ionic_lif_reset(lif); } -void ionic_lifs_deinit(struct ionic *ionic) -{ - struct list_head *cur, *tmp; - struct ionic_lif *lif; - - list_for_each_safe(cur, tmp, &ionic->lifs) { - lif = list_entry(cur, struct ionic_lif, list); - ionic_lif_deinit(lif); - } -} - static int ionic_lif_adminq_init(struct ionic_lif *lif) { struct device *dev = lif->ionic->dev; @@ -2490,7 +2693,7 @@ static int ionic_station_set(struct ionic_lif *lif) return 0; } -static int ionic_lif_init(struct ionic_lif *lif) +int ionic_lif_init(struct ionic_lif *lif) { struct ionic_dev *idev = &lif->ionic->idev; struct device *dev = lif->ionic->dev; @@ -2580,22 +2783,6 @@ err_out_free_dbid: return err; } -int ionic_lifs_init(struct ionic *ionic) -{ - struct list_head *cur, *tmp; - struct ionic_lif *lif; - int err; - - list_for_each_safe(cur, tmp, &ionic->lifs) { - lif = list_entry(cur, struct ionic_lif, list); - err = ionic_lif_init(lif); - if (err) - return err; - } - - return 0; -} - static void ionic_lif_notify_work(struct work_struct *ws) { } @@ -2644,45 +2831,41 @@ static int ionic_lif_notify(struct notifier_block *nb, return NOTIFY_DONE; } -int ionic_lifs_register(struct ionic *ionic) +int ionic_lif_register(struct ionic_lif *lif) { int err; - INIT_WORK(&ionic->nb_work, ionic_lif_notify_work); + INIT_WORK(&lif->ionic->nb_work, ionic_lif_notify_work); - ionic->nb.notifier_call = ionic_lif_notify; + lif->ionic->nb.notifier_call = ionic_lif_notify; - err = register_netdevice_notifier(&ionic->nb); + err = register_netdevice_notifier(&lif->ionic->nb); if (err) - ionic->nb.notifier_call = NULL; + lif->ionic->nb.notifier_call = NULL; /* only register LIF0 for now */ - err = register_netdev(ionic->master_lif->netdev); + err = register_netdev(lif->netdev); if (err) { - dev_err(ionic->dev, "Cannot register net device, aborting\n"); + dev_err(lif->ionic->dev, "Cannot register net device, aborting\n"); return err; } - ionic->master_lif->registered = true; - ionic_lif_set_netdev_info(ionic->master_lif); + lif->registered = true; + ionic_lif_set_netdev_info(lif); return 0; } -void ionic_lifs_unregister(struct ionic *ionic) +void ionic_lif_unregister(struct ionic_lif *lif) { - if (ionic->nb.notifier_call) { - unregister_netdevice_notifier(&ionic->nb); - cancel_work_sync(&ionic->nb_work); - ionic->nb.notifier_call = NULL; + if (lif->ionic->nb.notifier_call) { + unregister_netdevice_notifier(&lif->ionic->nb); + cancel_work_sync(&lif->ionic->nb_work); + lif->ionic->nb.notifier_call = NULL; } - /* There is only one lif ever registered in the - * current model, so don't bother searching the - * ionic->lif for candidates to unregister - */ - if (ionic->master_lif && - ionic->master_lif->netdev->reg_state == NETREG_REGISTERED) - unregister_netdev(ionic->master_lif->netdev); + if (lif->netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(lif->netdev); + lif->registered = false; } static void ionic_lif_queue_identify(struct ionic_lif *lif) @@ -2801,7 +2984,7 @@ int ionic_lif_identify(struct ionic *ionic, u8 lif_type, return 0; } -int ionic_lifs_size(struct ionic *ionic) +int ionic_lif_size(struct ionic *ionic) { struct ionic_identity *ident = &ionic->ident; unsigned int nintrs, dev_nintrs; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 1ee3b14c8d50..11ea9e0c6a4a 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -16,32 +16,32 @@ #define IONIC_TX_BUDGET_DEFAULT 256 struct ionic_tx_stats { - u64 dma_map_err; u64 pkts; u64 bytes; - u64 clean; - u64 linearize; u64 csum_none; u64 csum; - u64 crc32_csum; u64 tso; u64 tso_bytes; u64 frags; u64 vlan_inserted; + u64 clean; + u64 linearize; + u64 crc32_csum; u64 sg_cntr[IONIC_MAX_NUM_SG_CNTR]; + u64 dma_map_err; }; struct ionic_rx_stats { - u64 dma_map_err; - u64 alloc_err; u64 pkts; u64 bytes; u64 csum_none; u64 csum_complete; - u64 csum_error; u64 buffers_posted; u64 dropped; u64 vlan_stripped; + u64 csum_error; + u64 dma_map_err; + u64 alloc_err; }; #define IONIC_QCQ_F_INITED BIT(0) @@ -56,35 +56,28 @@ struct ionic_napi_stats { u64 work_done_cntr[IONIC_MAX_NUM_NAPI_CNTR]; }; -struct ionic_q_stats { - union { - struct ionic_tx_stats tx; - struct ionic_rx_stats rx; - }; -}; - struct ionic_qcq { - void *base; - dma_addr_t base_pa; - unsigned int total_size; + void *q_base; + dma_addr_t q_base_pa; + u32 q_size; + void *cq_base; + dma_addr_t cq_base_pa; + u32 cq_size; + void *sg_base; + dma_addr_t sg_base_pa; + u32 sg_size; struct ionic_queue q; struct ionic_cq cq; struct ionic_intr_info intr; struct napi_struct napi; struct ionic_napi_stats napi_stats; - struct ionic_q_stats *stats; unsigned int flags; struct dentry *dentry; }; -struct ionic_qcqst { - struct ionic_qcq *qcq; - struct ionic_q_stats *stats; -}; - #define q_to_qcq(q) container_of(q, struct ionic_qcq, q) -#define q_to_tx_stats(q) (&q_to_qcq(q)->stats->tx) -#define q_to_rx_stats(q) (&q_to_qcq(q)->stats->rx) +#define q_to_tx_stats(q) (&(q)->lif->txqstats[(q)->index]) +#define q_to_rx_stats(q) (&(q)->lif->rxqstats[(q)->index]) #define napi_to_qcq(napi) container_of(napi, struct ionic_qcq, napi) #define napi_to_cq(napi) (&napi_to_qcq(napi)->cq) @@ -170,8 +163,10 @@ struct ionic_lif { spinlock_t adminq_lock; /* lock for AdminQ operations */ struct ionic_qcq *adminqcq; struct ionic_qcq *notifyqcq; - struct ionic_qcqst *txqcqs; - struct ionic_qcqst *rxqcqs; + struct ionic_qcq **txqcqs; + struct ionic_tx_stats *txqstats; + struct ionic_qcq **rxqcqs; + struct ionic_rx_stats *rxqstats; u64 last_eid; unsigned int neqs; unsigned int nxqs; @@ -212,12 +207,21 @@ struct ionic_lif { struct work_struct tx_timeout_work; }; -#define lif_to_txqcq(lif, i) ((lif)->txqcqs[i].qcq) -#define lif_to_rxqcq(lif, i) ((lif)->rxqcqs[i].qcq) -#define lif_to_txstats(lif, i) ((lif)->txqcqs[i].stats->tx) -#define lif_to_rxstats(lif, i) ((lif)->rxqcqs[i].stats->rx) -#define lif_to_txq(lif, i) (&lif_to_txqcq((lif), i)->q) -#define lif_to_rxq(lif, i) (&lif_to_txqcq((lif), i)->q) +struct ionic_queue_params { + unsigned int nxqs; + unsigned int ntxq_descs; + unsigned int nrxq_descs; + unsigned int intr_split; +}; + +static inline void ionic_init_queue_params(struct ionic_lif *lif, + struct ionic_queue_params *qparam) +{ + qparam->nxqs = lif->nxqs; + qparam->ntxq_descs = lif->ntxq_descs; + qparam->nrxq_descs = lif->nrxq_descs; + qparam->intr_split = test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); +} static inline u32 ionic_coal_usec_to_hw(struct ionic *ionic, u32 usecs) { @@ -242,34 +246,33 @@ void ionic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *ns); void ionic_lif_deferred_enqueue(struct ionic_deferred *def, struct ionic_deferred_work *work); -int ionic_lifs_alloc(struct ionic *ionic); -void ionic_lifs_free(struct ionic *ionic); -void ionic_lifs_deinit(struct ionic *ionic); -int ionic_lifs_init(struct ionic *ionic); -int ionic_lifs_register(struct ionic *ionic); -void ionic_lifs_unregister(struct ionic *ionic); +int ionic_lif_alloc(struct ionic *ionic); +int ionic_lif_init(struct ionic_lif *lif); +void ionic_lif_free(struct ionic_lif *lif); +void ionic_lif_deinit(struct ionic_lif *lif); +int ionic_lif_register(struct ionic_lif *lif); +void ionic_lif_unregister(struct ionic_lif *lif); int ionic_lif_identify(struct ionic *ionic, u8 lif_type, union ionic_lif_identity *lif_ident); -int ionic_lifs_size(struct ionic *ionic); +int ionic_lif_size(struct ionic *ionic); int ionic_lif_rss_config(struct ionic_lif *lif, u16 types, const u8 *key, const u32 *indir); +int ionic_reconfigure_queues(struct ionic_lif *lif, + struct ionic_queue_params *qparam); -int ionic_open(struct net_device *netdev); -int ionic_stop(struct net_device *netdev); -int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg); - -static inline void debug_stats_txq_post(struct ionic_qcq *qcq, - struct ionic_txq_desc *desc, bool dbell) +static inline void debug_stats_txq_post(struct ionic_queue *q, bool dbell) { - u8 num_sg_elems = ((le64_to_cpu(desc->cmd) >> IONIC_TXQ_DESC_NSGE_SHIFT) - & IONIC_TXQ_DESC_NSGE_MASK); + struct ionic_txq_desc *desc = &q->txq[q->head_idx]; + u8 num_sg_elems; - qcq->q.dbell_count += dbell; + q->dbell_count += dbell; + num_sg_elems = ((le64_to_cpu(desc->cmd) >> IONIC_TXQ_DESC_NSGE_SHIFT) + & IONIC_TXQ_DESC_NSGE_MASK); if (num_sg_elems > (IONIC_MAX_NUM_SG_CNTR - 1)) num_sg_elems = IONIC_MAX_NUM_SG_CNTR - 1; - qcq->stats->tx.sg_cntr[num_sg_elems]++; + q->lif->txqstats[q->index].sg_cntr[num_sg_elems]++; } static inline void debug_stats_napi_poll(struct ionic_qcq *qcq, @@ -284,10 +287,9 @@ static inline void debug_stats_napi_poll(struct ionic_qcq *qcq, } #define DEBUG_STATS_CQE_CNT(cq) ((cq)->compl_count++) -#define DEBUG_STATS_RX_BUFF_CNT(qcq) ((qcq)->stats->rx.buffers_posted++) +#define DEBUG_STATS_RX_BUFF_CNT(q) ((q)->lif->rxqstats[q->index].buffers_posted++) #define DEBUG_STATS_INTR_REARM(intr) ((intr)->rearm_count++) -#define DEBUG_STATS_TXQ_POST(qcq, txdesc, dbell) \ - debug_stats_txq_post(qcq, txdesc, dbell) +#define DEBUG_STATS_TXQ_POST(q, dbell) debug_stats_txq_post(q, dbell) #define DEBUG_STATS_NAPI_POLL(qcq, work_done) \ debug_stats_napi_poll(qcq, work_done) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index df5b9bcc3aba..cfb90bf605fe 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -181,15 +181,17 @@ static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode) static void ionic_adminq_flush(struct ionic_lif *lif) { - struct ionic_queue *adminq = &lif->adminqcq->q; + struct ionic_queue *q = &lif->adminqcq->q; + struct ionic_desc_info *desc_info; spin_lock(&lif->adminq_lock); - while (adminq->tail != adminq->head) { - memset(adminq->tail->desc, 0, sizeof(union ionic_adminq_cmd)); - adminq->tail->cb = NULL; - adminq->tail->cb_arg = NULL; - adminq->tail = adminq->tail->next; + while (q->tail_idx != q->head_idx) { + desc_info = &q->info[q->tail_idx]; + memset(desc_info->desc, 0, sizeof(union ionic_adminq_cmd)); + desc_info->cb = NULL; + desc_info->cb_arg = NULL; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); } spin_unlock(&lif->adminq_lock); } @@ -245,7 +247,8 @@ static void ionic_adminq_cb(struct ionic_queue *q, static int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) { - struct ionic_queue *adminq; + struct ionic_desc_info *desc_info; + struct ionic_queue *q; int err = 0; WARN_ON(in_interrupt()); @@ -253,10 +256,10 @@ static int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) if (!lif->adminqcq) return -EIO; - adminq = &lif->adminqcq->q; + q = &lif->adminqcq->q; spin_lock(&lif->adminq_lock); - if (!ionic_q_has_space(adminq, 1)) { + if (!ionic_q_has_space(q, 1)) { err = -ENOSPC; goto err_out; } @@ -265,13 +268,14 @@ static int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) if (err) goto err_out; - memcpy(adminq->head->desc, &ctx->cmd, sizeof(ctx->cmd)); + desc_info = &q->info[q->head_idx]; + memcpy(desc_info->desc, &ctx->cmd, sizeof(ctx->cmd)); dev_dbg(&lif->netdev->dev, "post admin queue command:\n"); dynamic_hex_dump("cmd ", DUMP_PREFIX_OFFSET, 16, 1, &ctx->cmd, sizeof(ctx->cmd), true); - ionic_q_post(adminq, true, ionic_adminq_cb, ctx); + ionic_q_post(q, true, ionic_adminq_cb, ctx); err_out: spin_unlock(&lif->adminq_lock); @@ -301,32 +305,6 @@ int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) return ionic_adminq_check_err(lif, ctx, (remaining == 0)); } -int ionic_napi(struct napi_struct *napi, int budget, ionic_cq_cb cb, - ionic_cq_done_cb done_cb, void *done_arg) -{ - struct ionic_qcq *qcq = napi_to_qcq(napi); - struct ionic_cq *cq = &qcq->cq; - u32 work_done, flags = 0; - - work_done = ionic_cq_service(cq, budget, cb, done_cb, done_arg); - - if (work_done < budget && napi_complete_done(napi, work_done)) { - flags |= IONIC_INTR_CRED_UNMASK; - DEBUG_STATS_INTR_REARM(cq->bound_intr); - } - - if (work_done || flags) { - flags |= IONIC_INTR_CRED_RESET_COALESCE; - ionic_intr_credits(cq->lif->ionic->idev.intr_ctrl, - cq->bound_intr->index, - work_done, flags); - } - - DEBUG_STATS_NAPI_POLL(qcq, work_done); - - return work_done; -} - static void ionic_dev_cmd_clean(struct ionic *ionic) { union ionic_dev_cmd_regs *regs = ionic->idev.dev_cmd_regs; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c index 2a1885da58a6..ff20a2ac4c2f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c @@ -179,36 +179,28 @@ static const struct ionic_stat_desc ionic_dbg_napi_stats_desc[] = { static void ionic_get_lif_stats(struct ionic_lif *lif, struct ionic_lif_sw_stats *stats) { - struct ionic_tx_stats *tstats; - struct ionic_rx_stats *rstats; + struct ionic_tx_stats *txstats; + struct ionic_rx_stats *rxstats; struct rtnl_link_stats64 ns; - struct ionic_qcq *txqcq; - struct ionic_qcq *rxqcq; int q_num; memset(stats, 0, sizeof(*stats)); for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - txqcq = lif_to_txqcq(lif, q_num); - if (txqcq && txqcq->stats) { - tstats = &txqcq->stats->tx; - stats->tx_packets += tstats->pkts; - stats->tx_bytes += tstats->bytes; - stats->tx_tso += tstats->tso; - stats->tx_tso_bytes += tstats->tso_bytes; - stats->tx_csum_none += tstats->csum_none; - stats->tx_csum += tstats->csum; - } - - rxqcq = lif_to_rxqcq(lif, q_num); - if (rxqcq && rxqcq->stats) { - rstats = &rxqcq->stats->rx; - stats->rx_packets += rstats->pkts; - stats->rx_bytes += rstats->bytes; - stats->rx_csum_none += rstats->csum_none; - stats->rx_csum_complete += rstats->csum_complete; - stats->rx_csum_error += rstats->csum_error; - } + txstats = &lif->txqstats[q_num]; + stats->tx_packets += txstats->pkts; + stats->tx_bytes += txstats->bytes; + stats->tx_tso += txstats->tso; + stats->tx_tso_bytes += txstats->tso_bytes; + stats->tx_csum_none += txstats->csum_none; + stats->tx_csum += txstats->csum; + + rxstats = &lif->rxqstats[q_num]; + stats->rx_packets += rxstats->pkts; + stats->rx_bytes += rxstats->bytes; + stats->rx_csum_none += rxstats->csum_none; + stats->rx_csum_complete += rxstats->csum_complete; + stats->rx_csum_error += rxstats->csum_error; } ionic_get_stats64(lif->netdev, &ns); @@ -371,7 +363,7 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) } for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - txstats = &lif_to_txstats(lif, q_num); + txstats = &lif->txqstats[q_num]; for (i = 0; i < IONIC_NUM_TX_STATS; i++) { **buf = IONIC_READ_STAT64(txstats, @@ -381,7 +373,7 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) if (test_bit(IONIC_LIF_F_UP, lif->state) && test_bit(IONIC_LIF_F_SW_DEBUG_STATS, lif->state)) { - txqcq = lif_to_txqcq(lif, q_num); + txqcq = lif->txqcqs[q_num]; for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { **buf = IONIC_READ_STAT64(&txqcq->q, &ionic_txq_stats_desc[i]); @@ -405,7 +397,7 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) } for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - rxstats = &lif_to_rxstats(lif, q_num); + rxstats = &lif->rxqstats[q_num]; for (i = 0; i < IONIC_NUM_RX_STATS; i++) { **buf = IONIC_READ_STAT64(rxstats, @@ -415,7 +407,7 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) if (test_bit(IONIC_LIF_F_UP, lif->state) && test_bit(IONIC_LIF_F_SW_DEBUG_STATS, lif->state)) { - rxqcq = lif_to_rxqcq(lif, q_num); + rxqcq = lif->rxqcqs[q_num]; for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { **buf = IONIC_READ_STAT64(&rxqcq->cq, &ionic_dbg_cq_stats_desc[i]); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 8107d32c2767..7225251c5563 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -22,7 +22,7 @@ static bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell, ionic_desc_cb cb_func, void *cb_arg) { - DEBUG_STATS_TXQ_POST(q_to_qcq(q), q->head->desc, ring_dbell); + DEBUG_STATS_TXQ_POST(q, ring_dbell); ionic_q_post(q, ring_dbell, cb_func, cb_arg); } @@ -32,7 +32,7 @@ static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell, { ionic_q_post(q, ring_dbell, cb_func, cb_arg); - DEBUG_STATS_RX_BUFF_CNT(q_to_qcq(q)); + DEBUG_STATS_RX_BUFF_CNT(q); } static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q) @@ -49,7 +49,7 @@ static struct sk_buff *ionic_rx_skb_alloc(struct ionic_queue *q, struct sk_buff *skb; netdev = lif->netdev; - stats = q_to_rx_stats(q); + stats = &q->lif->rxqstats[q->index]; if (frags) skb = napi_get_frags(&q_to_qcq(q)->napi); @@ -235,14 +235,14 @@ static bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) return false; /* check for empty queue */ - if (q->tail->index == q->head->index) + if (q->tail_idx == q->head_idx) return false; - desc_info = q->tail; - if (desc_info->index != le16_to_cpu(comp->comp_index)) + if (q->tail_idx != le16_to_cpu(comp->comp_index)) return false; - q->tail = desc_info->next; + desc_info = &q->info[q->tail_idx]; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); /* clean the related q entry, only one per qc completion */ ionic_rx_clean(q, desc_info, cq_info, desc_info->cb_arg); @@ -266,40 +266,49 @@ void ionic_rx_flush(struct ionic_cq *cq) work_done, IONIC_INTR_CRED_RESET_COALESCE); } -static struct page *ionic_rx_page_alloc(struct ionic_queue *q, - dma_addr_t *dma_addr) +static int ionic_rx_page_alloc(struct ionic_queue *q, + struct ionic_page_info *page_info) { struct ionic_lif *lif = q->lif; struct ionic_rx_stats *stats; struct net_device *netdev; struct device *dev; - struct page *page; netdev = lif->netdev; dev = lif->ionic->dev; stats = q_to_rx_stats(q); - page = alloc_page(GFP_ATOMIC); - if (unlikely(!page)) { - net_err_ratelimited("%s: Page alloc failed on %s!\n", + + if (unlikely(!page_info)) { + net_err_ratelimited("%s: %s invalid page_info in alloc\n", + netdev->name, q->name); + return -EINVAL; + } + + page_info->page = dev_alloc_page(); + if (unlikely(!page_info->page)) { + net_err_ratelimited("%s: %s page alloc failed\n", netdev->name, q->name); stats->alloc_err++; - return NULL; + return -ENOMEM; } - *dma_addr = dma_map_page(dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(dev, *dma_addr))) { - __free_page(page); - net_err_ratelimited("%s: DMA single map failed on %s!\n", + page_info->dma_addr = dma_map_page(dev, page_info->page, 0, PAGE_SIZE, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(dev, page_info->dma_addr))) { + put_page(page_info->page); + page_info->dma_addr = 0; + page_info->page = NULL; + net_err_ratelimited("%s: %s dma map failed\n", netdev->name, q->name); stats->dma_map_err++; - return NULL; + return -EIO; } - return page; + return 0; } -static void ionic_rx_page_free(struct ionic_queue *q, struct page *page, - dma_addr_t dma_addr) +static void ionic_rx_page_free(struct ionic_queue *q, + struct ionic_page_info *page_info) { struct ionic_lif *lif = q->lif; struct net_device *netdev; @@ -308,15 +317,23 @@ static void ionic_rx_page_free(struct ionic_queue *q, struct page *page, netdev = lif->netdev; dev = lif->ionic->dev; - if (unlikely(!page)) { - net_err_ratelimited("%s: Trying to free unallocated buffer on %s!\n", + if (unlikely(!page_info)) { + net_err_ratelimited("%s: %s invalid page_info in free\n", netdev->name, q->name); return; } - dma_unmap_page(dev, dma_addr, PAGE_SIZE, DMA_FROM_DEVICE); + if (unlikely(!page_info->page)) { + net_err_ratelimited("%s: %s invalid page in free\n", + netdev->name, q->name); + return; + } + + dma_unmap_page(dev, page_info->dma_addr, PAGE_SIZE, DMA_FROM_DEVICE); - __free_page(page); + put_page(page_info->page); + page_info->dma_addr = 0; + page_info->page = NULL; } void ionic_rx_fill(struct ionic_queue *q) @@ -338,7 +355,7 @@ void ionic_rx_fill(struct ionic_queue *q) for (i = ionic_q_space_avail(q); i; i--) { remain_len = len; - desc_info = q->head; + desc_info = &q->info[q->head_idx]; desc = desc_info->desc; sg_desc = desc_info->sg_desc; page_info = &desc_info->pages[0]; @@ -352,8 +369,7 @@ void ionic_rx_fill(struct ionic_queue *q) desc->opcode = (nfrags > 1) ? IONIC_RXQ_DESC_OPCODE_SG : IONIC_RXQ_DESC_OPCODE_SIMPLE; desc_info->npages = nfrags; - page_info->page = ionic_rx_page_alloc(q, &page_info->dma_addr); - if (unlikely(!page_info->page)) { + if (unlikely(ionic_rx_page_alloc(q, page_info))) { desc->addr = 0; desc->len = 0; return; @@ -370,8 +386,7 @@ void ionic_rx_fill(struct ionic_queue *q) continue; sg_elem = &sg_desc->elems[j]; - page_info->page = ionic_rx_page_alloc(q, &page_info->dma_addr); - if (unlikely(!page_info->page)) { + if (unlikely(ionic_rx_page_alloc(q, page_info))) { sg_elem->addr = 0; sg_elem->len = 0; return; @@ -387,7 +402,7 @@ void ionic_rx_fill(struct ionic_queue *q) } ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, - q->dbval | q->head->index); + q->dbval | q->head_idx); } static void ionic_rx_fill_cb(void *arg) @@ -397,25 +412,23 @@ static void ionic_rx_fill_cb(void *arg) void ionic_rx_empty(struct ionic_queue *q) { - struct ionic_desc_info *cur; + struct ionic_desc_info *desc_info; struct ionic_rxq_desc *desc; unsigned int i; + u16 idx; - for (cur = q->tail; cur != q->head; cur = cur->next) { - desc = cur->desc; + idx = q->tail_idx; + while (idx != q->head_idx) { + desc_info = &q->info[idx]; + desc = desc_info->desc; desc->addr = 0; desc->len = 0; - for (i = 0; i < cur->npages; i++) { - if (likely(cur->pages[i].page)) { - ionic_rx_page_free(q, cur->pages[i].page, - cur->pages[i].dma_addr); - cur->pages[i].page = NULL; - cur->pages[i].dma_addr = 0; - } - } + for (i = 0; i < desc_info->npages; i++) + ionic_rx_page_free(q, &desc_info->pages[i]); - cur->cb_arg = NULL; + desc_info->cb_arg = NULL; + idx = (idx + 1) & (q->num_descs - 1); } } @@ -496,13 +509,11 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) struct ionic_cq *txcq; u32 rx_work_done = 0; u32 tx_work_done = 0; - u32 work_done = 0; u32 flags = 0; - bool unmask; lif = rxcq->bound_q->lif; idev = &lif->ionic->idev; - txcq = &lif->txqcqs[qi].qcq->cq; + txcq = &lif->txqcqs[qi]->cq; tx_work_done = ionic_cq_service(txcq, lif->tx_budget, ionic_tx_service, NULL, NULL); @@ -512,17 +523,12 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) if (rx_work_done) ionic_rx_fill_cb(rxcq->bound_q); - unmask = (rx_work_done < budget) && (tx_work_done < lif->tx_budget); - - if (unmask && napi_complete_done(napi, rx_work_done)) { + if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) { flags |= IONIC_INTR_CRED_UNMASK; DEBUG_STATS_INTR_REARM(rxcq->bound_intr); - work_done = rx_work_done; - } else { - work_done = budget; } - if (work_done || flags) { + if (rx_work_done || flags) { flags |= IONIC_INTR_CRED_RESET_COALESCE; ionic_intr_credits(idev->intr_ctrl, rxcq->bound_intr->index, tx_work_done + rx_work_done, flags); @@ -531,7 +537,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) DEBUG_STATS_NAPI_POLL(qcq, rx_work_done); DEBUG_STATS_NAPI_POLL(qcq, tx_work_done); - return work_done; + return rx_work_done; } static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, @@ -622,6 +628,7 @@ static bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) struct ionic_txq_comp *comp = cq_info->cq_desc; struct ionic_queue *q = cq->bound_q; struct ionic_desc_info *desc_info; + u16 index; if (!color_match(comp->color, cq->done_color)) return false; @@ -630,12 +637,13 @@ static bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) * several q entries completed for each cq completion */ do { - desc_info = q->tail; - q->tail = desc_info->next; - ionic_tx_clean(q, desc_info, cq->tail, desc_info->cb_arg); + desc_info = &q->info[q->tail_idx]; + index = q->tail_idx; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); + ionic_tx_clean(q, desc_info, cq_info, desc_info->cb_arg); desc_info->cb = NULL; desc_info->cb_arg = NULL; - } while (desc_info->index != le16_to_cpu(comp->comp_index)); + } while (index != le16_to_cpu(comp->comp_index)); return true; } @@ -655,16 +663,14 @@ void ionic_tx_flush(struct ionic_cq *cq) void ionic_tx_empty(struct ionic_queue *q) { struct ionic_desc_info *desc_info; - int done = 0; /* walk the not completed tx entries, if any */ - while (q->head != q->tail) { - desc_info = q->tail; - q->tail = desc_info->next; + while (q->head_idx != q->tail_idx) { + desc_info = &q->info[q->tail_idx]; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); ionic_tx_clean(q, desc_info, NULL, desc_info->cb_arg); desc_info->cb = NULL; desc_info->cb_arg = NULL; - done++; } } @@ -748,8 +754,8 @@ static void ionic_tx_tso_post(struct ionic_queue *q, struct ionic_txq_desc *desc static struct ionic_txq_desc *ionic_tx_tso_next(struct ionic_queue *q, struct ionic_txq_sg_elem **elem) { - struct ionic_txq_sg_desc *sg_desc = q->head->sg_desc; - struct ionic_txq_desc *desc = q->head->desc; + struct ionic_txq_sg_desc *sg_desc = q->info[q->head_idx].txq_sg_desc; + struct ionic_txq_desc *desc = q->info[q->head_idx].txq_desc; *elem = sg_desc->elems; return desc; @@ -758,13 +764,13 @@ static struct ionic_txq_desc *ionic_tx_tso_next(struct ionic_queue *q, static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) { struct ionic_tx_stats *stats = q_to_tx_stats(q); - struct ionic_desc_info *abort = q->head; + struct ionic_desc_info *rewind_desc_info; struct device *dev = q->lif->ionic->dev; - struct ionic_desc_info *rewind = abort; struct ionic_txq_sg_elem *elem; struct ionic_txq_desc *desc; unsigned int frag_left = 0; unsigned int offset = 0; + u16 abort = q->head_idx; unsigned int len_left; dma_addr_t desc_addr; unsigned int hdrlen; @@ -772,6 +778,7 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) unsigned int seglen; u64 total_bytes = 0; u64 total_pkts = 0; + u16 rewind = abort; unsigned int left; unsigned int len; unsigned int mss; @@ -916,19 +923,20 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) return 0; err_out_abort: - while (rewind->desc != q->head->desc) { - ionic_tx_clean(q, rewind, NULL, NULL); - rewind = rewind->next; + while (rewind != q->head_idx) { + rewind_desc_info = &q->info[rewind]; + ionic_tx_clean(q, rewind_desc_info, NULL, NULL); + rewind = (rewind + 1) & (q->num_descs - 1); } - q->head = abort; + q->head_idx = abort; return -ENOMEM; } static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb) { + struct ionic_txq_desc *desc = q->info[q->head_idx].txq_desc; struct ionic_tx_stats *stats = q_to_tx_stats(q); - struct ionic_txq_desc *desc = q->head->desc; struct device *dev = q->lif->ionic->dev; dma_addr_t dma_addr; bool has_vlan; @@ -967,8 +975,8 @@ static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb) static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb) { + struct ionic_txq_desc *desc = q->info[q->head_idx].txq_desc; struct ionic_tx_stats *stats = q_to_tx_stats(q); - struct ionic_txq_desc *desc = q->head->desc; struct device *dev = q->lif->ionic->dev; dma_addr_t dma_addr; bool has_vlan; @@ -1002,7 +1010,7 @@ static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb) static int ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb) { - struct ionic_txq_sg_desc *sg_desc = q->head->sg_desc; + struct ionic_txq_sg_desc *sg_desc = q->info[q->head_idx].txq_sg_desc; unsigned int len_left = skb->len - skb_headlen(skb); struct ionic_txq_sg_elem *elem = sg_desc->elems; struct ionic_tx_stats *stats = q_to_tx_stats(q); @@ -1111,9 +1119,9 @@ netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } - if (unlikely(!lif_to_txqcq(lif, queue_index))) + if (unlikely(queue_index >= lif->nxqs)) queue_index = 0; - q = lif_to_txq(lif, queue_index); + q = &lif->txqcqs[queue_index]->q; ndescs = ionic_tx_descs_needed(q, skb); if (ndescs < 0) diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig index 8f743d80760b..4366c7a8de95 100644 --- a/drivers/net/ethernet/qlogic/Kconfig +++ b/drivers/net/ethernet/qlogic/Kconfig @@ -80,7 +80,7 @@ config QED select CRC8 select NET_DEVLINK help - This enables the support for ... + This enables the support for Marvell FastLinQ adapters family. config QED_LL2 bool @@ -100,7 +100,8 @@ config QEDE depends on QED imply PTP_1588_CLOCK help - This enables the support for ... + This enables the support for Marvell FastLinQ adapters family, + ethernet driver. config QED_RDMA bool diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c index 66f45fce90fa..c3f50ddbe824 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c @@ -153,7 +153,7 @@ skip: case NETXEN_BRDTYPE_P3_4_GB_MM: supported |= SUPPORTED_Autoneg; advertising |= ADVERTISED_Autoneg; - /* fall through */ + fallthrough; case NETXEN_BRDTYPE_P2_SB31_10G_CX4: case NETXEN_BRDTYPE_P3_10G_CX4: case NETXEN_BRDTYPE_P3_10G_CX4_LP: @@ -182,7 +182,7 @@ skip: supported |= SUPPORTED_TP; check_sfp_module = netif_running(dev) && adapter->has_link_events; - /* fall through */ + fallthrough; case NETXEN_BRDTYPE_P2_SB31_10G: case NETXEN_BRDTYPE_P3_10G_XFP: supported |= SUPPORTED_FIBRE; diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile index f947b105cf14..8251755ec18c 100644 --- a/drivers/net/ethernet/qlogic/qed/Makefile +++ b/drivers/net/ethernet/qlogic/qed/Makefile @@ -9,6 +9,7 @@ qed-y := \ qed_dcbx.o \ qed_debug.o \ qed_dev.o \ + qed_devlink.o \ qed_hw.o \ qed_init_fw_funcs.o \ qed_init_ops.o \ diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index b2a7b53ee760..f34b25a79449 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -807,6 +807,7 @@ struct qed_dev { struct qed_llh_info *p_llh_info; /* Linux specific here */ + struct qed_dev_info common_dev_info; struct qede_dev *edev; struct pci_dev *pdev; u32 flags; @@ -849,7 +850,6 @@ struct qed_dev { u32 rdma_max_srq_sge; u16 tunn_feature_mask; - struct devlink *dl; bool iwarp_cmt; }; @@ -981,6 +981,7 @@ void qed_bw_update(struct qed_hwfn *hwfn, struct qed_ptt *ptt); u32 qed_unzip_data(struct qed_hwfn *p_hwfn, u32 input_len, u8 *input_buf, u32 max_size, u8 *unzip_buf); +int qed_recovery_process(struct qed_dev *cdev); void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn); void qed_hw_error_occurred(struct qed_hwfn *p_hwfn, enum qed_hw_err_type err_type); diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 876743a79c1f..0e4cd8890cff 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -2046,7 +2046,7 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) rdma_tasks); /* no need for break since RoCE coexist with Ethernet */ } - /* fall through */ + fallthrough; case QED_PCI_ETH: { struct qed_eth_pf_params *p_params = diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index b3c9ebaf2280..f7f08e6a3acf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -3109,14 +3109,14 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) p_hwfn->hw_info.hw_mode); if (rc) break; - /* Fall through */ + fallthrough; case FW_MSG_CODE_DRV_LOAD_PORT: rc = qed_hw_init_port(p_hwfn, p_hwfn->p_main_ptt, p_hwfn->hw_info.hw_mode); if (rc) break; - /* Fall through */ + fallthrough; case FW_MSG_CODE_DRV_LOAD_FUNCTION: rc = qed_hw_init_pf(p_hwfn, p_hwfn->p_main_ptt, p_params->p_tunn, @@ -3973,6 +3973,7 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) struct qed_mcp_link_speed_params *ext_speed; struct qed_mcp_link_capabilities *p_caps; struct qed_mcp_link_params *link; + int i; /* Read global nvm_cfg address */ nvm_cfg_addr = qed_rd(p_hwfn, p_ptt, MISC_REG_GEN_PURP_CR0); @@ -4290,6 +4291,14 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) __set_bit(QED_DEV_CAP_ROCE, &p_hwfn->hw_info.device_capabilities); + /* Read device serial number information from shmem */ + addr = MCP_REG_SCRATCH + nvm_cfg1_offset + + offsetof(struct nvm_cfg1, glob) + + offsetof(struct nvm_cfg1_glob, serial_number); + + for (i = 0; i < 4; i++) + p_hwfn->hw_info.part_num[i] = qed_rd(p_hwfn, p_ptt, addr + i * 4); + return qed_mcp_fill_shmem_func_info(p_hwfn, p_ptt); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c new file mode 100644 index 000000000000..cf7f4da68e69 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Marvell/Qlogic FastLinQ NIC driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ + +#include <linux/kernel.h> +#include <linux/qed/qed_if.h> +#include <linux/vmalloc.h> +#include "qed.h" +#include "qed_devlink.h" + +enum qed_devlink_param_id { + QED_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + QED_DEVLINK_PARAM_ID_IWARP_CMT, +}; + +struct qed_fw_fatal_ctx { + enum qed_hw_err_type err_type; +}; + +int qed_report_fatal_error(struct devlink *devlink, enum qed_hw_err_type err_type) +{ + struct qed_devlink *qdl = devlink_priv(devlink); + struct qed_fw_fatal_ctx fw_fatal_ctx = { + .err_type = err_type, + }; + + if (qdl->fw_reporter) + devlink_health_report(qdl->fw_reporter, + "Fatal error occurred", &fw_fatal_ctx); + + return 0; +} + +static int +qed_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct qed_devlink *qdl = devlink_health_reporter_priv(reporter); + struct qed_fw_fatal_ctx *fw_fatal_ctx = priv_ctx; + struct qed_dev *cdev = qdl->cdev; + u32 dbg_data_buf_size; + u8 *p_dbg_data_buf; + int err; + + /* Having context means that was a dump request after fatal, + * so we enable extra debugging while gathering the dump, + * just in case + */ + cdev->print_dbg_data = fw_fatal_ctx ? true : false; + + dbg_data_buf_size = qed_dbg_all_data_size(cdev); + p_dbg_data_buf = vzalloc(dbg_data_buf_size); + if (!p_dbg_data_buf) { + DP_NOTICE(cdev, + "Failed to allocate memory for a debug data buffer\n"); + return -ENOMEM; + } + + err = qed_dbg_all_data(cdev, p_dbg_data_buf); + if (err) { + DP_NOTICE(cdev, "Failed to obtain debug data\n"); + vfree(p_dbg_data_buf); + return err; + } + + err = devlink_fmsg_binary_pair_put(fmsg, "dump_data", + p_dbg_data_buf, dbg_data_buf_size); + + vfree(p_dbg_data_buf); + + return err; +} + +static int +qed_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter, + void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct qed_devlink *qdl = devlink_health_reporter_priv(reporter); + struct qed_dev *cdev = qdl->cdev; + + qed_recovery_process(cdev); + + return 0; +} + +static const struct devlink_health_reporter_ops qed_fw_fatal_reporter_ops = { + .name = "fw_fatal", + .recover = qed_fw_fatal_reporter_recover, + .dump = qed_fw_fatal_reporter_dump, +}; + +#define QED_REPORTER_FW_GRACEFUL_PERIOD 1200000 + +void qed_fw_reporters_create(struct devlink *devlink) +{ + struct qed_devlink *dl = devlink_priv(devlink); + + dl->fw_reporter = devlink_health_reporter_create(devlink, &qed_fw_fatal_reporter_ops, + QED_REPORTER_FW_GRACEFUL_PERIOD, dl); + if (IS_ERR(dl->fw_reporter)) { + DP_NOTICE(dl->cdev, "Failed to create fw reporter, err = %ld\n", + PTR_ERR(dl->fw_reporter)); + dl->fw_reporter = NULL; + } +} + +void qed_fw_reporters_destroy(struct devlink *devlink) +{ + struct qed_devlink *dl = devlink_priv(devlink); + struct devlink_health_reporter *rep; + + rep = dl->fw_reporter; + + if (!IS_ERR_OR_NULL(rep)) + devlink_health_reporter_destroy(rep); +} + +static int qed_dl_param_get(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct qed_devlink *qed_dl = devlink_priv(dl); + struct qed_dev *cdev; + + cdev = qed_dl->cdev; + ctx->val.vbool = cdev->iwarp_cmt; + + return 0; +} + +static int qed_dl_param_set(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct qed_devlink *qed_dl = devlink_priv(dl); + struct qed_dev *cdev; + + cdev = qed_dl->cdev; + cdev->iwarp_cmt = ctx->val.vbool; + + return 0; +} + +static const struct devlink_param qed_devlink_params[] = { + DEVLINK_PARAM_DRIVER(QED_DEVLINK_PARAM_ID_IWARP_CMT, + "iwarp_cmt", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + qed_dl_param_get, qed_dl_param_set, NULL), +}; + +static int qed_devlink_info_get(struct devlink *devlink, + struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct qed_devlink *qed_dl = devlink_priv(devlink); + struct qed_dev *cdev = qed_dl->cdev; + struct qed_dev_info *dev_info; + char buf[100]; + int err; + + dev_info = &cdev->common_dev_info; + + err = devlink_info_driver_name_put(req, KBUILD_MODNAME); + if (err) + return err; + + memcpy(buf, cdev->hwfns[0].hw_info.part_num, sizeof(cdev->hwfns[0].hw_info.part_num)); + buf[sizeof(cdev->hwfns[0].hw_info.part_num)] = 0; + + if (buf[0]) { + err = devlink_info_board_serial_number_put(req, buf); + if (err) + return err; + } + + snprintf(buf, sizeof(buf), "%d.%d.%d.%d", + GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_3), + GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_2), + GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_1), + GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_0)); + + err = devlink_info_version_stored_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, buf); + if (err) + return err; + + snprintf(buf, sizeof(buf), "%d.%d.%d.%d", + dev_info->fw_major, + dev_info->fw_minor, + dev_info->fw_rev, + dev_info->fw_eng); + + return devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_APP, buf); +} + +static const struct devlink_ops qed_dl_ops = { + .info_get = qed_devlink_info_get, +}; + +struct devlink *qed_devlink_register(struct qed_dev *cdev) +{ + union devlink_param_value value; + struct qed_devlink *qdevlink; + struct devlink *dl; + int rc; + + dl = devlink_alloc(&qed_dl_ops, sizeof(struct qed_devlink)); + if (!dl) + return ERR_PTR(-ENOMEM); + + qdevlink = devlink_priv(dl); + qdevlink->cdev = cdev; + + rc = devlink_register(dl, &cdev->pdev->dev); + if (rc) + goto err_free; + + rc = devlink_params_register(dl, qed_devlink_params, + ARRAY_SIZE(qed_devlink_params)); + if (rc) + goto err_unregister; + + value.vbool = false; + devlink_param_driverinit_value_set(dl, + QED_DEVLINK_PARAM_ID_IWARP_CMT, + value); + + devlink_params_publish(dl); + cdev->iwarp_cmt = false; + + qed_fw_reporters_create(dl); + + return dl; + +err_unregister: + devlink_unregister(dl); + +err_free: + devlink_free(dl); + + return ERR_PTR(rc); +} + +void qed_devlink_unregister(struct devlink *devlink) +{ + if (!devlink) + return; + + qed_fw_reporters_destroy(devlink); + + devlink_params_unregister(devlink, qed_devlink_params, + ARRAY_SIZE(qed_devlink_params)); + + devlink_unregister(devlink); + devlink_free(devlink); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.h b/drivers/net/ethernet/qlogic/qed/qed_devlink.h new file mode 100644 index 000000000000..ccc7d1d1bfd4 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Marvell/Qlogic FastLinQ NIC driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ +#ifndef _QED_DEVLINK_H +#define _QED_DEVLINK_H + +#include <linux/qed/qed_if.h> +#include <net/devlink.h> + +struct devlink *qed_devlink_register(struct qed_dev *cdev); +void qed_devlink_unregister(struct devlink *devlink); + +void qed_fw_reporters_create(struct devlink *devlink); +void qed_fw_reporters_destroy(struct devlink *devlink); + +int qed_report_fatal_error(struct devlink *dl, enum qed_hw_err_type err_type); + +#endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 2558cb680db3..5b149ceff6b6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -39,6 +39,7 @@ #include "qed_hw.h" #include "qed_selftest.h" #include "qed_debug.h" +#include "qed_devlink.h" #define QED_ROCE_QPS (8192) #define QED_ROCE_DPIS (8) @@ -478,6 +479,7 @@ int qed_fill_dev_info(struct qed_dev *cdev, } dev_info->mtu = hw_info->mtu; + cdev->common_dev_info = *dev_info; return 0; } @@ -510,107 +512,6 @@ static int qed_set_power_state(struct qed_dev *cdev, pci_power_t state) return 0; } -struct qed_devlink { - struct qed_dev *cdev; -}; - -enum qed_devlink_param_id { - QED_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, - QED_DEVLINK_PARAM_ID_IWARP_CMT, -}; - -static int qed_dl_param_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct qed_devlink *qed_dl; - struct qed_dev *cdev; - - qed_dl = devlink_priv(dl); - cdev = qed_dl->cdev; - ctx->val.vbool = cdev->iwarp_cmt; - - return 0; -} - -static int qed_dl_param_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct qed_devlink *qed_dl; - struct qed_dev *cdev; - - qed_dl = devlink_priv(dl); - cdev = qed_dl->cdev; - cdev->iwarp_cmt = ctx->val.vbool; - - return 0; -} - -static const struct devlink_param qed_devlink_params[] = { - DEVLINK_PARAM_DRIVER(QED_DEVLINK_PARAM_ID_IWARP_CMT, - "iwarp_cmt", DEVLINK_PARAM_TYPE_BOOL, - BIT(DEVLINK_PARAM_CMODE_RUNTIME), - qed_dl_param_get, qed_dl_param_set, NULL), -}; - -static const struct devlink_ops qed_dl_ops; - -static int qed_devlink_register(struct qed_dev *cdev) -{ - union devlink_param_value value; - struct qed_devlink *qed_dl; - struct devlink *dl; - int rc; - - dl = devlink_alloc(&qed_dl_ops, sizeof(*qed_dl)); - if (!dl) - return -ENOMEM; - - qed_dl = devlink_priv(dl); - - cdev->dl = dl; - qed_dl->cdev = cdev; - - rc = devlink_register(dl, &cdev->pdev->dev); - if (rc) - goto err_free; - - rc = devlink_params_register(dl, qed_devlink_params, - ARRAY_SIZE(qed_devlink_params)); - if (rc) - goto err_unregister; - - value.vbool = false; - devlink_param_driverinit_value_set(dl, - QED_DEVLINK_PARAM_ID_IWARP_CMT, - value); - - devlink_params_publish(dl); - cdev->iwarp_cmt = false; - - return 0; - -err_unregister: - devlink_unregister(dl); - -err_free: - cdev->dl = NULL; - devlink_free(dl); - - return rc; -} - -static void qed_devlink_unregister(struct qed_dev *cdev) -{ - if (!cdev->dl) - return; - - devlink_params_unregister(cdev->dl, qed_devlink_params, - ARRAY_SIZE(qed_devlink_params)); - - devlink_unregister(cdev->dl); - devlink_free(cdev->dl); -} - /* probing */ static struct qed_dev *qed_probe(struct pci_dev *pdev, struct qed_probe_params *params) @@ -639,12 +540,6 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev, } DP_INFO(cdev, "PCI init completed successfully\n"); - rc = qed_devlink_register(cdev); - if (rc) { - DP_INFO(cdev, "Failed to register devlink.\n"); - goto err2; - } - rc = qed_hw_prepare(cdev, QED_PCI_DEFAULT); if (rc) { DP_ERR(cdev, "hw prepare failed\n"); @@ -674,8 +569,6 @@ static void qed_remove(struct qed_dev *cdev) qed_set_power_state(cdev, PCI_D3hot); - qed_devlink_unregister(cdev); - qed_free_cdev(cdev); } @@ -761,7 +654,7 @@ static int qed_set_int_mode(struct qed_dev *cdev, bool force_mode) kfree(int_params->msix_table); if (force_mode) goto out; - /* Fallthrough */ + fallthrough; case QED_INT_MODE_MSI: if (cdev->num_hwfns == 1) { @@ -775,7 +668,7 @@ static int qed_set_int_mode(struct qed_dev *cdev, bool force_mode) if (force_mode) goto out; } - /* Fallthrough */ + fallthrough; case QED_INT_MODE_INTA: int_params->out.int_mode = QED_INT_MODE_INTA; @@ -2924,7 +2817,7 @@ static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode) return status; } -static int qed_recovery_process(struct qed_dev *cdev) +int qed_recovery_process(struct qed_dev *cdev) { struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); struct qed_ptt *p_ptt; @@ -3112,6 +3005,9 @@ const struct qed_common_ops qed_common_ops_pass = { .get_link = &qed_get_current_link, .drain = &qed_drain, .update_msglvl = &qed_init_dp, + .devlink_register = qed_devlink_register, + .devlink_unregister = qed_devlink_unregister, + .report_fatal_error = qed_report_fatal_error, .dbg_all_data = &qed_dbg_all_data, .dbg_all_data_size = &qed_dbg_all_data_size, .chain_alloc = &qed_chain_alloc, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 5be08f83e0aa..cd882c453394 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1085,7 +1085,7 @@ int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) DP_NOTICE(p_hwfn, "Unknown WoL configuration %02x\n", p_hwfn->cdev->wol_config); - /* Fallthrough */ + fallthrough; case QED_OV_WOL_DEFAULT: wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP; } @@ -1365,7 +1365,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, break; case LINK_STATUS_SPEED_AND_DUPLEX_1000THD: p_link->full_duplex = false; - /* Fall-through */ + fallthrough; case LINK_STATUS_SPEED_AND_DUPLEX_1000TFD: p_link->speed = 1000; break; @@ -2451,7 +2451,7 @@ qed_mcp_get_shmem_proto(struct qed_hwfn *p_hwfn, break; case FUNC_MF_CFG_PROTOCOL_ROCE: DP_NOTICE(p_hwfn, "RoCE personality is not a valid value!\n"); - /* Fallthrough */ + fallthrough; default: rc = -EINVAL; } @@ -3546,7 +3546,7 @@ qed_mcp_resc_allocation_msg(struct qed_hwfn *p_hwfn, switch (p_in_params->cmd) { case DRV_MSG_SET_RESOURCE_VALUE_MSG: mfw_resc_info.size = p_in_params->resc_max_val; - /* Fallthrough */ + fallthrough; case DRV_MSG_GET_RESOURCE_ALLOC_MSG: break; default: @@ -3823,7 +3823,7 @@ qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn, DP_INFO(p_hwfn, "Resource unlock request for an already released resource [%d]\n", p_params->resource); - /* Fallthrough */ + fallthrough; case RESOURCE_OPCODE_RELEASED: p_params->b_released = true; break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index a4bcde522cdf..4394a4d77224 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -1151,7 +1151,6 @@ qed_rdma_destroy_cq(void *rdma_cxt, DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", in_params->icid); p_ramrod_res = - (struct rdma_destroy_cq_output_params *) dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, sizeof(struct rdma_destroy_cq_output_params), &ramrod_res_phys, GFP_KERNEL); diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 803c1fcca8ad..3efc5899f656 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -172,6 +172,7 @@ struct qede_dev { struct qed_dev *cdev; struct net_device *ndev; struct pci_dev *pdev; + struct devlink *devlink; u32 dp_module; u8 dp_level; @@ -263,6 +264,7 @@ struct qede_dev { struct bpf_prog *xdp_prog; + enum qed_hw_err_type last_err_type; unsigned long err_flags; #define QEDE_ERR_IS_HANDLED 31 #define QEDE_ERR_ATTN_CLR_EN 0 diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 140a392a81bb..20d2296beb79 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1170,10 +1170,23 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, rc = -ENOMEM; goto err2; } + + edev->devlink = qed_ops->common->devlink_register(cdev); + if (IS_ERR(edev->devlink)) { + DP_NOTICE(edev, "Cannot register devlink\n"); + edev->devlink = NULL; + /* Go on, we can live without devlink */ + } } else { struct net_device *ndev = pci_get_drvdata(pdev); edev = netdev_priv(ndev); + + if (edev->devlink) { + struct qed_devlink *qdl = devlink_priv(edev->devlink); + + qdl->cdev = cdev; + } edev->cdev = cdev; memset(&edev->stats, 0, sizeof(edev->stats)); memcpy(&edev->dev_info, &dev_info, sizeof(dev_info)); @@ -1225,7 +1238,10 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, err4: qede_rdma_dev_remove(edev, (mode == QEDE_PROBE_RECOVERY)); err3: - free_netdev(edev->ndev); + if (mode != QEDE_PROBE_RECOVERY) + free_netdev(edev->ndev); + else + edev->cdev = NULL; err2: qed_ops->common->slowpath_stop(cdev); err1: @@ -1296,6 +1312,11 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) qed_ops->common->slowpath_stop(cdev); if (system_state == SYSTEM_POWER_OFF) return; + + if (mode != QEDE_REMOVE_RECOVERY && edev->devlink) { + qed_ops->common->devlink_unregister(edev->devlink); + edev->devlink = NULL; + } qed_ops->common->remove(cdev); edev->cdev = NULL; @@ -2455,7 +2476,8 @@ static int qede_close(struct net_device *ndev) qede_unload(edev, QEDE_UNLOAD_NORMAL, false); - edev->ops->common->update_drv_state(edev->cdev, false); + if (edev->cdev) + edev->ops->common->update_drv_state(edev->cdev, false); return 0; } @@ -2577,19 +2599,12 @@ static void qede_atomic_hw_err_handler(struct qede_dev *edev) static void qede_generic_hw_err_handler(struct qede_dev *edev) { - struct qed_dev *cdev = edev->cdev; - DP_NOTICE(edev, "Generic sleepable HW error handling started - err_flags 0x%lx\n", edev->err_flags); - /* Trigger a recovery process. - * This is placed in the sleep requiring section just to make - * sure it is the last one, and that all the other operations - * were completed. - */ - if (test_bit(QEDE_ERR_IS_RECOVERABLE, &edev->err_flags)) - edev->ops->common->recovery_process(cdev); + if (edev->devlink) + edev->ops->common->report_fatal_error(edev->devlink, edev->last_err_type); clear_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags); @@ -2643,6 +2658,7 @@ static void qede_schedule_hw_err_handler(void *dev, return; } + edev->last_err_type = err_type; qede_set_hw_err_flags(edev, err_type); qede_atomic_hw_err_handler(edev); set_bit(QEDE_SP_HW_ERR, &edev->sp_flags); diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 0d0e38debbc2..569e2a7a64e5 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -1542,7 +1542,7 @@ static void ql_link_state_machine_work(struct work_struct *work) if (test_bit(QL_LINK_MASTER, &qdev->flags)) ql_port_start(qdev); qdev->port_link_state = LS_DOWN; - /* Fall Through */ + fallthrough; case LS_DOWN: if (curr_link_state == LS_UP) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 5c2a3acf1e89..b9894d54469c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -353,7 +353,7 @@ skip: case QLCNIC_BRDTYPE_P3P_4_GB_MM: supported |= SUPPORTED_Autoneg; advertising |= ADVERTISED_Autoneg; - /* fall through */ + fallthrough; case QLCNIC_BRDTYPE_P3P_10G_CX4: case QLCNIC_BRDTYPE_P3P_10G_CX4_LP: case QLCNIC_BRDTYPE_P3P_10000_BASE_T: @@ -377,7 +377,7 @@ skip: supported |= SUPPORTED_TP; check_sfp_module = netif_running(adapter->netdev) && ahw->has_link_events; - /* fall through */ + fallthrough; case QLCNIC_BRDTYPE_P3P_10G_XFP: supported |= SUPPORTED_FIBRE; advertising |= ADVERTISED_FIBRE; diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c index 375a844cd27c..362b4f5c162c 100644 --- a/drivers/net/ethernet/qualcomm/qca_uart.c +++ b/drivers/net/ethernet/qualcomm/qca_uart.c @@ -167,7 +167,7 @@ static void qca_tty_wakeup(struct serdev_device *serdev) schedule_work(&qca->tx_work); } -static struct serdev_device_ops qca_serdev_ops = { +static const struct serdev_device_ops qca_serdev_ops = { .receive_buf = qca_tty_receive, .write_wakeup = qca_tty_wakeup, }; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index d1da92ac7fbe..9e4e6a883877 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -617,7 +617,6 @@ struct rtl8169_private { struct work_struct work; } wk; - unsigned irq_enabled:1; unsigned supports_gmii:1; unsigned aspm_manageable:1; dma_addr_t counters_phys_addr; @@ -1280,12 +1279,10 @@ static void rtl_irq_disable(struct rtl8169_private *tp) RTL_W32(tp, IntrMask_8125, 0); else RTL_W16(tp, IntrMask, 0); - tp->irq_enabled = 0; } static void rtl_irq_enable(struct rtl8169_private *tp) { - tp->irq_enabled = 1; if (rtl_is_8125(tp)) RTL_W32(tp, IntrMask_8125, tp->irq_mask); else @@ -4541,8 +4538,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) struct rtl8169_private *tp = dev_instance; u32 status = rtl_get_events(tp); - if (!tp->irq_enabled || (status & 0xffff) == 0xffff || - !(status & tp->irq_mask)) + if ((status & 0xffff) == 0xffff || !(status & tp->irq_mask)) return IRQ_NONE; if (unlikely(status & SYSErr)) { @@ -4596,10 +4592,8 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) rtl_tx(dev, tp, budget); - if (work_done < budget) { - napi_complete_done(napi, work_done); + if (work_done < budget && napi_complete_done(napi, work_done)) rtl_irq_enable(tp); - } return work_done; } @@ -4994,7 +4988,7 @@ static int rtl_alloc_irq(struct rtl8169_private *tp) rtl_unlock_config_regs(tp); RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable); rtl_lock_config_regs(tp); - /* fall through */ + fallthrough; case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_17: flags = PCI_IRQ_LEGACY; break; @@ -5137,7 +5131,7 @@ static void rtl_hw_initialize(struct rtl8169_private *tp) switch (tp->mac_version) { case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_52: rtl8168ep_stop_cmac(tp); - /* fall through */ + fallthrough; case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48: rtl_hw_init_8168g(tp); break; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 99f7aae102ce..f684296df871 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -162,7 +162,7 @@ static int ravb_get_mdio_data(struct mdiobb_ctrl *ctrl) } /* MDIO bus control struct */ -static struct mdiobb_ops bb_ops = { +static const struct mdiobb_ops bb_ops = { .owner = THIS_MODULE, .set_mdc = ravb_set_mdc, .set_mdio_dir = ravb_set_mdio_dir, @@ -1342,6 +1342,51 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler, return error; } +/* MDIO bus init function */ +static int ravb_mdio_init(struct ravb_private *priv) +{ + struct platform_device *pdev = priv->pdev; + struct device *dev = &pdev->dev; + int error; + + /* Bitbang init */ + priv->mdiobb.ops = &bb_ops; + + /* MII controller setting */ + priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); + if (!priv->mii_bus) + return -ENOMEM; + + /* Hook up MII support for ethtool */ + priv->mii_bus->name = "ravb_mii"; + priv->mii_bus->parent = dev; + snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", + pdev->name, pdev->id); + + /* Register MDIO bus */ + error = of_mdiobus_register(priv->mii_bus, dev->of_node); + if (error) + goto out_free_bus; + + return 0; + +out_free_bus: + free_mdio_bitbang(priv->mii_bus); + return error; +} + +/* MDIO bus release function */ +static int ravb_mdio_release(struct ravb_private *priv) +{ + /* Unregister mdio bus */ + mdiobus_unregister(priv->mii_bus); + + /* Free bitbang info */ + free_mdio_bitbang(priv->mii_bus); + + return 0; +} + /* Network device open function for Ethernet AVB */ static int ravb_open(struct net_device *ndev) { @@ -1350,6 +1395,13 @@ static int ravb_open(struct net_device *ndev) struct device *dev = &pdev->dev; int error; + /* MDIO bus init */ + error = ravb_mdio_init(priv); + if (error) { + netdev_err(ndev, "failed to initialize MDIO\n"); + return error; + } + napi_enable(&priv->napi[RAVB_BE]); napi_enable(&priv->napi[RAVB_NC]); @@ -1427,6 +1479,7 @@ out_free_irq: out_napi_off: napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); + ravb_mdio_release(priv); return error; } @@ -1736,6 +1789,8 @@ static int ravb_close(struct net_device *ndev) ravb_ring_free(ndev, RAVB_BE); ravb_ring_free(ndev, RAVB_NC); + ravb_mdio_release(priv); + return 0; } @@ -1887,51 +1942,6 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_set_features = ravb_set_features, }; -/* MDIO bus init function */ -static int ravb_mdio_init(struct ravb_private *priv) -{ - struct platform_device *pdev = priv->pdev; - struct device *dev = &pdev->dev; - int error; - - /* Bitbang init */ - priv->mdiobb.ops = &bb_ops; - - /* MII controller setting */ - priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); - if (!priv->mii_bus) - return -ENOMEM; - - /* Hook up MII support for ethtool */ - priv->mii_bus->name = "ravb_mii"; - priv->mii_bus->parent = dev; - snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", - pdev->name, pdev->id); - - /* Register MDIO bus */ - error = of_mdiobus_register(priv->mii_bus, dev->of_node); - if (error) - goto out_free_bus; - - return 0; - -out_free_bus: - free_mdio_bitbang(priv->mii_bus); - return error; -} - -/* MDIO bus release function */ -static int ravb_mdio_release(struct ravb_private *priv) -{ - /* Unregister mdio bus */ - mdiobus_unregister(priv->mii_bus); - - /* Free bitbang info */ - free_mdio_bitbang(priv->mii_bus); - - return 0; -} - static const struct of_device_id ravb_match_table[] = { { .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 }, { .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 }, @@ -2174,13 +2184,6 @@ static int ravb_probe(struct platform_device *pdev) eth_hw_addr_random(ndev); } - /* MDIO bus init */ - error = ravb_mdio_init(priv); - if (error) { - dev_err(&pdev->dev, "failed to initialize MDIO\n"); - goto out_dma_free; - } - netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64); netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64); @@ -2202,8 +2205,6 @@ static int ravb_probe(struct platform_device *pdev) out_napi_del: netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); - ravb_mdio_release(priv); -out_dma_free: dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, priv->desc_bat_dma); @@ -2235,7 +2236,6 @@ static int ravb_remove(struct platform_device *pdev) unregister_netdev(ndev); netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); - ravb_mdio_release(priv); pm_runtime_disable(&pdev->dev); free_netdev(ndev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index f45331ed90b0..586642c33d2b 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1202,7 +1202,7 @@ static void sh_mdc_ctrl(struct mdiobb_ctrl *ctrl, int bit) } /* mdio bus control struct */ -static struct mdiobb_ops bb_ops = { +static const struct mdiobb_ops bb_ops = { .owner = THIS_MODULE, .set_mdc = sh_mdc_ctrl, .set_mdio_dir = sh_mmd_ctrl, diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index fc99e7118e49..42458a46ffaf 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2169,7 +2169,7 @@ static void rocker_router_fib_event_work(struct work_struct *work) rocker_world_fib4_del(rocker, &fib_work->fen_info); fib_info_put(fib_work->fen_info.fi); break; - case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_ADD: case FIB_EVENT_RULE_DEL: rule = fib_work->fr_info.rule; if (!fib4_rule_default(rule)) @@ -2201,7 +2201,7 @@ static int rocker_router_fib_event(struct notifier_block *nb, fib_work->event = event; switch (event) { - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_DEL: if (info->family == AF_INET) { struct fib_entry_notifier_info *fen_info = ptr; @@ -2224,7 +2224,7 @@ static int rocker_router_fib_event(struct notifier_block *nb, */ fib_info_hold(fib_work->fen_info.fi); break; - case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_ADD: case FIB_EVENT_RULE_DEL: memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info)); fib_rule_get(fib_work->fr_info.rule); @@ -2811,7 +2811,7 @@ static int rocker_switchdev_event(struct notifier_block *unused, switchdev_work->event = event; switch (event) { - case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */ + case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: memcpy(&switchdev_work->fdb_info, ptr, sizeof(switchdev_work->fdb_info)); diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c index 21465cb3d60a..7f8b10c49660 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c @@ -316,7 +316,7 @@ static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv, case TCP_V4_FLOW: case UDP_V4_FLOW: cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - /* Fall through */ + fallthrough; case SCTP_V4_FLOW: case AH_ESP_V4_FLOW: case AH_V4_FLOW: @@ -327,7 +327,7 @@ static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv, case TCP_V6_FLOW: case UDP_V6_FLOW: cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - /* Fall through */ + fallthrough; case SCTP_V6_FLOW: case AH_ESP_V6_FLOW: case AH_V6_FLOW: diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 4b0b2cf026a5..316e14533e9d 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -2367,7 +2367,7 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue) unsigned int write_ptr; efx_qword_t *txd; - tx_queue->xmit_more_available = false; + tx_queue->xmit_pending = false; if (unlikely(tx_queue->write_count == tx_queue->insert_count)) return; @@ -3955,7 +3955,6 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .start_stats = efx_port_dummy_op_void, .pull_stats = efx_port_dummy_op_void, .stop_stats = efx_port_dummy_op_void, - .set_id_led = efx_mcdi_set_id_led, .push_irq_moderation = efx_ef10_push_irq_moderation, .reconfigure_mac = efx_ef10_mac_reconfigure, .check_mac_fault = efx_mcdi_mac_check_fault, @@ -4066,7 +4065,6 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .start_stats = efx_mcdi_mac_start_stats, .pull_stats = efx_mcdi_mac_pull_stats, .stop_stats = efx_mcdi_mac_stop_stats, - .set_id_led = efx_mcdi_set_id_led, .push_irq_moderation = efx_ef10_push_irq_moderation, .reconfigure_mac = efx_ef10_mac_reconfigure, .check_mac_fault = efx_mcdi_mac_check_fault, diff --git a/drivers/net/ethernet/sfc/ef100.c b/drivers/net/ethernet/sfc/ef100.c index 9729983f4840..c54b7f8243f3 100644 --- a/drivers/net/ethernet/sfc/ef100.c +++ b/drivers/net/ethernet/sfc/ef100.c @@ -142,7 +142,7 @@ static int ef100_pci_parse_continue_entry(struct efx_nic *efx, int entry_locatio /* Temporarily map new BAR. */ rc = efx_init_io(efx, bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, bar)); if (rc) { netif_err(efx, probe, efx->net_dev, @@ -160,7 +160,7 @@ static int ef100_pci_parse_continue_entry(struct efx_nic *efx, int entry_locatio /* Put old BAR back. */ rc = efx_init_io(efx, previous_bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, previous_bar)); if (rc) { netif_err(efx, probe, efx->net_dev, @@ -334,7 +334,7 @@ static int ef100_pci_parse_xilinx_cap(struct efx_nic *efx, int vndr_cap, /* Temporarily map BAR. */ rc = efx_init_io(efx, bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, bar)); if (rc) { netif_err(efx, probe, efx->net_dev, @@ -495,7 +495,7 @@ static int ef100_pci_probe(struct pci_dev *pci_dev, /* Set up basic I/O (BAR mappings etc) */ rc = efx_init_io(efx, fcw.bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, fcw.bar)); if (rc) goto fail; diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c index 729c425d0f78..835c838b7dfa 100644 --- a/drivers/net/ethernet/sfc/ef100_ethtool.c +++ b/drivers/net/ethernet/sfc/ef100_ethtool.c @@ -17,8 +17,49 @@ #include "ef100_ethtool.h" #include "mcdi_functions.h" +/* This is the maximum number of descriptor rings supported by the QDMA */ +#define EFX_EF100_MAX_DMAQ_SIZE 16384UL + +static void ef100_ethtool_get_ringparam(struct net_device *net_dev, + struct ethtool_ringparam *ring) +{ + struct efx_nic *efx = netdev_priv(net_dev); + + ring->rx_max_pending = EFX_EF100_MAX_DMAQ_SIZE; + ring->tx_max_pending = EFX_EF100_MAX_DMAQ_SIZE; + ring->rx_pending = efx->rxq_entries; + ring->tx_pending = efx->txq_entries; +} + /* Ethtool options available */ const struct ethtool_ops ef100_ethtool_ops = { .get_drvinfo = efx_ethtool_get_drvinfo, + .get_msglevel = efx_ethtool_get_msglevel, + .set_msglevel = efx_ethtool_set_msglevel, + .get_pauseparam = efx_ethtool_get_pauseparam, + .set_pauseparam = efx_ethtool_set_pauseparam, + .get_sset_count = efx_ethtool_get_sset_count, + .self_test = efx_ethtool_self_test, + .get_strings = efx_ethtool_get_strings, + .get_link_ksettings = efx_ethtool_get_link_ksettings, + .set_link_ksettings = efx_ethtool_set_link_ksettings, + .get_link = ethtool_op_get_link, + .get_ringparam = ef100_ethtool_get_ringparam, + .get_fecparam = efx_ethtool_get_fecparam, + .set_fecparam = efx_ethtool_set_fecparam, + .get_ethtool_stats = efx_ethtool_get_stats, + .get_rxnfc = efx_ethtool_get_rxnfc, + .set_rxnfc = efx_ethtool_set_rxnfc, + .reset = efx_ethtool_reset, + + .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, + .get_rxfh_key_size = efx_ethtool_get_rxfh_key_size, + .get_rxfh = efx_ethtool_get_rxfh, + .set_rxfh = efx_ethtool_set_rxfh, + .get_rxfh_context = efx_ethtool_get_rxfh_context, + .set_rxfh_context = efx_ethtool_set_rxfh_context, + + .get_module_info = efx_ethtool_get_module_info, + .get_module_eeprom = efx_ethtool_get_module_eeprom, }; diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index 63c311ba28b9..67fe44db6b61 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -217,9 +217,13 @@ static const struct net_device_ops ef100_netdev_ops = { .ndo_open = ef100_net_open, .ndo_stop = ef100_net_stop, .ndo_start_xmit = ef100_hard_start_xmit, + .ndo_tx_timeout = efx_watchdog, .ndo_get_stats64 = efx_net_stats, + .ndo_change_mtu = efx_change_mtu, .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = efx_set_mac_address, .ndo_set_rx_mode = efx_set_rx_mode, /* Lookout */ + .ndo_set_features = efx_set_features, .ndo_get_phys_port_id = efx_get_phys_port_id, .ndo_get_phys_port_name = efx_get_phys_port_name, #ifdef CONFIG_RFS_ACCEL diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 206d70f9d95b..fb7752d62ce0 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -428,24 +428,12 @@ static int ef100_reset(struct efx_nic *efx, enum reset_type reset_type) __clear_bit(reset_type, &efx->reset_pending); rc = dev_open(efx->net_dev, NULL); } else if (reset_type == RESET_TYPE_ALL) { - /* A RESET_TYPE_ALL will cause filters to be removed, so we remove filters - * and reprobe after reset to avoid removing filters twice - */ - down_read(&efx->filter_sem); - ef100_filter_table_down(efx); - up_read(&efx->filter_sem); rc = efx_mcdi_reset(efx, reset_type); if (rc) return rc; netif_device_attach(efx->net_dev); - down_read(&efx->filter_sem); - rc = ef100_filter_table_up(efx); - up_read(&efx->filter_sem); - if (rc) - return rc; - rc = dev_open(efx->net_dev, NULL); } else { rc = 1; /* Leave the device closed */ @@ -696,7 +684,7 @@ static unsigned int ef100_check_caps(const struct efx_nic *efx, /* NIC level access functions */ #define EF100_OFFLOAD_FEATURES (NETIF_F_HW_CSUM | NETIF_F_RXCSUM | \ - NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_FRAGLIST | \ + NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_NTUPLE | \ NETIF_F_RXHASH | NETIF_F_RXFCS | NETIF_F_TSO_ECN | NETIF_F_RXALL | \ NETIF_F_TSO_MANGLEID | NETIF_F_HW_VLAN_CTAG_TX) @@ -739,6 +727,7 @@ const struct efx_nic_type ef100_pf_nic_type = { .rx_remove = efx_mcdi_rx_remove, .rx_write = ef100_rx_write, .rx_packet = __ef100_rx_packet, + .rx_buf_hash_valid = ef100_rx_buf_hash_valid, .fini_dmaq = efx_fini_dmaq, .max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS, .filter_table_probe = ef100_filter_table_up, @@ -768,6 +757,7 @@ const struct efx_nic_type ef100_pf_nic_type = { .rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts, .reconfigure_mac = ef100_reconfigure_mac, + .reconfigure_port = efx_mcdi_port_reconfigure, .test_nvram = efx_new_mcdi_nvram_test_all, .describe_stats = ef100_describe_stats, .start_stats = efx_mcdi_mac_start_stats, @@ -820,6 +810,7 @@ const struct efx_nic_type ef100_vf_nic_type = { .rx_remove = efx_mcdi_rx_remove, .rx_write = ef100_rx_write, .rx_packet = __ef100_rx_packet, + .rx_buf_hash_valid = ef100_rx_buf_hash_valid, .fini_dmaq = efx_fini_dmaq, .max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS, .filter_table_probe = ef100_filter_table_up, @@ -1170,6 +1161,10 @@ static int ef100_probe_main(struct efx_nic *efx) rc = efx_mcdi_reset(efx, RESET_TYPE_ALL); if (rc) goto fail; + /* Enable event logging */ + rc = efx_mcdi_log_ctrl(efx, true, false, 0); + if (rc) + goto fail; rc = efx_get_pf_index(efx, &nic_data->pf_index); if (rc) diff --git a/drivers/net/ethernet/sfc/ef100_rx.c b/drivers/net/ethernet/sfc/ef100_rx.c index 13ba1a4f66fc..85207acf7dee 100644 --- a/drivers/net/ethernet/sfc/ef100_rx.c +++ b/drivers/net/ethernet/sfc/ef100_rx.c @@ -31,7 +31,12 @@ #define ESF_GZ_RX_PREFIX_NT_OR_INNER_L3_CLASS_WIDTH \ ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L3_CLASS_WIDTH -static bool check_fcs(struct efx_channel *channel, u32 *prefix) +bool ef100_rx_buf_hash_valid(const u8 *prefix) +{ + return PREFIX_FIELD(prefix, RSS_HASH_VALID); +} + +static bool ef100_has_fcs_error(struct efx_channel *channel, u32 *prefix) { u16 rxclass; u8 l2status; @@ -41,11 +46,11 @@ static bool check_fcs(struct efx_channel *channel, u32 *prefix) if (likely(l2status == ESE_GZ_RH_HCLASS_L2_STATUS_OK)) /* Everything is ok */ - return 0; + return false; if (l2status == ESE_GZ_RH_HCLASS_L2_STATUS_FCS_ERR) channel->n_rx_eth_crc_err++; - return 1; + return true; } void __ef100_rx_packet(struct efx_channel *channel) @@ -58,7 +63,7 @@ void __ef100_rx_packet(struct efx_channel *channel) prefix = (u32 *)(eh - ESE_GZ_RX_PKT_PREFIX_LEN); - if (check_fcs(channel, prefix) && + if (ef100_has_fcs_error(channel, prefix) && unlikely(!(efx->net_dev->features & NETIF_F_RXALL))) goto out; diff --git a/drivers/net/ethernet/sfc/ef100_rx.h b/drivers/net/ethernet/sfc/ef100_rx.h index f2f266863966..fe45b36458d1 100644 --- a/drivers/net/ethernet/sfc/ef100_rx.h +++ b/drivers/net/ethernet/sfc/ef100_rx.h @@ -14,6 +14,7 @@ #include "net_driver.h" +bool ef100_rx_buf_hash_valid(const u8 *prefix); void efx_ef100_ev_rx(struct efx_channel *channel, const efx_qword_t *p_event); void ef100_rx_write(struct efx_rx_queue *rx_queue); void __ef100_rx_packet(struct efx_channel *channel); diff --git a/drivers/net/ethernet/sfc/ef100_tx.c b/drivers/net/ethernet/sfc/ef100_tx.c index a09546e43408..078c7ec2a70e 100644 --- a/drivers/net/ethernet/sfc/ef100_tx.c +++ b/drivers/net/ethernet/sfc/ef100_tx.c @@ -117,11 +117,13 @@ static efx_oword_t *ef100_tx_desc(struct efx_tx_queue *tx_queue, unsigned int in return NULL; } -void ef100_notify_tx_desc(struct efx_tx_queue *tx_queue) +static void ef100_notify_tx_desc(struct efx_tx_queue *tx_queue) { unsigned int write_ptr; efx_dword_t reg; + tx_queue->xmit_pending = false; + if (unlikely(tx_queue->notify_count == tx_queue->write_count)) return; @@ -131,7 +133,6 @@ void ef100_notify_tx_desc(struct efx_tx_queue *tx_queue) efx_writed_page(tx_queue->efx, ®, ER_GZ_TX_RING_DOORBELL, tx_queue->queue); tx_queue->notify_count = tx_queue->write_count; - tx_queue->xmit_more_available = false; } static void ef100_tx_push_buffers(struct efx_tx_queue *tx_queue) @@ -359,28 +360,31 @@ int ef100_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) goto err; ef100_tx_make_descriptors(tx_queue, skb, segments); - fill_level = efx_channel_tx_fill_level(tx_queue->channel); + fill_level = efx_channel_tx_old_fill_level(tx_queue->channel); if (fill_level > efx->txq_stop_thresh) { + struct efx_tx_queue *txq2; + netif_tx_stop_queue(tx_queue->core_txq); /* Re-read after a memory barrier in case we've raced with * the completion path. Otherwise there's a danger we'll never * restart the queue if all completions have just happened. */ smp_mb(); - fill_level = efx_channel_tx_fill_level(tx_queue->channel); + efx_for_each_channel_tx_queue(txq2, tx_queue->channel) + txq2->old_read_count = READ_ONCE(txq2->read_count); + fill_level = efx_channel_tx_old_fill_level(tx_queue->channel); if (fill_level < efx->txq_stop_thresh) netif_tx_start_queue(tx_queue->core_txq); } - if (__netdev_tx_sent_queue(tx_queue->core_txq, skb->len, xmit_more)) - tx_queue->xmit_more_available = false; /* push doorbell */ - else if (tx_queue->write_count - tx_queue->notify_count > 255) - /* Ensure we never push more than 256 packets at once */ - tx_queue->xmit_more_available = false; /* push */ - else - tx_queue->xmit_more_available = true; /* don't push yet */ + tx_queue->xmit_pending = true; - if (!tx_queue->xmit_more_available) + /* If xmit_more then we don't need to push the doorbell, unless there + * are 256 descriptors already queued in which case we have to push to + * ensure we never push more than 256 at once. + */ + if (__netdev_tx_sent_queue(tx_queue->core_txq, skb->len, xmit_more) || + tx_queue->write_count - tx_queue->notify_count > 255) ef100_tx_push_buffers(tx_queue); if (segments) { @@ -399,10 +403,10 @@ err: /* If we're not expecting another transmit and we had something to push * on this queue then we need to push here to get the previous packets - * out. We only enter this branch from before the 'Update BQL' section - * above, so xmit_more_available still refers to the old state. + * out. We only enter this branch from before the xmit_more handling + * above, so xmit_pending still refers to the old state. */ - if (tx_queue->xmit_more_available && !xmit_more) + if (tx_queue->xmit_pending && !xmit_more) ef100_tx_push_buffers(tx_queue); return rc; } diff --git a/drivers/net/ethernet/sfc/ef100_tx.h b/drivers/net/ethernet/sfc/ef100_tx.h index fa23e430bdd7..ddc4b98fa6db 100644 --- a/drivers/net/ethernet/sfc/ef100_tx.h +++ b/drivers/net/ethernet/sfc/ef100_tx.h @@ -17,7 +17,6 @@ int ef100_tx_probe(struct efx_tx_queue *tx_queue); void ef100_tx_init(struct efx_tx_queue *tx_queue); void ef100_tx_write(struct efx_tx_queue *tx_queue); -void ef100_notify_tx_desc(struct efx_tx_queue *tx_queue); unsigned int ef100_tx_max_skb_descs(struct efx_nic *efx); void ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index e06fa89f2d72..58b043f946b4 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -33,7 +33,7 @@ #include "selftest.h" #include "sriov.h" -#include "mcdi.h" +#include "mcdi_port_common.h" #include "mcdi_pcol.h" #include "workarounds.h" @@ -149,23 +149,17 @@ static int efx_init_port(struct efx_nic *efx) mutex_lock(&efx->mac_lock); - rc = efx->phy_op->init(efx); - if (rc) - goto fail1; - efx->port_initialized = true; /* Ensure the PHY advertises the correct flow control settings */ - rc = efx->phy_op->reconfigure(efx); + rc = efx_mcdi_port_reconfigure(efx); if (rc && rc != -EPERM) - goto fail2; + goto fail; mutex_unlock(&efx->mac_lock); return 0; -fail2: - efx->phy_op->fini(efx); -fail1: +fail: mutex_unlock(&efx->mac_lock); return rc; } @@ -177,7 +171,6 @@ static void efx_fini_port(struct efx_nic *efx) if (!efx->port_initialized) return; - efx->phy_op->fini(efx); efx->port_initialized = false; efx->link_state.up = false; @@ -1229,7 +1222,7 @@ static int efx_pm_thaw(struct device *dev) goto fail; mutex_lock(&efx->mac_lock); - efx->phy_op->reconfigure(efx); + efx_mcdi_port_reconfigure(efx); mutex_unlock(&efx->mac_lock); efx_start_all(efx); @@ -1336,7 +1329,7 @@ static int __init efx_init_module(void) { int rc; - printk(KERN_INFO "Solarflare NET driver v" EFX_DRIVER_VERSION "\n"); + printk(KERN_INFO "Solarflare NET driver\n"); rc = register_netdevice_notifier(&efx_netdev_notifier); if (rc) @@ -1398,4 +1391,3 @@ MODULE_AUTHOR("Solarflare Communications and " MODULE_DESCRIPTION("Solarflare network driver"); MODULE_LICENSE("GPL"); MODULE_DEVICE_TABLE(pci, efx_pci_table); -MODULE_VERSION(EFX_DRIVER_VERSION); diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index a9808e86068d..daf0c00c1242 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -45,6 +45,14 @@ static inline void efx_rx_flush_packet(struct efx_channel *channel) __ef100_rx_packet, __efx_rx_packet, channel); } +static inline bool efx_rx_buf_hash_valid(struct efx_nic *efx, const u8 *prefix) +{ + if (efx->type->rx_buf_hash_valid) + return INDIRECT_CALL_1(efx->type->rx_buf_hash_valid, + ef100_rx_buf_hash_valid, + prefix); + return true; +} /* Maximum number of TCP segments we support for soft-TSO */ #define EFX_TSO_MAX_SEGS 100 diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index dfc6032e75f4..80a23def96ad 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -19,6 +19,7 @@ #include "rx_common.h" #include "tx_common.h" #include "nic.h" +#include "mcdi_port_common.h" #include "io.h" #include "mcdi_pcol.h" @@ -544,7 +545,7 @@ void efx_start_all(struct efx_nic *efx) * to poll now because we could have missed a change */ mutex_lock(&efx->mac_lock); - if (efx->phy_op->poll(efx)) + if (efx_mcdi_phy_poll(efx)) efx_link_status_changed(efx); mutex_unlock(&efx->mac_lock); @@ -714,9 +715,6 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method) mutex_lock(&efx->mac_lock); down_write(&efx->filter_sem); mutex_lock(&efx->rss_lock); - if (efx->port_initialized && method != RESET_TYPE_INVISIBLE && - method != RESET_TYPE_DATAPATH) - efx->phy_op->fini(efx); efx->type->fini(efx); } @@ -759,10 +757,7 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok) if (efx->port_initialized && method != RESET_TYPE_INVISIBLE && method != RESET_TYPE_DATAPATH) { - rc = efx->phy_op->init(efx); - if (rc) - goto fail; - rc = efx->phy_op->reconfigure(efx); + rc = efx_mcdi_port_reconfigure(efx); if (rc && rc != -EPERM) netif_err(efx, drv, efx->net_dev, "could not restore PHY settings\n"); @@ -959,7 +954,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) /************************************************************************** * - * Dummy PHY/MAC operations + * Dummy NIC operations * * Can be used for some unimplemented operations * Needed so all function pointers are valid and do not have to be tested @@ -972,18 +967,6 @@ int efx_port_dummy_op_int(struct efx_nic *efx) } void efx_port_dummy_op_void(struct efx_nic *efx) {} -static bool efx_port_dummy_op_poll(struct efx_nic *efx) -{ - return false; -} - -static const struct efx_phy_operations efx_dummy_phy_operations = { - .init = efx_port_dummy_op_int, - .reconfigure = efx_port_dummy_op_int, - .poll = efx_port_dummy_op_poll, - .fini = efx_port_dummy_op_void, -}; - /************************************************************************** * * Data housekeeping @@ -1037,7 +1020,6 @@ int efx_init_struct(struct efx_nic *efx, efx->rps_hash_table = kcalloc(EFX_ARFS_HASH_TABLE_SIZE, sizeof(*efx->rps_hash_table), GFP_KERNEL); #endif - efx->phy_op = &efx_dummy_phy_operations; efx->mdio.dev = net_dev; INIT_WORK(&efx->mac_work, efx_mac_work); init_waitqueue_head(&efx->flush_wq); @@ -1104,17 +1086,7 @@ int efx_init_io(struct efx_nic *efx, int bar, dma_addr_t dma_mask, pci_set_master(pci_dev); - /* Set the PCI DMA mask. Try all possibilities from our - * genuine mask down to 32 bits, because some architectures - * (e.g. x86_64 with iommu_sac_force set) will allow 40 bit - * masks event though they reject 46 bit masks. - */ - while (dma_mask > 0x7fffffffUL) { - rc = dma_set_mask_and_coherent(&pci_dev->dev, dma_mask); - if (rc == 0) - break; - dma_mask >>= 1; - } + rc = dma_set_mask_and_coherent(&pci_dev->dev, dma_mask); if (rc) { netif_err(efx, probe, efx->net_dev, "could not find a suitable DMA mask\n"); diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 4ffda7782f68..12a91c559aa2 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -50,8 +50,7 @@ static int efx_ethtool_phys_id(struct net_device *net_dev, return 1; /* cycle on/off once per second */ } - efx->type->set_id_led(efx, mode); - return 0; + return efx_mcdi_set_id_led(efx, mode); } static int efx_ethtool_get_regs_len(struct net_device *net_dev) diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c index 05ac87807929..b18a4bcfccdf 100644 --- a/drivers/net/ethernet/sfc/ethtool_common.c +++ b/drivers/net/ethernet/sfc/ethtool_common.c @@ -15,6 +15,7 @@ #include "selftest.h" #include "rx_common.h" #include "ethtool_common.h" +#include "mcdi_port_common.h" struct efx_sw_stat_desc { const char *name; @@ -105,7 +106,6 @@ void efx_ethtool_get_drvinfo(struct net_device *net_dev, struct efx_nic *efx = netdev_priv(net_dev); strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); - strlcpy(info->version, EFX_DRIVER_VERSION, sizeof(info->version)); efx_mcdi_print_fwver(efx, info->fw_version, sizeof(info->fw_version)); strlcpy(info->bus_info, pci_name(efx->pci_dev), sizeof(info->bus_info)); @@ -221,7 +221,7 @@ int efx_ethtool_set_pauseparam(struct net_device *net_dev, efx_link_set_wanted_fc(efx, wanted_fc); if (efx->link_advertising[0] != old_adv || (efx->wanted_fc ^ old_fc) & EFX_FC_AUTO) { - rc = efx->phy_op->reconfigure(efx); + rc = efx_mcdi_port_reconfigure(efx); if (rc) { netif_err(efx, drv, efx->net_dev, "Unable to advertise requested flow " @@ -372,20 +372,15 @@ int efx_ethtool_fill_self_tests(struct efx_nic *efx, efx_fill_test(n++, strings, data, &tests->registers, "core", 0, "registers", NULL); - if (efx->phy_op->run_tests != NULL) { - EFX_WARN_ON_PARANOID(efx->phy_op->test_name == NULL); + for (i = 0; true; ++i) { + const char *name; - for (i = 0; true; ++i) { - const char *name; - - EFX_WARN_ON_PARANOID(i >= EFX_MAX_PHY_TESTS); - name = efx->phy_op->test_name(efx, i); - if (name == NULL) - break; + EFX_WARN_ON_PARANOID(i >= EFX_MAX_PHY_TESTS); + name = efx_mcdi_phy_test_name(efx, i); + if (name == NULL) + break; - efx_fill_test(n++, strings, data, &tests->phy_ext[i], - "phy", 0, name, NULL); - } + efx_fill_test(n++, strings, data, &tests->phy_ext[i], "phy", 0, name, NULL); } /* Loopback tests */ @@ -571,7 +566,7 @@ int efx_ethtool_get_link_ksettings(struct net_device *net_dev, u32 supported; mutex_lock(&efx->mac_lock); - efx->phy_op->get_link_ksettings(efx, cmd); + efx_mcdi_phy_get_link_ksettings(efx, cmd); mutex_unlock(&efx->mac_lock); /* Both MACs support pause frames (bidirectional and respond-only) */ @@ -607,7 +602,7 @@ int efx_ethtool_set_link_ksettings(struct net_device *net_dev, } mutex_lock(&efx->mac_lock); - rc = efx->phy_op->set_link_ksettings(efx, cmd); + rc = efx_mcdi_phy_set_link_ksettings(efx, cmd); mutex_unlock(&efx->mac_lock); return rc; } @@ -618,10 +613,8 @@ int efx_ethtool_get_fecparam(struct net_device *net_dev, struct efx_nic *efx = netdev_priv(net_dev); int rc; - if (!efx->phy_op || !efx->phy_op->get_fecparam) - return -EOPNOTSUPP; mutex_lock(&efx->mac_lock); - rc = efx->phy_op->get_fecparam(efx, fecparam); + rc = efx_mcdi_phy_get_fecparam(efx, fecparam); mutex_unlock(&efx->mac_lock); return rc; @@ -633,10 +626,8 @@ int efx_ethtool_set_fecparam(struct net_device *net_dev, struct efx_nic *efx = netdev_priv(net_dev); int rc; - if (!efx->phy_op || !efx->phy_op->get_fecparam) - return -EOPNOTSUPP; mutex_lock(&efx->mac_lock); - rc = efx->phy_op->set_fecparam(efx, fecparam); + rc = efx_mcdi_phy_set_fecparam(efx, fecparam); mutex_unlock(&efx->mac_lock); return rc; @@ -1332,11 +1323,8 @@ int efx_ethtool_get_module_eeprom(struct net_device *net_dev, struct efx_nic *efx = netdev_priv(net_dev); int ret; - if (!efx->phy_op || !efx->phy_op->get_module_eeprom) - return -EOPNOTSUPP; - mutex_lock(&efx->mac_lock); - ret = efx->phy_op->get_module_eeprom(efx, ee, data); + ret = efx_mcdi_phy_get_module_eeprom(efx, ee, data); mutex_unlock(&efx->mac_lock); return ret; @@ -1348,11 +1336,8 @@ int efx_ethtool_get_module_info(struct net_device *net_dev, struct efx_nic *efx = netdev_priv(net_dev); int ret; - if (!efx->phy_op || !efx->phy_op->get_module_info) - return -EOPNOTSUPP; - mutex_lock(&efx->mac_lock); - ret = efx->phy_op->get_module_info(efx, modinfo); + ret = efx_mcdi_phy_get_module_info(efx, modinfo); mutex_unlock(&efx->mac_lock); return ret; diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c index db90d94e24c9..a6bae6a234ba 100644 --- a/drivers/net/ethernet/sfc/falcon/ethtool.c +++ b/drivers/net/ethernet/sfc/falcon/ethtool.c @@ -957,7 +957,7 @@ ef4_ethtool_get_rxnfc(struct net_device *net_dev, switch (info->flow_type) { case TCP_V4_FLOW: info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - /* Fall through */ + fallthrough; case UDP_V4_FLOW: case SCTP_V4_FLOW: case AH_ESP_V4_FLOW: diff --git a/drivers/net/ethernet/sfc/falcon/farch.c b/drivers/net/ethernet/sfc/falcon/farch.c index 332183280a45..fa1ade856b10 100644 --- a/drivers/net/ethernet/sfc/falcon/farch.c +++ b/drivers/net/ethernet/sfc/falcon/farch.c @@ -1049,10 +1049,10 @@ ef4_farch_handle_rx_event(struct ef4_channel *channel, const ef4_qword_t *event) switch (rx_ev_hdr_type) { case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP: flags |= EF4_RX_PKT_TCP; - /* fall through */ + fallthrough; case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP: flags |= EF4_RX_PKT_CSUMMED; - /* fall through */ + fallthrough; case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_OTHER: case FSE_AZ_RX_EV_HDR_TYPE_OTHER: break; @@ -1310,7 +1310,7 @@ int ef4_farch_ev_process(struct ef4_channel *channel, int budget) if (efx->type->handle_global_event && efx->type->handle_global_event(channel, &event)) break; - /* else fall through */ + fallthrough; default: netif_err(channel->efx, hw, channel->efx->net_dev, "channel %d unknown event type %d (data " @@ -1983,7 +1983,7 @@ ef4_farch_filter_from_gen_spec(struct ef4_farch_filter_spec *spec, EF4_FILTER_MATCH_LOC_HOST | EF4_FILTER_MATCH_LOC_PORT | EF4_FILTER_MATCH_REM_HOST | EF4_FILTER_MATCH_REM_PORT): is_full = true; - /* fall through */ + fallthrough; case (EF4_FILTER_MATCH_ETHER_TYPE | EF4_FILTER_MATCH_IP_PROTO | EF4_FILTER_MATCH_LOC_HOST | EF4_FILTER_MATCH_LOC_PORT): { __be32 rhost, host1, host2; @@ -2034,7 +2034,7 @@ ef4_farch_filter_from_gen_spec(struct ef4_farch_filter_spec *spec, case EF4_FILTER_MATCH_LOC_MAC | EF4_FILTER_MATCH_OUTER_VID: is_full = true; - /* fall through */ + fallthrough; case EF4_FILTER_MATCH_LOC_MAC: spec->type = (is_full ? EF4_FARCH_FILTER_MAC_FULL : EF4_FARCH_FILTER_MAC_WILD); @@ -2081,7 +2081,7 @@ ef4_farch_filter_to_gen_spec(struct ef4_filter_spec *gen_spec, case EF4_FARCH_FILTER_TCP_FULL: case EF4_FARCH_FILTER_UDP_FULL: is_full = true; - /* fall through */ + fallthrough; case EF4_FARCH_FILTER_TCP_WILD: case EF4_FARCH_FILTER_UDP_WILD: { __be32 host1, host2; @@ -2125,7 +2125,7 @@ ef4_farch_filter_to_gen_spec(struct ef4_filter_spec *gen_spec, case EF4_FARCH_FILTER_MAC_FULL: is_full = true; - /* fall through */ + fallthrough; case EF4_FARCH_FILTER_MAC_WILD: gen_spec->match_flags = EF4_FILTER_MATCH_LOC_MAC; if (is_full) diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index d07eeaad9bdf..e004524e14a8 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -320,7 +320,7 @@ void efx_farch_tx_write(struct efx_tx_queue *tx_queue) unsigned write_ptr; unsigned old_write_count = tx_queue->write_count; - tx_queue->xmit_more_available = false; + tx_queue->xmit_pending = false; if (unlikely(tx_queue->write_count == tx_queue->insert_count)) return; @@ -863,13 +863,8 @@ static u16 efx_farch_handle_rx_not_ok(struct efx_rx_queue *rx_queue, bool rx_ev_tcp_udp_chksum_err, rx_ev_eth_crc_err; bool rx_ev_frm_trunc, rx_ev_tobe_disc; bool rx_ev_other_err, rx_ev_pause_frm; - bool rx_ev_hdr_type, rx_ev_mcast_pkt; - unsigned rx_ev_pkt_type; - rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE); - rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT); rx_ev_tobe_disc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_TOBE_DISC); - rx_ev_pkt_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_TYPE); rx_ev_buf_owner_id_err = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_BUF_OWNER_ID_ERR); rx_ev_ip_hdr_chksum_err = EFX_QWORD_FIELD(*event, @@ -918,6 +913,8 @@ static u16 efx_farch_handle_rx_not_ok(struct efx_rx_queue *rx_queue, rx_ev_tobe_disc ? " [TOBE_DISC]" : "", rx_ev_pause_frm ? " [PAUSE]" : ""); } +#else + (void) rx_ev_other_err; #endif if (efx->net_dev->features & NETIF_F_RXALL) @@ -1038,10 +1035,10 @@ efx_farch_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event) switch (rx_ev_hdr_type) { case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP: flags |= EFX_RX_PKT_TCP; - /* fall through */ + fallthrough; case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP: flags |= EFX_RX_PKT_CSUMMED; - /* fall through */ + fallthrough; case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_OTHER: case FSE_AZ_RX_EV_HDR_TYPE_OTHER: break; @@ -1316,7 +1313,7 @@ int efx_farch_ev_process(struct efx_channel *channel, int budget) if (efx->type->handle_global_event && efx->type->handle_global_event(channel, &event)) break; - /* else fall through */ + fallthrough; default: netif_err(channel->efx, hw, channel->efx->net_dev, "channel %d unknown event type %d (data " @@ -2043,7 +2040,7 @@ efx_farch_filter_from_gen_spec(struct efx_farch_filter_spec *spec, EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT | EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT): is_full = true; - /* fall through */ + fallthrough; case (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO | EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT): { __be32 rhost, host1, host2; @@ -2094,7 +2091,7 @@ efx_farch_filter_from_gen_spec(struct efx_farch_filter_spec *spec, case EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_OUTER_VID: is_full = true; - /* fall through */ + fallthrough; case EFX_FILTER_MATCH_LOC_MAC: spec->type = (is_full ? EFX_FARCH_FILTER_MAC_FULL : EFX_FARCH_FILTER_MAC_WILD); @@ -2141,7 +2138,7 @@ efx_farch_filter_to_gen_spec(struct efx_filter_spec *gen_spec, case EFX_FARCH_FILTER_TCP_FULL: case EFX_FARCH_FILTER_UDP_FULL: is_full = true; - /* fall through */ + fallthrough; case EFX_FARCH_FILTER_TCP_WILD: case EFX_FARCH_FILTER_UDP_WILD: { __be32 host1, host2; @@ -2185,7 +2182,7 @@ efx_farch_filter_to_gen_spec(struct efx_filter_spec *gen_spec, case EFX_FARCH_FILTER_MAC_FULL: is_full = true; - /* fall through */ + fallthrough; case EFX_FARCH_FILTER_MAC_WILD: gen_spec->match_flags = EFX_FILTER_MATCH_LOC_MAC; if (is_full) @@ -2592,7 +2589,6 @@ int efx_farch_filter_remove_safe(struct efx_nic *efx, enum efx_farch_filter_table_id table_id; struct efx_farch_filter_table *table; unsigned int filter_idx; - struct efx_farch_filter_spec *spec; int rc; table_id = efx_farch_filter_id_table_id(filter_id); @@ -2604,7 +2600,6 @@ int efx_farch_filter_remove_safe(struct efx_nic *efx, if (filter_idx >= table->size) return -ENOENT; down_write(&state->lock); - spec = &table->spec[filter_idx]; rc = efx_farch_filter_remove(efx, table, filter_idx, priority); up_write(&state->lock); diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 5467819aef6e..be6bfd6b7ec7 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -1868,10 +1868,9 @@ int efx_mcdi_handle_assertion(struct efx_nic *efx) return efx_mcdi_exit_assertion(efx); } -void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) +int efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) { MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_ID_LED_IN_LEN); - int rc; BUILD_BUG_ON(EFX_LED_OFF != MC_CMD_LED_OFF); BUILD_BUG_ON(EFX_LED_ON != MC_CMD_LED_ON); @@ -1881,8 +1880,7 @@ void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) MCDI_SET_DWORD(inbuf, SET_ID_LED_IN_STATE, mode); - rc = efx_mcdi_rpc(efx, MC_CMD_SET_ID_LED, inbuf, sizeof(inbuf), - NULL, 0, NULL); + return efx_mcdi_rpc(efx, MC_CMD_SET_ID_LED, inbuf, sizeof(inbuf), NULL, 0, NULL); } static int efx_mcdi_reset_func(struct efx_nic *efx) diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index 658cf345420d..ef6d21e4bd0b 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -348,14 +348,13 @@ int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type, int efx_new_mcdi_nvram_test_all(struct efx_nic *efx); int efx_mcdi_nvram_test_all(struct efx_nic *efx); int efx_mcdi_handle_assertion(struct efx_nic *efx); -void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); +int efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); int efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, const u8 *mac, int *id_out); int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out); int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id); int efx_mcdi_wol_filter_reset(struct efx_nic *efx); int efx_mcdi_flush_rxqs(struct efx_nic *efx); -int efx_mcdi_port_reconfigure(struct efx_nic *efx); void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev); void efx_mcdi_mac_start_stats(struct efx_nic *efx); void efx_mcdi_mac_stop_stats(struct efx_nic *efx); diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c index 5a74d880b733..1523be77b9db 100644 --- a/drivers/net/ethernet/sfc/mcdi_filters.c +++ b/drivers/net/ethernet/sfc/mcdi_filters.c @@ -140,7 +140,7 @@ efx_mcdi_filter_push_prep_set_match_fields(struct efx_nic *efx, switch (encap_type & EFX_ENCAP_TYPES_MASK) { case EFX_ENCAP_TYPE_VXLAN: vni_type = MC_CMD_FILTER_OP_EXT_IN_VNI_TYPE_VXLAN; - /* fallthrough */ + fallthrough; case EFX_ENCAP_TYPE_GENEVE: COPY_VALUE(ether_type, ETHER_TYPE); outer_ip_proto = IPPROTO_UDP; diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c index 98eeb404f68d..94c6a345c0b1 100644 --- a/drivers/net/ethernet/sfc/mcdi_port.c +++ b/drivers/net/ethernet/sfc/mcdi_port.c @@ -70,592 +70,6 @@ static int efx_mcdi_mdio_write(struct net_device *net_dev, return 0; } -static int efx_mcdi_phy_probe(struct efx_nic *efx) -{ - struct efx_mcdi_phy_data *phy_data; - MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN); - u32 caps; - int rc; - - /* Initialise and populate phy_data */ - phy_data = kzalloc(sizeof(*phy_data), GFP_KERNEL); - if (phy_data == NULL) - return -ENOMEM; - - rc = efx_mcdi_get_phy_cfg(efx, phy_data); - if (rc != 0) - goto fail; - - /* Read initial link advertisement */ - BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); - rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, - outbuf, sizeof(outbuf), NULL); - if (rc) - goto fail; - - /* Fill out nic state */ - efx->phy_data = phy_data; - efx->phy_type = phy_data->type; - - efx->mdio_bus = phy_data->channel; - efx->mdio.prtad = phy_data->port; - efx->mdio.mmds = phy_data->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22); - efx->mdio.mode_support = 0; - if (phy_data->mmd_mask & (1 << MC_CMD_MMD_CLAUSE22)) - efx->mdio.mode_support |= MDIO_SUPPORTS_C22; - if (phy_data->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22)) - efx->mdio.mode_support |= MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; - - caps = MCDI_DWORD(outbuf, GET_LINK_OUT_CAP); - if (caps & (1 << MC_CMD_PHY_CAP_AN_LBN)) - mcdi_to_ethtool_linkset(phy_data->media, caps, - efx->link_advertising); - else - phy_data->forced_cap = caps; - - /* Assert that we can map efx -> mcdi loopback modes */ - BUILD_BUG_ON(LOOPBACK_NONE != MC_CMD_LOOPBACK_NONE); - BUILD_BUG_ON(LOOPBACK_DATA != MC_CMD_LOOPBACK_DATA); - BUILD_BUG_ON(LOOPBACK_GMAC != MC_CMD_LOOPBACK_GMAC); - BUILD_BUG_ON(LOOPBACK_XGMII != MC_CMD_LOOPBACK_XGMII); - BUILD_BUG_ON(LOOPBACK_XGXS != MC_CMD_LOOPBACK_XGXS); - BUILD_BUG_ON(LOOPBACK_XAUI != MC_CMD_LOOPBACK_XAUI); - BUILD_BUG_ON(LOOPBACK_GMII != MC_CMD_LOOPBACK_GMII); - BUILD_BUG_ON(LOOPBACK_SGMII != MC_CMD_LOOPBACK_SGMII); - BUILD_BUG_ON(LOOPBACK_XGBR != MC_CMD_LOOPBACK_XGBR); - BUILD_BUG_ON(LOOPBACK_XFI != MC_CMD_LOOPBACK_XFI); - BUILD_BUG_ON(LOOPBACK_XAUI_FAR != MC_CMD_LOOPBACK_XAUI_FAR); - BUILD_BUG_ON(LOOPBACK_GMII_FAR != MC_CMD_LOOPBACK_GMII_FAR); - BUILD_BUG_ON(LOOPBACK_SGMII_FAR != MC_CMD_LOOPBACK_SGMII_FAR); - BUILD_BUG_ON(LOOPBACK_XFI_FAR != MC_CMD_LOOPBACK_XFI_FAR); - BUILD_BUG_ON(LOOPBACK_GPHY != MC_CMD_LOOPBACK_GPHY); - BUILD_BUG_ON(LOOPBACK_PHYXS != MC_CMD_LOOPBACK_PHYXS); - BUILD_BUG_ON(LOOPBACK_PCS != MC_CMD_LOOPBACK_PCS); - BUILD_BUG_ON(LOOPBACK_PMAPMD != MC_CMD_LOOPBACK_PMAPMD); - BUILD_BUG_ON(LOOPBACK_XPORT != MC_CMD_LOOPBACK_XPORT); - BUILD_BUG_ON(LOOPBACK_XGMII_WS != MC_CMD_LOOPBACK_XGMII_WS); - BUILD_BUG_ON(LOOPBACK_XAUI_WS != MC_CMD_LOOPBACK_XAUI_WS); - BUILD_BUG_ON(LOOPBACK_XAUI_WS_FAR != MC_CMD_LOOPBACK_XAUI_WS_FAR); - BUILD_BUG_ON(LOOPBACK_XAUI_WS_NEAR != MC_CMD_LOOPBACK_XAUI_WS_NEAR); - BUILD_BUG_ON(LOOPBACK_GMII_WS != MC_CMD_LOOPBACK_GMII_WS); - BUILD_BUG_ON(LOOPBACK_XFI_WS != MC_CMD_LOOPBACK_XFI_WS); - BUILD_BUG_ON(LOOPBACK_XFI_WS_FAR != MC_CMD_LOOPBACK_XFI_WS_FAR); - BUILD_BUG_ON(LOOPBACK_PHYXS_WS != MC_CMD_LOOPBACK_PHYXS_WS); - - rc = efx_mcdi_loopback_modes(efx, &efx->loopback_modes); - if (rc != 0) - goto fail; - /* The MC indicates that LOOPBACK_NONE is a valid loopback mode, - * but by convention we don't */ - efx->loopback_modes &= ~(1 << LOOPBACK_NONE); - - /* Set the initial link mode */ - efx_mcdi_phy_decode_link( - efx, &efx->link_state, - MCDI_DWORD(outbuf, GET_LINK_OUT_LINK_SPEED), - MCDI_DWORD(outbuf, GET_LINK_OUT_FLAGS), - MCDI_DWORD(outbuf, GET_LINK_OUT_FCNTL)); - - /* Record the initial FEC configuration (or nearest approximation - * representable in the ethtool configuration space) - */ - efx->fec_config = mcdi_fec_caps_to_ethtool(caps, - efx->link_state.speed == 25000 || - efx->link_state.speed == 50000); - - /* Default to Autonegotiated flow control if the PHY supports it */ - efx->wanted_fc = EFX_FC_RX | EFX_FC_TX; - if (phy_data->supported_cap & (1 << MC_CMD_PHY_CAP_AN_LBN)) - efx->wanted_fc |= EFX_FC_AUTO; - efx_link_set_wanted_fc(efx, efx->wanted_fc); - - return 0; - -fail: - kfree(phy_data); - return rc; -} - -static void efx_mcdi_phy_remove(struct efx_nic *efx) -{ - struct efx_mcdi_phy_data *phy_data = efx->phy_data; - - efx->phy_data = NULL; - kfree(phy_data); -} - -static void efx_mcdi_phy_get_link_ksettings(struct efx_nic *efx, - struct ethtool_link_ksettings *cmd) -{ - struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; - MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN); - int rc; - - cmd->base.speed = efx->link_state.speed; - cmd->base.duplex = efx->link_state.fd; - cmd->base.port = mcdi_to_ethtool_media(phy_cfg->media); - cmd->base.phy_address = phy_cfg->port; - cmd->base.autoneg = !!(efx->link_advertising[0] & ADVERTISED_Autoneg); - cmd->base.mdio_support = (efx->mdio.mode_support & - (MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22)); - - mcdi_to_ethtool_linkset(phy_cfg->media, phy_cfg->supported_cap, - cmd->link_modes.supported); - memcpy(cmd->link_modes.advertising, efx->link_advertising, - sizeof(__ETHTOOL_DECLARE_LINK_MODE_MASK())); - - BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); - rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, - outbuf, sizeof(outbuf), NULL); - if (rc) - return; - mcdi_to_ethtool_linkset(phy_cfg->media, - MCDI_DWORD(outbuf, GET_LINK_OUT_LP_CAP), - cmd->link_modes.lp_advertising); -} - -static int -efx_mcdi_phy_set_link_ksettings(struct efx_nic *efx, - const struct ethtool_link_ksettings *cmd) -{ - struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; - u32 caps; - int rc; - - if (cmd->base.autoneg) { - caps = (ethtool_linkset_to_mcdi_cap(cmd->link_modes.advertising) | - 1 << MC_CMD_PHY_CAP_AN_LBN); - } else if (cmd->base.duplex) { - switch (cmd->base.speed) { - case 10: caps = 1 << MC_CMD_PHY_CAP_10FDX_LBN; break; - case 100: caps = 1 << MC_CMD_PHY_CAP_100FDX_LBN; break; - case 1000: caps = 1 << MC_CMD_PHY_CAP_1000FDX_LBN; break; - case 10000: caps = 1 << MC_CMD_PHY_CAP_10000FDX_LBN; break; - case 40000: caps = 1 << MC_CMD_PHY_CAP_40000FDX_LBN; break; - case 100000: caps = 1 << MC_CMD_PHY_CAP_100000FDX_LBN; break; - case 25000: caps = 1 << MC_CMD_PHY_CAP_25000FDX_LBN; break; - case 50000: caps = 1 << MC_CMD_PHY_CAP_50000FDX_LBN; break; - default: return -EINVAL; - } - } else { - switch (cmd->base.speed) { - case 10: caps = 1 << MC_CMD_PHY_CAP_10HDX_LBN; break; - case 100: caps = 1 << MC_CMD_PHY_CAP_100HDX_LBN; break; - case 1000: caps = 1 << MC_CMD_PHY_CAP_1000HDX_LBN; break; - default: return -EINVAL; - } - } - - caps |= ethtool_fec_caps_to_mcdi(efx->fec_config); - - rc = efx_mcdi_set_link(efx, caps, efx_get_mcdi_phy_flags(efx), - efx->loopback_mode, 0); - if (rc) - return rc; - - if (cmd->base.autoneg) { - efx_link_set_advertising(efx, cmd->link_modes.advertising); - phy_cfg->forced_cap = 0; - } else { - efx_link_clear_advertising(efx); - phy_cfg->forced_cap = caps; - } - return 0; -} - -static int efx_mcdi_phy_set_fecparam(struct efx_nic *efx, - const struct ethtool_fecparam *fec) -{ - struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; - u32 caps; - int rc; - - /* Work out what efx_mcdi_phy_set_link_ksettings() would produce from - * saved advertising bits - */ - if (test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, efx->link_advertising)) - caps = (ethtool_linkset_to_mcdi_cap(efx->link_advertising) | - 1 << MC_CMD_PHY_CAP_AN_LBN); - else - caps = phy_cfg->forced_cap; - - caps |= ethtool_fec_caps_to_mcdi(fec->fec); - rc = efx_mcdi_set_link(efx, caps, efx_get_mcdi_phy_flags(efx), - efx->loopback_mode, 0); - if (rc) - return rc; - - /* Record the new FEC setting for subsequent set_link calls */ - efx->fec_config = fec->fec; - return 0; -} - -static const char *const mcdi_sft9001_cable_diag_names[] = { - "cable.pairA.length", - "cable.pairB.length", - "cable.pairC.length", - "cable.pairD.length", - "cable.pairA.status", - "cable.pairB.status", - "cable.pairC.status", - "cable.pairD.status", -}; - -static int efx_mcdi_bist(struct efx_nic *efx, unsigned int bist_mode, - int *results) -{ - unsigned int retry, i, count = 0; - size_t outlen; - u32 status; - MCDI_DECLARE_BUF(inbuf, MC_CMD_START_BIST_IN_LEN); - MCDI_DECLARE_BUF(outbuf, MC_CMD_POLL_BIST_OUT_SFT9001_LEN); - u8 *ptr; - int rc; - - BUILD_BUG_ON(MC_CMD_START_BIST_OUT_LEN != 0); - MCDI_SET_DWORD(inbuf, START_BIST_IN_TYPE, bist_mode); - rc = efx_mcdi_rpc(efx, MC_CMD_START_BIST, - inbuf, MC_CMD_START_BIST_IN_LEN, NULL, 0, NULL); - if (rc) - goto out; - - /* Wait up to 10s for BIST to finish */ - for (retry = 0; retry < 100; ++retry) { - BUILD_BUG_ON(MC_CMD_POLL_BIST_IN_LEN != 0); - rc = efx_mcdi_rpc(efx, MC_CMD_POLL_BIST, NULL, 0, - outbuf, sizeof(outbuf), &outlen); - if (rc) - goto out; - - status = MCDI_DWORD(outbuf, POLL_BIST_OUT_RESULT); - if (status != MC_CMD_POLL_BIST_RUNNING) - goto finished; - - msleep(100); - } - - rc = -ETIMEDOUT; - goto out; - -finished: - results[count++] = (status == MC_CMD_POLL_BIST_PASSED) ? 1 : -1; - - /* SFT9001 specific cable diagnostics output */ - if (efx->phy_type == PHY_TYPE_SFT9001B && - (bist_mode == MC_CMD_PHY_BIST_CABLE_SHORT || - bist_mode == MC_CMD_PHY_BIST_CABLE_LONG)) { - ptr = MCDI_PTR(outbuf, POLL_BIST_OUT_SFT9001_CABLE_LENGTH_A); - if (status == MC_CMD_POLL_BIST_PASSED && - outlen >= MC_CMD_POLL_BIST_OUT_SFT9001_LEN) { - for (i = 0; i < 8; i++) { - results[count + i] = - EFX_DWORD_FIELD(((efx_dword_t *)ptr)[i], - EFX_DWORD_0); - } - } - count += 8; - } - rc = count; - -out: - return rc; -} - -static int efx_mcdi_phy_run_tests(struct efx_nic *efx, int *results, - unsigned flags) -{ - struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; - u32 mode; - int rc; - - if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_LBN)) { - rc = efx_mcdi_bist(efx, MC_CMD_PHY_BIST, results); - if (rc < 0) - return rc; - - results += rc; - } - - /* If we support both LONG and SHORT, then run each in response to - * break or not. Otherwise, run the one we support */ - mode = 0; - if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_SHORT_LBN)) { - if ((flags & ETH_TEST_FL_OFFLINE) && - (phy_cfg->flags & - (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN))) - mode = MC_CMD_PHY_BIST_CABLE_LONG; - else - mode = MC_CMD_PHY_BIST_CABLE_SHORT; - } else if (phy_cfg->flags & - (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN)) - mode = MC_CMD_PHY_BIST_CABLE_LONG; - - if (mode != 0) { - rc = efx_mcdi_bist(efx, mode, results); - if (rc < 0) - return rc; - results += rc; - } - - return 0; -} - -static const char *efx_mcdi_phy_test_name(struct efx_nic *efx, - unsigned int index) -{ - struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; - - if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_LBN)) { - if (index == 0) - return "bist"; - --index; - } - - if (phy_cfg->flags & ((1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_SHORT_LBN) | - (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN))) { - if (index == 0) - return "cable"; - --index; - - if (efx->phy_type == PHY_TYPE_SFT9001B) { - if (index < ARRAY_SIZE(mcdi_sft9001_cable_diag_names)) - return mcdi_sft9001_cable_diag_names[index]; - index -= ARRAY_SIZE(mcdi_sft9001_cable_diag_names); - } - } - - return NULL; -} - -#define SFP_PAGE_SIZE 128 -#define SFF_DIAG_TYPE_OFFSET 92 -#define SFF_DIAG_ADDR_CHANGE BIT(2) -#define SFF_8079_NUM_PAGES 2 -#define SFF_8472_NUM_PAGES 4 -#define SFF_8436_NUM_PAGES 5 -#define SFF_DMT_LEVEL_OFFSET 94 - -/** efx_mcdi_phy_get_module_eeprom_page() - Get a single page of module eeprom - * @efx: NIC context - * @page: EEPROM page number - * @data: Destination data pointer - * @offset: Offset in page to copy from in to data - * @space: Space available in data - * - * Return: - * >=0 - amount of data copied - * <0 - error - */ -static int efx_mcdi_phy_get_module_eeprom_page(struct efx_nic *efx, - unsigned int page, - u8 *data, ssize_t offset, - ssize_t space) -{ - MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX); - MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_PHY_MEDIA_INFO_IN_LEN); - size_t outlen; - unsigned int payload_len; - unsigned int to_copy; - int rc; - - if (offset > SFP_PAGE_SIZE) - return -EINVAL; - - to_copy = min(space, SFP_PAGE_SIZE - offset); - - MCDI_SET_DWORD(inbuf, GET_PHY_MEDIA_INFO_IN_PAGE, page); - rc = efx_mcdi_rpc_quiet(efx, MC_CMD_GET_PHY_MEDIA_INFO, - inbuf, sizeof(inbuf), - outbuf, sizeof(outbuf), - &outlen); - - if (rc) - return rc; - - if (outlen < (MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST + - SFP_PAGE_SIZE)) - return -EIO; - - payload_len = MCDI_DWORD(outbuf, GET_PHY_MEDIA_INFO_OUT_DATALEN); - if (payload_len != SFP_PAGE_SIZE) - return -EIO; - - memcpy(data, MCDI_PTR(outbuf, GET_PHY_MEDIA_INFO_OUT_DATA) + offset, - to_copy); - - return to_copy; -} - -static int efx_mcdi_phy_get_module_eeprom_byte(struct efx_nic *efx, - unsigned int page, - u8 byte) -{ - int rc; - u8 data; - - rc = efx_mcdi_phy_get_module_eeprom_page(efx, page, &data, byte, 1); - if (rc == 1) - return data; - - return rc; -} - -static int efx_mcdi_phy_diag_type(struct efx_nic *efx) -{ - /* Page zero of the EEPROM includes the diagnostic type at byte 92. */ - return efx_mcdi_phy_get_module_eeprom_byte(efx, 0, - SFF_DIAG_TYPE_OFFSET); -} - -static int efx_mcdi_phy_sff_8472_level(struct efx_nic *efx) -{ - /* Page zero of the EEPROM includes the DMT level at byte 94. */ - return efx_mcdi_phy_get_module_eeprom_byte(efx, 0, - SFF_DMT_LEVEL_OFFSET); -} - -static u32 efx_mcdi_phy_module_type(struct efx_nic *efx) -{ - struct efx_mcdi_phy_data *phy_data = efx->phy_data; - - if (phy_data->media != MC_CMD_MEDIA_QSFP_PLUS) - return phy_data->media; - - /* A QSFP+ NIC may actually have an SFP+ module attached. - * The ID is page 0, byte 0. - */ - switch (efx_mcdi_phy_get_module_eeprom_byte(efx, 0, 0)) { - case 0x3: - return MC_CMD_MEDIA_SFP_PLUS; - case 0xc: - case 0xd: - return MC_CMD_MEDIA_QSFP_PLUS; - default: - return 0; - } -} - -static int efx_mcdi_phy_get_module_eeprom(struct efx_nic *efx, - struct ethtool_eeprom *ee, u8 *data) -{ - int rc; - ssize_t space_remaining = ee->len; - unsigned int page_off; - bool ignore_missing; - int num_pages; - int page; - - switch (efx_mcdi_phy_module_type(efx)) { - case MC_CMD_MEDIA_SFP_PLUS: - num_pages = efx_mcdi_phy_sff_8472_level(efx) > 0 ? - SFF_8472_NUM_PAGES : SFF_8079_NUM_PAGES; - page = 0; - ignore_missing = false; - break; - case MC_CMD_MEDIA_QSFP_PLUS: - num_pages = SFF_8436_NUM_PAGES; - page = -1; /* We obtain the lower page by asking for -1. */ - ignore_missing = true; /* Ignore missing pages after page 0. */ - break; - default: - return -EOPNOTSUPP; - } - - page_off = ee->offset % SFP_PAGE_SIZE; - page += ee->offset / SFP_PAGE_SIZE; - - while (space_remaining && (page < num_pages)) { - rc = efx_mcdi_phy_get_module_eeprom_page(efx, page, - data, page_off, - space_remaining); - - if (rc > 0) { - space_remaining -= rc; - data += rc; - page_off = 0; - page++; - } else if (rc == 0) { - space_remaining = 0; - } else if (ignore_missing && (page > 0)) { - int intended_size = SFP_PAGE_SIZE - page_off; - - space_remaining -= intended_size; - if (space_remaining < 0) { - space_remaining = 0; - } else { - memset(data, 0, intended_size); - data += intended_size; - page_off = 0; - page++; - rc = 0; - } - } else { - return rc; - } - } - - return 0; -} - -static int efx_mcdi_phy_get_module_info(struct efx_nic *efx, - struct ethtool_modinfo *modinfo) -{ - int sff_8472_level; - int diag_type; - - switch (efx_mcdi_phy_module_type(efx)) { - case MC_CMD_MEDIA_SFP_PLUS: - sff_8472_level = efx_mcdi_phy_sff_8472_level(efx); - - /* If we can't read the diagnostics level we have none. */ - if (sff_8472_level < 0) - return -EOPNOTSUPP; - - /* Check if this module requires the (unsupported) address - * change operation. - */ - diag_type = efx_mcdi_phy_diag_type(efx); - - if ((sff_8472_level == 0) || - (diag_type & SFF_DIAG_ADDR_CHANGE)) { - modinfo->type = ETH_MODULE_SFF_8079; - modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; - } else { - modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; - } - break; - - case MC_CMD_MEDIA_QSFP_PLUS: - modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; - break; - - default: - return -EOPNOTSUPP; - } - - return 0; -} - -static const struct efx_phy_operations efx_mcdi_phy_ops = { - .probe = efx_mcdi_phy_probe, - .init = efx_port_dummy_op_int, - .reconfigure = efx_mcdi_port_reconfigure, - .poll = efx_mcdi_phy_poll, - .fini = efx_port_dummy_op_void, - .remove = efx_mcdi_phy_remove, - .get_link_ksettings = efx_mcdi_phy_get_link_ksettings, - .set_link_ksettings = efx_mcdi_phy_set_link_ksettings, - .get_fecparam = efx_mcdi_phy_get_fecparam, - .set_fecparam = efx_mcdi_phy_set_fecparam, - .test_alive = efx_mcdi_phy_test_alive, - .run_tests = efx_mcdi_phy_run_tests, - .test_name = efx_mcdi_phy_test_name, - .get_module_eeprom = efx_mcdi_phy_get_module_eeprom, - .get_module_info = efx_mcdi_phy_get_module_info, -}; - u32 efx_mcdi_phy_get_caps(struct efx_nic *efx) { struct efx_mcdi_phy_data *phy_data = efx->phy_data; @@ -683,16 +97,13 @@ int efx_mcdi_port_probe(struct efx_nic *efx) { int rc; - /* Hook in PHY operations table */ - efx->phy_op = &efx_mcdi_phy_ops; - /* Set up MDIO structure for PHY */ efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; efx->mdio.mdio_read = efx_mcdi_mdio_read; efx->mdio.mdio_write = efx_mcdi_mdio_write; /* Fill out MDIO structure, loopback modes, and initial link state */ - rc = efx->phy_op->probe(efx); + rc = efx_mcdi_phy_probe(efx); if (rc != 0) return rc; @@ -701,6 +112,6 @@ int efx_mcdi_port_probe(struct efx_nic *efx) void efx_mcdi_port_remove(struct efx_nic *efx) { - efx->phy_op->remove(efx); + efx_mcdi_phy_remove(efx); efx_mcdi_mac_fini_stats(efx); } diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c index 56af8b54a864..4bd3ef8f3384 100644 --- a/drivers/net/ethernet/sfc/mcdi_port_common.c +++ b/drivers/net/ethernet/sfc/mcdi_port_common.c @@ -282,7 +282,7 @@ void efx_mcdi_phy_decode_link(struct efx_nic *efx, break; default: WARN_ON(1); - /* Fall through */ + fallthrough; case MC_CMD_FCNTL_OFF: link_state->fc = 0; break; @@ -308,7 +308,7 @@ void efx_mcdi_phy_decode_link(struct efx_nic *efx, * Both RS and BASER (whether AUTO or not) means use FEC if cable and link * partner support it, preferring RS to BASER. */ -u32 ethtool_fec_caps_to_mcdi(u32 ethtool_cap) +u32 ethtool_fec_caps_to_mcdi(u32 supported_cap, u32 ethtool_cap) { u32 ret = 0; @@ -316,17 +316,21 @@ u32 ethtool_fec_caps_to_mcdi(u32 ethtool_cap) return 0; if (ethtool_cap & ETHTOOL_FEC_AUTO) - ret |= (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN) | - (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN) | - (1 << MC_CMD_PHY_CAP_RS_FEC_LBN); - if (ethtool_cap & ETHTOOL_FEC_RS) + ret |= ((1 << MC_CMD_PHY_CAP_BASER_FEC_LBN) | + (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN) | + (1 << MC_CMD_PHY_CAP_RS_FEC_LBN)) & supported_cap; + if (ethtool_cap & ETHTOOL_FEC_RS && + supported_cap & (1 << MC_CMD_PHY_CAP_RS_FEC_LBN)) ret |= (1 << MC_CMD_PHY_CAP_RS_FEC_LBN) | (1 << MC_CMD_PHY_CAP_RS_FEC_REQUESTED_LBN); - if (ethtool_cap & ETHTOOL_FEC_BASER) - ret |= (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN) | - (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN) | - (1 << MC_CMD_PHY_CAP_BASER_FEC_REQUESTED_LBN) | - (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_LBN); + if (ethtool_cap & ETHTOOL_FEC_BASER) { + if (supported_cap & (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN)) + ret |= (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN) | + (1 << MC_CMD_PHY_CAP_BASER_FEC_REQUESTED_LBN); + if (supported_cap & (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN)) + ret |= (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN) | + (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_LBN); + } return ret; } @@ -404,6 +408,196 @@ bool efx_mcdi_phy_poll(struct efx_nic *efx) return !efx_link_state_equal(&efx->link_state, &old_state); } +int efx_mcdi_phy_probe(struct efx_nic *efx) +{ + struct efx_mcdi_phy_data *phy_data; + MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN); + u32 caps; + int rc; + + /* Initialise and populate phy_data */ + phy_data = kzalloc(sizeof(*phy_data), GFP_KERNEL); + if (phy_data == NULL) + return -ENOMEM; + + rc = efx_mcdi_get_phy_cfg(efx, phy_data); + if (rc != 0) + goto fail; + + /* Read initial link advertisement */ + BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); + rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, + outbuf, sizeof(outbuf), NULL); + if (rc) + goto fail; + + /* Fill out nic state */ + efx->phy_data = phy_data; + efx->phy_type = phy_data->type; + + efx->mdio_bus = phy_data->channel; + efx->mdio.prtad = phy_data->port; + efx->mdio.mmds = phy_data->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22); + efx->mdio.mode_support = 0; + if (phy_data->mmd_mask & (1 << MC_CMD_MMD_CLAUSE22)) + efx->mdio.mode_support |= MDIO_SUPPORTS_C22; + if (phy_data->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22)) + efx->mdio.mode_support |= MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; + + caps = MCDI_DWORD(outbuf, GET_LINK_OUT_CAP); + if (caps & (1 << MC_CMD_PHY_CAP_AN_LBN)) + mcdi_to_ethtool_linkset(phy_data->media, caps, + efx->link_advertising); + else + phy_data->forced_cap = caps; + + /* Assert that we can map efx -> mcdi loopback modes */ + BUILD_BUG_ON(LOOPBACK_NONE != MC_CMD_LOOPBACK_NONE); + BUILD_BUG_ON(LOOPBACK_DATA != MC_CMD_LOOPBACK_DATA); + BUILD_BUG_ON(LOOPBACK_GMAC != MC_CMD_LOOPBACK_GMAC); + BUILD_BUG_ON(LOOPBACK_XGMII != MC_CMD_LOOPBACK_XGMII); + BUILD_BUG_ON(LOOPBACK_XGXS != MC_CMD_LOOPBACK_XGXS); + BUILD_BUG_ON(LOOPBACK_XAUI != MC_CMD_LOOPBACK_XAUI); + BUILD_BUG_ON(LOOPBACK_GMII != MC_CMD_LOOPBACK_GMII); + BUILD_BUG_ON(LOOPBACK_SGMII != MC_CMD_LOOPBACK_SGMII); + BUILD_BUG_ON(LOOPBACK_XGBR != MC_CMD_LOOPBACK_XGBR); + BUILD_BUG_ON(LOOPBACK_XFI != MC_CMD_LOOPBACK_XFI); + BUILD_BUG_ON(LOOPBACK_XAUI_FAR != MC_CMD_LOOPBACK_XAUI_FAR); + BUILD_BUG_ON(LOOPBACK_GMII_FAR != MC_CMD_LOOPBACK_GMII_FAR); + BUILD_BUG_ON(LOOPBACK_SGMII_FAR != MC_CMD_LOOPBACK_SGMII_FAR); + BUILD_BUG_ON(LOOPBACK_XFI_FAR != MC_CMD_LOOPBACK_XFI_FAR); + BUILD_BUG_ON(LOOPBACK_GPHY != MC_CMD_LOOPBACK_GPHY); + BUILD_BUG_ON(LOOPBACK_PHYXS != MC_CMD_LOOPBACK_PHYXS); + BUILD_BUG_ON(LOOPBACK_PCS != MC_CMD_LOOPBACK_PCS); + BUILD_BUG_ON(LOOPBACK_PMAPMD != MC_CMD_LOOPBACK_PMAPMD); + BUILD_BUG_ON(LOOPBACK_XPORT != MC_CMD_LOOPBACK_XPORT); + BUILD_BUG_ON(LOOPBACK_XGMII_WS != MC_CMD_LOOPBACK_XGMII_WS); + BUILD_BUG_ON(LOOPBACK_XAUI_WS != MC_CMD_LOOPBACK_XAUI_WS); + BUILD_BUG_ON(LOOPBACK_XAUI_WS_FAR != MC_CMD_LOOPBACK_XAUI_WS_FAR); + BUILD_BUG_ON(LOOPBACK_XAUI_WS_NEAR != MC_CMD_LOOPBACK_XAUI_WS_NEAR); + BUILD_BUG_ON(LOOPBACK_GMII_WS != MC_CMD_LOOPBACK_GMII_WS); + BUILD_BUG_ON(LOOPBACK_XFI_WS != MC_CMD_LOOPBACK_XFI_WS); + BUILD_BUG_ON(LOOPBACK_XFI_WS_FAR != MC_CMD_LOOPBACK_XFI_WS_FAR); + BUILD_BUG_ON(LOOPBACK_PHYXS_WS != MC_CMD_LOOPBACK_PHYXS_WS); + + rc = efx_mcdi_loopback_modes(efx, &efx->loopback_modes); + if (rc != 0) + goto fail; + /* The MC indicates that LOOPBACK_NONE is a valid loopback mode, + * but by convention we don't + */ + efx->loopback_modes &= ~(1 << LOOPBACK_NONE); + + /* Set the initial link mode */ + efx_mcdi_phy_decode_link(efx, &efx->link_state, + MCDI_DWORD(outbuf, GET_LINK_OUT_LINK_SPEED), + MCDI_DWORD(outbuf, GET_LINK_OUT_FLAGS), + MCDI_DWORD(outbuf, GET_LINK_OUT_FCNTL)); + + /* Record the initial FEC configuration (or nearest approximation + * representable in the ethtool configuration space) + */ + efx->fec_config = mcdi_fec_caps_to_ethtool(caps, + efx->link_state.speed == 25000 || + efx->link_state.speed == 50000); + + /* Default to Autonegotiated flow control if the PHY supports it */ + efx->wanted_fc = EFX_FC_RX | EFX_FC_TX; + if (phy_data->supported_cap & (1 << MC_CMD_PHY_CAP_AN_LBN)) + efx->wanted_fc |= EFX_FC_AUTO; + efx_link_set_wanted_fc(efx, efx->wanted_fc); + + return 0; + +fail: + kfree(phy_data); + return rc; +} + +void efx_mcdi_phy_remove(struct efx_nic *efx) +{ + struct efx_mcdi_phy_data *phy_data = efx->phy_data; + + efx->phy_data = NULL; + kfree(phy_data); +} + +void efx_mcdi_phy_get_link_ksettings(struct efx_nic *efx, struct ethtool_link_ksettings *cmd) +{ + struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; + MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN); + int rc; + + cmd->base.speed = efx->link_state.speed; + cmd->base.duplex = efx->link_state.fd; + cmd->base.port = mcdi_to_ethtool_media(phy_cfg->media); + cmd->base.phy_address = phy_cfg->port; + cmd->base.autoneg = !!(efx->link_advertising[0] & ADVERTISED_Autoneg); + cmd->base.mdio_support = (efx->mdio.mode_support & + (MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22)); + + mcdi_to_ethtool_linkset(phy_cfg->media, phy_cfg->supported_cap, + cmd->link_modes.supported); + memcpy(cmd->link_modes.advertising, efx->link_advertising, + sizeof(__ETHTOOL_DECLARE_LINK_MODE_MASK())); + + BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); + rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, + outbuf, sizeof(outbuf), NULL); + if (rc) + return; + mcdi_to_ethtool_linkset(phy_cfg->media, + MCDI_DWORD(outbuf, GET_LINK_OUT_LP_CAP), + cmd->link_modes.lp_advertising); +} + +int efx_mcdi_phy_set_link_ksettings(struct efx_nic *efx, const struct ethtool_link_ksettings *cmd) +{ + struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; + u32 caps; + int rc; + + if (cmd->base.autoneg) { + caps = (ethtool_linkset_to_mcdi_cap(cmd->link_modes.advertising) | + 1 << MC_CMD_PHY_CAP_AN_LBN); + } else if (cmd->base.duplex) { + switch (cmd->base.speed) { + case 10: caps = 1 << MC_CMD_PHY_CAP_10FDX_LBN; break; + case 100: caps = 1 << MC_CMD_PHY_CAP_100FDX_LBN; break; + case 1000: caps = 1 << MC_CMD_PHY_CAP_1000FDX_LBN; break; + case 10000: caps = 1 << MC_CMD_PHY_CAP_10000FDX_LBN; break; + case 40000: caps = 1 << MC_CMD_PHY_CAP_40000FDX_LBN; break; + case 100000: caps = 1 << MC_CMD_PHY_CAP_100000FDX_LBN; break; + case 25000: caps = 1 << MC_CMD_PHY_CAP_25000FDX_LBN; break; + case 50000: caps = 1 << MC_CMD_PHY_CAP_50000FDX_LBN; break; + default: return -EINVAL; + } + } else { + switch (cmd->base.speed) { + case 10: caps = 1 << MC_CMD_PHY_CAP_10HDX_LBN; break; + case 100: caps = 1 << MC_CMD_PHY_CAP_100HDX_LBN; break; + case 1000: caps = 1 << MC_CMD_PHY_CAP_1000HDX_LBN; break; + default: return -EINVAL; + } + } + + caps |= ethtool_fec_caps_to_mcdi(phy_cfg->supported_cap, efx->fec_config); + + rc = efx_mcdi_set_link(efx, caps, efx_get_mcdi_phy_flags(efx), + efx->loopback_mode, 0); + if (rc) + return rc; + + if (cmd->base.autoneg) { + efx_link_set_advertising(efx, cmd->link_modes.advertising); + phy_cfg->forced_cap = 0; + } else { + efx_link_clear_advertising(efx); + phy_cfg->forced_cap = caps; + } + return 0; +} + int efx_mcdi_phy_get_fecparam(struct efx_nic *efx, struct ethtool_fecparam *fec) { MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_V2_LEN); @@ -455,6 +649,50 @@ int efx_mcdi_phy_get_fecparam(struct efx_nic *efx, struct ethtool_fecparam *fec) return 0; } +/* Basic validation to ensure that the caps we are going to attempt to set are + * in fact supported by the adapter. Note that 'no FEC' is always supported. + */ +static int ethtool_fec_supported(u32 supported_cap, u32 ethtool_cap) +{ + if (ethtool_cap & ETHTOOL_FEC_OFF) + return 0; + + if (ethtool_cap && + !ethtool_fec_caps_to_mcdi(supported_cap, ethtool_cap)) + return -EINVAL; + return 0; +} + +int efx_mcdi_phy_set_fecparam(struct efx_nic *efx, const struct ethtool_fecparam *fec) +{ + struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; + u32 caps; + int rc; + + rc = ethtool_fec_supported(phy_cfg->supported_cap, fec->fec); + if (rc) + return rc; + + /* Work out what efx_mcdi_phy_set_link_ksettings() would produce from + * saved advertising bits + */ + if (test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, efx->link_advertising)) + caps = (ethtool_linkset_to_mcdi_cap(efx->link_advertising) | + 1 << MC_CMD_PHY_CAP_AN_LBN); + else + caps = phy_cfg->forced_cap; + + caps |= ethtool_fec_caps_to_mcdi(phy_cfg->supported_cap, fec->fec); + rc = efx_mcdi_set_link(efx, caps, efx_get_mcdi_phy_flags(efx), + efx->loopback_mode, 0); + if (rc) + return rc; + + /* Record the new FEC setting for subsequent set_link calls */ + efx->fec_config = fec->fec; + return 0; +} + int efx_mcdi_phy_test_alive(struct efx_nic *efx) { MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_STATE_OUT_LEN); @@ -483,12 +721,357 @@ int efx_mcdi_port_reconfigure(struct efx_nic *efx) ethtool_linkset_to_mcdi_cap(efx->link_advertising) : phy_cfg->forced_cap); - caps |= ethtool_fec_caps_to_mcdi(efx->fec_config); + caps |= ethtool_fec_caps_to_mcdi(phy_cfg->supported_cap, efx->fec_config); return efx_mcdi_set_link(efx, caps, efx_get_mcdi_phy_flags(efx), efx->loopback_mode, 0); } +static const char *const mcdi_sft9001_cable_diag_names[] = { + "cable.pairA.length", + "cable.pairB.length", + "cable.pairC.length", + "cable.pairD.length", + "cable.pairA.status", + "cable.pairB.status", + "cable.pairC.status", + "cable.pairD.status", +}; + +static int efx_mcdi_bist(struct efx_nic *efx, unsigned int bist_mode, + int *results) +{ + unsigned int retry, i, count = 0; + size_t outlen; + u32 status; + MCDI_DECLARE_BUF(inbuf, MC_CMD_START_BIST_IN_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_POLL_BIST_OUT_SFT9001_LEN); + u8 *ptr; + int rc; + + BUILD_BUG_ON(MC_CMD_START_BIST_OUT_LEN != 0); + MCDI_SET_DWORD(inbuf, START_BIST_IN_TYPE, bist_mode); + rc = efx_mcdi_rpc(efx, MC_CMD_START_BIST, + inbuf, MC_CMD_START_BIST_IN_LEN, NULL, 0, NULL); + if (rc) + goto out; + + /* Wait up to 10s for BIST to finish */ + for (retry = 0; retry < 100; ++retry) { + BUILD_BUG_ON(MC_CMD_POLL_BIST_IN_LEN != 0); + rc = efx_mcdi_rpc(efx, MC_CMD_POLL_BIST, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto out; + + status = MCDI_DWORD(outbuf, POLL_BIST_OUT_RESULT); + if (status != MC_CMD_POLL_BIST_RUNNING) + goto finished; + + msleep(100); + } + + rc = -ETIMEDOUT; + goto out; + +finished: + results[count++] = (status == MC_CMD_POLL_BIST_PASSED) ? 1 : -1; + + /* SFT9001 specific cable diagnostics output */ + if (efx->phy_type == PHY_TYPE_SFT9001B && + (bist_mode == MC_CMD_PHY_BIST_CABLE_SHORT || + bist_mode == MC_CMD_PHY_BIST_CABLE_LONG)) { + ptr = MCDI_PTR(outbuf, POLL_BIST_OUT_SFT9001_CABLE_LENGTH_A); + if (status == MC_CMD_POLL_BIST_PASSED && + outlen >= MC_CMD_POLL_BIST_OUT_SFT9001_LEN) { + for (i = 0; i < 8; i++) { + results[count + i] = + EFX_DWORD_FIELD(((efx_dword_t *)ptr)[i], + EFX_DWORD_0); + } + } + count += 8; + } + rc = count; + +out: + return rc; +} + +int efx_mcdi_phy_run_tests(struct efx_nic *efx, int *results, unsigned int flags) +{ + struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; + u32 mode; + int rc; + + if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_LBN)) { + rc = efx_mcdi_bist(efx, MC_CMD_PHY_BIST, results); + if (rc < 0) + return rc; + + results += rc; + } + + /* If we support both LONG and SHORT, then run each in response to + * break or not. Otherwise, run the one we support + */ + mode = 0; + if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_SHORT_LBN)) { + if ((flags & ETH_TEST_FL_OFFLINE) && + (phy_cfg->flags & + (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN))) + mode = MC_CMD_PHY_BIST_CABLE_LONG; + else + mode = MC_CMD_PHY_BIST_CABLE_SHORT; + } else if (phy_cfg->flags & + (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN)) + mode = MC_CMD_PHY_BIST_CABLE_LONG; + + if (mode != 0) { + rc = efx_mcdi_bist(efx, mode, results); + if (rc < 0) + return rc; + results += rc; + } + + return 0; +} + +const char *efx_mcdi_phy_test_name(struct efx_nic *efx, unsigned int index) +{ + struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; + + if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_LBN)) { + if (index == 0) + return "bist"; + --index; + } + + if (phy_cfg->flags & ((1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_SHORT_LBN) | + (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN))) { + if (index == 0) + return "cable"; + --index; + + if (efx->phy_type == PHY_TYPE_SFT9001B) { + if (index < ARRAY_SIZE(mcdi_sft9001_cable_diag_names)) + return mcdi_sft9001_cable_diag_names[index]; + index -= ARRAY_SIZE(mcdi_sft9001_cable_diag_names); + } + } + + return NULL; +} + +#define SFP_PAGE_SIZE 128 +#define SFF_DIAG_TYPE_OFFSET 92 +#define SFF_DIAG_ADDR_CHANGE BIT(2) +#define SFF_8079_NUM_PAGES 2 +#define SFF_8472_NUM_PAGES 4 +#define SFF_8436_NUM_PAGES 5 +#define SFF_DMT_LEVEL_OFFSET 94 + +/** efx_mcdi_phy_get_module_eeprom_page() - Get a single page of module eeprom + * @efx: NIC context + * @page: EEPROM page number + * @data: Destination data pointer + * @offset: Offset in page to copy from in to data + * @space: Space available in data + * + * Return: + * >=0 - amount of data copied + * <0 - error + */ +static int efx_mcdi_phy_get_module_eeprom_page(struct efx_nic *efx, + unsigned int page, + u8 *data, ssize_t offset, + ssize_t space) +{ + MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX); + MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_PHY_MEDIA_INFO_IN_LEN); + unsigned int payload_len; + unsigned int to_copy; + size_t outlen; + int rc; + + if (offset > SFP_PAGE_SIZE) + return -EINVAL; + + to_copy = min(space, SFP_PAGE_SIZE - offset); + + MCDI_SET_DWORD(inbuf, GET_PHY_MEDIA_INFO_IN_PAGE, page); + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_GET_PHY_MEDIA_INFO, + inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), + &outlen); + + if (rc) + return rc; + + if (outlen < (MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST + + SFP_PAGE_SIZE)) + return -EIO; + + payload_len = MCDI_DWORD(outbuf, GET_PHY_MEDIA_INFO_OUT_DATALEN); + if (payload_len != SFP_PAGE_SIZE) + return -EIO; + + memcpy(data, MCDI_PTR(outbuf, GET_PHY_MEDIA_INFO_OUT_DATA) + offset, + to_copy); + + return to_copy; +} + +static int efx_mcdi_phy_get_module_eeprom_byte(struct efx_nic *efx, + unsigned int page, + u8 byte) +{ + u8 data; + int rc; + + rc = efx_mcdi_phy_get_module_eeprom_page(efx, page, &data, byte, 1); + if (rc == 1) + return data; + + return rc; +} + +static int efx_mcdi_phy_diag_type(struct efx_nic *efx) +{ + /* Page zero of the EEPROM includes the diagnostic type at byte 92. */ + return efx_mcdi_phy_get_module_eeprom_byte(efx, 0, + SFF_DIAG_TYPE_OFFSET); +} + +static int efx_mcdi_phy_sff_8472_level(struct efx_nic *efx) +{ + /* Page zero of the EEPROM includes the DMT level at byte 94. */ + return efx_mcdi_phy_get_module_eeprom_byte(efx, 0, + SFF_DMT_LEVEL_OFFSET); +} + +static u32 efx_mcdi_phy_module_type(struct efx_nic *efx) +{ + struct efx_mcdi_phy_data *phy_data = efx->phy_data; + + if (phy_data->media != MC_CMD_MEDIA_QSFP_PLUS) + return phy_data->media; + + /* A QSFP+ NIC may actually have an SFP+ module attached. + * The ID is page 0, byte 0. + */ + switch (efx_mcdi_phy_get_module_eeprom_byte(efx, 0, 0)) { + case 0x3: + return MC_CMD_MEDIA_SFP_PLUS; + case 0xc: + case 0xd: + return MC_CMD_MEDIA_QSFP_PLUS; + default: + return 0; + } +} + +int efx_mcdi_phy_get_module_eeprom(struct efx_nic *efx, struct ethtool_eeprom *ee, u8 *data) +{ + int rc; + ssize_t space_remaining = ee->len; + unsigned int page_off; + bool ignore_missing; + int num_pages; + int page; + + switch (efx_mcdi_phy_module_type(efx)) { + case MC_CMD_MEDIA_SFP_PLUS: + num_pages = efx_mcdi_phy_sff_8472_level(efx) > 0 ? + SFF_8472_NUM_PAGES : SFF_8079_NUM_PAGES; + page = 0; + ignore_missing = false; + break; + case MC_CMD_MEDIA_QSFP_PLUS: + num_pages = SFF_8436_NUM_PAGES; + page = -1; /* We obtain the lower page by asking for -1. */ + ignore_missing = true; /* Ignore missing pages after page 0. */ + break; + default: + return -EOPNOTSUPP; + } + + page_off = ee->offset % SFP_PAGE_SIZE; + page += ee->offset / SFP_PAGE_SIZE; + + while (space_remaining && (page < num_pages)) { + rc = efx_mcdi_phy_get_module_eeprom_page(efx, page, + data, page_off, + space_remaining); + + if (rc > 0) { + space_remaining -= rc; + data += rc; + page_off = 0; + page++; + } else if (rc == 0) { + space_remaining = 0; + } else if (ignore_missing && (page > 0)) { + int intended_size = SFP_PAGE_SIZE - page_off; + + space_remaining -= intended_size; + if (space_remaining < 0) { + space_remaining = 0; + } else { + memset(data, 0, intended_size); + data += intended_size; + page_off = 0; + page++; + rc = 0; + } + } else { + return rc; + } + } + + return 0; +} + +int efx_mcdi_phy_get_module_info(struct efx_nic *efx, struct ethtool_modinfo *modinfo) +{ + int sff_8472_level; + int diag_type; + + switch (efx_mcdi_phy_module_type(efx)) { + case MC_CMD_MEDIA_SFP_PLUS: + sff_8472_level = efx_mcdi_phy_sff_8472_level(efx); + + /* If we can't read the diagnostics level we have none. */ + if (sff_8472_level < 0) + return -EOPNOTSUPP; + + /* Check if this module requires the (unsupported) address + * change operation. + */ + diag_type = efx_mcdi_phy_diag_type(efx); + + if (sff_8472_level == 0 || + (diag_type & SFF_DIAG_ADDR_CHANGE)) { + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else { + modinfo->type = ETH_MODULE_SFF_8472; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + } + break; + + case MC_CMD_MEDIA_QSFP_PLUS: + modinfo->type = ETH_MODULE_SFF_8436; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + break; + + default: + return -EOPNOTSUPP; + } + + return 0; +} + static unsigned int efx_calc_mac_mtu(struct efx_nic *efx) { return EFX_MAX_FRAME_LEN(efx->net_dev->mtu); diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.h b/drivers/net/ethernet/sfc/mcdi_port_common.h index 9dbeee83266f..ed31690e591c 100644 --- a/drivers/net/ethernet/sfc/mcdi_port_common.h +++ b/drivers/net/ethernet/sfc/mcdi_port_common.h @@ -41,13 +41,22 @@ u8 mcdi_to_ethtool_media(u32 media); void efx_mcdi_phy_decode_link(struct efx_nic *efx, struct efx_link_state *link_state, u32 speed, u32 flags, u32 fcntl); -u32 ethtool_fec_caps_to_mcdi(u32 ethtool_cap); +u32 ethtool_fec_caps_to_mcdi(u32 supported_cap, u32 ethtool_cap); u32 mcdi_fec_caps_to_ethtool(u32 caps, bool is_25g); void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa); bool efx_mcdi_phy_poll(struct efx_nic *efx); -int efx_mcdi_phy_get_fecparam(struct efx_nic *efx, - struct ethtool_fecparam *fec); +int efx_mcdi_phy_probe(struct efx_nic *efx); +void efx_mcdi_phy_remove(struct efx_nic *efx); +void efx_mcdi_phy_get_link_ksettings(struct efx_nic *efx, struct ethtool_link_ksettings *cmd); +int efx_mcdi_phy_set_link_ksettings(struct efx_nic *efx, const struct ethtool_link_ksettings *cmd); +int efx_mcdi_phy_get_fecparam(struct efx_nic *efx, struct ethtool_fecparam *fec); +int efx_mcdi_phy_set_fecparam(struct efx_nic *efx, const struct ethtool_fecparam *fec); int efx_mcdi_phy_test_alive(struct efx_nic *efx); +int efx_mcdi_port_reconfigure(struct efx_nic *efx); +int efx_mcdi_phy_run_tests(struct efx_nic *efx, int *results, unsigned int flags); +const char *efx_mcdi_phy_test_name(struct efx_nic *efx, unsigned int index); +int efx_mcdi_phy_get_module_eeprom(struct efx_nic *efx, struct ethtool_eeprom *ee, u8 *data); +int efx_mcdi_phy_get_module_info(struct efx_nic *efx, struct ethtool_modinfo *modinfo); int efx_mcdi_set_mac(struct efx_nic *efx); int efx_mcdi_set_mtu(struct efx_nic *efx); int efx_mcdi_mac_init_stats(struct efx_nic *efx); diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 7bb7ecb480ae..3fd0b59107d1 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -38,8 +38,6 @@ * **************************************************************************/ -#define EFX_DRIVER_VERSION "4.1" - #ifdef DEBUG #define EFX_WARN_ON_ONCE_PARANOID(x) WARN_ON_ONCE(x) #define EFX_WARN_ON_PARANOID(x) WARN_ON(x) @@ -244,7 +242,7 @@ struct efx_tx_buffer { * @tso_fallbacks: Number of times TSO fallback used * @pushes: Number of times the TX push feature has been used * @pio_packets: Number of times the TX PIO feature has been used - * @xmit_more_available: Are any packets waiting to be pushed to the NIC + * @xmit_pending: Are any packets waiting to be pushed to the NIC * @cb_packets: Number of times the TX copybreak feature has been used * @notify_count: Count of notified descriptors to the NIC * @empty_read_count: If the completion path has seen the queue as empty @@ -292,7 +290,7 @@ struct efx_tx_queue { unsigned int tso_fallbacks; unsigned int pushes; unsigned int pio_packets; - bool xmit_more_available; + bool xmit_pending; unsigned int cb_packets; unsigned int notify_count; /* Statistics to supplement MAC stats */ @@ -658,51 +656,6 @@ static inline bool efx_link_state_equal(const struct efx_link_state *left, } /** - * struct efx_phy_operations - Efx PHY operations table - * @probe: Probe PHY and initialise efx->mdio.mode_support, efx->mdio.mmds, - * efx->loopback_modes. - * @init: Initialise PHY - * @fini: Shut down PHY - * @reconfigure: Reconfigure PHY (e.g. for new link parameters) - * @poll: Update @link_state and report whether it changed. - * Serialised by the mac_lock. - * @get_link_ksettings: Get ethtool settings. Serialised by the mac_lock. - * @set_link_ksettings: Set ethtool settings. Serialised by the mac_lock. - * @get_fecparam: Get Forward Error Correction settings. Serialised by mac_lock. - * @set_fecparam: Set Forward Error Correction settings. Serialised by mac_lock. - * @set_npage_adv: Set abilities advertised in (Extended) Next Page - * (only needed where AN bit is set in mmds) - * @test_alive: Test that PHY is 'alive' (online) - * @test_name: Get the name of a PHY-specific test/result - * @run_tests: Run tests and record results as appropriate (offline). - * Flags are the ethtool tests flags. - */ -struct efx_phy_operations { - int (*probe) (struct efx_nic *efx); - int (*init) (struct efx_nic *efx); - void (*fini) (struct efx_nic *efx); - void (*remove) (struct efx_nic *efx); - int (*reconfigure) (struct efx_nic *efx); - bool (*poll) (struct efx_nic *efx); - void (*get_link_ksettings)(struct efx_nic *efx, - struct ethtool_link_ksettings *cmd); - int (*set_link_ksettings)(struct efx_nic *efx, - const struct ethtool_link_ksettings *cmd); - int (*get_fecparam)(struct efx_nic *efx, struct ethtool_fecparam *fec); - int (*set_fecparam)(struct efx_nic *efx, - const struct ethtool_fecparam *fec); - void (*set_npage_adv) (struct efx_nic *efx, u32); - int (*test_alive) (struct efx_nic *efx); - const char *(*test_name) (struct efx_nic *efx, unsigned int index); - int (*run_tests) (struct efx_nic *efx, int *results, unsigned flags); - int (*get_module_eeprom) (struct efx_nic *efx, - struct ethtool_eeprom *ee, - u8 *data); - int (*get_module_info) (struct efx_nic *efx, - struct ethtool_modinfo *modinfo); -}; - -/** * enum efx_phy_mode - PHY operating mode flags * @PHY_MODE_NORMAL: on and should pass traffic * @PHY_MODE_TX_DISABLED: on with TX disabled @@ -846,6 +799,7 @@ struct efx_async_filter_insertion { * @timer_quantum_ns: Interrupt timer quantum, in nanoseconds * @timer_max_ns: Interrupt timer maximum value, in nanoseconds * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues + * @irqs_hooked: Channel interrupts are hooked * @irq_rx_mod_step_us: Step size for IRQ moderation for RX event queues * @irq_rx_moderation_us: IRQ moderation time for RX event queues * @msg_enable: Log message enable flags @@ -919,7 +873,6 @@ struct efx_async_filter_insertion { * field of %MC_CMD_GET_CAPABILITIES_V4 response, or %MC_CMD_MAC_NSTATS) * @stats_buffer: DMA buffer for statistics * @phy_type: PHY type - * @phy_op: PHY interface * @phy_data: PHY private data (including PHY-specific stats) * @mdio: PHY MDIO interface * @mdio_bus: PHY MDIO bus ID (only used by Siena) @@ -1004,6 +957,7 @@ struct efx_nic { unsigned int timer_quantum_ns; unsigned int timer_max_ns; bool irq_rx_adaptive; + bool irqs_hooked; unsigned int irq_mod_step_us; unsigned int irq_rx_moderation_us; u32 msg_enable; @@ -1092,7 +1046,6 @@ struct efx_nic { bool rx_nodesc_drops_prev_state; unsigned int phy_type; - const struct efx_phy_operations *phy_op; void *phy_data; struct mdio_if_info mdio; unsigned int mdio_bus; @@ -1215,7 +1168,6 @@ struct efx_udp_tunnel { * @start_stats: Start the regular fetching of statistics * @pull_stats: Pull stats from the NIC and wait until they arrive. * @stop_stats: Stop the regular fetching of statistics - * @set_id_led: Set state of identifying LED or revert to automatic function * @push_irq_moderation: Apply interrupt moderation value * @reconfigure_port: Push loopback/power/txdis changes to the MAC and PHY * @prepare_enable_fc_tx: Prepare MAC to enable pause frame TX (may be %NULL) @@ -1265,6 +1217,7 @@ struct efx_udp_tunnel { * @rx_write: Write RX descriptors and doorbell * @rx_defer_refill: Generate a refill reminder event * @rx_packet: Receive the queued RX buffer on a channel + * @rx_buf_hash_valid: Determine whether the RX prefix contains a valid hash * @ev_probe: Allocate resources for event queue * @ev_init: Initialise event queue on the NIC * @ev_fini: Deinitialise event queue on the NIC @@ -1359,7 +1312,6 @@ struct efx_nic_type { void (*start_stats)(struct efx_nic *efx); void (*pull_stats)(struct efx_nic *efx); void (*stop_stats)(struct efx_nic *efx); - void (*set_id_led)(struct efx_nic *efx, enum efx_led_mode mode); void (*push_irq_moderation)(struct efx_channel *channel); int (*reconfigure_port)(struct efx_nic *efx); void (*prepare_enable_fc_tx)(struct efx_nic *efx); @@ -1409,6 +1361,7 @@ struct efx_nic_type { void (*rx_write)(struct efx_rx_queue *rx_queue); void (*rx_defer_refill)(struct efx_rx_queue *rx_queue); void (*rx_packet)(struct efx_channel *channel); + bool (*rx_buf_hash_valid)(const u8 *prefix); int (*ev_probe)(struct efx_channel *channel); int (*ev_init)(struct efx_channel *channel); void (*ev_fini)(struct efx_channel *channel); @@ -1679,10 +1632,6 @@ efx_channel_tx_fill_level(struct efx_channel *channel) struct efx_tx_queue *tx_queue; unsigned int fill_level = 0; - /* This function is currently only used by EF100, which maybe - * could do something simpler and just compute the fill level - * of the single TXQ that's really in use. - */ efx_for_each_channel_tx_queue(tx_queue, channel) fill_level = max(fill_level, tx_queue->insert_count - tx_queue->read_count); @@ -1690,6 +1639,20 @@ efx_channel_tx_fill_level(struct efx_channel *channel) return fill_level; } +/* Conservative approximation of efx_channel_tx_fill_level using cached value */ +static inline unsigned int +efx_channel_tx_old_fill_level(struct efx_channel *channel) +{ + struct efx_tx_queue *tx_queue; + unsigned int fill_level = 0; + + efx_for_each_channel_tx_queue(tx_queue, channel) + fill_level = max(fill_level, + tx_queue->insert_count - tx_queue->old_read_count); + + return fill_level; +} + /* Get all supported features. * If a feature is not fixed, it is present in hw_features. * If a feature is fixed, it does not present in hw_features, but diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index d994d136bb03..d1e908846f5d 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -129,6 +129,7 @@ int efx_nic_init_interrupt(struct efx_nic *efx) #endif } + efx->irqs_hooked = true; return 0; fail2: @@ -154,6 +155,8 @@ void efx_nic_fini_interrupt(struct efx_nic *efx) efx->net_dev->rx_cpu_rmap = NULL; #endif + if (!efx->irqs_hooked) + return; if (EFX_INT_MODE_USE_MSI(efx)) { /* Disable MSI/MSI-X interrupts */ efx_for_each_channel(channel, efx) @@ -163,6 +166,7 @@ void efx_nic_fini_interrupt(struct efx_nic *efx) /* Disable legacy interrupt */ free_irq(efx->legacy_irq, efx); } + efx->irqs_hooked = false; } /* Register dump */ diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h index 974107354087..82271f0b8627 100644 --- a/drivers/net/ethernet/sfc/nic_common.h +++ b/drivers/net/ethernet/sfc/nic_common.h @@ -65,8 +65,7 @@ efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index) /* Report whether this TX queue would be empty for the given write_count. * May return false negative. */ -static inline bool __efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue, - unsigned int write_count) +static inline bool efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue, unsigned int write_count) { unsigned int empty_read_count = READ_ONCE(tx_queue->empty_read_count); @@ -76,41 +75,6 @@ static inline bool __efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue, return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0; } -/* Report whether the NIC considers this TX queue empty, using - * packet_write_count (the write count recorded for the last completable - * doorbell push). May return false negative. EF10 only, which is OK - * because only EF10 supports PIO. - */ -static inline bool efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue) -{ - EFX_WARN_ON_ONCE_PARANOID(!tx_queue->efx->type->option_descriptors); - return __efx_nic_tx_is_empty(tx_queue, tx_queue->packet_write_count); -} - -/* Get partner of a TX queue, seen as part of the same net core queue */ -/* XXX is this a thing on EF100? */ -static inline struct efx_tx_queue *efx_tx_queue_partner(struct efx_tx_queue *tx_queue) -{ - if (tx_queue->label & EFX_TXQ_TYPE_OFFLOAD) - return tx_queue - EFX_TXQ_TYPE_OFFLOAD; - else - return tx_queue + EFX_TXQ_TYPE_OFFLOAD; -} - -/* Decide whether we can use TX PIO, ie. write packet data directly into - * a buffer on the device. This can reduce latency at the expense of - * throughput, so we only do this if both hardware and software TX rings - * are empty. This also ensures that only one packet at a time can be - * using the PIO buffer. - */ -static inline bool efx_nic_may_tx_pio(struct efx_tx_queue *tx_queue) -{ - struct efx_tx_queue *partner = efx_tx_queue_partner(tx_queue); - - return tx_queue->piobuf && efx_nic_tx_is_empty(tx_queue) && - efx_nic_tx_is_empty(partner); -} - int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb, bool *data_mapped); @@ -125,7 +89,7 @@ int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb, static inline bool efx_nic_may_push_tx_desc(struct efx_tx_queue *tx_queue, unsigned int write_count) { - bool was_empty = __efx_nic_tx_is_empty(tx_queue, write_count); + bool was_empty = efx_nic_tx_is_empty(tx_queue, write_count); tx_queue->empty_read_count = 0; return was_empty && tx_queue->write_count - write_count == 1; diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 59a43d586967..aaa112877561 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -358,7 +358,7 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel, case XDP_ABORTED: trace_xdp_exception(efx->net_dev, xdp_prog, xdp_act); - /* Fall through */ + fallthrough; case XDP_DROP: efx_free_rx_buffers(rx_queue, rx_buf, 1); channel->n_rx_xdp_drops++; diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index fb77c7bbe4af..5e29284c89c9 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -525,7 +525,8 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, return; } - if (efx->net_dev->features & NETIF_F_RXHASH) + if (efx->net_dev->features & NETIF_F_RXHASH && + efx_rx_buf_hash_valid(efx, eh)) skb_set_hash(skb, efx_rx_buf_hash(efx, eh), PKT_HASH_TYPE_L3); if (csum) { @@ -848,6 +849,7 @@ void efx_remove_filters(struct efx_nic *efx) efx_for_each_channel(channel, efx) { cancel_delayed_work_sync(&channel->filter_work); kfree(channel->rps_flow_id); + channel->rps_flow_id = NULL; } #endif down_write(&efx->filter_sem); diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c index e71d6d37a317..574856a8a83c 100644 --- a/drivers/net/ethernet/sfc/selftest.c +++ b/drivers/net/ethernet/sfc/selftest.c @@ -21,6 +21,7 @@ #include "efx_common.h" #include "efx_channels.h" #include "nic.h" +#include "mcdi_port_common.h" #include "selftest.h" #include "workarounds.h" @@ -67,7 +68,7 @@ static const char *const efx_interrupt_mode_names[] = { STRING_TABLE_LOOKUP(efx->interrupt_mode, efx_interrupt_mode) /** - * efx_loopback_state - persistent state during a loopback selftest + * struct efx_loopback_state - persistent state during a loopback selftest * @flush: Drop all packets in efx_loopback_rx_packet * @packet_count: Number of packets being used in this test * @skbs: An array of skbs transmitted @@ -99,10 +100,8 @@ static int efx_test_phy_alive(struct efx_nic *efx, struct efx_self_tests *tests) { int rc = 0; - if (efx->phy_op->test_alive) { - rc = efx->phy_op->test_alive(efx); - tests->phy_alive = rc ? -1 : 1; - } + rc = efx_mcdi_phy_test_alive(efx); + tests->phy_alive = rc ? -1 : 1; return rc; } @@ -257,11 +256,8 @@ static int efx_test_phy(struct efx_nic *efx, struct efx_self_tests *tests, { int rc; - if (!efx->phy_op->run_tests) - return 0; - mutex_lock(&efx->mac_lock); - rc = efx->phy_op->run_tests(efx, tests->phy_ext, flags); + rc = efx_mcdi_phy_run_tests(efx, tests->phy_ext, flags); mutex_unlock(&efx->mac_lock); if (rc == -EPERM) rc = 0; diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c index a7ea630bb5e6..16347a6d0c47 100644 --- a/drivers/net/ethernet/sfc/siena.c +++ b/drivers/net/ethernet/sfc/siena.c @@ -994,7 +994,6 @@ const struct efx_nic_type siena_a0_nic_type = { .start_stats = efx_mcdi_mac_start_stats, .pull_stats = efx_mcdi_mac_pull_stats, .stop_stats = efx_mcdi_mac_stop_stats, - .set_id_led = efx_mcdi_set_id_led, .push_irq_moderation = siena_push_irq_moderation, .reconfigure_mac = siena_mac_reconfigure, .check_mac_fault = efx_mcdi_mac_check_fault, diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 727201d5eb24..48d91b26f1a2 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -59,13 +59,12 @@ u8 *efx_tx_get_copy_buffer_limited(struct efx_tx_queue *tx_queue, static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1) { - /* We need to consider both queues that the net core sees as one */ - struct efx_tx_queue *txq2 = efx_tx_queue_partner(txq1); + /* We need to consider all queues that the net core sees as one */ struct efx_nic *efx = txq1->efx; + struct efx_tx_queue *txq2; unsigned int fill_level; - fill_level = max(txq1->insert_count - txq1->old_read_count, - txq2->insert_count - txq2->old_read_count); + fill_level = efx_channel_tx_old_fill_level(txq1->channel); if (likely(fill_level < efx->txq_stop_thresh)) return; @@ -85,11 +84,10 @@ static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1) */ netif_tx_stop_queue(txq1->core_txq); smp_mb(); - txq1->old_read_count = READ_ONCE(txq1->read_count); - txq2->old_read_count = READ_ONCE(txq2->read_count); + efx_for_each_channel_tx_queue(txq2, txq1->channel) + txq2->old_read_count = READ_ONCE(txq2->read_count); - fill_level = max(txq1->insert_count - txq1->old_read_count, - txq2->insert_count - txq2->old_read_count); + fill_level = efx_channel_tx_old_fill_level(txq1->channel); EFX_WARN_ON_ONCE_PARANOID(fill_level >= efx->txq_entries); if (likely(fill_level < efx->txq_stop_thresh)) { smp_mb(); @@ -266,8 +264,45 @@ static int efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, ++tx_queue->insert_count; return 0; } + +/* Decide whether we can use TX PIO, ie. write packet data directly into + * a buffer on the device. This can reduce latency at the expense of + * throughput, so we only do this if both hardware and software TX rings + * are empty, including all queues for the channel. This also ensures that + * only one packet at a time can be using the PIO buffer. If the xmit_more + * flag is set then we don't use this - there'll be another packet along + * shortly and we want to hold off the doorbell. + */ +static bool efx_tx_may_pio(struct efx_tx_queue *tx_queue) +{ + struct efx_channel *channel = tx_queue->channel; + + if (!tx_queue->piobuf) + return false; + + EFX_WARN_ON_ONCE_PARANOID(!channel->efx->type->option_descriptors); + + efx_for_each_channel_tx_queue(tx_queue, channel) + if (!efx_nic_tx_is_empty(tx_queue, tx_queue->packet_write_count)) + return false; + + return true; +} #endif /* EFX_USE_PIO */ +/* Send any pending traffic for a channel. xmit_more is shared across all + * queues for a channel, so we must check all of them. + */ +static void efx_tx_send_pending(struct efx_channel *channel) +{ + struct efx_tx_queue *q; + + efx_for_each_channel_tx_queue(q, channel) { + if (q->xmit_pending) + efx_nic_push_buffers(q); + } +} + /* * Add a socket buffer to a TX queue * @@ -315,7 +350,7 @@ netdev_tx_t __efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb goto err; #ifdef EFX_USE_PIO } else if (skb_len <= efx_piobuf_size && !xmit_more && - efx_nic_may_tx_pio(tx_queue)) { + efx_tx_may_pio(tx_queue)) { /* Use PIO for short packets with an empty queue. */ if (efx_enqueue_skb_pio(tx_queue, skb)) goto err; @@ -336,21 +371,11 @@ netdev_tx_t __efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb efx_tx_maybe_stop_queue(tx_queue); - /* Pass off to hardware */ - if (__netdev_tx_sent_queue(tx_queue->core_txq, skb_len, xmit_more)) { - struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue); - - /* There could be packets left on the partner queue if - * xmit_more was set. If we do not push those they - * could be left for a long time and cause a netdev watchdog. - */ - if (txq2->xmit_more_available) - efx_nic_push_buffers(txq2); + tx_queue->xmit_pending = true; - efx_nic_push_buffers(tx_queue); - } else { - tx_queue->xmit_more_available = xmit_more; - } + /* Pass off to hardware */ + if (__netdev_tx_sent_queue(tx_queue->core_txq, skb_len, xmit_more)) + efx_tx_send_pending(tx_queue->channel); if (segments) { tx_queue->tso_bursts++; @@ -371,14 +396,8 @@ err: * on this queue or a partner queue then we need to push here to get the * previous packets out. */ - if (!xmit_more) { - struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue); - - if (txq2->xmit_more_available) - efx_nic_push_buffers(txq2); - - efx_nic_push_buffers(tx_queue); - } + if (!xmit_more) + efx_tx_send_pending(tx_queue->channel); return NETDEV_TX_OK; } @@ -489,18 +508,24 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, EFX_WARN_ON_PARANOID(!netif_device_present(net_dev)); - /* PTP "event" packet */ - if (unlikely(efx_xmit_with_hwtstamp(skb)) && - unlikely(efx_ptp_is_ptp_tx(efx, skb))) { - return efx_ptp_tx(efx, skb); - } - index = skb_get_queue_mapping(skb); type = skb->ip_summed == CHECKSUM_PARTIAL ? EFX_TXQ_TYPE_OFFLOAD : 0; if (index >= efx->n_tx_channels) { index -= efx->n_tx_channels; type |= EFX_TXQ_TYPE_HIGHPRI; } + + /* PTP "event" packet */ + if (unlikely(efx_xmit_with_hwtstamp(skb)) && + unlikely(efx_ptp_is_ptp_tx(efx, skb))) { + /* There may be existing transmits on the channel that are + * waiting for this packet to trigger the doorbell write. + * We need to send the packets at this point. + */ + efx_tx_send_pending(efx_get_tx_channel(efx, index)); + return efx_ptp_tx(efx, skb); + } + tx_queue = efx_get_tx_queue(efx, index, type); return __efx_enqueue_skb(tx_queue, skb); diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index 793e234819a8..f2dac83beb7d 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -78,7 +78,7 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue) tx_queue->read_count = 0; tx_queue->old_read_count = 0; tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID; - tx_queue->xmit_more_available = false; + tx_queue->xmit_pending = false; tx_queue->timestamping = (efx_ptp_use_mac_tx_timestamps(efx) && tx_queue->channel == efx_ptp_channel(efx)); tx_queue->completed_timestamp_major = 0; @@ -116,7 +116,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) ++tx_queue->read_count; } - tx_queue->xmit_more_available = false; + tx_queue->xmit_pending = false; netdev_tx_reset_queue(tx_queue->core_txq); } @@ -242,7 +242,6 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) { unsigned int fill_level, pkts_compl = 0, bytes_compl = 0; struct efx_nic *efx = tx_queue->efx; - struct efx_tx_queue *txq2; EFX_WARN_ON_ONCE_PARANOID(index > tx_queue->ptr_mask); @@ -261,9 +260,7 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) if (unlikely(netif_tx_queue_stopped(tx_queue->core_txq)) && likely(efx->port_enabled) && likely(netif_device_present(efx->net_dev))) { - txq2 = efx_tx_queue_partner(tx_queue); - fill_level = max(tx_queue->insert_count - tx_queue->read_count, - txq2->insert_count - txq2->read_count); + fill_level = efx_channel_tx_fill_level(tx_queue->channel); if (fill_level <= efx->txq_wake_thresh) netif_tx_wake_queue(tx_queue->core_txq); } diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 336105f77313..cfa460c7db23 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -2228,7 +2228,7 @@ static int mii_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd) switch(cmd) { case SIOCGMIIPHY: /* Get address of MII PHY in use. */ data->phy_id = sis_priv->mii->phy_addr; - /* Fall Through */ + fallthrough; case SIOCGMIIREG: /* Read MII PHY register. */ data->val_out = mdio_read(net_dev, data->phy_id & 0x1f, data->reg_num & 0x1f); diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index d950b312c418..51cd7dca91cd 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -374,13 +374,15 @@ static int epic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) ep->mii.phy_id_mask = 0x1f; ep->mii.reg_num_mask = 0x1f; - ring_space = pci_alloc_consistent(pdev, TX_TOTAL_SIZE, &ring_dma); + ring_space = dma_alloc_coherent(&pdev->dev, TX_TOTAL_SIZE, &ring_dma, + GFP_KERNEL); if (!ring_space) goto err_out_iounmap; ep->tx_ring = ring_space; ep->tx_ring_dma = ring_dma; - ring_space = pci_alloc_consistent(pdev, RX_TOTAL_SIZE, &ring_dma); + ring_space = dma_alloc_coherent(&pdev->dev, RX_TOTAL_SIZE, &ring_dma, + GFP_KERNEL); if (!ring_space) goto err_out_unmap_tx; ep->rx_ring = ring_space; @@ -493,9 +495,11 @@ out: return ret; err_out_unmap_rx: - pci_free_consistent(pdev, RX_TOTAL_SIZE, ep->rx_ring, ep->rx_ring_dma); + dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, ep->rx_ring, + ep->rx_ring_dma); err_out_unmap_tx: - pci_free_consistent(pdev, TX_TOTAL_SIZE, ep->tx_ring, ep->tx_ring_dma); + dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, ep->tx_ring, + ep->tx_ring_dma); err_out_iounmap: pci_iounmap(pdev, ioaddr); err_out_free_netdev: @@ -918,8 +922,10 @@ static void epic_init_ring(struct net_device *dev) if (skb == NULL) break; skb_reserve(skb, 2); /* 16 byte align the IP header. */ - ep->rx_ring[i].bufaddr = pci_map_single(ep->pci_dev, - skb->data, ep->rx_buf_sz, PCI_DMA_FROMDEVICE); + ep->rx_ring[i].bufaddr = dma_map_single(&ep->pci_dev->dev, + skb->data, + ep->rx_buf_sz, + DMA_FROM_DEVICE); ep->rx_ring[i].rxstatus = DescOwn; } ep->dirty_rx = (unsigned int)(i - RX_RING_SIZE); @@ -955,8 +961,9 @@ static netdev_tx_t epic_start_xmit(struct sk_buff *skb, struct net_device *dev) entry = ep->cur_tx % TX_RING_SIZE; ep->tx_skbuff[entry] = skb; - ep->tx_ring[entry].bufaddr = pci_map_single(ep->pci_dev, skb->data, - skb->len, PCI_DMA_TODEVICE); + ep->tx_ring[entry].bufaddr = dma_map_single(&ep->pci_dev->dev, + skb->data, skb->len, + DMA_TO_DEVICE); if (free_count < TX_QUEUE_LEN/2) {/* Typical path */ ctrl_word = 0x100000; /* No interrupt */ } else if (free_count == TX_QUEUE_LEN/2) { @@ -1036,8 +1043,9 @@ static void epic_tx(struct net_device *dev, struct epic_private *ep) /* Free the original skb. */ skb = ep->tx_skbuff[entry]; - pci_unmap_single(ep->pci_dev, ep->tx_ring[entry].bufaddr, - skb->len, PCI_DMA_TODEVICE); + dma_unmap_single(&ep->pci_dev->dev, + ep->tx_ring[entry].bufaddr, skb->len, + DMA_TO_DEVICE); dev_consume_skb_irq(skb); ep->tx_skbuff[entry] = NULL; } @@ -1178,20 +1186,21 @@ static int epic_rx(struct net_device *dev, int budget) if (pkt_len < rx_copybreak && (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ - pci_dma_sync_single_for_cpu(ep->pci_dev, - ep->rx_ring[entry].bufaddr, - ep->rx_buf_sz, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&ep->pci_dev->dev, + ep->rx_ring[entry].bufaddr, + ep->rx_buf_sz, + DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, ep->rx_skbuff[entry]->data, pkt_len); skb_put(skb, pkt_len); - pci_dma_sync_single_for_device(ep->pci_dev, - ep->rx_ring[entry].bufaddr, - ep->rx_buf_sz, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&ep->pci_dev->dev, + ep->rx_ring[entry].bufaddr, + ep->rx_buf_sz, + DMA_FROM_DEVICE); } else { - pci_unmap_single(ep->pci_dev, - ep->rx_ring[entry].bufaddr, - ep->rx_buf_sz, PCI_DMA_FROMDEVICE); + dma_unmap_single(&ep->pci_dev->dev, + ep->rx_ring[entry].bufaddr, + ep->rx_buf_sz, + DMA_FROM_DEVICE); skb_put(skb = ep->rx_skbuff[entry], pkt_len); ep->rx_skbuff[entry] = NULL; } @@ -1213,8 +1222,10 @@ static int epic_rx(struct net_device *dev, int budget) if (skb == NULL) break; skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */ - ep->rx_ring[entry].bufaddr = pci_map_single(ep->pci_dev, - skb->data, ep->rx_buf_sz, PCI_DMA_FROMDEVICE); + ep->rx_ring[entry].bufaddr = dma_map_single(&ep->pci_dev->dev, + skb->data, + ep->rx_buf_sz, + DMA_FROM_DEVICE); work_done++; } /* AV: shouldn't we add a barrier here? */ @@ -1294,8 +1305,8 @@ static int epic_close(struct net_device *dev) ep->rx_ring[i].rxstatus = 0; /* Not owned by Epic chip. */ ep->rx_ring[i].buflength = 0; if (skb) { - pci_unmap_single(pdev, ep->rx_ring[i].bufaddr, - ep->rx_buf_sz, PCI_DMA_FROMDEVICE); + dma_unmap_single(&pdev->dev, ep->rx_ring[i].bufaddr, + ep->rx_buf_sz, DMA_FROM_DEVICE); dev_kfree_skb(skb); } ep->rx_ring[i].bufaddr = 0xBADF00D0; /* An invalid address. */ @@ -1305,8 +1316,8 @@ static int epic_close(struct net_device *dev) ep->tx_skbuff[i] = NULL; if (!skb) continue; - pci_unmap_single(pdev, ep->tx_ring[i].bufaddr, skb->len, - PCI_DMA_TODEVICE); + dma_unmap_single(&pdev->dev, ep->tx_ring[i].bufaddr, skb->len, + DMA_TO_DEVICE); dev_kfree_skb(skb); } @@ -1502,8 +1513,10 @@ static void epic_remove_one(struct pci_dev *pdev) struct net_device *dev = pci_get_drvdata(pdev); struct epic_private *ep = netdev_priv(dev); - pci_free_consistent(pdev, TX_TOTAL_SIZE, ep->tx_ring, ep->tx_ring_dma); - pci_free_consistent(pdev, RX_TOTAL_SIZE, ep->rx_ring, ep->rx_ring_dma); + dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, ep->tx_ring, + ep->tx_ring_dma); + dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, ep->rx_ring, + ep->rx_ring_dma); unregister_netdev(dev); pci_iounmap(pdev, ep->ioaddr); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index 186c0bddbe5f..01069dfaf75c 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -712,7 +712,7 @@ static void smc911x_phy_detect(struct net_device *dev) /* Found an external PHY */ break; } - /* Else, fall through */ + fallthrough; default: /* Internal media only */ SMC_GET_PHY_ID1(lp, 1, id1); diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 1c4fea9c3ec4..4492715d1e42 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -1036,7 +1036,6 @@ static void smc_phy_configure(struct work_struct *work) int phyaddr = lp->mii.phy_id; int my_phy_caps; /* My PHY capabilities */ int my_ad_caps; /* My Advertised capabilities */ - int status; DBG(3, dev, "smc_program_phy()\n"); @@ -1110,7 +1109,7 @@ static void smc_phy_configure(struct work_struct *work) * auto-negotiation is restarted, sometimes it isn't ready and * the link does not come up. */ - status = smc_phy_read(dev, phyaddr, MII_ADVERTISE); + smc_phy_read(dev, phyaddr, MII_ADVERTISE); DBG(2, dev, "phy caps=%x\n", my_phy_caps); DBG(2, dev, "phy advertised caps=%x\n", my_ad_caps); diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index fc168f85e7af..823d9a7184fe 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1196,9 +1196,8 @@ smsc911x_rx_fastforward(struct smsc911x_data *pdata, unsigned int pktwords) SMSC_WARN(pdata, hw, "Timed out waiting for " "RX FFWD to finish, RX_DP_CTRL: 0x%08X", val); } else { - unsigned int temp; while (pktwords--) - temp = smsc911x_reg_read(pdata, RX_DATA_FIFO); + smsc911x_reg_read(pdata, RX_DATA_FIFO); } } @@ -2055,7 +2054,6 @@ static int smsc911x_eeprom_write_location(struct smsc911x_data *pdata, u8 address, u8 data) { u32 op = E2P_CMD_EPC_CMD_ERASE_ | address; - u32 temp; int ret; SMSC_TRACE(pdata, drv, "address 0x%x, data 0x%x", address, data); @@ -2066,7 +2064,7 @@ static int smsc911x_eeprom_write_location(struct smsc911x_data *pdata, smsc911x_reg_write(pdata, E2P_DATA, (u32)data); /* Workaround for hardware read-after-write restriction */ - temp = smsc911x_reg_read(pdata, BYTE_TEST); + smsc911x_reg_read(pdata, BYTE_TEST); ret = smsc911x_eeprom_send_cmd(pdata, op); } diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 42bef04d65ba..c1dab009415d 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -497,8 +497,9 @@ static void smsc9420_free_tx_ring(struct smsc9420_pdata *pd) if (skb) { BUG_ON(!pd->tx_buffers[i].mapping); - pci_unmap_single(pd->pdev, pd->tx_buffers[i].mapping, - skb->len, PCI_DMA_TODEVICE); + dma_unmap_single(&pd->pdev->dev, + pd->tx_buffers[i].mapping, skb->len, + DMA_TO_DEVICE); dev_kfree_skb_any(skb); } @@ -530,8 +531,9 @@ static void smsc9420_free_rx_ring(struct smsc9420_pdata *pd) dev_kfree_skb_any(pd->rx_buffers[i].skb); if (pd->rx_buffers[i].mapping) - pci_unmap_single(pd->pdev, pd->rx_buffers[i].mapping, - PKT_BUF_SZ, PCI_DMA_FROMDEVICE); + dma_unmap_single(&pd->pdev->dev, + pd->rx_buffers[i].mapping, + PKT_BUF_SZ, DMA_FROM_DEVICE); pd->rx_ring[i].status = 0; pd->rx_ring[i].length = 0; @@ -749,8 +751,8 @@ static void smsc9420_rx_handoff(struct smsc9420_pdata *pd, const int index, dev->stats.rx_packets++; dev->stats.rx_bytes += packet_length; - pci_unmap_single(pd->pdev, pd->rx_buffers[index].mapping, - PKT_BUF_SZ, PCI_DMA_FROMDEVICE); + dma_unmap_single(&pd->pdev->dev, pd->rx_buffers[index].mapping, + PKT_BUF_SZ, DMA_FROM_DEVICE); pd->rx_buffers[index].mapping = 0; skb = pd->rx_buffers[index].skb; @@ -782,9 +784,9 @@ static int smsc9420_alloc_rx_buffer(struct smsc9420_pdata *pd, int index) if (unlikely(!skb)) return -ENOMEM; - mapping = pci_map_single(pd->pdev, skb_tail_pointer(skb), - PKT_BUF_SZ, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(pd->pdev, mapping)) { + mapping = dma_map_single(&pd->pdev->dev, skb_tail_pointer(skb), + PKT_BUF_SZ, DMA_FROM_DEVICE); + if (dma_mapping_error(&pd->pdev->dev, mapping)) { dev_kfree_skb_any(skb); netif_warn(pd, rx_err, pd->dev, "pci_map_single failed!\n"); return -ENOMEM; @@ -901,8 +903,10 @@ static void smsc9420_complete_tx(struct net_device *dev) BUG_ON(!pd->tx_buffers[index].skb); BUG_ON(!pd->tx_buffers[index].mapping); - pci_unmap_single(pd->pdev, pd->tx_buffers[index].mapping, - pd->tx_buffers[index].skb->len, PCI_DMA_TODEVICE); + dma_unmap_single(&pd->pdev->dev, + pd->tx_buffers[index].mapping, + pd->tx_buffers[index].skb->len, + DMA_TO_DEVICE); pd->tx_buffers[index].mapping = 0; dev_kfree_skb_any(pd->tx_buffers[index].skb); @@ -932,9 +936,9 @@ static netdev_tx_t smsc9420_hard_start_xmit(struct sk_buff *skb, BUG_ON(pd->tx_buffers[index].skb); BUG_ON(pd->tx_buffers[index].mapping); - mapping = pci_map_single(pd->pdev, skb->data, - skb->len, PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(pd->pdev, mapping)) { + mapping = dma_map_single(&pd->pdev->dev, skb->data, skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(&pd->pdev->dev, mapping)) { netif_warn(pd, tx_err, pd->dev, "pci_map_single failed, dropping packet\n"); return NETDEV_TX_BUSY; @@ -1522,7 +1526,7 @@ smsc9420_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto out_free_netdev_2; } - if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) { + if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) { netdev_err(dev, "No usable DMA configuration, aborting\n"); goto out_free_regions_3; } @@ -1540,10 +1544,9 @@ smsc9420_probe(struct pci_dev *pdev, const struct pci_device_id *id) pd = netdev_priv(dev); /* pci descriptors are created in the PCI consistent area */ - pd->rx_ring = pci_alloc_consistent(pdev, - sizeof(struct smsc9420_dma_desc) * RX_RING_SIZE + - sizeof(struct smsc9420_dma_desc) * TX_RING_SIZE, - &pd->rx_dma_addr); + pd->rx_ring = dma_alloc_coherent(&pdev->dev, + sizeof(struct smsc9420_dma_desc) * (RX_RING_SIZE + TX_RING_SIZE), + &pd->rx_dma_addr, GFP_KERNEL); if (!pd->rx_ring) goto out_free_io_4; @@ -1599,8 +1602,9 @@ smsc9420_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; out_free_dmadesc_5: - pci_free_consistent(pdev, sizeof(struct smsc9420_dma_desc) * - (RX_RING_SIZE + TX_RING_SIZE), pd->rx_ring, pd->rx_dma_addr); + dma_free_coherent(&pdev->dev, + sizeof(struct smsc9420_dma_desc) * (RX_RING_SIZE + TX_RING_SIZE), + pd->rx_ring, pd->rx_dma_addr); out_free_io_4: iounmap(virt_addr - LAN9420_CPSR_ENDIAN_OFFSET); out_free_regions_3: @@ -1632,8 +1636,9 @@ static void smsc9420_remove(struct pci_dev *pdev) BUG_ON(!pd->tx_ring); BUG_ON(!pd->rx_ring); - pci_free_consistent(pdev, sizeof(struct smsc9420_dma_desc) * - (RX_RING_SIZE + TX_RING_SIZE), pd->rx_ring, pd->rx_dma_addr); + dma_free_coherent(&pdev->dev, + sizeof(struct smsc9420_dma_desc) * (RX_RING_SIZE + TX_RING_SIZE), + pd->rx_ring, pd->rx_dma_addr); iounmap(pd->ioaddr - LAN9420_CPSR_ENDIAN_OFFSET); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 25db667fa879..806eb651cea3 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -919,10 +919,10 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog, break; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(priv->ndev, prog, act); - /* fall through -- handle aborts by dropping packet */ + fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: ret = NETSEC_XDP_CONSUMED; page = virt_to_head_page(xdp->data); diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 9a47c5aec91a..53f14c5a9e02 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -3,7 +3,7 @@ config STMMAC_ETH tristate "STMicroelectronics Multi-Gigabit Ethernet driver" depends on HAS_IOMEM && HAS_DMA select MII - select MDIO_XPCS + select PCS_XPCS select PAGE_POOL select PHYLINK select CRC32 @@ -209,6 +209,16 @@ config DWMAC_IMX8 device driver. This driver is used for i.MX8 series like iMX8MP/iMX8DXL GMAC ethernet controller. +config DWMAC_INTEL_PLAT + tristate "Intel dwmac support" + depends on OF && COMMON_CLK + depends on STMMAC_ETH + help + Support for ethernet controllers on Intel SoCs + + This selects the Intel platform specific glue layer support for + the stmmac device driver. This driver is used for the Intel Keem Bay + SoC. endif config DWMAC_INTEL diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index 295615ab36a7..24e6145d4eae 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_DWMAC_STM32) += dwmac-stm32.o obj-$(CONFIG_DWMAC_SUNXI) += dwmac-sunxi.o obj-$(CONFIG_DWMAC_SUN8I) += dwmac-sun8i.o obj-$(CONFIG_DWMAC_DWC_QOS_ETH) += dwmac-dwc-qos-eth.o +obj-$(CONFIG_DWMAC_INTEL_PLAT) += dwmac-intel-plat.o obj-$(CONFIG_DWMAC_GENERIC) += dwmac-generic.o obj-$(CONFIG_DWMAC_IMX8) += dwmac-imx.o stmmac-platform-objs:= stmmac_platform.o diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 127f75862962..acc5e3fc1c2f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -15,7 +15,7 @@ #include <linux/netdevice.h> #include <linux/stmmac.h> #include <linux/phy.h> -#include <linux/mdio-xpcs.h> +#include <linux/pcs/pcs-xpcs.h> #include <linux/module.h> #if IS_ENABLED(CONFIG_VLAN_8021Q) #define STMMAC_VLAN_TAG_USED diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c index d0d2d0fc5f0a..08c76636c164 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c @@ -84,9 +84,10 @@ static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev) return ERR_PTR(err); switch (phy_mode) { - case PHY_INTERFACE_MODE_RGMII: /* Fall through */ - case PHY_INTERFACE_MODE_RGMII_ID /* Fall through */: - case PHY_INTERFACE_MODE_RGMII_RXID: /* Fall through */ + case PHY_INTERFACE_MODE_RGMII: + fallthrough; + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: gmac->phy_intf_sel = GMAC_CONFIG_INTF_RGMII; break; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 3c5df5eeed6c..efef5476a577 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -129,8 +129,7 @@ static void imx_dwmac_exit(struct platform_device *pdev, void *priv) { struct imx_priv_data *dwmac = priv; - if (dwmac->clk_tx) - clk_disable_unprepare(dwmac->clk_tx); + clk_disable_unprepare(dwmac->clk_tx); clk_disable_unprepare(dwmac->clk_mem); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c new file mode 100644 index 000000000000..b1323d5c95b5 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Intel DWMAC platform driver + * + * Copyright(C) 2020 Intel Corporation + */ + +#include <linux/ethtool.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/stmmac.h> + +#include "stmmac.h" +#include "stmmac_platform.h" + +struct intel_dwmac { + struct device *dev; + struct clk *tx_clk; + const struct intel_dwmac_data *data; +}; + +struct intel_dwmac_data { + void (*fix_mac_speed)(void *priv, unsigned int speed); + unsigned long ptp_ref_clk_rate; + unsigned long tx_clk_rate; + bool tx_clk_en; +}; + +static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed) +{ + struct intel_dwmac *dwmac = priv; + unsigned long rate; + int ret; + + rate = clk_get_rate(dwmac->tx_clk); + + switch (speed) { + case SPEED_1000: + rate = 125000000; + break; + + case SPEED_100: + rate = 25000000; + break; + + case SPEED_10: + rate = 2500000; + break; + + default: + dev_err(dwmac->dev, "Invalid speed\n"); + break; + } + + ret = clk_set_rate(dwmac->tx_clk, rate); + if (ret) + dev_err(dwmac->dev, "Failed to configure tx clock rate\n"); +} + +static const struct intel_dwmac_data kmb_data = { + .fix_mac_speed = kmb_eth_fix_mac_speed, + .ptp_ref_clk_rate = 200000000, + .tx_clk_rate = 125000000, + .tx_clk_en = true, +}; + +static const struct of_device_id intel_eth_plat_match[] = { + { .compatible = "intel,keembay-dwmac", .data = &kmb_data }, + { } +}; +MODULE_DEVICE_TABLE(of, intel_eth_plat_match); + +static int intel_eth_plat_probe(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct stmmac_priv *priv = netdev_priv(ndev); + struct plat_stmmacenet_data *plat_dat; + struct stmmac_resources stmmac_res; + const struct of_device_id *match; + struct intel_dwmac *dwmac; + unsigned long rate; + int ret; + + plat_dat = priv->plat; + ret = stmmac_get_platform_resources(pdev, &stmmac_res); + if (ret) + return ret; + + plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac); + if (IS_ERR(plat_dat)) { + dev_err(&pdev->dev, "dt configuration failed\n"); + return PTR_ERR(plat_dat); + } + + dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } + + dwmac->dev = &pdev->dev; + dwmac->tx_clk = NULL; + + match = of_match_device(intel_eth_plat_match, &pdev->dev); + if (match && match->data) { + dwmac->data = (const struct intel_dwmac_data *)match->data; + + if (dwmac->data->fix_mac_speed) + plat_dat->fix_mac_speed = dwmac->data->fix_mac_speed; + + /* Enable TX clock */ + if (dwmac->data->tx_clk_en) { + dwmac->tx_clk = devm_clk_get(&pdev->dev, "tx_clk"); + if (IS_ERR(dwmac->tx_clk)) + goto err_remove_config_dt; + + clk_prepare_enable(dwmac->tx_clk); + + /* Check and configure TX clock rate */ + rate = clk_get_rate(dwmac->tx_clk); + if (dwmac->data->tx_clk_rate && + rate != dwmac->data->tx_clk_rate) { + rate = dwmac->data->tx_clk_rate; + ret = clk_set_rate(dwmac->tx_clk, rate); + if (ret) { + dev_err(&pdev->dev, + "Failed to set tx_clk\n"); + return ret; + } + } + } + + /* Check and configure PTP ref clock rate */ + rate = clk_get_rate(plat_dat->clk_ptp_ref); + if (dwmac->data->ptp_ref_clk_rate && + rate != dwmac->data->ptp_ref_clk_rate) { + rate = dwmac->data->ptp_ref_clk_rate; + ret = clk_set_rate(plat_dat->clk_ptp_ref, rate); + if (ret) { + dev_err(&pdev->dev, + "Failed to set clk_ptp_ref\n"); + return ret; + } + } + } + + plat_dat->bsp_priv = dwmac; + + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) { + clk_disable_unprepare(dwmac->tx_clk); + goto err_remove_config_dt; + } + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; +} + +static int intel_eth_plat_remove(struct platform_device *pdev) +{ + struct intel_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev); + int ret; + + ret = stmmac_pltfr_remove(pdev); + clk_disable_unprepare(dwmac->tx_clk); + + return ret; +} + +static struct platform_driver intel_eth_plat_driver = { + .probe = intel_eth_plat_probe, + .remove = intel_eth_plat_remove, + .driver = { + .name = "intel-eth-plat", + .pm = &stmmac_pltfr_pm_ops, + .of_match_table = intel_eth_plat_match, + }, +}; +module_platform_driver(intel_eth_plat_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel DWMAC platform driver"); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 89b2b3472852..c553047ff482 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -788,8 +788,7 @@ static int stmmac_init_ptp(struct stmmac_priv *priv) static void stmmac_release_ptp(struct stmmac_priv *priv) { - if (priv->plat->clk_ptp_ref) - clk_disable_unprepare(priv->plat->clk_ptp_ref); + clk_disable_unprepare(priv->plat->clk_ptp_ref); stmmac_ptp_unregister(priv); } @@ -5108,8 +5107,7 @@ int stmmac_suspend(struct device *dev) stmmac_mac_set(priv, priv->ioaddr, false); pinctrl_pm_select_sleep_state(priv->device); /* Disable clock in case of PWM is off */ - if (priv->plat->clk_ptp_ref) - clk_disable_unprepare(priv->plat->clk_ptp_ref); + clk_disable_unprepare(priv->plat->clk_ptp_ref); clk_disable_unprepare(priv->plat->pclk); clk_disable_unprepare(priv->plat->stmmac_clk); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index e113b1376fdd..bf195adee393 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -1985,7 +1985,7 @@ void stmmac_selftest_run(struct net_device *dev, ret = phy_loopback(dev->phydev, true); if (!ret) break; - /* Fallthrough */ + fallthrough; case STMMAC_LOOPBACK_MAC: ret = stmmac_set_mac_loopback(priv, priv->ioaddr, true); break; @@ -2018,7 +2018,7 @@ void stmmac_selftest_run(struct net_device *dev, ret = phy_loopback(dev->phydev, false); if (!ret) break; - /* Fallthrough */ + fallthrough; case STMMAC_LOOPBACK_MAC: stmmac_set_mac_loopback(priv, priv->ioaddr, false); break; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 3d747846f482..cc27d660a818 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -228,7 +228,7 @@ static int tc_setup_cls_u32(struct stmmac_priv *priv, switch (cls->command) { case TC_CLSU32_REPLACE_KNODE: tc_unfill_entry(priv, cls); - /* Fall through */ + fallthrough; case TC_CLSU32_NEW_KNODE: return tc_config_knode(priv, cls); case TC_CLSU32_DELETE_KNODE: diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index e2bc7a25f6d1..b624e177ec71 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -4759,7 +4759,7 @@ static int cas_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCGMIIPHY: /* Get address of MII PHY in use. */ data->phy_id = cp->phy_addr; - /* Fallthrough... */ + fallthrough; case SIOCGMIIREG: /* Read MII PHY register. */ spin_lock_irqsave(&cp->lock, flags); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 9b5effb72657..68695d4afacd 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -8835,7 +8835,7 @@ static int walk_phys(struct niu *np, struct niu_parent *parent) else goto unknown_vg_1g_port; - /* fallthru */ + fallthrough; case 0x22: val = (phy_encode(PORT_TYPE_10G, 0) | phy_encode(PORT_TYPE_10G, 1) | @@ -8860,7 +8860,7 @@ static int walk_phys(struct niu *np, struct niu_parent *parent) else goto unknown_vg_1g_port; - /* fallthru */ + fallthrough; case 0x13: if ((lowest_10g & 0x7) == 0) val = (phy_encode(PORT_TYPE_10G, 0) | diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index eeb8518c8a84..58f142ee78a3 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -2712,7 +2712,7 @@ static int gem_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCGMIIPHY: /* Get address of MII PHY in use. */ data->phy_id = gp->mii_phy_addr; - /* Fallthrough... */ + fallthrough; case SIOCGMIIREG: /* Read MII PHY register. */ data->val_out = __sungem_phy_read(gp, data->phy_id & 0x1f, @@ -2965,9 +2965,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* It is guaranteed that the returned buffer will be at least * PAGE_SIZE aligned. */ - gp->init_block = (struct gem_init_block *) - dma_alloc_coherent(&pdev->dev, sizeof(struct gem_init_block), - &gp->gblock_dvma, GFP_KERNEL); + gp->init_block = dma_alloc_coherent(&pdev->dev, sizeof(struct gem_init_block), + &gp->gblock_dvma, GFP_KERNEL); if (!gp->init_block) { pr_err("Cannot allocate init block, aborting\n"); err = -ENOMEM; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index cb994f66c3be..9baf3f3da91e 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -174,6 +174,8 @@ void am65_cpsw_nuss_adjust_link(struct net_device *ndev) if (phy->speed == 10 && phy_interface_is_rgmii(phy)) /* Can be used with in band mode only */ mac_control |= CPSW_SL_CTL_EXT_EN; + if (phy->speed == 100 && phy->interface == PHY_INTERFACE_MODE_RMII) + mac_control |= CPSW_SL_CTL_IFCTL_A; if (phy->duplex) mac_control |= CPSW_SL_CTL_FULLDUPLEX; diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index c59a289e428c..75056c14b161 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -83,6 +83,8 @@ struct am65_cpts_regs { #define AM65_CPTS_CONTROL_HW8_TS_PUSH_EN BIT(15) #define AM65_CPTS_CONTROL_HW1_TS_PUSH_OFFSET (8) +#define AM65_CPTS_CONTROL_TX_GENF_CLR_EN BIT(17) + #define AM65_CPTS_CONTROL_TS_SYNC_SEL_MASK (0xF) #define AM65_CPTS_CONTROL_TS_SYNC_SEL_SHIFT (28) @@ -748,42 +750,23 @@ EXPORT_SYMBOL_GPL(am65_cpts_rx_enable); static int am65_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid) { unsigned int ptp_class = ptp_classify_raw(skb); - u8 *msgtype, *data = skb->data; - unsigned int offset = 0; - __be16 *seqid; + struct ptp_header *hdr; + u8 msgtype; + u16 seqid; if (ptp_class == PTP_CLASS_NONE) return 0; - if (ptp_class & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (ptp_class & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return 0; - } - - if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid)) + hdr = ptp_parse_header(skb, ptp_class); + if (!hdr) return 0; - if (unlikely(ptp_class & PTP_CLASS_V1)) - msgtype = data + offset + OFF_PTP_CONTROL; - else - msgtype = data + offset; + msgtype = ptp_get_msgtype(hdr, ptp_class); + seqid = ntohs(hdr->sequence_id); - seqid = (__be16 *)(data + offset + OFF_PTP_SEQUENCE_ID); - *mtype_seqid = (*msgtype << AM65_CPTS_EVENT_1_MESSAGE_TYPE_SHIFT) & + *mtype_seqid = (msgtype << AM65_CPTS_EVENT_1_MESSAGE_TYPE_SHIFT) & AM65_CPTS_EVENT_1_MESSAGE_TYPE_MASK; - *mtype_seqid |= (ntohs(*seqid) & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK); + *mtype_seqid |= (seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK); return 1; } @@ -1005,7 +988,9 @@ struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, am65_cpts_set_add_val(cpts); - am65_cpts_write32(cpts, AM65_CPTS_CONTROL_EN | AM65_CPTS_CONTROL_64MODE, + am65_cpts_write32(cpts, AM65_CPTS_CONTROL_EN | + AM65_CPTS_CONTROL_64MODE | + AM65_CPTS_CONTROL_TX_GENF_CLR_EN, control); am65_cpts_write32(cpts, AM65_CPTS_INT_ENABLE_TS_PEND_EN, int_enable); diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c index 4e184eecc8e1..6e72ecbe5cf7 100644 --- a/drivers/net/ethernet/ti/cpsw-phy-sel.c +++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c @@ -67,7 +67,7 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv, dev_warn(priv->dev, "Unsupported PHY mode: \"%s\". Defaulting to MII.\n", phy_modes(phy_mode)); - /* fallthrough */ + fallthrough; case PHY_INTERFACE_MODE_MII: mode = AM33XX_GMII_SEL_MODE_MII; break; @@ -122,7 +122,7 @@ static void cpsw_gmii_sel_dra7xx(struct cpsw_phy_sel_priv *priv, dev_warn(priv->dev, "Unsupported PHY mode: \"%s\". Defaulting to MII.\n", phy_modes(phy_mode)); - /* fallthrough */ + fallthrough; case PHY_INTERFACE_MODE_MII: mode = AM33XX_GMII_SEL_MODE_MII; break; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9b17bbbe102f..4a65edc5a375 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1116,7 +1116,7 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, HOST_PORT_NUM, ALE_VLAN, vid); ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, 0, ALE_VLAN, vid); - ret |= cpsw_ale_flush_multicast(cpsw->ale, 0, vid); + ret |= cpsw_ale_flush_multicast(cpsw->ale, ALE_PORT_HOST, vid); err: pm_runtime_put(cpsw->dev); return ret; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 1247d35d42ef..8ed78577cded 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1032,19 +1032,34 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, return ret; } + /* reset the return code as pm_runtime_get_sync() can return + * non zero values as well. + */ + ret = 0; for (i = 0; i < cpsw->data.slaves; i++) { if (cpsw->slaves[i].ndev && - vid == cpsw->slaves[i].port_vlan) + vid == cpsw->slaves[i].port_vlan) { + ret = -EINVAL; goto err; + } } dev_dbg(priv->dev, "removing vlanid %d from vlan filter\n", vid); - cpsw_ale_del_vlan(cpsw->ale, vid, 0); - cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, - HOST_PORT_NUM, ALE_VLAN, vid); - cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, - 0, ALE_VLAN, vid); - cpsw_ale_flush_multicast(cpsw->ale, 0, vid); + ret = cpsw_ale_del_vlan(cpsw->ale, vid, 0); + if (ret) + dev_err(priv->dev, "cpsw_ale_del_vlan() failed: ret %d\n", ret); + ret = cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, + HOST_PORT_NUM, ALE_VLAN, vid); + if (ret) + dev_err(priv->dev, "cpsw_ale_del_ucast() failed: ret %d\n", + ret); + ret = cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, + 0, ALE_VLAN, vid); + if (ret) + dev_err(priv->dev, "cpsw_ale_del_mcast failed. ret %d\n", + ret); + cpsw_ale_flush_multicast(cpsw->ale, ALE_PORT_HOST, vid); + ret = 0; err: pm_runtime_put(cpsw->dev); return ret; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index d6d7a7d9c7ad..482a1a451e43 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1371,10 +1371,10 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp, break; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(ndev, prog, act); - /* fall through -- handle aborts by dropping packet */ + fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: goto drop; } diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index 7c55d395de2c..d1fc7955d422 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -446,41 +446,22 @@ static const struct ptp_clock_info cpts_info = { static int cpts_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid) { unsigned int ptp_class = ptp_classify_raw(skb); - u8 *msgtype, *data = skb->data; - unsigned int offset = 0; - u16 *seqid; + struct ptp_header *hdr; + u8 msgtype; + u16 seqid; if (ptp_class == PTP_CLASS_NONE) return 0; - if (ptp_class & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (ptp_class & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return 0; - } - - if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid)) + hdr = ptp_parse_header(skb, ptp_class); + if (!hdr) return 0; - if (unlikely(ptp_class & PTP_CLASS_V1)) - msgtype = data + offset + OFF_PTP_CONTROL; - else - msgtype = data + offset; + msgtype = ptp_get_msgtype(hdr, ptp_class); + seqid = ntohs(hdr->sequence_id); - seqid = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID); - *mtype_seqid = (*msgtype & MESSAGE_TYPE_MASK) << MESSAGE_TYPE_SHIFT; - *mtype_seqid |= (ntohs(*seqid) & SEQUENCE_ID_MASK) << SEQUENCE_ID_SHIFT; + *mtype_seqid = (msgtype & MESSAGE_TYPE_MASK) << MESSAGE_TYPE_SHIFT; + *mtype_seqid |= (seqid & SEQUENCE_ID_MASK) << SEQUENCE_ID_SHIFT; return 1; } @@ -528,6 +509,11 @@ void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb) int ret; u64 ns; + /* cpts_rx_timestamp() is called before eth_type_trans(), so + * skb MAC Hdr properties are not configured yet. Hence need to + * reset skb MAC header here + */ + skb_reset_mac_header(skb); ret = cpts_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid); if (!ret) return; diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 58623e974a0c..76a342ea3797 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -948,7 +948,7 @@ static int tlan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) switch (cmd) { case SIOCGMIIPHY: /* get address of MII PHY in use. */ data->phy_id = phy; - /* fall through */ + fallthrough; case SIOCGMIIREG: /* read MII PHY register. */ diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c index 2db546b27ee0..dc14a66583ff 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c @@ -877,7 +877,7 @@ static int gelic_wl_set_auth(struct net_device *netdev, case IW_AUTH_KEY_MGMT: if (param->value & IW_AUTH_KEY_MGMT_PSK) break; - /* intentionally fall through */ + fallthrough; default: ret = -EOPNOTSUPP; break; diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c index 07389702a540..5f5b33e6653b 100644 --- a/drivers/net/ethernet/toshiba/spider_net.c +++ b/drivers/net/ethernet/toshiba/spider_net.c @@ -786,7 +786,7 @@ spider_net_release_tx_chain(struct spider_net_card *card, int brutal) /* fallthrough, if we release the descriptors * brutally (then we don't care about * SPIDER_NET_DESCR_CARDOWNED) */ - /* Fall through */ + fallthrough; case SPIDER_NET_DESCR_RESPONSE_ERROR: case SPIDER_NET_DESCR_PROTECTION_ERROR: @@ -1397,9 +1397,9 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg, show_error = 0; break; - case SPIDER_NET_GDDDEN0INT: /* fallthrough */ - case SPIDER_NET_GDCDEN0INT: /* fallthrough */ - case SPIDER_NET_GDBDEN0INT: /* fallthrough */ + case SPIDER_NET_GDDDEN0INT: + case SPIDER_NET_GDCDEN0INT: + case SPIDER_NET_GDBDEN0INT: case SPIDER_NET_GDADEN0INT: /* someone has set RX_DMA_EN to 0 */ show_error = 0; @@ -1449,10 +1449,10 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg, * Logging is not needed. */ show_error = 0; break; - case SPIDER_NET_GRFDFLLINT: /* fallthrough */ - case SPIDER_NET_GRFCFLLINT: /* fallthrough */ - case SPIDER_NET_GRFBFLLINT: /* fallthrough */ - case SPIDER_NET_GRFAFLLINT: /* fallthrough */ + case SPIDER_NET_GRFDFLLINT: + case SPIDER_NET_GRFCFLLINT: + case SPIDER_NET_GRFBFLLINT: + case SPIDER_NET_GRFAFLLINT: case SPIDER_NET_GRMFLLINT: /* Could happen when rx chain is full */ if (card->ignore_rx_ramfull == 0) { @@ -1473,9 +1473,9 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg, break; /* chain end */ - case SPIDER_NET_GDDDCEINT: /* fallthrough */ - case SPIDER_NET_GDCDCEINT: /* fallthrough */ - case SPIDER_NET_GDBDCEINT: /* fallthrough */ + case SPIDER_NET_GDDDCEINT: + case SPIDER_NET_GDCDCEINT: + case SPIDER_NET_GDBDCEINT: case SPIDER_NET_GDADCEINT: spider_net_resync_head_ptr(card); spider_net_refill_rx_chain(card); @@ -1486,9 +1486,9 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg, break; /* invalid descriptor */ - case SPIDER_NET_GDDINVDINT: /* fallthrough */ - case SPIDER_NET_GDCINVDINT: /* fallthrough */ - case SPIDER_NET_GDBINVDINT: /* fallthrough */ + case SPIDER_NET_GDDINVDINT: + case SPIDER_NET_GDCINVDINT: + case SPIDER_NET_GDBINVDINT: case SPIDER_NET_GDAINVDINT: /* Could happen when rx chain is full */ spider_net_resync_head_ptr(card); diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index 6bcda20ed7e7..7a6e5ff8e5d4 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -454,9 +454,9 @@ static struct sk_buff *alloc_rxbuf_skb(struct net_device *dev, skb = netdev_alloc_skb(dev, RX_BUF_SIZE); if (!skb) return NULL; - *dma_handle = pci_map_single(hwdev, skb->data, RX_BUF_SIZE, - PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(hwdev, *dma_handle)) { + *dma_handle = dma_map_single(&hwdev->dev, skb->data, RX_BUF_SIZE, + DMA_FROM_DEVICE); + if (dma_mapping_error(&hwdev->dev, *dma_handle)) { dev_kfree_skb_any(skb); return NULL; } @@ -466,8 +466,8 @@ static struct sk_buff *alloc_rxbuf_skb(struct net_device *dev, static void free_rxbuf_skb(struct pci_dev *hwdev, struct sk_buff *skb, dma_addr_t dma_handle) { - pci_unmap_single(hwdev, dma_handle, RX_BUF_SIZE, - PCI_DMA_FROMDEVICE); + dma_unmap_single(&hwdev->dev, dma_handle, RX_BUF_SIZE, + DMA_FROM_DEVICE); dev_kfree_skb_any(skb); } @@ -876,9 +876,9 @@ tc35815_init_queues(struct net_device *dev) sizeof(struct TxFD) * TX_FD_NUM > PAGE_SIZE * FD_PAGE_NUM); - lp->fd_buf = pci_alloc_consistent(lp->pci_dev, - PAGE_SIZE * FD_PAGE_NUM, - &lp->fd_buf_dma); + lp->fd_buf = dma_alloc_coherent(&lp->pci_dev->dev, + PAGE_SIZE * FD_PAGE_NUM, + &lp->fd_buf_dma, GFP_ATOMIC); if (!lp->fd_buf) return -ENOMEM; for (i = 0; i < RX_BUF_NUM; i++) { @@ -892,10 +892,9 @@ tc35815_init_queues(struct net_device *dev) lp->rx_skbs[i].skb_dma); lp->rx_skbs[i].skb = NULL; } - pci_free_consistent(lp->pci_dev, - PAGE_SIZE * FD_PAGE_NUM, - lp->fd_buf, - lp->fd_buf_dma); + dma_free_coherent(&lp->pci_dev->dev, + PAGE_SIZE * FD_PAGE_NUM, + lp->fd_buf, lp->fd_buf_dma); lp->fd_buf = NULL; return -ENOMEM; } @@ -990,7 +989,9 @@ tc35815_clear_queues(struct net_device *dev) BUG_ON(lp->tx_skbs[i].skb != skb); #endif if (skb) { - pci_unmap_single(lp->pci_dev, lp->tx_skbs[i].skb_dma, skb->len, PCI_DMA_TODEVICE); + dma_unmap_single(&lp->pci_dev->dev, + lp->tx_skbs[i].skb_dma, skb->len, + DMA_TO_DEVICE); lp->tx_skbs[i].skb = NULL; lp->tx_skbs[i].skb_dma = 0; dev_kfree_skb_any(skb); @@ -1022,7 +1023,9 @@ tc35815_free_queues(struct net_device *dev) BUG_ON(lp->tx_skbs[i].skb != skb); #endif if (skb) { - pci_unmap_single(lp->pci_dev, lp->tx_skbs[i].skb_dma, skb->len, PCI_DMA_TODEVICE); + dma_unmap_single(&lp->pci_dev->dev, + lp->tx_skbs[i].skb_dma, + skb->len, DMA_TO_DEVICE); dev_kfree_skb(skb); lp->tx_skbs[i].skb = NULL; lp->tx_skbs[i].skb_dma = 0; @@ -1044,8 +1047,8 @@ tc35815_free_queues(struct net_device *dev) } } if (lp->fd_buf) { - pci_free_consistent(lp->pci_dev, PAGE_SIZE * FD_PAGE_NUM, - lp->fd_buf, lp->fd_buf_dma); + dma_free_coherent(&lp->pci_dev->dev, PAGE_SIZE * FD_PAGE_NUM, + lp->fd_buf, lp->fd_buf_dma); lp->fd_buf = NULL; } } @@ -1292,7 +1295,10 @@ tc35815_send_packet(struct sk_buff *skb, struct net_device *dev) BUG_ON(lp->tx_skbs[lp->tfd_start].skb); #endif lp->tx_skbs[lp->tfd_start].skb = skb; - lp->tx_skbs[lp->tfd_start].skb_dma = pci_map_single(lp->pci_dev, skb->data, skb->len, PCI_DMA_TODEVICE); + lp->tx_skbs[lp->tfd_start].skb_dma = dma_map_single(&lp->pci_dev->dev, + skb->data, + skb->len, + DMA_TO_DEVICE); /*add to ring */ txfd = &lp->tfd_base[lp->tfd_start]; @@ -1500,9 +1506,9 @@ tc35815_rx(struct net_device *dev, int limit) skb = lp->rx_skbs[cur_bd].skb; prefetch(skb->data); lp->rx_skbs[cur_bd].skb = NULL; - pci_unmap_single(lp->pci_dev, + dma_unmap_single(&lp->pci_dev->dev, lp->rx_skbs[cur_bd].skb_dma, - RX_BUF_SIZE, PCI_DMA_FROMDEVICE); + RX_BUF_SIZE, DMA_FROM_DEVICE); if (!HAVE_DMA_RXALIGN(lp) && NET_IP_ALIGN != 0) memmove(skb->data, skb->data - NET_IP_ALIGN, pkt_len); @@ -1756,7 +1762,9 @@ tc35815_txdone(struct net_device *dev) #endif if (skb) { dev->stats.tx_bytes += skb->len; - pci_unmap_single(lp->pci_dev, lp->tx_skbs[lp->tfd_end].skb_dma, skb->len, PCI_DMA_TODEVICE); + dma_unmap_single(&lp->pci_dev->dev, + lp->tx_skbs[lp->tfd_end].skb_dma, + skb->len, DMA_TO_DEVICE); lp->tx_skbs[lp->tfd_end].skb = NULL; lp->tx_skbs[lp->tfd_end].skb_dma = 0; dev_kfree_skb_any(skb); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index fa5dc2993520..9aafd3ecdaa4 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2038,8 +2038,7 @@ static int axienet_remove(struct platform_device *pdev) axienet_mdio_teardown(lp); - if (lp->clk) - clk_disable_unprepare(lp->clk); + clk_disable_unprepare(lp->clk); of_node_put(lp->phy_node); lp->phy_node = NULL; diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index 3e3883ad88b0..3e337142b516 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -1434,7 +1434,7 @@ do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) switch(cmd) { case SIOCGMIIPHY: /* Get the address of the PHY in use. */ data->phy_id = 0; /* we have only this address */ - /* fall through */ + fallthrough; case SIOCGMIIREG: /* Read the specified MII register. */ data->val_out = mii_rd(ioaddr, data->phy_id & 0x1f, data->reg_num & 0x1f); diff --git a/drivers/net/fddi/skfp/cfm.c b/drivers/net/fddi/skfp/cfm.c index e9bf42996de8..4eea3408034b 100644 --- a/drivers/net/fddi/skfp/cfm.c +++ b/drivers/net/fddi/skfp/cfm.c @@ -36,10 +36,6 @@ #define KERNEL #include "h/smtstate.h" -#ifndef lint -static const char ID_sccs[] = "@(#)cfm.c 2.18 98/10/06 (C) SK " ; -#endif - /* * FSM Macros */ @@ -208,7 +204,6 @@ void cfm(struct s_smc *smc, int event) { int state ; /* remember last state */ int cond ; - int oldstate ; /* We will do the following: */ /* - compute the variable WC_Flag for every port (This is where */ @@ -222,7 +217,6 @@ void cfm(struct s_smc *smc, int event) /* - change the portstates */ cem_priv_state (smc, event); - oldstate = smc->mib.fddiSMTCF_State ; do { DB_CFM("CFM : state %s%s event %s", smc->mib.fddiSMTCF_State & AFLAG ? "ACTIONS " : "", @@ -250,18 +244,11 @@ void cfm(struct s_smc *smc, int event) if (cond != smc->mib.fddiSMTPeerWrapFlag) smt_srf_event(smc,SMT_COND_SMT_PEER_WRAP,0,cond) ; -#if 0 /* - * Don't send ever MAC_PATH_CHANGE events. Our MAC is hard-wired + * Don't ever send MAC_PATH_CHANGE events. Our MAC is hard-wired * to the primary path. */ - /* - * path change - */ - if (smc->mib.fddiSMTCF_State != oldstate) { - smt_srf_event(smc,SMT_EVENT_MAC_PATH_CHANGE,INDEX_MAC,0) ; - } -#endif + #endif /* no SLIM_SMT */ /* diff --git a/drivers/net/fddi/skfp/fplustm.c b/drivers/net/fddi/skfp/fplustm.c index 02966d141948..4cbb145c74ab 100644 --- a/drivers/net/fddi/skfp/fplustm.c +++ b/drivers/net/fddi/skfp/fplustm.c @@ -21,10 +21,6 @@ #include <linux/bitrev.h> #include <linux/etherdevice.h> -#ifndef lint -static const char ID_sccs[] = "@(#)fplustm.c 1.32 99/02/23 (C) SK " ; -#endif - #ifndef UNUSED #ifdef lint #define UNUSED(x) (x) = (x) diff --git a/drivers/net/fddi/skfp/hwmtm.c b/drivers/net/fddi/skfp/hwmtm.c index 3412e0fb0ac4..107039056511 100644 --- a/drivers/net/fddi/skfp/hwmtm.c +++ b/drivers/net/fddi/skfp/hwmtm.c @@ -10,10 +10,6 @@ * ******************************************************************************/ -#ifndef lint -static char const ID_sccs[] = "@(#)hwmtm.c 1.40 99/05/31 (C) SK" ; -#endif - #define HWMTM #ifndef FDDI diff --git a/drivers/net/fddi/skfp/pcmplc.c b/drivers/net/fddi/skfp/pcmplc.c index 1be039579d70..554cde8d6073 100644 --- a/drivers/net/fddi/skfp/pcmplc.c +++ b/drivers/net/fddi/skfp/pcmplc.c @@ -847,7 +847,7 @@ static void pcm_fsm(struct s_smc *smc, struct s_phy *phy, int cmd) case ACTIONS(PC5_SIGNAL) : ACTIONS_DONE() ; - /* fall through */ + fallthrough; case PC5_SIGNAL : if ((cmd != PC_SIGNAL) && (cmd != PC_TIMEOUT_LCT)) break ; @@ -946,7 +946,7 @@ static void pcm_fsm(struct s_smc *smc, struct s_phy *phy, int cmd) SETMASK(PLC(np,PL_CNTRL_B),PL_PC_JOIN,PL_PC_JOIN) ; ACTIONS_DONE() ; cmd = 0 ; - /* fall thru */ + fallthrough; case PC6_JOIN : switch (plc->p_state) { case PS_ACTIVE: diff --git a/drivers/net/fddi/skfp/smt.c b/drivers/net/fddi/skfp/smt.c index b8c59d803ce6..774a6e3b0a67 100644 --- a/drivers/net/fddi/skfp/smt.c +++ b/drivers/net/fddi/skfp/smt.c @@ -20,10 +20,6 @@ #define KERNEL #include "h/smtstate.h" -#ifndef lint -static const char ID_sccs[] = "@(#)smt.c 2.43 98/11/23 (C) SK " ; -#endif - /* * FC in SMbuf */ @@ -1561,7 +1557,7 @@ u_long smt_get_tid(struct s_smc *smc) return tid & 0x3fffffffL; } - +#ifdef LITTLE_ENDIAN /* * table of parameter lengths */ @@ -1641,6 +1637,7 @@ static const struct smt_pdef { } ; #define N_SMT_PLEN ARRAY_SIZE(smt_pdef) +#endif int smt_check_para(struct s_smc *smc, struct smt_header *sm, const u_short list[]) diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index 8c810edece86..466622664424 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -974,7 +974,7 @@ static void fjes_stop_req_irq(struct fjes_adapter *adapter, int src_epid) FJES_RX_STOP_REQ_DONE; spin_unlock_irqrestore(&hw->rx_status_lock, flags); clear_bit(src_epid, &hw->txrx_stop_req_bit); - /* fall through */ + fallthrough; case EP_PARTNER_UNSHARE: case EP_PARTNER_COMPLETE: default: diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 21640a035d7d..611722eafed8 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -928,8 +928,8 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) } } -static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, - struct genl_info *info) +static struct pdp_ctx *gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, + struct genl_info *info) { struct pdp_ctx *pctx, *pctx_tid = NULL; struct net_device *dev = gtp->dev; @@ -956,12 +956,12 @@ static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, if (found) { if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) - return -EEXIST; + return ERR_PTR(-EEXIST); if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE) - return -EOPNOTSUPP; + return ERR_PTR(-EOPNOTSUPP); if (pctx && pctx_tid) - return -EEXIST; + return ERR_PTR(-EEXIST); if (!pctx) pctx = pctx_tid; @@ -974,13 +974,13 @@ static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, netdev_dbg(dev, "GTPv1-U: update tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); - return 0; + return pctx; } pctx = kmalloc(sizeof(*pctx), GFP_ATOMIC); if (pctx == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); sock_hold(sk); pctx->sk = sk; @@ -1018,7 +1018,7 @@ static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, break; } - return 0; + return pctx; } static void pdp_context_free(struct rcu_head *head) @@ -1036,9 +1036,12 @@ static void pdp_context_delete(struct pdp_ctx *pctx) call_rcu(&pctx->rcu_head, pdp_context_free); } +static int gtp_tunnel_notify(struct pdp_ctx *pctx, u8 cmd, gfp_t allocation); + static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) { unsigned int version; + struct pdp_ctx *pctx; struct gtp_dev *gtp; struct sock *sk; int err; @@ -1068,7 +1071,6 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) } rtnl_lock(); - rcu_read_lock(); gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); if (!gtp) { @@ -1088,10 +1090,15 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) goto out_unlock; } - err = gtp_pdp_add(gtp, sk, info); + pctx = gtp_pdp_add(gtp, sk, info); + if (IS_ERR(pctx)) { + err = PTR_ERR(pctx); + } else { + gtp_tunnel_notify(pctx, GTP_CMD_NEWPDP, GFP_KERNEL); + err = 0; + } out_unlock: - rcu_read_unlock(); rtnl_unlock(); return err; } @@ -1159,6 +1166,7 @@ static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); + gtp_tunnel_notify(pctx, GTP_CMD_DELPDP, GFP_ATOMIC); pdp_context_delete(pctx); out_unlock: @@ -1168,6 +1176,14 @@ out_unlock: static struct genl_family gtp_genl_family; +enum gtp_multicast_groups { + GTP_GENL_MCGRP, +}; + +static const struct genl_multicast_group gtp_genl_mcgrps[] = { + [GTP_GENL_MCGRP] = { .name = GTP_GENL_MCGRP_NAME }, +}; + static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, int flags, u32 type, struct pdp_ctx *pctx) { @@ -1179,6 +1195,7 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, goto nlmsg_failure; if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) || + nla_put_u32(skb, GTPA_LINK, pctx->dev->ifindex) || nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) || nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr)) goto nla_put_failure; @@ -1204,6 +1221,26 @@ nla_put_failure: return -EMSGSIZE; } +static int gtp_tunnel_notify(struct pdp_ctx *pctx, u8 cmd, gfp_t allocation) +{ + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, allocation); + if (!msg) + return -ENOMEM; + + ret = gtp_genl_fill_info(msg, 0, 0, 0, cmd, pctx); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + ret = genlmsg_multicast_netns(>p_genl_family, dev_net(pctx->dev), msg, + 0, GTP_GENL_MCGRP, GFP_ATOMIC); + return ret; +} + static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) { struct pdp_ctx *pctx = NULL; @@ -1334,6 +1371,8 @@ static struct genl_family gtp_genl_family __ro_after_init = { .module = THIS_MODULE, .ops = gtp_genl_ops, .n_ops = ARRAY_SIZE(gtp_genl_ops), + .mcgrps = gtp_genl_mcgrps, + .n_mcgrps = ARRAY_SIZE(gtp_genl_mcgrps), }; static int __net_init gtp_net_init(struct net *net) diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 4476491b58f9..e4e4981ac1d2 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -500,7 +500,7 @@ static int transmit(struct baycom_state *bc, int cnt, unsigned char stat) } break; } - /* fall through */ + fallthrough; default: if (bc->hdlctx.calibrate <= 0) diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index deef14215110..17be2bb2985c 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -482,7 +482,7 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len) case CRC_MODE_SMACK_TEST: ax->crcmode = CRC_MODE_FLEX_TEST; printk(KERN_INFO "mkiss: %s: Trying crc-smack\n", ax->dev->name); - // fall through + fallthrough; case CRC_MODE_SMACK: *p |= 0x80; crc = swab16(crc16(0, p, len)); @@ -491,7 +491,7 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len) case CRC_MODE_FLEX_TEST: ax->crcmode = CRC_MODE_NONE; printk(KERN_INFO "mkiss: %s: Trying crc-flexnet\n", ax->dev->name); - // fall through + fallthrough; case CRC_MODE_FLEX: *p |= 0x20; crc = calc_crc_flex(p, len); @@ -744,7 +744,6 @@ static int mkiss_open(struct tty_struct *tty) ax->dev->name); break; case 0: - /* fall through */ default: crc_force = 0; printk(KERN_INFO "mkiss: %s: crc mode is auto.\n", diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index a4b3fce69ecd..22010384c4a3 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -151,7 +151,8 @@ static int rr_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto out; } - tmpptr = pci_alloc_consistent(pdev, TX_TOTAL_SIZE, &ring_dma); + tmpptr = dma_alloc_coherent(&pdev->dev, TX_TOTAL_SIZE, &ring_dma, + GFP_KERNEL); rrpriv->tx_ring = tmpptr; rrpriv->tx_ring_dma = ring_dma; @@ -160,7 +161,8 @@ static int rr_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto out; } - tmpptr = pci_alloc_consistent(pdev, RX_TOTAL_SIZE, &ring_dma); + tmpptr = dma_alloc_coherent(&pdev->dev, RX_TOTAL_SIZE, &ring_dma, + GFP_KERNEL); rrpriv->rx_ring = tmpptr; rrpriv->rx_ring_dma = ring_dma; @@ -169,7 +171,8 @@ static int rr_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto out; } - tmpptr = pci_alloc_consistent(pdev, EVT_RING_SIZE, &ring_dma); + tmpptr = dma_alloc_coherent(&pdev->dev, EVT_RING_SIZE, &ring_dma, + GFP_KERNEL); rrpriv->evt_ring = tmpptr; rrpriv->evt_ring_dma = ring_dma; @@ -198,14 +201,14 @@ static int rr_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) out: if (rrpriv->evt_ring) - pci_free_consistent(pdev, EVT_RING_SIZE, rrpriv->evt_ring, - rrpriv->evt_ring_dma); + dma_free_coherent(&pdev->dev, EVT_RING_SIZE, rrpriv->evt_ring, + rrpriv->evt_ring_dma); if (rrpriv->rx_ring) - pci_free_consistent(pdev, RX_TOTAL_SIZE, rrpriv->rx_ring, - rrpriv->rx_ring_dma); + dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, rrpriv->rx_ring, + rrpriv->rx_ring_dma); if (rrpriv->tx_ring) - pci_free_consistent(pdev, TX_TOTAL_SIZE, rrpriv->tx_ring, - rrpriv->tx_ring_dma); + dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, rrpriv->tx_ring, + rrpriv->tx_ring_dma); if (rrpriv->regs) pci_iounmap(pdev, rrpriv->regs); if (pdev) @@ -228,12 +231,12 @@ static void rr_remove_one(struct pci_dev *pdev) } unregister_netdev(dev); - pci_free_consistent(pdev, EVT_RING_SIZE, rr->evt_ring, - rr->evt_ring_dma); - pci_free_consistent(pdev, RX_TOTAL_SIZE, rr->rx_ring, - rr->rx_ring_dma); - pci_free_consistent(pdev, TX_TOTAL_SIZE, rr->tx_ring, - rr->tx_ring_dma); + dma_free_coherent(&pdev->dev, EVT_RING_SIZE, rr->evt_ring, + rr->evt_ring_dma); + dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, rr->rx_ring, + rr->rx_ring_dma); + dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, rr->tx_ring, + rr->tx_ring_dma); pci_iounmap(pdev, rr->regs); pci_release_regions(pdev); pci_disable_device(pdev); @@ -648,8 +651,8 @@ static int rr_init1(struct net_device *dev) goto error; } rrpriv->rx_skbuff[i] = skb; - addr = pci_map_single(rrpriv->pci_dev, skb->data, - dev->mtu + HIPPI_HLEN, PCI_DMA_FROMDEVICE); + addr = dma_map_single(&rrpriv->pci_dev->dev, skb->data, + dev->mtu + HIPPI_HLEN, DMA_FROM_DEVICE); /* * Sanity test to see if we conflict with the DMA * limitations of the Roadrunner. @@ -699,10 +702,10 @@ static int rr_init1(struct net_device *dev) struct sk_buff *skb = rrpriv->rx_skbuff[i]; if (skb) { - pci_unmap_single(rrpriv->pci_dev, + dma_unmap_single(&rrpriv->pci_dev->dev, rrpriv->rx_ring[i].addr.addrlo, dev->mtu + HIPPI_HLEN, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); rrpriv->rx_ring[i].size = 0; set_rraddr(&rrpriv->rx_ring[i].addr, 0); dev_kfree_skb(skb); @@ -953,18 +956,18 @@ static void rx_int(struct net_device *dev, u32 rxlimit, u32 index) dev->stats.rx_dropped++; goto defer; } else { - pci_dma_sync_single_for_cpu(rrpriv->pci_dev, - desc->addr.addrlo, - pkt_len, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&rrpriv->pci_dev->dev, + desc->addr.addrlo, + pkt_len, + DMA_FROM_DEVICE); skb_put_data(skb, rx_skb->data, pkt_len); - pci_dma_sync_single_for_device(rrpriv->pci_dev, - desc->addr.addrlo, - pkt_len, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&rrpriv->pci_dev->dev, + desc->addr.addrlo, + pkt_len, + DMA_FROM_DEVICE); } }else{ struct sk_buff *newskb; @@ -974,16 +977,17 @@ static void rx_int(struct net_device *dev, u32 rxlimit, u32 index) if (newskb){ dma_addr_t addr; - pci_unmap_single(rrpriv->pci_dev, - desc->addr.addrlo, dev->mtu + - HIPPI_HLEN, PCI_DMA_FROMDEVICE); + dma_unmap_single(&rrpriv->pci_dev->dev, + desc->addr.addrlo, + dev->mtu + HIPPI_HLEN, + DMA_FROM_DEVICE); skb = rx_skb; skb_put(skb, pkt_len); rrpriv->rx_skbuff[index] = newskb; - addr = pci_map_single(rrpriv->pci_dev, - newskb->data, - dev->mtu + HIPPI_HLEN, - PCI_DMA_FROMDEVICE); + addr = dma_map_single(&rrpriv->pci_dev->dev, + newskb->data, + dev->mtu + HIPPI_HLEN, + DMA_FROM_DEVICE); set_rraddr(&desc->addr, addr); } else { printk("%s: Out of memory, deferring " @@ -1068,9 +1072,9 @@ static irqreturn_t rr_interrupt(int irq, void *dev_id) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - pci_unmap_single(rrpriv->pci_dev, + dma_unmap_single(&rrpriv->pci_dev->dev, desc->addr.addrlo, skb->len, - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); dev_kfree_skb_irq(skb); rrpriv->tx_skbuff[txcon] = NULL; @@ -1110,8 +1114,9 @@ static inline void rr_raz_tx(struct rr_private *rrpriv, if (skb) { struct tx_desc *desc = &(rrpriv->tx_ring[i]); - pci_unmap_single(rrpriv->pci_dev, desc->addr.addrlo, - skb->len, PCI_DMA_TODEVICE); + dma_unmap_single(&rrpriv->pci_dev->dev, + desc->addr.addrlo, skb->len, + DMA_TO_DEVICE); desc->size = 0; set_rraddr(&desc->addr, 0); dev_kfree_skb(skb); @@ -1132,8 +1137,10 @@ static inline void rr_raz_rx(struct rr_private *rrpriv, if (skb) { struct rx_desc *desc = &(rrpriv->rx_ring[i]); - pci_unmap_single(rrpriv->pci_dev, desc->addr.addrlo, - dev->mtu + HIPPI_HLEN, PCI_DMA_FROMDEVICE); + dma_unmap_single(&rrpriv->pci_dev->dev, + desc->addr.addrlo, + dev->mtu + HIPPI_HLEN, + DMA_FROM_DEVICE); desc->size = 0; set_rraddr(&desc->addr, 0); dev_kfree_skb(skb); @@ -1188,17 +1195,17 @@ static int rr_open(struct net_device *dev) goto error; } - rrpriv->rx_ctrl = pci_alloc_consistent(pdev, - 256 * sizeof(struct ring_ctrl), - &dma_addr); + rrpriv->rx_ctrl = dma_alloc_coherent(&pdev->dev, + 256 * sizeof(struct ring_ctrl), + &dma_addr, GFP_KERNEL); if (!rrpriv->rx_ctrl) { ecode = -ENOMEM; goto error; } rrpriv->rx_ctrl_dma = dma_addr; - rrpriv->info = pci_alloc_consistent(pdev, sizeof(struct rr_info), - &dma_addr); + rrpriv->info = dma_alloc_coherent(&pdev->dev, sizeof(struct rr_info), + &dma_addr, GFP_KERNEL); if (!rrpriv->info) { ecode = -ENOMEM; goto error; @@ -1237,13 +1244,13 @@ static int rr_open(struct net_device *dev) spin_unlock_irqrestore(&rrpriv->lock, flags); if (rrpriv->info) { - pci_free_consistent(pdev, sizeof(struct rr_info), rrpriv->info, - rrpriv->info_dma); + dma_free_coherent(&pdev->dev, sizeof(struct rr_info), + rrpriv->info, rrpriv->info_dma); rrpriv->info = NULL; } if (rrpriv->rx_ctrl) { - pci_free_consistent(pdev, 256 * sizeof(struct ring_ctrl), - rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma); + dma_free_coherent(&pdev->dev, 256 * sizeof(struct ring_ctrl), + rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma); rrpriv->rx_ctrl = NULL; } @@ -1365,12 +1372,12 @@ static int rr_close(struct net_device *dev) rr_raz_tx(rrpriv, dev); rr_raz_rx(rrpriv, dev); - pci_free_consistent(pdev, 256 * sizeof(struct ring_ctrl), - rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma); + dma_free_coherent(&pdev->dev, 256 * sizeof(struct ring_ctrl), + rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma); rrpriv->rx_ctrl = NULL; - pci_free_consistent(pdev, sizeof(struct rr_info), rrpriv->info, - rrpriv->info_dma); + dma_free_coherent(&pdev->dev, sizeof(struct rr_info), rrpriv->info, + rrpriv->info_dma); rrpriv->info = NULL; spin_unlock_irqrestore(&rrpriv->lock, flags); @@ -1430,8 +1437,8 @@ static netdev_tx_t rr_start_xmit(struct sk_buff *skb, index = txctrl->pi; rrpriv->tx_skbuff[index] = skb; - set_rraddr(&rrpriv->tx_ring[index].addr, pci_map_single( - rrpriv->pci_dev, skb->data, len + 8, PCI_DMA_TODEVICE)); + set_rraddr(&rrpriv->tx_ring[index].addr, + dma_map_single(&rrpriv->pci_dev->dev, skb->data, len + 8, DMA_TO_DEVICE)); rrpriv->tx_ring[index].size = len + 8; /* include IFIELD */ rrpriv->tx_ring[index].mode = PACKET_START | PACKET_END; txctrl->pi = (index + 1) % TX_RING_ENTRIES; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 787f17e2a971..64b0a74c1523 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -367,7 +367,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, } rcu_read_unlock(); - while (unlikely(txq >= ndev->real_num_tx_queues)) + while (txq >= ndev->real_num_tx_queues) txq -= ndev->real_num_tx_queues; return txq; @@ -502,7 +502,7 @@ static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev, int rc; skb->dev = vf_netdev; - skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping; + skb_record_rx_queue(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); rc = dev_queue_xmit(skb); if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) { diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index 55115cfb2972..407fee841a9a 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -10,7 +10,6 @@ #include <linux/device.h> #include <linux/notifier.h> #include <linux/pm_wakeup.h> -#include <linux/notifier.h> #include "ipa_version.h" #include "gsi.h" diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 15e87c097b0b..60b7d93bb834 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -106,12 +106,21 @@ static void ipvlan_port_destroy(struct net_device *dev) kfree(port); } +#define IPVLAN_ALWAYS_ON_OFLOADS \ + (NETIF_F_SG | NETIF_F_HW_CSUM | \ + NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL) + +#define IPVLAN_ALWAYS_ON \ + (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED) + #define IPVLAN_FEATURES \ - (NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ + (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \ NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) + /* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */ + #define IPVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) @@ -125,7 +134,9 @@ static int ipvlan_init(struct net_device *dev) dev->state = (dev->state & ~IPVLAN_STATE_MASK) | (phy_dev->state & IPVLAN_STATE_MASK); dev->features = phy_dev->features & IPVLAN_FEATURES; - dev->features |= NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED; + dev->features |= IPVLAN_ALWAYS_ON; + dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; + dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; dev->gso_max_size = phy_dev->gso_max_size; dev->gso_max_segs = phy_dev->gso_max_segs; @@ -227,7 +238,14 @@ static netdev_features_t ipvlan_fix_features(struct net_device *dev, { struct ipvl_dev *ipvlan = netdev_priv(dev); - return features & (ipvlan->sfeatures | ~IPVLAN_FEATURES); + features |= NETIF_F_ALL_FOR_ALL; + features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES); + features = netdev_increment_features(ipvlan->phy_dev->features, + features, features); + features |= IPVLAN_ALWAYS_ON; + features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON); + + return features; } static void ipvlan_change_rx_flags(struct net_device *dev, int change) @@ -666,6 +684,13 @@ static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] = [IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 }, }; +static struct net *ipvlan_get_link_net(const struct net_device *dev) +{ + struct ipvl_dev *ipvlan = netdev_priv(dev); + + return dev_net(ipvlan->phy_dev); +} + static struct rtnl_link_ops ipvlan_link_ops = { .kind = "ipvlan", .priv_size = sizeof(struct ipvl_dev), @@ -673,6 +698,7 @@ static struct rtnl_link_ops ipvlan_link_ops = { .setup = ipvlan_link_setup, .newlink = ipvlan_link_new, .dellink = ipvlan_link_delete, + .get_link_net = ipvlan_get_link_net, }; int ipvlan_link_register(struct rtnl_link_ops *ops) @@ -734,10 +760,9 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - ipvlan->dev->features = dev->features & IPVLAN_FEATURES; ipvlan->dev->gso_max_size = dev->gso_max_size; ipvlan->dev->gso_max_segs = dev->gso_max_segs; - netdev_features_change(ipvlan->dev); + netdev_update_features(ipvlan->dev); } break; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 9159846b8b93..124045cbcda3 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1611,7 +1611,7 @@ static const struct nla_policy macsec_genl_rxsc_policy[NUM_MACSEC_RXSC_ATTR] = { static const struct nla_policy macsec_genl_sa_policy[NUM_MACSEC_SA_ATTR] = { [MACSEC_SA_ATTR_AN] = { .type = NLA_U8 }, [MACSEC_SA_ATTR_ACTIVE] = { .type = NLA_U8 }, - [MACSEC_SA_ATTR_PN] = { .type = NLA_MIN_LEN, .len = 4 }, + [MACSEC_SA_ATTR_PN] = NLA_POLICY_MIN_LEN(4), [MACSEC_SA_ATTR_KEYID] = { .type = NLA_BINARY, .len = MACSEC_KEYID_LEN, }, [MACSEC_SA_ATTR_KEY] = { .type = NLA_BINARY, diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 4942f6112e51..c8d803d3616c 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -842,7 +842,7 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCSHWTSTAMP: if (!net_eq(dev_net(dev), &init_net)) break; - /* fall through */ + fallthrough; case SIOCGHWTSTAMP: if (netif_device_present(real_dev) && ops->ndo_do_ioctl) err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd); @@ -1269,6 +1269,9 @@ static void macvlan_port_destroy(struct net_device *dev) static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { + struct nlattr *nla, *head; + int rem, len; + if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; @@ -1316,6 +1319,20 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], return -EADDRNOTAVAIL; } + if (data[IFLA_MACVLAN_MACADDR_DATA]) { + head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); + len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); + + nla_for_each_attr(nla, head, len, rem) { + if (nla_type(nla) != IFLA_MACVLAN_MACADDR || + nla_len(nla) != ETH_ALEN) + return -EINVAL; + + if (!is_valid_ether_addr(nla_data(nla))) + return -EADDRNOTAVAIL; + } + } + if (data[IFLA_MACVLAN_MACADDR_COUNT]) return -EINVAL; @@ -1372,10 +1389,6 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { - if (nla_type(nla) != IFLA_MACVLAN_MACADDR || - nla_len(nla) != ETH_ALEN) - continue; - addr = nla_data(nla); ret = macvlan_hash_add_source(vlan, addr); if (ret) diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig new file mode 100644 index 000000000000..1299880dfe74 --- /dev/null +++ b/drivers/net/mdio/Kconfig @@ -0,0 +1,241 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# MDIO Layer Configuration +# + +menuconfig MDIO_DEVICE + tristate "MDIO bus device drivers" + help + MDIO devices and driver infrastructure code. + +if MDIO_DEVICE + +config MDIO_BUS + tristate + default m if PHYLIB=m + default MDIO_DEVICE + help + This internal symbol is used for link time dependencies and it + reflects whether the mdio_bus/mdio_device code is built as a + loadable module or built-in. + +if MDIO_BUS + +config MDIO_DEVRES + tristate + +config MDIO_SUN4I + tristate "Allwinner sun4i MDIO interface support" + depends on ARCH_SUNXI || COMPILE_TEST + help + This driver supports the MDIO interface found in the network + interface units of the Allwinner SoC that have an EMAC (A10, + A12, A10s, etc.) + +config MDIO_XGENE + tristate "APM X-Gene SoC MDIO bus controller" + depends on ARCH_XGENE || COMPILE_TEST + help + This module provides a driver for the MDIO busses found in the + APM X-Gene SoC's. + +config MDIO_ASPEED + tristate "ASPEED MDIO bus controller" + depends on ARCH_ASPEED || COMPILE_TEST + depends on OF_MDIO && HAS_IOMEM + help + This module provides a driver for the independent MDIO bus + controllers found in the ASPEED AST2600 SoC. This is a driver for the + third revision of the ASPEED MDIO register interface - the first two + revisions are the "old" and "new" interfaces found in the AST2400 and + AST2500, embedded in the MAC. For legacy reasons, FTGMAC100 driver + continues to drive the embedded MDIO controller for the AST2400 and + AST2500 SoCs, so say N if AST2600 support is not required. + +config MDIO_BITBANG + tristate "Bitbanged MDIO buses" + help + This module implements the MDIO bus protocol in software, + for use by low level drivers that export the ability to + drive the relevant pins. + + If in doubt, say N. + +config MDIO_BCM_IPROC + tristate "Broadcom iProc MDIO bus controller" + depends on ARCH_BCM_IPROC || COMPILE_TEST + depends on HAS_IOMEM && OF_MDIO + default ARCH_BCM_IPROC + help + This module provides a driver for the MDIO busses found in the + Broadcom iProc SoC's. + +config MDIO_BCM_UNIMAC + tristate "Broadcom UniMAC MDIO bus controller" + depends on HAS_IOMEM + help + This module provides a driver for the Broadcom UniMAC MDIO busses. + This hardware can be found in the Broadcom GENET Ethernet MAC + controllers as well as some Broadcom Ethernet switches such as the + Starfighter 2 switches. + +config MDIO_CAVIUM + tristate + +config MDIO_GPIO + tristate "GPIO lib-based bitbanged MDIO buses" + depends on MDIO_BITBANG + depends on GPIOLIB || COMPILE_TEST + help + Supports GPIO lib-based MDIO busses. + + To compile this driver as a module, choose M here: the module + will be called mdio-gpio. + +config MDIO_HISI_FEMAC + tristate "Hisilicon FEMAC MDIO bus controller" + depends on HAS_IOMEM && OF_MDIO + help + This module provides a driver for the MDIO busses found in the + Hisilicon SoC that have an Fast Ethernet MAC. + +config MDIO_I2C + tristate + depends on I2C + help + Support I2C based PHYs. This provides a MDIO bus bridged + to I2C to allow PHYs connected in I2C mode to be accessed + using the existing infrastructure. + + This is library mode. + +config MDIO_MVUSB + tristate "Marvell USB to MDIO Adapter" + depends on USB + select MDIO_DEVRES + help + A USB to MDIO converter present on development boards for + Marvell's Link Street family of Ethernet switches. + +config MDIO_MSCC_MIIM + tristate "Microsemi MIIM interface support" + depends on HAS_IOMEM + select MDIO_DEVRES + help + This driver supports the MIIM (MDIO) interface found in the network + switches of the Microsemi SoCs; it is recommended to switch on + CONFIG_HIGH_RES_TIMERS + +config MDIO_MOXART + tristate "MOXA ART MDIO interface support" + depends on ARCH_MOXART || COMPILE_TEST + help + This driver supports the MDIO interface found in the network + interface units of the MOXA ART SoC + +config MDIO_OCTEON + tristate "Octeon and some ThunderX SOCs MDIO buses" + depends on (64BIT && OF_MDIO) || COMPILE_TEST + depends on HAS_IOMEM + select MDIO_CAVIUM + help + This module provides a driver for the Octeon and ThunderX MDIO + buses. It is required by the Octeon and ThunderX ethernet device + drivers on some systems. + +config MDIO_IPQ4019 + tristate "Qualcomm IPQ4019 MDIO interface support" + depends on HAS_IOMEM && OF_MDIO + help + This driver supports the MDIO interface found in Qualcomm + IPQ40xx series Soc-s. + +config MDIO_IPQ8064 + tristate "Qualcomm IPQ8064 MDIO interface support" + depends on HAS_IOMEM && OF_MDIO + depends on MFD_SYSCON + help + This driver supports the MDIO interface found in the network + interface units of the IPQ8064 SoC + +config MDIO_THUNDER + tristate "ThunderX SOCs MDIO buses" + depends on 64BIT + depends on PCI + select MDIO_CAVIUM + help + This driver supports the MDIO interfaces found on Cavium + ThunderX SoCs when the MDIO bus device appears as a PCI + device. + +comment "MDIO Multiplexers" + +config MDIO_BUS_MUX + tristate + depends on OF_MDIO + help + This module provides a driver framework for MDIO bus + multiplexers which connect one of several child MDIO busses + to a parent bus. Switching between child busses is done by + device specific drivers. + +config MDIO_BUS_MUX_MESON_G12A + tristate "Amlogic G12a based MDIO bus multiplexer" + depends on ARCH_MESON || COMPILE_TEST + depends on OF_MDIO && HAS_IOMEM && COMMON_CLK + select MDIO_BUS_MUX + default m if ARCH_MESON + help + This module provides a driver for the MDIO multiplexer/glue of + the amlogic g12a SoC. The multiplexers connects either the external + or the internal MDIO bus to the parent bus. + +config MDIO_BUS_MUX_BCM_IPROC + tristate "Broadcom iProc based MDIO bus multiplexers" + depends on OF && OF_MDIO && (ARCH_BCM_IPROC || COMPILE_TEST) + select MDIO_BUS_MUX + default ARCH_BCM_IPROC + help + This module provides a driver for MDIO bus multiplexers found in + iProc based Broadcom SoCs. This multiplexer connects one of several + child MDIO bus to a parent bus. Buses could be internal as well as + external and selection logic lies inside the same multiplexer. + +config MDIO_BUS_MUX_GPIO + tristate "GPIO controlled MDIO bus multiplexers" + depends on OF_GPIO && OF_MDIO + select MDIO_BUS_MUX + help + This module provides a driver for MDIO bus multiplexers that + are controlled via GPIO lines. The multiplexer connects one of + several child MDIO busses to a parent bus. Child bus + selection is under the control of GPIO lines. + +config MDIO_BUS_MUX_MULTIPLEXER + tristate "MDIO bus multiplexer using kernel multiplexer subsystem" + depends on OF_MDIO + select MULTIPLEXER + select MDIO_BUS_MUX + help + This module provides a driver for MDIO bus multiplexer + that is controlled via the kernel multiplexer subsystem. The + bus multiplexer connects one of several child MDIO busses to + a parent bus. Child bus selection is under the control of + the kernel multiplexer subsystem. + +config MDIO_BUS_MUX_MMIOREG + tristate "MMIO device-controlled MDIO bus multiplexers" + depends on OF_MDIO && HAS_IOMEM + select MDIO_BUS_MUX + help + This module provides a driver for MDIO bus multiplexers that + are controlled via a simple memory-mapped device, like an FPGA. + The multiplexer connects one of several child MDIO busses to a + parent bus. Child bus selection is under the control of one of + the FPGA's registers. + + Currently, only 8/16/32 bits registers are supported. + + +endif +endif diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile new file mode 100644 index 000000000000..14d1beb633c9 --- /dev/null +++ b/drivers/net/mdio/Makefile @@ -0,0 +1,27 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for Linux MDIO bus drivers + +obj-$(CONFIG_MDIO_ASPEED) += mdio-aspeed.o +obj-$(CONFIG_MDIO_BCM_IPROC) += mdio-bcm-iproc.o +obj-$(CONFIG_MDIO_BCM_UNIMAC) += mdio-bcm-unimac.o +obj-$(CONFIG_MDIO_BITBANG) += mdio-bitbang.o +obj-$(CONFIG_MDIO_CAVIUM) += mdio-cavium.o +obj-$(CONFIG_MDIO_GPIO) += mdio-gpio.o +obj-$(CONFIG_MDIO_HISI_FEMAC) += mdio-hisi-femac.o +obj-$(CONFIG_MDIO_I2C) += mdio-i2c.o +obj-$(CONFIG_MDIO_IPQ4019) += mdio-ipq4019.o +obj-$(CONFIG_MDIO_IPQ8064) += mdio-ipq8064.o +obj-$(CONFIG_MDIO_MOXART) += mdio-moxart.o +obj-$(CONFIG_MDIO_MSCC_MIIM) += mdio-mscc-miim.o +obj-$(CONFIG_MDIO_MVUSB) += mdio-mvusb.o +obj-$(CONFIG_MDIO_OCTEON) += mdio-octeon.o +obj-$(CONFIG_MDIO_SUN4I) += mdio-sun4i.o +obj-$(CONFIG_MDIO_THUNDER) += mdio-thunder.o +obj-$(CONFIG_MDIO_XGENE) += mdio-xgene.o + +obj-$(CONFIG_MDIO_BUS_MUX) += mdio-mux.o +obj-$(CONFIG_MDIO_BUS_MUX_BCM_IPROC) += mdio-mux-bcm-iproc.o +obj-$(CONFIG_MDIO_BUS_MUX_GPIO) += mdio-mux-gpio.o +obj-$(CONFIG_MDIO_BUS_MUX_MESON_G12A) += mdio-mux-meson-g12a.o +obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o +obj-$(CONFIG_MDIO_BUS_MUX_MULTIPLEXER) += mdio-mux-multiplexer.o diff --git a/drivers/net/phy/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c index cad820568f75..cad820568f75 100644 --- a/drivers/net/phy/mdio-aspeed.c +++ b/drivers/net/mdio/mdio-aspeed.c diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/mdio/mdio-bcm-iproc.c index 77fc970cdfde..77fc970cdfde 100644 --- a/drivers/net/phy/mdio-bcm-iproc.c +++ b/drivers/net/mdio/mdio-bcm-iproc.c diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c index fbd36891ee64..fbd36891ee64 100644 --- a/drivers/net/phy/mdio-bcm-unimac.c +++ b/drivers/net/mdio/mdio-bcm-unimac.c diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/mdio/mdio-bitbang.c index 5136275c8e73..5136275c8e73 100644 --- a/drivers/net/phy/mdio-bitbang.c +++ b/drivers/net/mdio/mdio-bitbang.c diff --git a/drivers/net/phy/mdio-cavium.c b/drivers/net/mdio/mdio-cavium.c index 1afd6fc1a351..1afd6fc1a351 100644 --- a/drivers/net/phy/mdio-cavium.c +++ b/drivers/net/mdio/mdio-cavium.c diff --git a/drivers/net/phy/mdio-cavium.h b/drivers/net/mdio/mdio-cavium.h index a2245d436f5d..a2245d436f5d 100644 --- a/drivers/net/phy/mdio-cavium.h +++ b/drivers/net/mdio/mdio-cavium.h diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/mdio/mdio-gpio.c index 1b00235d7dc5..1b00235d7dc5 100644 --- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/mdio/mdio-gpio.c diff --git a/drivers/net/phy/mdio-hisi-femac.c b/drivers/net/mdio/mdio-hisi-femac.c index f231c2fbb1de..f231c2fbb1de 100644 --- a/drivers/net/phy/mdio-hisi-femac.c +++ b/drivers/net/mdio/mdio-hisi-femac.c diff --git a/drivers/net/phy/mdio-i2c.c b/drivers/net/mdio/mdio-i2c.c index 0746e2cc39ae..09200a70b315 100644 --- a/drivers/net/phy/mdio-i2c.c +++ b/drivers/net/mdio/mdio-i2c.c @@ -10,10 +10,9 @@ * of their settings. */ #include <linux/i2c.h> +#include <linux/mdio/mdio-i2c.h> #include <linux/phy.h> -#include "mdio-i2c.h" - /* * I2C bus addresses 0x50 and 0x51 are normally an EEPROM, which is * specified to be present in SFP modules. These correspond with PHY diff --git a/drivers/net/phy/mdio-ipq4019.c b/drivers/net/mdio/mdio-ipq4019.c index 1ce81ff2f41d..1ce81ff2f41d 100644 --- a/drivers/net/phy/mdio-ipq4019.c +++ b/drivers/net/mdio/mdio-ipq4019.c diff --git a/drivers/net/phy/mdio-ipq8064.c b/drivers/net/mdio/mdio-ipq8064.c index 1bd18857e1c5..1bd18857e1c5 100644 --- a/drivers/net/phy/mdio-ipq8064.c +++ b/drivers/net/mdio/mdio-ipq8064.c diff --git a/drivers/net/phy/mdio-moxart.c b/drivers/net/mdio/mdio-moxart.c index b72c6d185175..b72c6d185175 100644 --- a/drivers/net/phy/mdio-moxart.c +++ b/drivers/net/mdio/mdio-moxart.c diff --git a/drivers/net/phy/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index 11f583fd4611..11f583fd4611 100644 --- a/drivers/net/phy/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/mdio/mdio-mux-bcm-iproc.c index 42fb5f166136..42fb5f166136 100644 --- a/drivers/net/phy/mdio-mux-bcm-iproc.c +++ b/drivers/net/mdio/mdio-mux-bcm-iproc.c diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/mdio/mdio-mux-gpio.c index 10a758fdc9e6..10a758fdc9e6 100644 --- a/drivers/net/phy/mdio-mux-gpio.c +++ b/drivers/net/mdio/mdio-mux-gpio.c diff --git a/drivers/net/phy/mdio-mux-meson-g12a.c b/drivers/net/mdio/mdio-mux-meson-g12a.c index bf86c9c7a288..bf86c9c7a288 100644 --- a/drivers/net/phy/mdio-mux-meson-g12a.c +++ b/drivers/net/mdio/mdio-mux-meson-g12a.c diff --git a/drivers/net/phy/mdio-mux-mmioreg.c b/drivers/net/mdio/mdio-mux-mmioreg.c index d1a8780e24d8..d1a8780e24d8 100644 --- a/drivers/net/phy/mdio-mux-mmioreg.c +++ b/drivers/net/mdio/mdio-mux-mmioreg.c diff --git a/drivers/net/phy/mdio-mux-multiplexer.c b/drivers/net/mdio/mdio-mux-multiplexer.c index d6564381aa3e..d6564381aa3e 100644 --- a/drivers/net/phy/mdio-mux-multiplexer.c +++ b/drivers/net/mdio/mdio-mux-multiplexer.c diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/mdio/mdio-mux.c index 6a1d3540210b..6a1d3540210b 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/mdio/mdio-mux.c diff --git a/drivers/net/phy/mdio-mvusb.c b/drivers/net/mdio/mdio-mvusb.c index d5eabddfdf51..d5eabddfdf51 100644 --- a/drivers/net/phy/mdio-mvusb.c +++ b/drivers/net/mdio/mdio-mvusb.c diff --git a/drivers/net/phy/mdio-octeon.c b/drivers/net/mdio/mdio-octeon.c index d1e1009d51af..d1e1009d51af 100644 --- a/drivers/net/phy/mdio-octeon.c +++ b/drivers/net/mdio/mdio-octeon.c diff --git a/drivers/net/phy/mdio-sun4i.c b/drivers/net/mdio/mdio-sun4i.c index f798de3276dc..f798de3276dc 100644 --- a/drivers/net/phy/mdio-sun4i.c +++ b/drivers/net/mdio/mdio-sun4i.c diff --git a/drivers/net/phy/mdio-thunder.c b/drivers/net/mdio/mdio-thunder.c index 3d7eda99d34e..3d7eda99d34e 100644 --- a/drivers/net/phy/mdio-thunder.c +++ b/drivers/net/mdio/mdio-thunder.c diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/mdio/mdio-xgene.c index 34990eaa3298..461207cdf5d6 100644 --- a/drivers/net/phy/mdio-xgene.c +++ b/drivers/net/mdio/mdio-xgene.c @@ -11,6 +11,7 @@ #include <linux/efi.h> #include <linux/if_vlan.h> #include <linux/io.h> +#include <linux/mdio/mdio-xgene.h> #include <linux/module.h> #include <linux/of_platform.h> #include <linux/of_net.h> @@ -18,7 +19,6 @@ #include <linux/prefetch.h> #include <linux/phy.h> #include <net/ip.h> -#include "mdio-xgene.h" static bool xgene_mdio_status; diff --git a/drivers/net/mii.c b/drivers/net/mii.c index 44612122338b..f6a97c859f3a 100644 --- a/drivers/net/mii.c +++ b/drivers/net/mii.c @@ -597,7 +597,7 @@ int generic_mii_ioctl(struct mii_if_info *mii_if, switch(cmd) { case SIOCGMIIPHY: mii_data->phy_id = mii_if->phy_id; - /* fall through */ + fallthrough; case SIOCGMIIREG: mii_data->val_out = diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index 7971dc4f54f1..0e9511661601 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -193,7 +193,7 @@ new_device_store(struct bus_type *bus, const char *buf, size_t count) switch (err) { case 1: port_count = 1; - /* fall through */ + fallthrough; case 2: if (id > INT_MAX) { pr_err("Value of \"id\" is too big.\n"); diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f32d56ac3e80..deea17a0e79c 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -760,14 +760,14 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event, spin_lock_bh(&data->fib_lock); switch (event) { - case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_ADD: case FIB_EVENT_RULE_DEL: err = nsim_fib_rule_event(data, info, event == FIB_EVENT_RULE_ADD); break; - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ - case FIB_EVENT_ENTRY_APPEND: /* fall through */ + case FIB_EVENT_ENTRY_REPLACE: + case FIB_EVENT_ENTRY_APPEND: case FIB_EVENT_ENTRY_DEL: err = nsim_fib_event(data, info, event); break; diff --git a/drivers/net/pcs/Kconfig b/drivers/net/pcs/Kconfig new file mode 100644 index 000000000000..074fb3f5db18 --- /dev/null +++ b/drivers/net/pcs/Kconfig @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# PCS Layer Configuration +# + +menu "PCS device drivers" + +config PCS_XPCS + tristate "Synopsys DesignWare XPCS controller" + select MDIO_BUS + depends on MDIO_DEVICE + help + This module provides helper functions for Synopsys DesignWare XPCS + controllers. + +config PCS_LYNX + tristate + help + This module provides helpers to phylink for managing the Lynx PCS + which is part of the Layerscape and QorIQ Ethernet SERDES. + +endmenu diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile new file mode 100644 index 000000000000..c23146755972 --- /dev/null +++ b/drivers/net/pcs/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for Linux PCS drivers + +obj-$(CONFIG_PCS_XPCS) += pcs-xpcs.o +obj-$(CONFIG_PCS_LYNX) += pcs-lynx.o diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c new file mode 100644 index 000000000000..c43d97682083 --- /dev/null +++ b/drivers/net/pcs/pcs-lynx.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* Copyright 2020 NXP + * Lynx PCS MDIO helpers + */ + +#include <linux/mdio.h> +#include <linux/phylink.h> +#include <linux/pcs-lynx.h> + +#define SGMII_CLOCK_PERIOD_NS 8 /* PCS is clocked at 125 MHz */ +#define LINK_TIMER_VAL(ns) ((u32)((ns) / SGMII_CLOCK_PERIOD_NS)) + +#define SGMII_AN_LINK_TIMER_NS 1600000 /* defined by SGMII spec */ + +#define LINK_TIMER_LO 0x12 +#define LINK_TIMER_HI 0x13 +#define IF_MODE 0x14 +#define IF_MODE_SGMII_EN BIT(0) +#define IF_MODE_USE_SGMII_AN BIT(1) +#define IF_MODE_SPEED(x) (((x) << 2) & GENMASK(3, 2)) +#define IF_MODE_SPEED_MSK GENMASK(3, 2) +#define IF_MODE_HALF_DUPLEX BIT(4) + +enum sgmii_speed { + SGMII_SPEED_10 = 0, + SGMII_SPEED_100 = 1, + SGMII_SPEED_1000 = 2, + SGMII_SPEED_2500 = 2, +}; + +#define phylink_pcs_to_lynx(pl_pcs) container_of((pl_pcs), struct lynx_pcs, pcs) + +static void lynx_pcs_get_state_usxgmii(struct mdio_device *pcs, + struct phylink_link_state *state) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + int status, lpa; + + status = mdiobus_c45_read(bus, addr, MDIO_MMD_VEND2, MII_BMSR); + if (status < 0) + return; + + state->link = !!(status & MDIO_STAT1_LSTATUS); + state->an_complete = !!(status & MDIO_AN_STAT1_COMPLETE); + if (!state->link || !state->an_complete) + return; + + lpa = mdiobus_c45_read(bus, addr, MDIO_MMD_VEND2, MII_LPA); + if (lpa < 0) + return; + + phylink_decode_usxgmii_word(state, lpa); +} + +static void lynx_pcs_get_state_2500basex(struct mdio_device *pcs, + struct phylink_link_state *state) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + int bmsr, lpa; + + bmsr = mdiobus_read(bus, addr, MII_BMSR); + lpa = mdiobus_read(bus, addr, MII_LPA); + if (bmsr < 0 || lpa < 0) { + state->link = false; + return; + } + + state->link = !!(bmsr & BMSR_LSTATUS); + state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE); + if (!state->link) + return; + + state->speed = SPEED_2500; + state->pause |= MLO_PAUSE_TX | MLO_PAUSE_RX; + state->duplex = DUPLEX_FULL; +} + +static void lynx_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); + + switch (state->interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + phylink_mii_c22_pcs_get_state(lynx->mdio, state); + break; + case PHY_INTERFACE_MODE_2500BASEX: + lynx_pcs_get_state_2500basex(lynx->mdio, state); + break; + case PHY_INTERFACE_MODE_USXGMII: + lynx_pcs_get_state_usxgmii(lynx->mdio, state); + break; + default: + break; + } + + dev_dbg(&lynx->mdio->dev, + "mode=%s/%s/%s link=%u an_enabled=%u an_complete=%u\n", + phy_modes(state->interface), + phy_speed_to_str(state->speed), + phy_duplex_to_str(state->duplex), + state->link, state->an_enabled, state->an_complete); +} + +static int lynx_pcs_config_sgmii(struct mdio_device *pcs, unsigned int mode, + const unsigned long *advertising) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + u16 if_mode; + int err; + + if_mode = IF_MODE_SGMII_EN; + if (mode == MLO_AN_INBAND) { + u32 link_timer; + + if_mode |= IF_MODE_USE_SGMII_AN; + + /* Adjust link timer for SGMII */ + link_timer = LINK_TIMER_VAL(SGMII_AN_LINK_TIMER_NS); + mdiobus_write(bus, addr, LINK_TIMER_LO, link_timer & 0xffff); + mdiobus_write(bus, addr, LINK_TIMER_HI, link_timer >> 16); + } + err = mdiobus_modify(bus, addr, IF_MODE, + IF_MODE_SGMII_EN | IF_MODE_USE_SGMII_AN, + if_mode); + if (err) + return err; + + return phylink_mii_c22_pcs_config(pcs, mode, PHY_INTERFACE_MODE_SGMII, + advertising); +} + +static int lynx_pcs_config_usxgmii(struct mdio_device *pcs, unsigned int mode, + const unsigned long *advertising) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + + if (!phylink_autoneg_inband(mode)) { + dev_err(&pcs->dev, "USXGMII only supports in-band AN for now\n"); + return -EOPNOTSUPP; + } + + /* Configure device ability for the USXGMII Replicator */ + return mdiobus_c45_write(bus, addr, MDIO_MMD_VEND2, MII_ADVERTISE, + MDIO_USXGMII_10G | MDIO_USXGMII_LINK | + MDIO_USXGMII_FULL_DUPLEX | + ADVERTISE_SGMII | ADVERTISE_LPACK); +} + +static int lynx_pcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t ifmode, + const unsigned long *advertising, + bool permit) +{ + struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); + + switch (ifmode) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + return lynx_pcs_config_sgmii(lynx->mdio, mode, advertising); + case PHY_INTERFACE_MODE_2500BASEX: + if (phylink_autoneg_inband(mode)) { + dev_err(&lynx->mdio->dev, + "AN not supported on 3.125GHz SerDes lane\n"); + return -EOPNOTSUPP; + } + break; + case PHY_INTERFACE_MODE_USXGMII: + return lynx_pcs_config_usxgmii(lynx->mdio, mode, advertising); + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static void lynx_pcs_link_up_sgmii(struct mdio_device *pcs, unsigned int mode, + int speed, int duplex) +{ + struct mii_bus *bus = pcs->bus; + u16 if_mode = 0, sgmii_speed; + int addr = pcs->addr; + + /* The PCS needs to be configured manually only + * when not operating on in-band mode + */ + if (mode == MLO_AN_INBAND) + return; + + if (duplex == DUPLEX_HALF) + if_mode |= IF_MODE_HALF_DUPLEX; + + switch (speed) { + case SPEED_1000: + sgmii_speed = SGMII_SPEED_1000; + break; + case SPEED_100: + sgmii_speed = SGMII_SPEED_100; + break; + case SPEED_10: + sgmii_speed = SGMII_SPEED_10; + break; + case SPEED_UNKNOWN: + /* Silently don't do anything */ + return; + default: + dev_err(&pcs->dev, "Invalid PCS speed %d\n", speed); + return; + } + if_mode |= IF_MODE_SPEED(sgmii_speed); + + mdiobus_modify(bus, addr, IF_MODE, + IF_MODE_HALF_DUPLEX | IF_MODE_SPEED_MSK, + if_mode); +} + +/* 2500Base-X is SerDes protocol 7 on Felix and 6 on ENETC. It is a SerDes lane + * clocked at 3.125 GHz which encodes symbols with 8b/10b and does not have + * auto-negotiation of any link parameters. Electrically it is compatible with + * a single lane of XAUI. + * The hardware reference manual wants to call this mode SGMII, but it isn't + * really, since the fundamental features of SGMII: + * - Downgrading the link speed by duplicating symbols + * - Auto-negotiation + * are not there. + * The speed is configured at 1000 in the IF_MODE because the clock frequency + * is actually given by a PLL configured in the Reset Configuration Word (RCW). + * Since there is no difference between fixed speed SGMII w/o AN and 802.3z w/o + * AN, we call this PHY interface type 2500Base-X. In case a PHY negotiates a + * lower link speed on line side, the system-side interface remains fixed at + * 2500 Mbps and we do rate adaptation through pause frames. + */ +static void lynx_pcs_link_up_2500basex(struct mdio_device *pcs, + unsigned int mode, + int speed, int duplex) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + u16 if_mode = 0; + + if (mode == MLO_AN_INBAND) { + dev_err(&pcs->dev, "AN not supported for 2500BaseX\n"); + return; + } + + if (duplex == DUPLEX_HALF) + if_mode |= IF_MODE_HALF_DUPLEX; + if_mode |= IF_MODE_SPEED(SGMII_SPEED_2500); + + mdiobus_modify(bus, addr, IF_MODE, + IF_MODE_HALF_DUPLEX | IF_MODE_SPEED_MSK, + if_mode); +} + +static void lynx_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + int speed, int duplex) +{ + struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); + + switch (interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + lynx_pcs_link_up_sgmii(lynx->mdio, mode, speed, duplex); + break; + case PHY_INTERFACE_MODE_2500BASEX: + lynx_pcs_link_up_2500basex(lynx->mdio, mode, speed, duplex); + break; + case PHY_INTERFACE_MODE_USXGMII: + /* At the moment, only in-band AN is supported for USXGMII + * so nothing to do in link_up + */ + break; + default: + break; + } +} + +static const struct phylink_pcs_ops lynx_pcs_phylink_ops = { + .pcs_get_state = lynx_pcs_get_state, + .pcs_config = lynx_pcs_config, + .pcs_link_up = lynx_pcs_link_up, +}; + +struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio) +{ + struct lynx_pcs *lynx_pcs; + + lynx_pcs = kzalloc(sizeof(*lynx_pcs), GFP_KERNEL); + if (!lynx_pcs) + return NULL; + + lynx_pcs->mdio = mdio; + lynx_pcs->pcs.ops = &lynx_pcs_phylink_ops; + lynx_pcs->pcs.poll = true; + + return lynx_pcs; +} +EXPORT_SYMBOL(lynx_pcs_create); + +void lynx_pcs_destroy(struct lynx_pcs *pcs) +{ + kfree(pcs); +} +EXPORT_SYMBOL(lynx_pcs_destroy); + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/phy/mdio-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 0d66a8ba7eb6..1aa9903d602e 100644 --- a/drivers/net/phy/mdio-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -7,8 +7,8 @@ */ #include <linux/delay.h> +#include <linux/pcs/pcs-xpcs.h> #include <linux/mdio.h> -#include <linux/mdio-xpcs.h> #include <linux/phylink.h> #include <linux/workqueue.h> diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 726e4b240e7e..698bea312adc 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -3,246 +3,6 @@ # PHY Layer Configuration # -menuconfig MDIO_DEVICE - tristate "MDIO bus device drivers" - help - MDIO devices and driver infrastructure code. - -if MDIO_DEVICE - -config MDIO_BUS - tristate - default m if PHYLIB=m - default MDIO_DEVICE - help - This internal symbol is used for link time dependencies and it - reflects whether the mdio_bus/mdio_device code is built as a - loadable module or built-in. - -if MDIO_BUS - -config MDIO_DEVRES - tristate - -config MDIO_ASPEED - tristate "ASPEED MDIO bus controller" - depends on ARCH_ASPEED || COMPILE_TEST - depends on OF_MDIO && HAS_IOMEM - help - This module provides a driver for the independent MDIO bus - controllers found in the ASPEED AST2600 SoC. This is a driver for the - third revision of the ASPEED MDIO register interface - the first two - revisions are the "old" and "new" interfaces found in the AST2400 and - AST2500, embedded in the MAC. For legacy reasons, FTGMAC100 driver - continues to drive the embedded MDIO controller for the AST2400 and - AST2500 SoCs, so say N if AST2600 support is not required. - -config MDIO_BCM_IPROC - tristate "Broadcom iProc MDIO bus controller" - depends on ARCH_BCM_IPROC || COMPILE_TEST - depends on HAS_IOMEM && OF_MDIO - default ARCH_BCM_IPROC - help - This module provides a driver for the MDIO busses found in the - Broadcom iProc SoC's. - -config MDIO_BCM_UNIMAC - tristate "Broadcom UniMAC MDIO bus controller" - depends on HAS_IOMEM - help - This module provides a driver for the Broadcom UniMAC MDIO busses. - This hardware can be found in the Broadcom GENET Ethernet MAC - controllers as well as some Broadcom Ethernet switches such as the - Starfighter 2 switches. - -config MDIO_BITBANG - tristate "Bitbanged MDIO buses" - help - This module implements the MDIO bus protocol in software, - for use by low level drivers that export the ability to - drive the relevant pins. - - If in doubt, say N. - -config MDIO_BUS_MUX - tristate - depends on OF_MDIO - help - This module provides a driver framework for MDIO bus - multiplexers which connect one of several child MDIO busses - to a parent bus. Switching between child busses is done by - device specific drivers. - -config MDIO_BUS_MUX_BCM_IPROC - tristate "Broadcom iProc based MDIO bus multiplexers" - depends on OF && OF_MDIO && (ARCH_BCM_IPROC || COMPILE_TEST) - select MDIO_BUS_MUX - default ARCH_BCM_IPROC - help - This module provides a driver for MDIO bus multiplexers found in - iProc based Broadcom SoCs. This multiplexer connects one of several - child MDIO bus to a parent bus. Buses could be internal as well as - external and selection logic lies inside the same multiplexer. - -config MDIO_BUS_MUX_GPIO - tristate "GPIO controlled MDIO bus multiplexers" - depends on OF_GPIO && OF_MDIO - select MDIO_BUS_MUX - help - This module provides a driver for MDIO bus multiplexers that - are controlled via GPIO lines. The multiplexer connects one of - several child MDIO busses to a parent bus. Child bus - selection is under the control of GPIO lines. - -config MDIO_BUS_MUX_MESON_G12A - tristate "Amlogic G12a based MDIO bus multiplexer" - depends on ARCH_MESON || COMPILE_TEST - depends on OF_MDIO && HAS_IOMEM && COMMON_CLK - select MDIO_BUS_MUX - default m if ARCH_MESON - help - This module provides a driver for the MDIO multiplexer/glue of - the amlogic g12a SoC. The multiplexers connects either the external - or the internal MDIO bus to the parent bus. - -config MDIO_BUS_MUX_MMIOREG - tristate "MMIO device-controlled MDIO bus multiplexers" - depends on OF_MDIO && HAS_IOMEM - select MDIO_BUS_MUX - help - This module provides a driver for MDIO bus multiplexers that - are controlled via a simple memory-mapped device, like an FPGA. - The multiplexer connects one of several child MDIO busses to a - parent bus. Child bus selection is under the control of one of - the FPGA's registers. - - Currently, only 8/16/32 bits registers are supported. - -config MDIO_BUS_MUX_MULTIPLEXER - tristate "MDIO bus multiplexer using kernel multiplexer subsystem" - depends on OF_MDIO - select MULTIPLEXER - select MDIO_BUS_MUX - help - This module provides a driver for MDIO bus multiplexer - that is controlled via the kernel multiplexer subsystem. The - bus multiplexer connects one of several child MDIO busses to - a parent bus. Child bus selection is under the control of - the kernel multiplexer subsystem. - -config MDIO_CAVIUM - tristate - -config MDIO_GPIO - tristate "GPIO lib-based bitbanged MDIO buses" - depends on MDIO_BITBANG - depends on GPIOLIB || COMPILE_TEST - help - Supports GPIO lib-based MDIO busses. - - To compile this driver as a module, choose M here: the module - will be called mdio-gpio. - -config MDIO_HISI_FEMAC - tristate "Hisilicon FEMAC MDIO bus controller" - depends on HAS_IOMEM && OF_MDIO - help - This module provides a driver for the MDIO busses found in the - Hisilicon SoC that have an Fast Ethernet MAC. - -config MDIO_I2C - tristate - depends on I2C - help - Support I2C based PHYs. This provides a MDIO bus bridged - to I2C to allow PHYs connected in I2C mode to be accessed - using the existing infrastructure. - - This is library mode. - -config MDIO_IPQ4019 - tristate "Qualcomm IPQ4019 MDIO interface support" - depends on HAS_IOMEM && OF_MDIO - help - This driver supports the MDIO interface found in Qualcomm - IPQ40xx series Soc-s. - -config MDIO_IPQ8064 - tristate "Qualcomm IPQ8064 MDIO interface support" - depends on HAS_IOMEM && OF_MDIO - depends on MFD_SYSCON - help - This driver supports the MDIO interface found in the network - interface units of the IPQ8064 SoC - -config MDIO_MOXART - tristate "MOXA ART MDIO interface support" - depends on ARCH_MOXART || COMPILE_TEST - help - This driver supports the MDIO interface found in the network - interface units of the MOXA ART SoC - -config MDIO_MSCC_MIIM - tristate "Microsemi MIIM interface support" - depends on HAS_IOMEM - select MDIO_DEVRES - help - This driver supports the MIIM (MDIO) interface found in the network - switches of the Microsemi SoCs; it is recommended to switch on - CONFIG_HIGH_RES_TIMERS - -config MDIO_MVUSB - tristate "Marvell USB to MDIO Adapter" - depends on USB - select MDIO_DEVRES - help - A USB to MDIO converter present on development boards for - Marvell's Link Street family of Ethernet switches. - -config MDIO_OCTEON - tristate "Octeon and some ThunderX SOCs MDIO buses" - depends on (64BIT && OF_MDIO) || COMPILE_TEST - depends on HAS_IOMEM - select MDIO_CAVIUM - help - This module provides a driver for the Octeon and ThunderX MDIO - buses. It is required by the Octeon and ThunderX ethernet device - drivers on some systems. - -config MDIO_SUN4I - tristate "Allwinner sun4i MDIO interface support" - depends on ARCH_SUNXI || COMPILE_TEST - help - This driver supports the MDIO interface found in the network - interface units of the Allwinner SoC that have an EMAC (A10, - A12, A10s, etc.) - -config MDIO_THUNDER - tristate "ThunderX SOCs MDIO buses" - depends on 64BIT - depends on PCI - select MDIO_CAVIUM - help - This driver supports the MDIO interfaces found on Cavium - ThunderX SoCs when the MDIO bus device appears as a PCI - device. - -config MDIO_XGENE - tristate "APM X-Gene SoC MDIO bus controller" - depends on ARCH_XGENE || COMPILE_TEST - help - This module provides a driver for the MDIO busses found in the - APM X-Gene SoC's. - -config MDIO_XPCS - tristate "Synopsys DesignWare XPCS controller" - help - This module provides helper functions for Synopsys DesignWare XPCS - controllers. - -endif -endif - config PHYLINK tristate depends on NETDEVICES @@ -285,7 +45,15 @@ config LED_TRIGGER_PHY for any speed known to the PHY. -comment "MII PHY device drivers" +config FIXED_PHY + tristate "MDIO Bus/PHY emulation with fixed speed/link PHYs" + depends on PHYLIB + select SWPHY + help + Adds the platform "fixed" MDIO Bus to cover the boards that use + PHYs that are not connected to the real MDIO bus. + + Currently tested with mpc866ads and mpc8349e-mitx. config SFP tristate "SFP cage support" @@ -293,6 +61,19 @@ config SFP depends on HWMON || HWMON=n select MDIO_I2C +comment "MII PHY device drivers" + +config AMD_PHY + tristate "AMD PHYs" + help + Currently supports the am79c874 + +config MESON_GXL_PHY + tristate "Amlogic Meson GXL Internal PHY" + depends on ARCH_MESON || COMPILE_TEST + help + Currently has a driver for the Amlogic Meson GXL Internal PHY + config ADIN_PHY tristate "Analog Devices Industrial Ethernet PHYs" help @@ -302,11 +83,6 @@ config ADIN_PHY - ADIN1300 - Robust,Industrial, Low Latency 10/100/1000 Gigabit Ethernet PHY -config AMD_PHY - tristate "AMD PHYs" - help - Currently supports the am79c874 - config AQUANTIA_PHY tristate "Aquantia PHYs" help @@ -318,6 +94,24 @@ config AX88796B_PHY Currently supports the Asix Electronics PHY found in the X-Surf 100 AX88796B package. +config BROADCOM_PHY + tristate "Broadcom 54XX PHYs" + select BCM_NET_PHYLIB + help + Currently supports the BCM5411, BCM5421, BCM5461, BCM54616S, BCM5464, + BCM5481, BCM54810 and BCM5482 PHYs. + +config BCM54140_PHY + tristate "Broadcom BCM54140 PHY" + depends on PHYLIB + depends on HWMON || HWMON=n + select BCM_NET_PHYLIB + help + Support the Broadcom BCM54140 Quad SGMII/QSGMII PHY. + + This driver also supports the hardware monitoring of this PHY and + exposes voltage and temperature sensors. + config BCM63XX_PHY tristate "Broadcom 63xx SOCs internal PHY" depends on BCM63XX || COMPILE_TEST @@ -332,6 +126,12 @@ config BCM7XXX_PHY Currently supports the BCM7366, BCM7439, BCM7445, and 40nm and 65nm generation of BCM7xxx Set Top Box SoCs. +config BCM84881_PHY + tristate "Broadcom BCM84881 PHY" + depends on PHYLIB + help + Support the Broadcom BCM84881 PHY. + config BCM87XX_PHY tristate "Broadcom BCM8706 and BCM8727 PHYs" help @@ -353,30 +153,6 @@ config BCM_CYGNUS_PHY config BCM_NET_PHYLIB tristate -config BROADCOM_PHY - tristate "Broadcom PHYs" - select BCM_NET_PHYLIB - help - Currently supports the BCM5411, BCM5421, BCM5461, BCM54616S, BCM5464, - BCM5481, BCM54810 and BCM5482 PHYs. - -config BCM54140_PHY - tristate "Broadcom BCM54140 PHY" - depends on PHYLIB - depends on HWMON || HWMON=n - select BCM_NET_PHYLIB - help - Support the Broadcom BCM54140 Quad SGMII/QSGMII PHY. - - This driver also supports the hardware monitoring of this PHY and - exposes voltage and temperature sensors. - -config BCM84881_PHY - tristate "Broadcom BCM84881 PHY" - depends on PHYLIB - help - Support the Broadcom BCM84881 PHY. - config CICADA_PHY tristate "Cicada PHYs" help @@ -392,48 +168,16 @@ config DAVICOM_PHY help Currently supports dm9161e and dm9131 -config DP83822_PHY - tristate "Texas Instruments DP83822/825/826 PHYs" - help - Supports the DP83822, DP83825I, DP83825CM, DP83825CS, DP83825S, - DP83826C and DP83826NC PHYs. - -config DP83TC811_PHY - tristate "Texas Instruments DP83TC811 PHY" - help - Supports the DP83TC811 PHY. - -config DP83848_PHY - tristate "Texas Instruments DP83848 PHY" - help - Supports the DP83848 PHY. - -config DP83867_PHY - tristate "Texas Instruments DP83867 Gigabit PHY" - help - Currently supports the DP83867 PHY. - -config DP83869_PHY - tristate "Texas Instruments DP83869 Gigabit PHY" - help - Currently supports the DP83869 PHY. This PHY supports copper and - fiber connections. - -config FIXED_PHY - tristate "MDIO Bus/PHY emulation with fixed speed/link PHYs" - depends on PHYLIB - select SWPHY - help - Adds the platform "fixed" MDIO Bus to cover the boards that use - PHYs that are not connected to the real MDIO bus. - - Currently tested with mpc866ads and mpc8349e-mitx. - config ICPLUS_PHY tristate "ICPlus PHYs" help Currently supports the IP175C and IP1001 PHYs. +config LXT_PHY + tristate "Intel LXT PHYs" + help + Currently supports the lxt970, lxt971 + config INTEL_XWAY_PHY tristate "Intel XWAY PHYs" help @@ -447,27 +191,16 @@ config LSI_ET1011C_PHY help Supports the LSI ET1011C PHY. -config LXT_PHY - tristate "Intel LXT PHYs" - help - Currently supports the lxt970, lxt971 - config MARVELL_PHY - tristate "Marvell PHYs" + tristate "Marvell Alaska PHYs" help - Currently has a driver for the 88E1011S + Currently has a driver for the 88E1XXX config MARVELL_10G_PHY tristate "Marvell Alaska 10Gbit PHYs" help Support for the Marvell Alaska MV88X3310 and compatible PHYs. -config MESON_GXL_PHY - tristate "Amlogic Meson GXL Internal PHY" - depends on ARCH_MESON || COMPILE_TEST - help - Currently has a driver for the Amlogic Meson GXL Internal PHY - config MICREL_PHY tristate "Micrel PHYs" help @@ -518,12 +251,12 @@ config REALTEK_PHY Supports the Realtek 821x PHY. config RENESAS_PHY - tristate "Driver for Renesas PHYs" + tristate "Renesas PHYs" help Supports the Renesas PHYs uPD60620 and uPD60620A. config ROCKCHIP_PHY - tristate "Driver for Rockchip Ethernet PHYs" + tristate "Rockchip Ethernet PHYs" help Currently supports the integrated Ethernet PHY. @@ -542,6 +275,33 @@ config TERANETICS_PHY help Currently supports the Teranetics TN2020 +config DP83822_PHY + tristate "Texas Instruments DP83822/825/826 PHYs" + help + Supports the DP83822, DP83825I, DP83825CM, DP83825CS, DP83825S, + DP83826C and DP83826NC PHYs. + +config DP83TC811_PHY + tristate "Texas Instruments DP83TC811 PHY" + help + Supports the DP83TC811 PHY. + +config DP83848_PHY + tristate "Texas Instruments DP83848 PHY" + help + Supports the DP83848 PHY. + +config DP83867_PHY + tristate "Texas Instruments DP83867 Gigabit PHY" + help + Currently supports the DP83867 PHY. + +config DP83869_PHY + tristate "Texas Instruments DP83869 Gigabit PHY" + help + Currently supports the DP83869 PHY. This PHY supports copper and + fiber connections. + config VITESSE_PHY tristate "Vitesse PHYs" help diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index d84bab489a53..a13e402074cf 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Makefile for Linux PHY drivers and MDIO bus drivers +# Makefile for Linux PHY drivers libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ linkmode.o @@ -24,31 +24,6 @@ libphy-$(CONFIG_LED_TRIGGER_PHY) += phy_led_triggers.o obj-$(CONFIG_PHYLINK) += phylink.o obj-$(CONFIG_PHYLIB) += libphy.o -obj-$(CONFIG_MDIO_ASPEED) += mdio-aspeed.o -obj-$(CONFIG_MDIO_BCM_IPROC) += mdio-bcm-iproc.o -obj-$(CONFIG_MDIO_BCM_UNIMAC) += mdio-bcm-unimac.o -obj-$(CONFIG_MDIO_BITBANG) += mdio-bitbang.o -obj-$(CONFIG_MDIO_BUS_MUX) += mdio-mux.o -obj-$(CONFIG_MDIO_BUS_MUX_BCM_IPROC) += mdio-mux-bcm-iproc.o -obj-$(CONFIG_MDIO_BUS_MUX_GPIO) += mdio-mux-gpio.o -obj-$(CONFIG_MDIO_BUS_MUX_MESON_G12A) += mdio-mux-meson-g12a.o -obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o -obj-$(CONFIG_MDIO_BUS_MUX_MULTIPLEXER) += mdio-mux-multiplexer.o -obj-$(CONFIG_MDIO_CAVIUM) += mdio-cavium.o -obj-$(CONFIG_MDIO_GPIO) += mdio-gpio.o -obj-$(CONFIG_MDIO_HISI_FEMAC) += mdio-hisi-femac.o -obj-$(CONFIG_MDIO_I2C) += mdio-i2c.o -obj-$(CONFIG_MDIO_IPQ4019) += mdio-ipq4019.o -obj-$(CONFIG_MDIO_IPQ8064) += mdio-ipq8064.o -obj-$(CONFIG_MDIO_MOXART) += mdio-moxart.o -obj-$(CONFIG_MDIO_MSCC_MIIM) += mdio-mscc-miim.o -obj-$(CONFIG_MDIO_MVUSB) += mdio-mvusb.o -obj-$(CONFIG_MDIO_OCTEON) += mdio-octeon.o -obj-$(CONFIG_MDIO_SUN4I) += mdio-sun4i.o -obj-$(CONFIG_MDIO_THUNDER) += mdio-thunder.o -obj-$(CONFIG_MDIO_XGENE) += mdio-xgene.o -obj-$(CONFIG_MDIO_XPCS) += mdio-xpcs.o - obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += mii_timestamper.o obj-$(CONFIG_SFP) += sfp.o @@ -62,32 +37,32 @@ ifdef CONFIG_HWMON aquantia-objs += aquantia_hwmon.o endif obj-$(CONFIG_AQUANTIA_PHY) += aquantia.o -obj-$(CONFIG_AX88796B_PHY) += ax88796b.o obj-$(CONFIG_AT803X_PHY) += at803x.o +obj-$(CONFIG_AX88796B_PHY) += ax88796b.o +obj-$(CONFIG_BCM54140_PHY) += bcm54140.o obj-$(CONFIG_BCM63XX_PHY) += bcm63xx.o obj-$(CONFIG_BCM7XXX_PHY) += bcm7xxx.o +obj-$(CONFIG_BCM84881_PHY) += bcm84881.o obj-$(CONFIG_BCM87XX_PHY) += bcm87xx.o obj-$(CONFIG_BCM_CYGNUS_PHY) += bcm-cygnus.o obj-$(CONFIG_BCM_NET_PHYLIB) += bcm-phy-lib.o obj-$(CONFIG_BROADCOM_PHY) += broadcom.o -obj-$(CONFIG_BCM54140_PHY) += bcm54140.o -obj-$(CONFIG_BCM84881_PHY) += bcm84881.o obj-$(CONFIG_CICADA_PHY) += cicada.o obj-$(CONFIG_CORTINA_PHY) += cortina.o obj-$(CONFIG_DAVICOM_PHY) += davicom.o obj-$(CONFIG_DP83640_PHY) += dp83640.o obj-$(CONFIG_DP83822_PHY) += dp83822.o -obj-$(CONFIG_DP83TC811_PHY) += dp83tc811.o obj-$(CONFIG_DP83848_PHY) += dp83848.o obj-$(CONFIG_DP83867_PHY) += dp83867.o obj-$(CONFIG_DP83869_PHY) += dp83869.o +obj-$(CONFIG_DP83TC811_PHY) += dp83tc811.o obj-$(CONFIG_FIXED_PHY) += fixed_phy.o obj-$(CONFIG_ICPLUS_PHY) += icplus.o obj-$(CONFIG_INTEL_XWAY_PHY) += intel-xway.o obj-$(CONFIG_LSI_ET1011C_PHY) += et1011c.o obj-$(CONFIG_LXT_PHY) += lxt.o -obj-$(CONFIG_MARVELL_PHY) += marvell.o obj-$(CONFIG_MARVELL_10G_PHY) += marvell10g.o +obj-$(CONFIG_MARVELL_PHY) += marvell.o obj-$(CONFIG_MESON_GXL_PHY) += meson-gxl.o obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o obj-$(CONFIG_MICREL_PHY) += micrel.o diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c index 7471a8b90873..307f0ac1287b 100644 --- a/drivers/net/phy/adin.c +++ b/drivers/net/phy/adin.c @@ -366,10 +366,10 @@ static int adin_set_edpd(struct phy_device *phydev, u16 tx_interval) switch (tx_interval) { case 1000: /* 1 second */ - /* fallthrough */ + fallthrough; case ETHTOOL_PHY_EDPD_DFLT_TX_MSECS: val |= ADIN1300_NRG_PD_TX_EN; - /* fallthrough */ + fallthrough; case ETHTOOL_PHY_EDPD_NO_TX: break; default: diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 101651b2de54..ed601a7e46a0 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -343,7 +343,7 @@ static int at803x_rgmii_reg_get_voltage_sel(struct regulator_dev *rdev) return (val & AT803X_DEBUG_RGMII_1V8) ? 1 : 0; } -static struct regulator_ops vddio_regulator_ops = { +static const struct regulator_ops vddio_regulator_ops = { .list_voltage = regulator_list_voltage_table, .set_voltage_sel = at803x_rgmii_reg_set_voltage_sel, .get_voltage_sel = at803x_rgmii_reg_get_voltage_sel, @@ -364,7 +364,7 @@ static const struct regulator_desc vddio_desc = { .owner = THIS_MODULE, }; -static struct regulator_ops vddh_regulator_ops = { +static const struct regulator_ops vddh_regulator_ops = { }; static const struct regulator_desc vddh_desc = { diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 50fb7d16b75a..f2caccaf4408 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -766,13 +766,13 @@ static int decode_evnt(struct dp83640_private *dp83640, switch (words) { case 3: dp83640->edata.sec_hi = phy_txts->sec_hi; - /* fall through */ + fallthrough; case 2: dp83640->edata.sec_lo = phy_txts->sec_lo; - /* fall through */ + fallthrough; case 1: dp83640->edata.ns_hi = phy_txts->ns_hi; - /* fall through */ + fallthrough; case 0: dp83640->edata.ns_lo = phy_txts->ns_lo; } @@ -798,51 +798,32 @@ static int decode_evnt(struct dp83640_private *dp83640, return parsed; } -#define DP83640_PACKET_HASH_OFFSET 20 #define DP83640_PACKET_HASH_LEN 10 static int match(struct sk_buff *skb, unsigned int type, struct rxts *rxts) { - unsigned int offset = 0; - u8 *msgtype, *data = skb_mac_header(skb); - __be16 *seqid; + struct ptp_header *hdr; + u8 msgtype; + u16 seqid; u16 hash; /* check sequenceID, messageType, 12 bit hash of offset 20-29 */ - if (type & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (type & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: + hdr = ptp_parse_header(skb, type); + if (!hdr) return 0; - } - if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid)) - return 0; + msgtype = ptp_get_msgtype(hdr, type); - if (unlikely(type & PTP_CLASS_V1)) - msgtype = data + offset + OFF_PTP_CONTROL; - else - msgtype = data + offset; - if (rxts->msgtype != (*msgtype & 0xf)) + if (rxts->msgtype != (msgtype & 0xf)) return 0; - seqid = (__be16 *)(data + offset + OFF_PTP_SEQUENCE_ID); - if (rxts->seqid != ntohs(*seqid)) + seqid = be16_to_cpu(hdr->sequence_id); + if (rxts->seqid != seqid) return 0; hash = ether_crc(DP83640_PACKET_HASH_LEN, - data + offset + DP83640_PACKET_HASH_OFFSET) >> 20; + (unsigned char *)&hdr->source_port_identity) >> 20; if (rxts->hash != hash) return 0; @@ -982,35 +963,16 @@ static void decode_status_frame(struct dp83640_private *dp83640, static int is_sync(struct sk_buff *skb, int type) { - u8 *data = skb->data, *msgtype; - unsigned int offset = 0; - - if (type & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (type & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return 0; - } - - if (type & PTP_CLASS_V1) - offset += OFF_PTP_CONTROL; + struct ptp_header *hdr; + u8 msgtype; - if (skb->len < offset + 1) + hdr = ptp_parse_header(skb, type); + if (!hdr) return 0; - msgtype = data + offset; + msgtype = ptp_get_msgtype(hdr, type); - return (*msgtype & 0xf) == 0; + return (msgtype & 0xf) == 0; } static void dp83640_free_clocks(void) @@ -1409,7 +1371,7 @@ static void dp83640_txtstamp(struct mii_timestamper *mii_ts, kfree_skb(skb); return; } - /* fall through */ + fallthrough; case HWTSTAMP_TX_ON: skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT; diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 37643c468e19..732c8bec7452 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -23,16 +23,31 @@ #define DP83822_DEVADDR 0x1f +#define MII_DP83822_CTRL_2 0x0a +#define MII_DP83822_PHYSTS 0x10 #define MII_DP83822_PHYSCR 0x11 #define MII_DP83822_MISR1 0x12 #define MII_DP83822_MISR2 0x13 +#define MII_DP83822_FCSCR 0x14 #define MII_DP83822_RCSR 0x17 #define MII_DP83822_RESET_CTRL 0x1f #define MII_DP83822_GENCFG 0x465 +#define MII_DP83822_SOR1 0x467 + +/* GENCFG */ +#define DP83822_SIG_DET_LOW BIT(0) + +/* Control Register 2 bits */ +#define DP83822_FX_ENABLE BIT(14) #define DP83822_HW_RESET BIT(15) #define DP83822_SW_RESET BIT(14) +/* PHY STS bits */ +#define DP83822_PHYSTS_DUPLEX BIT(2) +#define DP83822_PHYSTS_10 BIT(1) +#define DP83822_PHYSTS_LINK BIT(0) + /* PHYSCR Register Fields */ #define DP83822_PHYSCR_INT_OE BIT(0) /* Interrupt Output Enable */ #define DP83822_PHYSCR_INTEN BIT(1) /* Interrupt Enable */ @@ -83,6 +98,28 @@ #define DP83822_RX_CLK_SHIFT BIT(12) #define DP83822_TX_CLK_SHIFT BIT(11) +/* SOR1 mode */ +#define DP83822_STRAP_MODE1 0 +#define DP83822_STRAP_MODE2 BIT(0) +#define DP83822_STRAP_MODE3 BIT(1) +#define DP83822_STRAP_MODE4 GENMASK(1, 0) + +#define DP83822_COL_STRAP_MASK GENMASK(11, 10) +#define DP83822_COL_SHIFT 10 +#define DP83822_RX_ER_STR_MASK GENMASK(9, 8) +#define DP83822_RX_ER_SHIFT 8 + +#define MII_DP83822_FIBER_ADVERTISE (ADVERTISED_TP | ADVERTISED_MII | \ + ADVERTISED_FIBRE | ADVERTISED_BNC | \ + ADVERTISED_Pause | ADVERTISED_Asym_Pause | \ + ADVERTISED_100baseT_Full) + +struct dp83822_private { + bool fx_signal_det_low; + int fx_enabled; + u16 fx_sd_enable; +}; + static int dp83822_ack_interrupt(struct phy_device *phydev) { int err; @@ -197,6 +234,7 @@ static void dp83822_get_wol(struct phy_device *phydev, static int dp83822_config_intr(struct phy_device *phydev) { + struct dp83822_private *dp83822 = phydev->priv; int misr_status; int physcr_status; int err; @@ -208,13 +246,16 @@ static int dp83822_config_intr(struct phy_device *phydev) misr_status |= (DP83822_RX_ERR_HF_INT_EN | DP83822_FALSE_CARRIER_HF_INT_EN | - DP83822_ANEG_COMPLETE_INT_EN | - DP83822_DUP_MODE_CHANGE_INT_EN | - DP83822_SPEED_CHANGED_INT_EN | DP83822_LINK_STAT_INT_EN | DP83822_ENERGY_DET_INT_EN | DP83822_LINK_QUAL_INT_EN); + if (!dp83822->fx_enabled) + misr_status |= DP83822_ANEG_COMPLETE_INT_EN | + DP83822_DUP_MODE_CHANGE_INT_EN | + DP83822_SPEED_CHANGED_INT_EN; + + err = phy_write(phydev, MII_DP83822_MISR1, misr_status); if (err < 0) return err; @@ -224,14 +265,16 @@ static int dp83822_config_intr(struct phy_device *phydev) return misr_status; misr_status |= (DP83822_JABBER_DET_INT_EN | - DP83822_WOL_PKT_INT_EN | DP83822_SLEEP_MODE_INT_EN | - DP83822_MDI_XOVER_INT_EN | DP83822_LB_FIFO_INT_EN | DP83822_PAGE_RX_INT_EN | - DP83822_ANEG_ERR_INT_EN | DP83822_EEE_ERROR_CHANGE_INT_EN); + if (!dp83822->fx_enabled) + misr_status |= DP83822_MDI_XOVER_INT_EN | + DP83822_ANEG_ERR_INT_EN | + DP83822_WOL_PKT_INT_EN; + err = phy_write(phydev, MII_DP83822_MISR2, misr_status); if (err < 0) return err; @@ -270,13 +313,60 @@ static int dp8382x_disable_wol(struct phy_device *phydev) MII_DP83822_WOL_CFG, value); } +static int dp83822_read_status(struct phy_device *phydev) +{ + struct dp83822_private *dp83822 = phydev->priv; + int status = phy_read(phydev, MII_DP83822_PHYSTS); + int ctrl2; + int ret; + + if (dp83822->fx_enabled) { + if (status & DP83822_PHYSTS_LINK) { + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; + } else { + ctrl2 = phy_read(phydev, MII_DP83822_CTRL_2); + if (ctrl2 < 0) + return ctrl2; + + if (!(ctrl2 & DP83822_FX_ENABLE)) { + ret = phy_write(phydev, MII_DP83822_CTRL_2, + DP83822_FX_ENABLE | ctrl2); + if (ret < 0) + return ret; + } + } + } + + ret = genphy_read_status(phydev); + if (ret) + return ret; + + if (status < 0) + return status; + + if (status & DP83822_PHYSTS_DUPLEX) + phydev->duplex = DUPLEX_FULL; + else + phydev->duplex = DUPLEX_HALF; + + if (status & DP83822_PHYSTS_10) + phydev->speed = SPEED_10; + else + phydev->speed = SPEED_100; + + return 0; +} + static int dp83822_config_init(struct phy_device *phydev) { + struct dp83822_private *dp83822 = phydev->priv; struct device *dev = &phydev->mdio.dev; int rgmii_delay; s32 rx_int_delay; s32 tx_int_delay; int err = 0; + int bmcr; if (phy_interface_is_rgmii(phydev)) { rx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, @@ -302,6 +392,53 @@ static int dp83822_config_init(struct phy_device *phydev) } } + if (dp83822->fx_enabled) { + err = phy_modify(phydev, MII_DP83822_CTRL_2, + DP83822_FX_ENABLE, 1); + if (err < 0) + return err; + + /* Only allow advertising what this PHY supports */ + linkmode_and(phydev->advertising, phydev->advertising, + phydev->supported); + + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + phydev->supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + phydev->advertising); + + /* Auto neg is not supported in fiber mode */ + bmcr = phy_read(phydev, MII_BMCR); + if (bmcr < 0) + return bmcr; + + if (bmcr & BMCR_ANENABLE) { + err = phy_modify(phydev, MII_BMCR, BMCR_ANENABLE, 0); + if (err < 0) + return err; + } + phydev->autoneg = AUTONEG_DISABLE; + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->supported); + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->advertising); + + /* Setup fiber advertisement */ + err = phy_modify_changed(phydev, MII_ADVERTISE, + MII_DP83822_FIBER_ADVERTISE, + MII_DP83822_FIBER_ADVERTISE); + + if (err < 0) + return err; + + if (dp83822->fx_signal_det_low) { + err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_GENCFG, + DP83822_SIG_DET_LOW); + if (err) + return err; + } + } return dp8382x_disable_wol(phydev); } @@ -314,13 +451,85 @@ static int dp83822_phy_reset(struct phy_device *phydev) { int err; - err = phy_write(phydev, MII_DP83822_RESET_CTRL, DP83822_HW_RESET); + err = phy_write(phydev, MII_DP83822_RESET_CTRL, DP83822_SW_RESET); if (err < 0) return err; return phydev->drv->config_init(phydev); } +#ifdef CONFIG_OF_MDIO +static int dp83822_of_init(struct phy_device *phydev) +{ + struct dp83822_private *dp83822 = phydev->priv; + struct device *dev = &phydev->mdio.dev; + + /* Signal detection for the PHY is only enabled if the FX_EN and the + * SD_EN pins are strapped. Signal detection can only enabled if FX_EN + * is strapped otherwise signal detection is disabled for the PHY. + */ + if (dp83822->fx_enabled && dp83822->fx_sd_enable) + dp83822->fx_signal_det_low = device_property_present(dev, + "ti,link-loss-low"); + if (!dp83822->fx_enabled) + dp83822->fx_enabled = device_property_present(dev, + "ti,fiber-mode"); + + return 0; +} +#else +static int dp83822_of_init(struct phy_device *phydev) +{ + return 0; +} +#endif /* CONFIG_OF_MDIO */ + +static int dp83822_read_straps(struct phy_device *phydev) +{ + struct dp83822_private *dp83822 = phydev->priv; + int fx_enabled, fx_sd_enable; + int val; + + val = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_SOR1); + if (val < 0) + return val; + + fx_enabled = (val & DP83822_COL_STRAP_MASK) >> DP83822_COL_SHIFT; + if (fx_enabled == DP83822_STRAP_MODE2 || + fx_enabled == DP83822_STRAP_MODE3) + dp83822->fx_enabled = 1; + + if (dp83822->fx_enabled) { + fx_sd_enable = (val & DP83822_RX_ER_STR_MASK) >> DP83822_RX_ER_SHIFT; + if (fx_sd_enable == DP83822_STRAP_MODE3 || + fx_sd_enable == DP83822_STRAP_MODE4) + dp83822->fx_sd_enable = 1; + } + + return 0; +} + +static int dp83822_probe(struct phy_device *phydev) +{ + struct dp83822_private *dp83822; + int ret; + + dp83822 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83822), + GFP_KERNEL); + if (!dp83822) + return -ENOMEM; + + phydev->priv = dp83822; + + ret = dp83822_read_straps(phydev); + if (ret) + return ret; + + dp83822_of_init(phydev); + + return 0; +} + static int dp83822_suspend(struct phy_device *phydev) { int value; @@ -352,8 +561,10 @@ static int dp83822_resume(struct phy_device *phydev) PHY_ID_MATCH_MODEL(_id), \ .name = (_name), \ /* PHY_BASIC_FEATURES */ \ + .probe = dp83822_probe, \ .soft_reset = dp83822_phy_reset, \ .config_init = dp83822_config_init, \ + .read_status = dp83822_read_status, \ .get_wol = dp83822_get_wol, \ .set_wol = dp83822_set_wol, \ .ack_interrupt = dp83822_ack_interrupt, \ diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index f3c04981b8da..69d3eacc2b96 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* - * Driver for the Texas Instruments DP83867 PHY +/* Driver for the Texas Instruments DP83867 PHY * * Copyright (C) 2015 Texas Instruments Inc. */ @@ -113,7 +112,6 @@ #define DP83867_RGMII_RX_CLK_DELAY_SHIFT 0 #define DP83867_RGMII_RX_CLK_DELAY_INV (DP83867_RGMII_RX_CLK_DELAY_MAX + 1) - /* IO_MUX_CFG bits */ #define DP83867_IO_MUX_CFG_IO_IMPEDANCE_MASK 0x1f #define DP83867_IO_MUX_CFG_IO_IMPEDANCE_MAX 0x0 @@ -215,9 +213,9 @@ static int dp83867_set_wol(struct phy_device *phydev, if (wol->wolopts & WAKE_MAGICSECURE) { phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP1, (wol->sopass[1] << 8) | wol->sopass[0]); - phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP1, + phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP2, (wol->sopass[3] << 8) | wol->sopass[2]); - phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP1, + phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP3, (wol->sopass[5] << 8) | wol->sopass[4]); val_rxcfg |= DP83867_WOL_SEC_EN; @@ -384,22 +382,22 @@ static int dp83867_set_downshift(struct phy_device *phydev, u8 cnt) DP83867_DOWNSHIFT_EN); switch (cnt) { - case DP83867_DOWNSHIFT_1_COUNT: - count = DP83867_DOWNSHIFT_1_COUNT_VAL; - break; - case DP83867_DOWNSHIFT_2_COUNT: - count = DP83867_DOWNSHIFT_2_COUNT_VAL; - break; - case DP83867_DOWNSHIFT_4_COUNT: - count = DP83867_DOWNSHIFT_4_COUNT_VAL; - break; - case DP83867_DOWNSHIFT_8_COUNT: - count = DP83867_DOWNSHIFT_8_COUNT_VAL; - break; - default: - phydev_err(phydev, - "Downshift count must be 1, 2, 4 or 8\n"); - return -EINVAL; + case DP83867_DOWNSHIFT_1_COUNT: + count = DP83867_DOWNSHIFT_1_COUNT_VAL; + break; + case DP83867_DOWNSHIFT_2_COUNT: + count = DP83867_DOWNSHIFT_2_COUNT_VAL; + break; + case DP83867_DOWNSHIFT_4_COUNT: + count = DP83867_DOWNSHIFT_4_COUNT_VAL; + break; + case DP83867_DOWNSHIFT_8_COUNT: + count = DP83867_DOWNSHIFT_8_COUNT_VAL; + break; + default: + phydev_err(phydev, + "Downshift count must be 1, 2, 4 or 8\n"); + return -EINVAL; } val = DP83867_DOWNSHIFT_EN; @@ -411,7 +409,7 @@ static int dp83867_set_downshift(struct phy_device *phydev, u8 cnt) } static int dp83867_get_tunable(struct phy_device *phydev, - struct ethtool_tunable *tuna, void *data) + struct ethtool_tunable *tuna, void *data) { switch (tuna->id) { case ETHTOOL_PHY_DOWNSHIFT: @@ -422,7 +420,7 @@ static int dp83867_get_tunable(struct phy_device *phydev, } static int dp83867_set_tunable(struct phy_device *phydev, - struct ethtool_tunable *tuna, const void *data) + struct ethtool_tunable *tuna, const void *data) { switch (tuna->id) { case ETHTOOL_PHY_DOWNSHIFT: @@ -524,11 +522,10 @@ static int dp83867_of_init(struct phy_device *phydev) dp83867->io_impedance = -1; /* leave at default */ dp83867->rxctrl_strap_quirk = of_property_read_bool(of_node, - "ti,dp83867-rxctrl-strap-quirk"); + "ti,dp83867-rxctrl-strap-quirk"); dp83867->sgmii_ref_clk_en = of_property_read_bool(of_node, - "ti,sgmii-ref-clock-output-enable"); - + "ti,sgmii-ref-clock-output-enable"); dp83867->rx_id_delay = DP83867_RGMII_RX_CLK_DELAY_INV; ret = of_property_read_u32(of_node, "ti,rx-internal-delay", diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index 58103152c601..6b98d74b5102 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -427,18 +427,18 @@ static int dp83869_config_init(struct phy_device *phydev) return ret; val = phy_read_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIICTL); - val &= ~(DP83869_RGMII_TX_CLK_DELAY_EN | - DP83869_RGMII_RX_CLK_DELAY_EN); + val |= (DP83869_RGMII_TX_CLK_DELAY_EN | + DP83869_RGMII_RX_CLK_DELAY_EN); if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) - val |= (DP83869_RGMII_TX_CLK_DELAY_EN | - DP83869_RGMII_RX_CLK_DELAY_EN); + val &= ~(DP83869_RGMII_TX_CLK_DELAY_EN | + DP83869_RGMII_RX_CLK_DELAY_EN); if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) - val |= DP83869_RGMII_TX_CLK_DELAY_EN; + val &= ~DP83869_RGMII_TX_CLK_DELAY_EN; if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) - val |= DP83869_RGMII_RX_CLK_DELAY_EN; + val &= ~DP83869_RGMII_RX_CLK_DELAY_EN; ret = phy_write_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIICTL, val); diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index c4641b1704d6..18d81f43f2a8 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -279,13 +279,13 @@ static struct phy_device *__fixed_phy_register(unsigned int irq, phy->supported); linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, phy->supported); - /* fall through */ + fallthrough; case SPEED_100: linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, phy->supported); linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, phy->supported); - /* fall through */ + fallthrough; case SPEED_10: default: linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c index 1d4c012194e9..6cf9b798b710 100644 --- a/drivers/net/phy/mscc/mscc_macsec.c +++ b/drivers/net/phy/mscc/mscc_macsec.c @@ -958,7 +958,7 @@ static int vsc8584_macsec_del_txsa(struct macsec_context *ctx) return 0; } -static struct macsec_ops vsc8584_macsec_ops = { +static const struct macsec_ops vsc8584_macsec_ops = { .mdo_dev_open = vsc8584_macsec_dev_open, .mdo_dev_stop = vsc8584_macsec_dev_stop, .mdo_add_secy = vsc8584_macsec_add_secy, diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index a4fbf3a4fa97..6bc7406a1ce7 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -1738,13 +1738,13 @@ static int __phy_write_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb, return 0; } -/* Trigger a read to the spcified MCB */ +/* Trigger a read to the specified MCB */ static int phy_update_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb) { return __phy_write_mcb_s6g(phydev, reg, mcb, PHY_MCB_S6G_READ); } -/* Trigger a write to the spcified MCB */ +/* Trigger a write to the specified MCB */ static int phy_commit_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb) { return __phy_write_mcb_s6g(phydev, reg, mcb, PHY_MCB_S6G_WRITE); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 79b4f35d151e..735a806045ac 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -355,7 +355,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCGMIIPHY: mii_data->phy_id = phydev->mdio.addr; - /* fall through */ + fallthrough; case SIOCGMIIREG: if (mdio_phy_id_is_c45(mii_data->phy_id)) { @@ -433,7 +433,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd) case SIOCSHWTSTAMP: if (phydev->mii_ts && phydev->mii_ts->hwtstamp) return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr); - /* fall through */ + fallthrough; default: return -EOPNOTSUPP; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 57d44648c8dd..8adfbad0a1e8 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1979,7 +1979,7 @@ static int genphy_setup_master_slave(struct phy_device *phydev) break; case MASTER_SLAVE_CFG_MASTER_FORCE: ctl |= CTL1000_AS_MASTER; - /* fallthrough */ + fallthrough; case MASTER_SLAVE_CFG_SLAVE_FORCE: ctl |= CTL1000_ENABLE_MASTER; break; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 32b4bd6a5b55..fe2296fdda19 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -535,8 +535,10 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, if (pl->pcs_ops) pl->pcs_ops->pcs_get_state(pl->pcs, state); - else + else if (pl->mac_ops->mac_pcs_get_state) pl->mac_ops->mac_pcs_get_state(pl->config, state); + else + state->link = 0; } /* The fixed state is... fixed except for the link state, @@ -1905,7 +1907,7 @@ int phylink_mii_ioctl(struct phylink *pl, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCGMIIPHY: mii->phy_id = pl->phydev->mdio.addr; - /* fall through */ + fallthrough; case SIOCGMIIREG: ret = phylink_phy_read(pl, mii->phy_id, mii->reg_num); @@ -1928,7 +1930,7 @@ int phylink_mii_ioctl(struct phylink *pl, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCGMIIPHY: mii->phy_id = 0; - /* fall through */ + fallthrough; case SIOCGMIIREG: ret = phylink_mii_read(pl, mii->phy_id, mii->reg_num); @@ -2319,6 +2321,49 @@ static void phylink_decode_sgmii_word(struct phylink_link_state *state, } /** + * phylink_decode_usxgmii_word() - decode the USXGMII word from a MAC PCS + * @state: a pointer to a struct phylink_link_state. + * @lpa: a 16 bit value which stores the USXGMII auto-negotiation word + * + * Helper for MAC PCS supporting the USXGMII protocol and the auto-negotiation + * code word. Decode the USXGMII code word and populate the corresponding fields + * (speed, duplex) into the phylink_link_state structure. + */ +void phylink_decode_usxgmii_word(struct phylink_link_state *state, + uint16_t lpa) +{ + switch (lpa & MDIO_USXGMII_SPD_MASK) { + case MDIO_USXGMII_10: + state->speed = SPEED_10; + break; + case MDIO_USXGMII_100: + state->speed = SPEED_100; + break; + case MDIO_USXGMII_1000: + state->speed = SPEED_1000; + break; + case MDIO_USXGMII_2500: + state->speed = SPEED_2500; + break; + case MDIO_USXGMII_5000: + state->speed = SPEED_5000; + break; + case MDIO_USXGMII_10G: + state->speed = SPEED_10000; + break; + default: + state->link = false; + return; + } + + if (lpa & MDIO_USXGMII_FULL_DUPLEX) + state->duplex = DUPLEX_FULL; + else + state->duplex = DUPLEX_HALF; +} +EXPORT_SYMBOL_GPL(phylink_decode_usxgmii_word); + +/** * phylink_mii_c22_pcs_get_state() - read the MAC PCS state * @pcs: a pointer to a &struct mdio_device. * @state: a pointer to a &struct phylink_link_state. @@ -2361,6 +2406,7 @@ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, break; case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: phylink_decode_sgmii_word(state, lpa); break; diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 6900c68260e0..58014feedf6c 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -149,7 +149,7 @@ int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, port = PORT_TP; break; } - /* fallthrough */ + fallthrough; case SFF8024_CONNECTOR_SG: /* guess */ case SFF8024_CONNECTOR_HSSDC_II: case SFF8024_CONNECTOR_NOSEPARATE: @@ -301,7 +301,7 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, break; case SFF8024_ECC_100GBASE_CR4: phylink_set(modes, 100000baseCR4_Full); - /* fallthrough */ + fallthrough; case SFF8024_ECC_25GBASE_CR_S: case SFF8024_ECC_25GBASE_CR_N: phylink_set(modes, 25000baseCR_Full); diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index c24b0e83dd32..1d18c10e8f82 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -7,6 +7,7 @@ #include <linux/i2c.h> #include <linux/interrupt.h> #include <linux/jiffies.h> +#include <linux/mdio/mdio-i2c.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/of.h> @@ -16,7 +17,6 @@ #include <linux/slab.h> #include <linux/workqueue.h> -#include "mdio-i2c.h" #include "sfp.h" #include "swphy.h" @@ -552,7 +552,7 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_temp_crit: if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) return 0; - /* fall through */ + fallthrough; case hwmon_temp_input: case hwmon_temp_label: return 0444; @@ -571,7 +571,7 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_in_crit: if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) return 0; - /* fall through */ + fallthrough; case hwmon_in_input: case hwmon_in_label: return 0444; @@ -590,7 +590,7 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_curr_crit: if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) return 0; - /* fall through */ + fallthrough; case hwmon_curr_input: case hwmon_curr_label: return 0444; @@ -618,7 +618,7 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_power_crit: if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) return 0; - /* fall through */ + fallthrough; case hwmon_power_input: case hwmon_power_label: return 0444; @@ -1872,7 +1872,7 @@ static void sfp_sm_module(struct sfp *sfp, unsigned int event) dev_warn(sfp->dev, "hwmon probe failed: %d\n", err); sfp_sm_mod_next(sfp, SFP_MOD_WAITDEV, 0); - /* fall through */ + fallthrough; case SFP_MOD_WAITDEV: /* Ensure that the device is attached before proceeding */ if (sfp->sm_dev_state < SFP_DEV_DOWN) @@ -1890,7 +1890,7 @@ static void sfp_sm_module(struct sfp *sfp, unsigned int event) goto insert; sfp_sm_mod_next(sfp, SFP_MOD_HPOWER, 0); - /* fall through */ + fallthrough; case SFP_MOD_HPOWER: /* Enable high power mode */ err = sfp_sm_mod_hpower(sfp, true); diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 74568ae16125..ec97669be5c2 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -12,6 +12,7 @@ * */ +#include <linux/clk.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mii.h> @@ -21,6 +22,17 @@ #include <linux/netdevice.h> #include <linux/smscphy.h> +/* Vendor-specific PHY Definitions */ +/* EDPD NLP / crossover time configuration */ +#define PHY_EDPD_CONFIG 16 +#define PHY_EDPD_CONFIG_EXT_CROSSOVER_ 0x0001 + +/* Control/Status Indication Register */ +#define SPECIAL_CTRL_STS 27 +#define SPECIAL_CTRL_STS_OVRRD_AMDIX_ 0x8000 +#define SPECIAL_CTRL_STS_AMDIX_ENABLE_ 0x4000 +#define SPECIAL_CTRL_STS_AMDIX_STATE_ 0x2000 + struct smsc_hw_stat { const char *string; u8 reg; @@ -33,14 +45,22 @@ static struct smsc_hw_stat smsc_hw_stats[] = { struct smsc_phy_priv { bool energy_enable; + struct clk *refclk; }; static int smsc_phy_config_intr(struct phy_device *phydev) { - int rc = phy_write (phydev, MII_LAN83C185_IM, - ((PHY_INTERRUPT_ENABLED == phydev->interrupts) - ? MII_LAN83C185_ISF_INT_PHYLIB_EVENTS - : 0)); + struct smsc_phy_priv *priv = phydev->priv; + u16 intmask = 0; + int rc; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + intmask = MII_LAN83C185_ISF_INT4 | MII_LAN83C185_ISF_INT6; + if (priv->energy_enable) + intmask |= MII_LAN83C185_ISF_INT7; + } + + rc = phy_write(phydev, MII_LAN83C185_IM, intmask); return rc < 0 ? rc : 0; } @@ -55,19 +75,21 @@ static int smsc_phy_ack_interrupt(struct phy_device *phydev) static int smsc_phy_config_init(struct phy_device *phydev) { struct smsc_phy_priv *priv = phydev->priv; + int rc; - int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS); + if (!priv->energy_enable) + return 0; + + rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS); if (rc < 0) return rc; - if (priv->energy_enable) { - /* Enable energy detect mode for this SMSC Transceivers */ - rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS, - rc | MII_LAN83C185_EDPWRDOWN); - if (rc < 0) - return rc; - } + /* Enable energy detect mode for this SMSC Transceivers */ + rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS, + rc | MII_LAN83C185_EDPWRDOWN); + if (rc < 0) + return rc; return smsc_phy_ack_interrupt(phydev); } @@ -96,6 +118,54 @@ static int lan911x_config_init(struct phy_device *phydev) return smsc_phy_ack_interrupt(phydev); } +static int lan87xx_config_aneg(struct phy_device *phydev) +{ + int rc; + int val; + + switch (phydev->mdix_ctrl) { + case ETH_TP_MDI: + val = SPECIAL_CTRL_STS_OVRRD_AMDIX_; + break; + case ETH_TP_MDI_X: + val = SPECIAL_CTRL_STS_OVRRD_AMDIX_ | + SPECIAL_CTRL_STS_AMDIX_STATE_; + break; + case ETH_TP_MDI_AUTO: + val = SPECIAL_CTRL_STS_AMDIX_ENABLE_; + break; + default: + return genphy_config_aneg(phydev); + } + + rc = phy_read(phydev, SPECIAL_CTRL_STS); + if (rc < 0) + return rc; + + rc &= ~(SPECIAL_CTRL_STS_OVRRD_AMDIX_ | + SPECIAL_CTRL_STS_AMDIX_ENABLE_ | + SPECIAL_CTRL_STS_AMDIX_STATE_); + rc |= val; + phy_write(phydev, SPECIAL_CTRL_STS, rc); + + phydev->mdix = phydev->mdix_ctrl; + return genphy_config_aneg(phydev); +} + +static int lan87xx_config_aneg_ext(struct phy_device *phydev) +{ + int rc; + + /* Extend Manual AutoMDIX timer */ + rc = phy_read(phydev, PHY_EDPD_CONFIG); + if (rc < 0) + return rc; + + rc |= PHY_EDPD_CONFIG_EXT_CROSSOVER_; + phy_write(phydev, PHY_EDPD_CONFIG, rc); + return lan87xx_config_aneg(phydev); +} + /* * The LAN87xx suffers from rare absence of the ENERGYON-bit when Ethernet cable * plugs in while LAN87xx is in Energy Detect Power-Down mode. This leads to @@ -185,11 +255,20 @@ static void smsc_get_stats(struct phy_device *phydev, data[i] = smsc_get_stat(phydev, i); } +static void smsc_phy_remove(struct phy_device *phydev) +{ + struct smsc_phy_priv *priv = phydev->priv; + + clk_disable_unprepare(priv->refclk); + clk_put(priv->refclk); +} + static int smsc_phy_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; struct device_node *of_node = dev->of_node; struct smsc_phy_priv *priv; + int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -202,6 +281,19 @@ static int smsc_phy_probe(struct phy_device *phydev) phydev->priv = priv; + /* Make clk optional to keep DTB backward compatibility. */ + priv->refclk = clk_get_optional(dev, NULL); + if (IS_ERR(priv->refclk)) + dev_err_probe(dev, PTR_ERR(priv->refclk), "Failed to request clock\n"); + + ret = clk_prepare_enable(priv->refclk); + if (ret) + return ret; + + ret = clk_set_rate(priv->refclk, 50 * 1000 * 1000); + if (ret) + return ret; + return 0; } @@ -250,6 +342,9 @@ static struct phy_driver smsc_phy_driver[] = { .suspend = genphy_suspend, .resume = genphy_resume, }, { + /* This covers internal PHY (phy_id: 0x0007C0C3) for + * LAN9500 (PID: 0x9500), LAN9514 (PID: 0xec00), LAN9505 (PID: 0x9505) + */ .phy_id = 0x0007c0c0, /* OUI=0x00800f, Model#=0x0c */ .phy_id_mask = 0xfffffff0, .name = "SMSC LAN8700", @@ -262,6 +357,7 @@ static struct phy_driver smsc_phy_driver[] = { .read_status = lan87xx_read_status, .config_init = smsc_phy_config_init, .soft_reset = smsc_phy_reset, + .config_aneg = lan87xx_config_aneg, /* IRQ related */ .ack_interrupt = smsc_phy_ack_interrupt, @@ -293,19 +389,23 @@ static struct phy_driver smsc_phy_driver[] = { .suspend = genphy_suspend, .resume = genphy_resume, }, { + /* This covers internal PHY (phy_id: 0x0007C0F0) for + * LAN9500A (PID: 0x9E00), LAN9505A (PID: 0x9E01) + */ .phy_id = 0x0007c0f0, /* OUI=0x00800f, Model#=0x0f */ .phy_id_mask = 0xfffffff0, .name = "SMSC LAN8710/LAN8720", /* PHY_BASIC_FEATURES */ - .flags = PHY_RST_AFTER_CLK_EN, .probe = smsc_phy_probe, + .remove = smsc_phy_remove, /* basic functions */ .read_status = lan87xx_read_status, .config_init = smsc_phy_config_init, .soft_reset = smsc_phy_reset, + .config_aneg = lan87xx_config_aneg_ext, /* IRQ related */ .ack_interrupt = smsc_phy_ack_interrupt, diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c index d82016dcde3b..4406b353123e 100644 --- a/drivers/net/plip/plip.c +++ b/drivers/net/plip/plip.c @@ -498,7 +498,7 @@ plip_receive(unsigned short nibble_timeout, struct net_device *dev, *data_p = (c0 >> 3) & 0x0f; write_data (dev, 0x10); /* send ACK */ *ns_p = PLIP_NB_1; - /* fall through */ + fallthrough; case PLIP_NB_1: cx = nibble_timeout; @@ -594,7 +594,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl, printk(KERN_DEBUG "%s: receive start\n", dev->name); rcv->state = PLIP_PK_LENGTH_LSB; rcv->nibble = PLIP_NB_BEGIN; - /* fall through */ + fallthrough; case PLIP_PK_LENGTH_LSB: if (snd->state != PLIP_PK_DONE) { @@ -615,7 +615,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl, return TIMEOUT; } rcv->state = PLIP_PK_LENGTH_MSB; - /* fall through */ + fallthrough; case PLIP_PK_LENGTH_MSB: if (plip_receive(nibble_timeout, dev, @@ -638,7 +638,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl, rcv->state = PLIP_PK_DATA; rcv->byte = 0; rcv->checksum = 0; - /* fall through */ + fallthrough; case PLIP_PK_DATA: lbuf = rcv->skb->data; @@ -651,7 +651,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl, rcv->checksum += lbuf[--rcv->byte]; } while (rcv->byte); rcv->state = PLIP_PK_CHECKSUM; - /* fall through */ + fallthrough; case PLIP_PK_CHECKSUM: if (plip_receive(nibble_timeout, dev, @@ -664,7 +664,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl, return ERROR; } rcv->state = PLIP_PK_DONE; - /* fall through */ + fallthrough; case PLIP_PK_DONE: /* Inform the upper layer for the arrival of a packet. */ @@ -710,7 +710,7 @@ plip_send(unsigned short nibble_timeout, struct net_device *dev, case PLIP_NB_BEGIN: write_data (dev, data & 0x0f); *ns_p = PLIP_NB_1; - /* fall through */ + fallthrough; case PLIP_NB_1: write_data (dev, 0x10 | (data & 0x0f)); @@ -725,7 +725,7 @@ plip_send(unsigned short nibble_timeout, struct net_device *dev, } write_data (dev, 0x10 | (data >> 4)); *ns_p = PLIP_NB_2; - /* fall through */ + fallthrough; case PLIP_NB_2: write_data (dev, (data >> 4)); @@ -814,7 +814,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl, &snd->nibble, snd->length.b.lsb)) return TIMEOUT; snd->state = PLIP_PK_LENGTH_MSB; - /* fall through */ + fallthrough; case PLIP_PK_LENGTH_MSB: if (plip_send(nibble_timeout, dev, @@ -823,7 +823,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl, snd->state = PLIP_PK_DATA; snd->byte = 0; snd->checksum = 0; - /* fall through */ + fallthrough; case PLIP_PK_DATA: do { @@ -835,7 +835,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl, snd->checksum += lbuf[--snd->byte]; } while (snd->byte); snd->state = PLIP_PK_CHECKSUM; - /* fall through */ + fallthrough; case PLIP_PK_CHECKSUM: if (plip_send(nibble_timeout, dev, @@ -846,7 +846,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl, dev_kfree_skb(snd->skb); dev->stats.tx_packets++; snd->state = PLIP_PK_DONE; - /* fall through */ + fallthrough; case PLIP_PK_DONE: /* Close the connection */ @@ -935,7 +935,7 @@ plip_interrupt(void *dev_id) switch (nl->connection) { case PLIP_CN_CLOSING: netif_wake_queue (dev); - /* fall through */ + fallthrough; case PLIP_CN_NONE: case PLIP_CN_SEND: rcv->state = PLIP_PK_TRIGGER; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3c11a77f5709..be69d272052f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -219,24 +219,6 @@ struct veth { __be16 h_vlan_TCI; }; -bool tun_is_xdp_frame(void *ptr) -{ - return (unsigned long)ptr & TUN_XDP_FLAG; -} -EXPORT_SYMBOL(tun_is_xdp_frame); - -void *tun_xdp_to_ptr(void *ptr) -{ - return (void *)((unsigned long)ptr | TUN_XDP_FLAG); -} -EXPORT_SYMBOL(tun_xdp_to_ptr); - -void *tun_ptr_to_xdp(void *ptr) -{ - return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG); -} -EXPORT_SYMBOL(tun_ptr_to_xdp); - static int tun_napi_receive(struct napi_struct *napi, int budget) { struct tun_file *tfile = container_of(napi, struct tun_file, napi); @@ -1590,10 +1572,10 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, break; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(tun->dev, xdp_prog, act); - /* fall through */ + fallthrough; case XDP_DROP: this_cpu_inc(tun->pcpu_stats->rx_dropped); break; @@ -2417,7 +2399,7 @@ static int tun_xdp_one(struct tun_struct *tun, switch (err) { case XDP_REDIRECT: *flush = true; - /* fall through */ + fallthrough; case XDP_TX: return 0; case XDP_PASS: diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index a7fbc3ccd29e..b46993d5f997 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -252,6 +252,7 @@ config USB_NET_CDC_EEM config USB_NET_CDC_NCM tristate "CDC NCM support" depends on USB_USBNET + select USB_NET_CDCETHER default y help This driver provides support for CDC NCM (Network Control Model @@ -345,6 +346,8 @@ config USB_NET_SMSC75XX config USB_NET_SMSC95XX tristate "SMSC LAN95XX based USB 2.0 10/100 ethernet devices" depends on USB_USBNET + select PHYLIB + select SMSC_PHY select BITREVERSE select CRC16 select CRC32 diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index 7e44110746dd..0717c18015c9 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -333,13 +333,13 @@ static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed) switch (speed) { case SPEED_5000: aqc111_data->phy_cfg |= AQ_ADV_5G; - /* fall-through */ + fallthrough; case SPEED_2500: aqc111_data->phy_cfg |= AQ_ADV_2G5; - /* fall-through */ + fallthrough; case SPEED_1000: aqc111_data->phy_cfg |= AQ_ADV_1G; - /* fall-through */ + fallthrough; case SPEED_100: aqc111_data->phy_cfg |= AQ_ADV_100M; /* fall-through */ diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index e39f41efda3e..7bc6e8f856fe 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -296,7 +296,7 @@ int asix_read_phy_addr(struct usbnet *dev, int internal) netdev_dbg(dev->net, "asix_get_phy_addr()\n"); - if (ret < 0) { + if (ret < 2) { netdev_err(dev->net, "Error reading PHYID register: %02x\n", ret); goto out; } diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index d387bc7ac1b6..97ba67042d12 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -858,7 +858,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id default: dev_warn(&intf->dev, "Couldn't detect memory size, assuming 32k\n"); - /* fall through */ + fallthrough; case 0x87654321: catc_set_reg(catc, TxBufCount, 4); catc_set_reg(catc, RxBufCount, 16); diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 9bdbd7b472a0..dba847f28096 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -97,7 +97,7 @@ static void tx_complete(struct urb *req) case -ECONNRESET: case -ESHUTDOWN: dev->stats.tx_aborted_errors++; - /* fall through */ + fallthrough; default: dev->stats.tx_errors++; dev_dbg(&dev->dev, "TX error (%d)\n", status); diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index b91f92e4e5f2..915ac75b55fc 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -625,6 +625,10 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0a46, 0x1269), /* DM9621A USB to Fast Ethernet Adapter */ .driver_info = (unsigned long)&dm9601_info, }, + { + USB_DEVICE(0x0586, 0x3427), /* ZyXEL Keenetic Plus DSL xDSL modem */ + .driver_info = (unsigned long)&dm9601_info, + }, {}, // END }; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 442507f25aad..65b315bc60ab 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3192,7 +3192,7 @@ static void rx_complete(struct urb *urb) case -EPIPE: dev->net->stats.rx_errors++; lan78xx_defer_kevent(dev, EVENT_RX_HALT); - /* FALLTHROUGH */ + fallthrough; case -ECONNRESET: /* async unlink */ case -ESHUTDOWN: /* hardware gone */ netif_dbg(dev, ifdown, dev->net, @@ -3213,7 +3213,7 @@ static void rx_complete(struct urb *urb) /* data overrun ... flush fifo? */ case -EOVERFLOW: dev->net->stats.rx_over_errors++; - /* FALLTHROUGH */ + fallthrough; default: state = rx_cleanup; diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 0ef7e1f443e3..e92cb51a2c77 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -629,7 +629,7 @@ static void write_bulk_callback(struct urb *urb) return; default: netif_info(pegasus, tx_err, net, "TX status %d\n", status); - /* FALL THROUGH */ + fallthrough; case 0: break; } @@ -1009,7 +1009,7 @@ static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd) switch (cmd) { case SIOCDEVPRIVATE: data[0] = pegasus->phy; - /* fall through */ + fallthrough; case SIOCDEVPRIVATE + 1: read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]); res = 0; diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 2b02fefd094d..b1770489aca5 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1682,7 +1682,7 @@ static void intr_callback(struct urb *urb) case -ECONNRESET: /* unlink */ case -ESHUTDOWN: netif_device_detach(tp->netdev); - /* fall through */ + fallthrough; case -ENOENT: case -EPROTO: netif_info(tp, intr, tp->netdev, @@ -3251,7 +3251,7 @@ static void r8153b_ups_en(struct r8152 *tp, bool enable) r8152_mdio_write(tp, MII_BMCR, data); data = r8153_phy_status(tp, PHY_STAT_LAN_ON); - /* fall through */ + fallthrough; default: if (data != PHY_STAT_LAN_ON) @@ -4849,7 +4849,7 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex, tp->ups_info.speed_duplex = NWAY_1000M_FULL; break; } - /* fall through */ + fallthrough; default: ret = -EINVAL; goto out; diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index e7c630d37589..733f120c852b 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -843,7 +843,7 @@ static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) switch (cmd) { case SIOCDEVPRIVATE: data[0] = dev->phy; - /* fall through */ + fallthrough; case SIOCDEVPRIVATE + 1: read_mii_word(dev, dev->phy, (data[1] & 0x1f), &data[3]); break; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index bb4ccbda031a..601fb40a2a0a 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -18,10 +18,12 @@ #include <linux/usb/usbnet.h> #include <linux/slab.h> #include <linux/of_net.h> +#include <linux/mdio.h> +#include <linux/phy.h> #include "smsc95xx.h" #define SMSC_CHIPNAME "smsc95xx" -#define SMSC_DRIVER_VERSION "1.0.6" +#define SMSC_DRIVER_VERSION "2.0.0" #define HS_USB_PKT_SIZE (512) #define FS_USB_PKT_SIZE (64) #define DEFAULT_HS_BURST_CAP_SIZE (16 * 1024 + 5 * HS_USB_PKT_SIZE) @@ -49,10 +51,7 @@ #define SUSPEND_ALLMODES (SUSPEND_SUSPEND0 | SUSPEND_SUSPEND1 | \ SUSPEND_SUSPEND2 | SUSPEND_SUSPEND3) -#define CARRIER_CHECK_DELAY (2 * HZ) - struct smsc95xx_priv { - u32 chip_id; u32 mac_cr; u32 hash_hi; u32 hash_lo; @@ -60,10 +59,8 @@ struct smsc95xx_priv { spinlock_t mac_cr_lock; u8 features; u8 suspend_flags; - u8 mdix_ctrl; - bool link_ok; - struct delayed_work carrier_check; - struct usbnet *dev; + struct mii_bus *mdiobus; + struct phy_device *phydev; }; static bool turbo_mode = true; @@ -173,10 +170,14 @@ static int __must_check __smsc95xx_phy_wait_not_busy(struct usbnet *dev, return -EIO; } -static int __smsc95xx_mdio_read(struct net_device *netdev, int phy_id, int idx, +static u32 mii_address_cmd(int phy_id, int idx, u16 op) +{ + return (phy_id & 0x1f) << 11 | (idx & 0x1f) << 6 | op; +} + +static int __smsc95xx_mdio_read(struct usbnet *dev, int phy_id, int idx, int in_pm) { - struct usbnet *dev = netdev_priv(netdev); u32 val, addr; int ret; @@ -185,14 +186,12 @@ static int __smsc95xx_mdio_read(struct net_device *netdev, int phy_id, int idx, /* confirm MII not busy */ ret = __smsc95xx_phy_wait_not_busy(dev, in_pm); if (ret < 0) { - netdev_warn(dev->net, "MII is busy in smsc95xx_mdio_read\n"); + netdev_warn(dev->net, "%s: MII is busy\n", __func__); goto done; } /* set the address, index & direction (read from PHY) */ - phy_id &= dev->mii.phy_id_mask; - idx &= dev->mii.reg_num_mask; - addr = (phy_id << 11) | (idx << 6) | MII_READ_ | MII_BUSY_; + addr = mii_address_cmd(phy_id, idx, MII_READ_ | MII_BUSY_); ret = __smsc95xx_write_reg(dev, MII_ADDR, addr, in_pm); if (ret < 0) { netdev_warn(dev->net, "Error writing MII_ADDR\n"); @@ -218,10 +217,9 @@ done: return ret; } -static void __smsc95xx_mdio_write(struct net_device *netdev, int phy_id, +static void __smsc95xx_mdio_write(struct usbnet *dev, int phy_id, int idx, int regval, int in_pm) { - struct usbnet *dev = netdev_priv(netdev); u32 val, addr; int ret; @@ -230,7 +228,7 @@ static void __smsc95xx_mdio_write(struct net_device *netdev, int phy_id, /* confirm MII not busy */ ret = __smsc95xx_phy_wait_not_busy(dev, in_pm); if (ret < 0) { - netdev_warn(dev->net, "MII is busy in smsc95xx_mdio_write\n"); + netdev_warn(dev->net, "%s: MII is busy\n", __func__); goto done; } @@ -242,9 +240,7 @@ static void __smsc95xx_mdio_write(struct net_device *netdev, int phy_id, } /* set the address, index & direction (write to PHY) */ - phy_id &= dev->mii.phy_id_mask; - idx &= dev->mii.reg_num_mask; - addr = (phy_id << 11) | (idx << 6) | MII_WRITE_ | MII_BUSY_; + addr = mii_address_cmd(phy_id, idx, MII_WRITE_ | MII_BUSY_); ret = __smsc95xx_write_reg(dev, MII_ADDR, addr, in_pm); if (ret < 0) { netdev_warn(dev->net, "Error writing MII_ADDR\n"); @@ -261,27 +257,34 @@ done: mutex_unlock(&dev->phy_mutex); } -static int smsc95xx_mdio_read_nopm(struct net_device *netdev, int phy_id, - int idx) +static int smsc95xx_mdio_read_nopm(struct usbnet *dev, int idx) { - return __smsc95xx_mdio_read(netdev, phy_id, idx, 1); + struct smsc95xx_priv *pdata = dev->driver_priv; + + return __smsc95xx_mdio_read(dev, pdata->phydev->mdio.addr, idx, 1); } -static void smsc95xx_mdio_write_nopm(struct net_device *netdev, int phy_id, - int idx, int regval) +static void smsc95xx_mdio_write_nopm(struct usbnet *dev, int idx, int regval) { - __smsc95xx_mdio_write(netdev, phy_id, idx, regval, 1); + struct smsc95xx_priv *pdata = dev->driver_priv; + + __smsc95xx_mdio_write(dev, pdata->phydev->mdio.addr, idx, regval, 1); } -static int smsc95xx_mdio_read(struct net_device *netdev, int phy_id, int idx) +static int smsc95xx_mdiobus_read(struct mii_bus *bus, int phy_id, int idx) { - return __smsc95xx_mdio_read(netdev, phy_id, idx, 0); + struct usbnet *dev = bus->priv; + + return __smsc95xx_mdio_read(dev, phy_id, idx, 0); } -static void smsc95xx_mdio_write(struct net_device *netdev, int phy_id, int idx, - int regval) +static int smsc95xx_mdiobus_write(struct mii_bus *bus, int phy_id, int idx, + u16 regval) { - __smsc95xx_mdio_write(netdev, phy_id, idx, regval, 0); + struct usbnet *dev = bus->priv; + + __smsc95xx_mdio_write(dev, phy_id, idx, regval, 0); + return 0; } static int __must_check smsc95xx_wait_eeprom(struct usbnet *dev) @@ -455,7 +458,7 @@ static unsigned int smsc95xx_hash(char addr[ETH_ALEN]) static void smsc95xx_set_multicast(struct net_device *netdev) { struct usbnet *dev = netdev_priv(netdev); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; unsigned long flags; int ret; @@ -511,22 +514,23 @@ static void smsc95xx_set_multicast(struct net_device *netdev) netdev_warn(dev->net, "failed to initiate async write to MAC_CR\n"); } -static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev, u8 duplex, - u16 lcladv, u16 rmtadv) +static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev) { u32 flow = 0, afc_cfg; + struct smsc95xx_priv *pdata = dev->driver_priv; + bool tx_pause, rx_pause; int ret = smsc95xx_read_reg(dev, AFC_CFG, &afc_cfg); if (ret < 0) return ret; - if (duplex == DUPLEX_FULL) { - u8 cap = mii_resolve_flowctrl_fdx(lcladv, rmtadv); + if (pdata->phydev->duplex == DUPLEX_FULL) { + phy_get_pause(pdata->phydev, &tx_pause, &rx_pause); - if (cap & FLOW_CTRL_RX) + if (rx_pause) flow = 0xFFFF0002; - if (cap & FLOW_CTRL_TX) { + if (tx_pause) { afc_cfg |= 0xF; flow |= 0xFFFF0000; } else { @@ -534,8 +538,8 @@ static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev, u8 duplex, } netif_dbg(dev, link, dev->net, "rx pause %s, tx pause %s\n", - cap & FLOW_CTRL_RX ? "enabled" : "disabled", - cap & FLOW_CTRL_TX ? "enabled" : "disabled"); + rx_pause ? "enabled" : "disabled", + tx_pause ? "enabled" : "disabled"); } else { netif_dbg(dev, link, dev->net, "half duplex\n"); afc_cfg |= 0xF; @@ -550,33 +554,16 @@ static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev, u8 duplex, static int smsc95xx_link_reset(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - struct mii_if_info *mii = &dev->mii; - struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET }; + struct smsc95xx_priv *pdata = dev->driver_priv; unsigned long flags; - u16 lcladv, rmtadv; int ret; - /* clear interrupt status */ - ret = smsc95xx_mdio_read(dev->net, mii->phy_id, PHY_INT_SRC); - if (ret < 0) - return ret; - ret = smsc95xx_write_reg(dev, INT_STS, INT_STS_CLEAR_ALL_); if (ret < 0) return ret; - mii_check_media(mii, 1, 1); - mii_ethtool_gset(&dev->mii, &ecmd); - lcladv = smsc95xx_mdio_read(dev->net, mii->phy_id, MII_ADVERTISE); - rmtadv = smsc95xx_mdio_read(dev->net, mii->phy_id, MII_LPA); - - netif_dbg(dev, link, dev->net, - "speed: %u duplex: %d lcladv: %04x rmtadv: %04x\n", - ethtool_cmd_speed(&ecmd), ecmd.duplex, lcladv, rmtadv); - spin_lock_irqsave(&pdata->mac_cr_lock, flags); - if (ecmd.duplex != DUPLEX_FULL) { + if (pdata->phydev->duplex != DUPLEX_FULL) { pdata->mac_cr &= ~MAC_CR_FDPX_; pdata->mac_cr |= MAC_CR_RCVOWN_; } else { @@ -589,7 +576,7 @@ static int smsc95xx_link_reset(struct usbnet *dev) if (ret < 0) return ret; - ret = smsc95xx_phy_update_flowcontrol(dev, ecmd.duplex, lcladv, rmtadv); + ret = smsc95xx_phy_update_flowcontrol(dev); if (ret < 0) netdev_warn(dev->net, "Error updating PHY flow control\n"); @@ -616,44 +603,6 @@ static void smsc95xx_status(struct usbnet *dev, struct urb *urb) intdata); } -static void set_carrier(struct usbnet *dev, bool link) -{ - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - - if (pdata->link_ok == link) - return; - - pdata->link_ok = link; - - if (link) - usbnet_link_change(dev, 1, 0); - else - usbnet_link_change(dev, 0, 0); -} - -static void check_carrier(struct work_struct *work) -{ - struct smsc95xx_priv *pdata = container_of(work, struct smsc95xx_priv, - carrier_check.work); - struct usbnet *dev = pdata->dev; - int ret; - - if (pdata->suspend_flags != 0) - return; - - ret = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, MII_BMSR); - if (ret < 0) { - netdev_warn(dev->net, "Failed to read MII_BMSR\n"); - return; - } - if (ret & BMSR_LSTATUS) - set_carrier(dev, 1); - else - set_carrier(dev, 0); - - schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); -} - /* Enable or disable Tx & Rx checksum offload engines */ static int smsc95xx_set_features(struct net_device *netdev, netdev_features_t features) @@ -747,7 +696,7 @@ static void smsc95xx_ethtool_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) { struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; wolinfo->supported = SUPPORTED_WAKE; wolinfo->wolopts = pdata->wolopts; @@ -757,7 +706,7 @@ static int smsc95xx_ethtool_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) { struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; int ret; if (wolinfo->wolopts & ~SUPPORTED_WAKE) @@ -772,108 +721,15 @@ static int smsc95xx_ethtool_set_wol(struct net_device *net, return ret; } -static int get_mdix_status(struct net_device *net) -{ - struct usbnet *dev = netdev_priv(net); - u32 val; - int buf; - - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, SPECIAL_CTRL_STS); - if (buf & SPECIAL_CTRL_STS_OVRRD_AMDIX_) { - if (buf & SPECIAL_CTRL_STS_AMDIX_ENABLE_) - return ETH_TP_MDI_AUTO; - else if (buf & SPECIAL_CTRL_STS_AMDIX_STATE_) - return ETH_TP_MDI_X; - } else { - buf = smsc95xx_read_reg(dev, STRAP_STATUS, &val); - if (val & STRAP_STATUS_AMDIX_EN_) - return ETH_TP_MDI_AUTO; - } - - return ETH_TP_MDI; -} - -static void set_mdix_status(struct net_device *net, __u8 mdix_ctrl) -{ - struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - int buf; - - if ((pdata->chip_id == ID_REV_CHIP_ID_9500A_) || - (pdata->chip_id == ID_REV_CHIP_ID_9530_) || - (pdata->chip_id == ID_REV_CHIP_ID_89530_) || - (pdata->chip_id == ID_REV_CHIP_ID_9730_)) { - /* Extend Manual AutoMDIX timer for 9500A/9500Ai */ - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, - PHY_EDPD_CONFIG); - buf |= PHY_EDPD_CONFIG_EXT_CROSSOVER_; - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, - PHY_EDPD_CONFIG, buf); - } - - if (mdix_ctrl == ETH_TP_MDI) { - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS); - buf |= SPECIAL_CTRL_STS_OVRRD_AMDIX_; - buf &= ~(SPECIAL_CTRL_STS_AMDIX_ENABLE_ | - SPECIAL_CTRL_STS_AMDIX_STATE_); - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS, buf); - } else if (mdix_ctrl == ETH_TP_MDI_X) { - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS); - buf |= SPECIAL_CTRL_STS_OVRRD_AMDIX_; - buf &= ~(SPECIAL_CTRL_STS_AMDIX_ENABLE_ | - SPECIAL_CTRL_STS_AMDIX_STATE_); - buf |= SPECIAL_CTRL_STS_AMDIX_STATE_; - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS, buf); - } else if (mdix_ctrl == ETH_TP_MDI_AUTO) { - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS); - buf &= ~SPECIAL_CTRL_STS_OVRRD_AMDIX_; - buf &= ~(SPECIAL_CTRL_STS_AMDIX_ENABLE_ | - SPECIAL_CTRL_STS_AMDIX_STATE_); - buf |= SPECIAL_CTRL_STS_AMDIX_ENABLE_; - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS, buf); - } - pdata->mdix_ctrl = mdix_ctrl; -} - -static int smsc95xx_get_link_ksettings(struct net_device *net, - struct ethtool_link_ksettings *cmd) +static u32 smsc95xx_get_link(struct net_device *net) { - struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - int retval; - - retval = usbnet_get_link_ksettings(net, cmd); - - cmd->base.eth_tp_mdix = pdata->mdix_ctrl; - cmd->base.eth_tp_mdix_ctrl = pdata->mdix_ctrl; - - return retval; -} - -static int smsc95xx_set_link_ksettings(struct net_device *net, - const struct ethtool_link_ksettings *cmd) -{ - struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - int retval; - - if (pdata->mdix_ctrl != cmd->base.eth_tp_mdix_ctrl) - set_mdix_status(net, cmd->base.eth_tp_mdix_ctrl); - - retval = usbnet_set_link_ksettings(net, cmd); - - return retval; + phy_read_status(net->phydev); + return net->phydev->link; } static const struct ethtool_ops smsc95xx_ethtool_ops = { - .get_link = usbnet_get_link, - .nway_reset = usbnet_nway_reset, + .get_link = smsc95xx_get_link, + .nway_reset = phy_ethtool_nway_reset, .get_drvinfo = usbnet_get_drvinfo, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, @@ -884,19 +740,17 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .get_regs = smsc95xx_ethtool_getregs, .get_wol = smsc95xx_ethtool_get_wol, .set_wol = smsc95xx_ethtool_set_wol, - .get_link_ksettings = smsc95xx_get_link_ksettings, - .set_link_ksettings = smsc95xx_set_link_ksettings, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_ts_info = ethtool_op_get_ts_info, }; static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) { - struct usbnet *dev = netdev_priv(netdev); - if (!netif_running(netdev)) return -EINVAL; - return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL); + return phy_mii_ioctl(netdev->phydev, rq, cmd); } static void smsc95xx_init_mac_address(struct usbnet *dev) @@ -942,7 +796,7 @@ static int smsc95xx_set_mac_address(struct usbnet *dev) /* starts the TX path */ static int smsc95xx_start_tx_path(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; unsigned long flags; int ret; @@ -962,7 +816,7 @@ static int smsc95xx_start_tx_path(struct usbnet *dev) /* Starts the Receive path */ static int smsc95xx_start_rx_path(struct usbnet *dev, int in_pm) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; unsigned long flags; spin_lock_irqsave(&pdata->mac_cr_lock, flags); @@ -972,54 +826,9 @@ static int smsc95xx_start_rx_path(struct usbnet *dev, int in_pm) return __smsc95xx_write_reg(dev, MAC_CR, pdata->mac_cr, in_pm); } -static int smsc95xx_phy_initialize(struct usbnet *dev) -{ - int bmcr, ret, timeout = 0; - - /* Initialize MII structure */ - dev->mii.dev = dev->net; - dev->mii.mdio_read = smsc95xx_mdio_read; - dev->mii.mdio_write = smsc95xx_mdio_write; - dev->mii.phy_id_mask = 0x1f; - dev->mii.reg_num_mask = 0x1f; - dev->mii.phy_id = SMSC95XX_INTERNAL_PHY_ID; - - /* reset phy and wait for reset to complete */ - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, MII_BMCR, BMCR_RESET); - - do { - msleep(10); - bmcr = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, MII_BMCR); - timeout++; - } while ((bmcr & BMCR_RESET) && (timeout < 100)); - - if (timeout >= 100) { - netdev_warn(dev->net, "timeout on PHY Reset"); - return -EIO; - } - - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE, - ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP | - ADVERTISE_PAUSE_ASYM); - - /* read to clear */ - ret = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, PHY_INT_SRC); - if (ret < 0) { - netdev_warn(dev->net, "Failed to read PHY_INT_SRC during init\n"); - return ret; - } - - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, PHY_INT_MASK, - PHY_INT_MASK_DEFAULT_); - mii_nway_restart(&dev->mii); - - netif_dbg(dev, ifup, dev->net, "phy initialised successfully\n"); - return 0; -} - static int smsc95xx_reset(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 read_buf, write_buf, burst_cap; int ret = 0, timeout; @@ -1198,12 +1007,6 @@ static int smsc95xx_reset(struct usbnet *dev) smsc95xx_set_multicast(dev->net); - ret = smsc95xx_phy_initialize(dev); - if (ret < 0) { - netdev_warn(dev->net, "Failed to init PHY\n"); - return ret; - } - ret = smsc95xx_read_reg(dev, INT_EP_CTL, &read_buf); if (ret < 0) return ret; @@ -1247,7 +1050,8 @@ static const struct net_device_ops smsc95xx_netdev_ops = { static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) { - struct smsc95xx_priv *pdata = NULL; + struct smsc95xx_priv *pdata; + bool is_internal_phy; u32 val; int ret; @@ -1259,13 +1063,12 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) return ret; } - dev->data[0] = (unsigned long)kzalloc(sizeof(struct smsc95xx_priv), - GFP_KERNEL); - - pdata = (struct smsc95xx_priv *)(dev->data[0]); + pdata = kzalloc(sizeof(*pdata), GFP_KERNEL); if (!pdata) return -ENOMEM; + dev->driver_priv = pdata; + spin_lock_init(&pdata->mac_cr_lock); /* LAN95xx devices do not alter the computed checksum of 0 to 0xffff. @@ -1290,15 +1093,50 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) if (ret) goto free_pdata; + pdata->mdiobus = mdiobus_alloc(); + if (!pdata->mdiobus) { + ret = -ENOMEM; + goto free_pdata; + } + + ret = smsc95xx_read_reg(dev, HW_CFG, &val); + if (ret < 0) + goto free_mdio; + + is_internal_phy = !(val & HW_CFG_PSEL_); + if (is_internal_phy) + pdata->mdiobus->phy_mask = ~(1u << SMSC95XX_INTERNAL_PHY_ID); + + pdata->mdiobus->priv = dev; + pdata->mdiobus->read = smsc95xx_mdiobus_read; + pdata->mdiobus->write = smsc95xx_mdiobus_write; + pdata->mdiobus->name = "smsc95xx-mdiobus"; + pdata->mdiobus->parent = &dev->udev->dev; + + snprintf(pdata->mdiobus->id, ARRAY_SIZE(pdata->mdiobus->id), + "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); + + ret = mdiobus_register(pdata->mdiobus); + if (ret) { + netdev_err(dev->net, "Could not register MDIO bus\n"); + goto free_mdio; + } + + pdata->phydev = phy_find_first(pdata->mdiobus); + if (!pdata->phydev) { + netdev_err(dev->net, "no PHY found\n"); + ret = -ENODEV; + goto unregister_mdio; + } + + pdata->phydev->is_internal = is_internal_phy; + /* detect device revision as different features may be available */ ret = smsc95xx_read_reg(dev, ID_REV, &val); if (ret < 0) - goto free_pdata; + goto unregister_mdio; val >>= 16; - pdata->chip_id = val; - pdata->mdix_ctrl = get_mdix_status(dev->net); - if ((val == ID_REV_CHIP_ID_9500A_) || (val == ID_REV_CHIP_ID_9530_) || (val == ID_REV_CHIP_ID_89530_) || (val == ID_REV_CHIP_ID_9730_)) pdata->features = (FEATURE_8_WAKEUP_FILTERS | @@ -1314,12 +1152,13 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->min_mtu = ETH_MIN_MTU; dev->net->max_mtu = ETH_DATA_LEN; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; + return 0; - pdata->dev = dev; - INIT_DELAYED_WORK(&pdata->carrier_check, check_carrier); - schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); +unregister_mdio: + mdiobus_unregister(pdata->mdiobus); - return 0; +free_mdio: + mdiobus_free(pdata->mdiobus); free_pdata: kfree(pdata); @@ -1328,15 +1167,47 @@ free_pdata: static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - - if (pdata) { - cancel_delayed_work_sync(&pdata->carrier_check); - netif_dbg(dev, ifdown, dev->net, "free pdata\n"); - kfree(pdata); - pdata = NULL; - dev->data[0] = 0; + struct smsc95xx_priv *pdata = dev->driver_priv; + + mdiobus_unregister(pdata->mdiobus); + mdiobus_free(pdata->mdiobus); + netif_dbg(dev, ifdown, dev->net, "free pdata\n"); + kfree(pdata); +} + +static void smsc95xx_handle_link_change(struct net_device *net) +{ + phy_print_status(net->phydev); +} + +static int smsc95xx_start_phy(struct usbnet *dev) +{ + struct smsc95xx_priv *pdata = dev->driver_priv; + struct net_device *net = dev->net; + int ret; + + ret = smsc95xx_reset(dev); + if (ret < 0) + return ret; + + ret = phy_connect_direct(net, pdata->phydev, + &smsc95xx_handle_link_change, + PHY_INTERFACE_MODE_MII); + if (ret) { + netdev_err(net, "can't attach PHY to %s\n", pdata->mdiobus->id); + return ret; } + + phy_attached_info(net->phydev); + phy_start(net->phydev); + return 0; +} + +static int smsc95xx_disconnect_phy(struct usbnet *dev) +{ + phy_stop(dev->net->phydev); + phy_disconnect(dev->net->phydev); + return 0; } static u32 smsc_crc(const u8 *buffer, size_t len, int filter) @@ -1347,39 +1218,37 @@ static u32 smsc_crc(const u8 *buffer, size_t len, int filter) static int smsc95xx_enable_phy_wakeup_interrupts(struct usbnet *dev, u16 mask) { - struct mii_if_info *mii = &dev->mii; int ret; netdev_dbg(dev->net, "enabling PHY wakeup interrupts\n"); /* read to clear */ - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, PHY_INT_SRC); + ret = smsc95xx_mdio_read_nopm(dev, PHY_INT_SRC); if (ret < 0) return ret; /* enable interrupt source */ - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, PHY_INT_MASK); + ret = smsc95xx_mdio_read_nopm(dev, PHY_INT_MASK); if (ret < 0) return ret; ret |= mask; - smsc95xx_mdio_write_nopm(dev->net, mii->phy_id, PHY_INT_MASK, ret); + smsc95xx_mdio_write_nopm(dev, PHY_INT_MASK, ret); return 0; } static int smsc95xx_link_ok_nopm(struct usbnet *dev) { - struct mii_if_info *mii = &dev->mii; int ret; /* first, a dummy read, needed to latch some MII phys */ - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, MII_BMSR); + ret = smsc95xx_mdio_read_nopm(dev, MII_BMSR); if (ret < 0) return ret; - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, MII_BMSR); + ret = smsc95xx_mdio_read_nopm(dev, MII_BMSR); if (ret < 0) return ret; @@ -1388,7 +1257,7 @@ static int smsc95xx_link_ok_nopm(struct usbnet *dev) static int smsc95xx_enter_suspend0(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val; int ret; @@ -1427,8 +1296,7 @@ static int smsc95xx_enter_suspend0(struct usbnet *dev) static int smsc95xx_enter_suspend1(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - struct mii_if_info *mii = &dev->mii; + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val; int ret; @@ -1436,17 +1304,17 @@ static int smsc95xx_enter_suspend1(struct usbnet *dev) * compatibility with non-standard link partners */ if (pdata->features & FEATURE_PHY_NLP_CROSSOVER) - smsc95xx_mdio_write_nopm(dev->net, mii->phy_id, PHY_EDPD_CONFIG, - PHY_EDPD_CONFIG_DEFAULT); + smsc95xx_mdio_write_nopm(dev, PHY_EDPD_CONFIG, + PHY_EDPD_CONFIG_DEFAULT); /* enable energy detect power-down mode */ - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, PHY_MODE_CTRL_STS); + ret = smsc95xx_mdio_read_nopm(dev, PHY_MODE_CTRL_STS); if (ret < 0) return ret; ret |= MODE_CTRL_STS_EDPWRDOWN_; - smsc95xx_mdio_write_nopm(dev->net, mii->phy_id, PHY_MODE_CTRL_STS, ret); + smsc95xx_mdio_write_nopm(dev, PHY_MODE_CTRL_STS, ret); /* enter SUSPEND1 mode */ ret = smsc95xx_read_reg_nopm(dev, PM_CTRL, &val); @@ -1475,7 +1343,7 @@ static int smsc95xx_enter_suspend1(struct usbnet *dev) static int smsc95xx_enter_suspend2(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val; int ret; @@ -1497,7 +1365,7 @@ static int smsc95xx_enter_suspend2(struct usbnet *dev) static int smsc95xx_enter_suspend3(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val; int ret; @@ -1536,7 +1404,7 @@ static int smsc95xx_enter_suspend3(struct usbnet *dev) static int smsc95xx_autosuspend(struct usbnet *dev, u32 link_up) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; int ret; if (!netif_running(dev->net)) { @@ -1584,7 +1452,7 @@ static int smsc95xx_autosuspend(struct usbnet *dev, u32 link_up) static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message) { struct usbnet *dev = usb_get_intfdata(intf); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val, link_up; int ret; @@ -1594,8 +1462,6 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message) return ret; } - cancel_delayed_work_sync(&pdata->carrier_check); - if (pdata->suspend_flags) { netdev_warn(dev->net, "error during last resume\n"); pdata->suspend_flags = 0; @@ -1839,10 +1705,6 @@ done: if (ret && PMSG_IS_AUTO(message)) usbnet_resume(intf); - if (ret) - schedule_delayed_work(&pdata->carrier_check, - CARRIER_CHECK_DELAY); - return ret; } @@ -1855,14 +1717,13 @@ static int smsc95xx_resume(struct usb_interface *intf) u32 val; BUG_ON(!dev); - pdata = (struct smsc95xx_priv *)(dev->data[0]); + pdata = dev->driver_priv; suspend_flags = pdata->suspend_flags; netdev_dbg(dev->net, "resume suspend_flags=0x%02x\n", suspend_flags); /* do this first to ensure it's cleared even in error case */ pdata->suspend_flags = 0; - schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); if (suspend_flags & SUSPEND_ALLMODES) { /* clear wake-up sources */ @@ -1893,6 +1754,7 @@ static int smsc95xx_resume(struct usb_interface *intf) if (ret < 0) netdev_warn(dev->net, "usbnet_resume error\n"); + phy_init_hw(pdata->phydev); return ret; } @@ -2075,7 +1937,7 @@ static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev, static int smsc95xx_manage_power(struct usbnet *dev, int on) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; dev->intf->needs_remote_wakeup = on; @@ -2098,7 +1960,8 @@ static const struct driver_info smsc95xx_info = { .bind = smsc95xx_bind, .unbind = smsc95xx_unbind, .link_reset = smsc95xx_link_reset, - .reset = smsc95xx_reset, + .reset = smsc95xx_start_phy, + .stop = smsc95xx_disconnect_phy, .rx_fixup = smsc95xx_rx_fixup, .tx_fixup = smsc95xx_tx_fixup, .status = smsc95xx_status, diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index e45935a5856a..2b2a841cd938 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -110,7 +110,7 @@ int usbnet_get_endpoints(struct usbnet *dev, struct usb_interface *intf) if (!usb_endpoint_dir_in(&e->desc)) continue; intr = 1; - /* FALLTHROUGH */ + fallthrough; case USB_ENDPOINT_XFER_BULK: break; default: @@ -628,7 +628,7 @@ block: /* data overrun ... flush fifo? */ case -EOVERFLOW: dev->net->stats.rx_over_errors++; - // FALLTHROUGH + fallthrough; default: state = rx_cleanup; @@ -1530,7 +1530,7 @@ static void usbnet_bh (struct timer_list *t) continue; case tx_done: kfree(entry->urb->sg); - /* fall through */ + fallthrough; case rx_cleanup: usb_free_urb (entry->urb); dev_kfree_skb (skb); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index e56cd562a664..091e5b4ba042 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -234,14 +234,14 @@ static bool veth_is_xdp_frame(void *ptr) return (unsigned long)ptr & VETH_XDP_FLAG; } -static void *veth_ptr_to_xdp(void *ptr) +static struct xdp_frame *veth_ptr_to_xdp(void *ptr) { return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG); } -static void *veth_xdp_to_ptr(void *ptr) +static void *veth_xdp_to_ptr(struct xdp_frame *xdp) { - return (void *)((unsigned long)ptr | VETH_XDP_FLAG); + return (void *)((unsigned long)xdp | VETH_XDP_FLAG); } static void veth_ptr_free(void *ptr) @@ -610,10 +610,10 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); - /* fall through */ + fallthrough; case XDP_DROP: stats->xdp_drops++; goto err_xdp; @@ -745,10 +745,10 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); - /* fall through */ + fallthrough; case XDP_DROP: stats->xdp_drops++; goto xdp_drop; @@ -897,14 +897,13 @@ static void veth_napi_del(struct net_device *dev) struct veth_rq *rq = &priv->rq[i]; napi_disable(&rq->xdp_napi); - napi_hash_del(&rq->xdp_napi); + __netif_napi_del(&rq->xdp_napi); } synchronize_net(); for (i = 0; i < dev->real_num_rx_queues; i++) { struct veth_rq *rq = &priv->rq[i]; - netif_napi_del(&rq->xdp_napi); rq->rx_notify_masked = false; ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free); } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0ada48edf749..7145c83c6c8c 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -724,7 +724,7 @@ static struct sk_buff *receive_small(struct net_device *dev, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(vi->dev, xdp_prog, act); case XDP_DROP: @@ -922,10 +922,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(vi->dev, xdp_prog, act); - /* fall through */ + fallthrough; case XDP_DROP: if (unlikely(xdp_page != page)) __free_pages(xdp_page, 0); @@ -2604,12 +2604,11 @@ static void virtnet_free_queues(struct virtnet_info *vi) int i; for (i = 0; i < vi->max_queue_pairs; i++) { - napi_hash_del(&vi->rq[i].napi); - netif_napi_del(&vi->rq[i].napi); - netif_napi_del(&vi->sq[i].napi); + __netif_napi_del(&vi->rq[i].napi); + __netif_napi_del(&vi->sq[i].napi); } - /* We called napi_hash_del() before netif_napi_del(), + /* We called __netif_napi_del(), * we need to respect an RCU grace period before freeing vi->rq */ synchronize_net(); diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index def27afa1c69..1014693a5ceb 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -743,7 +743,7 @@ vmxnet3_get_rss_hash_opts(struct vmxnet3_adapter *adapter, case ESP_V4_FLOW: if (rss_fields & VMXNET3_RSS_FIELDS_ESPIP4) info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - /* fallthrough */ + fallthrough; case SCTP_V4_FLOW: case IPV4_FLOW: info->data |= RXH_IP_SRC | RXH_IP_DST; diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c index 7bcee41905cf..3ca4daf63389 100644 --- a/drivers/net/wan/dlci.c +++ b/drivers/net/wan/dlci.c @@ -295,14 +295,13 @@ static int dlci_close(struct net_device *dev) { struct dlci_local *dlp; struct frad_local *flp; - int err; netif_stop_queue(dev); dlp = netdev_priv(dev); flp = netdev_priv(dlp->slave); - err = (*flp->deactivate)(dlp->slave, dev); + (*flp->deactivate)(dlp->slave, dev); return 0; } diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 9edd94679283..dca97cd7c4e7 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -1295,3 +1295,4 @@ static struct platform_driver ucc_hdlc_driver = { module_platform_driver(ucc_hdlc_driver); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION(DRV_DESC); diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index dfc16770458d..9b00708676cf 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -229,7 +229,8 @@ static void hdlc_setup_dev(struct net_device *dev) dev->min_mtu = 68; dev->max_mtu = HDLC_MAX_MTU; dev->type = ARPHRD_RAWHDLC; - dev->hard_header_len = 16; + dev->hard_header_len = 0; + dev->needed_headroom = 0; dev->addr_len = 0; dev->header_ops = &hdlc_null_ops; } diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index d8cba3625c18..444130655d8e 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -370,6 +370,7 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr) memcpy(&state(hdlc)->settings, &new_settings, size); spin_lock_init(&state(hdlc)->lock); dev->header_ops = &cisco_header_ops; + dev->hard_header_len = sizeof(struct hdlc_header); dev->type = ARPHRD_CISCO; call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev); netif_dormant_on(dev); diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index f70336bb6f52..f52b9fed0593 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -107,8 +107,14 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) { int result; + /* There should be a pseudo header of 1 byte added by upper layers. + * Check to make sure it is there before reading it. + */ + if (skb->len < 1) { + kfree_skb(skb); + return NETDEV_TX_OK; + } - /* X.25 to LAPB */ switch (skb->data[0]) { case X25_IFACE_DATA: /* Data to be transmitted */ skb_pull(skb, 1); @@ -294,6 +300,15 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return result; memcpy(&state(hdlc)->settings, &new_settings, size); + + /* There's no header_ops so hard_header_len should be 0. */ + dev->hard_header_len = 0; + /* When transmitting data: + * first we'll remove a pseudo header of 1 byte, + * then we'll prepend an LAPB header of at most 3 bytes. + */ + dev->needed_headroom = 3 - 1; + dev->type = ARPHRD_X25; call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev); netif_dormant_off(dev); diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 1ea15f2123ed..732a6c1851f5 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -173,7 +173,7 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb, case X25_IFACE_DISCONNECT: if ((err = lapb_disconnect_request(dev)) != LAPB_OK) pr_err("lapb_disconnect_request err: %d\n", err); - /* Fall thru */ + fallthrough; default: goto drop; } @@ -210,6 +210,8 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) skb->dev = dev = lapbeth->ethdev; + skb_reset_network_header(skb); + dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0); dev_queue_xmit(skb); @@ -340,6 +342,7 @@ static int lapbeth_new_device(struct net_device *dev) */ ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len + dev->needed_headroom; + ndev->needed_tailroom = dev->needed_tailroom; lapbeth = netdev_priv(ndev); lapbeth->axdev = ndev; diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c index 40c04ea1200a..2fde439543fb 100644 --- a/drivers/net/wan/sbni.c +++ b/drivers/net/wan/sbni.c @@ -260,11 +260,12 @@ static int __init sbni_init(struct net_device *dev) return sbni_isa_probe( dev ); /* otherwise we have to perform search our adapter */ - if( io[ num ] != -1 ) - dev->base_addr = io[ num ], + if( io[ num ] != -1 ) { + dev->base_addr = io[ num ]; dev->irq = irq[ num ]; - else if( scandone || io[ 0 ] != -1 ) + } else if( scandone || io[ 0 ] != -1 ) { return -ENODEV; + } /* if io[ num ] contains non-zero address, then that is on ISA bus */ if( dev->base_addr ) @@ -399,12 +400,13 @@ sbni_probe1( struct net_device *dev, unsigned long ioaddr, int irq ) nl->maxframe = DEFAULT_FRAME_LEN; nl->csr1.rate = baud[ num ]; - if( (nl->cur_rxl_index = rxl[ num ]) == -1 ) + if( (nl->cur_rxl_index = rxl[ num ]) == -1 ) { /* autotune rxl */ - nl->cur_rxl_index = DEF_RXL, + nl->cur_rxl_index = DEF_RXL; nl->delta_rxl = DEF_RXL_DELTA; - else + } else { nl->delta_rxl = 0; + } nl->csr1.rxl = rxl_tab[ nl->cur_rxl_index ]; if( inb( ioaddr + CSR0 ) & 0x01 ) nl->state |= FL_SLOW_MODE; @@ -512,13 +514,15 @@ sbni_interrupt( int irq, void *dev_id ) do { repeat = 0; - if( inb( dev->base_addr + CSR0 ) & (RC_RDY | TR_RDY) ) - handle_channel( dev ), + if( inb( dev->base_addr + CSR0 ) & (RC_RDY | TR_RDY) ) { + handle_channel( dev ); repeat = 1; + } if( nl->second && /* second channel present */ - (inb( nl->second->base_addr+CSR0 ) & (RC_RDY | TR_RDY)) ) - handle_channel( nl->second ), + (inb( nl->second->base_addr+CSR0 ) & (RC_RDY | TR_RDY)) ) { + handle_channel( nl->second ); repeat = 1; + } } while( repeat ); if( nl->second ) @@ -610,11 +614,12 @@ recv_frame( struct net_device *dev ) nl->state |= FL_PREV_OK; if( framelen > 4 ) nl->in_stats.all_rx_number++; - } else - nl->state &= ~FL_PREV_OK, - change_level( dev ), - nl->in_stats.all_rx_number++, + } else { + nl->state &= ~FL_PREV_OK; + change_level( dev ); + nl->in_stats.all_rx_number++; nl->in_stats.bad_rx_number++; + } return !frame_ok || framelen > 4; } @@ -689,9 +694,10 @@ download_data( struct net_device *dev, u32 *crc_p ) *crc_p = calc_crc32( *crc_p, skb->data + nl->outpos, len ); /* if packet too short we should write some more bytes to pad */ - for( len = nl->framelen - len; len--; ) - outb( 0, dev->base_addr + DAT ), + for( len = nl->framelen - len; len--; ) { + outb( 0, dev->base_addr + DAT ); *crc_p = CRC32( 0, *crc_p ); + } } @@ -703,9 +709,10 @@ upload_data( struct net_device *dev, unsigned framelen, unsigned frameno, int frame_ok; - if( is_first ) - nl->wait_frameno = frameno, + if( is_first ) { + nl->wait_frameno = frameno; nl->inppos = 0; + } if( nl->wait_frameno == frameno ) { @@ -717,33 +724,35 @@ upload_data( struct net_device *dev, unsigned framelen, unsigned frameno, * error was occurred... drop entire packet */ else if( (frame_ok = skip_tail( dev->base_addr, framelen, crc )) - != 0 ) - nl->wait_frameno = 0, - nl->inppos = 0, + != 0 ) { + nl->wait_frameno = 0; + nl->inppos = 0; #ifdef CONFIG_SBNI_MULTILINE - nl->master->stats.rx_errors++, + nl->master->stats.rx_errors++; nl->master->stats.rx_missed_errors++; #else - dev->stats.rx_errors++, + dev->stats.rx_errors++; dev->stats.rx_missed_errors++; #endif + } /* now skip all frames until is_first != 0 */ } else frame_ok = skip_tail( dev->base_addr, framelen, crc ); - if( is_first && !frame_ok ) + if( is_first && !frame_ok ) { /* * Frame has been broken, but we had already stored * is_first... Drop entire packet. */ - nl->wait_frameno = 0, + nl->wait_frameno = 0; #ifdef CONFIG_SBNI_MULTILINE - nl->master->stats.rx_errors++, + nl->master->stats.rx_errors++; nl->master->stats.rx_crc_errors++; #else - dev->stats.rx_errors++, + dev->stats.rx_errors++; dev->stats.rx_crc_errors++; #endif + } return frame_ok; } @@ -782,17 +791,18 @@ interpret_ack( struct net_device *dev, unsigned ack ) if( nl->state & FL_WAIT_ACK ) { nl->outpos += nl->framelen; - if( --nl->tx_frameno ) + if( --nl->tx_frameno ) { nl->framelen = min_t(unsigned int, nl->maxframe, nl->tx_buf_p->len - nl->outpos); - else - send_complete( dev ), + } else { + send_complete( dev ); #ifdef CONFIG_SBNI_MULTILINE netif_wake_queue( nl->master ); #else netif_wake_queue( dev ); #endif + } } } @@ -872,16 +882,17 @@ drop_xmit_queue( struct net_device *dev ) { struct net_local *nl = netdev_priv(dev); - if( nl->tx_buf_p ) - dev_kfree_skb_any( nl->tx_buf_p ), - nl->tx_buf_p = NULL, + if( nl->tx_buf_p ) { + dev_kfree_skb_any( nl->tx_buf_p ); + nl->tx_buf_p = NULL; #ifdef CONFIG_SBNI_MULTILINE - nl->master->stats.tx_errors++, + nl->master->stats.tx_errors++; nl->master->stats.tx_carrier_errors++; #else - dev->stats.tx_errors++, + dev->stats.tx_errors++; dev->stats.tx_carrier_errors++; #endif + } nl->tx_frameno = 0; nl->framelen = 0; @@ -1327,12 +1338,13 @@ sbni_ioctl( struct net_device *dev, struct ifreq *ifr, int cmd ) spin_lock( &nl->lock ); flags = *(struct sbni_flags*) &ifr->ifr_ifru; - if( flags.fixed_rxl ) - nl->delta_rxl = 0, + if( flags.fixed_rxl ) { + nl->delta_rxl = 0; nl->cur_rxl_index = flags.rxl; - else - nl->delta_rxl = DEF_RXL_DELTA, + } else { + nl->delta_rxl = DEF_RXL_DELTA; nl->cur_rxl_index = DEF_RXL; + } nl->csr1.rxl = rxl_tab[ nl->cur_rxl_index ]; nl->csr1.rate = flags.rate; @@ -1526,13 +1538,16 @@ sbni_setup( char *p ) (*dest[ parm ])[ n ] = simple_strtol( p, &p, 0 ); if( !*p || *p == ')' ) return 1; - if( *p == ';' ) - ++p, ++n, parm = 0; - else if( *p++ != ',' ) + if( *p == ';' ) { + ++p; + ++n; + parm = 0; + } else if( *p++ != ',' ) { break; - else + } else { if( ++parm >= 5 ) break; + } } bad_param: pr_err("Error in sbni kernel parameter!\n"); diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c index 77ccf3672ede..bc2c1c7fb1a4 100644 --- a/drivers/net/wan/sdla.c +++ b/drivers/net/wan/sdla.c @@ -413,7 +413,7 @@ static void sdla_errors(struct net_device *dev, int cmd, int dlci, int ret, int case SDLA_RET_NO_BUFS: if (cmd == SDLA_INFORMATION_WRITE) break; - /* Else, fall through */ + fallthrough; default: netdev_dbg(dev, "Cmd 0x%02X generated return code 0x%02X\n", diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c index 29053bec694e..8e3b1c717c10 100644 --- a/drivers/net/wan/slic_ds26522.c +++ b/drivers/net/wan/slic_ds26522.c @@ -22,8 +22,6 @@ #include <linux/io.h> #include "slic_ds26522.h" -#define DRV_NAME "ds26522" - #define SLIC_TRANS_LEN 1 #define SLIC_TWO_LEN 2 #define SLIC_THREE_LEN 3 diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index de7984463595..7ee980575208 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -330,7 +330,7 @@ static netdev_tx_t x25_asy_xmit(struct sk_buff *skb, if (err != LAPB_OK) netdev_err(dev, "lapb_disconnect_request error: %d\n", err); - /* fall through */ + fallthrough; default: kfree_skb(skb); return NETDEV_TX_OK; diff --git a/drivers/net/wimax/i2400m/control.c b/drivers/net/wimax/i2400m/control.c index 4fe7c7e132c4..8df98757d901 100644 --- a/drivers/net/wimax/i2400m/control.c +++ b/drivers/net/wimax/i2400m/control.c @@ -352,7 +352,7 @@ void i2400m_report_tlv_system_state(struct i2400m *i2400m, case I2400M_SS_IDLE: d_printf(1, dev, "entering BS-negotiated idle mode\n"); - /* Fall through */ + fallthrough; case I2400M_SS_DISCONNECTING: case I2400M_SS_DATA_PATH_CONNECTED: wimax_state_change(wimax_dev, WIMAX_ST_CONNECTED); @@ -656,8 +656,6 @@ void i2400m_msg_to_dev_cancel_wait(struct i2400m *i2400m, int code) * * @i2400m: device descriptor * - * @msg_skb: an skb * - * * @buf: pointer to the buffer containing the message to be sent; it * has to start with a &struct i2400M_l3l4_hdr and then * followed by the payload. Once this function returns, the diff --git a/drivers/net/wimax/i2400m/usb-fw.c b/drivers/net/wimax/i2400m/usb-fw.c index 1f7709d24f35..27ab233650d5 100644 --- a/drivers/net/wimax/i2400m/usb-fw.c +++ b/drivers/net/wimax/i2400m/usb-fw.c @@ -135,7 +135,7 @@ retry: msleep(10); /* give the device some time */ goto retry; } - /* fall through */ + fallthrough; case -EINVAL: /* while removing driver */ case -ENODEV: /* dev disconnect ... */ case -ENOENT: /* just ignore it */ diff --git a/drivers/net/wimax/i2400m/usb-tx.c b/drivers/net/wimax/i2400m/usb-tx.c index 3a0e7226768a..3ba9d70cca1b 100644 --- a/drivers/net/wimax/i2400m/usb-tx.c +++ b/drivers/net/wimax/i2400m/usb-tx.c @@ -136,7 +136,7 @@ retry: msleep(10); /* give the device some time */ goto retry; } - /* fall through */ + fallthrough; case -EINVAL: /* while removing driver */ case -ENODEV: /* dev disconnect ... */ case -ENOENT: /* just ignore it */ diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c index 9659f9e1aaa6..b684e97ac976 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/net/wimax/i2400m/usb.c @@ -195,7 +195,7 @@ retry: msleep(10); /* give the device some time */ goto retry; } - /* fall through */ + fallthrough; case -EINVAL: /* while removing driver */ case -ENODEV: /* dev disconnect ... */ case -ENOENT: /* just ignore it */ diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 20a4f3c0a0a1..d0f3b6d7f408 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -22,8 +22,8 @@ static struct genl_family genl_family; static const struct nla_policy device_policy[WGDEVICE_A_MAX + 1] = { [WGDEVICE_A_IFINDEX] = { .type = NLA_U32 }, [WGDEVICE_A_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, - [WGDEVICE_A_PRIVATE_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN }, - [WGDEVICE_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN }, + [WGDEVICE_A_PRIVATE_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN), + [WGDEVICE_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN), [WGDEVICE_A_FLAGS] = { .type = NLA_U32 }, [WGDEVICE_A_LISTEN_PORT] = { .type = NLA_U16 }, [WGDEVICE_A_FWMARK] = { .type = NLA_U32 }, @@ -31,12 +31,12 @@ static const struct nla_policy device_policy[WGDEVICE_A_MAX + 1] = { }; static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = { - [WGPEER_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN }, - [WGPEER_A_PRESHARED_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_SYMMETRIC_KEY_LEN }, + [WGPEER_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN), + [WGPEER_A_PRESHARED_KEY] = NLA_POLICY_EXACT_LEN(NOISE_SYMMETRIC_KEY_LEN), [WGPEER_A_FLAGS] = { .type = NLA_U32 }, - [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) }, + [WGPEER_A_ENDPOINT] = NLA_POLICY_MIN_LEN(sizeof(struct sockaddr)), [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 }, - [WGPEER_A_LAST_HANDSHAKE_TIME] = { .type = NLA_EXACT_LEN, .len = sizeof(struct __kernel_timespec) }, + [WGPEER_A_LAST_HANDSHAKE_TIME] = NLA_POLICY_EXACT_LEN(sizeof(struct __kernel_timespec)), [WGPEER_A_RX_BYTES] = { .type = NLA_U64 }, [WGPEER_A_TX_BYTES] = { .type = NLA_U64 }, [WGPEER_A_ALLOWEDIPS] = { .type = NLA_NESTED }, @@ -45,7 +45,7 @@ static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = { static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = { [WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 }, - [WGALLOWEDIP_A_IPADDR] = { .type = NLA_MIN_LEN, .len = sizeof(struct in_addr) }, + [WGALLOWEDIP_A_IPADDR] = NLA_POLICY_MIN_LEN(sizeof(struct in_addr)), [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 } }; diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 13e5cfe95a75..2e3eb5bbe49c 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -2019,8 +2019,8 @@ static void ath10k_mac_vif_ap_csa_count_down(struct ath10k_vif *arvif) if (!arvif->is_up) return; - if (!ieee80211_csa_is_complete(vif)) { - ieee80211_csa_update_counter(vif); + if (!ieee80211_beacon_cntdwn_is_complete(vif)) { + ieee80211_beacon_update_cntdwn(vif); ret = ath10k_mac_setup_bcn_tmpl(arvif); if (ret) diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index acc0cd3c4a95..1fa7107a5051 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -3879,7 +3879,7 @@ void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb) * actual channel switch is done */ if (arvif->vif->csa_active && - ieee80211_csa_is_complete(arvif->vif)) { + ieee80211_beacon_cntdwn_is_complete(arvif->vif)) { ieee80211_csa_finish(arvif->vif); continue; } diff --git a/drivers/net/wireless/ath/ath11k/thermal.c b/drivers/net/wireless/ath/ath11k/thermal.c index 5a7e150c621b..c96b26f39a25 100644 --- a/drivers/net/wireless/ath/ath11k/thermal.c +++ b/drivers/net/wireless/ath/ath11k/thermal.c @@ -53,7 +53,7 @@ ath11k_thermal_set_cur_throttle_state(struct thermal_cooling_device *cdev, return ret; } -static struct thermal_cooling_device_ops ath11k_thermal_ops = { +static const struct thermal_cooling_device_ops ath11k_thermal_ops = { .get_max_state = ath11k_thermal_get_max_throttle_state, .get_cur_state = ath11k_thermal_get_cur_throttle_state, .set_cur_state = ath11k_thermal_set_cur_throttle_state, diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index d61260efeaf1..adde14a390ec 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -1599,8 +1599,8 @@ int ath11k_wmi_bcn_tmpl(struct ath11k *ar, u32 vdev_id, FIELD_PREP(WMI_TLV_LEN, sizeof(*cmd) - TLV_HDR_SIZE); cmd->vdev_id = vdev_id; cmd->tim_ie_offset = offs->tim_offset; - cmd->csa_switch_count_offset = offs->csa_counter_offs[0]; - cmd->ext_csa_switch_count_offset = offs->csa_counter_offs[1]; + cmd->csa_switch_count_offset = offs->cntdwn_counter_offs[0]; + cmd->ext_csa_switch_count_offset = offs->cntdwn_counter_offs[1]; cmd->buf_len = bcn->len; ptr = skb->data + sizeof(*cmd); diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c index 4876bff2dc2c..71e2ada86793 100644 --- a/drivers/net/wireless/ath/ath9k/beacon.c +++ b/drivers/net/wireless/ath/ath9k/beacon.c @@ -365,7 +365,7 @@ bool ath9k_csa_is_finished(struct ath_softc *sc, struct ieee80211_vif *vif) if (!vif || !vif->csa_active) return false; - if (!ieee80211_csa_is_complete(vif)) + if (!ieee80211_beacon_cntdwn_is_complete(vif)) return false; ieee80211_csa_finish(vif); diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c index f20c839aeda2..c745897aa3d6 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c @@ -514,7 +514,7 @@ bool ath9k_htc_csa_is_finished(struct ath9k_htc_priv *priv) if (!vif || !vif->csa_active) return false; - if (!ieee80211_csa_is_complete(vif)) + if (!ieee80211_beacon_cntdwn_is_complete(vif)) return false; ieee80211_csa_finish(vif); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index b78992e341d5..81bc05d70267 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -1300,8 +1300,8 @@ static void iwl_mvm_csa_count_down(struct iwl_mvm *mvm, mvmvif->csa_countdown = true; - if (!ieee80211_csa_is_complete(csa_vif)) { - int c = ieee80211_csa_update_counter(csa_vif); + if (!ieee80211_beacon_cntdwn_is_complete(csa_vif)) { + int c = ieee80211_beacon_update_cntdwn(csa_vif); iwl_mvm_mac_ctxt_beacon_changed(mvm, csa_vif); if (csa_vif->p2p && @@ -1543,7 +1543,7 @@ void iwl_mvm_probe_resp_data_notif(struct iwl_mvm *mvm, if (notif->csa_counter != IWL_PROBE_RESP_DATA_NO_CSA && notif->csa_counter >= 1) - ieee80211_csa_set_counter(vif, notif->csa_counter); + ieee80211_beacon_set_cntdwn(vif, notif->csa_counter); } void iwl_mvm_channel_switch_noa_notif(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 1babc4bb5194..8abb57012240 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -172,7 +172,7 @@ static void iwl_mvm_csa_noa_start(struct iwl_mvm *mvm) * So we just do nothing here and the switch * will be performed on the last TBTT. */ - if (!ieee80211_csa_is_complete(csa_vif)) { + if (!ieee80211_beacon_cntdwn_is_complete(csa_vif)) { IWL_WARN(mvm, "CSA NOA started too early\n"); goto out_unlock; } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 9dd9d73f4484..dce3bc9c9f84 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1699,7 +1699,7 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac, rcu_dereference(vif->chanctx_conf)->def.chan); } - if (vif->csa_active && ieee80211_csa_is_complete(vif)) + if (vif->csa_active && ieee80211_beacon_cntdwn_is_complete(vif)) ieee80211_csa_finish(vif); } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 3d4bf72700a5..fbfb991ebd90 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -1095,7 +1095,7 @@ EXPORT_SYMBOL_GPL(mt76_get_txpower); static void __mt76_csa_finish(void *priv, u8 *mac, struct ieee80211_vif *vif) { - if (vif->csa_active && ieee80211_csa_is_complete(vif)) + if (vif->csa_active && ieee80211_beacon_cntdwn_is_complete(vif)) ieee80211_csa_finish(vif); } @@ -1120,7 +1120,7 @@ __mt76_csa_check(void *priv, u8 *mac, struct ieee80211_vif *vif) if (!vif->csa_active) return; - dev->csa_complete |= ieee80211_csa_is_complete(vif); + dev->csa_complete |= ieee80211_beacon_cntdwn_is_complete(vif); } void mt76_csa_check(struct mt76_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index d0cbb283982f..084982eb6abd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -650,12 +650,12 @@ mt7615_mcu_add_beacon_offload(struct mt7615_dev *dev, memcpy(req.pkt + MT_TXD_SIZE, skb->data, skb->len); req.pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len); req.tim_ie_pos = cpu_to_le16(MT_TXD_SIZE + offs.tim_offset); - if (offs.csa_counter_offs[0]) { + if (offs.cntdwn_counter_offs[0]) { u16 csa_offs; - csa_offs = MT_TXD_SIZE + offs.csa_counter_offs[0] - 4; + csa_offs = MT_TXD_SIZE + offs.cntdwn_counter_offs[0] - 4; req.csa_ie_pos = cpu_to_le16(csa_offs); - req.csa_cnt = skb->data[offs.csa_counter_offs[0]]; + req.csa_cnt = skb->data[offs.cntdwn_counter_offs[0]]; } dev_kfree_skb(skb); @@ -1713,10 +1713,10 @@ mt7615_mcu_uni_add_beacon_offload(struct mt7615_dev *dev, req.beacon_tlv.pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len); req.beacon_tlv.tim_ie_pos = cpu_to_le16(MT_TXD_SIZE + offs.tim_offset); - if (offs.csa_counter_offs[0]) { + if (offs.cntdwn_counter_offs[0]) { u16 csa_offs; - csa_offs = MT_TXD_SIZE + offs.csa_counter_offs[0] - 4; + csa_offs = MT_TXD_SIZE + offs.cntdwn_counter_offs[0] - 4; req.beacon_tlv.csa_ie_pos = cpu_to_le16(csa_offs); } dev_kfree_skb(skb); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index eaed5ef05401..ac8ec257da03 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -2282,7 +2282,7 @@ mt7915_mcu_beacon_csa(struct sk_buff *rskb, struct sk_buff *skb, struct bss_info_bcn *bcn, struct ieee80211_mutable_offsets *offs) { - if (offs->csa_counter_offs[0]) { + if (offs->cntdwn_counter_offs[0]) { struct tlv *tlv; struct bss_info_bcn_csa *csa; @@ -2290,7 +2290,7 @@ mt7915_mcu_beacon_csa(struct sk_buff *rskb, struct sk_buff *skb, sizeof(*csa), &bcn->sub_ntlv, &bcn->len); csa = (struct bss_info_bcn_csa *)tlv; - csa->cnt = skb->data[offs->csa_counter_offs[0]]; + csa->cnt = skb->data[offs->cntdwn_counter_offs[0]]; } } @@ -2312,8 +2312,8 @@ mt7915_mcu_beacon_cont(struct mt7915_dev *dev, struct sk_buff *rskb, cont->pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len); cont->tim_ofs = cpu_to_le16(offs->tim_offset); - if (offs->csa_counter_offs[0]) - cont->csa_ofs = cpu_to_le16(offs->csa_counter_offs[0] - 4); + if (offs->cntdwn_counter_offs[0]) + cont->csa_ofs = cpu_to_le16(offs->cntdwn_counter_offs[0] - 4); buf = (u8 *)tlv + sizeof(*cont); mt7915_mac_write_txwi(dev, (__le32 *)buf, skb, wcid, NULL, diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c index 6b7532f7c936..ff96f22648ef 100644 --- a/drivers/net/xen-netback/hash.c +++ b/drivers/net/xen-netback/hash.c @@ -393,7 +393,7 @@ void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m) case XEN_NETIF_CTRL_HASH_ALGORITHM_NONE: seq_puts(m, "Hash Algorithm: NONE\n"); - /* FALLTHRU */ + fallthrough; default: return; } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 7e62a6ee7622..f1c1624cec8f 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -448,7 +448,7 @@ static void frontend_changed(struct xenbus_device *dev, set_backend_state(be, XenbusStateClosed); if (xenbus_dev_is_online(dev)) break; - /* fall through - if not online */ + fallthrough; /* if not online */ case XenbusStateUnknown: set_backend_state(be, XenbusStateClosed); device_unregister(&dev->dev); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 458be6882b98..3e9895bec15f 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -2341,7 +2341,7 @@ static void netback_changed(struct xenbus_device *dev, case XenbusStateClosed: if (dev->state == XenbusStateClosed) break; - /* Fall through - Missed the backend's CLOSING state. */ + fallthrough; /* Missed the backend's CLOSING state */ case XenbusStateClosing: xenbus_frontend_closed(dev); break; diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c index 346e084387f7..f7464bd6d57c 100644 --- a/drivers/nfc/pn533/pn533.c +++ b/drivers/nfc/pn533/pn533.c @@ -2321,7 +2321,7 @@ static int pn533_transceive(struct nfc_dev *nfc_dev, break; } - /* fall through */ + fallthrough; default: /* jumbo frame ? */ if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) { @@ -2448,7 +2448,7 @@ static void pn533_wq_mi_recv(struct work_struct *work) break; } - /* fall through */ + fallthrough; default: skb_put_u8(skb, 1); /*TG*/ diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index f5bb7ace2ff5..84f2983bf384 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -210,7 +210,7 @@ static void pn533_usb_abort_cmd(struct pn533 *dev, gfp_t flags) usb_kill_urb(phy->in_urb); } -/* ACR122 specific structs and fucntions */ +/* ACR122 specific structs and functions */ /* ACS ACR122 pn533 frame definitions */ #define PN533_ACR122_TX_FRAME_HEADER_LEN (sizeof(struct pn533_acr122_tx_frame) \ diff --git a/drivers/nfc/s3fwrn5/Kconfig b/drivers/nfc/s3fwrn5/Kconfig index af9d18690afe..3f8b6da58280 100644 --- a/drivers/nfc/s3fwrn5/Kconfig +++ b/drivers/nfc/s3fwrn5/Kconfig @@ -2,6 +2,7 @@ config NFC_S3FWRN5 tristate select CRYPTO + select CRYPTO_HASH help Core driver for Samsung S3FWRN5 NFC chip. Contains core utilities of chip. It's intended to be used by PHYs to avoid duplicating lots diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c index 69857f080704..ec930ee2c847 100644 --- a/drivers/nfc/s3fwrn5/firmware.c +++ b/drivers/nfc/s3fwrn5/firmware.c @@ -348,7 +348,7 @@ static int s3fwrn5_fw_get_base_addr( } static inline bool -s3fwrn5_fw_is_custom(struct s3fwrn5_fw_cmd_get_bootinfo_rsp *bootinfo) +s3fwrn5_fw_is_custom(const struct s3fwrn5_fw_cmd_get_bootinfo_rsp *bootinfo) { return !!bootinfo->hw_version[2]; } @@ -399,7 +399,7 @@ err: return ret; } -bool s3fwrn5_fw_check_version(struct s3fwrn5_fw_info *fw_info, u32 version) +bool s3fwrn5_fw_check_version(const struct s3fwrn5_fw_info *fw_info, u32 version) { struct s3fwrn5_fw_version *new = (void *) &fw_info->fw.version; struct s3fwrn5_fw_version *old = (void *) &version; diff --git a/drivers/nfc/s3fwrn5/firmware.h b/drivers/nfc/s3fwrn5/firmware.h index cf1a83a5a525..3c83e6730d30 100644 --- a/drivers/nfc/s3fwrn5/firmware.h +++ b/drivers/nfc/s3fwrn5/firmware.h @@ -91,7 +91,7 @@ struct s3fwrn5_fw_info { void s3fwrn5_fw_init(struct s3fwrn5_fw_info *fw_info, const char *fw_name); int s3fwrn5_fw_setup(struct s3fwrn5_fw_info *fw_info); -bool s3fwrn5_fw_check_version(struct s3fwrn5_fw_info *fw_info, u32 version); +bool s3fwrn5_fw_check_version(const struct s3fwrn5_fw_info *fw_info, u32 version); int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info); void s3fwrn5_fw_cleanup(struct s3fwrn5_fw_info *fw_info); diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c index b4eb926d220a..dc995286be84 100644 --- a/drivers/nfc/s3fwrn5/i2c.c +++ b/drivers/nfc/s3fwrn5/i2c.c @@ -164,7 +164,6 @@ out: static irqreturn_t s3fwrn5_i2c_irq_thread_fn(int irq, void *phy_id) { struct s3fwrn5_i2c_phy *phy = phy_id; - int ret = 0; if (!phy || !phy->ndev) { WARN_ON_ONCE(1); @@ -179,10 +178,9 @@ static irqreturn_t s3fwrn5_i2c_irq_thread_fn(int irq, void *phy_id) switch (phy->mode) { case S3FWRN5_MODE_NCI: case S3FWRN5_MODE_FW: - ret = s3fwrn5_i2c_read(phy); + s3fwrn5_i2c_read(phy); break; case S3FWRN5_MODE_COLD: - ret = -EREMOTEIO; break; } @@ -200,13 +198,21 @@ static int s3fwrn5_i2c_parse_dt(struct i2c_client *client) if (!np) return -ENODEV; - phy->gpio_en = of_get_named_gpio(np, "s3fwrn5,en-gpios", 0); - if (!gpio_is_valid(phy->gpio_en)) - return -ENODEV; + phy->gpio_en = of_get_named_gpio(np, "en-gpios", 0); + if (!gpio_is_valid(phy->gpio_en)) { + /* Support also deprecated property */ + phy->gpio_en = of_get_named_gpio(np, "s3fwrn5,en-gpios", 0); + if (!gpio_is_valid(phy->gpio_en)) + return -ENODEV; + } - phy->gpio_fw_wake = of_get_named_gpio(np, "s3fwrn5,fw-gpios", 0); - if (!gpio_is_valid(phy->gpio_fw_wake)) - return -ENODEV; + phy->gpio_fw_wake = of_get_named_gpio(np, "wake-gpios", 0); + if (!gpio_is_valid(phy->gpio_fw_wake)) { + /* Support also deprecated property */ + phy->gpio_fw_wake = of_get_named_gpio(np, "s3fwrn5,fw-gpios", 0); + if (!gpio_is_valid(phy->gpio_fw_wake)) + return -ENODEV; + } return 0; } diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index f25f1ec5f9e9..807eae04c1e3 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -331,8 +331,7 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) return -EPROTO; - transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, - skb->len - 2, GFP_KERNEL); + transaction = devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); if (!transaction) return -ENOMEM; diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c index 0b9ca6d20ffa..8874d605b14f 100644 --- a/drivers/nfc/st21nfca/dep.c +++ b/drivers/nfc/st21nfca/dep.c @@ -611,7 +611,7 @@ static void st21nfca_im_recv_dep_res_cb(void *context, struct sk_buff *skb, switch (ST21NFCA_NFC_DEP_PFB_TYPE(dep_res->pfb)) { case ST21NFCA_NFC_DEP_PFB_ACK_NACK_PDU: pr_err("Received a ACK/NACK PDU\n"); - /* fall through */ + fallthrough; case ST21NFCA_NFC_DEP_PFB_I_PDU: info->dep_info.curr_nfc_dep_pni = ST21NFCA_NFC_DEP_PFB_PNI(dep_res->pfb + 1); diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index 6586378cacb0..c8bdf078d111 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -315,8 +315,7 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host, skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) return -EPROTO; - transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, - skb->len - 2, GFP_KERNEL); + transaction = devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); if (!transaction) return -ENOMEM; diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c index 9642971e89ce..457854765983 100644 --- a/drivers/nfc/st95hf/core.c +++ b/drivers/nfc/st95hf/core.c @@ -966,7 +966,7 @@ static int st95hf_in_send_cmd(struct nfc_digital_dev *ddev, rc = down_killable(&stcontext->exchange_lock); if (rc) { WARN(1, "Semaphore is not found up in st95hf_in_send_cmd\n"); - return rc; + goto free_skb_resp; } rc = st95hf_spi_send(&stcontext->spicontext, skb->data, diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index e46adaac1c63..3bd97c73f983 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -1153,7 +1153,7 @@ static int trf7970a_switch_rf(struct nfc_digital_dev *ddev, bool on) dev_err(trf->dev, "%s - Invalid request: %d %d\n", __func__, trf->state, on); ret = -EINVAL; - /* FALLTHROUGH */ + fallthrough; case TRF7970A_ST_IDLE: case TRF7970A_ST_IDLE_RX_BLOCKED: case TRF7970A_ST_WAIT_FOR_RX_DATA: @@ -1960,7 +1960,7 @@ static void trf7970a_shutdown(struct trf7970a *trf) case TRF7970A_ST_WAIT_TO_ISSUE_EOF: case TRF7970A_ST_LISTENING: trf7970a_send_err_upstream(trf, -ECANCELED); - /* FALLTHROUGH */ + fallthrough; case TRF7970A_ST_IDLE: case TRF7970A_ST_IDLE_RX_BLOCKED: trf7970a_switch_rf_off(trf); diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index e6d1f5b298f3..4a02561cfb96 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -1483,7 +1483,7 @@ static void ntb_rx_copy_callback(void *data, case DMA_TRANS_READ_FAILED: case DMA_TRANS_WRITE_FAILED: entry->errors++; - /* fall through */ + fallthrough; case DMA_TRANS_ABORTED: { struct ntb_transport_qp *qp = entry->qp; @@ -1739,7 +1739,7 @@ static void ntb_tx_copy_callback(void *data, case DMA_TRANS_READ_FAILED: case DMA_TRANS_WRITE_FAILED: entry->errors++; - /* fall through */ + fallthrough; case DMA_TRANS_ABORTED: { void __iomem *offset = diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 61374def5155..b59032e0859b 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -529,6 +529,7 @@ static DEVICE_ATTR_ADMIN_RW(activate); static struct attribute *nvdimm_firmware_attributes[] = { &dev_attr_activate.attr, &dev_attr_result.attr, + NULL, }; static umode_t nvdimm_firmware_visible(struct kobject *kobj, struct attribute *a, int n) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 88cff309d8e4..d543bc1747fd 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -241,17 +241,6 @@ static blk_status_t nvme_error_status(u16 status) } } -static inline bool nvme_req_needs_retry(struct request *req) -{ - if (blk_noretry_request(req)) - return false; - if (nvme_req(req)->status & NVME_SC_DNR) - return false; - if (nvme_req(req)->retries >= nvme_max_retries) - return false; - return true; -} - static void nvme_retry_req(struct request *req) { struct nvme_ns *ns = req->q->queuedata; @@ -268,34 +257,67 @@ static void nvme_retry_req(struct request *req) blk_mq_delay_kick_requeue_list(req->q, delay); } -void nvme_complete_rq(struct request *req) +enum nvme_disposition { + COMPLETE, + RETRY, + FAILOVER, +}; + +static inline enum nvme_disposition nvme_decide_disposition(struct request *req) { - blk_status_t status = nvme_error_status(nvme_req(req)->status); + if (likely(nvme_req(req)->status == 0)) + return COMPLETE; - trace_nvme_complete_rq(req); + if (blk_noretry_request(req) || + (nvme_req(req)->status & NVME_SC_DNR) || + nvme_req(req)->retries >= nvme_max_retries) + return COMPLETE; - nvme_cleanup_cmd(req); + if (req->cmd_flags & REQ_NVME_MPATH) { + if (nvme_is_path_error(nvme_req(req)->status) || + blk_queue_dying(req->q)) + return FAILOVER; + } else { + if (blk_queue_dying(req->q)) + return COMPLETE; + } - if (nvme_req(req)->ctrl->kas) - nvme_req(req)->ctrl->comp_seen = true; + return RETRY; +} - if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) { - if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req)) - return; +static inline void nvme_end_req(struct request *req) +{ + blk_status_t status = nvme_error_status(nvme_req(req)->status); - if (!blk_queue_dying(req->q)) { - nvme_retry_req(req); - return; - } - } else if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && - req_op(req) == REQ_OP_ZONE_APPEND) { + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + req_op(req) == REQ_OP_ZONE_APPEND) req->__sector = nvme_lba_to_sect(req->q->queuedata, le64_to_cpu(nvme_req(req)->result.u64)); - } nvme_trace_bio_complete(req, status); blk_mq_end_request(req, status); } + +void nvme_complete_rq(struct request *req) +{ + trace_nvme_complete_rq(req); + nvme_cleanup_cmd(req); + + if (nvme_req(req)->ctrl->kas) + nvme_req(req)->ctrl->comp_seen = true; + + switch (nvme_decide_disposition(req)) { + case COMPLETE: + nvme_end_req(req); + return; + case RETRY: + nvme_retry_req(req); + return; + case FAILOVER: + nvme_failover_req(req); + return; + } +} EXPORT_SYMBOL_GPL(nvme_complete_rq); bool nvme_cancel_request(struct request *req, void *data, bool reserved) @@ -330,7 +352,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -340,7 +362,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, case NVME_CTRL_NEW: case NVME_CTRL_LIVE: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -350,7 +372,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, case NVME_CTRL_NEW: case NVME_CTRL_RESETTING: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -361,7 +383,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -371,7 +393,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, case NVME_CTRL_DELETING: case NVME_CTRL_DEAD: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -380,7 +402,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (old_state) { case NVME_CTRL_DELETING: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -2004,13 +2026,49 @@ static void nvme_update_disk_info(struct gendisk *disk, blk_mq_unfreeze_queue(disk->queue); } +static inline bool nvme_first_scan(struct gendisk *disk) +{ + /* nvme_alloc_ns() scans the disk prior to adding it */ + return !(disk->flags & GENHD_FL_UP); +} + +static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id) +{ + struct nvme_ctrl *ctrl = ns->ctrl; + u32 iob; + + if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) && + is_power_of_2(ctrl->max_hw_sectors)) + iob = ctrl->max_hw_sectors; + else + iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob)); + + if (!iob) + return; + + if (!is_power_of_2(iob)) { + if (nvme_first_scan(ns->disk)) + pr_warn("%s: ignoring unaligned IO boundary:%u\n", + ns->disk->disk_name, iob); + return; + } + + if (blk_queue_is_zoned(ns->disk->queue)) { + if (nvme_first_scan(ns->disk)) + pr_warn("%s: ignoring zoned namespace IO boundary\n", + ns->disk->disk_name); + return; + } + + blk_queue_chunk_sectors(ns->queue, iob); +} + static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) { unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK; struct nvme_ns *ns = disk->private_data; struct nvme_ctrl *ctrl = ns->ctrl; int ret; - u32 iob; /* * If identify namespace failed, use default 512 byte block size so @@ -2038,12 +2096,6 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) return -ENODEV; } - if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) && - is_power_of_2(ctrl->max_hw_sectors)) - iob = ctrl->max_hw_sectors; - else - iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob)); - ns->features = 0; ns->ms = le16_to_cpu(id->lbaf[lbaf].ms); /* the PI implementation requires metadata equal t10 pi tuple size */ @@ -2075,8 +2127,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) } } - if (iob) - blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob)); + nvme_set_chunk_sectors(ns, id); nvme_update_disk_info(disk, ns, id); #ifdef CONFIG_NVME_MULTIPATH if (ns->head->disk) { @@ -2965,14 +3016,14 @@ static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi) { struct nvme_cel *cel, *ret = NULL; - spin_lock(&ctrl->lock); + spin_lock_irq(&ctrl->lock); list_for_each_entry(cel, &ctrl->cels, entry) { if (cel->csi == csi) { ret = cel; break; } } - spin_unlock(&ctrl->lock); + spin_unlock_irq(&ctrl->lock); return ret; } @@ -2999,9 +3050,9 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, cel->csi = csi; - spin_lock(&ctrl->lock); + spin_lock_irq(&ctrl->lock); list_add_tail(&cel->entry, &ctrl->cels); - spin_unlock(&ctrl->lock); + spin_unlock_irq(&ctrl->lock); out: *log = &cel->log; return 0; @@ -3654,6 +3705,10 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, return 0; if (a == &dev_attr_hostid.attr && !ctrl->opts) return 0; + if (a == &dev_attr_ctrl_loss_tmo.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts) + return 0; return a->mode; } @@ -4368,7 +4423,7 @@ static void nvme_free_ctrl(struct device *dev) struct nvme_subsystem *subsys = ctrl->subsys; struct nvme_cel *cel, *next; - if (subsys && ctrl->instance != subsys->instance) + if (!subsys || ctrl->instance != subsys->instance) ida_simple_remove(&nvme_instance_ida, ctrl->instance); list_for_each_entry_safe(cel, next, &ctrl->cels, entry) { @@ -4512,7 +4567,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_unfreeze); -void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout) +int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout) { struct nvme_ns *ns; @@ -4523,6 +4578,7 @@ void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout) break; } up_read(&ctrl->namespaces_rwsem); + return timeout; } EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 4ec4829d6233..32f61fc5f4c5 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -576,7 +576,6 @@ bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq, * which is require to set the queue live in the appropinquate states. */ switch (ctrl->state) { - case NVME_CTRL_NEW: case NVME_CTRL_CONNECTING: if (nvme_is_fabrics(req->cmd) && req->cmd->fabrics.fctype == nvme_fabrics_type_connect) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index eae43bb444e0..a7f474ddfff7 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2035,7 +2035,7 @@ done: } __nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate); - if (!nvme_end_request(rq, status, result)) + if (!nvme_try_complete_req(rq, status, result)) nvme_fc_complete_rq(rq); check_error: @@ -2078,7 +2078,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl, if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.cmddma)) { dev_err(ctrl->dev, "FCP Op failed - cmdiu dma mapping failed.\n"); - ret = EFAULT; + ret = -EFAULT; goto out_on_error; } @@ -2088,7 +2088,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl, if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.rspdma)) { dev_err(ctrl->dev, "FCP Op failed - rspiu dma mapping failed.\n"); - ret = EFAULT; + ret = -EFAULT; } atomic_set(&op->state, FCPOP_STATE_IDLE); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 3ded54d2c9c6..d4ba736c6c89 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -65,51 +65,30 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, } } -bool nvme_failover_req(struct request *req) +void nvme_failover_req(struct request *req) { struct nvme_ns *ns = req->q->queuedata; - u16 status = nvme_req(req)->status; + u16 status = nvme_req(req)->status & 0x7ff; unsigned long flags; - switch (status & 0x7ff) { - case NVME_SC_ANA_TRANSITION: - case NVME_SC_ANA_INACCESSIBLE: - case NVME_SC_ANA_PERSISTENT_LOSS: - /* - * If we got back an ANA error we know the controller is alive, - * but not ready to serve this namespaces. The spec suggests - * we should update our general state here, but due to the fact - * that the admin and I/O queues are not serialized that is - * fundamentally racy. So instead just clear the current path, - * mark the the path as pending and kick of a re-read of the ANA - * log page ASAP. - */ - nvme_mpath_clear_current_path(ns); - if (ns->ctrl->ana_log_buf) { - set_bit(NVME_NS_ANA_PENDING, &ns->flags); - queue_work(nvme_wq, &ns->ctrl->ana_work); - } - break; - case NVME_SC_HOST_PATH_ERROR: - case NVME_SC_HOST_ABORTED_CMD: - /* - * Temporary transport disruption in talking to the controller. - * Try to send on a new path. - */ - nvme_mpath_clear_current_path(ns); - break; - default: - /* This was a non-ANA error so follow the normal error path. */ - return false; + nvme_mpath_clear_current_path(ns); + + /* + * If we got back an ANA error, we know the controller is alive but not + * ready to serve this namespace. Kick of a re-read of the ANA + * information page, and just try any other available path for now. + */ + if (nvme_is_ana_error(status) && ns->ctrl->ana_log_buf) { + set_bit(NVME_NS_ANA_PENDING, &ns->flags); + queue_work(nvme_wq, &ns->ctrl->ana_work); } spin_lock_irqsave(&ns->head->requeue_lock, flags); blk_steal_bios(&ns->head->requeue_list, req); spin_unlock_irqrestore(&ns->head->requeue_lock, flags); - blk_mq_end_request(req, 0); + blk_mq_end_request(req, 0); kblockd_schedule_work(&ns->head->requeue_work); - return true; } void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) @@ -233,7 +212,7 @@ static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head, static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head, int node, struct nvme_ns *old) { - struct nvme_ns *ns, *found, *fallback = NULL; + struct nvme_ns *ns, *found = NULL; if (list_is_singular(&head->list)) { if (nvme_path_is_disabled(old)) @@ -252,18 +231,22 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head, goto out; } if (ns->ana_state == NVME_ANA_NONOPTIMIZED) - fallback = ns; + found = ns; } - /* No optimized path found, re-check the current path */ + /* + * The loop above skips the current path for round-robin semantics. + * Fall back to the current path if either: + * - no other optimized path found and current is optimized, + * - no other usable path found and current is usable. + */ if (!nvme_path_is_disabled(old) && - old->ana_state == NVME_ANA_OPTIMIZED) { - found = old; - goto out; - } - if (!fallback) + (old->ana_state == NVME_ANA_OPTIMIZED || + (!found && old->ana_state == NVME_ANA_NONOPTIMIZED))) + return old; + + if (!found) return NULL; - found = fallback; out: rcu_assign_pointer(head->current_path[node], found); return found; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index ebb8c3ed3885..2910f6caab7d 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -523,7 +523,31 @@ static inline u32 nvme_bytes_to_numd(size_t len) return (len >> 2) - 1; } -static inline bool nvme_end_request(struct request *req, __le16 status, +static inline bool nvme_is_ana_error(u16 status) +{ + switch (status & 0x7ff) { + case NVME_SC_ANA_TRANSITION: + case NVME_SC_ANA_INACCESSIBLE: + case NVME_SC_ANA_PERSISTENT_LOSS: + return true; + default: + return false; + } +} + +static inline bool nvme_is_path_error(u16 status) +{ + /* check for a status code type of 'path related status' */ + return (status & 0x700) == 0x300; +} + +/* + * Fill in the status and result information from the CQE, and then figure out + * if blk-mq will need to use IPI magic to complete the request, and if yes do + * so. If not let the caller complete the request without an indirect function + * call. + */ +static inline bool nvme_try_complete_req(struct request *req, __le16 status, union nvme_result result) { struct nvme_request *rq = nvme_req(req); @@ -581,7 +605,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl); void nvme_sync_queues(struct nvme_ctrl *ctrl); void nvme_unfreeze(struct nvme_ctrl *ctrl); void nvme_wait_freeze(struct nvme_ctrl *ctrl); -void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout); +int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout); void nvme_start_freeze(struct nvme_ctrl *ctrl); #define NVME_QID_ANY -1 @@ -629,7 +653,7 @@ void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys); void nvme_mpath_start_freeze(struct nvme_subsystem *subsys); void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, struct nvme_ctrl *ctrl, int *flags); -bool nvme_failover_req(struct request *req); +void nvme_failover_req(struct request *req); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id); @@ -688,9 +712,8 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance); } -static inline bool nvme_failover_req(struct request *req) +static inline void nvme_failover_req(struct request *req) { - return false; } static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) { diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ba725ae47305..899d2f4d7ab6 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -120,7 +120,7 @@ struct nvme_dev { unsigned max_qid; unsigned io_queues[HCTX_MAX_TYPES]; unsigned int num_vecs; - u16 q_depth; + u32 q_depth; int io_sqes; u32 db_stride; void __iomem *bar; @@ -157,13 +157,13 @@ struct nvme_dev { static int io_queue_depth_set(const char *val, const struct kernel_param *kp) { int ret; - u16 n; + u32 n; - ret = kstrtou16(val, 10, &n); + ret = kstrtou32(val, 10, &n); if (ret != 0 || n < 2) return -EINVAL; - return param_set_ushort(val, kp); + return param_set_uint(val, kp); } static inline unsigned int sq_idx(unsigned int qid, u32 stride) @@ -195,7 +195,7 @@ struct nvme_queue { dma_addr_t sq_dma_addr; dma_addr_t cq_dma_addr; u32 __iomem *q_db; - u16 q_depth; + u32 q_depth; u16 cq_vector; u16 sq_tail; u16 cq_head; @@ -961,7 +961,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id); trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail); - if (!nvme_end_request(req, cqe->status, cqe->result)) + if (!nvme_try_complete_req(req, cqe->status, cqe->result)) nvme_pci_complete_rq(req); } @@ -1244,13 +1244,13 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) switch (dev->ctrl.state) { case NVME_CTRL_CONNECTING: nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING); - /* fall through */ + fallthrough; case NVME_CTRL_DELETING: dev_warn_ratelimited(dev->ctrl.device, "I/O %d QID %d timeout, disable controller\n", req->tag, nvmeq->qid); - nvme_dev_disable(dev, true); nvme_req(req)->flags |= NVME_REQ_CANCELLED; + nvme_dev_disable(dev, true); return BLK_EH_DONE; case NVME_CTRL_RESETTING: return BLK_EH_RESET_TIMER; @@ -1267,10 +1267,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) dev_warn(dev->ctrl.device, "I/O %d QID %d timeout, reset controller\n", req->tag, nvmeq->qid); + nvme_req(req)->flags |= NVME_REQ_CANCELLED; nvme_dev_disable(dev, false); nvme_reset_ctrl(&dev->ctrl); - nvme_req(req)->flags |= NVME_REQ_CANCELLED; return BLK_EH_DONE; } @@ -2320,7 +2320,7 @@ static int nvme_pci_enable(struct nvme_dev *dev) dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP); - dev->q_depth = min_t(u16, NVME_CAP_MQES(dev->ctrl.cap) + 1, + dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1, io_queue_depth); dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */ dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap); @@ -2460,7 +2460,8 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown) static int nvme_setup_prp_pools(struct nvme_dev *dev) { dev->prp_page_pool = dma_pool_create("prp list page", dev->dev, - PAGE_SIZE, PAGE_SIZE, 0); + NVME_CTRL_PAGE_SIZE, + NVME_CTRL_PAGE_SIZE, 0); if (!dev->prp_page_pool) return -ENOMEM; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 44c76ffbb264..8e5ffe2f117d 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -122,6 +122,7 @@ struct nvme_rdma_ctrl { struct sockaddr_storage src_addr; struct nvme_ctrl ctrl; + struct mutex teardown_lock; bool use_inline_data; u32 io_queues[HCTX_MAX_TYPES]; }; @@ -975,7 +976,15 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) if (!new) { nvme_start_queues(&ctrl->ctrl); - nvme_wait_freeze(&ctrl->ctrl); + if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) { + /* + * If we timed out waiting for freeze we are likely to + * be stuck. Fail the controller initialization just + * to be safe. + */ + ret = -ENODEV; + goto out_wait_freeze_timed_out; + } blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset, ctrl->ctrl.queue_count - 1); nvme_unfreeze(&ctrl->ctrl); @@ -983,6 +992,9 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) return 0; +out_wait_freeze_timed_out: + nvme_stop_queues(&ctrl->ctrl); + nvme_rdma_stop_io_queues(ctrl); out_cleanup_connect_q: if (new) blk_cleanup_queue(ctrl->ctrl.connect_q); @@ -997,6 +1009,7 @@ out_free_io_queues: static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl, bool remove) { + mutex_lock(&ctrl->teardown_lock); blk_mq_quiesce_queue(ctrl->ctrl.admin_q); nvme_rdma_stop_queue(&ctrl->queues[0]); if (ctrl->ctrl.admin_tagset) { @@ -1007,11 +1020,13 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl, if (remove) blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); nvme_rdma_destroy_admin_queue(ctrl, remove); + mutex_unlock(&ctrl->teardown_lock); } static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, bool remove) { + mutex_lock(&ctrl->teardown_lock); if (ctrl->ctrl.queue_count > 1) { nvme_start_freeze(&ctrl->ctrl); nvme_stop_queues(&ctrl->ctrl); @@ -1025,6 +1040,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, nvme_start_queues(&ctrl->ctrl); nvme_rdma_destroy_io_queues(ctrl, remove); } + mutex_unlock(&ctrl->teardown_lock); } static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl) @@ -1180,6 +1196,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING)) return; + dev_warn(ctrl->ctrl.device, "starting error recovery\n"); queue_work(nvme_reset_wq, &ctrl->err_work); } @@ -1189,7 +1206,7 @@ static void nvme_rdma_end_request(struct nvme_rdma_request *req) if (!refcount_dec_and_test(&req->ref)) return; - if (!nvme_end_request(rq, req->status, req->result)) + if (!nvme_try_complete_req(rq, req->status, req->result)) nvme_rdma_complete_rq(rq); } @@ -1915,7 +1932,7 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, case RDMA_CM_EVENT_CONNECT_ERROR: case RDMA_CM_EVENT_UNREACHABLE: nvme_rdma_destroy_queue_ib(queue); - /* fall through */ + fallthrough; case RDMA_CM_EVENT_ADDR_ERROR: dev_dbg(queue->ctrl->ctrl.device, "CM error event %d\n", ev->event); @@ -1946,6 +1963,22 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, return 0; } +static void nvme_rdma_complete_timed_out(struct request *rq) +{ + struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_rdma_queue *queue = req->queue; + struct nvme_rdma_ctrl *ctrl = queue->ctrl; + + /* fence other contexts that may complete the command */ + mutex_lock(&ctrl->teardown_lock); + nvme_rdma_stop_queue(queue); + if (!blk_mq_request_completed(rq)) { + nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; + blk_mq_complete_request(rq); + } + mutex_unlock(&ctrl->teardown_lock); +} + static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq, bool reserved) { @@ -1956,29 +1989,29 @@ nvme_rdma_timeout(struct request *rq, bool reserved) dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n", rq->tag, nvme_rdma_queue_idx(queue)); - /* - * Restart the timer if a controller reset is already scheduled. Any - * timed out commands would be handled before entering the connecting - * state. - */ - if (ctrl->ctrl.state == NVME_CTRL_RESETTING) - return BLK_EH_RESET_TIMER; - if (ctrl->ctrl.state != NVME_CTRL_LIVE) { /* - * Teardown immediately if controller times out while starting - * or we are already started error recovery. all outstanding - * requests are completed on shutdown, so we return BLK_EH_DONE. + * If we are resetting, connecting or deleting we should + * complete immediately because we may block controller + * teardown or setup sequence + * - ctrl disable/shutdown fabrics requests + * - connect requests + * - initialization admin requests + * - I/O requests that entered after unquiescing and + * the controller stopped responding + * + * All other requests should be cancelled by the error + * recovery work, so it's fine that we fail it here. */ - flush_work(&ctrl->err_work); - nvme_rdma_teardown_io_queues(ctrl, false); - nvme_rdma_teardown_admin_queue(ctrl, false); + nvme_rdma_complete_timed_out(rq); return BLK_EH_DONE; } - dev_warn(ctrl->ctrl.device, "starting error recovery\n"); + /* + * LIVE state should trigger the normal error recovery which will + * handle completing this request. + */ nvme_rdma_error_recovery(ctrl); - return BLK_EH_RESET_TIMER; } @@ -2278,6 +2311,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, return ERR_PTR(-ENOMEM); ctrl->ctrl.opts = opts; INIT_LIST_HEAD(&ctrl->list); + mutex_init(&ctrl->teardown_lock); if (!(opts->mask & NVMF_OPT_TRSVCID)) { opts->trsvcid = diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 62fbaecdc960..16851ae3bddf 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -124,6 +124,7 @@ struct nvme_tcp_ctrl { struct sockaddr_storage src_addr; struct nvme_ctrl ctrl; + struct mutex teardown_lock; struct work_struct err_work; struct delayed_work connect_work; struct nvme_tcp_request async_req; @@ -464,6 +465,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl) if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) return; + dev_warn(ctrl->device, "starting error recovery\n"); queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work); } @@ -481,7 +483,7 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, return -EINVAL; } - if (!nvme_end_request(rq, cqe->status, cqe->result)) + if (!nvme_try_complete_req(rq, cqe->status, cqe->result)) nvme_complete_rq(rq); queue->nr_cqe++; @@ -672,7 +674,7 @@ static inline void nvme_tcp_end_request(struct request *rq, u16 status) { union nvme_result res = {}; - if (!nvme_end_request(rq, cpu_to_le16(status << 1), res)) + if (!nvme_try_complete_req(rq, cpu_to_le16(status << 1), res)) nvme_complete_rq(rq); } @@ -866,7 +868,6 @@ static void nvme_tcp_state_change(struct sock *sk) case TCP_LAST_ACK: case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: - /* fallthrough */ nvme_tcp_error_recovery(&queue->ctrl->ctrl); break; default: @@ -1527,7 +1528,6 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags)) return; - __nvme_tcp_stop_queue(queue); } @@ -1782,7 +1782,15 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) if (!new) { nvme_start_queues(ctrl); - nvme_wait_freeze(ctrl); + if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) { + /* + * If we timed out waiting for freeze we are likely to + * be stuck. Fail the controller initialization just + * to be safe. + */ + ret = -ENODEV; + goto out_wait_freeze_timed_out; + } blk_mq_update_nr_hw_queues(ctrl->tagset, ctrl->queue_count - 1); nvme_unfreeze(ctrl); @@ -1790,6 +1798,9 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) return 0; +out_wait_freeze_timed_out: + nvme_stop_queues(ctrl); + nvme_tcp_stop_io_queues(ctrl); out_cleanup_connect_q: if (new) blk_cleanup_queue(ctrl->connect_q); @@ -1875,6 +1886,7 @@ out_free_queue: static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl, bool remove) { + mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock); blk_mq_quiesce_queue(ctrl->admin_q); nvme_tcp_stop_queue(ctrl, 0); if (ctrl->admin_tagset) { @@ -1885,13 +1897,16 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl, if (remove) blk_mq_unquiesce_queue(ctrl->admin_q); nvme_tcp_destroy_admin_queue(ctrl, remove); + mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock); } static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, bool remove) { + mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock); if (ctrl->queue_count <= 1) - return; + goto out; + blk_mq_quiesce_queue(ctrl->admin_q); nvme_start_freeze(ctrl); nvme_stop_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); @@ -1903,6 +1918,8 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, if (remove) nvme_start_queues(ctrl); nvme_tcp_destroy_io_queues(ctrl, remove); +out: + mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock); } static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl) @@ -2149,40 +2166,55 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg) nvme_tcp_queue_request(&ctrl->async_req, true, true); } +static void nvme_tcp_complete_timed_out(struct request *rq) +{ + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl; + + /* fence other contexts that may complete the command */ + mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock); + nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue)); + if (!blk_mq_request_completed(rq)) { + nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; + blk_mq_complete_request(rq); + } + mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock); +} + static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq, bool reserved) { struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); - struct nvme_tcp_ctrl *ctrl = req->queue->ctrl; + struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl; struct nvme_tcp_cmd_pdu *pdu = req->pdu; - /* - * Restart the timer if a controller reset is already scheduled. Any - * timed out commands would be handled before entering the connecting - * state. - */ - if (ctrl->ctrl.state == NVME_CTRL_RESETTING) - return BLK_EH_RESET_TIMER; - - dev_warn(ctrl->ctrl.device, + dev_warn(ctrl->device, "queue %d: timeout request %#x type %d\n", nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type); - if (ctrl->ctrl.state != NVME_CTRL_LIVE) { + if (ctrl->state != NVME_CTRL_LIVE) { /* - * Teardown immediately if controller times out while starting - * or we are already started error recovery. all outstanding - * requests are completed on shutdown, so we return BLK_EH_DONE. + * If we are resetting, connecting or deleting we should + * complete immediately because we may block controller + * teardown or setup sequence + * - ctrl disable/shutdown fabrics requests + * - connect requests + * - initialization admin requests + * - I/O requests that entered after unquiescing and + * the controller stopped responding + * + * All other requests should be cancelled by the error + * recovery work, so it's fine that we fail it here. */ - flush_work(&ctrl->err_work); - nvme_tcp_teardown_io_queues(&ctrl->ctrl, false); - nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false); + nvme_tcp_complete_timed_out(rq); return BLK_EH_DONE; } - dev_warn(ctrl->ctrl.device, "starting error recovery\n"); - nvme_tcp_error_recovery(&ctrl->ctrl); - + /* + * LIVE state should trigger the normal error recovery which will + * handle completing this request. + */ + nvme_tcp_error_recovery(ctrl); return BLK_EH_RESET_TIMER; } @@ -2423,6 +2455,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, nvme_tcp_reconnect_ctrl_work); INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work); INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work); + mutex_init(&ctrl->teardown_lock); if (!(opts->mask & NVMF_OPT_TRSVCID)) { opts->trsvcid = diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 74b2b61c773b..37e1d7784e17 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1136,6 +1136,7 @@ static ssize_t nvmet_subsys_attr_model_store(struct config_item *item, up_write(&nvmet_config_sem); kfree_rcu(new_model, rcuhead); + kfree(new_model_number); return count; } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b92f45f5cd5b..b7b63330b5ef 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -73,7 +73,7 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno) status = NVME_SC_ACCESS_DENIED; break; case -EIO: - /* FALLTHRU */ + fallthrough; default: req->error_loc = offsetof(struct nvme_common_command, opcode); status = NVME_SC_INTERNAL | NVME_SC_DNR; @@ -397,6 +397,9 @@ static void nvmet_keep_alive_timer(struct work_struct *work) static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl) { + if (unlikely(ctrl->kato == 0)) + return; + pr_debug("ctrl %d start keep-alive timer for %d secs\n", ctrl->cntlid, ctrl->kato); @@ -406,6 +409,9 @@ static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl) static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl) { + if (unlikely(ctrl->kato == 0)) + return; + pr_debug("ctrl %d stop keep-alive\n", ctrl->cntlid); cancel_delayed_work_sync(&ctrl->ka_work); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 55bafd56166a..e6861cc10e7d 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -2342,9 +2342,9 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod) return; if (fcpreq->fcp_error || fcpreq->transferred_length != fcpreq->transfer_length) { - spin_lock(&fod->flock); + spin_lock_irqsave(&fod->flock, flags); fod->abort = true; - spin_unlock(&fod->flock); + spin_unlock_irqrestore(&fod->flock, flags); nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); return; diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index c97e60b71bbc..3da067a8311e 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -812,7 +812,7 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport, break; /* Fall-Thru to RSP handling */ - /* FALLTHRU */ + fallthrough; case NVMET_FCOP_RSP: if (fcpreq) { diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 3dd6f566a240..125dde3f410e 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -139,7 +139,6 @@ static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) req->error_loc = offsetof(struct nvme_rw_command, nsid); break; case BLK_STS_IOERR: - /* fallthru */ default: status = NVME_SC_INTERNAL | NVME_SC_DNR; req->error_loc = offsetof(struct nvme_common_command, opcode); diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 4884ef1e46a2..0d6008cf66a2 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -115,7 +115,7 @@ static void nvme_loop_queue_response(struct nvmet_req *req) return; } - if (!nvme_end_request(rq, cqe->status, cqe->result)) + if (!nvme_try_complete_req(rq, cqe->status, cqe->result)) nvme_loop_complete_rq(rq); } } diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 89d91dc999a6..8bd7f656e240 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -165,7 +165,7 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) req->cqe->result = nvme_req(rq)->result; nvmet_req_complete(req, status); - blk_put_request(rq); + blk_mq_free_request(rq); } static void nvmet_passthru_req_done(struct request *rq, @@ -175,7 +175,7 @@ static void nvmet_passthru_req_done(struct request *rq, req->cqe->result = nvme_req(rq)->result; nvmet_req_complete(req, nvme_req(rq)->status); - blk_put_request(rq); + blk_mq_free_request(rq); } static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq) @@ -230,7 +230,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) if (unlikely(!ns)) { pr_err("failed to get passthru ns nsid:%u\n", nsid); status = NVME_SC_INVALID_NS | NVME_SC_DNR; - goto fail_out; + goto out; } q = ns->queue; @@ -238,16 +238,15 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) rq = nvme_alloc_request(q, req->cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY); if (IS_ERR(rq)) { - rq = NULL; status = NVME_SC_INTERNAL; - goto fail_out; + goto out_put_ns; } if (req->sg_cnt) { ret = nvmet_passthru_map_sg(req, rq); if (unlikely(ret)) { status = NVME_SC_INTERNAL; - goto fail_out; + goto out_put_req; } } @@ -274,11 +273,13 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) return; -fail_out: +out_put_req: + blk_mq_free_request(rq); +out_put_ns: if (ns) nvme_put_ns(ns); +out: nvmet_req_complete(req, status); - blk_put_request(rq); } /* @@ -326,6 +327,10 @@ static u16 nvmet_setup_passthru_command(struct nvmet_req *req) u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req) { + /* Reject any commands with non-sgl flags set (ie. fused commands) */ + if (req->cmd->common.flags & ~NVME_CMD_SGL_ALL) + return NVME_SC_INVALID_FIELD; + switch (req->cmd->common.opcode) { case nvme_cmd_resv_register: case nvme_cmd_resv_report: @@ -396,6 +401,10 @@ static u16 nvmet_passthru_get_set_features(struct nvmet_req *req) u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req) { + /* Reject any commands with non-sgl flags set (ie. fused commands) */ + if (req->cmd->common.flags & ~NVME_CMD_SGL_ALL) + return NVME_SC_INVALID_FIELD; + /* * Passthru all vendor specific commands */ diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 3ccb59260b4a..ae6620489457 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1758,7 +1758,7 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, schedule_delayed_work(&port->repair_work, 0); break; } - /* FALLTHROUGH */ + fallthrough; case RDMA_CM_EVENT_DISCONNECTED: case RDMA_CM_EVENT_TIMEWAIT_EXIT: nvmet_rdma_queue_disconnect(queue); @@ -1769,7 +1769,7 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, case RDMA_CM_EVENT_REJECTED: pr_debug("Connection rejected: %s\n", rdma_reject_msg(cm_id, event->status)); - /* FALLTHROUGH */ + fallthrough; case RDMA_CM_EVENT_UNREACHABLE: case RDMA_CM_EVENT_CONNECT_ERROR: nvmet_rdma_queue_connect_fail(cm_id, queue); diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 9eda91162fe4..8e0d766d2722 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -160,6 +160,11 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd); static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue, struct nvmet_tcp_cmd *cmd) { + if (unlikely(!queue->nr_cmds)) { + /* We didn't allocate cmds yet, send 0xffff */ + return USHRT_MAX; + } + return cmd - queue->cmds; } @@ -866,7 +871,10 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) struct nvme_tcp_data_pdu *data = &queue->pdu.data; struct nvmet_tcp_cmd *cmd; - cmd = &queue->cmds[data->ttag]; + if (likely(queue->nr_cmds)) + cmd = &queue->cmds[data->ttag]; + else + cmd = &queue->connect; if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) { pr_err("ttag %u unexpected data offset %u (expected %u)\n", diff --git a/drivers/of/address.c b/drivers/of/address.c index 590493e04b01..da4f7341323f 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -128,15 +128,29 @@ static unsigned int of_bus_pci_get_flags(const __be32 *addr) * PCI bus specific translator */ +static bool of_node_is_pcie(struct device_node *np) +{ + bool is_pcie = of_node_name_eq(np, "pcie"); + + if (is_pcie) + pr_warn_once("%pOF: Missing device_type\n", np); + + return is_pcie; +} + static int of_bus_pci_match(struct device_node *np) { /* * "pciex" is PCI Express * "vci" is for the /chaos bridge on 1st-gen PCI powermacs * "ht" is hypertransport + * + * If none of the device_type match, and that the node name is + * "pcie", accept the device as PCI (with a warning). */ return of_node_is_type(np, "pci") || of_node_is_type(np, "pciex") || - of_node_is_type(np, "vci") || of_node_is_type(np, "ht"); + of_node_is_type(np, "vci") || of_node_is_type(np, "ht") || + of_node_is_pcie(np); } static void of_bus_pci_count_cells(struct device_node *np, @@ -985,6 +999,11 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz /* Don't error out as we'd break some existing DTs */ continue; } + if (range.cpu_addr == OF_BAD_ADDR) { + pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n", + range.bus_addr, node); + continue; + } dma_offset = range.cpu_addr - range.bus_addr; /* Take lower and upper limits */ diff --git a/drivers/of/base.c b/drivers/of/base.c index ea44fea99813..161a23631472 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1869,6 +1869,7 @@ int of_remove_property(struct device_node *np, struct property *prop) return rc; } +EXPORT_SYMBOL_GPL(of_remove_property); int __of_update_property(struct device_node *np, struct property *newprop, struct property **oldpropp) diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 9d7fb45b1786..3ca7543142bf 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -893,8 +893,10 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) * have OPP table for the device, while others don't and * opp_set_rate() just needs to behave like clk_set_rate(). */ - if (!_get_opp_count(opp_table)) - return 0; + if (!_get_opp_count(opp_table)) { + ret = 0; + goto put_opp_table; + } if (!opp_table->required_opp_tables && !opp_table->regulators && !opp_table->paths) { @@ -905,7 +907,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) ret = _set_opp_bw(opp_table, NULL, dev, true); if (ret) - return ret; + goto put_opp_table; if (opp_table->regulator_enabled) { regulator_disable(opp_table->regulators[0]); @@ -932,10 +934,13 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) /* Return early if nothing to do */ if (old_freq == freq) { - dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n", - __func__, freq); - ret = 0; - goto put_opp_table; + if (!opp_table->required_opp_tables && !opp_table->regulators && + !opp_table->paths) { + dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n", + __func__, freq); + ret = 0; + goto put_opp_table; + } } /* @@ -1291,13 +1296,19 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq) } EXPORT_SYMBOL_GPL(dev_pm_opp_remove); -void _opp_remove_all_static(struct opp_table *opp_table) +bool _opp_remove_all_static(struct opp_table *opp_table) { struct dev_pm_opp *opp, *tmp; + bool ret = true; mutex_lock(&opp_table->lock); - if (!opp_table->parsed_static_opps || --opp_table->parsed_static_opps) + if (!opp_table->parsed_static_opps) { + ret = false; + goto unlock; + } + + if (--opp_table->parsed_static_opps) goto unlock; list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) { @@ -1307,6 +1318,8 @@ void _opp_remove_all_static(struct opp_table *opp_table) unlock: mutex_unlock(&opp_table->lock); + + return ret; } /** @@ -2409,13 +2422,15 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev) return; } - _opp_remove_all_static(opp_table); + /* + * Drop the extra reference only if the OPP table was successfully added + * with dev_pm_opp_of_add_table() earlier. + **/ + if (_opp_remove_all_static(opp_table)) + dev_pm_opp_put_opp_table(opp_table); /* Drop reference taken by _find_opp_table() */ dev_pm_opp_put_opp_table(opp_table); - - /* Drop reference taken while the OPP table was added */ - dev_pm_opp_put_opp_table(opp_table); } /** diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h index e51646ff279e..c3fcd571e446 100644 --- a/drivers/opp/opp.h +++ b/drivers/opp/opp.h @@ -212,7 +212,7 @@ struct opp_table { /* Routines internal to opp core */ void dev_pm_opp_get(struct dev_pm_opp *opp); -void _opp_remove_all_static(struct opp_table *opp_table); +bool _opp_remove_all_static(struct opp_table *opp_table); void _get_opp_table_kref(struct opp_table *opp_table); int _get_opp_count(struct opp_table *opp_table); struct opp_table *_find_opp_table(struct device *dev); diff --git a/drivers/parport/ieee1284.c b/drivers/parport/ieee1284.c index f28d6a3c5a68..4547ac44c8d4 100644 --- a/drivers/parport/ieee1284.c +++ b/drivers/parport/ieee1284.c @@ -260,7 +260,7 @@ static void parport_ieee1284_terminate (struct parport *port) port->ieee1284.phase = IEEE1284_PH_FWD_IDLE; } - /* fall through */ + fallthrough; default: /* Terminate from all other modes. */ @@ -598,7 +598,7 @@ ssize_t parport_write (struct parport *port, const void *buffer, size_t len) case IEEE1284_MODE_NIBBLE: case IEEE1284_MODE_BYTE: parport_negotiate (port, IEEE1284_MODE_COMPAT); - /* fall through */ + fallthrough; case IEEE1284_MODE_COMPAT: pr_debug("%s: Using compatibility mode\n", port->name); fn = port->ops->compat_write_data; @@ -702,7 +702,7 @@ ssize_t parport_read (struct parport *port, void *buffer, size_t len) if (parport_negotiate (port, IEEE1284_MODE_NIBBLE)) { return -EIO; } - /* fall through - to NIBBLE */ + fallthrough; /* to NIBBLE */ case IEEE1284_MODE_NIBBLE: pr_debug("%s: Using nibble mode\n", port->name); fn = port->ops->nibble_read_data; diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c index 77e37e3cb3a0..eda4ded4d5e5 100644 --- a/drivers/parport/parport_pc.c +++ b/drivers/parport/parport_pc.c @@ -1647,7 +1647,7 @@ static int parport_ECP_supported(struct parport *pb) break; default: pr_warn("0x%lx: Unknown implementation ID\n", pb->base); - /* Fall through - Assume 1 */ + fallthrough; /* Assume 1 */ case 1: pword = 1; } diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 90df28c7cb0c..5fef2613b223 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -439,7 +439,7 @@ static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie) regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_TEST_POWERDOWN, 0); break; - case IMX6QP: /* FALLTHROUGH */ + case IMX6QP: case IMX6Q: /* power up core phy and enable ref clock */ regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, @@ -642,7 +642,7 @@ static void imx6_pcie_init_phy(struct imx6_pcie *imx6_pcie) regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_RX_EQ_MASK, IMX6SX_GPR12_PCIE_RX_EQ_2); - /* FALLTHROUGH */ + fallthrough; default: regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6Q_GPR12_PCIE_CTL_2, 0 << 10); @@ -1105,7 +1105,7 @@ static int imx6_pcie_probe(struct platform_device *pdev) dev_err(dev, "pcie_aux clock source missing or invalid\n"); return PTR_ERR(imx6_pcie->pcie_aux); } - /* fall through */ + fallthrough; case IMX7D: if (dbi_base->start == IMX8MQ_PCIE2_BASE_ADDR) imx6_pcie->controller_id = 1; diff --git a/drivers/pci/controller/pci-rcar-gen2.c b/drivers/pci/controller/pci-rcar-gen2.c index c9530038ca9a..afde4aa8f6dc 100644 --- a/drivers/pci/controller/pci-rcar-gen2.c +++ b/drivers/pci/controller/pci-rcar-gen2.c @@ -223,7 +223,7 @@ static void rcar_pci_setup(struct rcar_pci_priv *priv) pr_warn("unknown window size %ld - defaulting to 256M\n", window_size); window_size = SZ_256M; - /* fall-through */ + fallthrough; case SZ_256M: val |= RCAR_USBCTR_PCIAHB_WIN1_256M; break; diff --git a/drivers/pci/hotplug/ibmphp_res.c b/drivers/pci/hotplug/ibmphp_res.c index 5c93aa14f0de..ae9acc77d14f 100644 --- a/drivers/pci/hotplug/ibmphp_res.c +++ b/drivers/pci/hotplug/ibmphp_res.c @@ -1941,7 +1941,7 @@ static int __init update_bridge_ranges(struct bus_node **bus) break; case PCI_HEADER_TYPE_BRIDGE: function = 0x8; - /* fall through */ + fallthrough; case PCI_HEADER_TYPE_MULTIBRIDGE: /* We assume here that only 1 bus behind the bridge TO DO: add functionality for several: diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index 6503d15effbb..9f85815b4f53 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -236,7 +236,7 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) switch (ctrl->state) { case BLINKINGOFF_STATE: cancel_delayed_work(&ctrl->button_work); - /* fall through */ + fallthrough; case ON_STATE: ctrl->state = POWEROFF_STATE; mutex_unlock(&ctrl->state_lock); @@ -265,7 +265,7 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) switch (ctrl->state) { case BLINKINGON_STATE: cancel_delayed_work(&ctrl->button_work); - /* fall through */ + fallthrough; case OFF_STATE: ctrl->state = POWERON_STATE; mutex_unlock(&ctrl->state_lock); diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index b59f84918fe0..c9e790c74051 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -83,21 +83,19 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev, hotplug_slot); struct pci_dev *pdev; - struct zpci_bus *zbus = zdev->zbus; int rc; if (!zpci_fn_configured(zdev->state)) return -EIO; - pdev = pci_get_slot(zbus->bus, zdev->devfn); - if (pdev) { - if (pci_num_vf(pdev)) - return -EBUSY; - - pci_stop_and_remove_bus_device_locked(pdev); + pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + if (pdev && pci_num_vf(pdev)) { pci_dev_put(pdev); + return -EBUSY; } + zpci_remove_device(zdev); + rc = zpci_disable_device(zdev); if (rc) return rc; diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c index afdc52d1cae7..65502e3f7b4f 100644 --- a/drivers/pci/hotplug/shpchp_ctrl.c +++ b/drivers/pci/hotplug/shpchp_ctrl.c @@ -642,7 +642,7 @@ int shpchp_sysfs_enable_slot(struct slot *p_slot) switch (p_slot->state) { case BLINKINGON_STATE: cancel_delayed_work(&p_slot->work); - /* fall through */ + fallthrough; case STATIC_STATE: p_slot->state = POWERON_STATE; mutex_unlock(&p_slot->lock); @@ -678,7 +678,7 @@ int shpchp_sysfs_disable_slot(struct slot *p_slot) switch (p_slot->state) { case BLINKINGOFF_STATE: cancel_delayed_work(&p_slot->work); - /* fall through */ + fallthrough; case STATIC_STATE: p_slot->state = POWEROFF_STATE; mutex_unlock(&p_slot->lock); diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 64ebed129dbf..f357f9a32b3a 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -556,13 +556,14 @@ int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients, return -1; for (i = 0; i < num_clients; i++) { - if (IS_ENABLED(CONFIG_DMA_VIRT_OPS) && - clients[i]->dma_ops == &dma_virt_ops) { +#ifdef CONFIG_DMA_VIRT_OPS + if (clients[i]->dma_ops == &dma_virt_ops) { if (verbose) dev_warn(clients[i], "cannot be used for peer-to-peer DMA because the driver makes use of dma_virt_ops\n"); return -1; } +#endif pci_client = find_parent_pci_dev(clients[i]); if (!pci_client) { @@ -842,9 +843,10 @@ static int __pci_p2pdma_map_sg(struct pci_p2pdma_pagemap *p2p_pgmap, * this should never happen because it will be prevented * by the check in pci_p2pdma_distance_many() */ - if (WARN_ON_ONCE(IS_ENABLED(CONFIG_DMA_VIRT_OPS) && - dev->dma_ops == &dma_virt_ops)) +#ifdef CONFIG_DMA_VIRT_OPS + if (WARN_ON_ONCE(dev->dma_ops == &dma_virt_ops)) return 0; +#endif for_each_sg(sg, s, nents, i) { paddr = sg_phys(s); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a458c46d7e39..e39c5499770f 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1049,7 +1049,7 @@ static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state) if ((pmcsr & PCI_PM_CTRL_STATE_MASK) == PCI_D3hot && !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET)) need_restore = true; - /* Fall-through - force to D0 */ + fallthrough; /* force to D0 */ default: pmcsr = 0; break; @@ -2541,7 +2541,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup) case PCI_D2: if (pci_no_d1d2(dev)) break; - /* else, fall through */ + fallthrough; default: target_state = state; } diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index bd2b691fa7a3..d35186b01d98 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -231,7 +231,7 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd, } /* If arch decided it can't, fall through... */ #endif /* HAVE_PCI_MMAP */ - /* fall through */ + fallthrough; default: ret = -EINVAL; break; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index bdf9b52567e0..2a589b6d6ed8 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -1730,7 +1730,7 @@ static void quirk_jmicron_ata(struct pci_dev *pdev) case PCI_DEVICE_ID_JMICRON_JMB366: /* Redirect IDE second PATA port to the right spot */ conf5 |= (1 << 24); - /* Fall through */ + fallthrough; case PCI_DEVICE_ID_JMICRON_JMB361: case PCI_DEVICE_ID_JMICRON_JMB363: case PCI_DEVICE_ID_JMICRON_JMB369: @@ -2224,7 +2224,7 @@ static void quirk_netmos(struct pci_dev *dev) if (dev->subsystem_vendor == PCI_VENDOR_ID_IBM && dev->subsystem_device == 0x0299) return; - /* else, fall through */ + fallthrough; case PCI_DEVICE_ID_NETMOS_9735: case PCI_DEVICE_ID_NETMOS_9745: case PCI_DEVICE_ID_NETMOS_9845: diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 3951e02b7ded..2ce636937c6e 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1253,7 +1253,7 @@ void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head) additional_mmio_size = pci_hotplug_mmio_size; additional_mmio_pref_size = pci_hotplug_mmio_pref_size; } - /* Fall through */ + fallthrough; default: pbus_size_io(bus, realloc_head ? 0 : additional_io_size, additional_io_size, realloc_head); diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index fab267e359e7..c0e85be598c1 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -1096,7 +1096,7 @@ static void __ref pcifront_backend_changed(struct xenbus_device *xdev, case XenbusStateClosed: if (xdev->state == XenbusStateClosed) break; - /* fall through - Missed the backend's CLOSING state. */ + fallthrough; /* Missed the backend's CLOSING state */ case XenbusStateClosing: dev_warn(&xdev->dev, "backend going away!\n"); pcifront_try_disconnect(pdev); diff --git a/drivers/pcmcia/db1xxx_ss.c b/drivers/pcmcia/db1xxx_ss.c index 590e594092f2..a7c7c7cd2326 100644 --- a/drivers/pcmcia/db1xxx_ss.c +++ b/drivers/pcmcia/db1xxx_ss.c @@ -255,10 +255,10 @@ static int db1x_pcmcia_configure(struct pcmcia_socket *skt, switch (state->Vcc) { case 50: ++v; - /* fall through */ + fallthrough; case 33: ++v; - /* fall through */ + fallthrough; case 0: break; default: @@ -269,11 +269,11 @@ static int db1x_pcmcia_configure(struct pcmcia_socket *skt, switch (state->Vpp) { case 12: ++p; - /* fall through */ + fallthrough; case 33: case 50: ++p; - /* fall through */ + fallthrough; case 0: break; default: diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c index 7b7d23f25713..a0a71c1df042 100644 --- a/drivers/perf/arm-ccn.c +++ b/drivers/perf/arm-ccn.c @@ -1404,7 +1404,7 @@ static int arm_ccn_init_nodes(struct arm_ccn *ccn, int region, break; case CCN_TYPE_SBAS: ccn->sbas_present = 1; - /* Fall-through */ + fallthrough; default: component = &ccn->node[id]; break; diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index e51ddb6d63ed..cc00915ad6d1 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -1002,7 +1002,7 @@ static void __arm_spe_pmu_dev_probe(void *info) default: dev_warn(dev, "unknown PMSIDR_EL1.Interval [%d]; assuming 8\n", fld); - /* Fallthrough */ + fallthrough; case 8: spe_pmu->min_period = 4096; } @@ -1021,7 +1021,7 @@ static void __arm_spe_pmu_dev_probe(void *info) default: dev_warn(dev, "unknown PMSIDR_EL1.CountSize [%d]; assuming 2\n", fld); - /* Fallthrough */ + fallthrough; case 2: spe_pmu->counter_sz = 12; } diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs.c b/drivers/phy/qualcomm/phy-qcom-usb-hs.c index 61054272a7c8..327df1a99f77 100644 --- a/drivers/phy/qualcomm/phy-qcom-usb-hs.c +++ b/drivers/phy/qualcomm/phy-qcom-usb-hs.c @@ -53,7 +53,7 @@ static int qcom_usb_hs_phy_set_mode(struct phy *phy, case PHY_MODE_USB_OTG: case PHY_MODE_USB_HOST: val |= ULPI_INT_IDGRD; - /* fall through */ + fallthrough; case PHY_MODE_USB_DEVICE: val |= ULPI_INT_SESS_VALID; default: diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c index a84e9f027fc4..46ebdb1460a3 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c @@ -546,7 +546,7 @@ static void rockchip_usb2phy_otg_sm_work(struct work_struct *work) rport->state = OTG_STATE_B_IDLE; if (!vbus_attach) rockchip_usb2phy_power_off(rport->phy); - /* fall through */ + fallthrough; case OTG_STATE_B_IDLE: if (extcon_get_state(rphy->edev, EXTCON_USB_HOST) > 0) { dev_dbg(&rport->phy->dev, "usb otg host connect\n"); @@ -754,11 +754,11 @@ static void rockchip_chg_detect_work(struct work_struct *work) rphy->chg_type = POWER_SUPPLY_TYPE_USB_DCP; else rphy->chg_type = POWER_SUPPLY_TYPE_USB_CDP; - /* fall through */ + fallthrough; case USB_CHG_STATE_SECONDARY_DONE: rphy->chg_state = USB_CHG_STATE_DETECTED; delay = 0; - /* fall through */ + fallthrough; case USB_CHG_STATE_DETECTED: /* put the controller in normal mode */ property_enable(base, &rphy->phy_cfg->chg_det.opmode, true); @@ -835,7 +835,7 @@ static void rockchip_usb2phy_sm_work(struct work_struct *work) dev_dbg(&rport->phy->dev, "FS/LS online\n"); break; } - /* fall through */ + fallthrough; case PHY_STATE_CONNECT: if (rport->suspended) { dev_dbg(&rport->phy->dev, "Connected\n"); diff --git a/drivers/platform/olpc/olpc-xo175-ec.c b/drivers/platform/olpc/olpc-xo175-ec.c index 5e1d14e35f20..0d46706afd2d 100644 --- a/drivers/platform/olpc/olpc-xo175-ec.c +++ b/drivers/platform/olpc/olpc-xo175-ec.c @@ -431,7 +431,7 @@ static void olpc_xo175_ec_complete(void *arg) input_sync(priv->pwrbtn); input_report_key(priv->pwrbtn, KEY_POWER, 0); input_sync(priv->pwrbtn); - /* fall through */ + fallthrough; case EVENT_POWER_PRESS_WAKE: case EVENT_TIMED_HOST_WAKE: pm_wakeup_event(priv->pwrbtn->dev.parent, diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 60c18f21588d..49f4b73be513 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -1001,7 +1001,7 @@ static acpi_status WMID_get_u32(u32 *value, u32 cap) *value = tmp & 0x1; return 0; } - /* fall through */ + fallthrough; default: return AE_ERROR; } @@ -1328,7 +1328,7 @@ static acpi_status get_u32(u32 *value, u32 cap) status = AMW0_get_u32(value, cap); break; } - /* fall through */ + fallthrough; case ACER_WMID: status = WMID_get_u32(value, cap); break; @@ -1371,7 +1371,7 @@ static acpi_status set_u32(u32 value, u32 cap) return AMW0_set_u32(value, cap); } - /* fall through */ + fallthrough; case ACER_WMID: return WMID_set_u32(value, cap); case ACER_WMID_v2: @@ -1381,7 +1381,7 @@ static acpi_status set_u32(u32 value, u32 cap) return wmid_v2_set_u32(value, cap); else if (wmi_has_guid(WMID_GUID2)) return WMID_set_u32(value, cap); - /* fall through */ + fallthrough; default: return AE_BAD_PARAMETER; } diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index 5e9c2296931c..70edc5bb3a14 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -1587,10 +1587,10 @@ static ssize_t kbd_led_timeout_store(struct device *dev, switch (unit) { case KBD_TIMEOUT_DAYS: value *= 24; - /* fall through */ + fallthrough; case KBD_TIMEOUT_HOURS: value *= 60; - /* fall through */ + fallthrough; case KBD_TIMEOUT_MINUTES: value *= 60; unit = KBD_TIMEOUT_SECONDS; diff --git a/drivers/platform/x86/surfacepro3_button.c b/drivers/platform/x86/surfacepro3_button.c index ec515223f654..d8afed5db94c 100644 --- a/drivers/platform/x86/surfacepro3_button.c +++ b/drivers/platform/x86/surfacepro3_button.c @@ -84,28 +84,28 @@ static void surface_button_notify(struct acpi_device *device, u32 event) /* Power button press,release handle */ case SURFACE_BUTTON_NOTIFY_PRESS_POWER: pressed = true; - /*fall through*/ + fallthrough; case SURFACE_BUTTON_NOTIFY_RELEASE_POWER: key_code = KEY_POWER; break; /* Home button press,release handle */ case SURFACE_BUTTON_NOTIFY_PRESS_HOME: pressed = true; - /*fall through*/ + fallthrough; case SURFACE_BUTTON_NOTIFY_RELEASE_HOME: key_code = KEY_LEFTMETA; break; /* Volume up button press,release handle */ case SURFACE_BUTTON_NOTIFY_PRESS_VOLUME_UP: pressed = true; - /*fall through*/ + fallthrough; case SURFACE_BUTTON_NOTIFY_RELEASE_VOLUME_UP: key_code = KEY_VOLUMEUP; break; /* Volume down button press,release handle */ case SURFACE_BUTTON_NOTIFY_PRESS_VOLUME_DOWN: pressed = true; - /*fall through*/ + fallthrough; case SURFACE_BUTTON_NOTIFY_RELEASE_VOLUME_DOWN: key_code = KEY_VOLUMEDOWN; break; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 4864a5c189d4..9c4df41687a3 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -4060,7 +4060,7 @@ static bool hotkey_notify_6xxx(const u32 hkey, * AC status changed; can be triggered by plugging or * unplugging AC adapter, docking or undocking. */ - /* fallthrough */ + fallthrough; case TP_HKEY_EV_KEY_NUMLOCK: case TP_HKEY_EV_KEY_FN: @@ -4176,7 +4176,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event) known_ev = true; break; } - /* fallthrough - to default */ + fallthrough; /* to default */ default: known_ev = false; } @@ -6266,7 +6266,7 @@ static int thermal_get_sensor(int idx, s32 *value) idx -= 8; } #endif - /* fallthrough */ + fallthrough; case TPACPI_THERMAL_TPEC_8: if (idx <= 7) { if (!acpi_ec_read(t + idx, &tmp)) diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index 36fff00af9eb..e557d757c647 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -2748,7 +2748,7 @@ static void toshiba_acpi_process_hotkeys(struct toshiba_acpi_dev *dev) result = hci_write(dev, HCI_SYSTEM_EVENT, 1); if (result == TOS_SUCCESS) pr_notice("Re-enabled hotkeys\n"); - /* Fall through */ + fallthrough; default: retries--; break; diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c index 9469fe182d02..db65be026920 100644 --- a/drivers/power/supply/ab8500_charger.c +++ b/drivers/power/supply/ab8500_charger.c @@ -748,7 +748,7 @@ static int ab8500_charger_max_usb_curr(struct ab8500_charger *di, USB_CH_IP_CUR_LVL_1P5; break; } - /* else, fall through */ + fallthrough; case USB_STAT_HM_IDGND: dev_err(di->dev, "USB Type - Charging not allowed\n"); di->max_usb_in_curr.usb_type_max = USB_CH_IP_CUR_LVL_0P05; @@ -2410,7 +2410,7 @@ static void ab8500_charger_usb_state_changed_work(struct work_struct *work) * of 1sec for enabling charging */ msleep(1000); - /* Intentional fall through */ + fallthrough; case AB8500_BM_USB_STATE_CONFIGURED: /* * USB is configured, enable charging with the charging diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index 751c4f6c7487..7eec415c82a3 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -1542,7 +1542,7 @@ static void ab8500_fg_algorithm_discharging(struct ab8500_fg *di) ab8500_fg_discharge_state_to(di, AB8500_FG_DISCHARGE_INITMEASURING); - /* Intentional fallthrough */ + fallthrough; case AB8500_FG_DISCHARGE_INITMEASURING: /* * Discard a number of samples during startup. @@ -1572,7 +1572,7 @@ static void ab8500_fg_algorithm_discharging(struct ab8500_fg *di) ab8500_fg_discharge_state_to(di, AB8500_FG_DISCHARGE_RECOVERY); - /* Intentional fallthrough */ + fallthrough; case AB8500_FG_DISCHARGE_RECOVERY: sleep_time = di->bm->fg_params->recovery_sleep_timer; diff --git a/drivers/power/supply/abx500_chargalg.c b/drivers/power/supply/abx500_chargalg.c index 2fb33a07879a..175c4f3d7955 100644 --- a/drivers/power/supply/abx500_chargalg.c +++ b/drivers/power/supply/abx500_chargalg.c @@ -1419,7 +1419,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) abx500_chargalg_stop_charging(di); di->charge_status = POWER_SUPPLY_STATUS_DISCHARGING; abx500_chargalg_state_to(di, STATE_HANDHELD); - /* Intentional fallthrough */ + fallthrough; case STATE_HANDHELD: break; @@ -1435,7 +1435,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) di->maintenance_chg = false; abx500_chargalg_state_to(di, STATE_SUSPENDED); power_supply_changed(di->chargalg_psy); - /* Intentional fallthrough */ + fallthrough; case STATE_SUSPENDED: /* CHARGING is suspended */ @@ -1444,7 +1444,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) case STATE_BATT_REMOVED_INIT: abx500_chargalg_stop_charging(di); abx500_chargalg_state_to(di, STATE_BATT_REMOVED); - /* Intentional fallthrough */ + fallthrough; case STATE_BATT_REMOVED: if (!di->events.batt_rem) @@ -1454,7 +1454,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) case STATE_HW_TEMP_PROTECT_INIT: abx500_chargalg_stop_charging(di); abx500_chargalg_state_to(di, STATE_HW_TEMP_PROTECT); - /* Intentional fallthrough */ + fallthrough; case STATE_HW_TEMP_PROTECT: if (!di->events.main_thermal_prot && @@ -1465,7 +1465,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) case STATE_OVV_PROTECT_INIT: abx500_chargalg_stop_charging(di); abx500_chargalg_state_to(di, STATE_OVV_PROTECT); - /* Intentional fallthrough */ + fallthrough; case STATE_OVV_PROTECT: if (!di->events.vbus_ovv && @@ -1479,7 +1479,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) case STATE_CHG_NOT_OK_INIT: abx500_chargalg_stop_charging(di); abx500_chargalg_state_to(di, STATE_CHG_NOT_OK); - /* Intentional fallthrough */ + fallthrough; case STATE_CHG_NOT_OK: if (!di->events.mainextchnotok && @@ -1490,7 +1490,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) case STATE_SAFETY_TIMER_EXPIRED_INIT: abx500_chargalg_stop_charging(di); abx500_chargalg_state_to(di, STATE_SAFETY_TIMER_EXPIRED); - /* Intentional fallthrough */ + fallthrough; case STATE_SAFETY_TIMER_EXPIRED: /* We exit this state when charger is removed */ @@ -1537,7 +1537,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) case STATE_WAIT_FOR_RECHARGE_INIT: abx500_chargalg_hold_charging(di); abx500_chargalg_state_to(di, STATE_WAIT_FOR_RECHARGE); - /* Intentional fallthrough */ + fallthrough; case STATE_WAIT_FOR_RECHARGE: if (di->batt_data.percent <= @@ -1558,7 +1558,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) di->bm->batt_id].maint_a_cur_lvl); abx500_chargalg_state_to(di, STATE_MAINTENANCE_A); power_supply_changed(di->chargalg_psy); - /* Intentional fallthrough*/ + fallthrough; case STATE_MAINTENANCE_A: if (di->events.maintenance_timer_expired) { @@ -1578,7 +1578,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) di->bm->batt_id].maint_b_cur_lvl); abx500_chargalg_state_to(di, STATE_MAINTENANCE_B); power_supply_changed(di->chargalg_psy); - /* Intentional fallthrough*/ + fallthrough; case STATE_MAINTENANCE_B: if (di->events.maintenance_timer_expired) { @@ -1597,7 +1597,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) di->charge_status = POWER_SUPPLY_STATUS_CHARGING; abx500_chargalg_state_to(di, STATE_TEMP_LOWHIGH); power_supply_changed(di->chargalg_psy); - /* Intentional fallthrough */ + fallthrough; case STATE_TEMP_LOWHIGH: if (!di->events.btemp_lowhigh) @@ -1607,7 +1607,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) case STATE_WD_EXPIRED_INIT: abx500_chargalg_stop_charging(di); abx500_chargalg_state_to(di, STATE_WD_EXPIRED); - /* Intentional fallthrough */ + fallthrough; case STATE_WD_EXPIRED: if (!di->events.ac_wd_expired && @@ -1618,7 +1618,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di) case STATE_TEMP_UNDEROVER_INIT: abx500_chargalg_stop_charging(di); abx500_chargalg_state_to(di, STATE_TEMP_UNDEROVER); - /* Intentional fallthrough */ + fallthrough; case STATE_TEMP_UNDEROVER: if (!di->events.btemp_underover) diff --git a/drivers/power/supply/axp20x_usb_power.c b/drivers/power/supply/axp20x_usb_power.c index d01dc0332edc..0eaa86c52874 100644 --- a/drivers/power/supply/axp20x_usb_power.c +++ b/drivers/power/supply/axp20x_usb_power.c @@ -349,7 +349,7 @@ static int axp20x_usb_power_set_current_max(struct axp20x_usb_power *power, case 100000: if (power->axp20x_id == AXP221_ID) return -EINVAL; - /* fall through */ + fallthrough; case 500000: case 900000: val = (900000 - intval) / 400000; diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c index 2a45e84447fe..d89e08efd2ad 100644 --- a/drivers/power/supply/cros_usbpd-charger.c +++ b/drivers/power/supply/cros_usbpd-charger.c @@ -383,7 +383,7 @@ static int cros_usbpd_charger_get_prop(struct power_supply *psy, */ if (ec_device->mkbp_event_supported || port->psy_online) break; - /* fall through */ + fallthrough; case POWER_SUPPLY_PROP_CURRENT_MAX: case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: case POWER_SUPPLY_PROP_VOLTAGE_NOW: diff --git a/drivers/power/supply/max8925_power.c b/drivers/power/supply/max8925_power.c index 5fca4960f440..8878f9131184 100644 --- a/drivers/power/supply/max8925_power.c +++ b/drivers/power/supply/max8925_power.c @@ -121,7 +121,7 @@ static irqreturn_t max8925_charger_handler(int irq, void *data) case MAX8925_IRQ_VCHG_THM_OK_F: /* Battery is not ready yet */ dev_dbg(chip->dev, "Battery temperature is out of range\n"); - /* Fall through */ + fallthrough; case MAX8925_IRQ_VCHG_DC_OVP: dev_dbg(chip->dev, "Error detection\n"); __set_charger(info, 0); diff --git a/drivers/power/supply/wm831x_power.c b/drivers/power/supply/wm831x_power.c index 65832bc229f6..18b33f14dfee 100644 --- a/drivers/power/supply/wm831x_power.c +++ b/drivers/power/supply/wm831x_power.c @@ -665,7 +665,7 @@ static int wm831x_power_probe(struct platform_device *pdev) break; default: dev_err(&pdev->dev, "Failed to find USB phy: %d\n", ret); - /* fall-through */ + fallthrough; case -EPROBE_DEFER: goto err_bat_irq; break; diff --git a/drivers/power/supply/wm8350_power.c b/drivers/power/supply/wm8350_power.c index 26923af574f4..e05cee457471 100644 --- a/drivers/power/supply/wm8350_power.c +++ b/drivers/power/supply/wm8350_power.c @@ -227,7 +227,7 @@ static irqreturn_t wm8350_charger_handler(int irq, void *data) case WM8350_IRQ_EXT_USB_FB: case WM8350_IRQ_EXT_WALL_FB: wm8350_charger_config(wm8350, policy); - /* Fall through */ + fallthrough; case WM8350_IRQ_EXT_BAT_FB: power_supply_changed(power->battery); power_supply_changed(power->usb); diff --git a/drivers/ps3/ps3av.c b/drivers/ps3/ps3av.c index 24f04ffdd986..9d66257e1da5 100644 --- a/drivers/ps3/ps3av.c +++ b/drivers/ps3/ps3av.c @@ -769,7 +769,7 @@ static int ps3av_auto_videomode(struct ps3av_pkt_av_get_hw_conf *av_hw_conf) switch (info->monitor_type) { case PS3AV_MONITOR_TYPE_DVI: dvi = PS3AV_MODE_DVI; - /* fall through */ + fallthrough; case PS3AV_MONITOR_TYPE_HDMI: id = ps3av_hdmi_get_id(info); break; diff --git a/drivers/ps3/ps3av_cmd.c b/drivers/ps3/ps3av_cmd.c index f0e650cc866e..c22206652f06 100644 --- a/drivers/ps3/ps3av_cmd.c +++ b/drivers/ps3/ps3av_cmd.c @@ -693,11 +693,11 @@ void ps3av_cmd_set_audio_mode(struct ps3av_pkt_audio_mode *audio, u32 avport, switch (ch) { case PS3AV_CMD_AUDIO_NUM_OF_CH_8: audio->audio_enable[3] = 1; - /* fall through */ + fallthrough; case PS3AV_CMD_AUDIO_NUM_OF_CH_6: audio->audio_enable[2] = 1; audio->audio_enable[1] = 1; - /* fall through */ + fallthrough; case PS3AV_CMD_AUDIO_NUM_OF_CH_2: default: audio->audio_enable[0] = 1; diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index 73aaae5574ed..e020faff7da5 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -142,16 +142,15 @@ static int idtcm_strverscmp(const char *ver1, const char *ver2) return result; } -static int idtcm_xfer(struct idtcm *idtcm, - u8 regaddr, - u8 *buf, - u16 count, - bool write) +static int idtcm_xfer_read(struct idtcm *idtcm, + u8 regaddr, + u8 *buf, + u16 count) { struct i2c_client *client = idtcm->client; struct i2c_msg msg[2]; int cnt; - char *fmt = "i2c_transfer failed at %d in %s for %s, at addr: %04X!\n"; + char *fmt = "i2c_transfer failed at %d in %s, at addr: %04X!\n"; msg[0].addr = client->addr; msg[0].flags = 0; @@ -159,7 +158,7 @@ static int idtcm_xfer(struct idtcm *idtcm, msg[0].buf = ®addr; msg[1].addr = client->addr; - msg[1].flags = write ? 0 : I2C_M_RD; + msg[1].flags = I2C_M_RD; msg[1].len = count; msg[1].buf = buf; @@ -170,7 +169,6 @@ static int idtcm_xfer(struct idtcm *idtcm, fmt, __LINE__, __func__, - write ? "write" : "read", regaddr); return cnt; } else if (cnt != 2) { @@ -182,6 +180,37 @@ static int idtcm_xfer(struct idtcm *idtcm, return 0; } +static int idtcm_xfer_write(struct idtcm *idtcm, + u8 regaddr, + u8 *buf, + u16 count) +{ + struct i2c_client *client = idtcm->client; + /* we add 1 byte for device register */ + u8 msg[IDTCM_MAX_WRITE_COUNT + 1]; + int cnt; + char *fmt = "i2c_master_send failed at %d in %s, at addr: %04X!\n"; + + if (count > IDTCM_MAX_WRITE_COUNT) + return -EINVAL; + + msg[0] = regaddr; + memcpy(&msg[1], buf, count); + + cnt = i2c_master_send(client, msg, count + 1); + + if (cnt < 0) { + dev_err(&client->dev, + fmt, + __LINE__, + __func__, + regaddr); + return cnt; + } + + return 0; +} + static int idtcm_page_offset(struct idtcm *idtcm, u8 val) { u8 buf[4]; @@ -195,7 +224,7 @@ static int idtcm_page_offset(struct idtcm *idtcm, u8 val) buf[2] = 0x10; buf[3] = 0x20; - err = idtcm_xfer(idtcm, PAGE_ADDR, buf, sizeof(buf), 1); + err = idtcm_xfer_write(idtcm, PAGE_ADDR, buf, sizeof(buf)); if (err) { idtcm->page_offset = 0xff; @@ -223,11 +252,12 @@ static int _idtcm_rdwr(struct idtcm *idtcm, err = idtcm_page_offset(idtcm, hi); if (err) - goto out; + return err; - err = idtcm_xfer(idtcm, lo, buf, count, write); -out: - return err; + if (write) + return idtcm_xfer_write(idtcm, lo, buf, count); + + return idtcm_xfer_read(idtcm, lo, buf, count); } static int idtcm_read(struct idtcm *idtcm, diff --git a/drivers/ptp/ptp_clockmatrix.h b/drivers/ptp/ptp_clockmatrix.h index ffae56c5d97f..82840d72364a 100644 --- a/drivers/ptp/ptp_clockmatrix.h +++ b/drivers/ptp/ptp_clockmatrix.h @@ -55,6 +55,8 @@ #define PEROUT_ENABLE_OUTPUT_MASK (0xdeadbeef) +#define IDTCM_MAX_WRITE_COUNT (512) + /* Values of DPLL_N.DPLL_MODE.PLL_MODE */ enum pll_mode { PLL_MODE_MIN = 0, diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c index 7711651ff19e..4700ffbdfced 100644 --- a/drivers/ptp/ptp_ines.c +++ b/drivers/ptp/ptp_ines.c @@ -93,9 +93,6 @@ MODULE_LICENSE("GPL"); #define TC_E2E_PTP_V2 2 #define TC_P2P_PTP_V2 3 -#define OFF_PTP_CLOCK_ID 20 -#define OFF_PTP_PORT_NUM 28 - #define PHY_SPEED_10 0 #define PHY_SPEED_100 1 #define PHY_SPEED_1000 2 @@ -443,57 +440,41 @@ static void ines_link_state(struct mii_timestamper *mii_ts, static bool ines_match(struct sk_buff *skb, unsigned int ptp_class, struct ines_timestamp *ts, struct device *dev) { - u8 *msgtype, *data = skb_mac_header(skb); - unsigned int offset = 0; - __be16 *portn, *seqid; - __be64 *clkid; + struct ptp_header *hdr; + u16 portn, seqid; + u8 msgtype; + u64 clkid; if (unlikely(ptp_class & PTP_CLASS_V1)) return false; - if (ptp_class & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (ptp_class & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return false; - } - - if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid)) + hdr = ptp_parse_header(skb, ptp_class); + if (!hdr) return false; - msgtype = data + offset; - clkid = (__be64 *)(data + offset + OFF_PTP_CLOCK_ID); - portn = (__be16 *)(data + offset + OFF_PTP_PORT_NUM); - seqid = (__be16 *)(data + offset + OFF_PTP_SEQUENCE_ID); + msgtype = ptp_get_msgtype(hdr, ptp_class); + clkid = be64_to_cpup((__be64 *)&hdr->source_port_identity.clock_identity.id[0]); + portn = be16_to_cpu(hdr->source_port_identity.port_number); + seqid = be16_to_cpu(hdr->sequence_id); - if (tag_to_msgtype(ts->tag & 0x7) != (*msgtype & 0xf)) { + if (tag_to_msgtype(ts->tag & 0x7) != msgtype) { dev_dbg(dev, "msgtype mismatch ts %hhu != skb %hhu\n", - tag_to_msgtype(ts->tag & 0x7), *msgtype & 0xf); + tag_to_msgtype(ts->tag & 0x7), msgtype); return false; } - if (cpu_to_be64(ts->clkid) != *clkid) { + if (ts->clkid != clkid) { dev_dbg(dev, "clkid mismatch ts %llx != skb %llx\n", - cpu_to_be64(ts->clkid), *clkid); + ts->clkid, clkid); return false; } - if (ts->portnum != ntohs(*portn)) { + if (ts->portnum != portn) { dev_dbg(dev, "portn mismatch ts %hu != skb %hu\n", - ts->portnum, ntohs(*portn)); + ts->portnum, portn); return false; } - if (ts->seqid != ntohs(*seqid)) { + if (ts->seqid != seqid) { dev_dbg(dev, "seqid mismatch ts %hu != skb %hu\n", - ts->seqid, ntohs(*seqid)); + ts->seqid, seqid); return false; } @@ -663,8 +644,7 @@ static void ines_txtstamp(struct mii_timestamper *mii_ts, spin_unlock_irqrestore(&port->lock, flags); - if (old_skb) - kfree_skb(old_skb); + kfree_skb(old_skb); schedule_delayed_work(&port->ts_work, 1); } @@ -694,35 +674,16 @@ static void ines_txtstamp_work(struct work_struct *work) static bool is_sync_pdelay_resp(struct sk_buff *skb, int type) { - u8 *data = skb->data, *msgtype; - unsigned int offset = 0; - - if (type & PTP_CLASS_VLAN) - offset += VLAN_HLEN; + struct ptp_header *hdr; + u8 msgtype; - switch (type & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return 0; - } - - if (type & PTP_CLASS_V1) - offset += OFF_PTP_CONTROL; - - if (skb->len < offset + 1) - return 0; + hdr = ptp_parse_header(skb, type); + if (!hdr) + return false; - msgtype = data + offset; + msgtype = ptp_get_msgtype(hdr, type); - switch ((*msgtype & 0xf)) { + switch ((msgtype & 0xf)) { case SYNC: case PDELAY_RESP: return true; diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index c07ceec3c6d4..a30342942e26 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -2150,7 +2150,7 @@ static void mport_release_mapping(struct kref *ref) switch (map->dir) { case MAP_INBOUND: rio_unmap_inb_region(mport, map->phys_addr); - /* fall through */ + fallthrough; case MAP_DMA: dma_free_coherent(mport->dev.parent, map->size, map->virt_addr, map->phys_addr); diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index fbc95cadaf53..1bacb37e8a99 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -399,7 +399,7 @@ static int axp20x_set_ramp_delay(struct regulator_dev *rdev, int ramp) if (rate_count > 0) break; - /* fall through */ + fallthrough; default: /* Not supported for this regulator */ return -ENOTSUPP; @@ -1022,7 +1022,7 @@ static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq) * (See include/linux/mfd/axp20x.h) */ reg = AXP803_DCDC_FREQ_CTRL; - /* Fall through - to the check below.*/ + fallthrough; /* to the check below */ case AXP806_ID: /* * AXP806 also have DCDC work frequency setting register at a @@ -1030,7 +1030,7 @@ static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq) */ if (axp20x->variant == AXP806_ID) reg = AXP806_DCDC_FREQ_CTRL; - /* Fall through */ + fallthrough; case AXP221_ID: case AXP223_ID: case AXP809_ID: @@ -1118,7 +1118,7 @@ static int axp20x_set_dcdc_workmode(struct regulator_dev *rdev, int id, u32 work * (See include/linux/mfd/axp20x.h) */ reg = AXP806_DCDC_MODE_CTRL2; - /* Fall through - to the check below. */ + fallthrough; /* to the check below */ case AXP221_ID: case AXP223_ID: case AXP809_ID: diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 75ff7c563c5d..3fd359914690 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1895,7 +1895,7 @@ struct regulator *_regulator_get(struct device *dev, const char *id, case EXCLUSIVE_GET: dev_warn(dev, "dummy supplies not allowed for exclusive requests\n"); - /* fall through */ + fallthrough; default: return ERR_PTR(-ENODEV); diff --git a/drivers/regulator/slg51000-regulator.c b/drivers/regulator/slg51000-regulator.c index 44e4cecbf6de..87b020d0b958 100644 --- a/drivers/regulator/slg51000-regulator.c +++ b/drivers/regulator/slg51000-regulator.c @@ -319,7 +319,7 @@ static int slg51000_regulator_init(struct slg51000 *chip) rdesc->linear_min_sel = 0; break; } - /* Fall through - to the check below.*/ + fallthrough; /* to the check below */ default: rdesc->linear_min_sel = vsel_range[0]; diff --git a/drivers/regulator/twl6030-regulator.c b/drivers/regulator/twl6030-regulator.c index f7db250a7583..430265c404d6 100644 --- a/drivers/regulator/twl6030-regulator.c +++ b/drivers/regulator/twl6030-regulator.c @@ -312,7 +312,7 @@ static int twl6030smps_list_voltage(struct regulator_dev *rdev, unsigned index) switch (info->flags) { case SMPS_OFFSET_EN: voltage = 100000; - /* fall through */ + fallthrough; case 0: switch (index) { case 0: diff --git a/drivers/remoteproc/omap_remoteproc.c b/drivers/remoteproc/omap_remoteproc.c index 6955fab0a78b..d94b7391bf9d 100644 --- a/drivers/remoteproc/omap_remoteproc.c +++ b/drivers/remoteproc/omap_remoteproc.c @@ -511,7 +511,6 @@ static void omap_rproc_mbox_callback(struct mbox_client *client, void *data) dev_info(dev, "received echo reply from %s\n", name); break; case RP_MBOX_SUSPEND_ACK: - /* Fall through */ case RP_MBOX_SUSPEND_CANCEL: oproc->suspend_acked = msg == RP_MBOX_SUSPEND_ACK; complete(&oproc->pm_comp); diff --git a/drivers/reset/reset-imx7.c b/drivers/reset/reset-imx7.c index d170fe663210..e8aa8691deb2 100644 --- a/drivers/reset/reset-imx7.c +++ b/drivers/reset/reset-imx7.c @@ -222,7 +222,7 @@ static int imx8mq_reset_set(struct reset_controller_dev *rcdev, switch (id) { case IMX8MQ_RESET_PCIEPHY: - case IMX8MQ_RESET_PCIEPHY2: /* fallthrough */ + case IMX8MQ_RESET_PCIEPHY2: /* * wait for more than 10us to release phy g_rst and * btnrst @@ -232,12 +232,12 @@ static int imx8mq_reset_set(struct reset_controller_dev *rcdev, break; case IMX8MQ_RESET_PCIE_CTRL_APPS_EN: - case IMX8MQ_RESET_PCIE2_CTRL_APPS_EN: /* fallthrough */ - case IMX8MQ_RESET_MIPI_DSI_PCLK_RESET_N: /* fallthrough */ - case IMX8MQ_RESET_MIPI_DSI_ESC_RESET_N: /* fallthrough */ - case IMX8MQ_RESET_MIPI_DSI_DPI_RESET_N: /* fallthrough */ - case IMX8MQ_RESET_MIPI_DSI_RESET_N: /* fallthrough */ - case IMX8MQ_RESET_MIPI_DSI_RESET_BYTE_N: /* fallthrough */ + case IMX8MQ_RESET_PCIE2_CTRL_APPS_EN: + case IMX8MQ_RESET_MIPI_DSI_PCLK_RESET_N: + case IMX8MQ_RESET_MIPI_DSI_ESC_RESET_N: + case IMX8MQ_RESET_MIPI_DSI_DPI_RESET_N: + case IMX8MQ_RESET_MIPI_DSI_RESET_N: + case IMX8MQ_RESET_MIPI_DSI_RESET_BYTE_N: value = assert ? 0 : bit; break; } diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 1995f5b3ea67..f40312b16da0 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -553,7 +553,7 @@ static void qcom_glink_receive_version(struct qcom_glink *glink, break; case GLINK_VERSION_1: glink->features &= features; - /* FALLTHROUGH */ + fallthrough; default: qcom_glink_send_version_ack(glink); break; @@ -584,7 +584,7 @@ static void qcom_glink_receive_version_ack(struct qcom_glink *glink, break; glink->features &= features; - /* FALLTHROUGH */ + fallthrough; default: qcom_glink_send_version(glink); break; diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 9b70b371bd0c..8a89bc52b0d4 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -740,7 +740,7 @@ static int wdt_ioctl(struct file *file, unsigned int cmd, return -EINVAL; wdt_margin = new_margin; wdt_ping(); - /* Fall through */ + fallthrough; case WDIOC_GETTIMEOUT: return put_user(wdt_margin, (int __user *)arg); diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c index ca55ba975aeb..f8b99cb72959 100644 --- a/drivers/rtc/rtc-pcf85063.c +++ b/drivers/rtc/rtc-pcf85063.c @@ -353,7 +353,7 @@ static int pcf85063_load_capacitance(struct pcf85063 *pcf85063, default: dev_warn(&pcf85063->rtc->dev, "Unknown quartz-load-femtofarads value: %d. Assuming 7000", load); - /* fall through */ + fallthrough; case 7000: break; case 12500: diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c index 47e0f411dd5c..57d351dfe272 100644 --- a/drivers/rtc/rtc-pcf8523.c +++ b/drivers/rtc/rtc-pcf8523.c @@ -108,7 +108,7 @@ static int pcf8523_load_capacitance(struct i2c_client *client) default: dev_warn(&client->dev, "Unknown quartz-load-femtofarads value: %d. Assuming 12500", load); - /* fall through */ + fallthrough; case 12500: value |= REG_CONTROL1_CAP_SEL; break; diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c index c9bc3d4a1e66..0a969af80af7 100644 --- a/drivers/rtc/rtc-stmp3xxx.c +++ b/drivers/rtc/rtc-stmp3xxx.c @@ -331,7 +331,7 @@ static int stmp3xxx_rtc_probe(struct platform_device *pdev) default: dev_warn(&pdev->dev, "invalid crystal-freq specified in device-tree. Assuming no crystal\n"); - /* fall-through */ + fallthrough; case 0: /* keep XTAL on in low-power mode */ pers0_set = STMP3XXX_RTC_PERSISTENT0_XTAL24MHZ_PWRUP; diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 94edbb33d0d1..aca022239b33 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -677,6 +677,11 @@ static int slow_eval_known_fn(struct subchannel *sch, void *data) rc = css_evaluate_known_subchannel(sch, 1); if (rc == -EAGAIN) css_schedule_eval(sch->schid); + /* + * The loop might take long time for platforms with lots of + * known devices. Allow scheduling here. + */ + cond_resched(); } return 0; } diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig index 53120e68796e..bf236d474538 100644 --- a/drivers/s390/net/Kconfig +++ b/drivers/s390/net/Kconfig @@ -107,7 +107,7 @@ config QETH_OSX config CCWGROUP tristate - default (LCS || CTCM || QETH) + default (LCS || CTCM || QETH || SMC) config ISM tristate "Support for ISM vPCI Adapter" diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c index 3ce99e4db44d..661d2a49bce9 100644 --- a/drivers/s390/net/ctcm_fsms.c +++ b/drivers/s390/net/ctcm_fsms.c @@ -1695,7 +1695,7 @@ static void ctcmpc_chx_attnbusy(fsm_instance *fsm, int event, void *arg) grp->changed_side = 2; break; } - /* Else, fall through */ + fallthrough; case MPCG_STATE_XID0IOWAIX: case MPCG_STATE_XID7INITW: case MPCG_STATE_XID7INITX: diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index ab316baa8284..85a1a4533cbe 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -357,7 +357,7 @@ int ctc_mpc_alloc_channel(int port_num, void (*callback)(int, int)) /*fsm_newstate(grp->fsm, MPCG_STATE_XID2INITW);*/ if (callback) grp->send_qllc_disc = 1; - /* Else, fall through */ + fallthrough; case MPCG_STATE_XID0IOWAIT: fsm_deltimer(&grp->timer); grp->outstanding_xid2 = 0; @@ -1470,7 +1470,7 @@ static void mpc_action_timeout(fsm_instance *fi, int event, void *arg) if ((fsm_getstate(rch->fsm) == CH_XID0_PENDING) && (fsm_getstate(wch->fsm) == CH_XID0_PENDING)) break; - /* Else, fall through */ + fallthrough; default: fsm_event(grp->fsm, MPCG_EVENT_INOP, dev); } @@ -2089,7 +2089,7 @@ static int mpc_send_qllc_discontact(struct net_device *dev) grp->estconnfunc = NULL; break; } - /* Else, fall through */ + fallthrough; case MPCG_STATE_FLOWC: case MPCG_STATE_READY: grp->send_qllc_disc = 2; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index ecfd6d152e86..da46af682af8 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -420,12 +420,6 @@ struct qeth_qdio_out_buffer { struct qeth_card; -enum qeth_out_q_states { - QETH_OUT_Q_UNLOCKED, - QETH_OUT_Q_LOCKED, - QETH_OUT_Q_LOCKED_FLUSH, -}; - #define QETH_CARD_STAT_ADD(_c, _stat, _val) ((_c)->stats._stat += (_val)) #define QETH_CARD_STAT_INC(_c, _stat) QETH_CARD_STAT_ADD(_c, _stat, 1) @@ -486,12 +480,12 @@ struct qeth_qdio_out_q { struct qeth_qdio_out_buffer *bufs[QDIO_MAX_BUFFERS_PER_Q]; struct qdio_outbuf_state *bufstates; /* convenience pointer */ struct qeth_out_q_stats stats; + spinlock_t lock; u8 next_buf_to_fill; u8 max_elements; u8 queue_no; u8 do_pack; struct qeth_card *card; - atomic_t state; /* * number of buffers that are currently filled (PRIMED) * -> these buffers are hardware-owned @@ -680,6 +674,11 @@ struct qeth_card_blkt { int inter_packet_jumbo; }; +enum qeth_pnso_mode { + QETH_PNSO_NONE, + QETH_PNSO_BRIDGEPORT, +}; + #define QETH_BROADCAST_WITH_ECHO 0x01 #define QETH_BROADCAST_WITHOUT_ECHO 0x02 struct qeth_card_info { @@ -696,6 +695,7 @@ struct qeth_card_info { /* no bitfield, we take a pointer on these two: */ u8 has_lp2lp_cso_v6; u8 has_lp2lp_cso_v4; + enum qeth_pnso_mode pnso_mode; enum qeth_card_types type; enum qeth_link_types link_type; int broadcast_capable; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index bba1b54b8aa3..e19640bc6daa 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1071,7 +1071,7 @@ static void qeth_issue_next_read_cb(struct qeth_card *card, break; case -EIO: qeth_schedule_recovery(card); - /* fall through */ + fallthrough; default: qeth_clear_ipacmd_list(card); goto err_idx; @@ -2702,6 +2702,7 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) card->qdio.out_qs[i] = queue; queue->card = card; queue->queue_no = i; + spin_lock_init(&queue->lock); timer_setup(&queue->timer, qeth_tx_completion_timer, 0); queue->coalesce_usecs = QETH_TX_COALESCE_USECS; queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES; @@ -2886,7 +2887,7 @@ void qeth_print_status_message(struct qeth_card *card) card->info.mcl_level[3]); break; } - /* fallthrough */ + fallthrough; case QETH_CARD_TYPE_IQD: if (IS_VM_NIC(card) || (card->info.mcl_level[0] & 0x80)) { card->info.mcl_level[0] = (char) _ebcasc[(__u8) @@ -3068,7 +3069,6 @@ static int qeth_init_qdio_queues(struct qeth_card *card) queue->bulk_max = qeth_tx_select_bulk_max(card, queue); atomic_set(&queue->used_buffers, 0); atomic_set(&queue->set_pci_flags_count, 0); - atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED); netdev_tx_reset_queue(netdev_get_tx_queue(card->dev, i)); } return 0; @@ -3549,8 +3549,9 @@ static unsigned int qeth_rx_refill_queue(struct qeth_card *card, static void qeth_buffer_reclaim_work(struct work_struct *work) { - struct qeth_card *card = container_of(work, struct qeth_card, - buffer_reclaim_work.work); + struct qeth_card *card = container_of(to_delayed_work(work), + struct qeth_card, + buffer_reclaim_work); local_bh_disable(); napi_schedule(&card->napi); @@ -3740,37 +3741,31 @@ static void qeth_flush_queue(struct qeth_qdio_out_q *queue) static void qeth_check_outbound_queue(struct qeth_qdio_out_q *queue) { - int index; - int flush_cnt = 0; - int q_was_packing = 0; - /* * check if weed have to switch to non-packing mode or if * we have to get a pci flag out on the queue */ if ((atomic_read(&queue->used_buffers) <= QETH_LOW_WATERMARK_PACK) || !atomic_read(&queue->set_pci_flags_count)) { - if (atomic_xchg(&queue->state, QETH_OUT_Q_LOCKED_FLUSH) == - QETH_OUT_Q_UNLOCKED) { - /* - * If we get in here, there was no action in - * do_send_packet. So, we check if there is a - * packing buffer to be flushed here. - */ - index = queue->next_buf_to_fill; - q_was_packing = queue->do_pack; - /* queue->do_pack may change */ - barrier(); - flush_cnt += qeth_switch_to_nonpacking_if_needed(queue); - if (!flush_cnt && - !atomic_read(&queue->set_pci_flags_count)) - flush_cnt += qeth_prep_flush_pack_buffer(queue); + unsigned int index, flush_cnt; + bool q_was_packing; + + spin_lock(&queue->lock); + + index = queue->next_buf_to_fill; + q_was_packing = queue->do_pack; + + flush_cnt = qeth_switch_to_nonpacking_if_needed(queue); + if (!flush_cnt && !atomic_read(&queue->set_pci_flags_count)) + flush_cnt = qeth_prep_flush_pack_buffer(queue); + + if (flush_cnt) { + qeth_flush_buffers(queue, index, flush_cnt); if (q_was_packing) QETH_TXQ_STAT_ADD(queue, bufs_pack, flush_cnt); - if (flush_cnt) - qeth_flush_buffers(queue, index, flush_cnt); - atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED); } + + spin_unlock(&queue->lock); } } @@ -4282,29 +4277,22 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, unsigned int offset, unsigned int hd_len, int elements_needed) { + unsigned int start_index = queue->next_buf_to_fill; struct qeth_qdio_out_buffer *buffer; unsigned int next_element; struct netdev_queue *txq; bool stopped = false; - int start_index; int flush_count = 0; int do_pack = 0; - int tmp; int rc = 0; - /* spin until we get the queue ... */ - while (atomic_cmpxchg(&queue->state, QETH_OUT_Q_UNLOCKED, - QETH_OUT_Q_LOCKED) != QETH_OUT_Q_UNLOCKED); - start_index = queue->next_buf_to_fill; buffer = queue->bufs[queue->next_buf_to_fill]; /* Just a sanity check, the wake/stop logic should ensure that we always * get a free buffer. */ - if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY) { - atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED); + if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY) return -EBUSY; - } txq = netdev_get_tx_queue(card->dev, skb_get_queue_mapping(skb)); @@ -4327,8 +4315,6 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, QETH_QDIO_BUF_EMPTY) { qeth_flush_buffers(queue, start_index, flush_count); - atomic_set(&queue->state, - QETH_OUT_Q_UNLOCKED); rc = -EBUSY; goto out; } @@ -4360,31 +4346,8 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, if (flush_count) qeth_flush_buffers(queue, start_index, flush_count); - else if (!atomic_read(&queue->set_pci_flags_count)) - atomic_xchg(&queue->state, QETH_OUT_Q_LOCKED_FLUSH); - /* - * queue->state will go from LOCKED -> UNLOCKED or from - * LOCKED_FLUSH -> LOCKED if output_handler wanted to 'notify' us - * (switch packing state or flush buffer to get another pci flag out). - * In that case we will enter this loop - */ - while (atomic_dec_return(&queue->state)) { - start_index = queue->next_buf_to_fill; - /* check if we can go back to non-packing state */ - tmp = qeth_switch_to_nonpacking_if_needed(queue); - /* - * check if we need to flush a packing buffer to get a pci - * flag out on the queue - */ - if (!tmp && !atomic_read(&queue->set_pci_flags_count)) - tmp = qeth_prep_flush_pack_buffer(queue); - if (tmp) { - qeth_flush_buffers(queue, start_index, tmp); - flush_count += tmp; - } - } + out: - /* at this point the queue is UNLOCKED again */ if (do_pack) QETH_TXQ_STAT_ADD(queue, bufs_pack, flush_count); @@ -4458,8 +4421,10 @@ int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, } else { /* TODO: drop skb_orphan() once TX completion is fast enough */ skb_orphan(skb); + spin_lock(&queue->lock); rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset, hd_len, elements); + spin_unlock(&queue->lock); } if (rc && !push_len) diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index b459def0fb26..6541bab96822 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -719,15 +719,8 @@ struct qeth_sbp_port_entry { struct net_if_token token; } __packed; -struct qeth_sbp_query_ports { - __u8 primary_bp_supported; - __u8 secondary_bp_supported; - __u8 num_entries; - __u8 entry_length; - struct qeth_sbp_port_entry entry[]; -} __packed; - -struct qeth_sbp_state_change { +/* For IPA_SBP_QUERY_BRIDGE_PORTS, IPA_SBP_BRIDGE_PORT_STATE_CHANGE */ +struct qeth_sbp_port_data { __u8 primary_bp_supported; __u8 secondary_bp_supported; __u8 num_entries; @@ -741,8 +734,7 @@ struct qeth_ipacmd_setbridgeport { union { struct qeth_sbp_query_cmds_supp query_cmds_supp; struct qeth_sbp_set_primary set_primary; - struct qeth_sbp_query_ports query_ports; - struct qeth_sbp_state_change state_change; + struct qeth_sbp_port_data port_data; } data; } __packed; diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index ebdc03210608..f870c5322bfe 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -356,7 +356,7 @@ static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd, 10000baseT_Full); ethtool_link_ksettings_add_link_mode(cmd, advertising, 10000baseT_Full); - /* fall through */ + fallthrough; case SPEED_1000: ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full); @@ -366,7 +366,7 @@ static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd, 1000baseT_Half); ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Half); - /* fall through */ + fallthrough; case SPEED_100: ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Full); @@ -376,7 +376,7 @@ static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd, 100baseT_Half); ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half); - /* fall through */ + fallthrough; case SPEED_10: ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Full); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 8b342a88ff5c..491578009f12 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -273,6 +273,17 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, return qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN); } +static void qeth_l2_set_pnso_mode(struct qeth_card *card, + enum qeth_pnso_mode mode) +{ + spin_lock_irq(get_ccwdev_lock(CARD_RDEV(card))); + WRITE_ONCE(card->info.pnso_mode, mode); + spin_unlock_irq(get_ccwdev_lock(CARD_RDEV(card))); + + if (mode == QETH_PNSO_NONE) + drain_workqueue(card->event_wq); +} + static void qeth_l2_stop_card(struct qeth_card *card) { QETH_CARD_TEXT(card, 2, "stopcard"); @@ -290,7 +301,7 @@ static void qeth_l2_stop_card(struct qeth_card *card) qeth_qdio_clear_card(card, 0); qeth_clear_working_pool_list(card); - flush_workqueue(card->event_wq); + qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE); qeth_flush_local_addrs(card); card->info.promisc_mode = 0; } @@ -488,7 +499,7 @@ static void qeth_l2_rx_mode_work(struct work_struct *work) kfree(mac); break; } - /* fall through */ + fallthrough; default: /* for next call to set_rx_mode(): */ mac->disp_flag = QETH_DISP_ADDR_DELETE; @@ -810,8 +821,6 @@ static void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) if (card->options.sbp.hostnotification) { if (qeth_bridgeport_an_set(card, 1)) card->options.sbp.hostnotification = 0; - } else { - qeth_bridgeport_an_set(card, 0); } } @@ -1090,15 +1099,14 @@ static void qeth_bridge_emit_host_event(struct qeth_card *card, struct qeth_bridge_state_data { struct work_struct worker; struct qeth_card *card; - struct qeth_sbp_state_change qports; + u8 role; + u8 state; }; static void qeth_bridge_state_change_worker(struct work_struct *work) { struct qeth_bridge_state_data *data = container_of(work, struct qeth_bridge_state_data, worker); - /* We are only interested in the first entry - local port */ - struct qeth_sbp_port_entry *entry = &data->qports.entry[0]; char env_locrem[32]; char env_role[32]; char env_state[32]; @@ -1109,22 +1117,16 @@ static void qeth_bridge_state_change_worker(struct work_struct *work) NULL }; - /* Role should not change by itself, but if it did, */ - /* information from the hardware is authoritative. */ - mutex_lock(&data->card->sbp_lock); - data->card->options.sbp.role = entry->role; - mutex_unlock(&data->card->sbp_lock); - snprintf(env_locrem, sizeof(env_locrem), "BRIDGEPORT=statechange"); snprintf(env_role, sizeof(env_role), "ROLE=%s", - (entry->role == QETH_SBP_ROLE_NONE) ? "none" : - (entry->role == QETH_SBP_ROLE_PRIMARY) ? "primary" : - (entry->role == QETH_SBP_ROLE_SECONDARY) ? "secondary" : + (data->role == QETH_SBP_ROLE_NONE) ? "none" : + (data->role == QETH_SBP_ROLE_PRIMARY) ? "primary" : + (data->role == QETH_SBP_ROLE_SECONDARY) ? "secondary" : "<INVALID>"); snprintf(env_state, sizeof(env_state), "STATE=%s", - (entry->state == QETH_SBP_STATE_INACTIVE) ? "inactive" : - (entry->state == QETH_SBP_STATE_STANDBY) ? "standby" : - (entry->state == QETH_SBP_STATE_ACTIVE) ? "active" : + (data->state == QETH_SBP_STATE_INACTIVE) ? "inactive" : + (data->state == QETH_SBP_STATE_STANDBY) ? "standby" : + (data->state == QETH_SBP_STATE_ACTIVE) ? "active" : "<INVALID>"); kobject_uevent_env(&data->card->gdev->dev.kobj, KOBJ_CHANGE, env); @@ -1134,10 +1136,8 @@ static void qeth_bridge_state_change_worker(struct work_struct *work) static void qeth_bridge_state_change(struct qeth_card *card, struct qeth_ipa_cmd *cmd) { - struct qeth_sbp_state_change *qports = - &cmd->data.sbp.data.state_change; + struct qeth_sbp_port_data *qports = &cmd->data.sbp.data.port_data; struct qeth_bridge_state_data *data; - int extrasize; QETH_CARD_TEXT(card, 2, "brstchng"); if (qports->num_entries == 0) { @@ -1148,34 +1148,50 @@ static void qeth_bridge_state_change(struct qeth_card *card, QETH_CARD_TEXT_(card, 2, "BPsz%04x", qports->entry_length); return; } - extrasize = sizeof(struct qeth_sbp_port_entry) * qports->num_entries; - data = kzalloc(sizeof(struct qeth_bridge_state_data) + extrasize, - GFP_ATOMIC); + + data = kzalloc(sizeof(*data), GFP_ATOMIC); if (!data) { QETH_CARD_TEXT(card, 2, "BPSalloc"); return; } INIT_WORK(&data->worker, qeth_bridge_state_change_worker); data->card = card; - memcpy(&data->qports, qports, - sizeof(struct qeth_sbp_state_change) + extrasize); + /* Information for the local port: */ + data->role = qports->entry[0].role; + data->state = qports->entry[0].state; + queue_work(card->event_wq, &data->worker); } struct qeth_addr_change_data { - struct work_struct worker; + struct delayed_work dwork; struct qeth_card *card; struct qeth_ipacmd_addr_change ac_event; }; static void qeth_addr_change_event_worker(struct work_struct *work) { - struct qeth_addr_change_data *data = - container_of(work, struct qeth_addr_change_data, worker); + struct delayed_work *dwork = to_delayed_work(work); + struct qeth_addr_change_data *data; + struct qeth_card *card; int i; + data = container_of(dwork, struct qeth_addr_change_data, dwork); + card = data->card; + QETH_CARD_TEXT(data->card, 4, "adrchgew"); + + if (READ_ONCE(card->info.pnso_mode) == QETH_PNSO_NONE) + goto free; + if (data->ac_event.lost_event_mask) { + /* Potential re-config in progress, try again later: */ + if (!mutex_trylock(&card->sbp_lock)) { + queue_delayed_work(card->event_wq, dwork, + msecs_to_jiffies(100)); + return; + } + dev_info(&data->card->gdev->dev, "Address change notification stopped on %s (%s)\n", data->card->dev->name, @@ -1184,8 +1200,9 @@ static void qeth_addr_change_event_worker(struct work_struct *work) : (data->ac_event.lost_event_mask == 0x02) ? "Bridge port state change" : "Unknown reason"); - mutex_lock(&data->card->sbp_lock); + data->card->options.sbp.hostnotification = 0; + card->info.pnso_mode = QETH_PNSO_NONE; mutex_unlock(&data->card->sbp_lock); qeth_bridge_emit_host_event(data->card, anev_abort, 0, NULL, NULL); @@ -1199,6 +1216,8 @@ static void qeth_addr_change_event_worker(struct work_struct *work) &entry->token, &entry->addr_lnid); } + +free: kfree(data); } @@ -1210,6 +1229,9 @@ static void qeth_addr_change_event(struct qeth_card *card, struct qeth_addr_change_data *data; int extrasize; + if (card->info.pnso_mode == QETH_PNSO_NONE) + return; + QETH_CARD_TEXT(card, 4, "adrchgev"); if (cmd->hdr.return_code != 0x0000) { if (cmd->hdr.return_code == 0x0010) { @@ -1229,11 +1251,11 @@ static void qeth_addr_change_event(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "ACNalloc"); return; } - INIT_WORK(&data->worker, qeth_addr_change_event_worker); + INIT_DELAYED_WORK(&data->dwork, qeth_addr_change_event_worker); data->card = card; memcpy(&data->ac_event, hostevs, sizeof(struct qeth_ipacmd_addr_change) + extrasize); - queue_work(card->event_wq, &data->worker); + queue_delayed_work(card->event_wq, &data->dwork, 0); } /* SETBRIDGEPORT support; sending commands */ @@ -1418,8 +1440,8 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; - struct qeth_sbp_query_ports *qports = &cmd->data.sbp.data.query_ports; struct _qeth_sbp_cbctl *cbctl = (struct _qeth_sbp_cbctl *)reply->param; + struct qeth_sbp_port_data *qports; int rc; QETH_CARD_TEXT(card, 2, "brqprtcb"); @@ -1427,6 +1449,7 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, if (rc) return rc; + qports = &cmd->data.sbp.data.port_data; if (qports->entry_length != sizeof(struct qeth_sbp_port_entry)) { QETH_CARD_TEXT_(card, 2, "SBPs%04x", qports->entry_length); return -EINVAL; @@ -1554,9 +1577,14 @@ int qeth_bridgeport_an_set(struct qeth_card *card, int enable) if (enable) { qeth_bridge_emit_host_event(card, anev_reset, 0, NULL, NULL); + qeth_l2_set_pnso_mode(card, QETH_PNSO_BRIDGEPORT); rc = qeth_l2_pnso(card, 1, qeth_bridgeport_an_set_cb, card); - } else + if (rc) + qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE); + } else { rc = qeth_l2_pnso(card, 0, NULL, NULL); + qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE); + } return rc; } diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 86bcae992f72..4695d25e54f2 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -157,6 +157,7 @@ static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev, rc = -EBUSY; else if (qeth_card_hw_is_reachable(card)) { rc = qeth_bridgeport_an_set(card, enable); + /* sbp_lock ensures ordering vs notifications-stopped events */ if (!rc) card->options.sbp.hostnotification = enable; } else diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index fe44b0249e34..767c5bb7c24c 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -314,7 +314,8 @@ static int qeth_l3_setdelip_cb(struct qeth_card *card, struct qeth_reply *reply, } static int qeth_l3_send_setdelmc(struct qeth_card *card, - struct qeth_ipaddr *addr, int ipacmd) + struct qeth_ipaddr *addr, + enum qeth_ipa_cmds ipacmd) { struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; @@ -1235,7 +1236,7 @@ static void qeth_l3_rx_mode_work(struct work_struct *work) break; } addr->ref_counter = 1; - /* fall through */ + fallthrough; default: /* for next call to set_rx_mode(): */ addr->disp_flag = QETH_DISP_ADDR_DELETE; diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index c795f22249d8..140186fe1d1e 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -434,7 +434,7 @@ static void zfcp_fsf_req_complete(struct zfcp_fsf_req *req) return; } - del_timer(&req->timer); + del_timer_sync(&req->timer); zfcp_fsf_protstatus_eval(req); zfcp_fsf_fsfstatus_eval(req); req->handler(req); @@ -867,7 +867,7 @@ static int zfcp_fsf_req_send(struct zfcp_fsf_req *req) req->qdio_req.qdio_outb_usage = atomic_read(&qdio->req_q_free); req->issued = get_tod_clock(); if (zfcp_qdio_send(qdio, &req->qdio_req)) { - del_timer(&req->timer); + del_timer_sync(&req->timer); /* lookup request again, list might have changed */ zfcp_reqlist_find_rm(adapter->req_list, req_id); zfcp_erp_adapter_reopen(adapter, 0, "fsrs__1"); diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index 461b3babb601..84b57a8f86bf 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -1832,7 +1832,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *) case REQUEST_SENSE: /* clear the internal sense magic */ SCp->cmnd[6] = 0; - /* fall through */ + fallthrough; default: /* OK, get it from the command */ switch(SCp->sc_data_direction) { diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c index bb49d83cadc7..ccb061ab0a0a 100644 --- a/drivers/scsi/BusLogic.c +++ b/drivers/scsi/BusLogic.c @@ -2635,7 +2635,7 @@ static int blogic_resultcode(struct blogic_adapter *adapter, case BLOGIC_BAD_CMD_PARAM: blogic_warn("BusLogic Driver Protocol Error 0x%02X\n", adapter, adapter_status); - /* fall through */ + fallthrough; case BLOGIC_DATA_UNDERRUN: case BLOGIC_DATA_OVERRUN: case BLOGIC_NOEXPECT_BUSFREE: diff --git a/drivers/scsi/FlashPoint.c b/drivers/scsi/FlashPoint.c index 0f17bd51088a..24ace1824048 100644 --- a/drivers/scsi/FlashPoint.c +++ b/drivers/scsi/FlashPoint.c @@ -1034,11 +1034,14 @@ static int FlashPoint_ProbeHostAdapter(struct sccb_mgr_info *pCardInfo) temp6 >>= 1; switch (temp & 0x3) { case AUTO_RATE_20: /* Synchronous, 20 mega-transfers/second */ - temp6 |= 0x8000; /* Fall through */ + temp6 |= 0x8000; + fallthrough; case AUTO_RATE_10: /* Synchronous, 10 mega-transfers/second */ - temp5 |= 0x8000; /* Fall through */ + temp5 |= 0x8000; + fallthrough; case AUTO_RATE_05: /* Synchronous, 5 mega-transfers/second */ - temp2 |= 0x8000; /* Fall through */ + temp2 |= 0x8000; + fallthrough; case AUTO_RATE_00: /* Asynchronous */ break; } diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c index f2f7e6e76c07..d654a6cc4162 100644 --- a/drivers/scsi/NCR5380.c +++ b/drivers/scsi/NCR5380.c @@ -1943,7 +1943,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) return; /* Reject message */ - /* Fall through */ + fallthrough; default: /* * If we get something weird that we aren't expecting, diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index 769af4ca9ca9..fd6ae5c38086 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -2809,7 +2809,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd) !(dev->raw_io_64) || ((scsicmd->cmnd[1] & 0x1f) != SAI_READ_CAPACITY_16)) break; - /* fall through */ + fallthrough; case INQUIRY: case READ_CAPACITY: case TEST_UNIT_READY: @@ -2884,7 +2884,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd) /* Issue FIB to tell Firmware to flush it's cache */ if ((aac_cache & 6) != 2) return aac_synchronize(scsicmd); - /* fall through */ + fallthrough; case INQUIRY: { struct inquiry_data inq_data; @@ -3240,7 +3240,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd) SCSI_SENSE_BUFFERSIZE)); break; } - /* fall through */ + fallthrough; case RESERVE: case RELEASE: case REZERO_UNIT: @@ -3253,7 +3253,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd) case START_STOP: return aac_start_stop(scsicmd); - /* FALLTHRU */ + fallthrough; default: /* * Unhandled commands diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index adbdc3b7c7a7..383e74fea6ed 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -1431,7 +1431,7 @@ retry_next: "enclosure services event"); scsi_device_set_state(device, SDEV_RUNNING); } - /* FALLTHRU */ + fallthrough; case CHANGE: if ((channel == CONTAINER_CHANNEL) && (!dev->fsa_dev[container].valid)) { diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 8588da0a0655..a3aee146537b 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -765,7 +765,7 @@ static int aac_eh_abort(struct scsi_cmnd* cmd) !(aac->raw_io_64) || ((cmd->cmnd[1] & 0x1f) != SAI_READ_CAPACITY_16)) break; - /* fall through */ + fallthrough; case INQUIRY: case READ_CAPACITY: /* diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c index c912d29b8bdf..1c617c0d5899 100644 --- a/drivers/scsi/aic7xxx/aic79xx_core.c +++ b/drivers/scsi/aic7xxx/aic79xx_core.c @@ -2274,7 +2274,7 @@ ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat) switch (scb->hscb->task_management) { case SIU_TASKMGMT_ABORT_TASK: tag = SCB_GET_TAG(scb); - /* fall through */ + fallthrough; case SIU_TASKMGMT_ABORT_TASK_SET: case SIU_TASKMGMT_CLEAR_TASK_SET: lun = scb->hscb->lun; @@ -2285,7 +2285,7 @@ ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat) break; case SIU_TASKMGMT_LUN_RESET: lun = scb->hscb->lun; - /* fall through */ + fallthrough; case SIU_TASKMGMT_TARGET_RESET: { struct ahd_devinfo devinfo; @@ -3791,7 +3791,7 @@ ahd_validate_width(struct ahd_softc *ahd, struct ahd_initiator_tinfo *tinfo, *bus_width = MSG_EXT_WDTR_BUS_16_BIT; break; } - /* FALLTHROUGH */ + fallthrough; case MSG_EXT_WDTR_BUS_8_BIT: *bus_width = MSG_EXT_WDTR_BUS_8_BIT; break; @@ -5104,7 +5104,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) break; case MSG_MESSAGE_REJECT: response = ahd_handle_msg_reject(ahd, devinfo); - /* FALLTHROUGH */ + fallthrough; case MSG_NOOP: done = MSGLOOP_MSGCOMPLETE; break; @@ -5454,7 +5454,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) ahd_name(ahd), ahd_inb(ahd, SCSISIGI)); #endif ahd->msg_flags |= MSG_FLAG_EXPECT_QASREJ_BUSFREE; - /* FALLTHROUGH */ + fallthrough; case MSG_TERM_IO_PROC: default: reject = TRUE; @@ -6117,17 +6117,17 @@ ahd_free(struct ahd_softc *ahd) default: case 5: ahd_shutdown(ahd); - /* FALLTHROUGH */ + fallthrough; case 4: ahd_dmamap_unload(ahd, ahd->shared_data_dmat, ahd->shared_data_map.dmamap); - /* FALLTHROUGH */ + fallthrough; case 3: ahd_dmamem_free(ahd, ahd->shared_data_dmat, ahd->qoutfifo, ahd->shared_data_map.dmamap); ahd_dmamap_destroy(ahd, ahd->shared_data_dmat, ahd->shared_data_map.dmamap); - /* FALLTHROUGH */ + fallthrough; case 2: ahd_dma_tag_destroy(ahd, ahd->shared_data_dmat); case 1: @@ -6513,7 +6513,7 @@ ahd_fini_scbdata(struct ahd_softc *ahd) } ahd_dma_tag_destroy(ahd, scb_data->sense_dmat); } - /* fall through */ + fallthrough; case 6: { struct map_node *sg_map; @@ -6528,7 +6528,7 @@ ahd_fini_scbdata(struct ahd_softc *ahd) } ahd_dma_tag_destroy(ahd, scb_data->sg_dmat); } - /* fall through */ + fallthrough; case 5: { struct map_node *hscb_map; @@ -7171,7 +7171,7 @@ ahd_init(struct ahd_softc *ahd) case FLX_CSTAT_OVER: case FLX_CSTAT_UNDER: warn_user++; - /* fall through */ + fallthrough; case FLX_CSTAT_INVALID: case FLX_CSTAT_OKAY: if (warn_user == 0 && bootverbose == 0) @@ -8175,12 +8175,12 @@ ahd_search_qinfifo(struct ahd_softc *ahd, int target, char channel, if ((scb->flags & SCB_ACTIVE) == 0) printk("Inactive SCB in qinfifo\n"); ahd_done_with_status(ahd, scb, status); - /* FALLTHROUGH */ + fallthrough; case SEARCH_REMOVE: break; case SEARCH_PRINT: printk(" 0x%x", ahd->qinfifo[qinpos]); - /* FALLTHROUGH */ + fallthrough; case SEARCH_COUNT: ahd_qinfifo_requeue(ahd, prev_scb, scb); prev_scb = scb; @@ -8271,7 +8271,7 @@ ahd_search_qinfifo(struct ahd_softc *ahd, int target, char channel, if ((mk_msg_scb->flags & SCB_ACTIVE) == 0) printk("Inactive SCB pending MK_MSG\n"); ahd_done_with_status(ahd, mk_msg_scb, status); - /* FALLTHROUGH */ + fallthrough; case SEARCH_REMOVE: { u_int tail_offset; @@ -8295,7 +8295,7 @@ ahd_search_qinfifo(struct ahd_softc *ahd, int target, char channel, } case SEARCH_PRINT: printk(" 0x%x", SCB_GET_TAG(scb)); - /* FALLTHROUGH */ + fallthrough; case SEARCH_COUNT: break; } @@ -8376,7 +8376,7 @@ ahd_search_scb_list(struct ahd_softc *ahd, int target, char channel, if ((scb->flags & SCB_ACTIVE) == 0) printk("Inactive SCB in Waiting List\n"); ahd_done_with_status(ahd, scb, status); - /* fall through */ + fallthrough; case SEARCH_REMOVE: ahd_rem_wscb(ahd, scbid, prev, next, tid); *list_tail = prev; @@ -8385,7 +8385,7 @@ ahd_search_scb_list(struct ahd_softc *ahd, int target, char channel, break; case SEARCH_PRINT: printk("0x%x ", scbid); - /* fall through */ + fallthrough; case SEARCH_COUNT: prev = scbid; break; @@ -9023,7 +9023,7 @@ ahd_handle_scsi_status(struct ahd_softc *ahd, struct scb *scb) case SCSI_STATUS_OK: printk("%s: Interrupted for status of 0???\n", ahd_name(ahd)); - /* FALLTHROUGH */ + fallthrough; default: ahd_done(ahd, scb); break; @@ -9512,7 +9512,7 @@ ahd_download_instr(struct ahd_softc *ahd, u_int instrptr, uint8_t *dconsts) fmt3_ins = &instr.format3; fmt3_ins->address = ahd_resolve_seqaddr(ahd, fmt3_ins->address); } - /* fall through */ + fallthrough; case AIC_OP_OR: case AIC_OP_AND: case AIC_OP_XOR: @@ -9523,7 +9523,7 @@ ahd_download_instr(struct ahd_softc *ahd, u_int instrptr, uint8_t *dconsts) fmt1_ins->immediate = dconsts[fmt1_ins->immediate]; } fmt1_ins->parity = 0; - /* fall through */ + fallthrough; case AIC_OP_ROL: { int i, count; diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c index d019e3f2bb9b..7c321303969e 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.c +++ b/drivers/scsi/aic7xxx/aic79xx_osm.c @@ -2035,7 +2035,7 @@ ahd_linux_queue_cmd_complete(struct ahd_softc *ahd, struct scsi_cmnd *cmd) break; case CAM_AUTOSENSE_FAIL: new_status = DID_ERROR; - /* Fallthrough */ + fallthrough; case CAM_SCSI_STATUS_ERROR: scsi_status = ahd_cmd_get_scsi_status(cmd); diff --git a/drivers/scsi/aic7xxx/aic7xxx_core.c b/drivers/scsi/aic7xxx/aic7xxx_core.c index 3d4df906fa4f..2231c4afa531 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_core.c +++ b/drivers/scsi/aic7xxx/aic7xxx_core.c @@ -2404,7 +2404,7 @@ ahc_validate_width(struct ahc_softc *ahc, struct ahc_initiator_tinfo *tinfo, *bus_width = MSG_EXT_WDTR_BUS_16_BIT; break; } - /* FALLTHROUGH */ + fallthrough; case MSG_EXT_WDTR_BUS_8_BIT: *bus_width = MSG_EXT_WDTR_BUS_8_BIT; break; @@ -3599,7 +3599,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) break; case MSG_MESSAGE_REJECT: response = ahc_handle_msg_reject(ahc, devinfo); - /* FALLTHROUGH */ + fallthrough; case MSG_NOOP: done = MSGLOOP_MSGCOMPLETE; break; @@ -4465,17 +4465,17 @@ ahc_free(struct ahc_softc *ahc) default: case 5: ahc_shutdown(ahc); - /* FALLTHROUGH */ + fallthrough; case 4: ahc_dmamap_unload(ahc, ahc->shared_data_dmat, ahc->shared_data_dmamap); - /* FALLTHROUGH */ + fallthrough; case 3: ahc_dmamem_free(ahc, ahc->shared_data_dmat, ahc->qoutfifo, ahc->shared_data_dmamap); ahc_dmamap_destroy(ahc, ahc->shared_data_dmat, ahc->shared_data_dmamap); - /* FALLTHROUGH */ + fallthrough; case 2: ahc_dma_tag_destroy(ahc, ahc->shared_data_dmat); case 1: @@ -4893,30 +4893,30 @@ ahc_fini_scbdata(struct ahc_softc *ahc) } ahc_dma_tag_destroy(ahc, scb_data->sg_dmat); } - /* fall through */ + fallthrough; case 6: ahc_dmamap_unload(ahc, scb_data->sense_dmat, scb_data->sense_dmamap); - /* fall through */ + fallthrough; case 5: ahc_dmamem_free(ahc, scb_data->sense_dmat, scb_data->sense, scb_data->sense_dmamap); ahc_dmamap_destroy(ahc, scb_data->sense_dmat, scb_data->sense_dmamap); - /* fall through */ + fallthrough; case 4: ahc_dma_tag_destroy(ahc, scb_data->sense_dmat); - /* fall through */ + fallthrough; case 3: ahc_dmamap_unload(ahc, scb_data->hscb_dmat, scb_data->hscb_dmamap); - /* fall through */ + fallthrough; case 2: ahc_dmamem_free(ahc, scb_data->hscb_dmat, scb_data->hscbs, scb_data->hscb_dmamap); ahc_dmamap_destroy(ahc, scb_data->hscb_dmat, scb_data->hscb_dmamap); - /* fall through */ + fallthrough; case 1: ahc_dma_tag_destroy(ahc, scb_data->hscb_dmat); break; @@ -5981,7 +5981,7 @@ ahc_search_qinfifo(struct ahc_softc *ahc, int target, char channel, printk("Inactive SCB in Waiting List\n"); ahc_done(ahc, scb); } - /* fall through */ + fallthrough; case SEARCH_REMOVE: next = ahc_rem_wscb(ahc, next, prev); break; @@ -6987,7 +6987,7 @@ ahc_download_instr(struct ahc_softc *ahc, u_int instrptr, uint8_t *dconsts) address -= address_offset; fmt3_ins->address = address; } - /* fall through */ + fallthrough; case AIC_OP_OR: case AIC_OP_AND: case AIC_OP_XOR: @@ -7013,7 +7013,7 @@ ahc_download_instr(struct ahc_softc *ahc, u_int instrptr, uint8_t *dconsts) fmt1_ins->opcode = AIC_OP_AND; fmt1_ins->immediate = 0xff; } - /* fall through */ + fallthrough; case AIC_OP_ROL: if ((ahc->features & AHC_ULTRA2) != 0) { int i, count; diff --git a/drivers/scsi/aic94xx/aic94xx_scb.c b/drivers/scsi/aic94xx/aic94xx_scb.c index c264b4b56970..e2d880a5f391 100644 --- a/drivers/scsi/aic94xx/aic94xx_scb.c +++ b/drivers/scsi/aic94xx/aic94xx_scb.c @@ -706,11 +706,11 @@ static void set_speed_mask(u8 *speed_mask, struct asd_phy_desc *pd) switch (pd->max_sas_lrate) { case SAS_LINK_RATE_6_0_GBPS: *speed_mask &= ~SAS_SPEED_60_DIS; - /* fall through*/ + fallthrough; default: case SAS_LINK_RATE_3_0_GBPS: *speed_mask &= ~SAS_SPEED_30_DIS; - /* fall through*/ + fallthrough; case SAS_LINK_RATE_1_5_GBPS: *speed_mask &= ~SAS_SPEED_15_DIS; } @@ -718,7 +718,7 @@ static void set_speed_mask(u8 *speed_mask, struct asd_phy_desc *pd) switch (pd->min_sas_lrate) { case SAS_LINK_RATE_6_0_GBPS: *speed_mask |= SAS_SPEED_30_DIS; - /* fall through*/ + fallthrough; case SAS_LINK_RATE_3_0_GBPS: *speed_mask |= SAS_SPEED_15_DIS; default: @@ -730,7 +730,7 @@ static void set_speed_mask(u8 *speed_mask, struct asd_phy_desc *pd) switch (pd->max_sata_lrate) { case SAS_LINK_RATE_3_0_GBPS: *speed_mask &= ~SATA_SPEED_30_DIS; - /* fall through*/ + fallthrough; default: case SAS_LINK_RATE_1_5_GBPS: *speed_mask &= ~SATA_SPEED_15_DIS; @@ -789,7 +789,7 @@ void asd_build_control_phy(struct asd_ascb *ascb, int phy_id, u8 subfunc) /* link reset retries, this should be nominal */ control_phy->link_reset_retries = 10; - /* fall through */ + fallthrough; case RELEASE_SPINUP_HOLD: /* 0x02 */ /* decide the func_mask */ diff --git a/drivers/scsi/aic94xx/aic94xx_tmf.c b/drivers/scsi/aic94xx/aic94xx_tmf.c index 1fcee65193a3..0eb6e206a2b4 100644 --- a/drivers/scsi/aic94xx/aic94xx_tmf.c +++ b/drivers/scsi/aic94xx/aic94xx_tmf.c @@ -490,7 +490,7 @@ int asd_abort_task(struct sas_task *task) switch (tcs.dl_opcode) { default: res = asd_clear_nexus(task); - /* fallthrough */ + fallthrough; case TC_NO_ERROR: break; /* The task hasn't been sent to the device xor diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index fa562a085600..ec895d0319f0 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -4470,7 +4470,7 @@ static const char *arcmsr_info(struct Scsi_Host *host) case PCI_DEVICE_ID_ARECA_1202: case PCI_DEVICE_ID_ARECA_1210: raid6 = 0; - /*FALLTHRU*/ + fallthrough; case PCI_DEVICE_ID_ARECA_1120: case PCI_DEVICE_ID_ARECA_1130: case PCI_DEVICE_ID_ARECA_1160: diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c index 6c68c2303638..2e687ce60753 100644 --- a/drivers/scsi/arm/fas216.c +++ b/drivers/scsi/arm/fas216.c @@ -603,7 +603,7 @@ static void fas216_handlesync(FAS216_Info *info, char *msg) msgqueue_flush(&info->scsi.msgs); msgqueue_addmsg(&info->scsi.msgs, 1, MESSAGE_REJECT); info->scsi.phase = PHASE_MSGOUT_EXPECT; - /* fall through */ + fallthrough; case async: dev->period = info->ifcfg.asyncperiod / 4; @@ -916,7 +916,7 @@ static void fas216_disconnect_intr(FAS216_Info *info) fas216_done(info, DID_ABORT); break; } - /* else, fall through */ + fallthrough; default: /* huh? */ printk(KERN_ERR "scsi%d.%c: unexpected disconnect in phase %s\n", @@ -1413,7 +1413,7 @@ static void fas216_busservice_intr(FAS216_Info *info, unsigned int stat, unsigne case STATE(STAT_STATUS, PHASE_DATAOUT): /* Data Out -> Status */ case STATE(STAT_STATUS, PHASE_DATAIN): /* Data In -> Status */ fas216_stoptransfer(info); - /* fall through */ + fallthrough; case STATE(STAT_STATUS, PHASE_SELSTEPS):/* Sel w/ steps -> Status */ case STATE(STAT_STATUS, PHASE_MSGOUT): /* Message Out -> Status */ @@ -1426,7 +1426,7 @@ static void fas216_busservice_intr(FAS216_Info *info, unsigned int stat, unsigne case STATE(STAT_MESGIN, PHASE_DATAOUT): /* Data Out -> Message In */ case STATE(STAT_MESGIN, PHASE_DATAIN): /* Data In -> Message In */ fas216_stoptransfer(info); - /* fall through */ + fallthrough; case STATE(STAT_MESGIN, PHASE_COMMAND): /* Command -> Message In */ case STATE(STAT_MESGIN, PHASE_SELSTEPS):/* Sel w/ steps -> Message In */ @@ -1581,7 +1581,7 @@ static void fas216_funcdone_intr(FAS216_Info *info, unsigned int stat, unsigned fas216_message(info); break; } - /* else, fall through */ + fallthrough; default: fas216_log(info, 0, "internal phase %s for function done?" @@ -1964,7 +1964,7 @@ static void fas216_kick(FAS216_Info *info) switch (where_from) { case TYPE_QUEUE: fas216_allocate_tag(info, SCpnt); - /* fall through */ + fallthrough; case TYPE_OTHER: fas216_start_command(info, SCpnt); break; diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c index 93da6344424d..a13c203ef7a9 100644 --- a/drivers/scsi/be2iscsi/be_iscsi.c +++ b/drivers/scsi/be2iscsi/be_iscsi.c @@ -677,7 +677,7 @@ int beiscsi_set_param(struct iscsi_cls_conn *cls_conn, case ISCSI_PARAM_MAX_XMIT_DLENGTH: if (conn->max_xmit_dlength > 65536) conn->max_xmit_dlength = 65536; - /* fall through */ + fallthrough; default: return 0; } diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 8dc2e0824ad7..5c3513a4b450 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -1532,7 +1532,7 @@ beiscsi_hdl_get_handle(struct beiscsi_conn *beiscsi_conn, break; case UNSOL_DATA_DIGEST_ERROR_NOTIFY: error = 1; - /* fall through */ + fallthrough; case UNSOL_DATA_NOTIFY: pasync_handle = pasync_ctx->async_entry[ci].data; break; diff --git a/drivers/scsi/bfa/bfa_fcpim.c b/drivers/scsi/bfa/bfa_fcpim.c index 29f99561dfc3..38d1c453074d 100644 --- a/drivers/scsi/bfa/bfa_fcpim.c +++ b/drivers/scsi/bfa/bfa_fcpim.c @@ -2572,7 +2572,7 @@ bfa_ioim_send_ioreq(struct bfa_ioim_s *ioim) case FCP_IODIR_RW: bfa_stats(itnim, input_reqs); bfa_stats(itnim, output_reqs); - /* fall through */ + fallthrough; default: bfi_h2i_set(m->mh, BFI_MC_IOIM_IO, 0, bfa_fn_lpu(ioim->bfa)); } @@ -2807,7 +2807,7 @@ bfa_ioim_isr(struct bfa_s *bfa, struct bfi_msg_s *m) case BFI_IOIM_STS_TIMEDOUT: bfa_stats(ioim->itnim, iocomp_timedout); - /* fall through */ + fallthrough; case BFI_IOIM_STS_ABORTED: rsp->io_status = BFI_IOIM_STS_ABORTED; bfa_stats(ioim->itnim, iocomp_aborted); @@ -3203,7 +3203,7 @@ bfa_tskim_sm_cleanup_qfull(struct bfa_tskim_s *tskim, switch (event) { case BFA_TSKIM_SM_DONE: bfa_reqq_wcancel(&tskim->reqq_wait); - /* fall through */ + fallthrough; case BFA_TSKIM_SM_QRESUME: bfa_sm_set_state(tskim, bfa_tskim_sm_cleanup); bfa_tskim_send_abort(tskim); diff --git a/drivers/scsi/bfa/bfa_fcs_lport.c b/drivers/scsi/bfa/bfa_fcs_lport.c index 297a77f5806c..3486e402bfc1 100644 --- a/drivers/scsi/bfa/bfa_fcs_lport.c +++ b/drivers/scsi/bfa/bfa_fcs_lport.c @@ -6422,7 +6422,7 @@ bfa_fcs_vport_sm_logo_for_stop(struct bfa_fcs_vport_s *vport, switch (event) { case BFA_FCS_VPORT_SM_OFFLINE: bfa_sm_send_event(vport->lps, BFA_LPS_SM_OFFLINE); - /* fall through */ + fallthrough; case BFA_FCS_VPORT_SM_RSP_OK: case BFA_FCS_VPORT_SM_RSP_ERROR: @@ -6448,7 +6448,7 @@ bfa_fcs_vport_sm_logo(struct bfa_fcs_vport_s *vport, switch (event) { case BFA_FCS_VPORT_SM_OFFLINE: bfa_sm_send_event(vport->lps, BFA_LPS_SM_OFFLINE); - /* fall through */ + fallthrough; case BFA_FCS_VPORT_SM_RSP_OK: case BFA_FCS_VPORT_SM_RSP_ERROR: diff --git a/drivers/scsi/bfa/bfa_fcs_rport.c b/drivers/scsi/bfa/bfa_fcs_rport.c index 143c35bd668c..c21aa37b8adb 100644 --- a/drivers/scsi/bfa/bfa_fcs_rport.c +++ b/drivers/scsi/bfa/bfa_fcs_rport.c @@ -419,13 +419,13 @@ bfa_fcs_rport_sm_plogi(struct bfa_fcs_rport_s *rport, enum rport_event event) case RPSM_EVENT_LOGO_RCVD: bfa_fcs_rport_send_logo_acc(rport); - /* fall through */ + fallthrough; case RPSM_EVENT_PRLO_RCVD: if (rport->prlo == BFA_TRUE) bfa_fcs_rport_send_prlo_acc(rport); bfa_fcxp_discard(rport->fcxp); - /* fall through */ + fallthrough; case RPSM_EVENT_FAILED: if (rport->plogi_retries < BFA_FCS_RPORT_MAX_RETRIES) { rport->plogi_retries++; @@ -856,7 +856,7 @@ bfa_fcs_rport_sm_adisc_online(struct bfa_fcs_rport_s *rport, * At least go offline when a PLOGI is received. */ bfa_fcxp_discard(rport->fcxp); - /* fall through */ + fallthrough; case RPSM_EVENT_FAILED: case RPSM_EVENT_ADDRESS_CHANGE: @@ -1042,7 +1042,7 @@ bfa_fcs_rport_sm_fc4_logosend(struct bfa_fcs_rport_s *rport, case RPSM_EVENT_LOGO_RCVD: bfa_fcs_rport_send_logo_acc(rport); - /* fall through */ + fallthrough; case RPSM_EVENT_PRLO_RCVD: if (rport->prlo == BFA_TRUE) bfa_fcs_rport_send_prlo_acc(rport); @@ -1131,7 +1131,7 @@ bfa_fcs_rport_sm_hcb_offline(struct bfa_fcs_rport_s *rport, bfa_fcs_rport_send_plogiacc(rport, NULL); break; } - /* fall through */ + fallthrough; case RPSM_EVENT_ADDRESS_CHANGE: if (!bfa_fcs_lport_is_online(rport->port)) { @@ -1288,7 +1288,7 @@ bfa_fcs_rport_sm_hcb_logosend(struct bfa_fcs_rport_s *rport, case RPSM_EVENT_LOGO_RCVD: bfa_fcs_rport_send_logo_acc(rport); - /* fall through */ + fallthrough; case RPSM_EVENT_PRLO_RCVD: if (rport->prlo == BFA_TRUE) bfa_fcs_rport_send_prlo_acc(rport); @@ -1332,7 +1332,7 @@ bfa_fcs_rport_sm_logo_sending(struct bfa_fcs_rport_s *rport, case RPSM_EVENT_LOGO_RCVD: bfa_fcs_rport_send_logo_acc(rport); - /* fall through */ + fallthrough; case RPSM_EVENT_PRLO_RCVD: if (rport->prlo == BFA_TRUE) bfa_fcs_rport_send_prlo_acc(rport); diff --git a/drivers/scsi/bfa/bfa_ioc.c b/drivers/scsi/bfa/bfa_ioc.c index dd5821dfcac2..325ad8a592bb 100644 --- a/drivers/scsi/bfa/bfa_ioc.c +++ b/drivers/scsi/bfa/bfa_ioc.c @@ -969,7 +969,7 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf_s *iocpf, enum iocpf_event event) case IOCPF_E_INITFAIL: bfa_iocpf_timer_stop(ioc); - /* fall through */ + fallthrough; case IOCPF_E_TIMEOUT: writel(1, ioc->ioc_regs.ioc_sem_reg); @@ -1045,7 +1045,7 @@ bfa_iocpf_sm_disabling(struct bfa_iocpf_s *iocpf, enum iocpf_event event) case IOCPF_E_FAIL: bfa_iocpf_timer_stop(ioc); - /* fall through */ + fallthrough; case IOCPF_E_TIMEOUT: bfa_ioc_set_cur_ioc_fwstate(ioc, BFI_IOC_FAIL); @@ -5988,7 +5988,7 @@ bfa_dconf_sm_final_sync(struct bfa_dconf_mod_s *dconf, case BFA_DCONF_SM_IOCDISABLE: case BFA_DCONF_SM_FLASH_COMP: bfa_timer_stop(&dconf->timer); - /* fall through */ + fallthrough; case BFA_DCONF_SM_TIMEOUT: bfa_sm_set_state(dconf, bfa_dconf_sm_uninit); bfa_fsm_send_event(&dconf->bfa->iocfc, IOCFC_E_DCONF_DONE); diff --git a/drivers/scsi/bfa/bfa_svc.c b/drivers/scsi/bfa/bfa_svc.c index 1e266c1ef793..11c0c3e6f014 100644 --- a/drivers/scsi/bfa/bfa_svc.c +++ b/drivers/scsi/bfa/bfa_svc.c @@ -6397,7 +6397,7 @@ bfa_dport_sm_starting(struct bfa_dport_s *dport, enum bfa_dport_sm_event event) dport->test_state = BFA_DPORT_ST_INP; bfa_dport_result_start(dport, BFA_DPORT_OPMODE_MANU); } - /* fall thru */ + fallthrough; case BFA_DPORT_SM_REQFAIL: bfa_sm_set_state(dport, bfa_dport_sm_enabled); diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index e72d7bb7f4f4..08992095ce7a 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -1404,7 +1404,6 @@ void bnx2fc_indicate_kcqe(void *context, struct kcqe *kcq[], break; case FCOE_KCQE_OPCODE_FCOE_ERROR: - /* fall thru */ default: printk(KERN_ERR PFX "unknown opcode 0x%x\n", kcqe->op_code); diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c index 98d4d39aaa57..7fa20609d5e7 100644 --- a/drivers/scsi/csiostor/csio_hw.c +++ b/drivers/scsi/csiostor/csio_hw.c @@ -2939,7 +2939,7 @@ csio_hws_quiescing(struct csio_hw *hw, enum csio_hw_ev evt) case CSIO_HWE_FW_DLOAD: csio_set_state(&hw->sm, csio_hws_resetting); /* Download firmware */ - /* Fall through */ + fallthrough; case CSIO_HWE_HBA_RESET: csio_set_state(&hw->sm, csio_hws_resetting); diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c index 61cf54208451..dc98f51f466f 100644 --- a/drivers/scsi/csiostor/csio_lnode.c +++ b/drivers/scsi/csiostor/csio_lnode.c @@ -1187,7 +1187,6 @@ csio_lns_online(struct csio_lnode *ln, enum csio_ln_ev evt) break; case CSIO_LNE_LINK_DOWN: - /* Fall through */ case CSIO_LNE_DOWN_LINK: csio_set_state(&ln->sm, csio_lns_uninit); if (csio_is_phys_ln(ln)) { diff --git a/drivers/scsi/csiostor/csio_wr.c b/drivers/scsi/csiostor/csio_wr.c index 0ca695110f54..9010cb6045dc 100644 --- a/drivers/scsi/csiostor/csio_wr.c +++ b/drivers/scsi/csiostor/csio_wr.c @@ -808,7 +808,7 @@ csio_wr_destroy_queues(struct csio_hw *hw, bool cmd) csio_q_eqid(hw, i) = CSIO_MAX_QID; } - /* fall through */ + fallthrough; case CSIO_INGRESS: if (csio_q_iqid(hw, i) != CSIO_MAX_QID) { csio_wr_cleanup_iq_ftr(hw, i); diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c index 2b48954b6b1e..37d99357120f 100644 --- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c +++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c @@ -643,7 +643,7 @@ static int abort_status_to_errno(struct cxgbi_sock *csk, int abort_reason, int *need_rst) { switch (abort_reason) { - case CPL_ERR_BAD_SYN: /* fall through */ + case CPL_ERR_BAD_SYN: case CPL_ERR_CONN_RESET: return csk->state > CTP_ESTABLISHED ? -EPIPE : -ECONNRESET; case CPL_ERR_XMIT_TIMEDOUT: diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c index 4e82c14cb795..2c3491528d42 100644 --- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c +++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c @@ -1133,7 +1133,7 @@ static int abort_status_to_errno(struct cxgbi_sock *csk, int abort_reason, int *need_rst) { switch (abort_reason) { - case CPL_ERR_BAD_SYN: /* fall through */ + case CPL_ERR_BAD_SYN: case CPL_ERR_CONN_RESET: return csk->state > CTP_ESTABLISHED ? -EPIPE : -ECONNRESET; diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 71aebaf533ea..0e8621a6956d 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -2457,10 +2457,10 @@ int cxgbi_conn_xmit_pdu(struct iscsi_task *task) return err; } - __kfree_skb(skb); log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX, "itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n", task->itt, skb, skb->len, skb->data_len, err); + __kfree_skb(skb); iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err); iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED); return err; diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 94250ebe9e80..e72440d919d2 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -748,16 +748,16 @@ static void term_intr(struct cxlflash_cfg *cfg, enum undo_level level, /* SISL_MSI_ASYNC_ERROR is setup only for the primary HWQ */ if (index == PRIMARY_HWQ) cfg->ops->unmap_afu_irq(hwq->ctx_cookie, 3, hwq); - /* fall through */ + fallthrough; case UNMAP_TWO: cfg->ops->unmap_afu_irq(hwq->ctx_cookie, 2, hwq); - /* fall through */ + fallthrough; case UNMAP_ONE: cfg->ops->unmap_afu_irq(hwq->ctx_cookie, 1, hwq); - /* fall through */ + fallthrough; case FREE_IRQ: cfg->ops->free_afu_irqs(hwq->ctx_cookie); - /* fall through */ + fallthrough; case UNDO_NOOP: /* No action required */ break; @@ -971,18 +971,18 @@ static void cxlflash_remove(struct pci_dev *pdev) switch (cfg->init_state) { case INIT_STATE_CDEV: cxlflash_release_chrdev(cfg); - /* fall through */ + fallthrough; case INIT_STATE_SCSI: cxlflash_term_local_luns(cfg); scsi_remove_host(cfg->host); - /* fall through */ + fallthrough; case INIT_STATE_AFU: term_afu(cfg); - /* fall through */ + fallthrough; case INIT_STATE_PCI: cfg->ops->destroy_afu(cfg->afu_cookie); pci_disable_device(pdev); - /* fall through */ + fallthrough; case INIT_STATE_NONE: free_mem(cfg); scsi_host_put(cfg->host); @@ -2355,11 +2355,11 @@ retry: cxlflash_schedule_async_reset(cfg); break; } - /* fall through - to retry */ + fallthrough; /* to retry */ case -EAGAIN: if (++nretry < 2) goto retry; - /* fall through - to exit */ + fallthrough; /* to exit */ default: break; } @@ -2533,12 +2533,12 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp) cfg->state = STATE_NORMAL; wake_up_all(&cfg->reset_waitq); ssleep(1); - /* fall through */ + fallthrough; case STATE_RESET: wait_event(cfg->reset_waitq, cfg->state != STATE_RESET); if (cfg->state == STATE_NORMAL) break; - /* fall through */ + fallthrough; default: rc = FAILED; break; @@ -3019,7 +3019,7 @@ retry: wait_event(cfg->reset_waitq, cfg->state != STATE_RESET); if (cfg->state == STATE_NORMAL) goto retry; - /* else, fall through */ + fallthrough; default: /* Ideally should not happen */ dev_err(dev, "%s: Device is not ready, state=%d\n", @@ -3531,7 +3531,7 @@ static long cxlflash_chr_ioctl(struct file *file, unsigned int cmd, if (likely(do_ioctl)) break; - /* fall through */ + fallthrough; default: rc = -EINVAL; goto out; diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c index 593669ac3669..5dddf67dfa24 100644 --- a/drivers/scsi/cxlflash/superpipe.c +++ b/drivers/scsi/cxlflash/superpipe.c @@ -375,14 +375,13 @@ retry: switch (sshdr.sense_key) { case NO_SENSE: case RECOVERED_ERROR: - /* fall through */ case NOT_READY: result &= ~SAM_STAT_CHECK_CONDITION; break; case UNIT_ATTENTION: switch (sshdr.asc) { case 0x29: /* Power on Reset or Device Reset */ - /* fall through */ + fallthrough; case 0x2A: /* Device capacity changed */ case 0x3F: /* Report LUNs changed */ /* Retry the command once more */ @@ -1791,13 +1790,12 @@ static int process_sense(struct scsi_device *sdev, switch (sshdr.sense_key) { case NO_SENSE: case RECOVERED_ERROR: - /* fall through */ case NOT_READY: break; case UNIT_ATTENTION: switch (sshdr.asc) { case 0x29: /* Power on Reset or Device Reset */ - /* fall through */ + fallthrough; case 0x2A: /* Device settings/capacity changed */ rc = read_cap16(sdev, lli); if (rc) { @@ -2157,7 +2155,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, unsigned int cmd, void __user *arg) if (unlikely(rc)) goto cxlflash_ioctl_exit; - /* fall through */ + fallthrough; case DK_CXLFLASH_MANAGE_LUN: known_ioctl = true; @@ -2168,7 +2166,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, unsigned int cmd, void __user *arg) if (likely(do_ioctl)) break; - /* fall through */ + fallthrough; default: rc = -EINVAL; goto cxlflash_ioctl_exit; diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c index 8acd4bb9fefb..4a3f7831a2d6 100644 --- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c +++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c @@ -60,7 +60,7 @@ static int tur_done(struct scsi_device *sdev, struct hp_sw_dh_data *h, ret = SCSI_DH_OK; break; } - /* Fallthrough */ + fallthrough; default: sdev_printk(KERN_WARNING, sdev, "%s: sending tur failed, sense %x/%x/%x\n", @@ -147,7 +147,7 @@ retry: rc = SCSI_DH_RETRY; break; } - /* fall through */ + fallthrough; default: sdev_printk(KERN_WARNING, sdev, "%s: sending start_stop_unit failed, " diff --git a/drivers/scsi/esas2r/esas2r_flash.c b/drivers/scsi/esas2r/esas2r_flash.c index b02ac389e6c6..429d64299fe9 100644 --- a/drivers/scsi/esas2r/esas2r_flash.c +++ b/drivers/scsi/esas2r/esas2r_flash.c @@ -1500,7 +1500,7 @@ bool esas2r_fm_api(struct esas2r_adapter *a, struct esas2r_flash_img *fi, return complete_fmapi_req(a, rq, FI_STAT_SUCCESS); } - /* fall through */ + fallthrough; case FI_ACT_UP: /* Upload the components */ default: diff --git a/drivers/scsi/esas2r/esas2r_init.c b/drivers/scsi/esas2r/esas2r_init.c index eb7d139ffc00..09c5c24bf391 100644 --- a/drivers/scsi/esas2r/esas2r_init.c +++ b/drivers/scsi/esas2r/esas2r_init.c @@ -1236,7 +1236,7 @@ static bool esas2r_format_init_msg(struct esas2r_adapter *a, a->init_msg = ESAS2R_INIT_MSG_GET_INIT; break; } - /* fall through */ + fallthrough; case ESAS2R_INIT_MSG_GET_INIT: if (msg == ESAS2R_INIT_MSG_GET_INIT) { @@ -1250,7 +1250,7 @@ static bool esas2r_format_init_msg(struct esas2r_adapter *a, esas2r_hdebug("FAILED"); } } - /* fall through */ + fallthrough; default: rq->req_stat = RS_SUCCESS; diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c index 89afa31e33cb..43a1fd11df5e 100644 --- a/drivers/scsi/esp_scsi.c +++ b/drivers/scsi/esp_scsi.c @@ -307,7 +307,7 @@ static void esp_reset_esp(struct esp *esp) case FASHME: esp->config2 |= (ESP_CONFIG2_HME32 | ESP_CONFIG2_HMEFENAB); - /* fallthrough... */ + fallthrough; case FAS236: case PCSCSI: @@ -1741,7 +1741,7 @@ again: case ESP_EVENT_DATA_IN: write = 1; - /* fallthru */ + fallthrough; case ESP_EVENT_DATA_OUT: { struct esp_cmd_entry *ent = esp->active_cmd; diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 1409c7687853..5ea426effa60 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -450,10 +450,10 @@ void fcoe_ctlr_link_up(struct fcoe_ctlr *fip) switch (fip->mode) { default: LIBFCOE_FIP_DBG(fip, "invalid mode %d\n", fip->mode); - /* fall-through */ + fallthrough; case FIP_MODE_AUTO: LIBFCOE_FIP_DBG(fip, "%s", "setting AUTO mode.\n"); - /* fall-through */ + fallthrough; case FIP_MODE_FABRIC: case FIP_MODE_NON_FIP: mutex_unlock(&fip->ctlr_mutex); @@ -773,7 +773,7 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, fc_fcoe_set_mac(mac, fh->fh_d_id); fip->update_mac(lport, mac); } - /* fall through */ + fallthrough; case ELS_LS_RJT: op = fr_encaps(fp); if (op) @@ -2439,7 +2439,7 @@ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip, frport->enode_mac, 0); break; } - /* fall through */ + fallthrough; case FIP_ST_VNMP_START: LIBFCOE_FIP_DBG(fip, "vn_probe_req: " "restart VN2VN negotiation\n"); diff --git a/drivers/scsi/g_NCR5380.c b/drivers/scsi/g_NCR5380.c index 2cc676e3df6a..29e4cdcade72 100644 --- a/drivers/scsi/g_NCR5380.c +++ b/drivers/scsi/g_NCR5380.c @@ -340,7 +340,7 @@ static int generic_NCR5380_init_one(struct scsi_host_template *tpnt, break; case BOARD_DTC3181E: hostdata->io_width = 2; /* 16-bit PDMA */ - /* fall through */ + fallthrough; case BOARD_NCR53C400A: case BOARD_HP_C2502: hostdata->c400_ctl_status = 9; diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 11caa4b0d797..d9d21d23372e 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1144,7 +1144,7 @@ static int hisi_sas_control_phy(struct asd_sas_phy *sas_phy, enum phy_func func, hisi_hba->hw->get_events(hisi_hba, phy_no); break; } - /* fallthru */ + fallthrough; case PHY_FUNC_RELEASE_SPINUP_HOLD: default: return -EOPNOTSUPP; diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 91794a50b31f..48d5da59262b 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -4697,7 +4697,7 @@ static int fixup_ioaccel_cdb(u8 *cdb, int *cdb_len) case WRITE_6: case WRITE_12: is_write = 1; - /* fall through */ + fallthrough; case READ_6: case READ_12: if (*cdb_len == 6) { @@ -5147,7 +5147,7 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h, switch (cmd->cmnd[0]) { case WRITE_6: is_write = 1; - /* fall through */ + fallthrough; case READ_6: first_block = (((cmd->cmnd[1] & 0x1F) << 16) | (cmd->cmnd[2] << 8) | @@ -5158,7 +5158,7 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h, break; case WRITE_10: is_write = 1; - /* fall through */ + fallthrough; case READ_10: first_block = (((u64) cmd->cmnd[2]) << 24) | @@ -5171,7 +5171,7 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h, break; case WRITE_12: is_write = 1; - /* fall through */ + fallthrough; case READ_12: first_block = (((u64) cmd->cmnd[2]) << 24) | @@ -5186,7 +5186,7 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h, break; case WRITE_16: is_write = 1; - /* fall through */ + fallthrough; case READ_16: first_block = (((u64) cmd->cmnd[2]) << 56) | diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 77f4d37d5bd6..ea7c8930592d 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -1866,7 +1866,7 @@ static int ibmvfc_bsg_request(struct bsg_job *job) port_id = (bsg_request->rqst_data.h_els.port_id[0] << 16) | (bsg_request->rqst_data.h_els.port_id[1] << 8) | bsg_request->rqst_data.h_els.port_id[2]; - /* fall through */ + fallthrough; case FC_BSG_RPT_ELS: fc_flags = IBMVFC_FC_ELS; break; @@ -1875,7 +1875,7 @@ static int ibmvfc_bsg_request(struct bsg_job *job) port_id = (bsg_request->rqst_data.h_ct.port_id[0] << 16) | (bsg_request->rqst_data.h_ct.port_id[1] << 8) | bsg_request->rqst_data.h_ct.port_id[2]; - /* fall through */ + fallthrough; case FC_BSG_RPT_CT: fc_flags = IBMVFC_FC_CT_IU; break; @@ -4122,7 +4122,7 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt) return; case IBMVFC_MAD_CRQ_ERROR: ibmvfc_retry_host_init(vhost); - /* fall through */ + fallthrough; case IBMVFC_MAD_DRIVER_FAILED: ibmvfc_free_event(evt); return; diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index d9e94e81da01..cc3908c2d2f9 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -1581,7 +1581,7 @@ static long ibmvscsis_adapter_info(struct scsi_info *vscsi, case H_PERMISSION: if (connection_broken(vscsi)) flag_bits = (RESPONSE_Q_DOWN | CLIENT_FAILED); - /* Fall through */ + fallthrough; default: dev_err(&vscsi->dev, "adapter_info: h_copy_rdma to client failed, rc %ld\n", rc); @@ -2489,10 +2489,10 @@ static long ibmvscsis_ping_response(struct scsi_info *vscsi) break; case H_CLOSED: vscsi->flags |= CLIENT_FAILED; - /* Fall through */ + fallthrough; case H_DROPPED: vscsi->flags |= RESPONSE_Q_DOWN; - /* Fall through */ + fallthrough; case H_REMOTE_PARM: dev_err(&vscsi->dev, "ping_response: h_send_crq failed, rc %ld\n", rc); diff --git a/drivers/scsi/imm.c b/drivers/scsi/imm.c index 1459b1467027..862d35a098cf 100644 --- a/drivers/scsi/imm.c +++ b/drivers/scsi/imm.c @@ -801,7 +801,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd) case 1: /* Phase 1 - Connected */ imm_connect(dev, CONNECT_EPP_MAYBE); cmd->SCp.phase++; - /* fall through */ + fallthrough; case 2: /* Phase 2 - We are now talking to the scsi bus */ if (!imm_select(dev, scmd_id(cmd))) { @@ -809,7 +809,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd) return 0; } cmd->SCp.phase++; - /* fall through */ + fallthrough; case 3: /* Phase 3 - Ready to accept a command */ w_ctr(ppb, 0x0c); @@ -819,7 +819,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd) if (!imm_send_command(cmd)) return 0; cmd->SCp.phase++; - /* fall through */ + fallthrough; case 4: /* Phase 4 - Setup scatter/gather buffers */ if (scsi_bufflen(cmd)) { @@ -835,7 +835,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd) cmd->SCp.phase++; if (cmd->SCp.this_residual & 0x01) cmd->SCp.this_residual++; - /* fall through */ + fallthrough; case 5: /* Phase 5 - Pre-Data transfer stage */ /* Spin lock for BUSY */ @@ -852,7 +852,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd) if (imm_negotiate(dev)) return 0; cmd->SCp.phase++; - /* fall through */ + fallthrough; case 6: /* Phase 6 - Data transfer stage */ /* Spin lock for BUSY */ @@ -868,7 +868,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd) return 1; } cmd->SCp.phase++; - /* fall through */ + fallthrough; case 7: /* Phase 7 - Post data transfer stage */ if ((dev->dp) && (dev->rd)) { @@ -880,7 +880,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd) } } cmd->SCp.phase++; - /* fall through */ + fallthrough; case 8: /* Phase 8 - Read status/message */ /* Check for data overrun */ diff --git a/drivers/scsi/isci/phy.c b/drivers/scsi/isci/phy.c index 7f9b3f20e5e4..4cacb800b530 100644 --- a/drivers/scsi/isci/phy.c +++ b/drivers/scsi/isci/phy.c @@ -778,7 +778,7 @@ enum sci_status sci_phy_event_handler(struct isci_phy *iphy, u32 event_code) break; case SCU_EVENT_LINK_FAILURE: scu_link_layer_set_txcomsas_timeout(iphy, SCU_SAS_LINK_LAYER_TXCOMSAS_NEGTIME_DEFAULT); - /* fall through */ + fallthrough; case SCU_EVENT_HARD_RESET_RECEIVED: /* Start the oob/sn state machine over again */ sci_change_state(&iphy->sm, SCI_PHY_STARTING); diff --git a/drivers/scsi/isci/remote_device.c b/drivers/scsi/isci/remote_device.c index cd1e4b4d95bb..c3f540b55689 100644 --- a/drivers/scsi/isci/remote_device.c +++ b/drivers/scsi/isci/remote_device.c @@ -310,7 +310,7 @@ static void isci_remote_device_not_ready(struct isci_host *ihost, /* Kill all outstanding requests for the device. */ sci_remote_device_terminate_requests(idev); - /* Fall through - into the default case... */ + fallthrough; /* into the default case */ default: clear_bit(IDEV_IO_READY, &idev->flags); break; @@ -593,7 +593,7 @@ enum sci_status sci_remote_device_event_handler(struct isci_remote_device *idev, break; } - /* fall through - and treat as unhandled... */ + fallthrough; /* and treat as unhandled */ default: dev_dbg(scirdev_to_dev(idev), "%s: device: %p event code: %x: %s\n", diff --git a/drivers/scsi/isci/remote_node_context.c b/drivers/scsi/isci/remote_node_context.c index 474a43460963..68333f523b35 100644 --- a/drivers/scsi/isci/remote_node_context.c +++ b/drivers/scsi/isci/remote_node_context.c @@ -225,7 +225,7 @@ static void sci_remote_node_context_continue_state_transitions(struct sci_remote case RNC_DEST_READY: case RNC_DEST_SUSPENDED_RESUME: rnc->destination_state = RNC_DEST_READY; - /* Fall through... */ + fallthrough; case RNC_DEST_FINAL: sci_remote_node_context_resume(rnc, rnc->user_callback, rnc->user_cookie); @@ -601,9 +601,9 @@ enum sci_status sci_remote_node_context_suspend( __func__, sci_rnc); return SCI_FAILURE_INVALID_STATE; } - /* Fall through - and handle like SCI_RNC_POSTING */ + fallthrough; /* and handle like SCI_RNC_POSTING */ case SCI_RNC_RESUMING: - /* Fall through - and handle like SCI_RNC_POSTING */ + fallthrough; /* and handle like SCI_RNC_POSTING */ case SCI_RNC_POSTING: /* Set the destination state to AWAIT - this signals the * entry into the SCI_RNC_READY state that a suspension diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c index 6561a07db189..6e0817941fa7 100644 --- a/drivers/scsi/isci/request.c +++ b/drivers/scsi/isci/request.c @@ -894,7 +894,7 @@ sci_io_request_terminate(struct isci_request *ireq) * and don't wait for the task response. */ sci_change_state(&ireq->sm, SCI_REQ_ABORTING); - /* Fall through - and handle like ABORTING... */ + fallthrough; /* and handle like ABORTING */ case SCI_REQ_ABORTING: if (!isci_remote_device_is_safe_to_abort(ireq->target_device)) set_bit(IREQ_PENDING_ABORT, &ireq->flags); diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 16eb3b60ed58..96a2952cf626 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -2108,7 +2108,7 @@ static void fc_exch_rrq_resp(struct fc_seq *sp, struct fc_frame *fp, void *arg) switch (op) { case ELS_LS_RJT: FC_EXCH_DBG(aborted_ep, "LS_RJT for RRQ\n"); - /* fall through */ + fallthrough; case ELS_LS_ACC: goto cleanup; default: @@ -2622,7 +2622,7 @@ void fc_exch_recv(struct fc_lport *lport, struct fc_frame *fp) case FC_EOF_T: if (f_ctl & FC_FC_END_SEQ) skb_trim(fp_skb(fp), fr_len(fp) - FC_FC_FILL(f_ctl)); - /* fall through */ + fallthrough; case FC_EOF_N: if (fh->fh_type == FC_TYPE_BLS) fc_exch_recv_bls(ema->mp, fp); diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index e11d4f002bd4..7cfeb6886237 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -752,7 +752,7 @@ static void fc_fcp_abts_resp(struct fc_fcp_pkt *fsp, struct fc_frame *fp) brp = fc_frame_payload_get(fp, sizeof(*brp)); if (brp && brp->br_reason == FC_BA_RJT_LOG_ERR) break; - /* fall thru */ + fallthrough; default: /* * we will let the command timeout @@ -1536,7 +1536,7 @@ static void fc_fcp_rec_resp(struct fc_seq *seq, struct fc_frame *fp, void *arg) "device %x invalid REC reject %d/%d\n", fsp->rport->port_id, rjt->er_reason, rjt->er_explan); - /* fall through */ + fallthrough; case ELS_RJT_UNSUP: FC_FCP_DBG(fsp, "device does not support REC\n"); rpriv = fsp->rport->dd_data; @@ -1668,7 +1668,7 @@ static void fc_fcp_rec_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp) FC_FCP_DBG(fsp, "REC %p fid %6.6x error unexpected error %d\n", fsp, fsp->rport->port_id, error); fsp->status_code = FC_CMD_PLOGO; - /* fall through */ + fallthrough; case -FC_EX_TIMEOUT: /* @@ -1830,7 +1830,7 @@ static void fc_fcp_srr_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp) break; case -FC_EX_CLOSED: /* e.g., link failure */ FC_FCP_DBG(fsp, "SRR error, exchange closed\n"); - /* fall through */ + fallthrough; default: fc_fcp_retry_cmd(fsp, FC_ERROR); break; diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index b84dbc316df1..6557fda85c5c 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -1578,7 +1578,7 @@ static void fc_lport_timeout(struct work_struct *work) case LPORT_ST_DPRT: FC_LPORT_DBG(lport, "Skipping lport state %s to SCR\n", fc_lport_state(lport)); - /* fall thru */ + fallthrough; case LPORT_ST_SCR: fc_lport_enter_scr(lport); break; diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 18663a82865f..a60b228d13f1 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -1723,7 +1723,7 @@ static void fc_rport_recv_els_req(struct fc_lport *lport, struct fc_frame *fp) kref_put(&rdata->kref, fc_rport_destroy); goto busy; } - /* fall through */ + fallthrough; default: FC_RPORT_DBG(rdata, "Reject ELS 0x%02x while in state %s\n", diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 49c8a1818baf..1e9c3171fa9f 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -248,7 +248,7 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) hdr_lun = scsilun_to_int(&tmf->lun); if (hdr_lun != task->sc->device->lun) return 0; - /* fall through */ + fallthrough; case ISCSI_TM_FUNC_TARGET_WARM_RESET: /* * Fail all SCSI cmd PDUs @@ -1674,7 +1674,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) sc->result = DID_NO_CONNECT << 16; break; } - /* fall through */ + fallthrough; case ISCSI_STATE_IN_RECOVERY: reason = FAILURE_SESSION_IN_RECOVERY; sc->result = DID_IMM_RETRY << 16; @@ -2239,7 +2239,7 @@ int iscsi_eh_abort(struct scsi_cmnd *sc) "progress\n"); goto success; } - /* fall through */ + fallthrough; default: conn->tmf_state = TMF_INITIAL; goto failed; diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 6ef93c7af954..37e5d4e48c2f 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -772,7 +772,7 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr) iscsi_tcp_data_recv_prep(tcp_conn); return 0; } - /* fall through */ + fallthrough; case ISCSI_OP_LOGOUT_RSP: case ISCSI_OP_NOOP_IN: case ISCSI_OP_SCSI_TMFUNC_RSP: diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 1b93332daa6b..6a521ba7a616 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -324,7 +324,7 @@ static int smp_ata_check_ready(struct ata_link *link) case SAS_END_DEVICE: if (ex_phy->attached_sata_dev) return sas_ata_clear_pending(dev, ex_phy); - /* fall through */ + fallthrough; default: return -ENODEV; } diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index daf951b0b3f5..cd7c7d269f6f 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -108,7 +108,7 @@ static int sas_get_port_device(struct asd_sas_port *port) rphy = NULL; break; } - /* fall through */ + fallthrough; case SAS_END_DEVICE: rphy = sas_end_device_alloc(port->port); break; diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index b7d1b1ea185d..8d6bcc19359f 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -1096,7 +1096,7 @@ static int sas_ex_discover_dev(struct domain_device *dev, int phy_id) } else memcpy(dev->port->disc.fanout_sas_addr, ex_phy->attached_sas_addr, SAS_ADDR_SIZE); - /* fallthrough */ + fallthrough; case SAS_EDGE_EXPANDER_DEVICE: child = sas_ex_discover_expander(dev, phy_id); break; diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index 9e0975e55c27..1bf939818c98 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -622,7 +622,7 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head * sas_scsi_clear_queue_lu(work_q, cmd); goto Again; } - /* fallthrough */ + fallthrough; case TASK_IS_NOT_AT_LU: case TASK_ABORT_FAILED: pr_notice("task 0x%p is not at LU: I_T recover\n", diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index ef2015fad2d5..d0141a23a833 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -3202,7 +3202,7 @@ port_out: case SLI_MGMT_GHAT: case SLI_MGMT_GRPL: rsp_size = FC_MAX_NS_RSP; - /* fall through */ + fallthrough; case SLI_MGMT_DHBA: case SLI_MGMT_DHAT: pe = (struct lpfc_fdmi_port_entry *)&CtReq->un.PortID; @@ -3215,7 +3215,7 @@ port_out: case SLI_MGMT_GPAT: case SLI_MGMT_GPAS: rsp_size = FC_MAX_NS_RSP; - /* fall through */ + fallthrough; case SLI_MGMT_DPRT: case SLI_MGMT_DPA: pe = (struct lpfc_fdmi_port_entry *)&CtReq->un.PortID; diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 48dc63f22cca..6aae61d6ee16 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -9134,7 +9134,7 @@ lpfc_cmpl_reg_new_vport(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) lpfc_nlp_put(ndlp); return; } - /* fall through */ + fallthrough; default: /* Try to recover from this error */ if (phba->sli_rev == LPFC_SLI_REV4) diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 142a02114479..d32c7e7ab09d 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -4728,15 +4728,14 @@ lpfc_check_sli_ndlp(struct lpfc_hba *phba, case CMD_GEN_REQUEST64_CR: if (iocb->context_un.ndlp == ndlp) return 1; - /* fall through */ + fallthrough; case CMD_ELS_REQUEST64_CR: if (icmd->un.elsreq64.remoteID == ndlp->nlp_DID) return 1; - /* fall through */ + fallthrough; case CMD_XMIT_ELS_RSP64_CX: if (iocb->context1 == (uint8_t *) ndlp) return 1; - /* fall through */ } } else if (pring->ringno == LPFC_FCP_RING) { /* Skip match check if waiting to relogin to FCP target */ @@ -6055,7 +6054,7 @@ restart_disc: case LPFC_LINK_UP: lpfc_issue_clear_la(phba, vport); - /* fall through */ + fallthrough; case LPFC_LINK_UNKNOWN: case LPFC_WARM_START: case LPFC_INIT_START: diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index cad53d19cb25..92d6e7b98770 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -464,7 +464,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, case NLP_STE_NPR_NODE: if (!(ndlp->nlp_flag & NLP_NPR_ADISC)) break; - /* fall through */ + fallthrough; case NLP_STE_REG_LOGIN_ISSUE: case NLP_STE_PRLI_ISSUE: case NLP_STE_UNMAPPED_NODE: diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index e5be334d6a11..0c39ed50998c 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -1225,7 +1225,7 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn, lpfc_ncmd, nCmd, lpfc_ncmd->cur_iocbq.sli4_xritag, bf_get(lpfc_wcqe_c_xb, wcqe)); - /* fall through */ + fallthrough; default: out_err: lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR, diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 5e802c8b22a9..983eeb0e3d07 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1093,7 +1093,7 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc, break; } - /* fall through */ + fallthrough; case SCSI_PROT_WRITE_INSERT: /* * For WRITE_INSERT, force the error @@ -1213,7 +1213,7 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc, rc = BG_ERR_TGT | BG_ERR_CHECK; break; } - /* fall through */ + fallthrough; case SCSI_PROT_WRITE_INSERT: /* * For WRITE_INSERT, force the @@ -1295,7 +1295,7 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc, switch (op) { case SCSI_PROT_WRITE_PASS: rc = BG_ERR_CHECK; - /* fall through */ + fallthrough; case SCSI_PROT_WRITE_INSERT: /* @@ -3980,7 +3980,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, lpfc_cmd->cur_iocbq.sli4_lxritag, 0, 0); } - /* fall through */ + fallthrough; default: cmd->result = DID_ERROR << 16; break; diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 4cd7ded656b7..e158cd77d387 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -9339,7 +9339,7 @@ __lpfc_sli_issue_iocb_s3(struct lpfc_hba *phba, uint32_t ring_number, */ if (piocb->iocb_cmpl) piocb->iocb_cmpl = NULL; - /*FALLTHROUGH*/ + fallthrough; case CMD_CREATE_XRI_CR: case CMD_CLOSE_XRI_CN: case CMD_CLOSE_XRI_CX: @@ -9653,7 +9653,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq, cmnd = CMD_XMIT_SEQUENCE64_CR; if (phba->link_flag & LS_LOOPBACK_MODE) bf_set(wqe_xo, &wqe->xmit_sequence.wge_ctl, 1); - /* fall through */ + fallthrough; case CMD_XMIT_SEQUENCE64_CR: /* word3 iocb=io_tag32 wqe=reserved */ wqe->xmit_sequence.rsvd3 = 0; @@ -13630,7 +13630,7 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe) case FC_STATUS_RQ_BUF_LEN_EXCEEDED: lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "2537 Receive Frame Truncated!!\n"); - /* fall through */ + fallthrough; case FC_STATUS_RQ_SUCCESS: spin_lock_irqsave(&phba->hbalock, iflags); lpfc_sli4_rq_release(hrq, drq); @@ -13678,7 +13678,7 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe) atomic_read(&tgtp->rcv_fcp_cmd_out), atomic_read(&tgtp->xmt_fcp_release)); } - /* fallthrough */ + fallthrough; case FC_STATUS_INSUFF_BUF_NEED_BUF: hrq->RQ_no_posted_buf++; @@ -14162,7 +14162,7 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq, case FC_STATUS_RQ_BUF_LEN_EXCEEDED: lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "6126 Receive Frame Truncated!!\n"); - /* fall through */ + fallthrough; case FC_STATUS_RQ_SUCCESS: spin_lock_irqsave(&phba->hbalock, iflags); lpfc_sli4_rq_release(hrq, drq); @@ -14209,7 +14209,7 @@ drop: atomic_read(&tgtp->rcv_fcp_cmd_out), atomic_read(&tgtp->xmt_fcp_release)); } - /* fallthrough */ + fallthrough; case FC_STATUS_INSUFF_BUF_NEED_BUF: hrq->RQ_no_posted_buf++; @@ -15096,7 +15096,7 @@ lpfc_eq_create(struct lpfc_hba *phba, struct lpfc_queue *eq, uint32_t imax) status = -EINVAL; goto out; } - /* fall through - otherwise default to smallest count */ + fallthrough; /* otherwise default to smallest count */ case 256: bf_set(lpfc_eq_context_count, &eq_create->u.request.context, LPFC_EQ_CNT_256); @@ -15238,7 +15238,7 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq, LPFC_CQ_CNT_WORD7); break; } - /* fall through */ + fallthrough; default: lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "0361 Unsupported CQ count: " @@ -15249,7 +15249,7 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq, status = -EINVAL; goto out; } - /* fall through - otherwise default to smallest count */ + fallthrough; /* otherwise default to smallest count */ case 256: bf_set(lpfc_cq_context_count, &cq_create->u.request.context, LPFC_CQ_CNT_256); @@ -15417,7 +15417,7 @@ lpfc_cq_create_set(struct lpfc_hba *phba, struct lpfc_queue **cqp, LPFC_CQ_CNT_WORD7); break; } - /* fall through */ + fallthrough; default: lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "3118 Bad CQ count. (%d)\n", @@ -15426,7 +15426,7 @@ lpfc_cq_create_set(struct lpfc_hba *phba, struct lpfc_queue **cqp, status = -EINVAL; goto out; } - /* fall through - otherwise default to smallest */ + fallthrough; /* otherwise default to smallest */ case 256: bf_set(lpfc_mbx_cq_create_set_cqe_cnt, &cq_set->u.request, LPFC_CQ_CNT_256); @@ -15702,7 +15702,7 @@ lpfc_mq_create(struct lpfc_hba *phba, struct lpfc_queue *mq, status = -EINVAL; goto out; } - /* fall through - otherwise default to smallest count */ + fallthrough; /* otherwise default to smallest count */ case 16: bf_set(lpfc_mq_context_ring_size, &mq_create_ext->u.request.context, @@ -16123,7 +16123,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq, status = -EINVAL; goto out; } - /* fall through - otherwise default to smallest count */ + fallthrough; /* otherwise default to smallest count */ case 512: bf_set(lpfc_rq_context_rqe_count, &rq_create->u.request.context, @@ -16260,7 +16260,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq, status = -EINVAL; goto out; } - /* fall through - otherwise default to smallest count */ + fallthrough; /* otherwise default to smallest count */ case 512: bf_set(lpfc_rq_context_rqe_count, &rq_create->u.request.context, diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index 0484ee52ae80..ac406049e7c8 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -491,9 +491,9 @@ mega_get_ldrv_num(adapter_t *adapter, struct scsi_cmnd *cmd, int channel) if (adapter->support_random_del && adapter->read_ldidmap ) switch (cmd->cmnd[0]) { - case READ_6: /* fall through */ - case WRITE_6: /* fall through */ - case READ_10: /* fall through */ + case READ_6: + case WRITE_6: + case READ_10: case WRITE_10: ldrv_num += 0x80; } @@ -852,7 +852,7 @@ mega_build_cmd(adapter_t *adapter, struct scsi_cmnd *cmd, int *busy) return scb; #if MEGA_HAVE_CLUSTERING - case RESERVE: /* Fall through */ + case RESERVE: case RELEASE: /* @@ -987,7 +987,7 @@ mega_prepare_passthru(adapter_t *adapter, scb_t *scb, struct scsi_cmnd *cmd, adapter->flag |= (1L << cmd->device->channel); } - /* Fall through */ + fallthrough; default: pthru->numsgelements = mega_build_sglist(adapter, scb, &pthru->dataxferaddr, &pthru->dataxferlen); @@ -1050,7 +1050,7 @@ mega_prepare_extpassthru(adapter_t *adapter, scb_t *scb, adapter->flag |= (1L << cmd->device->channel); } - /* Fall through */ + fallthrough; default: epthru->numsgelements = mega_build_sglist(adapter, scb, &epthru->dataxferaddr, &epthru->dataxferlen); diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c index 19469a2c0ea3..4a27ac869f2e 100644 --- a/drivers/scsi/megaraid/megaraid_mbox.c +++ b/drivers/scsi/megaraid/megaraid_mbox.c @@ -1581,7 +1581,7 @@ megaraid_mbox_build_cmd(adapter_t *adapter, struct scsi_cmnd *scp, int *busy) return NULL; } - /* Fall through */ + fallthrough; case READ_CAPACITY: /* diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 861f7140f52e..2b7e7b5f38ed 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3522,7 +3522,7 @@ megasas_complete_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd, megasas_complete_int_cmd(instance, cmd); break; } - /* fall through */ + fallthrough; case MFI_CMD_LD_READ: case MFI_CMD_LD_WRITE: diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index 0824410f78f8..883cccb59c2d 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -3534,7 +3534,7 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex, atomic_dec(&lbinfo->scsi_pending_cmds[cmd_fusion->pd_r1_lb]); cmd_fusion->scmd->SCp.Status &= ~MEGASAS_LOAD_BALANCE_FLAG; } - /* Fall through - and complete IO */ + fallthrough; /* and complete IO */ case MEGASAS_MPI2_FUNCTION_LD_IO_REQUEST: /* LD-IO Path */ atomic_dec(&instance->fw_outstanding); if (cmd_fusion->r1_alt_dev_handle == MR_DEVHANDLE_INVALID) { diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c index fd1d03064079..0a9f4e44ab2c 100644 --- a/drivers/scsi/mesh.c +++ b/drivers/scsi/mesh.c @@ -1457,7 +1457,7 @@ static void cmd_complete(struct mesh_state *ms) /* huh? we expected a phase mismatch */ ms->n_msgin = 0; ms->msgphase = msg_in; - /* fall through */ + fallthrough; case msg_in: /* should have some message bytes in fifo */ diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 1d64524cd863..5730f32496b6 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -4681,7 +4681,7 @@ _base_update_ioc_page1_inlinewith_perf_mode(struct MPT3SAS_ADAPTER *ioc) ioc_info(ioc, "performance mode: balanced\n"); return; } - /* Fall through */ + fallthrough; case MPT_PERF_MODE_LATENCY: /* * Enable interrupt coalescing on all reply queues diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 43260306668c..7c119b904834 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -1002,7 +1002,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg, } /* drop to default case for posting the request */ } - /* fall through */ + fallthrough; default: ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz, data_in_dma, data_in_sz); diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 08fc4b381056..2e2756d8a49b 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -5470,7 +5470,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply) case MPI2_IOCSTATUS_SCSI_DATA_OVERRUN: scsi_set_resid(scmd, 0); - /* fall through */ + fallthrough; case MPI2_IOCSTATUS_SCSI_RECOVERED_ERROR: case MPI2_IOCSTATUS_SUCCESS: scmd->result = (DID_OK << 16) | scsi_status; @@ -6480,7 +6480,7 @@ _scsih_sas_topology_change_event(struct MPT3SAS_ADAPTER *ioc, if (!test_bit(handle, ioc->pend_os_device_add)) break; - /* fall through */ + fallthrough; case MPI2_EVENT_SAS_TOPO_RC_TARG_ADDED: @@ -7208,7 +7208,7 @@ _scsih_pcie_topology_change_event(struct MPT3SAS_ADAPTER *ioc, event_data->PortEntry[i].PortStatus &= 0xF0; event_data->PortEntry[i].PortStatus |= MPI26_EVENT_PCIE_TOPO_PS_DEV_ADDED; - /* fall through */ + fallthrough; case MPI26_EVENT_PCIE_TOPO_PS_DEV_ADDED: if (ioc->shost_recovery) break; @@ -10653,7 +10653,7 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id) case MPI26_MFGPAGE_DEVID_CFG_SEC_3916: dev_info(&pdev->dev, "HBA is in Configurable Secure mode\n"); - /* fall through */ + fallthrough; case MPI26_MFGPAGE_DEVID_HARD_SEC_3816: case MPI26_MFGPAGE_DEVID_HARD_SEC_3916: ioc->is_aero_ioc = ioc->is_gen35_ioc = 1; diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c index d4bd31a75b9d..b2869c5dd7fb 100644 --- a/drivers/scsi/myrb.c +++ b/drivers/scsi/myrb.c @@ -650,7 +650,7 @@ static void myrb_bgi_control(struct myrb_hba *cb) if (sdev && cb->bgi_status.status == MYRB_BGI_INPROGRESS) sdev_printk(KERN_INFO, sdev, "Background Initialization Aborted\n"); - /* Fallthrough */ + fallthrough; case MYRB_STATUS_NO_BGI_INPROGRESS: cb->bgi_status.status = MYRB_BGI_INVALID; break; @@ -1528,7 +1528,7 @@ static int myrb_ldev_queuecommand(struct Scsi_Host *shost, scmd->scsi_done(scmd); return 0; } - /* fall through */ + fallthrough; case WRITE_6: lba = (((scmd->cmnd[1] & 0x1F) << 16) | (scmd->cmnd[2] << 8) | @@ -1545,7 +1545,7 @@ static int myrb_ldev_queuecommand(struct Scsi_Host *shost, scmd->scsi_done(scmd); return 0; } - /* fall through */ + fallthrough; case WRITE_10: case VERIFY: /* 0x2F */ case WRITE_VERIFY: /* 0x2E */ @@ -1562,7 +1562,7 @@ static int myrb_ldev_queuecommand(struct Scsi_Host *shost, scmd->scsi_done(scmd); return 0; } - /* fall through */ + fallthrough; case WRITE_12: case VERIFY_12: /* 0xAF */ case WRITE_VERIFY_12: /* 0xAE */ diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c index f88adab3f913..03d70138ad58 100644 --- a/drivers/scsi/ncr53c8xx.c +++ b/drivers/scsi/ncr53c8xx.c @@ -3640,7 +3640,7 @@ ncr_script_copy_and_bind (struct ncb *np, ncrcmd *src, ncrcmd *dst, int len) new = old; break; } - /* fall through */ + fallthrough; default: panic("ncr_script_copy_and_bind: weird relocation %x\n", old); break; @@ -3910,14 +3910,14 @@ static void __init ncr_prepare_setting(struct ncb *np) np->scsi_mode = SMODE_HVD; break; } - /* fall through */ + fallthrough; case 3: /* SYMBIOS controllers report HVD through GPIO3 */ if (INB(nc_gpreg) & 0x08) break; - /* fall through */ + fallthrough; case 2: /* Set HVD unconditionally */ np->scsi_mode = SMODE_HVD; - /* fall through */ + fallthrough; case 1: /* Trust previous settings for HVD */ if (np->sv_stest2 & 0x20) np->scsi_mode = SMODE_HVD; @@ -4296,7 +4296,7 @@ static int ncr_queue_command (struct ncb *np, struct scsi_cmnd *cmd) break; cp->phys.header.wgoalp = cpu_to_scr(goalp); cp->phys.header.wlastp = cpu_to_scr(lastp); - /* fall through */ + fallthrough; case DMA_FROM_DEVICE: goalp = NCB_SCRIPT_PHYS (np, data_in2) + 8; if (segments <= MAX_SCATTERL) @@ -6717,7 +6717,7 @@ void ncr_int_sir (struct ncb *np) OUTL_DSP (scr_to_cpu(tp->lp[0]->jump_ccb[0])); return; } - /* fall through */ + fallthrough; case SIR_RESEL_BAD_TARGET: /* Will send a TARGET RESET message */ case SIR_RESEL_BAD_LUN: /* Will send a TARGET RESET message */ case SIR_RESEL_BAD_I_T_L_Q: /* Will send an ABORT TAG message */ @@ -6825,7 +6825,7 @@ void ncr_int_sir (struct ncb *np) */ OUTB (HS_PRT, HS_BUSY); - /* fall through */ + fallthrough; case SIR_NEGO_PROTO: /*------------------------------------------------------- diff --git a/drivers/scsi/pcmcia/nsp_cs.c b/drivers/scsi/pcmcia/nsp_cs.c index 8655ff1249bb..bc5a623519e7 100644 --- a/drivers/scsi/pcmcia/nsp_cs.c +++ b/drivers/scsi/pcmcia/nsp_cs.c @@ -1113,7 +1113,7 @@ static irqreturn_t nspintr(int irq, void *dev_id) nsp_scsi_done(tmpSC); return IRQ_HANDLED; } - /* fall thru */ + fallthrough; default: if ((irq_status & (IRQSTATUS_SCSI | IRQSTATUS_FIFO)) == 0) { return IRQ_HANDLED; diff --git a/drivers/scsi/ppa.c b/drivers/scsi/ppa.c index 0ae800c5b739..aa41f7ac91cb 100644 --- a/drivers/scsi/ppa.c +++ b/drivers/scsi/ppa.c @@ -717,7 +717,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd) } cmd->SCp.phase++; } - /* fall through */ + fallthrough; case 2: /* Phase 2 - We are now talking to the scsi bus */ if (!ppa_select(dev, scmd_id(cmd))) { @@ -725,7 +725,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd) return 0; } cmd->SCp.phase++; - /* fall through */ + fallthrough; case 3: /* Phase 3 - Ready to accept a command */ w_ctr(ppb, 0x0c); @@ -735,7 +735,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd) if (!ppa_send_command(cmd)) return 0; cmd->SCp.phase++; - /* fall through */ + fallthrough; case 4: /* Phase 4 - Setup scatter/gather buffers */ if (scsi_bufflen(cmd)) { @@ -749,7 +749,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd) } cmd->SCp.buffers_residual = scsi_sg_count(cmd) - 1; cmd->SCp.phase++; - /* fall through */ + fallthrough; case 5: /* Phase 5 - Data transfer stage */ w_ctr(ppb, 0x0c); @@ -762,7 +762,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd) if (retv == 0) return 1; cmd->SCp.phase++; - /* fall through */ + fallthrough; case 6: /* Phase 6 - Read status/message */ cmd->result = DID_OK << 16; diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 3f04f2c81366..5ca424df355c 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -3863,7 +3863,7 @@ void qedf_stag_change_work(struct work_struct *work) container_of(work, struct qedf_ctx, stag_work.work); if (!qedf) { - QEDF_ERR(&qedf->dbg_ctx, "qedf is NULL"); + QEDF_ERR(NULL, "qedf is NULL"); return; } QEDF_ERR(&qedf->dbg_ctx, "Performing software context reset.\n"); diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h index 91eb6901815c..e1d7de63e8f8 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.h +++ b/drivers/scsi/qla2xxx/qla_dbg.h @@ -380,5 +380,8 @@ extern int qla24xx_soft_reset(struct qla_hw_data *); static inline int ql_mask_match(uint level) { + if (ql2xextended_error_logging == 1) + ql2xextended_error_logging = QL_DBG_DEFAULT1_MASK; + return (level & ql2xextended_error_logging) == level; } diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 8c92af5e4390..1bc090d8a71b 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3880,6 +3880,7 @@ struct qla_hw_data { uint32_t scm_supported_f:1; /* Enabled in Driver */ uint32_t scm_enabled:1; + uint32_t max_req_queue_warned:1; } flags; uint16_t max_exchg; diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index df670fba2ab8..b569fd6e96d6 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -177,7 +177,7 @@ qla2x00_chk_ms_status(scsi_qla_host_t *vha, ms_iocb_entry_t *ms_pkt, break; case CS_TIMEOUT: rval = QLA_FUNCTION_TIMEOUT; - /* fall through */ + fallthrough; default: ql_dbg(ql_dbg_disc, vha, 0x2033, "%s failed, completion status (%x) on port_id: " @@ -1505,11 +1505,11 @@ qla2x00_prep_ct_fdmi_req(struct ct_sns_pkt *p, uint16_t cmd, static uint qla25xx_fdmi_port_speed_capability(struct qla_hw_data *ha) { + uint speeds = 0; + if (IS_CNA_CAPABLE(ha)) return FDMI_PORT_SPEED_10GB; if (IS_QLA28XX(ha) || IS_QLA27XX(ha)) { - uint speeds = 0; - if (ha->max_supported_speed == 2) { if (ha->min_supported_speed <= 6) speeds |= FDMI_PORT_SPEED_64GB; @@ -1536,9 +1536,16 @@ qla25xx_fdmi_port_speed_capability(struct qla_hw_data *ha) } return speeds; } - if (IS_QLA2031(ha)) - return FDMI_PORT_SPEED_16GB|FDMI_PORT_SPEED_8GB| - FDMI_PORT_SPEED_4GB; + if (IS_QLA2031(ha)) { + if ((ha->pdev->subsystem_vendor == 0x103C) && + (ha->pdev->subsystem_device == 0x8002)) { + speeds = FDMI_PORT_SPEED_16GB; + } else { + speeds = FDMI_PORT_SPEED_16GB|FDMI_PORT_SPEED_8GB| + FDMI_PORT_SPEED_4GB; + } + return speeds; + } if (IS_QLA25XX(ha)) return FDMI_PORT_SPEED_8GB|FDMI_PORT_SPEED_4GB| FDMI_PORT_SPEED_2GB|FDMI_PORT_SPEED_1GB; @@ -3436,7 +3443,6 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp) list_for_each_entry(fcport, &vha->vp_fcports, list) { if ((fcport->flags & FCF_FABRIC_DEVICE) != 0) { fcport->scan_state = QLA_FCPORT_SCAN; - fcport->logout_on_delete = 0; } } goto login_logout; @@ -3532,10 +3538,22 @@ login_logout: } if (fcport->scan_state != QLA_FCPORT_FOUND) { + bool do_delete = false; + + if (fcport->scan_needed && + fcport->disc_state == DSC_LOGIN_PEND) { + /* Cable got disconnected after we sent + * a login. Do delete to prevent timeout. + */ + fcport->logout_on_delete = 1; + do_delete = true; + } + fcport->scan_needed = 0; - if ((qla_dual_mode_enabled(vha) || - qla_ini_mode_enabled(vha)) && - atomic_read(&fcport->state) == FCS_ONLINE) { + if (((qla_dual_mode_enabled(vha) || + qla_ini_mode_enabled(vha)) && + atomic_read(&fcport->state) == FCS_ONLINE) || + do_delete) { if (fcport->loop_id != FC_NO_LOOP_ID) { if (fcport->flags & FCF_FCP2_DEVICE) fcport->logout_on_delete = 0; @@ -3736,6 +3754,18 @@ static void qla2x00_async_gpnft_gnnft_sp_done(srb_t *sp, int res) unsigned long flags; const char *name = sp->name; + if (res == QLA_OS_TIMER_EXPIRED) { + /* switch is ignoring all commands. + * This might be a zone disable behavior. + * This means we hit 64s timeout. + * 22s GPNFT + 44s Abort = 64s + */ + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s: Switch Zone check please .\n", + name); + qla2x00_mark_all_devices_lost(vha); + } + /* * We are in an Interrupt context, queue up this * sp for GNNFT_DONE work. This will allow all diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 57a2d76aa691..507919d4ab36 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -857,7 +857,7 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, fcport); break; } - /* fall through */ + fallthrough; default: if (fcport_is_smaller(fcport)) { /* local adapter is bigger */ diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index e3d2dea0b057..0954fa41911c 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2874,7 +2874,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res) &vha->dpc_flags); qla2xxx_wake_dpc(vha); } - /* fall through */ + fallthrough; default: ql_dbg(ql_dbg_disc, vha, 0x20eb, "%s %8phC cmd error fw_status 0x%x 0x%x 0x%x\n", diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 27bcd346af7c..25e0a1684763 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1580,11 +1580,11 @@ global_port_update: qla2xxx_wake_dpc(vha); } } - /* fall through */ + fallthrough; case MBA_IDC_COMPLETE: if (ha->notify_lb_portup_comp && !vha->vp_idx) complete(&ha->lb_portup_comp); - /* Fallthru */ + fallthrough; case MBA_IDC_TIME_EXT: if (IS_QLA81XX(vha->hw) || IS_QLA8031(vha->hw) || IS_QLA8044(ha)) @@ -2024,8 +2024,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, res = DID_ERROR << 16; } } - ql_dbg(ql_dbg_user, vha, 0x503f, - "ELS IOCB Done -%s error hdl=%x comp_status=0x%x error subcode 1=0x%x error subcode 2=0x%x total_byte=0x%x\n", + ql_dbg(ql_dbg_disc, vha, 0x503f, + "ELS IOCB Done -%s hdl=%x comp_status=0x%x error subcode 1=0x%x error subcode 2=0x%x total_byte=0x%x\n", type, sp->handle, comp_status, fw_status[1], fw_status[2], le32_to_cpu(ese->total_byte_count)); goto els_ct_done; @@ -2188,7 +2188,7 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req, set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags); qla2xxx_wake_dpc(vha); } - /* fall through */ + fallthrough; default: data[0] = MBS_COMMAND_ERROR; break; @@ -2368,7 +2368,7 @@ static void qla24xx_nvme_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, case CS_PORT_UNAVAILABLE: case CS_PORT_LOGGED_OUT: fcport->nvme_flag |= NVME_FLAG_RESETTING; - /* fall through */ + fallthrough; case CS_ABORTED: case CS_PORT_BUSY: fd->transferred_length = 0; @@ -3485,7 +3485,7 @@ process_err: } else { qlt_24xx_process_atio_queue(vha, 1); } - /* fall through */ + fallthrough; case ABTS_RESP_24XX: case CTIO_TYPE7: case CTIO_CRC2: diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 73883435ab58..226f1428d3e5 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -334,14 +334,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) if (time_after(jiffies, wait_time)) break; - /* - * Check if it's UNLOADING, cause we cannot poll in - * this case, or else a NULL pointer dereference - * is triggered. - */ - if (unlikely(test_bit(UNLOADING, &base_vha->dpc_flags))) - return QLA_FUNCTION_TIMEOUT; - /* Check for pending interrupts. */ qla2x00_poll(ha->rsp_q_map[0]); @@ -5240,7 +5232,7 @@ qla2x00_read_ram_word(scsi_qla_host_t *vha, uint32_t risc_addr, uint32_t *data) mcp->mb[8] = MSW(risc_addr); mcp->out_mb = MBX_8|MBX_1|MBX_0; mcp->in_mb = MBX_3|MBX_2|MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); if (rval != QLA_SUCCESS) { @@ -5428,7 +5420,7 @@ qla2x00_write_ram_word(scsi_qla_host_t *vha, uint32_t risc_addr, uint32_t data) mcp->mb[8] = MSW(risc_addr); mcp->out_mb = MBX_8|MBX_3|MBX_2|MBX_1|MBX_0; mcp->in_mb = MBX_1|MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); if (rval != QLA_SUCCESS) { @@ -5700,7 +5692,7 @@ qla24xx_set_fcp_prio(scsi_qla_host_t *vha, uint16_t loop_id, uint16_t priority, mcp->mb[9] = vha->vp_idx; mcp->out_mb = MBX_9|MBX_4|MBX_3|MBX_2|MBX_1|MBX_0; mcp->in_mb = MBX_4|MBX_3|MBX_1|MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); if (mb != NULL) { @@ -5787,7 +5779,7 @@ qla82xx_mbx_intr_enable(scsi_qla_host_t *vha) mcp->out_mb = MBX_1|MBX_0; mcp->in_mb = MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); @@ -5822,7 +5814,7 @@ qla82xx_mbx_intr_disable(scsi_qla_host_t *vha) mcp->out_mb = MBX_1|MBX_0; mcp->in_mb = MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); @@ -6014,7 +6006,7 @@ qla81xx_set_led_config(scsi_qla_host_t *vha, uint16_t *led_cfg) if (IS_QLA8031(ha)) mcp->out_mb |= MBX_6|MBX_5|MBX_4|MBX_3; mcp->in_mb = MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); @@ -6050,7 +6042,7 @@ qla81xx_get_led_config(scsi_qla_host_t *vha, uint16_t *led_cfg) mcp->in_mb = MBX_2|MBX_1|MBX_0; if (IS_QLA8031(ha)) mcp->in_mb |= MBX_6|MBX_5|MBX_4|MBX_3; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index fa695a4007f8..90bbc61f361b 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -536,6 +536,11 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, struct nvme_private *priv = fd->private; struct qla_nvme_rport *qla_rport = rport->private; + if (!priv) { + /* nvme association has been torn down */ + return rval; + } + fcport = qla_rport->fcport; if (!qpair || !fcport || (qpair && !qpair->fw_started) || @@ -687,7 +692,15 @@ int qla_nvme_register_hba(struct scsi_qla_host *vha) tmpl = &qla_nvme_fc_transport; WARN_ON(vha->nvme_local_port); - WARN_ON(ha->max_req_queues < 3); + + if (ha->max_req_queues < 3) { + if (!ha->flags.max_req_queue_warned) + ql_log(ql_log_info, vha, 0x2120, + "%s: Disabling FC-NVME due to lack of free queue pairs (%d).\n", + __func__, ha->max_req_queues); + ha->flags.max_req_queue_warned = 1; + return ret; + } qla_nvme_fc_transport.max_hw_queues = min((uint8_t)(qla_nvme_fc_transport.max_hw_queues), diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 9b59f032a569..8da00ba54aec 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2017,6 +2017,11 @@ skip_pio: /* Determine queue resources */ ha->max_req_queues = ha->max_rsp_queues = 1; ha->msix_count = QLA_BASE_VECTORS; + + /* Check if FW supports MQ or not */ + if (!(ha->fw_attributes & BIT_6)) + goto mqiobase_exit; + if (!ql2xmqsupport || !ql2xnvmeenable || (!IS_QLA25XX(ha) && !IS_QLA81XX(ha))) goto mqiobase_exit; @@ -2829,10 +2834,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) /* This may fail but that's ok */ pci_enable_pcie_error_reporting(pdev); - /* Turn off T10-DIF when FC-NVMe is enabled */ - if (ql2xnvmeenable) - ql2xenabledif = 0; - ha = kzalloc(sizeof(struct qla_hw_data), GFP_KERNEL); if (!ha) { ql_log_pci(ql_log_fatal, pdev, 0x0009, diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c index e161c05d7d82..411b8a9ff393 100644 --- a/drivers/scsi/qla2xxx/qla_sup.c +++ b/drivers/scsi/qla2xxx/qla_sup.c @@ -2457,7 +2457,7 @@ qla2x00_write_optrom_data(struct scsi_qla_host *vha, void *buf, sec_mask = 0x10000; break; } - /* Fall through... */ + fallthrough; case 0x1f: /* Atmel flash. */ /* 512k sector size. */ @@ -2466,7 +2466,7 @@ qla2x00_write_optrom_data(struct scsi_qla_host *vha, void *buf, sec_mask = 0x80000000; break; } - /* Fall through... */ + fallthrough; case 0x01: /* AMD flash. */ if (flash_id == 0x38 || flash_id == 0x40 || @@ -2499,7 +2499,7 @@ qla2x00_write_optrom_data(struct scsi_qla_host *vha, void *buf, sec_mask = 0x1e000; break; } - /* fall through */ + fallthrough; default: /* Default to 16 kb sector size. */ rest_addr = 0x3fff; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index fbb80a043b4f..2d445bdb2129 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -442,7 +442,7 @@ void qlt_response_pkt_all_vps(struct scsi_qla_host *vha, ql_dbg(ql_dbg_tgt, vha, 0xe073, "qla_target(%d):%s: CRC2 Response pkt\n", vha->vp_idx, __func__); - /* fall through */ + fallthrough; case CTIO_TYPE7: { struct ctio7_from_24xx *entry = (struct ctio7_from_24xx *)pkt; @@ -1270,7 +1270,7 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) qla24xx_chk_fcp_state(sess); - ql_dbg(ql_dbg_tgt, sess->vha, 0xe001, + ql_dbg(ql_dbg_disc, sess->vha, 0xe001, "Scheduling sess %p for deletion %8phC\n", sess, sess->port_name); @@ -4423,7 +4423,7 @@ static int qlt_issue_task_mgmt(struct fc_port *sess, u64 lun, case QLA_TGT_CLEAR_TS: case QLA_TGT_ABORT_TS: abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id); - /* fall through */ + fallthrough; case QLA_TGT_CLEAR_ACA: h = qlt_find_qphint(vha, mcmd->unpacked_lun); mcmd->qpair = h->qpair; @@ -5057,7 +5057,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, res = 1; break; } - /* fall through */ + fallthrough; case ELS_LOGO: case ELS_PRLO: spin_lock_irqsave(&ha->tgt.sess_lock, flags); diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index bab87e47b238..676778cbc550 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -2907,7 +2907,7 @@ static int qla4xxx_session_get_param(struct iscsi_cls_session *cls_sess, chap_tbl.secret_len); } } - /* fall through */ + fallthrough; default: return iscsi_session_get_param(cls_sess, param, buf); } diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c index 3790e8b70bba..48ff7d88af86 100644 --- a/drivers/scsi/qlogicpti.c +++ b/drivers/scsi/qlogicpti.c @@ -200,15 +200,15 @@ static int qlogicpti_mbox_command(struct qlogicpti *qpti, u_short param[], int f /* Write mailbox command registers. */ switch (mbox_param[param[0]] >> 4) { case 6: sbus_writew(param[5], qpti->qregs + MBOX5); - /* Fall through */ + fallthrough; case 5: sbus_writew(param[4], qpti->qregs + MBOX4); - /* Fall through */ + fallthrough; case 4: sbus_writew(param[3], qpti->qregs + MBOX3); - /* Fall through */ + fallthrough; case 3: sbus_writew(param[2], qpti->qregs + MBOX2); - /* Fall through */ + fallthrough; case 2: sbus_writew(param[1], qpti->qregs + MBOX1); - /* Fall through */ + fallthrough; case 1: sbus_writew(param[0], qpti->qregs + MBOX0); } @@ -259,15 +259,15 @@ static int qlogicpti_mbox_command(struct qlogicpti *qpti, u_short param[], int f /* Read back output parameters. */ switch (mbox_param[param[0]] & 0xf) { case 6: param[5] = sbus_readw(qpti->qregs + MBOX5); - /* Fall through */ + fallthrough; case 5: param[4] = sbus_readw(qpti->qregs + MBOX4); - /* Fall through */ + fallthrough; case 4: param[3] = sbus_readw(qpti->qregs + MBOX3); - /* Fall through */ + fallthrough; case 3: param[2] = sbus_readw(qpti->qregs + MBOX2); - /* Fall through */ + fallthrough; case 2: param[1] = sbus_readw(qpti->qregs + MBOX1); - /* Fall through */ + fallthrough; case 1: param[0] = sbus_readw(qpti->qregs + MBOX0); } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 064ed680c053..1ad7260d4758 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -4482,8 +4482,6 @@ static int resp_open_zone(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) goto fini; } - if (zc == ZC2_IMPLICIT_OPEN) - zbc_close_zone(devip, zsp); zbc_open_zone(devip, zsp, true); fini: write_unlock(macc_lckp); @@ -5490,9 +5488,11 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, u64 d = ktime_get_boottime_ns() - ns_from_boot; if (kt <= d) { /* elapsed duration >= kt */ + spin_lock_irqsave(&sqp->qc_lock, iflags); sqcp->a_cmnd = NULL; atomic_dec(&devip->num_in_q); clear_bit(k, sqp->in_use_bm); + spin_unlock_irqrestore(&sqp->qc_lock, iflags); if (new_sd_dp) kfree(sd_dp); /* call scsi_done() from this thread */ diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 927b1e641842..7d3571a2bd89 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -599,7 +599,7 @@ int scsi_check_sense(struct scsi_cmnd *scmd) set_host_byte(scmd, DID_ALLOC_FAILURE); return SUCCESS; } - /* FALLTHROUGH */ + fallthrough; case COPY_ABORTED: case VOLUME_OVERFLOW: case MISCOMPARE: @@ -621,7 +621,7 @@ int scsi_check_sense(struct scsi_cmnd *scmd) return ADD_TO_MLQUEUE; else set_host_byte(scmd, DID_TARGET_FAILURE); - /* FALLTHROUGH */ + fallthrough; case ILLEGAL_REQUEST: if (sshdr.asc == 0x20 || /* Invalid command operation code */ @@ -734,7 +734,7 @@ static int scsi_eh_completed_normally(struct scsi_cmnd *scmd) switch (status_byte(scmd->result)) { case GOOD: scsi_handle_queue_ramp_up(scmd->device); - /* FALLTHROUGH */ + fallthrough; case COMMAND_TERMINATED: return SUCCESS; case CHECK_CONDITION: @@ -755,7 +755,7 @@ static int scsi_eh_completed_normally(struct scsi_cmnd *scmd) return FAILED; case QUEUE_FULL: scsi_handle_queue_full(scmd->device); - /* fall through */ + fallthrough; case BUSY: return NEEDS_RETRY; default: @@ -1302,7 +1302,7 @@ retry_tur: case NEEDS_RETRY: if (retry_cnt--) goto retry_tur; - /*FALLTHRU*/ + fallthrough; case SUCCESS: return 0; default: @@ -1739,7 +1739,7 @@ int scsi_noretry_cmd(struct scsi_cmnd *scmd) if (msg_byte(scmd->result) == COMMAND_COMPLETE && status_byte(scmd->result) == RESERVATION_CONFLICT) return 0; - /* fall through */ + fallthrough; case DID_SOFT_ERROR: return (scmd->request->cmd_flags & REQ_FAILFAST_DRIVER); } @@ -1810,7 +1810,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) set_host_byte(scmd, DID_TIME_OUT); return SUCCESS; } - /* FALLTHROUGH */ + fallthrough; case DID_NO_CONNECT: case DID_BAD_TARGET: /* @@ -1854,7 +1854,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) * lower down */ break; - /* fallthrough */ + fallthrough; case DID_BUS_BUSY: case DID_PARITY: goto maybe_retry; @@ -1892,7 +1892,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) * the case of trying to send too many commands to a * tagged queueing device. */ - /* FALLTHROUGH */ + fallthrough; case BUSY: /* * device can't talk to us at the moment. Should only @@ -1905,7 +1905,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) if (scmd->cmnd[0] == REPORT_LUNS) scmd->device->sdev_target->expecting_lun_change = 0; scsi_handle_queue_ramp_up(scmd->device); - /* FALLTHROUGH */ + fallthrough; case COMMAND_TERMINATED: return SUCCESS; case TASK_ABORTED: @@ -2376,22 +2376,22 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg) rtn = scsi_try_bus_device_reset(scmd); if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE)) break; - /* FALLTHROUGH */ + fallthrough; case SG_SCSI_RESET_TARGET: rtn = scsi_try_target_reset(scmd); if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE)) break; - /* FALLTHROUGH */ + fallthrough; case SG_SCSI_RESET_BUS: rtn = scsi_try_bus_reset(scmd); if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE)) break; - /* FALLTHROUGH */ + fallthrough; case SG_SCSI_RESET_HOST: rtn = scsi_try_host_reset(scmd); if (rtn == SUCCESS) break; - /* FALLTHROUGH */ + fallthrough; default: rtn = FAILED; break; diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c index 45d04b7b2643..14872c9dc78c 100644 --- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -117,14 +117,14 @@ static int ioctl_internal_command(struct scsi_device *sdev, char *cmd, case NOT_READY: /* This happens if there is no disc in drive */ if (sdev->removable) break; - /* FALLTHROUGH */ + fallthrough; case UNIT_ATTENTION: if (sdev->removable) { sdev->changed = 1; result = 0; /* This is no longer considered an error */ break; } - /* FALLTHROUGH -- for non-removable media */ + fallthrough; /* for non-removable media */ default: sdev_printk(KERN_INFO, sdev, "ioctl_internal_command return code = %x\n", diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 7c6dd6f75190..7affaaf8b98e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -795,7 +795,7 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) } if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req))) return; - /*FALLTHRU*/ + fallthrough; case ACTION_REPREP: scsi_io_completion_reprep(cmd, q); break; diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index bd38c8cea56e..ca1e6cf6a38e 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -516,7 +516,7 @@ static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info, break; case BMIC_SENSE_DIAG_OPTIONS: cdb_length = 0; - /* fall through */ + fallthrough; case BMIC_IDENTIFY_CONTROLLER: case BMIC_IDENTIFY_PHYSICAL_DEVICE: case BMIC_SENSE_SUBSYSTEM_INFORMATION: @@ -527,7 +527,7 @@ static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info, break; case BMIC_SET_DIAG_OPTIONS: cdb_length = 0; - /* fall through */ + fallthrough; case BMIC_WRITE_HOST_WELLNESS: request->data_direction = SOP_WRITE_FLAG; cdb[0] = BMIC_WRITE; @@ -2324,7 +2324,7 @@ static int pqi_raid_bypass_submit_scsi_cmd(struct pqi_ctrl_info *ctrl_info, switch (scmd->cmnd[0]) { case WRITE_6: is_write = true; - /* fall through */ + fallthrough; case READ_6: first_block = (u64)(((scmd->cmnd[1] & 0x1f) << 16) | (scmd->cmnd[2] << 8) | scmd->cmnd[3]); @@ -2334,21 +2334,21 @@ static int pqi_raid_bypass_submit_scsi_cmd(struct pqi_ctrl_info *ctrl_info, break; case WRITE_10: is_write = true; - /* fall through */ + fallthrough; case READ_10: first_block = (u64)get_unaligned_be32(&scmd->cmnd[2]); block_cnt = (u32)get_unaligned_be16(&scmd->cmnd[7]); break; case WRITE_12: is_write = true; - /* fall through */ + fallthrough; case READ_12: first_block = (u64)get_unaligned_be32(&scmd->cmnd[2]); block_cnt = get_unaligned_be32(&scmd->cmnd[6]); break; case WRITE_16: is_write = true; - /* fall through */ + fallthrough; case READ_16: first_block = get_unaligned_be64(&scmd->cmnd[2]); block_cnt = get_unaligned_be32(&scmd->cmnd[10]); @@ -2948,7 +2948,7 @@ static unsigned int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info, case PQI_RESPONSE_IU_AIO_PATH_IO_SUCCESS: if (io_request->scmd) io_request->scmd->result = 0; - /* fall through */ + fallthrough; case PQI_RESPONSE_IU_GENERAL_MANAGEMENT: break; case PQI_RESPONSE_IU_VENDOR_GENERAL: @@ -3115,12 +3115,11 @@ static void pqi_process_soft_reset(struct pqi_ctrl_info *ctrl_info, switch (reset_status) { case RESET_INITIATE_DRIVER: - /* fall through */ case RESET_TIMEDOUT: dev_info(&ctrl_info->pci_dev->dev, "resetting controller %u\n", ctrl_info->ctrl_id); sis_soft_reset(ctrl_info); - /* fall through */ + fallthrough; case RESET_INITIATE_FIRMWARE: rc = pqi_ofa_ctrl_restart(ctrl_info); pqi_ofa_free_host_buffer(ctrl_info); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 0c4aa4665a2f..3b3a53c6a0de 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -877,10 +877,10 @@ static void get_sectorsize(struct scsi_cd *cd) case 2340: case 2352: sector_size = 2048; - /* fall through */ + fallthrough; case 2048: cd->capacity *= 4; - /* fall through */ + fallthrough; case 512: break; default: diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 87fbc0ea350b..e2e5356a997d 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -339,14 +339,14 @@ static void st_analyze_sense(struct st_request *SRpnt, struct st_cmdstatus *s) switch (sense[0] & 0x7f) { case 0x71: s->deferred = 1; - /* fall through */ + fallthrough; case 0x70: s->fixed_format = 1; s->flags = sense[2] & 0xe0; break; case 0x73: s->deferred = 1; - /* fall through */ + fallthrough; case 0x72: s->fixed_format = 0; ucp = scsi_sense_desc_find(sense, SCSI_SENSE_BUFFERSIZE, 4); @@ -2723,7 +2723,7 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon switch (cmd_in) { case MTFSFM: chg_eof = 0; /* Changed from the FSF after this */ - /* fall through */ + fallthrough; case MTFSF: cmd[0] = SPACE; cmd[1] = 0x01; /* Space FileMarks */ @@ -2738,7 +2738,7 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon break; case MTBSFM: chg_eof = 0; /* Changed from the FSF after this */ - /* fall through */ + fallthrough; case MTBSF: cmd[0] = SPACE; cmd[1] = 0x01; /* Space FileMarks */ diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c index 701b842296f0..2e3fbc2fae97 100644 --- a/drivers/scsi/sun3_scsi.c +++ b/drivers/scsi/sun3_scsi.c @@ -397,12 +397,12 @@ static int sun3scsi_dma_finish(int write_flag) case CSR_LEFT_3: *vaddr = (dregs->bpack_lo & 0xff00) >> 8; vaddr--; - /* Fall through */ + fallthrough; case CSR_LEFT_2: *vaddr = (dregs->bpack_hi & 0x00ff); vaddr--; - /* Fall through */ + fallthrough; case CSR_LEFT_1: *vaddr = (dregs->bpack_hi & 0xff00) >> 8; diff --git a/drivers/scsi/sym53c8xx_2/sym_fw.c b/drivers/scsi/sym53c8xx_2/sym_fw.c index 6d7651a7847e..c6db61b61de3 100644 --- a/drivers/scsi/sym53c8xx_2/sym_fw.c +++ b/drivers/scsi/sym53c8xx_2/sym_fw.c @@ -523,7 +523,7 @@ void sym_fw_bind_script(struct sym_hcb *np, u32 *start, int len) new = old; break; } - /* fall through */ + fallthrough; default: new = 0; panic("sym_fw_bind_script: " diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c index 8410117d5aa4..cc11daa1222b 100644 --- a/drivers/scsi/sym53c8xx_2/sym_hipd.c +++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c @@ -3059,7 +3059,7 @@ static void sym_sir_bad_scsi_status(struct sym_hcb *np, int num, struct sym_ccb sym_print_addr(cp->cmd, "%s\n", s_status == S_BUSY ? "BUSY" : "QUEUE FULL\n"); } - /* fall through */ + fallthrough; default: /* S_INT, S_INT_COND_MET, S_CONFLICT */ sym_complete_error (np, cp); break; @@ -4620,7 +4620,7 @@ static void sym_int_sir(struct sym_hcb *np) * Negotiation failed. * Target does not want answer message. */ - /* fall through */ + fallthrough; case SIR_NEGO_PROTO: sym_nego_default(np, tp, cp); goto out; diff --git a/drivers/scsi/sym53c8xx_2/sym_nvram.c b/drivers/scsi/sym53c8xx_2/sym_nvram.c index d37e2a69136a..e13d5351f155 100644 --- a/drivers/scsi/sym53c8xx_2/sym_nvram.c +++ b/drivers/scsi/sym53c8xx_2/sym_nvram.c @@ -695,7 +695,7 @@ static int sym_read_Tekram_nvram (struct sym_device *np, Tekram_nvram *nvram) data, len); if (!x) break; - /* fall through */ + fallthrough; default: x = sym_read_T93C46_nvram(np, nvram); break; diff --git a/drivers/scsi/ufs/ti-j721e-ufs.c b/drivers/scsi/ufs/ti-j721e-ufs.c index 46bb905b4d6a..eafe0db98d54 100644 --- a/drivers/scsi/ufs/ti-j721e-ufs.c +++ b/drivers/scsi/ufs/ti-j721e-ufs.c @@ -38,6 +38,7 @@ static int ti_j721e_ufs_probe(struct platform_device *pdev) /* Select MPHY refclk frequency */ clk = devm_clk_get(dev, NULL); if (IS_ERR(clk)) { + ret = PTR_ERR(clk); dev_err(dev, "Cannot claim MPHY clock.\n"); goto clk_err; } diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index 29cd017c1aa0..1755dd6b04ae 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -212,7 +212,7 @@ static int ufs_mtk_wait_link_state(struct ufs_hba *hba, u32 state, ktime_t timeout, time_checked; u32 val; - timeout = ktime_add_us(ktime_get(), ms_to_ktime(max_wait_ms)); + timeout = ktime_add_ms(ktime_get(), max_wait_ms); do { time_checked = ktime_get(); ufshcd_writel(hba, 0x20, REG_UFS_DEBUG_SEL); diff --git a/drivers/scsi/ufs/ufs_bsg.c b/drivers/scsi/ufs/ufs_bsg.c index bcfbbd0d5c45..5b2bc1a6f922 100644 --- a/drivers/scsi/ufs/ufs_bsg.c +++ b/drivers/scsi/ufs/ufs_bsg.c @@ -110,7 +110,7 @@ static int ufs_bsg_request(struct bsg_job *job) goto out; } - /* fall through */ + fallthrough; case UPIU_TRANSACTION_NOP_OUT: case UPIU_TRANSACTION_TASK_REQ: ret = ufshcd_exec_raw_upiu_cmd(hba, &bsg_request->upiu_req, diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index f407b13883ac..5a95a7bfbab0 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -44,11 +44,23 @@ static int ufs_intel_link_startup_notify(struct ufs_hba *hba, return err; } +static int ufs_intel_ehl_init(struct ufs_hba *hba) +{ + hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8; + return 0; +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .link_startup_notify = ufs_intel_link_startup_notify, }; +static struct ufs_hba_variant_ops ufs_intel_ehl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_ehl_init, + .link_startup_notify = ufs_intel_link_startup_notify, +}; + #ifdef CONFIG_PM_SLEEP /** * ufshcd_pci_suspend - suspend power management function @@ -177,8 +189,8 @@ static const struct dev_pm_ops ufshcd_pci_pm_ops = { static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VENDOR_ID_SAMSUNG, 0xC00C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, { PCI_VDEVICE(INTEL, 0x9DFA), (kernel_ulong_t)&ufs_intel_cnl_hba_vops }, - { PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_cnl_hba_vops }, - { PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_cnl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 307622284239..1d157ff58d81 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -1561,6 +1561,7 @@ unblock_reqs: int ufshcd_hold(struct ufs_hba *hba, bool async) { int rc = 0; + bool flush_result; unsigned long flags; if (!ufshcd_is_clkgating_allowed(hba)) @@ -1592,7 +1593,9 @@ start: break; } spin_unlock_irqrestore(hba->host->host_lock, flags); - flush_work(&hba->clk_gating.ungate_work); + flush_result = flush_work(&hba->clk_gating.ungate_work); + if (hba->clk_gating.is_suspended && !flush_result) + goto out; spin_lock_irqsave(hba->host->host_lock, flags); goto start; } @@ -1609,7 +1612,7 @@ start: * currently running. Hence, fall through to cancel gating * work and to enable clocks. */ - /* fallthrough */ + fallthrough; case CLKS_OFF: ufshcd_scsi_block_requests(hba); hba->clk_gating.state = REQ_CLKS_ON; @@ -1621,7 +1624,7 @@ start: * fall through to check if we should wait for this * work to be done or not. */ - /* fallthrough */ + fallthrough; case REQ_CLKS_ON: if (async) { rc = -EAGAIN; @@ -4734,7 +4737,7 @@ ufshcd_scsi_cmd_status(struct ufshcd_lrb *lrbp, int scsi_status) switch (scsi_status) { case SAM_STAT_CHECK_CONDITION: ufshcd_copy_sense_data(lrbp); - /* fallthrough */ + fallthrough; case SAM_STAT_GOOD: result |= DID_OK << 16 | COMMAND_COMPLETE << 8 | @@ -5941,7 +5944,7 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status) */ static irqreturn_t ufshcd_intr(int irq, void *__hba) { - u32 intr_status, enabled_intr_status; + u32 intr_status, enabled_intr_status = 0; irqreturn_t retval = IRQ_NONE; struct ufs_hba *hba = __hba; int retries = hba->nutrs; @@ -5955,7 +5958,7 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba) * read, make sure we handle them by checking the interrupt status * again in a loop until we process all of the reqs before returning. */ - do { + while (intr_status && retries--) { enabled_intr_status = intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE); if (intr_status) @@ -5964,9 +5967,9 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba) retval |= ufshcd_sl_intr(hba, enabled_intr_status); intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS); - } while (intr_status && --retries); + } - if (retval == IRQ_NONE) { + if (enabled_intr_status && retval == IRQ_NONE) { dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x\n", __func__, intr_status); ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: "); @@ -6274,7 +6277,7 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba, switch (msgcode) { case UPIU_TRANSACTION_NOP_OUT: cmd_type = DEV_CMD_TYPE_NOP; - /* fall through */ + fallthrough; case UPIU_TRANSACTION_QUERY_REQ: ufshcd_hold(hba, false); mutex_lock(&hba->dev_cmd.lock); @@ -6434,14 +6437,8 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) goto out; } - if (!(reg & (1 << tag))) { - dev_err(hba->dev, - "%s: cmd was completed, but without a notifying intr, tag = %d", - __func__, tag); - } - /* Print Transfer Request of aborted task */ - dev_err(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag); + dev_info(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag); /* * Print detailed info about aborted request. @@ -6462,6 +6459,13 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) } hba->req_abort_count++; + if (!(reg & (1 << tag))) { + dev_err(hba->dev, + "%s: cmd was completed, but without a notifying intr, tag = %d", + __func__, tag); + goto cleanup; + } + /* Skip task abort in case previous aborts failed and report failure */ if (lrbp->req_abort_skip) { err = -EIO; @@ -6492,7 +6496,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) /* command completed already */ dev_err(hba->dev, "%s: cmd at tag %d successfully cleared from DB.\n", __func__, tag); - goto out; + goto cleanup; } else { dev_err(hba->dev, "%s: no response from device. tag = %d, err %d\n", @@ -6526,6 +6530,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) goto out; } +cleanup: scsi_dma_unmap(cmd); spin_lock_irqsave(host->host_lock, flags); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index b2ef18f1b746..363589c0bd37 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -520,6 +520,12 @@ enum ufshcd_quirks { * OCS FATAL ERROR with device error through sense data */ UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR = 1 << 10, + + /* + * This quirk needs to be enabled if the host controller has + * auto-hibernate capability but it doesn't work. + */ + UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8 = 1 << 11, }; enum ufshcd_caps { @@ -803,7 +809,8 @@ return true; static inline bool ufshcd_is_auto_hibern8_supported(struct ufs_hba *hba) { - return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT); + return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT) && + !(hba->quirks & UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8); } static inline bool ufshcd_is_auto_hibern8_enabled(struct ufs_hba *hba) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index ca1c39b6f631..3b1803432090 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -148,7 +148,7 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf) default: scmd_printk(KERN_WARNING, sc, "Unknown response %d", resp->response); - /* fall through */ + fallthrough; case VIRTIO_SCSI_S_FAILURE: set_host_byte(sc, DID_ERROR); break; diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index 8dbb4db6831a..081f54ab7d86 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -607,7 +607,7 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter, case BTSTAT_TAGREJECT: case BTSTAT_BADMSG: cmd->result = (DRIVER_INVALID << 24); - /* fall through */ + fallthrough; case BTSTAT_HAHARDWARE: case BTSTAT_INVPHASE: diff --git a/drivers/scsi/wd33c93.c b/drivers/scsi/wd33c93.c index f81046f0e68a..87dafbc942d3 100644 --- a/drivers/scsi/wd33c93.c +++ b/drivers/scsi/wd33c93.c @@ -1854,7 +1854,7 @@ round_4(unsigned int x) case 1: --x; break; case 2: ++x; - /* fall through */ + fallthrough; case 3: ++x; } return x; diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index f0068e96a177..259fc248d06c 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -1111,7 +1111,7 @@ static void scsifront_backend_changed(struct xenbus_device *dev, case XenbusStateClosed: if (dev->state == XenbusStateClosed) break; - /* fall through - Missed the backend's Closing state */ + fallthrough; /* Missed the backend's Closing state */ case XenbusStateClosing: scsifront_disconnect(info); break; diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c index e19102f46302..b25d0f7dac9e 100644 --- a/drivers/soc/qcom/socinfo.c +++ b/drivers/soc/qcom/socinfo.c @@ -353,7 +353,7 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo, debugfs_create_u32("nmodem_supported", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.nmodem_supported); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 14): qcom_socinfo->info.num_clusters = __le32_to_cpu(info->num_clusters); qcom_socinfo->info.ncluster_array_offset = __le32_to_cpu(info->ncluster_array_offset); @@ -368,14 +368,14 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo, &qcom_socinfo->info.num_defective_parts); debugfs_create_u32("ndefective_parts_array_offset", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.ndefective_parts_array_offset); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 13): qcom_socinfo->info.nproduct_id = __le32_to_cpu(info->nproduct_id); debugfs_create_u32("nproduct_id", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.nproduct_id); DEBUGFS_ADD(info, chip_id); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 12): qcom_socinfo->info.chip_family = __le32_to_cpu(info->chip_family); @@ -392,7 +392,7 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo, debugfs_create_x32("raw_device_number", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.raw_device_num); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 11): case SOCINFO_VERSION(0, 10): case SOCINFO_VERSION(0, 9): @@ -400,12 +400,12 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo, debugfs_create_u32("foundry_id", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.foundry_id); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 8): case SOCINFO_VERSION(0, 7): DEBUGFS_ADD(info, pmic_model); DEBUGFS_ADD(info, pmic_die_rev); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 6): qcom_socinfo->info.hw_plat_subtype = __le32_to_cpu(info->hw_plat_subtype); @@ -413,7 +413,7 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo, debugfs_create_u32("hardware_platform_subtype", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.hw_plat_subtype); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 5): qcom_socinfo->info.accessory_chip = __le32_to_cpu(info->accessory_chip); @@ -421,27 +421,27 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo, debugfs_create_u32("accessory_chip", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.accessory_chip); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 4): qcom_socinfo->info.plat_ver = __le32_to_cpu(info->plat_ver); debugfs_create_u32("platform_version", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.plat_ver); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 3): qcom_socinfo->info.hw_plat = __le32_to_cpu(info->hw_plat); debugfs_create_u32("hardware_platform", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.hw_plat); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 2): qcom_socinfo->info.raw_ver = __le32_to_cpu(info->raw_ver); debugfs_create_u32("raw_version", 0400, qcom_socinfo->dbg_root, &qcom_socinfo->info.raw_ver); - /* Fall through */ + fallthrough; case SOCINFO_VERSION(0, 1): DEBUGFS_ADD(info, build_id); break; diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c index 42cf37a0556b..d332e5d9abac 100644 --- a/drivers/soc/tegra/pmc.c +++ b/drivers/soc/tegra/pmc.c @@ -2229,7 +2229,7 @@ static int tegra_pmc_clk_notify_cb(struct notifier_block *nb, case POST_RATE_CHANGE: pmc->rate = data->new_rate; - /* fall through */ + fallthrough; case ABORT_RATE_CHANGE: mutex_unlock(&pmc->powergates_lock); diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index c3008e423f59..c6ea760ea5f0 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -1017,4 +1017,7 @@ config SPI_SLAVE_SYSTEM_CONTROL endif # SPI_SLAVE +config SPI_DYNAMIC + def_bool ACPI || OF_DYNAMIC || SPI_SLAVE + endif # SPI diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c index 2f717812c766..03b034c15d2b 100644 --- a/drivers/spi/spi-bcm2835aux.c +++ b/drivers/spi/spi-bcm2835aux.c @@ -164,10 +164,10 @@ static inline void bcm2835aux_rd_fifo(struct bcm2835aux_spi *bs) switch (count) { case 3: *bs->rx_buf++ = (data >> 16) & 0xff; - /* fallthrough */ + fallthrough; case 2: *bs->rx_buf++ = (data >> 8) & 0xff; - /* fallthrough */ + fallthrough; case 1: *bs->rx_buf++ = (data >> 0) & 0xff; /* fallthrough - no default */ diff --git a/drivers/spi/spi-fsl-cpm.c b/drivers/spi/spi-fsl-cpm.c index 54ad0ac121e5..ee905880769e 100644 --- a/drivers/spi/spi-fsl-cpm.c +++ b/drivers/spi/spi-fsl-cpm.c @@ -226,7 +226,7 @@ static void fsl_spi_free_dummy_rx(void) case 1: kfree(fsl_dummy_rx); fsl_dummy_rx = NULL; - /* fall through */ + fallthrough; default: fsl_dummy_rx_refcnt--; break; @@ -294,7 +294,7 @@ int fsl_spi_cpm_init(struct mpc8xxx_spi *mspi) switch (mspi->subblock) { default: dev_warn(dev, "cell-index unspecified, assuming SPI1\n"); - /* fall through */ + fallthrough; case 0: mspi->subblock = QE_CR_SUBBLOCK_SPI1; break; diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c index bd23c4689b46..127b8bd25831 100644 --- a/drivers/spi/spi-sprd-adi.c +++ b/drivers/spi/spi-sprd-adi.c @@ -506,7 +506,7 @@ static int sprd_adi_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "failed to find hwlock id, %d\n", ret); - /* fall-through */ + fallthrough; case -EPROBE_DEFER: goto put_ctlr; } diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 4c643dfc7fbb..d4b33b358a31 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -13,6 +13,7 @@ #include <linux/iopoll.h> #include <linux/module.h> #include <linux/of_platform.h> +#include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> #include <linux/reset.h> #include <linux/spi/spi.h> @@ -441,7 +442,8 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, { u32 div, mbrdiv; - div = DIV_ROUND_UP(spi->clk_rate, speed_hz); + /* Ensure spi->clk_rate is even */ + div = DIV_ROUND_UP(spi->clk_rate & ~0x1, speed_hz); /* * SPI framework set xfer->speed_hz to master->max_speed_hz if @@ -467,20 +469,27 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, /** * stm32h7_spi_prepare_fthlv - Determine FIFO threshold level * @spi: pointer to the spi controller data structure + * @xfer_len: length of the message to be transferred */ -static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi) +static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi, u32 xfer_len) { - u32 fthlv, half_fifo; + u32 fthlv, half_fifo, packet; /* data packet should not exceed 1/2 of fifo space */ half_fifo = (spi->fifo_size / 2); + /* data_packet should not exceed transfer length */ + if (half_fifo > xfer_len) + packet = xfer_len; + else + packet = half_fifo; + if (spi->cur_bpw <= 8) - fthlv = half_fifo; + fthlv = packet; else if (spi->cur_bpw <= 16) - fthlv = half_fifo / 2; + fthlv = packet / 2; else - fthlv = half_fifo / 4; + fthlv = packet / 4; /* align packet size with data registers access */ if (spi->cur_bpw > 8) @@ -488,6 +497,9 @@ static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi) else fthlv -= (fthlv % 4); /* multiple of 4 */ + if (!fthlv) + fthlv = 1; + return fthlv; } @@ -966,13 +978,13 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id) if (!spi->cur_usedma && (spi->rx_buf && (spi->rx_len > 0))) stm32h7_spi_read_rxfifo(spi, false); - writel_relaxed(mask, spi->base + STM32H7_SPI_IFCR); + writel_relaxed(sr & mask, spi->base + STM32H7_SPI_IFCR); spin_unlock_irqrestore(&spi->lock, flags); if (end) { - spi_finalize_current_transfer(master); stm32h7_spi_disable(spi); + spi_finalize_current_transfer(master); } return IRQ_HANDLED; @@ -1393,7 +1405,7 @@ static void stm32h7_spi_set_bpw(struct stm32_spi *spi) cfg1_setb |= (bpw << STM32H7_SPI_CFG1_DSIZE_SHIFT) & STM32H7_SPI_CFG1_DSIZE; - spi->cur_fthlv = stm32h7_spi_prepare_fthlv(spi); + spi->cur_fthlv = stm32h7_spi_prepare_fthlv(spi, spi->cur_xferlen); fthlv = spi->cur_fthlv - 1; cfg1_clrb |= STM32H7_SPI_CFG1_FTHLV; @@ -1585,39 +1597,33 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi, unsigned long flags; unsigned int comm_type; int nb_words, ret = 0; + int mbr; spin_lock_irqsave(&spi->lock, flags); - if (spi->cur_bpw != transfer->bits_per_word) { - spi->cur_bpw = transfer->bits_per_word; - spi->cfg->set_bpw(spi); - } - - if (spi->cur_speed != transfer->speed_hz) { - int mbr; + spi->cur_xferlen = transfer->len; - /* Update spi->cur_speed with real clock speed */ - mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz, - spi->cfg->baud_rate_div_min, - spi->cfg->baud_rate_div_max); - if (mbr < 0) { - ret = mbr; - goto out; - } + spi->cur_bpw = transfer->bits_per_word; + spi->cfg->set_bpw(spi); - transfer->speed_hz = spi->cur_speed; - stm32_spi_set_mbr(spi, mbr); + /* Update spi->cur_speed with real clock speed */ + mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz, + spi->cfg->baud_rate_div_min, + spi->cfg->baud_rate_div_max); + if (mbr < 0) { + ret = mbr; + goto out; } + transfer->speed_hz = spi->cur_speed; + stm32_spi_set_mbr(spi, mbr); + comm_type = stm32_spi_communication_type(spi_dev, transfer); - if (spi->cur_comm != comm_type) { - ret = spi->cfg->set_mode(spi, comm_type); + ret = spi->cfg->set_mode(spi, comm_type); + if (ret < 0) + goto out; - if (ret < 0) - goto out; - - spi->cur_comm = comm_type; - } + spi->cur_comm = comm_type; if (spi->cfg->set_data_idleness) spi->cfg->set_data_idleness(spi, transfer->len); @@ -1635,8 +1641,6 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi, goto out; } - spi->cur_xferlen = transfer->len; - dev_dbg(spi->dev, "transfer communication mode set to %d\n", spi->cur_comm); dev_dbg(spi->dev, @@ -1996,6 +2000,8 @@ static int stm32_spi_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); + pinctrl_pm_select_sleep_state(&pdev->dev); + return 0; } @@ -2007,13 +2013,18 @@ static int stm32_spi_runtime_suspend(struct device *dev) clk_disable_unprepare(spi->clk); - return 0; + return pinctrl_pm_select_sleep_state(dev); } static int stm32_spi_runtime_resume(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct stm32_spi *spi = spi_master_get_devdata(master); + int ret; + + ret = pinctrl_pm_select_default_state(dev); + if (ret) + return ret; return clk_prepare_enable(spi->clk); } @@ -2043,10 +2054,23 @@ static int stm32_spi_resume(struct device *dev) return ret; ret = spi_master_resume(master); - if (ret) + if (ret) { clk_disable_unprepare(spi->clk); + return ret; + } - return ret; + ret = pm_runtime_get_sync(dev); + if (ret) { + dev_err(dev, "Unable to power device:%d\n", ret); + return ret; + } + + spi->cfg->config(spi); + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return 0; } #endif diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 6626587e77b4..dc12af018350 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -475,6 +475,12 @@ static LIST_HEAD(spi_controller_list); */ static DEFINE_MUTEX(board_lock); +/* + * Prevents addition of devices with same chip select and + * addition of devices below an unregistering controller. + */ +static DEFINE_MUTEX(spi_add_lock); + /** * spi_alloc_device - Allocate a new SPI device * @ctlr: Controller to which device is connected @@ -554,7 +560,6 @@ static int spi_dev_check(struct device *dev, void *data) */ int spi_add_device(struct spi_device *spi) { - static DEFINE_MUTEX(spi_add_lock); struct spi_controller *ctlr = spi->controller; struct device *dev = ctlr->dev.parent; int status; @@ -582,6 +587,13 @@ int spi_add_device(struct spi_device *spi) goto done; } + /* Controller may unregister concurrently */ + if (IS_ENABLED(CONFIG_SPI_DYNAMIC) && + !device_is_registered(&ctlr->dev)) { + status = -ENODEV; + goto done; + } + /* Descriptors take precedence */ if (ctlr->cs_gpiods) spi->cs_gpiod = ctlr->cs_gpiods[spi->chip_select]; @@ -2795,6 +2807,10 @@ void spi_unregister_controller(struct spi_controller *ctlr) struct spi_controller *found; int id = ctlr->bus_num; + /* Prevent addition of new devices, unregister existing ones */ + if (IS_ENABLED(CONFIG_SPI_DYNAMIC)) + mutex_lock(&spi_add_lock); + device_for_each_child(&ctlr->dev, NULL, __unregister); /* First make sure that this controller was ever added */ @@ -2815,6 +2831,9 @@ void spi_unregister_controller(struct spi_controller *ctlr) if (found == ctlr) idr_remove(&spi_master_idr, id); mutex_unlock(&board_lock); + + if (IS_ENABLED(CONFIG_SPI_DYNAMIC)) + mutex_unlock(&spi_add_lock); } EXPORT_SYMBOL_GPL(spi_unregister_controller); diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c index 823dc99be46f..a8d2525e7af9 100644 --- a/drivers/ssb/driver_chipcommon.c +++ b/drivers/ssb/driver_chipcommon.c @@ -425,7 +425,7 @@ void ssb_chipco_get_clockcontrol(struct ssb_chipcommon *cc, *m = chipco_read32(cc, SSB_CHIPCO_CLOCK_M2); break; } - /* Fall through */ + fallthrough; default: *m = chipco_read32(cc, SSB_CHIPCO_CLOCK_SB); } diff --git a/drivers/ssb/driver_mipscore.c b/drivers/ssb/driver_mipscore.c index 1ca2ac5ef2b8..354486b7ed3a 100644 --- a/drivers/ssb/driver_mipscore.c +++ b/drivers/ssb/driver_mipscore.c @@ -342,7 +342,7 @@ void ssb_mipscore_init(struct ssb_mipscore *mcore) set_irq(dev, irq++); break; } - /* fallthrough */ + fallthrough; case SSB_DEV_EXTIF: set_irq(dev, 0); break; diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c index b97a5c32d44a..f49ab1aa2149 100644 --- a/drivers/ssb/scan.c +++ b/drivers/ssb/scan.c @@ -228,7 +228,7 @@ static void __iomem *ssb_ioremap(struct ssb_bus *bus, switch (bus->bustype) { case SSB_BUSTYPE_SSB: /* Only map the first core for now. */ - /* fallthrough... */ + fallthrough; case SSB_BUSTYPE_PCMCIA: mmio = ioremap(baseaddr, SSB_CORE_SIZE); break; diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.c b/drivers/staging/media/atomisp/pci/atomisp_cmd.c index 8ea65bef35d2..a4e4eef55f35 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_cmd.c +++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.c @@ -4984,7 +4984,7 @@ enum mipi_port_id __get_mipi_port(struct atomisp_device *isp, if (MIPI_PORT1_ID + 1 != N_MIPI_PORT_ID) { return MIPI_PORT1_ID + 1; } - /* fall through */ + fallthrough; default: dev_err(isp->dev, "unsupported port: %d\n", port); return MIPI_PORT0_ID; diff --git a/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c b/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c index cccc5bfa1057..1b2b2c68025b 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c +++ b/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c @@ -704,14 +704,14 @@ static bool is_pipe_valid_to_current_run_mode(struct atomisp_sub_device *asd, return false; } - /* fall-through */ + fallthrough; case ATOMISP_RUN_MODE_CONTINUOUS_CAPTURE: if (pipe_id == IA_CSS_PIPE_ID_CAPTURE || pipe_id == IA_CSS_PIPE_ID_PREVIEW) return true; return false; - /* fall-through */ + fallthrough; case ATOMISP_RUN_MODE_VIDEO: if (!asd->continuous_mode->val) { if (pipe_id == IA_CSS_PIPE_ID_VIDEO || @@ -720,7 +720,7 @@ static bool is_pipe_valid_to_current_run_mode(struct atomisp_sub_device *asd, else return false; } - /* fall through */ + fallthrough; case ATOMISP_RUN_MODE_SDV: if (pipe_id == IA_CSS_PIPE_ID_CAPTURE || pipe_id == IA_CSS_PIPE_ID_VIDEO) @@ -2765,7 +2765,7 @@ static unsigned int atomisp_get_pipe_index(struct atomisp_sub_device *asd, if (!atomisp_is_mbuscode_raw(asd->fmt[asd->capture_pad].fmt.code)) { return IA_CSS_PIPE_ID_CAPTURE; } - /* fall through */ + fallthrough; case ATOMISP_SUBDEV_PAD_SOURCE_PREVIEW: if (asd->yuvpp_mode) return IA_CSS_PIPE_ID_YUVPP; diff --git a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c index f8d616f08b51..65b0c8a662a0 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c +++ b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c @@ -1467,7 +1467,6 @@ enum ia_css_pipe_id atomisp_get_css_pipe_id(struct atomisp_sub_device *asd) case ATOMISP_RUN_MODE_VIDEO: return IA_CSS_PIPE_ID_VIDEO; case ATOMISP_RUN_MODE_STILL_CAPTURE: - /* fall through */ default: return IA_CSS_PIPE_ID_CAPTURE; } diff --git a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c index a000a1e316f7..0114b040247b 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c +++ b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c @@ -1086,7 +1086,7 @@ static int atomisp_subdev_probe(struct atomisp_device *isp) case RAW_CAMERA: dev_dbg(isp->dev, "raw_index: %d\n", raw_index); raw_index = isp->input_cnt; - /* fall through */ + fallthrough; case SOC_CAMERA: dev_dbg(isp->dev, "SOC_INDEX: %d\n", isp->input_cnt); if (isp->input_cnt >= ATOM_ISP_MAX_INPUTS) { diff --git a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c index 4fb9bfdd2f4c..f13af2329f48 100644 --- a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c +++ b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c @@ -660,7 +660,7 @@ static void free_private_bo_pages(struct hmm_buffer_object *bo, break; } - /* fall through */ + fallthrough; /* * if dynamic memory pool doesn't exist, need to free diff --git a/drivers/staging/media/atomisp/pci/sh_css.c b/drivers/staging/media/atomisp/pci/sh_css.c index 54434c2dbaf9..a68cbb4995f0 100644 --- a/drivers/staging/media/atomisp/pci/sh_css.c +++ b/drivers/staging/media/atomisp/pci/sh_css.c @@ -4510,7 +4510,7 @@ ia_css_pipe_dequeue_buffer(struct ia_css_pipe *pipe, #endif pipe->stop_requested = false; } - /* fall through */ + fallthrough; case IA_CSS_BUFFER_TYPE_VF_OUTPUT_FRAME: case IA_CSS_BUFFER_TYPE_SEC_VF_OUTPUT_FRAME: frame = (struct ia_css_frame *)HOST_ADDRESS(ddr_buffer.kernel_ptr); diff --git a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c index 24041849384a..6386a3989bfe 100644 --- a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c +++ b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c @@ -110,7 +110,7 @@ hantro_g1_mpeg2_dec_set_buffers(struct hantro_dev *vpu, struct hantro_ctx *ctx, case V4L2_MPEG2_PICTURE_CODING_TYPE_B: backward_addr = hantro_get_ref(ctx, slice_params->backward_ref_ts); - /* fall-through */ + fallthrough; case V4L2_MPEG2_PICTURE_CODING_TYPE_P: forward_addr = hantro_get_ref(ctx, slice_params->forward_ref_ts); diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c index 7e9aad671489..f610fa5b4335 100644 --- a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c +++ b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c @@ -112,7 +112,7 @@ rk3399_vpu_mpeg2_dec_set_buffers(struct hantro_dev *vpu, case V4L2_MPEG2_PICTURE_CODING_TYPE_B: backward_addr = hantro_get_ref(ctx, slice_params->backward_ref_ts); - /* fall-through */ + fallthrough; case V4L2_MPEG2_PICTURE_CODING_TYPE_P: forward_addr = hantro_get_ref(ctx, slice_params->forward_ref_ts); diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c index d92fd804488e..21ebf7769696 100644 --- a/drivers/staging/media/imx/imx-media-csi.c +++ b/drivers/staging/media/imx/imx-media-csi.c @@ -488,7 +488,7 @@ static int csi_idmac_setup_channel(struct csi_priv *priv) passthrough_cycles = incc->cycles; break; } - /* fallthrough - non-passthrough RGB565 (CSI-2 bus) */ + fallthrough; /* non-passthrough RGB565 (CSI-2 bus) */ default: burst_size = (image.pix.width & 0xf) ? 8 : 16; passthrough_bits = 16; diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c index bc27f9430eeb..7c6b91f0e780 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -199,6 +199,7 @@ static int cedrus_request_validate(struct media_request *req) struct v4l2_ctrl *ctrl_test; unsigned int count; unsigned int i; + int ret = 0; list_for_each_entry(obj, &req->objects, list) { struct vb2_buffer *vb; @@ -243,12 +244,16 @@ static int cedrus_request_validate(struct media_request *req) if (!ctrl_test) { v4l2_info(&ctx->dev->v4l2_dev, "Missing required codec control\n"); - return -ENOENT; + ret = -ENOENT; + break; } } v4l2_ctrl_request_hdl_put(hdl); + if (ret) + return ret; + return vb2_request_validate(req); } diff --git a/drivers/staging/media/usbvision/usbvision-i2c.c b/drivers/staging/media/usbvision/usbvision-i2c.c index 6e4df3335b1b..aa3ff67a3cb1 100644 --- a/drivers/staging/media/usbvision/usbvision-i2c.c +++ b/drivers/staging/media/usbvision/usbvision-i2c.c @@ -303,13 +303,13 @@ usbvision_i2c_read_max4(struct usb_usbvision *usbvision, unsigned char addr, switch (len) { case 4: buf[3] = usbvision_read_reg(usbvision, USBVISION_SER_DAT4); - /* fall through */ + fallthrough; case 3: buf[2] = usbvision_read_reg(usbvision, USBVISION_SER_DAT3); - /* fall through */ + fallthrough; case 2: buf[1] = usbvision_read_reg(usbvision, USBVISION_SER_DAT2); - /* fall through */ + fallthrough; case 1: buf[0] = usbvision_read_reg(usbvision, USBVISION_SER_DAT1); break; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c index 30ea37e1a3f5..bd37f2afadea 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_main.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -444,7 +444,7 @@ cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp, case CPL_RX_ISCSI_DDP: case CPL_FW4_ACK: lro_flush = false; - /* fall through */ + fallthrough; case CPL_ABORT_RPL_RSS: case CPL_PASS_ESTABLISH: case CPL_PEER_CLOSE: diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index c9689610e186..cd045dc75a58 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -3740,7 +3740,7 @@ check_rsp_state: case ISTATE_SEND_LOGOUTRSP: if (!iscsit_logout_post_handler(cmd, conn)) return -ECONNRESET; - /* fall through */ + fallthrough; case ISTATE_SEND_STATUS: case ISTATE_SEND_ASYNCMSG: case ISTATE_SEND_NOPIN: diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 8fc88654bff6..5f79ea05f9b8 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -345,7 +345,7 @@ static int core_scsi3_pr_seq_non_holder(struct se_cmd *cmd, u32 pr_reg_type, break; case PR_TYPE_WRITE_EXCLUSIVE_REGONLY: we = 1; - /* fall through */ + fallthrough; case PR_TYPE_EXCLUSIVE_ACCESS_REGONLY: /* * Some commands are only allowed for registered I_T Nexuses. @@ -354,7 +354,7 @@ static int core_scsi3_pr_seq_non_holder(struct se_cmd *cmd, u32 pr_reg_type, break; case PR_TYPE_WRITE_EXCLUSIVE_ALLREG: we = 1; - /* fall through */ + fallthrough; case PR_TYPE_EXCLUSIVE_ACCESS_ALLREG: /* * Each registered I_T Nexus is a reservation holder. diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index f1e81886122d..6e8b8d30938f 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -734,7 +734,7 @@ sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb, } if (!protect) return TCM_NO_SENSE; - /* Fallthrough */ + fallthrough; default: pr_err("Unable to determine pi_prot_type for CDB: 0x%02x " "PROTECT: 0x%02x\n", cdb[0], protect); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 9fb0be0aa620..590eac2df909 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -2236,7 +2236,7 @@ static void transport_complete_qf(struct se_cmd *cmd) ret = cmd->se_tfo->queue_data_in(cmd); break; } - /* fall through */ + fallthrough; case DMA_NONE: queue_status: trace_target_cmd_complete(cmd); @@ -2431,7 +2431,7 @@ queue_rsp: goto queue_full; break; } - /* fall through */ + fallthrough; case DMA_NONE: queue_status: trace_target_cmd_complete(cmd); diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index e9f0dda5ff92..a7ed56602c6c 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -537,7 +537,7 @@ static void ft_send_work(struct work_struct *work) case FCP_PTA_ACA: task_attr = TCM_ACA_TAG; break; - case FCP_PTA_SIMPLE: /* Fallthrough */ + case FCP_PTA_SIMPLE: default: task_attr = TCM_SIMPLE_TAG; } diff --git a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c index bf7bae42c141..6dc879fea9c8 100644 --- a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c +++ b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2011-2015, 2017, The Linux Foundation. All rights reserved. + * Copyright (c) 2011-2015, 2017, 2020, The Linux Foundation. All rights reserved. */ #include <linux/bitops.h> @@ -191,7 +191,7 @@ static int qpnp_tm_get_temp(void *data, int *temp) chip->temp = mili_celsius; } - *temp = chip->temp < 0 ? 0 : chip->temp; + *temp = chip->temp; return 0; } diff --git a/drivers/thermal/qcom/tsens-v0_1.c b/drivers/thermal/qcom/tsens-v0_1.c index e64db5f80d90..4ffa2e2c0145 100644 --- a/drivers/thermal/qcom/tsens-v0_1.c +++ b/drivers/thermal/qcom/tsens-v0_1.c @@ -220,7 +220,7 @@ static int calibrate_8916(struct tsens_priv *priv) p2[4] = (qfprom_cdata[1] & MSM8916_S4_P2_MASK) >> MSM8916_S4_P2_SHIFT; for (i = 0; i < priv->num_sensors; i++) p2[i] = ((base1 + p2[i]) << 3); - /* Fall through */ + fallthrough; case ONE_PT_CALIB2: base0 = (qfprom_cdata[0] & MSM8916_BASE0_MASK); p1[0] = (qfprom_cdata[0] & MSM8916_S0_P1_MASK) >> MSM8916_S0_P1_SHIFT; @@ -355,7 +355,7 @@ static int calibrate_8974(struct tsens_priv *priv) p2[8] = (calib[5] & S8_P2_BKP_MASK) >> S8_P2_BKP_SHIFT; p2[9] = (calib[5] & S9_P2_BKP_MASK) >> S9_P2_BKP_SHIFT; p2[10] = (calib[5] & S10_P2_BKP_MASK) >> S10_P2_BKP_SHIFT; - /* Fall through */ + fallthrough; case ONE_PT_CALIB: case ONE_PT_CALIB2: base1 = bkp[0] & BASE1_MASK; @@ -390,7 +390,7 @@ static int calibrate_8974(struct tsens_priv *priv) p2[8] = (calib[4] & S8_P2_MASK) >> S8_P2_SHIFT; p2[9] = (calib[4] & S9_P2_MASK) >> S9_P2_SHIFT; p2[10] = (calib[4] & S10_P2_MASK) >> S10_P2_SHIFT; - /* Fall through */ + fallthrough; case ONE_PT_CALIB: case ONE_PT_CALIB2: base1 = calib[0] & BASE1_MASK; @@ -420,7 +420,7 @@ static int calibrate_8974(struct tsens_priv *priv) p2[i] <<= 2; p2[i] |= BIT_APPEND; } - /* Fall through */ + fallthrough; case ONE_PT_CALIB2: for (i = 0; i < priv->num_sensors; i++) { p1[i] += base1; diff --git a/drivers/thermal/qcom/tsens-v1.c b/drivers/thermal/qcom/tsens-v1.c index b682a4df0081..3c19a3800c6d 100644 --- a/drivers/thermal/qcom/tsens-v1.c +++ b/drivers/thermal/qcom/tsens-v1.c @@ -202,7 +202,7 @@ static int calibrate_v1(struct tsens_priv *priv) p2[9] = (qfprom_cdata[3] & S9_P2_MASK) >> S9_P2_SHIFT; for (i = 0; i < priv->num_sensors; i++) p2[i] = ((base1 + p2[i]) << 2); - /* Fall through */ + fallthrough; case ONE_PT_CALIB2: base0 = (qfprom_cdata[4] & BASE0_MASK) >> BASE0_SHIFT; p1[0] = (qfprom_cdata[0] & S0_P1_MASK) >> S0_P1_SHIFT; @@ -263,7 +263,7 @@ static int calibrate_8976(struct tsens_priv *priv) for (i = 0; i < priv->num_sensors; i++) p2[i] = ((base1 + p2[i]) << 2); - /* Fall through */ + fallthrough; case ONE_PT_CALIB2: base0 = qfprom_cdata[0] & MSM8976_BASE0_MASK; p1[0] = (qfprom_cdata[0] & MSM8976_S0_P1_MASK) >> MSM8976_S0_P1_SHIFT; diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 72bf159bcecc..a6616e530a84 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1516,7 +1516,7 @@ EXPORT_SYMBOL_GPL(thermal_zone_device_register); */ void thermal_zone_device_unregister(struct thermal_zone_device *tz) { - int i; + int i, tz_id; const struct thermal_zone_params *tzp; struct thermal_cooling_device *cdev; struct thermal_zone_device *pos = NULL; @@ -1525,6 +1525,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz) return; tzp = tz->tzp; + tz_id = tz->id; mutex_lock(&thermal_list_lock); list_for_each_entry(pos, &thermal_tz_list, node) @@ -1567,7 +1568,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz) mutex_destroy(&tz->lock); device_unregister(&tz->device); - thermal_notify_tz_delete(tz->id); + thermal_notify_tz_delete(tz_id); } EXPORT_SYMBOL_GPL(thermal_zone_device_unregister); diff --git a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c index 63b02bfb2adf..fdb8a495ab69 100644 --- a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c +++ b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c @@ -37,20 +37,21 @@ static struct temp_sensor_data omap4430_mpu_temp_sensor_data = { /* * Temperature values in milli degree celsius - * ADC code values from 530 to 923 + * ADC code values from 13 to 107, see TRM + * "18.4.10.2.3 ADC Codes Versus Temperature". */ static const int omap4430_adc_to_temp[OMAP4430_ADC_END_VALUE - OMAP4430_ADC_START_VALUE + 1] = { - -38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000, -22000, - -20000, -18000, -17000, -15000, -13000, -12000, -10000, -8000, -6000, - -5000, -3000, -1000, 0, 2000, 3000, 5000, 6000, 8000, 10000, 12000, - 13000, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28000, 30000, - 32000, 33000, 35000, 37000, 38000, 40000, 42000, 43000, 45000, 47000, - 48000, 50000, 52000, 53000, 55000, 57000, 58000, 60000, 62000, 64000, - 66000, 68000, 70000, 71000, 73000, 75000, 77000, 78000, 80000, 82000, - 83000, 85000, 87000, 88000, 90000, 92000, 93000, 95000, 97000, 98000, - 100000, 102000, 103000, 105000, 107000, 109000, 111000, 113000, 115000, - 117000, 118000, 120000, 122000, 123000, + -40000, -38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000, + -22000, -20000, -18500, -17000, -15000, -13500, -12000, -10000, -8000, + -6500, -5000, -3500, -1500, 0, 2000, 3500, 5000, 6500, 8500, 10000, + 12000, 13500, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28500, + 30000, 32000, 33500, 35000, 37000, 38500, 40000, 42000, 43500, 45000, + 47000, 48500, 50000, 52000, 53500, 55000, 57000, 58500, 60000, 62000, + 64000, 66000, 68000, 70000, 71500, 73500, 75000, 77000, 78500, 80000, + 82000, 83500, 85000, 87000, 88500, 90000, 92000, 93500, 95000, 97000, + 98500, 100000, 102000, 103500, 105000, 107000, 109000, 111000, 113000, + 115000, 117000, 118500, 120000, 122000, 123500, 125000, }; /* OMAP4430 data */ diff --git a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h index a453ff8eb313..9a3955c3853b 100644 --- a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h +++ b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h @@ -53,9 +53,13 @@ * and thresholds for OMAP4430. */ -/* ADC conversion table limits */ -#define OMAP4430_ADC_START_VALUE 0 -#define OMAP4430_ADC_END_VALUE 127 +/* + * ADC conversion table limits. Ignore values outside the TRM listed + * range to avoid bogus thermal shutdowns. See omap4430 TRM chapter + * "18.4.10.2.3 ADC Codes Versus Temperature". + */ +#define OMAP4430_ADC_START_VALUE 13 +#define OMAP4430_ADC_END_VALUE 107 /* bandgap clock limits (no control on 4430) */ #define OMAP4430_MAX_FREQ 32768 #define OMAP4430_MIN_FREQ 32768 diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c index f77ceae5c7d7..394a23ce6ca4 100644 --- a/drivers/thunderbolt/ctl.c +++ b/drivers/thunderbolt/ctl.c @@ -453,7 +453,7 @@ static void tb_ctl_rx_callback(struct tb_ring *ring, struct ring_frame *frame, "RX: checksum mismatch, dropping packet\n"); goto rx; } - /* Fall through */ + fallthrough; case TB_CFG_PKG_ICM_EVENT: if (tb_ctl_handle_event(pkg->ctl, frame->eof, pkg, frame->size)) goto rx; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 712395f518b8..3845db569e4c 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -2092,7 +2092,7 @@ static int tb_switch_add_dma_port(struct tb_switch *sw) if (tb_route(sw)) return 0; - /* fallthrough */ + fallthrough; case 3: ret = tb_switch_set_uuid(sw); if (ret) diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 2aae2c76d880..1a7e849840b2 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -315,7 +315,7 @@ static inline u32 tb_dp_cap_set_rate(u32 val, u32 rate) switch (rate) { default: WARN(1, "invalid rate %u passed, defaulting to 1620 MB/s\n", rate); - /* Fallthrough */ + fallthrough; case 1620: val |= DP_COMMON_CAP_RATE_RBR << DP_COMMON_CAP_RATE_SHIFT; break; @@ -355,7 +355,7 @@ static inline u32 tb_dp_cap_set_lanes(u32 val, u32 lanes) default: WARN(1, "invalid number of lanes %u passed, defaulting to 1\n", lanes); - /* Fallthrough */ + fallthrough; case 1: val |= DP_COMMON_CAP_1_LANE << DP_COMMON_CAP_LANES_SHIFT; break; diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 2a0e51a20e34..92c9a476defc 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -492,7 +492,7 @@ static void xencons_backend_changed(struct xenbus_device *dev, case XenbusStateClosed: if (dev->state == XenbusStateClosed) break; - /* fall through - Missed the backend's CLOSING state. */ + fallthrough; /* Missed the backend's CLOSING state */ case XenbusStateClosing: xenbus_frontend_closed(dev); break; diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c index 21e76a2ec182..a8e19b4833bf 100644 --- a/drivers/tty/mips_ejtag_fdc.c +++ b/drivers/tty/mips_ejtag_fdc.c @@ -243,7 +243,7 @@ done: /* Fall back to a 3 byte encoding */ word.bytes = 3; word.word &= 0x00ffffff; - /* Fall through */ + fallthrough; case 3: /* 3 byte encoding */ word.word |= 0x82000000; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 0a29a94ec438..35cf12147e39 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -1584,7 +1584,7 @@ static void gsm_dlci_data(struct gsm_dlci *dlci, const u8 *data, int clen) gsm_process_modem(tty, dlci, modem, clen); tty_kref_put(tty); } - /* Fall through */ + fallthrough; case 1: /* Line state will go via DLCI 0 controls only */ default: tty_insert_flip_string(port, data, len); @@ -1986,7 +1986,7 @@ static void gsm1_receive(struct gsm_mux *gsm, unsigned char c) gsm->address = 0; gsm->state = GSM_ADDRESS; gsm->fcs = INIT_FCS; - /* Fall through */ + fallthrough; case GSM_ADDRESS: /* Address continuation */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); if (gsm_read_ea(&gsm->address, c)) diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index b09eac4b6d64..8e975cb29833 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -602,7 +602,7 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, case TCOFLUSH: flush_tx_queue(tty); } - /* fall through - to default */ + fallthrough; /* to default */ default: error = n_tty_ioctl_helper(tty, file, cmd, arg); diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c index f75696f0ee2d..934dd2fb2ec8 100644 --- a/drivers/tty/n_r3964.c +++ b/drivers/tty/n_r3964.c @@ -605,7 +605,6 @@ static void receive_char(struct r3964_info *pInfo, const unsigned char c) } break; case R3964_WAIT_FOR_RX_REPEAT: - /* FALLTHROUGH */ case R3964_IDLE: if (c == STX) { /* Prevent rx_queue from overflow: */ diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index db88dee3a399..f8e99995eee9 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -39,7 +39,7 @@ static void serial8250_em_serial_out(struct uart_port *p, int offset, int value) break; case UART_IER: /* IER @ 0x04 */ value &= 0x0f; /* only 4 valid bits - not Xscale */ - /* fall-through */ + fallthrough; case UART_DLL_EM: /* DLL @ 0x24 (+9) */ case UART_DLM_EM: /* DLM @ 0x28 (+9) */ writel(value, p->membase + (offset << 2)); diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 04b9af7ed941..2d0e7c7e408d 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -744,6 +744,24 @@ static const struct exar8250_board pbn_exar_XR17V35x = { .exit = pci_xr17v35x_exit, }; +static const struct exar8250_board pbn_fastcom35x_2 = { + .num_ports = 2, + .setup = pci_xr17v35x_setup, + .exit = pci_xr17v35x_exit, +}; + +static const struct exar8250_board pbn_fastcom35x_4 = { + .num_ports = 4, + .setup = pci_xr17v35x_setup, + .exit = pci_xr17v35x_exit, +}; + +static const struct exar8250_board pbn_fastcom35x_8 = { + .num_ports = 8, + .setup = pci_xr17v35x_setup, + .exit = pci_xr17v35x_exit, +}; + static const struct exar8250_board pbn_exar_XR17V4358 = { .num_ports = 12, .setup = pci_xr17v35x_setup, @@ -811,9 +829,9 @@ static const struct pci_device_id exar_pci_tbl[] = { EXAR_DEVICE(EXAR, XR17V358, pbn_exar_XR17V35x), EXAR_DEVICE(EXAR, XR17V4358, pbn_exar_XR17V4358), EXAR_DEVICE(EXAR, XR17V8358, pbn_exar_XR17V8358), - EXAR_DEVICE(COMMTECH, 4222PCIE, pbn_exar_XR17V35x), - EXAR_DEVICE(COMMTECH, 4224PCIE, pbn_exar_XR17V35x), - EXAR_DEVICE(COMMTECH, 4228PCIE, pbn_exar_XR17V35x), + EXAR_DEVICE(COMMTECH, 4222PCIE, pbn_fastcom35x_2), + EXAR_DEVICE(COMMTECH, 4224PCIE, pbn_fastcom35x_4), + EXAR_DEVICE(COMMTECH, 4228PCIE, pbn_fastcom35x_8), EXAR_DEVICE(COMMTECH, 4222PCI335, pbn_fastcom335_2), EXAR_DEVICE(COMMTECH, 4224PCI335, pbn_fastcom335_4), diff --git a/drivers/tty/serial/8250/8250_fintek.c b/drivers/tty/serial/8250/8250_fintek.c index d1d253c4b518..31c9e83ea3cb 100644 --- a/drivers/tty/serial/8250/8250_fintek.c +++ b/drivers/tty/serial/8250/8250_fintek.c @@ -255,7 +255,7 @@ static void fintek_8250_set_irq_mode(struct fintek_8250 *pdata, bool is_level) case CHIP_ID_F81866: sio_write_mask_reg(pdata, F81866_FIFO_CTRL, F81866_IRQ_MODE1, 0); - /* fall through */ + fallthrough; case CHIP_ID_F81865: sio_write_mask_reg(pdata, F81866_IRQ_MODE, F81866_IRQ_SHARE, F81866_IRQ_SHARE); diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 1a74d511b02a..3eb2d485eaeb 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -631,7 +631,7 @@ pci_timedia_setup(struct serial_private *priv, break; case 3: offset = board->uart_offset; - /* FALLTHROUGH */ + fallthrough; case 4: /* BAR 2 */ case 5: /* BAR 3 */ case 6: /* BAR 4 */ diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 09475695effd..c71d647eb87a 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1872,7 +1872,7 @@ static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir) switch (iir & 0x3f) { case UART_IIR_RX_TIMEOUT: serial8250_rx_dma_flush(up); - /* fall-through */ + fallthrough; case UART_IIR_RLSI: return true; } @@ -2275,6 +2275,10 @@ int serial8250_do_startup(struct uart_port *port) if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) { unsigned char iir1; + + if (port->irqflags & IRQF_SHARED) + disable_irq_nosync(port->irq); + /* * Test for UARTs that do not reassert THRE when the * transmitter is idle and the interrupt has already @@ -2284,8 +2288,6 @@ int serial8250_do_startup(struct uart_port *port) * allow register changes to become visible. */ spin_lock_irqsave(&port->lock, flags); - if (up->port.irqflags & IRQF_SHARED) - disable_irq_nosync(port->irq); wait_for_xmitr(up, UART_LSR_THRE); serial_port_out_sync(port, UART_IER, UART_IER_THRI); @@ -2297,9 +2299,10 @@ int serial8250_do_startup(struct uart_port *port) iir = serial_port_in(port, UART_IIR); serial_port_out(port, UART_IER, 0); + spin_unlock_irqrestore(&port->lock, flags); + if (port->irqflags & IRQF_SHARED) enable_irq(port->irq); - spin_unlock_irqrestore(&port->lock, flags); /* * If the interrupt is not reasserted, or we otherwise diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c index e0b73a5402db..a2978abab0db 100644 --- a/drivers/tty/serial/8250/8250_uniphier.c +++ b/drivers/tty/serial/8250/8250_uniphier.c @@ -75,7 +75,7 @@ static unsigned int uniphier_serial_in(struct uart_port *p, int offset) break; case UART_LCR: valshift = 8; - /* fall through */ + fallthrough; case UART_MCR: offset = UNIPHIER_UART_LCR_MCR; break; @@ -101,7 +101,7 @@ static void uniphier_serial_out(struct uart_port *p, int offset, int value) case UART_SCR: /* No SCR for this hardware. Use CHAR as a scratch register */ valshift = 8; - /* fall through */ + fallthrough; case UART_FCR: offset = UNIPHIER_UART_CHAR_FCR; break; @@ -109,7 +109,7 @@ static void uniphier_serial_out(struct uart_port *p, int offset, int value) valshift = 8; /* Divisor latch access bit does not exist. */ value &= ~UART_LCR_DLAB; - /* fall through */ + fallthrough; case UART_MCR: offset = UNIPHIER_UART_LCR_MCR; break; diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 8a0352eb337c..9409be982aa6 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -517,6 +517,7 @@ config SERIAL_IMX_CONSOLE config SERIAL_IMX_EARLYCON bool "Earlycon on IMX serial port" + depends on ARCH_MXC || COMPILE_TEST depends on OF select SERIAL_EARLYCON help diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index d056ee6cca33..caf167f0c10a 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -43,6 +43,7 @@ obj-$(CONFIG_SERIAL_ZS) += zs.o obj-$(CONFIG_SERIAL_SH_SCI) += sh-sci.o obj-$(CONFIG_SERIAL_CPM) += cpm_uart/ obj-$(CONFIG_SERIAL_IMX) += imx.o +obj-$(CONFIG_SERIAL_IMX_EARLYCON) += imx_earlycon.o obj-$(CONFIG_SERIAL_MPC52xx) += mpc52xx_uart.o obj-$(CONFIG_SERIAL_ICOM) += icom.o obj-$(CONFIG_SERIAL_MESON) += meson_uart.o diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index c010f639298d..67498594d7d7 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2241,9 +2241,8 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) clk_disable(uap->clk); } -static void __init -pl011_console_get_options(struct uart_amba_port *uap, int *baud, - int *parity, int *bits) +static void pl011_console_get_options(struct uart_amba_port *uap, int *baud, + int *parity, int *bits) { if (pl011_read(uap, REG_CR) & UART01x_CR_UARTEN) { unsigned int lcr_h, ibrd, fbrd; @@ -2276,7 +2275,7 @@ pl011_console_get_options(struct uart_amba_port *uap, int *baud, } } -static int __init pl011_console_setup(struct console *co, char *options) +static int pl011_console_setup(struct console *co, char *options) { struct uart_amba_port *uap; int baud = 38400; @@ -2344,8 +2343,8 @@ static int __init pl011_console_setup(struct console *co, char *options) * * Returns 0 if console matches; otherwise non-zero to use default matching */ -static int __init pl011_console_match(struct console *co, char *name, int idx, - char *options) +static int pl011_console_match(struct console *co, char *name, int idx, + char *options) { unsigned char iotype; resource_size_t addr; @@ -2615,7 +2614,7 @@ static int pl011_setup_port(struct device *dev, struct uart_amba_port *uap, static int pl011_register_port(struct uart_amba_port *uap) { - int ret; + int ret, i; /* Ensure interrupts from this UART are masked and cleared */ pl011_write(0, uap, REG_IMSC); @@ -2626,6 +2625,9 @@ static int pl011_register_port(struct uart_amba_port *uap) if (ret < 0) { dev_err(uap->port.dev, "Failed to register AMBA-PL011 driver\n"); + for (i = 0; i < ARRAY_SIZE(amba_ports); i++) + if (amba_ports[i] == uap) + amba_ports[i] = NULL; return ret; } } diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index e43471b33710..bb5fc8bdd57a 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -1845,7 +1845,7 @@ static void atmel_get_ip_name(struct uart_port *port) version = atmel_uart_readl(port, ATMEL_US_VERSION); switch (version) { case 0x814: /* sama5d2 */ - /* fall through */ + fallthrough; case 0x701: /* sama5d4 */ atmel_port->fidi_min = 3; atmel_port->fidi_max = 65535; diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 8573fc9cb0cd..76b94d0ff586 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -587,7 +587,6 @@ static irqreturn_t serial_omap_irq(int irq, void *dev_id) transmit_chars(up, lsr); break; case UART_IIR_RX_TIMEOUT: - /* FALLTHROUGH */ case UART_IIR_RDI: serial_omap_rdi(up, lsr); break; @@ -598,7 +597,6 @@ static irqreturn_t serial_omap_irq(int irq, void *dev_id) /* simply try again */ break; case UART_IIR_XOFF: - /* FALLTHROUGH */ default: break; } diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 3aa29d201f54..184b458820a3 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -361,11 +361,16 @@ static int qcom_geni_serial_get_char(struct uart_port *uport) return NO_POLL_CHAR; if (word_cnt == 1 && (status & RX_LAST)) + /* + * NOTE: If RX_LAST_BYTE_VALID is 0 it needs to be + * treated as if it was BYTES_PER_FIFO_WORD. + */ private_data->poll_cached_bytes_cnt = (status & RX_LAST_BYTE_VALID_MSK) >> RX_LAST_BYTE_VALID_SHFT; - else - private_data->poll_cached_bytes_cnt = 4; + + if (private_data->poll_cached_bytes_cnt == 0) + private_data->poll_cached_bytes_cnt = BYTES_PER_FIFO_WORD; private_data->poll_cached_bytes = readl(uport->membase + SE_GENI_RX_FIFOn); @@ -1098,7 +1103,7 @@ static unsigned int qcom_geni_serial_tx_empty(struct uart_port *uport) } #ifdef CONFIG_SERIAL_QCOM_GENI_CONSOLE -static int __init qcom_geni_console_setup(struct console *co, char *options) +static int qcom_geni_console_setup(struct console *co, char *options) { struct uart_port *uport; struct qcom_geni_serial_port *port; diff --git a/drivers/tty/serial/rda-uart.c b/drivers/tty/serial/rda-uart.c index b5ef86ae2746..85366e059258 100644 --- a/drivers/tty/serial/rda-uart.c +++ b/drivers/tty/serial/rda-uart.c @@ -259,7 +259,7 @@ static void rda_uart_set_termios(struct uart_port *port, case CS5: case CS6: dev_warn(port->dev, "bit size not supported, using 7 bits\n"); - /* Fall through */ + fallthrough; case CS7: ctrl &= ~RDA_UART_DBITS_8; break; diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index 8ed3482d2e1e..8ae3e03fbd8c 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -1905,9 +1905,11 @@ static int s3c24xx_serial_init_port(struct s3c24xx_uart_port *ourport, ourport->tx_irq = ret + 1; } - ret = platform_get_irq(platdev, 1); - if (ret > 0) - ourport->tx_irq = ret; + if (!s3c24xx_serial_has_interrupt_mask(port)) { + ret = platform_get_irq(platdev, 1); + if (ret > 0) + ourport->tx_irq = ret; + } /* * DMA is currently supported only on DT platforms, if DMA properties * are specified. diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index b87914ae6da8..bd13014a1c53 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -876,7 +876,7 @@ static irqreturn_t tegra_uart_isr(int irq, void *data) tegra_uart_write(tup, ier, UART_IER); break; } - /* Fall through */ + fallthrough; case 2: /* Receive */ if (!tup->use_rx_pio) { is_rx_start = tup->rx_in_progress; diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 3403dd790517..f797c971cd82 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2101,7 +2101,7 @@ uart_set_options(struct uart_port *port, struct console *co, switch (parity) { case 'o': case 'O': termios.c_cflag |= PARODD; - /*fall through*/ + fallthrough; case 'e': case 'E': termios.c_cflag |= PARENB; break; diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 143300a80090..ba503dd04ce2 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -970,7 +970,7 @@ static int stm32_init_port(struct stm32_port *stm32port, return ret; if (stm32port->info->cfg.has_wakeup) { - stm32port->wakeirq = platform_get_irq(pdev, 1); + stm32port->wakeirq = platform_get_irq_optional(pdev, 1); if (stm32port->wakeirq <= 0 && stm32port->wakeirq != -ENXIO) return stm32port->wakeirq ? : -ENODEV; } diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c index 8ce9a7a256e5..319e5ceb6130 100644 --- a/drivers/tty/serial/sunsu.c +++ b/drivers/tty/serial/sunsu.c @@ -514,7 +514,7 @@ static void receive_kbd_ms_chars(struct uart_sunsu_port *up, int is_break) switch (ret) { case 2: sunsu_change_mouse_baud(up); - /* fallthru */ + fallthrough; case 1: break; diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c index 7ea06bbc6197..001e19d7c17d 100644 --- a/drivers/tty/serial/sunzilog.c +++ b/drivers/tty/serial/sunzilog.c @@ -306,7 +306,7 @@ static void sunzilog_kbdms_receive_chars(struct uart_sunzilog_port *up, switch (ret) { case 2: sunzilog_change_mouse_baud(up); - /* fallthru */ + fallthrough; case 1: break; diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index 2833f1418d6d..a9b1ee27183a 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -544,7 +544,7 @@ static int cdns_uart_clk_notifier_cb(struct notifier_block *nb, cdns_uart->baud = cdns_uart_set_baud_rate(cdns_uart->port, cdns_uart->baud); - /* fall through */ + fallthrough; case ABORT_RATE_CHANGE: if (!locked) spin_lock_irqsave(&cdns_uart->port->lock, flags); diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 9245fffdbceb..e18f318586ab 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -866,7 +866,7 @@ static int __tty_perform_flush(struct tty_struct *tty, unsigned long arg) ld->ops->flush_buffer(tty); tty_unthrottle(tty); } - /* fall through */ + fallthrough; case TCOFLUSH: tty_driver_flush_buffer(tty); break; diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index ccb533fd00a2..19cd4a4b1939 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1201,7 +1201,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, unsigned int old_rows, old_row_size, first_copied_row; unsigned int new_cols, new_rows, new_row_size, new_screen_size; unsigned int user; - unsigned short *newscreen; + unsigned short *oldscreen, *newscreen; struct uni_screen *new_uniscr = NULL; WARN_CONSOLE_UNLOCKED(); @@ -1299,10 +1299,11 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, if (new_scr_end > new_origin) scr_memsetw((void *)new_origin, vc->vc_video_erase_char, new_scr_end - new_origin); - kfree(vc->vc_screenbuf); + oldscreen = vc->vc_screenbuf; vc->vc_screenbuf = newscreen; vc->vc_screenbuf_size = new_screen_size; set_origin(vc); + kfree(oldscreen); /* do part of a reset_terminal() */ vc->vc_top = 0; @@ -1553,7 +1554,7 @@ static void csi_J(struct vc_data *vc, int vpar) break; case 3: /* include scrollback */ flush_scrollback(vc); - /* fallthrough */ + fallthrough; case 2: /* erase whole display */ vc_uniscr_clear_lines(vc, 0, vc->vc_rows); count = vc->vc_cols * vc->vc_rows; @@ -2167,7 +2168,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) lf(vc); if (!is_kbd(vc, lnm)) return; - /* fall through */ + fallthrough; case 13: cr(vc); return; @@ -2306,7 +2307,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) return; } vc->vc_priv = EPecma; - /* fall through */ + fallthrough; case ESgetpars: if (c == ';' && vc->vc_npar < NPAR - 1) { vc->vc_npar++; diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 91c301775047..a4e520bdd521 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -806,12 +806,22 @@ static int vt_resizex(struct vc_data *vc, struct vt_consize __user *cs) console_lock(); vcp = vc_cons[i].d; if (vcp) { + int ret; + int save_scan_lines = vcp->vc_scan_lines; + int save_font_height = vcp->vc_font.height; + if (v.v_vlin) vcp->vc_scan_lines = v.v_vlin; if (v.v_clin) vcp->vc_font.height = v.v_clin; vcp->vc_resize_user = 1; - vc_resize(vcp, v.v_cols, v.v_rows); + ret = vc_resize(vcp, v.v_cols, v.v_rows); + if (ret) { + vcp->vc_scan_lines = save_scan_lines; + vcp->vc_font.height = save_font_height; + console_unlock(); + return ret; + } } console_unlock(); } diff --git a/drivers/usb/c67x00/c67x00-sched.c b/drivers/usb/c67x00/c67x00-sched.c index f7f6229082ca..60f4711717d2 100644 --- a/drivers/usb/c67x00/c67x00-sched.c +++ b/drivers/usb/c67x00/c67x00-sched.c @@ -710,7 +710,8 @@ static int c67x00_add_ctrl_urb(struct c67x00_hcd *c67x00, struct urb *urb) if (ret) return ret; break; - } /* else fallthrough */ + } + fallthrough; case STATUS_STAGE: pid = !usb_pipeout(urb->pipe) ? USB_PID_OUT : USB_PID_IN; ret = c67x00_create_td(c67x00, urb, NULL, 0, pid, 1, diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 991786876dbb..7f6f3ab5b8a6 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -378,21 +378,19 @@ static void acm_ctrl_irq(struct urb *urb) if (current_size < expected_size) { /* notification is transmitted fragmented, reassemble */ if (acm->nb_size < expected_size) { - if (acm->nb_size) { - kfree(acm->notification_buffer); - acm->nb_size = 0; - } + u8 *new_buffer; alloc_size = roundup_pow_of_two(expected_size); - /* - * kmalloc ensures a valid notification_buffer after a - * use of kfree in case the previous allocation was too - * small. Final freeing is done on disconnect. - */ - acm->notification_buffer = - kmalloc(alloc_size, GFP_ATOMIC); - if (!acm->notification_buffer) + /* Final freeing is done on disconnect. */ + new_buffer = krealloc(acm->notification_buffer, + alloc_size, GFP_ATOMIC); + if (!new_buffer) { + acm->nb_index = 0; goto exit; + } + + acm->notification_buffer = new_buffer; acm->nb_size = alloc_size; + dr = (struct usb_cdc_notification *)acm->notification_buffer; } copy_size = min(current_size, diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index f81606c6a35b..7e73e989645b 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -905,6 +905,35 @@ static int usb_uevent(struct device *dev, struct kobj_uevent_env *env) return 0; } +static bool is_dev_usb_generic_driver(struct device *dev) +{ + struct usb_device_driver *udd = dev->driver ? + to_usb_device_driver(dev->driver) : NULL; + + return udd == &usb_generic_driver; +} + +static int __usb_bus_reprobe_drivers(struct device *dev, void *data) +{ + struct usb_device_driver *new_udriver = data; + struct usb_device *udev; + int ret; + + if (!is_dev_usb_generic_driver(dev)) + return 0; + + udev = to_usb_device(dev); + if (usb_device_match_id(udev, new_udriver->id_table) == NULL && + (!new_udriver->match || new_udriver->match(udev) != 0)) + return 0; + + ret = device_reprobe(dev); + if (ret && ret != -EPROBE_DEFER) + dev_err(dev, "Failed to reprobe device (error %d)\n", ret); + + return 0; +} + /** * usb_register_device_driver - register a USB device (not interface) driver * @new_udriver: USB operations for the device driver @@ -934,13 +963,20 @@ int usb_register_device_driver(struct usb_device_driver *new_udriver, retval = driver_register(&new_udriver->drvwrap.driver); - if (!retval) + if (!retval) { pr_info("%s: registered new device driver %s\n", usbcore_name, new_udriver->name); - else + /* + * Check whether any device could be better served with + * this new driver + */ + bus_for_each_dev(&usb_bus_type, NULL, new_udriver, + __usb_bus_reprobe_drivers); + } else { printk(KERN_ERR "%s: error %d registering device " " driver %s\n", usbcore_name, retval, new_udriver->name); + } return retval; } diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c index b6f2d4b44754..2b2f1ab6e36a 100644 --- a/drivers/usb/core/generic.c +++ b/drivers/usb/core/generic.c @@ -205,8 +205,9 @@ static int __check_usb_generic(struct device_driver *drv, void *data) udrv = to_usb_device_driver(drv); if (udrv == &usb_generic_driver) return 0; - - return usb_device_match_id(udev, udrv->id_table) != NULL; + if (usb_device_match_id(udev, udrv->id_table) != NULL) + return 1; + return (udrv->match && udrv->match(udev)); } static bool usb_generic_driver_match(struct usb_device *udev) diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index 4dc443aaef5c..ec0d6c50610c 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -315,11 +315,14 @@ EXPORT_SYMBOL_GPL(usb_hcd_pci_probe); void usb_hcd_pci_remove(struct pci_dev *dev) { struct usb_hcd *hcd; + int hcd_driver_flags; hcd = pci_get_drvdata(dev); if (!hcd) return; + hcd_driver_flags = hcd->driver->flags; + if (pci_dev_run_wake(dev)) pm_runtime_get_noresume(&dev->dev); @@ -347,7 +350,7 @@ void usb_hcd_pci_remove(struct pci_dev *dev) up_read(&companions_rwsem); } usb_put_hcd(hcd); - if ((hcd->driver->flags & HCD_MASK) < HCD_USB3) + if ((hcd_driver_flags & HCD_MASK) < HCD_USB3) pci_free_irq_vectors(dev); pci_disable_device(dev); } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 052d5accfe9b..5b768b80d1ee 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -727,7 +727,7 @@ static void hub_irq(struct urb *urb) if ((++hub->nerrors < 10) || hub->error) goto resubmit; hub->error = status; - /* FALL THROUGH */ + fallthrough; /* let hub_wq handle things */ case 0: /* we got data: port status changed */ diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 7c1198f80c23..f232914de5fd 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -370,6 +370,10 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0926, 0x0202), .driver_info = USB_QUIRK_ENDPOINT_IGNORE }, + /* Sound Devices MixPre-D */ + { USB_DEVICE(0x0926, 0x0208), .driver_info = + USB_QUIRK_ENDPOINT_IGNORE }, + /* Keytouch QWERTY Panel keyboard */ { USB_DEVICE(0x0926, 0x3333), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -465,6 +469,8 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x2386, 0x3119), .driver_info = USB_QUIRK_NO_LPM }, + { USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM }, + /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, @@ -509,6 +515,7 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = { */ static const struct usb_device_id usb_endpoint_ignore[] = { { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 }, + { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0208, 1), .driver_info = 0x85 }, { } }; diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 422aea24afcd..2eb34c8b4065 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -646,9 +646,8 @@ static int dwc3_phy_setup(struct dwc3 *dwc) if (!(reg & DWC3_GUSB2PHYCFG_ULPI_UTMI)) break; } - /* FALLTHROUGH */ + fallthrough; case DWC3_GHWPARAMS3_HSPHY_IFC_ULPI: - /* FALLTHROUGH */ default: break; } @@ -1411,7 +1410,7 @@ static void dwc3_check_params(struct dwc3 *dwc) default: dev_err(dev, "invalid maximum_speed parameter %d\n", dwc->maximum_speed); - /* fall through */ + fallthrough; case USB_SPEED_UNKNOWN: /* default to superspeed */ dwc->maximum_speed = USB_SPEED_SUPER; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index e44bfc3b5096..c2a0f64f8d1e 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1054,27 +1054,25 @@ static void __dwc3_prepare_one_trb(struct dwc3_ep *dep, struct dwc3_trb *trb, * dwc3_prepare_one_trb - setup one TRB from one request * @dep: endpoint for which this request is prepared * @req: dwc3_request pointer + * @trb_length: buffer size of the TRB * @chain: should this TRB be chained to the next? * @node: only for isochronous endpoints. First TRB needs different type. */ static void dwc3_prepare_one_trb(struct dwc3_ep *dep, - struct dwc3_request *req, unsigned chain, unsigned node) + struct dwc3_request *req, unsigned int trb_length, + unsigned chain, unsigned node) { struct dwc3_trb *trb; - unsigned int length; dma_addr_t dma; unsigned stream_id = req->request.stream_id; unsigned short_not_ok = req->request.short_not_ok; unsigned no_interrupt = req->request.no_interrupt; unsigned is_last = req->request.is_last; - if (req->request.num_sgs > 0) { - length = sg_dma_len(req->start_sg); + if (req->request.num_sgs > 0) dma = sg_dma_address(req->start_sg); - } else { - length = req->request.length; + else dma = req->request.dma; - } trb = &dep->trb_pool[dep->trb_enqueue]; @@ -1086,7 +1084,7 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep, req->num_trbs++; - __dwc3_prepare_one_trb(dep, trb, dma, length, chain, node, + __dwc3_prepare_one_trb(dep, trb, dma, trb_length, chain, node, stream_id, short_not_ok, no_interrupt, is_last); } @@ -1096,16 +1094,27 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep, struct scatterlist *sg = req->start_sg; struct scatterlist *s; int i; - + unsigned int length = req->request.length; unsigned int remaining = req->request.num_mapped_sgs - req->num_queued_sgs; + /* + * If we resume preparing the request, then get the remaining length of + * the request and resume where we left off. + */ + for_each_sg(req->request.sg, s, req->num_queued_sgs, i) + length -= sg_dma_len(s); + for_each_sg(sg, s, remaining, i) { - unsigned int length = req->request.length; unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc); unsigned int rem = length % maxp; + unsigned int trb_length; unsigned chain = true; + trb_length = min_t(unsigned int, length, sg_dma_len(s)); + + length -= trb_length; + /* * IOMMU driver is coalescing the list of sgs which shares a * page boundary into one and giving it to USB driver. With @@ -1113,7 +1122,7 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep, * sgs passed. So mark the chain bit to false if it isthe last * mapped sg. */ - if (i == remaining - 1) + if ((i == remaining - 1) || !length) chain = false; if (rem && usb_endpoint_dir_out(dep->endpoint.desc) && !chain) { @@ -1123,7 +1132,7 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep, req->needs_extra_trb = true; /* prepare normal TRB */ - dwc3_prepare_one_trb(dep, req, true, i); + dwc3_prepare_one_trb(dep, req, trb_length, true, i); /* Now prepare one extra TRB to align transfer size */ trb = &dep->trb_pool[dep->trb_enqueue]; @@ -1134,8 +1143,39 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep, req->request.short_not_ok, req->request.no_interrupt, req->request.is_last); + } else if (req->request.zero && req->request.length && + !usb_endpoint_xfer_isoc(dep->endpoint.desc) && + !rem && !chain) { + struct dwc3 *dwc = dep->dwc; + struct dwc3_trb *trb; + + req->needs_extra_trb = true; + + /* Prepare normal TRB */ + dwc3_prepare_one_trb(dep, req, trb_length, true, i); + + /* Prepare one extra TRB to handle ZLP */ + trb = &dep->trb_pool[dep->trb_enqueue]; + req->num_trbs++; + __dwc3_prepare_one_trb(dep, trb, dwc->bounce_addr, 0, + !req->direction, 1, + req->request.stream_id, + req->request.short_not_ok, + req->request.no_interrupt, + req->request.is_last); + + /* Prepare one more TRB to handle MPS alignment */ + if (!req->direction) { + trb = &dep->trb_pool[dep->trb_enqueue]; + req->num_trbs++; + __dwc3_prepare_one_trb(dep, trb, dwc->bounce_addr, maxp, + false, 1, req->request.stream_id, + req->request.short_not_ok, + req->request.no_interrupt, + req->request.is_last); + } } else { - dwc3_prepare_one_trb(dep, req, chain, i); + dwc3_prepare_one_trb(dep, req, trb_length, chain, i); } /* @@ -1150,6 +1190,16 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep, req->num_queued_sgs++; + /* + * The number of pending SG entries may not correspond to the + * number of mapped SG entries. If all the data are queued, then + * don't include unused SG entries. + */ + if (length == 0) { + req->num_pending_sgs -= req->request.num_mapped_sgs - req->num_queued_sgs; + break; + } + if (!dwc3_calc_trbs_left(dep)) break; } @@ -1169,7 +1219,7 @@ static void dwc3_prepare_one_trb_linear(struct dwc3_ep *dep, req->needs_extra_trb = true; /* prepare normal TRB */ - dwc3_prepare_one_trb(dep, req, true, 0); + dwc3_prepare_one_trb(dep, req, length, true, 0); /* Now prepare one extra TRB to align transfer size */ trb = &dep->trb_pool[dep->trb_enqueue]; @@ -1180,6 +1230,7 @@ static void dwc3_prepare_one_trb_linear(struct dwc3_ep *dep, req->request.no_interrupt, req->request.is_last); } else if (req->request.zero && req->request.length && + !usb_endpoint_xfer_isoc(dep->endpoint.desc) && (IS_ALIGNED(req->request.length, maxp))) { struct dwc3 *dwc = dep->dwc; struct dwc3_trb *trb; @@ -1187,18 +1238,29 @@ static void dwc3_prepare_one_trb_linear(struct dwc3_ep *dep, req->needs_extra_trb = true; /* prepare normal TRB */ - dwc3_prepare_one_trb(dep, req, true, 0); + dwc3_prepare_one_trb(dep, req, length, true, 0); - /* Now prepare one extra TRB to handle ZLP */ + /* Prepare one extra TRB to handle ZLP */ trb = &dep->trb_pool[dep->trb_enqueue]; req->num_trbs++; __dwc3_prepare_one_trb(dep, trb, dwc->bounce_addr, 0, - false, 1, req->request.stream_id, + !req->direction, 1, req->request.stream_id, req->request.short_not_ok, req->request.no_interrupt, req->request.is_last); + + /* Prepare one more TRB to handle MPS alignment for OUT */ + if (!req->direction) { + trb = &dep->trb_pool[dep->trb_enqueue]; + req->num_trbs++; + __dwc3_prepare_one_trb(dep, trb, dwc->bounce_addr, maxp, + false, 1, req->request.stream_id, + req->request.short_not_ok, + req->request.no_interrupt, + req->request.is_last); + } } else { - dwc3_prepare_one_trb(dep, req, false, 0); + dwc3_prepare_one_trb(dep, req, length, false, 0); } } @@ -2671,8 +2733,17 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, status); if (req->needs_extra_trb) { + unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc); + ret = dwc3_gadget_ep_reclaim_trb_linear(dep, req, event, status); + + /* Reclaim MPS padding TRB for ZLP */ + if (!req->direction && req->request.zero && req->request.length && + !usb_endpoint_xfer_isoc(dep->endpoint.desc) && + (IS_ALIGNED(req->request.length, maxp))) + ret = dwc3_gadget_ep_reclaim_trb_linear(dep, req, event, status); + req->needs_extra_trb = false; } diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 331c951d72dc..950c9435beec 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -2039,7 +2039,6 @@ static int do_scsi_command(struct fsg_common *common) case RELEASE: case RESERVE: case SEND_DIAGNOSTIC: - fallthrough; default: unknown_cmnd: diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 1d900081b1f0..b4206b0dede5 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1181,12 +1181,15 @@ static int ncm_unwrap_ntb(struct gether *port, int ndp_index; unsigned dg_len, dg_len2; unsigned ndp_len; + unsigned block_len; struct sk_buff *skb2; int ret = -EINVAL; - unsigned max_size = le32_to_cpu(ntb_parameters.dwNtbOutMaxSize); + unsigned ntb_max = le32_to_cpu(ntb_parameters.dwNtbOutMaxSize); + unsigned frame_max = le16_to_cpu(ecm_desc.wMaxSegmentSize); const struct ndp_parser_opts *opts = ncm->parser_opts; unsigned crc_len = ncm->is_crc ? sizeof(uint32_t) : 0; int dgram_counter; + bool ndp_after_header; /* dwSignature */ if (get_unaligned_le32(tmp) != opts->nth_sign) { @@ -1205,25 +1208,37 @@ static int ncm_unwrap_ntb(struct gether *port, } tmp++; /* skip wSequence */ + block_len = get_ncm(&tmp, opts->block_length); /* (d)wBlockLength */ - if (get_ncm(&tmp, opts->block_length) > max_size) { + if (block_len > ntb_max) { INFO(port->func.config->cdev, "OUT size exceeded\n"); goto err; } ndp_index = get_ncm(&tmp, opts->ndp_index); + ndp_after_header = false; /* Run through all the NDP's in the NTB */ do { - /* NCM 3.2 */ - if (((ndp_index % 4) != 0) && - (ndp_index < opts->nth_size)) { + /* + * NCM 3.2 + * dwNdpIndex + */ + if (((ndp_index % 4) != 0) || + (ndp_index < opts->nth_size) || + (ndp_index > (block_len - + opts->ndp_size))) { INFO(port->func.config->cdev, "Bad index: %#X\n", ndp_index); goto err; } + if (ndp_index == opts->nth_size) + ndp_after_header = true; - /* walk through NDP */ + /* + * walk through NDP + * dwSignature + */ tmp = (void *)(skb->data + ndp_index); if (get_unaligned_le32(tmp) != ncm->ndp_sign) { INFO(port->func.config->cdev, "Wrong NDP SIGN\n"); @@ -1234,14 +1249,15 @@ static int ncm_unwrap_ntb(struct gether *port, ndp_len = get_unaligned_le16(tmp++); /* * NCM 3.3.1 + * wLength * entry is 2 items * item size is 16/32 bits, opts->dgram_item_len * 2 bytes * minimal: struct usb_cdc_ncm_ndpX + normal entry + zero entry * Each entry is a dgram index and a dgram length. */ if ((ndp_len < opts->ndp_size - + 2 * 2 * (opts->dgram_item_len * 2)) - || (ndp_len % opts->ndplen_align != 0)) { + + 2 * 2 * (opts->dgram_item_len * 2)) || + (ndp_len % opts->ndplen_align != 0)) { INFO(port->func.config->cdev, "Bad NDP length: %#X\n", ndp_len); goto err; @@ -1258,8 +1274,21 @@ static int ncm_unwrap_ntb(struct gether *port, do { index = index2; + /* wDatagramIndex[0] */ + if ((index < opts->nth_size) || + (index > block_len - opts->dpe_size)) { + INFO(port->func.config->cdev, + "Bad index: %#X\n", index); + goto err; + } + dg_len = dg_len2; - if (dg_len < 14 + crc_len) { /* ethernet hdr + crc */ + /* + * wDatagramLength[0] + * ethernet hdr + crc or larger than max frame size + */ + if ((dg_len < 14 + crc_len) || + (dg_len > frame_max)) { INFO(port->func.config->cdev, "Bad dgram length: %#X\n", dg_len); goto err; @@ -1283,6 +1312,37 @@ static int ncm_unwrap_ntb(struct gether *port, index2 = get_ncm(&tmp, opts->dgram_item_len); dg_len2 = get_ncm(&tmp, opts->dgram_item_len); + if (index2 == 0 || dg_len2 == 0) + break; + + /* wDatagramIndex[1] */ + if (ndp_after_header) { + if (index2 < opts->nth_size + opts->ndp_size) { + INFO(port->func.config->cdev, + "Bad index: %#X\n", index2); + goto err; + } + } else { + if (index2 < opts->nth_size + opts->dpe_size) { + INFO(port->func.config->cdev, + "Bad index: %#X\n", index2); + goto err; + } + } + if (index2 > block_len - opts->dpe_size) { + INFO(port->func.config->cdev, + "Bad index: %#X\n", index2); + goto err; + } + + /* wDatagramLength[1] */ + if ((dg_len2 < 14 + crc_len) || + (dg_len2 > frame_max)) { + INFO(port->func.config->cdev, + "Bad dgram length: %#X\n", dg_len); + goto err; + } + /* * Copy the data into a new skb. * This ensures the truesize is correct @@ -1299,9 +1359,6 @@ static int ncm_unwrap_ntb(struct gether *port, ndp_len -= 2 * (opts->dgram_item_len * 2); dgram_counter++; - - if (index2 == 0 || dg_len2 == 0) - break; } while (ndp_len > 2 * (opts->dgram_item_len * 2)); } while (ndp_index); diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index d94b814328c8..184165e27908 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -753,12 +753,13 @@ static int uasp_alloc_stream_res(struct f_uas *fu, struct uas_stream *stream) goto err_sts; return 0; + err_sts: - usb_ep_free_request(fu->ep_status, stream->req_status); - stream->req_status = NULL; -err_out: usb_ep_free_request(fu->ep_out, stream->req_out); stream->req_out = NULL; +err_out: + usb_ep_free_request(fu->ep_in, stream->req_in); + stream->req_in = NULL; out: return -ENOMEM; } diff --git a/drivers/usb/gadget/u_f.h b/drivers/usb/gadget/u_f.h index eaa13fd3dc7f..e313c3b8dcb1 100644 --- a/drivers/usb/gadget/u_f.h +++ b/drivers/usb/gadget/u_f.h @@ -14,6 +14,7 @@ #define __U_F_H__ #include <linux/usb/gadget.h> +#include <linux/overflow.h> /* Variable Length Array Macros **********************************************/ #define vla_group(groupname) size_t groupname##__next = 0 @@ -21,21 +22,36 @@ #define vla_item(groupname, type, name, n) \ size_t groupname##_##name##__offset = ({ \ - size_t align_mask = __alignof__(type) - 1; \ - size_t offset = (groupname##__next + align_mask) & ~align_mask;\ - size_t size = (n) * sizeof(type); \ - groupname##__next = offset + size; \ + size_t offset = 0; \ + if (groupname##__next != SIZE_MAX) { \ + size_t align_mask = __alignof__(type) - 1; \ + size_t size = array_size(n, sizeof(type)); \ + offset = (groupname##__next + align_mask) & \ + ~align_mask; \ + if (check_add_overflow(offset, size, \ + &groupname##__next)) { \ + groupname##__next = SIZE_MAX; \ + offset = 0; \ + } \ + } \ offset; \ }) #define vla_item_with_sz(groupname, type, name, n) \ - size_t groupname##_##name##__sz = (n) * sizeof(type); \ - size_t groupname##_##name##__offset = ({ \ - size_t align_mask = __alignof__(type) - 1; \ - size_t offset = (groupname##__next + align_mask) & ~align_mask;\ - size_t size = groupname##_##name##__sz; \ - groupname##__next = offset + size; \ - offset; \ + size_t groupname##_##name##__sz = array_size(n, sizeof(type)); \ + size_t groupname##_##name##__offset = ({ \ + size_t offset = 0; \ + if (groupname##__next != SIZE_MAX) { \ + size_t align_mask = __alignof__(type) - 1; \ + offset = (groupname##__next + align_mask) & \ + ~align_mask; \ + if (check_add_overflow(offset, groupname##_##name##__sz,\ + &groupname##__next)) { \ + groupname##__next = SIZE_MAX; \ + offset = 0; \ + } \ + } \ + offset; \ }) #define vla_ptr(ptr, groupname, name) \ diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index fa6793065c7c..a6426dd1cfef 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -328,7 +328,7 @@ static int usba_config_fifo_table(struct usba_udc *udc) switch (fifo_mode) { default: fifo_mode = 0; - /* fall through */ + fallthrough; case 0: udc->fifo_cfg = NULL; n = 0; diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index b2638e83bb49..a6f7b2594c09 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -250,7 +250,7 @@ static int dr_controller_setup(struct fsl_udc *udc) break; case FSL_USB2_PHY_UTMI_WIDE: portctrl |= PORTSCX_PTW_16BIT; - /* fall through */ + fallthrough; case FSL_USB2_PHY_UTMI: case FSL_USB2_PHY_UTMI_DUAL: if (udc->pdata->have_sysif_regs) { diff --git a/drivers/usb/gadget/udc/pxa25x_udc.c b/drivers/usb/gadget/udc/pxa25x_udc.c index cfafdd92c2a8..10324a7334fe 100644 --- a/drivers/usb/gadget/udc/pxa25x_udc.c +++ b/drivers/usb/gadget/udc/pxa25x_udc.c @@ -2340,12 +2340,12 @@ static int pxa25x_udc_probe(struct platform_device *pdev) case PXA250_A0: case PXA250_A1: /* A0/A1 "not released"; ep 13, 15 unusable */ - /* fall through */ + fallthrough; case PXA250_B2: case PXA210_B2: case PXA250_B1: case PXA210_B1: case PXA250_B0: case PXA210_B0: /* OUT-DMA is broken ... */ - /* fall through */ + fallthrough; case PXA250_C0: case PXA210_C0: break; #elif defined(CONFIG_ARCH_IXP4XX) diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c index a87c0b26279e..3055d9abfec3 100644 --- a/drivers/usb/host/isp116x-hcd.c +++ b/drivers/usb/host/isp116x-hcd.c @@ -1019,7 +1019,7 @@ static int isp116x_hub_control(struct usb_hcd *hcd, spin_lock_irqsave(&isp116x->lock, flags); isp116x_write_reg32(isp116x, HCRHSTATUS, RH_HS_OCIC); spin_unlock_irqrestore(&isp116x->lock, flags); - /* fall through */ + fallthrough; case C_HUB_LOCAL_POWER: DBG("C_HUB_LOCAL_POWER\n"); break; @@ -1421,10 +1421,10 @@ static int isp116x_bus_suspend(struct usb_hcd *hcd) isp116x_write_reg32(isp116x, HCCONTROL, (val & ~HCCONTROL_HCFS) | HCCONTROL_USB_RESET); - /* fall through */ + fallthrough; case HCCONTROL_USB_RESET: ret = -EBUSY; - /* fall through */ + fallthrough; default: /* HCCONTROL_USB_SUSPEND */ spin_unlock_irqrestore(&isp116x->lock, flags); break; diff --git a/drivers/usb/host/ohci-exynos.c b/drivers/usb/host/ohci-exynos.c index bd40e597f256..5f5e8a64c8e2 100644 --- a/drivers/usb/host/ohci-exynos.c +++ b/drivers/usb/host/ohci-exynos.c @@ -171,9 +171,8 @@ static int exynos_ohci_probe(struct platform_device *pdev) hcd->rsrc_len = resource_size(res); irq = platform_get_irq(pdev, 0); - if (!irq) { - dev_err(&pdev->dev, "Failed to get IRQ\n"); - err = -ENODEV; + if (irq < 0) { + err = irq; goto fail_io; } diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index b8961c0381cf..8c1bbac6d136 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -957,7 +957,8 @@ static void quirk_usb_disable_ehci(struct pci_dev *pdev) ehci_bios_handoff(pdev, op_reg_base, cap, offset); break; case 0: /* Illegal reserved cap, set cap=0 so we exit */ - cap = 0; /* fall through */ + cap = 0; + fallthrough; default: dev_warn(&pdev->dev, "EHCI: unrecognized capability %02x\n", diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index fcc5ac5ce8b1..ccb0156fcebe 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -699,7 +699,7 @@ static void dbc_handle_xfer_event(struct xhci_dbc *dbc, union xhci_trb *event) switch (comp_code) { case COMP_SUCCESS: remain_length = 0; - /* FALLTHROUGH */ + fallthrough; case COMP_SHORT_PACKET: status = 0; break; diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index 92e25a62fdb5..c88bffd68742 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -274,7 +274,7 @@ static int xhci_slot_context_show(struct seq_file *s, void *unused) static int xhci_endpoint_context_show(struct seq_file *s, void *unused) { - int dci; + int ep_index; dma_addr_t dma; struct xhci_hcd *xhci; struct xhci_ep_ctx *ep_ctx; @@ -283,9 +283,9 @@ static int xhci_endpoint_context_show(struct seq_file *s, void *unused) xhci = hcd_to_xhci(bus_to_hcd(dev->udev->bus)); - for (dci = 1; dci < 32; dci++) { - ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, dci); - dma = dev->out_ctx->dma + dci * CTX_SIZE(xhci->hcc_params); + for (ep_index = 0; ep_index < 31; ep_index++) { + ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index); + dma = dev->out_ctx->dma + (ep_index + 1) * CTX_SIZE(xhci->hcc_params); seq_printf(s, "%pad: %s\n", &dma, xhci_decode_ep_context(le32_to_cpu(ep_ctx->ep_info), le32_to_cpu(ep_ctx->ep_info2), diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index c3554e37e09f..c799ca5361d4 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -740,15 +740,6 @@ static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci, { u32 pls = status_reg & PORT_PLS_MASK; - /* resume state is a xHCI internal state. - * Do not report it to usb core, instead, pretend to be U3, - * thus usb core knows it's not ready for transfer - */ - if (pls == XDEV_RESUME) { - *status |= USB_SS_PORT_LS_U3; - return; - } - /* When the CAS bit is set then warm reset * should be performed on port */ @@ -771,6 +762,16 @@ static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci, pls |= USB_PORT_STAT_CONNECTION; } else { /* + * Resume state is an xHCI internal state. Do not report it to + * usb core, instead, pretend to be U3, thus usb core knows + * it's not ready for transfer. + */ + if (pls == XDEV_RESUME) { + *status |= USB_SS_PORT_LS_U3; + return; + } + + /* * If CAS bit isn't set but the Port is already at * Compliance Mode, fake a connection so the USB core * notices the Compliance state and resets the port. @@ -1483,7 +1484,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, break; case USB_PORT_FEAT_C_SUSPEND: bus_state->port_c_suspend &= ~(1 << wIndex); - /* fall through */ + fallthrough; case USB_PORT_FEAT_C_RESET: case USB_PORT_FEAT_C_BH_PORT_RESET: case USB_PORT_FEAT_C_CONNECTION: diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 696fad50b478..fe405cd38dbc 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1311,7 +1311,7 @@ static unsigned int xhci_get_endpoint_interval(struct usb_device *udev, interval = xhci_parse_microframe_interval(udev, ep); break; } - /* Fall through - SS and HS isoc/int have same decoding */ + fallthrough; /* SS and HS isoc/int have same decoding */ case USB_SPEED_SUPER_PLUS: case USB_SPEED_SUPER: @@ -1331,7 +1331,7 @@ static unsigned int xhci_get_endpoint_interval(struct usb_device *udev, * since it uses the same rules as low speed interrupt * endpoints. */ - /* fall through */ + fallthrough; case USB_SPEED_LOW: if (usb_endpoint_xfer_int(&ep->desc) || diff --git a/drivers/usb/host/xhci-pci-renesas.c b/drivers/usb/host/xhci-pci-renesas.c index 59b1965ad0a3..f97ac9f52bf4 100644 --- a/drivers/usb/host/xhci-pci-renesas.c +++ b/drivers/usb/host/xhci-pci-renesas.c @@ -50,20 +50,6 @@ #define RENESAS_RETRY 10000 #define RENESAS_DELAY 10 -#define ROM_VALID_01 0x2013 -#define ROM_VALID_02 0x2026 - -static int renesas_verify_fw_version(struct pci_dev *pdev, u32 version) -{ - switch (version) { - case ROM_VALID_01: - case ROM_VALID_02: - return 0; - } - dev_err(&pdev->dev, "FW has invalid version :%d\n", version); - return -EINVAL; -} - static int renesas_fw_download_image(struct pci_dev *dev, const u32 *fw, size_t step, bool rom) { @@ -202,10 +188,7 @@ static int renesas_check_rom_state(struct pci_dev *pdev) version &= RENESAS_FW_VERSION_FIELD; version = version >> RENESAS_FW_VERSION_OFFSET; - - err = renesas_verify_fw_version(pdev, version); - if (err) - return err; + dev_dbg(&pdev->dev, "Found ROM version: %x\n", version); /* * Test if ROM is present and loaded, if so we can skip everything diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 2c255d0620b0..a741a38a4c69 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2103,7 +2103,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, break; xhci_dbg(xhci, "TRB error %u, halted endpoint index = %u\n", trb_comp_code, ep_index); - /* else fall through */ + fallthrough; case COMP_STALL_ERROR: /* Did we transfer part of the data (middle) phase? */ if (trb_type == TRB_DATA || trb_type == TRB_NORMAL) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 014d79334f50..190923d8b246 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1136,7 +1136,7 @@ static struct phy *tegra_xusb_get_phy(struct tegra_xusb *tegra, char *name, unsigned int i, phy_count = 0; for (i = 0; i < tegra->soc->num_types; i++) { - if (!strncmp(tegra->soc->phy_types[i].name, "usb2", + if (!strncmp(tegra->soc->phy_types[i].name, name, strlen(name))) return tegra->phys[phy_count+port]; @@ -1258,6 +1258,8 @@ static int tegra_xusb_init_usb_phy(struct tegra_xusb *tegra) INIT_WORK(&tegra->id_work, tegra_xhci_id_work); tegra->id_nb.notifier_call = tegra_xhci_id_notify; + tegra->otg_usb2_port = -EINVAL; + tegra->otg_usb3_port = -EINVAL; for (i = 0; i < tegra->num_usb_phys; i++) { struct phy *phy = tegra_xusb_get_phy(tegra, "usb2", i); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 3c41b14ecce7..f4cedcaee14b 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3236,10 +3236,11 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd, wait_for_completion(cfg_cmd->completion); - ep->ep_state &= ~EP_SOFT_CLEAR_TOGGLE; xhci_free_command(xhci, cfg_cmd); cleanup: xhci_free_command(xhci, stop_cmd); + if (ep->ep_state & EP_SOFT_CLEAR_TOGGLE) + ep->ep_state &= ~EP_SOFT_CLEAR_TOGGLE; } static int xhci_check_streams_endpoint(struct xhci_hcd *xhci, @@ -4618,7 +4619,7 @@ static unsigned long long xhci_calculate_intel_u1_timeout( break; } /* Otherwise the calculation is the same as isoc eps */ - /* fall through */ + fallthrough; case USB_ENDPOINT_XFER_ISOC: timeout_ns = xhci_service_interval_to_ns(desc); timeout_ns = DIV_ROUND_UP_ULL(timeout_ns * 105, 100); diff --git a/drivers/usb/misc/lvstest.c b/drivers/usb/misc/lvstest.c index 407fe7570f3b..f8686139d6f3 100644 --- a/drivers/usb/misc/lvstest.c +++ b/drivers/usb/misc/lvstest.c @@ -426,7 +426,7 @@ static int lvs_rh_probe(struct usb_interface *intf, USB_DT_SS_HUB_SIZE, USB_CTRL_GET_TIMEOUT); if (ret < (USB_DT_HUB_NONVAR_SIZE + 2)) { dev_err(&hdev->dev, "wrong root hub descriptor read %d\n", ret); - return ret; + return ret < 0 ? ret : -EINVAL; } /* submit urb to poll interrupt endpoint */ diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c index 6e7d34e7fec4..b2e09883c7e2 100644 --- a/drivers/usb/misc/yurex.c +++ b/drivers/usb/misc/yurex.c @@ -492,7 +492,7 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer, prepare_to_wait(&dev->waitq, &wait, TASK_INTERRUPTIBLE); dev_dbg(&dev->interface->dev, "%s - submit %c\n", __func__, dev->cntl_buffer[0]); - retval = usb_submit_urb(dev->cntl_urb, GFP_KERNEL); + retval = usb_submit_urb(dev->cntl_urb, GFP_ATOMIC); if (retval >= 0) timeout = schedule_timeout(YUREX_WRITE_TIMEOUT); finish_wait(&dev->waitq, &wait); diff --git a/drivers/usb/musb/cppi_dma.c b/drivers/usb/musb/cppi_dma.c index c545b27ea568..edb5b63d7063 100644 --- a/drivers/usb/musb/cppi_dma.c +++ b/drivers/usb/musb/cppi_dma.c @@ -975,7 +975,7 @@ static int cppi_channel_program(struct dma_channel *ch, musb_dbg(musb, "%cX DMA%d not allocated!", cppi_ch->transmit ? 'T' : 'R', cppi_ch->index); - /* FALLTHROUGH */ + fallthrough; case MUSB_DMA_STATUS_FREE: break; } diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 5a56a03996b1..849e0b770130 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -852,7 +852,7 @@ static void musb_handle_intr_suspend(struct musb *musb, u8 devctl) case OTG_STATE_B_IDLE: if (!musb->is_active) break; - /* fall through */ + fallthrough; case OTG_STATE_B_PERIPHERAL: musb_g_suspend(musb); musb->is_active = musb->g.b_hnp_enable; @@ -972,9 +972,8 @@ static void musb_handle_intr_disconnect(struct musb *musb, u8 devctl) case OTG_STATE_A_PERIPHERAL: musb_hnp_stop(musb); musb_root_disconnect(musb); - /* FALLTHROUGH */ + fallthrough; case OTG_STATE_B_WAIT_ACON: - /* FALLTHROUGH */ case OTG_STATE_B_PERIPHERAL: case OTG_STATE_B_IDLE: musb_g_disconnect(musb); @@ -1009,7 +1008,7 @@ static void musb_handle_intr_reset(struct musb *musb) switch (musb->xceiv->otg->state) { case OTG_STATE_A_SUSPEND: musb_g_reset(musb); - /* FALLTHROUGH */ + fallthrough; case OTG_STATE_A_WAIT_BCON: /* OPT TD.4.7-900ms */ /* never use invalid T(a_wait_bcon) */ musb_dbg(musb, "HNP: in %s, %d msec timeout", @@ -1030,7 +1029,7 @@ static void musb_handle_intr_reset(struct musb *musb) break; case OTG_STATE_B_IDLE: musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL; - /* FALLTHROUGH */ + fallthrough; case OTG_STATE_B_PERIPHERAL: musb_g_reset(musb); break; @@ -1471,7 +1470,7 @@ static int ep_config_from_table(struct musb *musb) switch (fifo_mode) { default: fifo_mode = 0; - /* FALLTHROUGH */ + fallthrough; case 0: cfg = mode_0_cfg; n = ARRAY_SIZE(mode_0_cfg); @@ -2018,7 +2017,7 @@ static void musb_pm_runtime_check_session(struct musb *musb) musb->quirk_retries--; return; } - /* fall through */ + fallthrough; case MUSB_QUIRK_A_DISCONNECT_19: if (musb->quirk_retries && !musb->flush_irq_work) { musb_dbg(musb, diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 19556c1a8ae8..30085b2be7b9 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -232,7 +232,7 @@ static int dsps_check_status(struct musb *musb, void *unused) dsps_mod_timer_optional(glue); break; } - /* fall through */ + fallthrough; case OTG_STATE_A_WAIT_BCON: /* keep VBUS on for host-only mode */ @@ -242,7 +242,7 @@ static int dsps_check_status(struct musb *musb, void *unused) } musb_writeb(musb->mregs, MUSB_DEVCTL, 0); skip_session = 1; - /* fall through */ + fallthrough; case OTG_STATE_A_IDLE: case OTG_STATE_B_IDLE: @@ -793,7 +793,7 @@ static int dsps_create_musb_pdev(struct dsps_glue *glue, case USB_SPEED_SUPER: dev_warn(dev, "ignore incorrect maximum_speed " "(super-speed) setting in dts"); - /* fall through */ + fallthrough; default: config->maximum_speed = USB_SPEED_HIGH; } diff --git a/drivers/usb/musb/musb_gadget_ep0.c b/drivers/usb/musb/musb_gadget_ep0.c index 0ae3e0be043e..44d3cb02fa76 100644 --- a/drivers/usb/musb/musb_gadget_ep0.c +++ b/drivers/usb/musb/musb_gadget_ep0.c @@ -735,7 +735,7 @@ irqreturn_t musb_g_ep0_irq(struct musb *musb) musb_writeb(mbase, MUSB_TESTMODE, musb->test_mode_nr); } - /* FALLTHROUGH */ + fallthrough; case MUSB_EP0_STAGE_STATUSOUT: /* end of sequence #1: write to host (TX state) */ @@ -767,7 +767,7 @@ irqreturn_t musb_g_ep0_irq(struct musb *musb) */ retval = IRQ_HANDLED; musb->ep0_state = MUSB_EP0_STAGE_SETUP; - /* FALLTHROUGH */ + fallthrough; case MUSB_EP0_STAGE_SETUP: setup: diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 8b7d22a0c0fb..30c5e7de0761 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -360,7 +360,7 @@ static void musb_advance_schedule(struct musb *musb, struct urb *urb, qh = first_qh(head); break; } - /* fall through */ + fallthrough; case USB_ENDPOINT_XFER_ISOC: case USB_ENDPOINT_XFER_INT: @@ -1019,7 +1019,7 @@ static bool musb_h_ep0_continue(struct musb *musb, u16 len, struct urb *urb) musb->ep0_stage = MUSB_EP0_OUT; more = true; } - /* FALLTHROUGH */ + fallthrough; case MUSB_EP0_OUT: fifo_count = min_t(size_t, qh->maxpacket, urb->transfer_buffer_length - @@ -2222,7 +2222,7 @@ static int musb_urb_enqueue( interval = max_t(u8, epd->bInterval, 1); break; } - /* FALLTHROUGH */ + fallthrough; case USB_ENDPOINT_XFER_ISOC: /* ISO always uses logarithmic encoding */ interval = min_t(u8, epd->bInterval, 16); diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c index cb7ae297a3af..cafc69536e1d 100644 --- a/drivers/usb/musb/musb_virthub.c +++ b/drivers/usb/musb/musb_virthub.c @@ -211,7 +211,7 @@ void musb_root_disconnect(struct musb *musb) musb->g.is_a_peripheral = 1; break; } - /* FALLTHROUGH */ + fallthrough; case OTG_STATE_A_HOST: musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON; musb->is_active = 0; diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index d62c78b97cad..4232f1ce3fbf 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -104,7 +104,7 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue) if (error) break; musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE; - /* Fall through */ + fallthrough; case OTG_STATE_A_WAIT_VRISE: case OTG_STATE_A_WAIT_BCON: case OTG_STATE_A_HOST: diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c index 99890d1bbfcb..c26683a2702b 100644 --- a/drivers/usb/musb/tusb6010.c +++ b/drivers/usb/musb/tusb6010.c @@ -464,7 +464,7 @@ static void musb_do_idle(struct timer_list *t) dev_dbg(musb->controller, "Nothing connected %s, turning off VBUS\n", usb_otg_state_string(musb->xceiv->otg->state)); } - /* FALLTHROUGH */ + fallthrough; case OTG_STATE_A_IDLE: tusb_musb_set_vbus(musb, 0); default: diff --git a/drivers/usb/phy/phy-jz4770.c b/drivers/usb/phy/phy-jz4770.c index d4ee3cb721ea..f6d3731581eb 100644 --- a/drivers/usb/phy/phy-jz4770.c +++ b/drivers/usb/phy/phy-jz4770.c @@ -176,6 +176,7 @@ static int ingenic_usb_phy_init(struct usb_phy *phy) /* Wait for PHY to reset */ usleep_range(30, 300); + reg = readl(priv->base + REG_USBPCR_OFFSET); writel(reg & ~USBPCR_POR, priv->base + REG_USBPCR_OFFSET); usleep_range(300, 1000); diff --git a/drivers/usb/storage/sddr55.c b/drivers/usb/storage/sddr55.c index c8a988d2cfdd..15dc25801cdc 100644 --- a/drivers/usb/storage/sddr55.c +++ b/drivers/usb/storage/sddr55.c @@ -592,7 +592,7 @@ static unsigned long sddr55_get_capacity(struct us_data *us) { case 0x64: info->pageshift = 8; info->smallpageshift = 1; - /* fall through */ + fallthrough; case 0x5d: // 5d is a ROM card with pagesize 512. return 0x00200000; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index d592071119ba..08f9296431e9 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -688,7 +688,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, break; case DMA_BIDIRECTIONAL: cmdinfo->state |= ALLOC_DATA_IN_URB | SUBMIT_DATA_IN_URB; - /* fall through */ + fallthrough; case DMA_TO_DEVICE: cmdinfo->state |= ALLOC_DATA_OUT_URB | SUBMIT_DATA_OUT_URB; case DMA_NONE: diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 220ae2c356ee..5732e9691f08 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2328,7 +2328,7 @@ UNUSUAL_DEV( 0x357d, 0x7788, 0x0114, 0x0114, "JMicron", "USB to ATA/ATAPI Bridge", USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_BROKEN_FUA ), + US_FL_BROKEN_FUA | US_FL_IGNORE_UAS ), /* Reported by Andrey Rahmatullin <wrar@altlinux.org> */ UNUSUAL_DEV( 0x4102, 0x1020, 0x0100, 0x0100, diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 162b09d69f62..711ab240058c 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -28,6 +28,13 @@ * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org> */ +/* Reported-by: Till Dörges <doerges@pre-sense.de> */ +UNUSUAL_DEV(0x054c, 0x087d, 0x0000, 0x9999, + "Sony", + "PSZ-HA*", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_OPCODES), + /* Reported-by: Julian Groß <julian.g@posteo.de> */ UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999, "LaCie", @@ -80,6 +87,13 @@ UNUSUAL_DEV(0x152d, 0x0578, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_BROKEN_FUA), +/* Reported-by: Thinh Nguyen <thinhn@synopsys.com> */ +UNUSUAL_DEV(0x154b, 0xf00d, 0x0000, 0x9999, + "PNY", + "Pro Elite SSD", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_ATA_1X), + /* Reported-by: Hans de Goede <hdegoede@redhat.com> */ UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999, "VIA", diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index f57d91fd0e09..bd80e03b2b6f 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -157,7 +157,7 @@ static enum typec_cc_status tcpci_to_typec_cc(unsigned int cc, bool sink) case 0x3: if (sink) return TYPEC_CC_RP_3_0; - /* fall through */ + fallthrough; case 0x0: default: return TYPEC_CC_OPEN; diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 3ef37202ee37..a48e3f90d196 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -3372,13 +3372,31 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_state(port, SNK_HARD_RESET_SINK_OFF, 0); break; case SRC_HARD_RESET_VBUS_OFF: - tcpm_set_vconn(port, true); + /* + * 7.1.5 Response to Hard Resets + * Hard Reset Signaling indicates a communication failure has occurred and the + * Source Shall stop driving VCONN, Shall remove Rp from the VCONN pin and Shall + * drive VBUS to vSafe0V as shown in Figure 7-9. + */ + tcpm_set_vconn(port, false); tcpm_set_vbus(port, false); tcpm_set_roles(port, port->self_powered, TYPEC_SOURCE, tcpm_data_role_for_source(port)); - tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, PD_T_SRC_RECOVER); + /* + * If tcpc fails to notify vbus off, TCPM will wait for PD_T_SAFE_0V + + * PD_T_SRC_RECOVER before turning vbus back on. + * From Table 7-12 Sequence Description for a Source Initiated Hard Reset: + * 4. Policy Engine waits tPSHardReset after sending Hard Reset Signaling and then + * tells the Device Policy Manager to instruct the power supply to perform a + * Hard Reset. The transition to vSafe0V Shall occur within tSafe0V (t2). + * 5. After tSrcRecover the Source applies power to VBUS in an attempt to + * re-establish communication with the Sink and resume USB Default Operation. + * The transition to vSafe5V Shall occur within tSrcTurnOn(t4). + */ + tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, PD_T_SAFE_0V + PD_T_SRC_RECOVER); break; case SRC_HARD_RESET_VBUS_ON: + tcpm_set_vconn(port, true); tcpm_set_vbus(port, true); port->tcpc->set_pd_rx(port->tcpc, true); tcpm_set_attached_state(port, true); @@ -3944,7 +3962,11 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port) tcpm_set_state(port, SNK_HARD_RESET_WAIT_VBUS, 0); break; case SRC_HARD_RESET_VBUS_OFF: - tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, 0); + /* + * After establishing the vSafe0V voltage condition on VBUS, the Source Shall wait + * tSrcRecover before re-applying VCONN and restoring VBUS to vSafe5V. + */ + tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, PD_T_SRC_RECOVER); break; case HARD_RESET_SEND: break; diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index 048381c058a5..261131c9e37c 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -288,8 +288,6 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con, struct typec_altmode *alt; struct ucsi_dp *dp; - mutex_lock(&con->lock); - /* We can't rely on the firmware with the capabilities. */ desc->vdo |= DP_CAP_DP_SIGNALING | DP_CAP_RECEPTACLE; @@ -298,15 +296,12 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con, desc->vdo |= all_assignments << 16; alt = typec_port_register_altmode(con->port, desc); - if (IS_ERR(alt)) { - mutex_unlock(&con->lock); + if (IS_ERR(alt)) return alt; - } dp = devm_kzalloc(&alt->dev, sizeof(*dp), GFP_KERNEL); if (!dp) { typec_unregister_altmode(alt); - mutex_unlock(&con->lock); return ERR_PTR(-ENOMEM); } @@ -319,7 +314,5 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con, alt->ops = &ucsi_displayport_ops; typec_altmode_set_drvdata(alt, dp); - mutex_unlock(&con->lock); - return alt; } diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index affd024190c9..e680fcfdee60 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -146,40 +146,33 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd) return UCSI_CCI_LENGTH(cci); } -static int ucsi_run_command(struct ucsi *ucsi, u64 command, - void *data, size_t size) +int ucsi_send_command(struct ucsi *ucsi, u64 command, + void *data, size_t size) { u8 length; int ret; + mutex_lock(&ucsi->ppm_lock); + ret = ucsi_exec_command(ucsi, command); if (ret < 0) - return ret; + goto out; length = ret; if (data) { ret = ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, data, size); if (ret) - return ret; + goto out; } ret = ucsi_acknowledge_command(ucsi); if (ret) - return ret; - - return length; -} - -int ucsi_send_command(struct ucsi *ucsi, u64 command, - void *retval, size_t size) -{ - int ret; + goto out; - mutex_lock(&ucsi->ppm_lock); - ret = ucsi_run_command(ucsi, command, retval, size); + ret = length; +out: mutex_unlock(&ucsi->ppm_lock); - return ret; } EXPORT_SYMBOL_GPL(ucsi_send_command); @@ -205,7 +198,7 @@ void ucsi_altmode_update_active(struct ucsi_connector *con) int i; command = UCSI_GET_CURRENT_CAM | UCSI_CONNECTOR_NUMBER(con->num); - ret = ucsi_run_command(con->ucsi, command, &cur, sizeof(cur)); + ret = ucsi_send_command(con->ucsi, command, &cur, sizeof(cur)); if (ret < 0) { if (con->ucsi->version > 0x0100) { dev_err(con->ucsi->dev, @@ -354,7 +347,7 @@ ucsi_register_altmodes_nvidia(struct ucsi_connector *con, u8 recipient) command |= UCSI_GET_ALTMODE_RECIPIENT(recipient); command |= UCSI_GET_ALTMODE_CONNECTOR_NUMBER(con->num); command |= UCSI_GET_ALTMODE_OFFSET(i); - len = ucsi_run_command(con->ucsi, command, &alt, sizeof(alt)); + len = ucsi_send_command(con->ucsi, command, &alt, sizeof(alt)); /* * We are collecting all altmodes first and then registering. * Some type-C device will return zero length data beyond last @@ -431,7 +424,7 @@ static int ucsi_register_altmodes(struct ucsi_connector *con, u8 recipient) command |= UCSI_GET_ALTMODE_RECIPIENT(recipient); command |= UCSI_GET_ALTMODE_CONNECTOR_NUMBER(con->num); command |= UCSI_GET_ALTMODE_OFFSET(i); - len = ucsi_run_command(con->ucsi, command, alt, sizeof(alt)); + len = ucsi_send_command(con->ucsi, command, alt, sizeof(alt)); if (len <= 0) return len; @@ -502,7 +495,7 @@ static void ucsi_get_pdos(struct ucsi_connector *con, int is_partner) command |= UCSI_GET_PDOS_PARTNER_PDO(is_partner); command |= UCSI_GET_PDOS_NUM_PDOS(UCSI_MAX_PDOS - 1); command |= UCSI_GET_PDOS_SRC_PDOS; - ret = ucsi_run_command(ucsi, command, con->src_pdos, + ret = ucsi_send_command(ucsi, command, con->src_pdos, sizeof(con->src_pdos)); if (ret < 0) { dev_err(ucsi->dev, "UCSI_GET_PDOS failed (%d)\n", ret); @@ -681,7 +674,7 @@ static void ucsi_handle_connector_change(struct work_struct *work) */ command = UCSI_GET_CAM_SUPPORTED; command |= UCSI_CONNECTOR_NUMBER(con->num); - ucsi_run_command(con->ucsi, command, NULL, 0); + ucsi_send_command(con->ucsi, command, NULL, 0); } if (con->status.change & UCSI_CONSTAT_PARTNER_CHANGE) @@ -736,20 +729,24 @@ static int ucsi_reset_ppm(struct ucsi *ucsi) u32 cci; int ret; + mutex_lock(&ucsi->ppm_lock); + ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command, sizeof(command)); if (ret < 0) - return ret; + goto out; tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS); do { - if (time_is_before_jiffies(tmo)) - return -ETIMEDOUT; + if (time_is_before_jiffies(tmo)) { + ret = -ETIMEDOUT; + goto out; + } ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci)); if (ret) - return ret; + goto out; /* If the PPM is still doing something else, reset it again. */ if (cci & ~UCSI_CCI_RESET_COMPLETE) { @@ -757,13 +754,15 @@ static int ucsi_reset_ppm(struct ucsi *ucsi) &command, sizeof(command)); if (ret < 0) - return ret; + goto out; } msleep(20); } while (!(cci & UCSI_CCI_RESET_COMPLETE)); - return 0; +out: + mutex_unlock(&ucsi->ppm_lock); + return ret; } static int ucsi_role_cmd(struct ucsi_connector *con, u64 command) @@ -775,9 +774,7 @@ static int ucsi_role_cmd(struct ucsi_connector *con, u64 command) u64 c; /* PPM most likely stopped responding. Resetting everything. */ - mutex_lock(&con->ucsi->ppm_lock); ucsi_reset_ppm(con->ucsi); - mutex_unlock(&con->ucsi->ppm_lock); c = UCSI_SET_NOTIFICATION_ENABLE | con->ucsi->ntfy; ucsi_send_command(con->ucsi, c, NULL, 0); @@ -901,12 +898,15 @@ static int ucsi_register_port(struct ucsi *ucsi, int index) con->num = index + 1; con->ucsi = ucsi; + /* Delay other interactions with the con until registration is complete */ + mutex_lock(&con->lock); + /* Get connector capability */ command = UCSI_GET_CONNECTOR_CAPABILITY; command |= UCSI_CONNECTOR_NUMBER(con->num); - ret = ucsi_run_command(ucsi, command, &con->cap, sizeof(con->cap)); + ret = ucsi_send_command(ucsi, command, &con->cap, sizeof(con->cap)); if (ret < 0) - return ret; + goto out; if (con->cap.op_mode & UCSI_CONCAP_OPMODE_DRP) cap->data = TYPEC_PORT_DRD; @@ -938,27 +938,32 @@ static int ucsi_register_port(struct ucsi *ucsi, int index) ret = ucsi_register_port_psy(con); if (ret) - return ret; + goto out; /* Register the connector */ con->port = typec_register_port(ucsi->dev, cap); - if (IS_ERR(con->port)) - return PTR_ERR(con->port); + if (IS_ERR(con->port)) { + ret = PTR_ERR(con->port); + goto out; + } /* Alternate modes */ ret = ucsi_register_altmodes(con, UCSI_RECIPIENT_CON); - if (ret) + if (ret) { dev_err(ucsi->dev, "con%d: failed to register alt modes\n", con->num); + goto out; + } /* Get the status */ command = UCSI_GET_CONNECTOR_STATUS | UCSI_CONNECTOR_NUMBER(con->num); - ret = ucsi_run_command(ucsi, command, &con->status, - sizeof(con->status)); + ret = ucsi_send_command(ucsi, command, &con->status, sizeof(con->status)); if (ret < 0) { dev_err(ucsi->dev, "con%d: failed to get status\n", con->num); - return 0; + ret = 0; + goto out; } + ret = 0; /* ucsi_send_command() returns length on success */ switch (UCSI_CONSTAT_PARTNER_TYPE(con->status.flags)) { case UCSI_CONSTAT_PARTNER_TYPE_UFP: @@ -983,17 +988,21 @@ static int ucsi_register_port(struct ucsi *ucsi, int index) if (con->partner) { ret = ucsi_register_altmodes(con, UCSI_RECIPIENT_SOP); - if (ret) + if (ret) { dev_err(ucsi->dev, "con%d: failed to register alternate modes\n", con->num); - else + ret = 0; + } else { ucsi_altmode_update_active(con); + } } trace_ucsi_register_port(con->num, &con->status); - return 0; +out: + mutex_unlock(&con->lock); + return ret; } /** @@ -1009,8 +1018,6 @@ static int ucsi_init(struct ucsi *ucsi) int ret; int i; - mutex_lock(&ucsi->ppm_lock); - /* Reset the PPM */ ret = ucsi_reset_ppm(ucsi); if (ret) { @@ -1021,13 +1028,13 @@ static int ucsi_init(struct ucsi *ucsi) /* Enable basic notifications */ ucsi->ntfy = UCSI_ENABLE_NTFY_CMD_COMPLETE | UCSI_ENABLE_NTFY_ERROR; command = UCSI_SET_NOTIFICATION_ENABLE | ucsi->ntfy; - ret = ucsi_run_command(ucsi, command, NULL, 0); + ret = ucsi_send_command(ucsi, command, NULL, 0); if (ret < 0) goto err_reset; /* Get PPM capabilities */ command = UCSI_GET_CAPABILITY; - ret = ucsi_run_command(ucsi, command, &ucsi->cap, sizeof(ucsi->cap)); + ret = ucsi_send_command(ucsi, command, &ucsi->cap, sizeof(ucsi->cap)); if (ret < 0) goto err_reset; @@ -1054,12 +1061,10 @@ static int ucsi_init(struct ucsi *ucsi) /* Enable all notifications */ ucsi->ntfy = UCSI_ENABLE_NTFY_ALL; command = UCSI_SET_NOTIFICATION_ENABLE | ucsi->ntfy; - ret = ucsi_run_command(ucsi, command, NULL, 0); + ret = ucsi_send_command(ucsi, command, NULL, 0); if (ret < 0) goto err_unregister; - mutex_unlock(&ucsi->ppm_lock); - return 0; err_unregister: @@ -1074,8 +1079,6 @@ err_unregister: err_reset: ucsi_reset_ppm(ucsi); err: - mutex_unlock(&ucsi->ppm_lock); - return ret; } diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c index 2305d425e6c9..9d7d642022d1 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -461,6 +461,11 @@ static void stub_disconnect(struct usb_device *udev) return; } +static bool usbip_match(struct usb_device *udev) +{ + return true; +} + #ifdef CONFIG_PM /* These functions need usb_port_suspend and usb_port_resume, @@ -486,6 +491,7 @@ struct usb_device_driver stub_driver = { .name = "usbip-host", .probe = stub_probe, .disconnect = stub_disconnect, + .match = usbip_match, #ifdef CONFIG_PM .suspend = stub_suspend, .resume = stub_resume, diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h index 08f267a2aafe..64696d63fe07 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.h +++ b/drivers/vdpa/ifcvf/ifcvf_base.h @@ -84,7 +84,7 @@ struct ifcvf_hw { void __iomem * const *base; char config_msix_name[256]; struct vdpa_callback config_cb; - + unsigned int config_irq; }; struct ifcvf_adapter { diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index 076d7ac5e723..8b4028556cb6 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -55,6 +55,7 @@ static void ifcvf_free_irq(struct ifcvf_adapter *adapter, int queues) vf->vring[i].irq = -EINVAL; } + devm_free_irq(&pdev->dev, vf->config_irq, vf); ifcvf_free_irq_vectors(pdev); } @@ -74,10 +75,14 @@ static int ifcvf_request_irq(struct ifcvf_adapter *adapter) snprintf(vf->config_msix_name, 256, "ifcvf[%s]-config\n", pci_name(pdev)); vector = 0; - irq = pci_irq_vector(pdev, vector); - ret = devm_request_irq(&pdev->dev, irq, + vf->config_irq = pci_irq_vector(pdev, vector); + ret = devm_request_irq(&pdev->dev, vf->config_irq, ifcvf_config_changed, 0, vf->config_msix_name, vf); + if (ret) { + IFCVF_ERR(pdev, "Failed to request config irq\n"); + return ret; + } for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) { snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n", diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 9df69d5efe8c..70676a6d1691 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -16,19 +16,19 @@ #define to_mvdev(__vdev) container_of((__vdev), struct mlx5_vdpa_dev, vdev) #define VALID_FEATURES_MASK \ - (BIT(VIRTIO_NET_F_CSUM) | BIT(VIRTIO_NET_F_GUEST_CSUM) | \ - BIT(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) | BIT(VIRTIO_NET_F_MTU) | BIT(VIRTIO_NET_F_MAC) | \ - BIT(VIRTIO_NET_F_GUEST_TSO4) | BIT(VIRTIO_NET_F_GUEST_TSO6) | \ - BIT(VIRTIO_NET_F_GUEST_ECN) | BIT(VIRTIO_NET_F_GUEST_UFO) | BIT(VIRTIO_NET_F_HOST_TSO4) | \ - BIT(VIRTIO_NET_F_HOST_TSO6) | BIT(VIRTIO_NET_F_HOST_ECN) | BIT(VIRTIO_NET_F_HOST_UFO) | \ - BIT(VIRTIO_NET_F_MRG_RXBUF) | BIT(VIRTIO_NET_F_STATUS) | BIT(VIRTIO_NET_F_CTRL_VQ) | \ - BIT(VIRTIO_NET_F_CTRL_RX) | BIT(VIRTIO_NET_F_CTRL_VLAN) | \ - BIT(VIRTIO_NET_F_CTRL_RX_EXTRA) | BIT(VIRTIO_NET_F_GUEST_ANNOUNCE) | \ - BIT(VIRTIO_NET_F_MQ) | BIT(VIRTIO_NET_F_CTRL_MAC_ADDR) | BIT(VIRTIO_NET_F_HASH_REPORT) | \ - BIT(VIRTIO_NET_F_RSS) | BIT(VIRTIO_NET_F_RSC_EXT) | BIT(VIRTIO_NET_F_STANDBY) | \ - BIT(VIRTIO_NET_F_SPEED_DUPLEX) | BIT(VIRTIO_F_NOTIFY_ON_EMPTY) | \ - BIT(VIRTIO_F_ANY_LAYOUT) | BIT(VIRTIO_F_VERSION_1) | BIT(VIRTIO_F_ACCESS_PLATFORM) | \ - BIT(VIRTIO_F_RING_PACKED) | BIT(VIRTIO_F_ORDER_PLATFORM) | BIT(VIRTIO_F_SR_IOV)) + (BIT_ULL(VIRTIO_NET_F_CSUM) | BIT_ULL(VIRTIO_NET_F_GUEST_CSUM) | \ + BIT_ULL(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) | BIT_ULL(VIRTIO_NET_F_MTU) | BIT_ULL(VIRTIO_NET_F_MAC) | \ + BIT_ULL(VIRTIO_NET_F_GUEST_TSO4) | BIT_ULL(VIRTIO_NET_F_GUEST_TSO6) | \ + BIT_ULL(VIRTIO_NET_F_GUEST_ECN) | BIT_ULL(VIRTIO_NET_F_GUEST_UFO) | BIT_ULL(VIRTIO_NET_F_HOST_TSO4) | \ + BIT_ULL(VIRTIO_NET_F_HOST_TSO6) | BIT_ULL(VIRTIO_NET_F_HOST_ECN) | BIT_ULL(VIRTIO_NET_F_HOST_UFO) | \ + BIT_ULL(VIRTIO_NET_F_MRG_RXBUF) | BIT_ULL(VIRTIO_NET_F_STATUS) | BIT_ULL(VIRTIO_NET_F_CTRL_VQ) | \ + BIT_ULL(VIRTIO_NET_F_CTRL_RX) | BIT_ULL(VIRTIO_NET_F_CTRL_VLAN) | \ + BIT_ULL(VIRTIO_NET_F_CTRL_RX_EXTRA) | BIT_ULL(VIRTIO_NET_F_GUEST_ANNOUNCE) | \ + BIT_ULL(VIRTIO_NET_F_MQ) | BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR) | BIT_ULL(VIRTIO_NET_F_HASH_REPORT) | \ + BIT_ULL(VIRTIO_NET_F_RSS) | BIT_ULL(VIRTIO_NET_F_RSC_EXT) | BIT_ULL(VIRTIO_NET_F_STANDBY) | \ + BIT_ULL(VIRTIO_NET_F_SPEED_DUPLEX) | BIT_ULL(VIRTIO_F_NOTIFY_ON_EMPTY) | \ + BIT_ULL(VIRTIO_F_ANY_LAYOUT) | BIT_ULL(VIRTIO_F_VERSION_1) | BIT_ULL(VIRTIO_F_ACCESS_PLATFORM) | \ + BIT_ULL(VIRTIO_F_RING_PACKED) | BIT_ULL(VIRTIO_F_ORDER_PLATFORM) | BIT_ULL(VIRTIO_F_SR_IOV)) #define VALID_STATUS_MASK \ (VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER | VIRTIO_CONFIG_S_DRIVER_OK | \ @@ -149,7 +149,7 @@ static bool mlx5_vdpa_debug; #define MLX5_LOG_VIO_FLAG(_feature) \ do { \ - if (features & BIT(_feature)) \ + if (features & BIT_ULL(_feature)) \ mlx5_vdpa_info(mvdev, "%s\n", #_feature); \ } while (0) @@ -750,10 +750,10 @@ static bool vq_is_tx(u16 idx) static u16 get_features_12_3(u64 features) { - return (!!(features & BIT(VIRTIO_NET_F_HOST_TSO4)) << 9) | - (!!(features & BIT(VIRTIO_NET_F_HOST_TSO6)) << 8) | - (!!(features & BIT(VIRTIO_NET_F_CSUM)) << 7) | - (!!(features & BIT(VIRTIO_NET_F_GUEST_CSUM)) << 6); + return (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO4)) << 9) | + (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO6)) << 8) | + (!!(features & BIT_ULL(VIRTIO_NET_F_CSUM)) << 7) | + (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_CSUM)) << 6); } static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) @@ -1439,13 +1439,13 @@ static u64 mlx_to_vritio_features(u16 dev_features) u64 result = 0; if (dev_features & MLX5_VIRTIO_NET_F_GUEST_CSUM) - result |= BIT(VIRTIO_NET_F_GUEST_CSUM); + result |= BIT_ULL(VIRTIO_NET_F_GUEST_CSUM); if (dev_features & MLX5_VIRTIO_NET_F_CSUM) - result |= BIT(VIRTIO_NET_F_CSUM); + result |= BIT_ULL(VIRTIO_NET_F_CSUM); if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO6) - result |= BIT(VIRTIO_NET_F_HOST_TSO6); + result |= BIT_ULL(VIRTIO_NET_F_HOST_TSO6); if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO4) - result |= BIT(VIRTIO_NET_F_HOST_TSO4); + result |= BIT_ULL(VIRTIO_NET_F_HOST_TSO4); return result; } @@ -1459,15 +1459,15 @@ static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev) dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, device_features_bits_mask); ndev->mvdev.mlx_features = mlx_to_vritio_features(dev_features); if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, virtio_version_1_0)) - ndev->mvdev.mlx_features |= BIT(VIRTIO_F_VERSION_1); - ndev->mvdev.mlx_features |= BIT(VIRTIO_F_ACCESS_PLATFORM); + ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_VERSION_1); + ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM); print_features(mvdev, ndev->mvdev.mlx_features, false); return ndev->mvdev.mlx_features; } static int verify_min_features(struct mlx5_vdpa_dev *mvdev, u64 features) { - if (!(features & BIT(VIRTIO_F_ACCESS_PLATFORM))) + if (!(features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM))) return -EOPNOTSUPP; return 0; diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 620465c2a1da..1ab1f5cda4ac 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -990,7 +990,7 @@ static long vfio_pci_ioctl(void *device_data, case VFIO_PCI_ERR_IRQ_INDEX: if (pci_is_pcie(vdev->pdev)) break; - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 86a02aff8735..61ca8ab165dc 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -33,12 +33,14 @@ struct vfio_pci_ioeventfd { struct list_head next; + struct vfio_pci_device *vdev; struct virqfd *virqfd; void __iomem *addr; uint64_t data; loff_t pos; int bar; int count; + bool test_mem; }; struct vfio_pci_irq_ctx { diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 916b184df3a5..9e353c484ace 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -37,17 +37,70 @@ #define vfio_ioread8 ioread8 #define vfio_iowrite8 iowrite8 +#define VFIO_IOWRITE(size) \ +static int vfio_pci_iowrite##size(struct vfio_pci_device *vdev, \ + bool test_mem, u##size val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + vfio_iowrite##size(val, io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOWRITE(8) +VFIO_IOWRITE(16) +VFIO_IOWRITE(32) +#ifdef iowrite64 +VFIO_IOWRITE(64) +#endif + +#define VFIO_IOREAD(size) \ +static int vfio_pci_ioread##size(struct vfio_pci_device *vdev, \ + bool test_mem, u##size *val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + *val = vfio_ioread##size(io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOREAD(8) +VFIO_IOREAD(16) +VFIO_IOREAD(32) + /* * Read or write from an __iomem region (MMIO or I/O port) with an excluded * range which is inaccessible. The excluded range drops writes and fills * reads with -1. This is intended for handling MSI-X vector tables and * leftover space for ROM BARs. */ -static ssize_t do_io_rw(void __iomem *io, char __user *buf, +static ssize_t do_io_rw(struct vfio_pci_device *vdev, bool test_mem, + void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, size_t x_end, bool iswrite) { ssize_t done = 0; + int ret; while (count) { size_t fillable, filled; @@ -66,9 +119,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 4)) return -EFAULT; - vfio_iowrite32(val, io + off); + ret = vfio_pci_iowrite32(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread32(io + off); + ret = vfio_pci_ioread32(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 4)) return -EFAULT; @@ -82,9 +141,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 2)) return -EFAULT; - vfio_iowrite16(val, io + off); + ret = vfio_pci_iowrite16(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread16(io + off); + ret = vfio_pci_ioread16(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 2)) return -EFAULT; @@ -98,9 +163,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 1)) return -EFAULT; - vfio_iowrite8(val, io + off); + ret = vfio_pci_iowrite8(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread8(io + off); + ret = vfio_pci_ioread8(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 1)) return -EFAULT; @@ -178,14 +249,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, count = min(count, (size_t)(end - pos)); - if (res->flags & IORESOURCE_MEM) { - down_read(&vdev->memory_lock); - if (!__vfio_pci_memory_enabled(vdev)) { - up_read(&vdev->memory_lock); - return -EIO; - } - } - if (bar == PCI_ROM_RESOURCE) { /* * The ROM can fill less space than the BAR, so we start the @@ -213,7 +276,8 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, x_end = vdev->msix_offset + vdev->msix_size; } - done = do_io_rw(io, buf, pos, count, x_start, x_end, iswrite); + done = do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos, + count, x_start, x_end, iswrite); if (done >= 0) *ppos += done; @@ -221,9 +285,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, if (bar == PCI_ROM_RESOURCE) pci_unmap_rom(pdev, io); out: - if (res->flags & IORESOURCE_MEM) - up_read(&vdev->memory_lock); - return done; } @@ -278,7 +339,12 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf, return ret; } - done = do_io_rw(iomem, buf, off, count, 0, 0, iswrite); + /* + * VGA MMIO is a legacy, non-BAR resource that hopefully allows + * probing, so we don't currently worry about access in relation + * to the memory enable bit in the command register. + */ + done = do_io_rw(vdev, false, iomem, buf, off, count, 0, 0, iswrite); vga_put(vdev->pdev, rsrc); @@ -296,17 +362,21 @@ static int vfio_pci_ioeventfd_handler(void *opaque, void *unused) switch (ioeventfd->count) { case 1: - vfio_iowrite8(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; case 2: - vfio_iowrite16(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; case 4: - vfio_iowrite32(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; #ifdef iowrite64 case 8: - vfio_iowrite64(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; #endif } @@ -378,11 +448,13 @@ long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset, goto out_unlock; } + ioeventfd->vdev = vdev; ioeventfd->addr = vdev->barmap[bar] + pos; ioeventfd->data = data; ioeventfd->pos = pos; ioeventfd->bar = bar; ioeventfd->count = count; + ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM; ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler, NULL, NULL, &ioeventfd->virqfd, fd); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 6990fc711a80..5fbf0c1f7433 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1424,13 +1424,16 @@ static int vfio_bus_type(struct device *dev, void *data) static int vfio_iommu_replay(struct vfio_iommu *iommu, struct vfio_domain *domain) { - struct vfio_domain *d; + struct vfio_domain *d = NULL; struct rb_node *n; unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; int ret; /* Arbitrarily pick the first domain in the list for lookups */ - d = list_first_entry(&iommu->domain_list, struct vfio_domain, next); + if (!list_empty(&iommu->domain_list)) + d = list_first_entry(&iommu->domain_list, + struct vfio_domain, next); + n = rb_first(&iommu->dma_list); for (; n; n = rb_next(n)) { @@ -1448,6 +1451,11 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, phys_addr_t p; dma_addr_t i; + if (WARN_ON(!d)) { /* mapped w/o a domain?! */ + ret = -EINVAL; + goto unwind; + } + phys = iommu_iova_to_phys(d->domain, iova); if (WARN_ON(!phys)) { @@ -1477,7 +1485,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, if (npage <= 0) { WARN_ON(!npage); ret = (int)npage; - return ret; + goto unwind; } phys = pfn << PAGE_SHIFT; @@ -1486,14 +1494,67 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, ret = iommu_map(domain->domain, iova, phys, size, dma->prot | domain->prot); - if (ret) - return ret; + if (ret) { + if (!dma->iommu_mapped) + vfio_unpin_pages_remote(dma, iova, + phys >> PAGE_SHIFT, + size >> PAGE_SHIFT, + true); + goto unwind; + } iova += size; } + } + + /* All dmas are now mapped, defer to second tree walk for unwind */ + for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + dma->iommu_mapped = true; } + return 0; + +unwind: + for (; n; n = rb_prev(n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + dma_addr_t iova; + + if (dma->iommu_mapped) { + iommu_unmap(domain->domain, dma->iova, dma->size); + continue; + } + + iova = dma->iova; + while (iova < dma->iova + dma->size) { + phys_addr_t phys, p; + size_t size; + dma_addr_t i; + + phys = iommu_iova_to_phys(domain->domain, iova); + if (!phys) { + iova += PAGE_SIZE; + continue; + } + + size = PAGE_SIZE; + p = phys + size; + i = iova + size; + while (i < dma->iova + dma->size && + p == iommu_iova_to_phys(domain->domain, i)) { + size += PAGE_SIZE; + p += PAGE_SIZE; + i += PAGE_SIZE; + } + + iommu_unmap(domain->domain, iova, size); + vfio_unpin_pages_remote(dma, iova, phys >> PAGE_SHIFT, + size >> PAGE_SHIFT, true); + } + } + + return ret; } /* @@ -2378,7 +2439,7 @@ static void *vfio_iommu_type1_open(unsigned long arg) break; case VFIO_TYPE1_NESTING_IOMMU: iommu->nesting = true; - /* fall through */ + fallthrough; case VFIO_TYPE1v2_IOMMU: iommu->v2 = true; break; diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c index 1f0ca6e44410..34aec4ba331e 100644 --- a/drivers/vhost/iotlb.c +++ b/drivers/vhost/iotlb.c @@ -159,8 +159,8 @@ vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last) EXPORT_SYMBOL_GPL(vhost_iotlb_itree_first); /** - * vhost_iotlb_itree_first - return the next overlapped range - * @iotlb: the IOTLB + * vhost_iotlb_itree_next - return the next overlapped range + * @map: the starting map node * @start: start of IOVA range * @end: end of IOVA range */ diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5857d4eec9d7..b45519ca66a7 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2537,7 +2537,7 @@ void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) { r = vhost_update_used_flags(vq); if (r) - vq_err(vq, "Failed to enable notification at %p: %d\n", + vq_err(vq, "Failed to disable notification at %p: %d\n", &vq->used->flags, r); } } diff --git a/drivers/video/backlight/adp8860_bl.c b/drivers/video/backlight/adp8860_bl.c index ddc7f5f0401f..8ec19425671f 100644 --- a/drivers/video/backlight/adp8860_bl.c +++ b/drivers/video/backlight/adp8860_bl.c @@ -681,7 +681,7 @@ static int adp8860_probe(struct i2c_client *client, switch (ADP8860_MANID(reg_val)) { case ADP8863_MANUFID: data->gdwn_dis = !!pdata->gdwn_dis; - /* fall through */ + fallthrough; case ADP8860_MANUFID: data->en_ambl_sens = !!pdata->en_ambl_sens; break; diff --git a/drivers/video/fbdev/acornfb.c b/drivers/video/fbdev/acornfb.c index 09a9ad901dad..bcc92aecf666 100644 --- a/drivers/video/fbdev/acornfb.c +++ b/drivers/video/fbdev/acornfb.c @@ -857,7 +857,7 @@ static void acornfb_parse_dram(char *opt) case 'M': case 'm': size *= 1024; - /* Fall through */ + fallthrough; case 'K': case 'k': size *= 1024; diff --git a/drivers/video/fbdev/arcfb.c b/drivers/video/fbdev/arcfb.c index 6f7838979f0a..ae3d8e8b8d33 100644 --- a/drivers/video/fbdev/arcfb.c +++ b/drivers/video/fbdev/arcfb.c @@ -419,7 +419,7 @@ static int arcfb_ioctl(struct fb_info *info, schedule(); finish_wait(&arcfb_waitq, &wait); } - /* fall through */ + fallthrough; case FBIO_GETCONTROL2: { diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c index 1e252192569a..bfd2f00b403b 100644 --- a/drivers/video/fbdev/atmel_lcdfb.c +++ b/drivers/video/fbdev/atmel_lcdfb.c @@ -508,7 +508,7 @@ static int atmel_lcdfb_check_var(struct fb_var_screeninfo *var, case 32: var->transp.offset = 24; var->transp.length = 8; - /* fall through */ + fallthrough; case 24: if (pdata->lcd_wiring_mode == ATMEL_LCDC_WIRING_RGB) { /* RGB:888 mode */ @@ -633,7 +633,7 @@ static int atmel_lcdfb_set_par(struct fb_info *info) case 2: value |= ATMEL_LCDC_PIXELSIZE_2; break; case 4: value |= ATMEL_LCDC_PIXELSIZE_4; break; case 8: value |= ATMEL_LCDC_PIXELSIZE_8; break; - case 15: /* fall through */ + case 15: case 16: value |= ATMEL_LCDC_PIXELSIZE_16; break; case 24: value |= ATMEL_LCDC_PIXELSIZE_24; break; case 32: value |= ATMEL_LCDC_PIXELSIZE_32; break; diff --git a/drivers/video/fbdev/aty/radeon_pm.c b/drivers/video/fbdev/aty/radeon_pm.c index 7c4483c7f313..f3d8123d7f36 100644 --- a/drivers/video/fbdev/aty/radeon_pm.c +++ b/drivers/video/fbdev/aty/radeon_pm.c @@ -1208,11 +1208,11 @@ static void radeon_pm_enable_dll_m10(struct radeonfb_info *rinfo) case 1: if (mc & 0x4) break; - /* fall through */ + fallthrough; case 2: dll_sleep_mask |= MDLL_R300_RDCK__MRDCKB_SLEEP; dll_reset_mask |= MDLL_R300_RDCK__MRDCKB_RESET; - /* fall through */ + fallthrough; case 0: dll_sleep_mask |= MDLL_R300_RDCK__MRDCKA_SLEEP; dll_reset_mask |= MDLL_R300_RDCK__MRDCKA_RESET; @@ -1221,7 +1221,7 @@ static void radeon_pm_enable_dll_m10(struct radeonfb_info *rinfo) case 1: if (!(mc & 0x4)) break; - /* fall through */ + fallthrough; case 2: dll_sleep_mask |= MDLL_R300_RDCK__MRDCKD_SLEEP; dll_reset_mask |= MDLL_R300_RDCK__MRDCKD_RESET; diff --git a/drivers/video/fbdev/cirrusfb.c b/drivers/video/fbdev/cirrusfb.c index 3df64a973194..15a9ee7cd734 100644 --- a/drivers/video/fbdev/cirrusfb.c +++ b/drivers/video/fbdev/cirrusfb.c @@ -1476,11 +1476,11 @@ static void init_vgachip(struct fb_info *info) mdelay(100); /* mode */ vga_wgfx(cinfo->regbase, CL_GR31, 0x00); - /* fall through */ + fallthrough; case BT_GD5480: /* from Klaus' NetBSD driver: */ vga_wgfx(cinfo->regbase, CL_GR2F, 0x00); - /* fall through */ + fallthrough; case BT_ALPINE: /* put blitter into 542x compat */ vga_wgfx(cinfo->regbase, CL_GR33, 0x00); diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c index 9c4f1be856ec..2df56bd303d2 100644 --- a/drivers/video/fbdev/controlfb.c +++ b/drivers/video/fbdev/controlfb.c @@ -49,6 +49,8 @@ #include <linux/cuda.h> #ifdef CONFIG_PPC_PMAC #include <asm/prom.h> +#endif +#ifdef CONFIG_BOOTX_TEXT #include <asm/btext.h> #endif @@ -713,7 +715,7 @@ static int controlfb_blank(int blank_mode, struct fb_info *info) break; case FB_BLANK_POWERDOWN: ctrl &= ~0x33; - /* fall through */ + fallthrough; case FB_BLANK_NORMAL: ctrl |= 0x400; break; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 8a31fc2b2258..66167830fefd 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2191,6 +2191,9 @@ static void updatescrollmode(struct fbcon_display *p, } } +#define PITCH(w) (((w) + 7) >> 3) +#define CALC_FONTSZ(h, p, c) ((h) * (p) * (c)) /* size = height * pitch * charcount */ + static int fbcon_resize(struct vc_data *vc, unsigned int width, unsigned int height, unsigned int user) { @@ -2200,6 +2203,24 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, struct fb_var_screeninfo var = info->var; int x_diff, y_diff, virt_w, virt_h, virt_fw, virt_fh; + if (ops->p && ops->p->userfont && FNTSIZE(vc->vc_font.data)) { + int size; + int pitch = PITCH(vc->vc_font.width); + + /* + * If user font, ensure that a possible change to user font + * height or width will not allow a font data out-of-bounds access. + * NOTE: must use original charcount in calculation as font + * charcount can change and cannot be used to determine the + * font data allocated size. + */ + if (pitch <= 0) + return -EINVAL; + size = CALC_FONTSZ(vc->vc_font.height, pitch, FNTCHARCNT(vc->vc_font.data)); + if (size > FNTSIZE(vc->vc_font.data)) + return -EINVAL; + } + virt_w = FBCON_SWAP(ops->rotate, width, height); virt_h = FBCON_SWAP(ops->rotate, height, width); virt_fw = FBCON_SWAP(ops->rotate, vc->vc_font.width, @@ -2652,7 +2673,7 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, int size; int i, csum; u8 *new_data, *data = font->data; - int pitch = (font->width+7) >> 3; + int pitch = PITCH(font->width); /* Is there a reason why fbconsole couldn't handle any charcount >256? * If not this check should be changed to charcount < 256 */ @@ -2668,7 +2689,7 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, if (fbcon_invalid_charcount(info, charcount)) return -EINVAL; - size = h * pitch * charcount; + size = CALC_FONTSZ(h, pitch, charcount); new_data = kmalloc(FONT_EXTRA_WORDS * sizeof(int) + size, GFP_USER); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index da7c88ffaa6a..6815bfb7f572 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1306,7 +1306,7 @@ static long fb_compat_ioctl(struct file *file, unsigned int cmd, case FBIOGET_CON2FBMAP: case FBIOPUT_CON2FBMAP: arg = (unsigned long) compat_ptr(arg); - /* fall through */ + fallthrough; case FBIOBLANK: ret = do_fb_ioctl(info, cmd, arg); break; diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 65491ae74808..e57c00824965 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -453,7 +453,7 @@ static int efifb_probe(struct platform_device *dev) info->apertures->ranges[0].base = efifb_fix.smem_start; info->apertures->ranges[0].size = size_remap; - if (efi_enabled(EFI_BOOT) && + if (efi_enabled(EFI_MEMMAP) && !efi_mem_desc_lookup(efifb_fix.smem_start, &md)) { if ((efifb_fix.smem_start + efifb_fix.smem_len) > (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) { diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c index 67ebfe5c9f1d..a547c21c7e92 100644 --- a/drivers/video/fbdev/fsl-diu-fb.c +++ b/drivers/video/fbdev/fsl-diu-fb.c @@ -1287,7 +1287,7 @@ static int fsl_diu_ioctl(struct fb_info *info, unsigned int cmd, dev_warn(info->dev, "MFB_SET_PIXFMT value of 0x%08x is deprecated.\n", MFB_SET_PIXFMT_OLD); - /* fall through */ + fallthrough; case MFB_SET_PIXFMT: if (copy_from_user(&pix_fmt, buf, sizeof(pix_fmt))) return -EFAULT; @@ -1297,7 +1297,7 @@ static int fsl_diu_ioctl(struct fb_info *info, unsigned int cmd, dev_warn(info->dev, "MFB_GET_PIXFMT value of 0x%08x is deprecated.\n", MFB_GET_PIXFMT_OLD); - /* fall through */ + fallthrough; case MFB_GET_PIXFMT: pix_fmt = ad->pix_fmt; if (copy_to_user(buf, &pix_fmt, sizeof(pix_fmt))) diff --git a/drivers/video/fbdev/gxt4500.c b/drivers/video/fbdev/gxt4500.c index 13ded3a10708..e5475ae1e158 100644 --- a/drivers/video/fbdev/gxt4500.c +++ b/drivers/video/fbdev/gxt4500.c @@ -534,7 +534,7 @@ static int gxt4500_setcolreg(unsigned int reg, unsigned int red, break; case DFA_PIX_32BIT: val |= (reg << 24); - /* fall through */ + fallthrough; case DFA_PIX_24BIT: val |= (reg << 16) | (reg << 8); break; diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index e4c3c8b65da4..02411d89cb46 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -648,13 +648,13 @@ static int synthvid_connect_vsp(struct hv_device *hdev) ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN10); if (!ret) break; - /* Fallthrough */ + fallthrough; case VERSION_WIN8: case VERSION_WIN8_1: ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN8); if (!ret) break; - /* Fallthrough */ + fallthrough; case VERSION_WS2008: case VERSION_WIN7: ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN7); diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c index c65ec7386e87..e6f35f8feefc 100644 --- a/drivers/video/fbdev/i740fb.c +++ b/drivers/video/fbdev/i740fb.c @@ -430,7 +430,7 @@ static int i740fb_decode_var(const struct fb_var_screeninfo *var, break; case 9 ... 15: bpp = 15; - /* fall through */ + fallthrough; case 16: if ((1000000 / var->pixclock) > DACSPEED16) { dev_err(info->device, "requested pixclock %i MHz out of range (max. %i MHz at 15/16bpp)\n", diff --git a/drivers/video/fbdev/mmp/fb/mmpfb.c b/drivers/video/fbdev/mmp/fb/mmpfb.c index 01c75c031cb6..39ebbe026ddf 100644 --- a/drivers/video/fbdev/mmp/fb/mmpfb.c +++ b/drivers/video/fbdev/mmp/fb/mmpfb.c @@ -90,8 +90,6 @@ static int var_to_pixfmt(struct fb_var_screeninfo *var) else return PIXFMT_BGR888UNPACK; } - - /* fall through */ } return -EINVAL; diff --git a/drivers/video/fbdev/nvidia/nv_hw.c b/drivers/video/fbdev/nvidia/nv_hw.c index 8335da4ca30e..9b0a324bb1b4 100644 --- a/drivers/video/fbdev/nvidia/nv_hw.c +++ b/drivers/video/fbdev/nvidia/nv_hw.c @@ -896,7 +896,7 @@ void NVCalcStateExt(struct nvidia_par *par, if (!par->FlatPanel) state->control = NV_RD32(par->PRAMDAC0, 0x0580) & 0xeffffeff; - /* fallthrough */ + fallthrough; case NV_ARCH_10: case NV_ARCH_20: case NV_ARCH_30: diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c index 5cd0f5f6a4ae..4501e848a36f 100644 --- a/drivers/video/fbdev/offb.c +++ b/drivers/video/fbdev/offb.c @@ -141,7 +141,7 @@ static int offb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, /* Clear PALETTE_ACCESS_CNTL in DAC_CNTL */ out_le32(par->cmap_adr + 0x58, in_le32(par->cmap_adr + 0x58) & ~0x20); - /* fall through */ + fallthrough; case cmap_r128: /* Set palette index & data */ out_8(par->cmap_adr + 0xb0, regno); @@ -211,7 +211,7 @@ static int offb_blank(int blank, struct fb_info *info) /* Clear PALETTE_ACCESS_CNTL in DAC_CNTL */ out_le32(par->cmap_adr + 0x58, in_le32(par->cmap_adr + 0x58) & ~0x20); - /* fall through */ + fallthrough; case cmap_r128: /* Set palette index & data */ out_8(par->cmap_adr + 0xb0, i); diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c index fa73acfc1371..7317c9aad677 100644 --- a/drivers/video/fbdev/omap/lcdc.c +++ b/drivers/video/fbdev/omap/lcdc.c @@ -328,13 +328,13 @@ static int omap_lcdc_setup_plane(int plane, int channel_out, lcdc.bpp = 12; break; } - /* fallthrough */ + fallthrough; case OMAPFB_COLOR_YUV422: if (lcdc.ext_mode) { lcdc.bpp = 16; break; } - /* fallthrough */ + fallthrough; default: /* FIXME: other BPPs. * bpp1: code 0, size 256 diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c index 0cbcc74fa943..3d090d2d9ed9 100644 --- a/drivers/video/fbdev/omap/omapfb_main.c +++ b/drivers/video/fbdev/omap/omapfb_main.c @@ -253,7 +253,7 @@ static int _setcolreg(struct fb_info *info, u_int regno, u_int red, u_int green, if (fbdev->ctrl->setcolreg) r = fbdev->ctrl->setcolreg(regno, red, green, blue, transp, update_hw_pal); - /* Fallthrough */ + fallthrough; case OMAPFB_COLOR_RGB565: case OMAPFB_COLOR_RGB444: if (r != 0) @@ -443,7 +443,7 @@ static int set_color_mode(struct omapfb_plane_struct *plane, return 0; case 12: var->bits_per_pixel = 16; - /* fall through */ + fallthrough; case 16: if (plane->fbdev->panel->bpp == 12) plane->color_mode = OMAPFB_COLOR_RGB444; @@ -1531,27 +1531,27 @@ static void omapfb_free_resources(struct omapfb_device *fbdev, int state) case OMAPFB_ACTIVE: for (i = 0; i < fbdev->mem_desc.region_cnt; i++) unregister_framebuffer(fbdev->fb_info[i]); - /* fall through */ + fallthrough; case 7: omapfb_unregister_sysfs(fbdev); - /* fall through */ + fallthrough; case 6: if (fbdev->panel->disable) fbdev->panel->disable(fbdev->panel); - /* fall through */ + fallthrough; case 5: omapfb_set_update_mode(fbdev, OMAPFB_UPDATE_DISABLED); - /* fall through */ + fallthrough; case 4: planes_cleanup(fbdev); - /* fall through */ + fallthrough; case 3: ctrl_cleanup(fbdev); - /* fall through */ + fallthrough; case 2: if (fbdev->panel->cleanup) fbdev->panel->cleanup(fbdev->panel); - /* fall through */ + fallthrough; case 1: dev_set_drvdata(fbdev->dev, NULL); kfree(fbdev); @@ -1854,7 +1854,7 @@ static int __init omapfb_setup(char *options) case 'm': case 'M': vram *= 1024; - /* Fall through */ + fallthrough; case 'k': case 'K': vram *= 1024; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c index 3920a0db0390..b2d6e6df2161 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c @@ -1861,7 +1861,7 @@ static void calc_vrfb_rotation_offset(u8 rotation, bool mirror, if (color_mode == OMAP_DSS_COLOR_YUV2 || color_mode == OMAP_DSS_COLOR_UYVY) width = width >> 1; - /* fall through */ + fallthrough; case OMAP_DSS_ROT_90: case OMAP_DSS_ROT_270: *offset1 = 0; @@ -1884,7 +1884,7 @@ static void calc_vrfb_rotation_offset(u8 rotation, bool mirror, if (color_mode == OMAP_DSS_COLOR_YUV2 || color_mode == OMAP_DSS_COLOR_UYVY) width = width >> 1; - /* fall through */ + fallthrough; case OMAP_DSS_ROT_90 + 4: case OMAP_DSS_ROT_270 + 4: *offset1 = 0; diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c index f40be68d5aac..ea8c88aa4477 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c @@ -760,7 +760,7 @@ int omapfb_ioctl(struct fb_info *fbi, unsigned int cmd, unsigned long arg) r = -ENODEV; break; } - /* FALLTHROUGH */ + fallthrough; case OMAPFB_WAITFORVSYNC: DBG("ioctl WAITFORVSYNC\n"); diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c index 836e7b1639ce..a3decc7fadde 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c @@ -882,7 +882,7 @@ int omapfb_setup_overlay(struct fb_info *fbi, struct omap_overlay *ovl, / (var->bits_per_pixel >> 2); break; } - /* fall through */ + fallthrough; default: screen_width = fix->line_length / (var->bits_per_pixel >> 3); break; diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c index c7c98d8e2359..0642555289e0 100644 --- a/drivers/video/fbdev/pm2fb.c +++ b/drivers/video/fbdev/pm2fb.c @@ -233,10 +233,10 @@ static u32 to3264(u32 timing, int bpp, int is64) switch (bpp) { case 24: timing *= 3; - /* fall through */ + fallthrough; case 8: timing >>= 1; - /* fall through */ + fallthrough; case 16: timing >>= 1; case 32: diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c index eedfbd3572a8..47e6a1d0d229 100644 --- a/drivers/video/fbdev/pxa168fb.c +++ b/drivers/video/fbdev/pxa168fb.c @@ -60,8 +60,6 @@ static int determine_best_pix_fmt(struct fb_var_screeninfo *var) else return PIX_FMT_BGR1555; } - - /* fall through */ } /* @@ -87,8 +85,6 @@ static int determine_best_pix_fmt(struct fb_var_screeninfo *var) else return PIX_FMT_BGR888UNPACK; } - - /* fall through */ } return -EINVAL; diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index a53d24fb7183..f1551e00eb12 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -1614,7 +1614,7 @@ static void set_ctrlr_state(struct pxafb_info *fbi, u_int state) */ if (old_state != C_DISABLE_PM) break; - /* fall through */ + fallthrough; case C_ENABLE: /* diff --git a/drivers/video/fbdev/riva/fbdev.c b/drivers/video/fbdev/riva/fbdev.c index 9b3493846f4d..ce55b9d2e862 100644 --- a/drivers/video/fbdev/riva/fbdev.c +++ b/drivers/video/fbdev/riva/fbdev.c @@ -1093,7 +1093,7 @@ static int rivafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) break; case 9 ... 15: var->green.length = 5; - /* fall through */ + fallthrough; case 16: var->bits_per_pixel = 16; /* The Riva128 supports RGB555 only */ diff --git a/drivers/video/fbdev/s3c-fb.c b/drivers/video/fbdev/s3c-fb.c index 9dc925054930..ba316bd56efd 100644 --- a/drivers/video/fbdev/s3c-fb.c +++ b/drivers/video/fbdev/s3c-fb.c @@ -284,7 +284,7 @@ static int s3c_fb_check_var(struct fb_var_screeninfo *var, /* 666 with one bit alpha/transparency */ var->transp.offset = 18; var->transp.length = 1; - /* fall through */ + fallthrough; case 18: var->bits_per_pixel = 32; @@ -312,7 +312,7 @@ static int s3c_fb_check_var(struct fb_var_screeninfo *var, case 25: var->transp.length = var->bits_per_pixel - 24; var->transp.offset = 24; - /* fall through */ + fallthrough; case 24: /* our 24bpp is unpacked, so 32bpp */ var->bits_per_pixel = 32; @@ -809,7 +809,7 @@ static int s3c_fb_blank(int blank_mode, struct fb_info *info) case FB_BLANK_POWERDOWN: wincon &= ~WINCONx_ENWIN; sfb->enabled &= ~(1 << index); - /* fall through - to FB_BLANK_NORMAL */ + fallthrough; /* to FB_BLANK_NORMAL */ case FB_BLANK_NORMAL: /* disable the DMA and display 0x0 (black) */ diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c index bda6cc313c8b..e31cf63b0a62 100644 --- a/drivers/video/fbdev/sa1100fb.c +++ b/drivers/video/fbdev/sa1100fb.c @@ -935,7 +935,7 @@ static void set_ctrlr_state(struct sa1100fb_info *fbi, u_int state) */ if (old_state != C_DISABLE_PM) break; - /* fall through */ + fallthrough; case C_ENABLE: /* diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c index 3fd87aeb6c79..a2442aae7e12 100644 --- a/drivers/video/fbdev/savage/savagefb_driver.c +++ b/drivers/video/fbdev/savage/savagefb_driver.c @@ -1860,7 +1860,7 @@ static int savage_init_hw(struct savagefb_par *par) if ((vga_in8(0x3d5, par) & 0xC0) == (0x01 << 6)) RamSavage4[1] = 8; - /*FALLTHROUGH*/ + fallthrough; case S3_SAVAGE2000: videoRam = RamSavage4[(config1 & 0xE0) >> 5] * 1024; diff --git a/drivers/video/fbdev/sh_mobile_lcdcfb.c b/drivers/video/fbdev/sh_mobile_lcdcfb.c index 8a27d12e6ea8..c1043420dbd3 100644 --- a/drivers/video/fbdev/sh_mobile_lcdcfb.c +++ b/drivers/video/fbdev/sh_mobile_lcdcfb.c @@ -1594,7 +1594,7 @@ sh_mobile_lcdc_overlay_fb_init(struct sh_mobile_lcdc_overlay *ovl) case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: info->fix.ypanstep = 2; - /* Fall through */ + fallthrough; case V4L2_PIX_FMT_NV16: case V4L2_PIX_FMT_NV61: info->fix.xpanstep = 2; @@ -2085,7 +2085,7 @@ sh_mobile_lcdc_channel_fb_init(struct sh_mobile_lcdc_chan *ch, case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: info->fix.ypanstep = 2; - /* Fall through */ + fallthrough; case V4L2_PIX_FMT_NV16: case V4L2_PIX_FMT_NV61: info->fix.xpanstep = 2; diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index ac140962b1bf..03c736f6f3d0 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -1739,7 +1739,7 @@ static int sisfb_ioctl(struct fb_info *info, unsigned int cmd, if(ivideo->warncount++ < 10) printk(KERN_INFO "sisfb: Deprecated ioctl call received - update your application!\n"); - /* fall through */ + fallthrough; case SISFB_GET_INFO: /* For communication with X driver */ ivideo->sisfb_infoblock.sisfb_id = SISFB_ID; ivideo->sisfb_infoblock.sisfb_version = VER_MAJOR; @@ -1793,7 +1793,7 @@ static int sisfb_ioctl(struct fb_info *info, unsigned int cmd, if(ivideo->warncount++ < 10) printk(KERN_INFO "sisfb: Deprecated ioctl call received - update your application!\n"); - /* fall through */ + fallthrough; case SISFB_GET_VBRSTATUS: if(sisfb_CheckVBRetrace(ivideo)) return put_user((u32)1, argp); @@ -1804,7 +1804,7 @@ static int sisfb_ioctl(struct fb_info *info, unsigned int cmd, if(ivideo->warncount++ < 10) printk(KERN_INFO "sisfb: Deprecated ioctl call received - update your application!\n"); - /* fall through */ + fallthrough; case SISFB_GET_AUTOMAXIMIZE: if(ivideo->sisfb_max) return put_user((u32)1, argp); @@ -1815,7 +1815,7 @@ static int sisfb_ioctl(struct fb_info *info, unsigned int cmd, if(ivideo->warncount++ < 10) printk(KERN_INFO "sisfb: Deprecated ioctl call received - update your application!\n"); - /* fall through */ + fallthrough; case SISFB_SET_AUTOMAXIMIZE: if(get_user(gpu32, argp)) return -EFAULT; diff --git a/drivers/video/fbdev/sm501fb.c b/drivers/video/fbdev/sm501fb.c index 3dd1b1d76e98..6a52eba64559 100644 --- a/drivers/video/fbdev/sm501fb.c +++ b/drivers/video/fbdev/sm501fb.c @@ -1005,7 +1005,7 @@ static int sm501fb_blank_crt(int blank_mode, struct fb_info *info) case FB_BLANK_POWERDOWN: ctrl &= ~SM501_DC_CRT_CONTROL_ENABLE; sm501_misc_control(fbi->dev->parent, SM501_MISC_DAC_POWER, 0); - /* fall through */ + fallthrough; case FB_BLANK_NORMAL: ctrl |= SM501_DC_CRT_CONTROL_BLANK; diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index de953ddb6312..265865610edc 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -999,7 +999,7 @@ stifb_blank(int blank_mode, struct fb_info *info) case S9000_ID_HCRX: HYPER_ENABLE_DISABLE_DISPLAY(fb, enable); break; - case S9000_ID_A1659A: /* fall through */ + case S9000_ID_A1659A: case S9000_ID_TIMBER: case CRX24_OVERLAY_PLANES: default: @@ -1157,7 +1157,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) dev_name); goto out_err0; } - /* fall through */ + fallthrough; case S9000_ID_ARTIST: case S9000_ID_HCRX: case S9000_ID_TIMBER: diff --git a/drivers/video/fbdev/tdfxfb.c b/drivers/video/fbdev/tdfxfb.c index f73e26c18c09..f056d80f6359 100644 --- a/drivers/video/fbdev/tdfxfb.c +++ b/drivers/video/fbdev/tdfxfb.c @@ -523,7 +523,7 @@ static int tdfxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) case 32: var->transp.offset = 24; var->transp.length = 8; - /* fall through */ + fallthrough; case 24: var->red.offset = 16; var->green.offset = 8; diff --git a/drivers/video/fbdev/via/lcd.c b/drivers/video/fbdev/via/lcd.c index 3fea01db58d6..4a869402d120 100644 --- a/drivers/video/fbdev/via/lcd.c +++ b/drivers/video/fbdev/via/lcd.c @@ -744,7 +744,7 @@ static void set_lcd_output_path(int set_iga, int output_interface) viaparinfo->chip_info->gfx_chip_name)) viafb_write_reg_mask(CR97, VIACR, 0x84, BIT7 + BIT2 + BIT1 + BIT0); - /* fall through */ + fallthrough; case INTERFACE_DVP0: case INTERFACE_DVP1: case INTERFACE_DFP_HIGH: diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c index 00307b8693bf..5ec51445bee8 100644 --- a/drivers/video/fbdev/xen-fbfront.c +++ b/drivers/video/fbdev/xen-fbfront.c @@ -677,7 +677,7 @@ static void xenfb_backend_changed(struct xenbus_device *dev, case XenbusStateClosed: if (dev->state == XenbusStateClosed) break; - /* fall through - Missed the backend's CLOSING state. */ + fallthrough; /* Missed the backend's CLOSING state */ case XenbusStateClosing: xenbus_frontend_closed(dev); break; diff --git a/drivers/watchdog/sc1200wdt.c b/drivers/watchdog/sc1200wdt.c index 9673eb12dacd..f22ebe89fe13 100644 --- a/drivers/watchdog/sc1200wdt.c +++ b/drivers/watchdog/sc1200wdt.c @@ -234,7 +234,7 @@ static long sc1200wdt_ioctl(struct file *file, unsigned int cmd, return -EINVAL; timeout = new_timeout; sc1200wdt_write_data(WDTO, timeout); - /* fall through - and return the new timeout */ + fallthrough; /* and return the new timeout */ case WDIOC_GETTIMEOUT: return put_user(timeout * 60, p); diff --git a/drivers/watchdog/wdrtas.c b/drivers/watchdog/wdrtas.c index 184a06a74f83..c00627825de8 100644 --- a/drivers/watchdog/wdrtas.c +++ b/drivers/watchdog/wdrtas.c @@ -332,7 +332,7 @@ static long wdrtas_ioctl(struct file *file, unsigned int cmd, wdrtas_interval = i; else wdrtas_interval = wdrtas_get_interval(i); - /* fallthrough */ + fallthrough; case WDIOC_GETTIMEOUT: return put_user(wdrtas_interval, argp); diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 140c7bf33a98..90b8f56fbadb 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -156,7 +156,7 @@ int get_evtchn_to_irq(evtchn_port_t evtchn) /* Get info for IRQ */ struct irq_info *info_for_irq(unsigned irq) { - return irq_get_handler_data(irq); + return irq_get_chip_data(irq); } /* Constructors for packed IRQ information. */ @@ -377,7 +377,7 @@ static void xen_irq_init(unsigned irq) info->type = IRQT_UNBOUND; info->refcnt = -1; - irq_set_handler_data(irq, info); + irq_set_chip_data(irq, info); list_add_tail(&info->list, &xen_irq_list_head); } @@ -426,14 +426,14 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi) static void xen_free_irq(unsigned irq) { - struct irq_info *info = irq_get_handler_data(irq); + struct irq_info *info = irq_get_chip_data(irq); if (WARN_ON(!info)) return; list_del(&info->list); - irq_set_handler_data(irq, NULL); + irq_set_chip_data(irq, NULL); WARN_ON(info->refcnt > 0); @@ -603,7 +603,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi); static void __unbind_from_irq(unsigned int irq) { evtchn_port_t evtchn = evtchn_from_irq(irq); - struct irq_info *info = irq_get_handler_data(irq); + struct irq_info *info = irq_get_chip_data(irq); if (info->refcnt > 0) { info->refcnt--; @@ -1108,7 +1108,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, void unbind_from_irqhandler(unsigned int irq, void *dev_id) { - struct irq_info *info = irq_get_handler_data(irq); + struct irq_info *info = irq_get_chip_data(irq); if (WARN_ON(!info)) return; @@ -1142,7 +1142,7 @@ int evtchn_make_refcounted(evtchn_port_t evtchn) if (irq == -1) return -ENOENT; - info = irq_get_handler_data(irq); + info = irq_get_chip_data(irq); if (!info) return -ENOENT; @@ -1170,7 +1170,7 @@ int evtchn_get(evtchn_port_t evtchn) if (irq == -1) goto done; - info = irq_get_handler_data(irq); + info = irq_get_chip_data(irq); if (!info) goto done; diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index b43b5595e988..72d725a0ab5c 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -1263,7 +1263,7 @@ static void pvcalls_front_changed(struct xenbus_device *dev, if (dev->state == XenbusStateClosed) break; /* Missed the backend's CLOSING state */ - /* fall through */ + fallthrough; case XenbusStateClosing: xenbus_frontend_closed(dev); break; diff --git a/drivers/xen/xen-acpi-memhotplug.c b/drivers/xen/xen-acpi-memhotplug.c index 7457213b8915..f914b72557ef 100644 --- a/drivers/xen/xen-acpi-memhotplug.c +++ b/drivers/xen/xen-acpi-memhotplug.c @@ -229,7 +229,7 @@ static void acpi_memory_device_notify(acpi_handle handle, u32 event, void *data) case ACPI_NOTIFY_BUS_CHECK: ACPI_DEBUG_PRINT((ACPI_DB_INFO, "\nReceived BUS CHECK notification for device\n")); - /* Fall Through */ + fallthrough; case ACPI_NOTIFY_DEVICE_CHECK: if (event == ACPI_NOTIFY_DEVICE_CHECK) ACPI_DEBUG_PRINT((ACPI_DB_INFO, diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index f2115587855f..b500466a6c37 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -545,7 +545,7 @@ static void xen_pcibk_frontend_changed(struct xenbus_device *xdev, xenbus_switch_state(xdev, XenbusStateClosed); if (xenbus_dev_is_online(xdev)) break; - /* fall through - if not online */ + fallthrough; /* if not online */ case XenbusStateUnknown: dev_dbg(&xdev->dev, "frontend is gone! unregister device\n"); device_unregister(&xdev->dev); diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 75c0a2e9a6db..1e8cfd80a4e6 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1185,7 +1185,7 @@ static void scsiback_frontend_changed(struct xenbus_device *dev, xenbus_switch_state(dev, XenbusStateClosed); if (xenbus_dev_is_online(dev)) break; - /* fall through - if not online */ + fallthrough; /* if not online */ case XenbusStateUnknown: device_unregister(&dev->dev); break; diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 786fbb7d8be0..907bcbb93afb 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -379,8 +379,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, int i, j; for (i = 0; i < nr_pages; i++) { - err = gnttab_grant_foreign_access(dev->otherend_id, - virt_to_gfn(vaddr), 0); + unsigned long gfn; + + if (is_vmalloc_addr(vaddr)) + gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr)); + else + gfn = virt_to_gfn(vaddr); + + err = gnttab_grant_foreign_access(dev->otherend_id, gfn, 0); if (err < 0) { xenbus_dev_fatal(dev, err, "granting access to ring page"); diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index 15379089853b..480944606a3c 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -401,12 +401,12 @@ static void xenbus_reset_frontend(char *fe, char *be, int be_state) case XenbusStateConnected: xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosing); xenbus_reset_wait_for_backend(be, XenbusStateClosing); - /* fall through */ + fallthrough; case XenbusStateClosing: xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosed); xenbus_reset_wait_for_backend(be, XenbusStateClosed); - /* fall through */ + fallthrough; case XenbusStateClosed: xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateInitialising); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 92cd1d80218d..3576123d8299 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -213,7 +213,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) break; default: WARN_ONCE(1, "unknown lock status code: %d\n", status); - /* fall through */ + fallthrough; case P9_LOCK_ERROR: case P9_LOCK_GRACE: res = -ENOLCK; diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c index 30d526fecc3f..05e963402e25 100644 --- a/fs/adfs/dir_f.c +++ b/fs/adfs/dir_f.c @@ -18,11 +18,11 @@ static inline unsigned int adfs_readval(unsigned char *p, int len) switch (len) { case 4: val |= p[3] << 24; - /* fall through */ + fallthrough; case 3: val |= p[2] << 16; - /* fall through */ + fallthrough; case 2: val |= p[1] << 8; - /* fall through */ + fallthrough; default: val |= p[0]; } return val; @@ -32,11 +32,11 @@ static inline void adfs_writeval(unsigned char *p, int len, unsigned int val) { switch (len) { case 4: p[3] = val >> 24; - /* fall through */ + fallthrough; case 3: p[2] = val >> 16; - /* fall through */ + fallthrough; case 2: p[1] = val >> 8; - /* fall through */ + fallthrough; default: p[0] = val; } } diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index f708c45d5f66..29f11e10a7c7 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -420,24 +420,51 @@ affs_mode_to_prot(struct inode *inode) u32 prot = AFFS_I(inode)->i_protect; umode_t mode = inode->i_mode; + /* + * First, clear all RWED bits for owner, group, other. + * Then, recalculate them afresh. + * + * We'll always clear the delete-inhibit bit for the owner, as that is + * the classic single-user mode AmigaOS protection bit and we need to + * stay compatible with all scenarios. + * + * Since multi-user AmigaOS is an extension, we'll only set the + * delete-allow bit if any of the other bits in the same user class + * (group/other) are used. + */ + prot &= ~(FIBF_NOEXECUTE | FIBF_NOREAD + | FIBF_NOWRITE | FIBF_NODELETE + | FIBF_GRP_EXECUTE | FIBF_GRP_READ + | FIBF_GRP_WRITE | FIBF_GRP_DELETE + | FIBF_OTR_EXECUTE | FIBF_OTR_READ + | FIBF_OTR_WRITE | FIBF_OTR_DELETE); + + /* Classic single-user AmigaOS flags. These are inverted. */ if (!(mode & 0100)) prot |= FIBF_NOEXECUTE; if (!(mode & 0400)) prot |= FIBF_NOREAD; if (!(mode & 0200)) prot |= FIBF_NOWRITE; + + /* Multi-user extended flags. Not inverted. */ if (mode & 0010) prot |= FIBF_GRP_EXECUTE; if (mode & 0040) prot |= FIBF_GRP_READ; if (mode & 0020) prot |= FIBF_GRP_WRITE; + if (mode & 0070) + prot |= FIBF_GRP_DELETE; + if (mode & 0001) prot |= FIBF_OTR_EXECUTE; if (mode & 0004) prot |= FIBF_OTR_READ; if (mode & 0002) prot |= FIBF_OTR_WRITE; + if (mode & 0007) + prot |= FIBF_OTR_DELETE; AFFS_I(inode)->i_protect = prot; } diff --git a/fs/affs/file.c b/fs/affs/file.c index a26a0f96c119..d91b0133d95d 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -429,6 +429,24 @@ static int affs_write_begin(struct file *file, struct address_space *mapping, return ret; } +static int affs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned int len, unsigned int copied, + struct page *page, void *fsdata) +{ + struct inode *inode = mapping->host; + int ret; + + ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + + /* Clear Archived bit on file writes, as AmigaOS would do */ + if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { + AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED; + mark_inode_dirty(inode); + } + + return ret; +} + static sector_t _affs_bmap(struct address_space *mapping, sector_t block) { return generic_block_bmap(mapping,block,affs_get_block); @@ -438,7 +456,7 @@ const struct address_space_operations affs_aops = { .readpage = affs_readpage, .writepage = affs_writepage, .write_begin = affs_write_begin, - .write_end = generic_write_end, + .write_end = affs_write_end, .direct_IO = affs_direct_IO, .bmap = _affs_bmap }; @@ -795,6 +813,12 @@ done: if (tmp > inode->i_size) inode->i_size = AFFS_I(inode)->mmu_private = tmp; + /* Clear Archived bit on file writes, as AmigaOS would do */ + if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { + AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED; + mark_inode_dirty(inode); + } + err_first_bh: unlock_page(page); put_page(page); diff --git a/fs/affs/inode.c b/fs/affs/inode.c index a346cf7659f1..044412110b52 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -93,7 +93,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) case ST_ROOT: inode->i_uid = sbi->s_uid; inode->i_gid = sbi->s_gid; - /* fall through */ + fallthrough; case ST_USERDIR: if (be32_to_cpu(tail->stype) == ST_USERDIR || affs_test_opt(sbi->s_flags, SF_SETMODE)) { diff --git a/fs/affs/super.c b/fs/affs/super.c index 47107c6712a6..a100cd9950c8 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -474,7 +474,7 @@ got_root: case MUFS_INTLFFS: case MUFS_DCFFS: affs_set_opt(sbi->s_flags, SF_MUFS); - /* fall thru */ + fallthrough; case FS_INTLFFS: case FS_DCFFS: affs_set_opt(sbi->s_flags, SF_INTL); @@ -486,7 +486,7 @@ got_root: break; case MUFS_OFS: affs_set_opt(sbi->s_flags, SF_MUFS); - /* fall through */ + fallthrough; case FS_OFS: affs_set_opt(sbi->s_flags, SF_OFS); sb->s_flags |= SB_NOEXEC; @@ -494,7 +494,7 @@ got_root: case MUFS_DCOFS: case MUFS_INTLOFS: affs_set_opt(sbi->s_flags, SF_MUFS); - /* fall through */ + fallthrough; case FS_DCOFS: case FS_INTLOFS: affs_set_opt(sbi->s_flags, SF_INTL); diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index bef413818af7..a4e9e6e07e93 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -252,7 +252,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) call->unmarshall++; /* extract the FID array and its count in two steps */ - /* fall through */ + fallthrough; case 1: _debug("extract FID count"); ret = afs_extract_data(call, true); @@ -271,7 +271,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) afs_extract_to_buf(call, call->count * 3 * 4); call->unmarshall++; - /* Fall through */ + fallthrough; case 2: _debug("extract FID array"); ret = afs_extract_data(call, true); @@ -297,7 +297,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) call->unmarshall++; /* extract the callback array and its count in two steps */ - /* fall through */ + fallthrough; case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -312,7 +312,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) iov_iter_discard(&call->def_iter, READ, call->count2 * 3 * 4); call->unmarshall++; - /* Fall through */ + fallthrough; case 4: _debug("extract discard %zu/%u", iov_iter_count(call->iter), call->count2 * 3 * 4); @@ -391,7 +391,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) afs_extract_to_buf(call, 11 * sizeof(__be32)); call->unmarshall++; - /* Fall through */ + fallthrough; case 1: _debug("extract UUID"); ret = afs_extract_data(call, false); @@ -503,7 +503,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) afs_extract_to_buf(call, 11 * sizeof(__be32)); call->unmarshall++; - /* Fall through */ + fallthrough; case 1: _debug("extract UUID"); ret = afs_extract_data(call, false); @@ -618,7 +618,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call) call->unmarshall++; /* extract the FID array and its count in two steps */ - /* Fall through */ + fallthrough; case 1: _debug("extract FID count"); ret = afs_extract_data(call, true); @@ -637,7 +637,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call) afs_extract_to_buf(call, size); call->unmarshall++; - /* Fall through */ + fallthrough; case 2: _debug("extract FID array"); ret = afs_extract_data(call, false); diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index b79879aacc02..7b784af604fd 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -382,15 +382,17 @@ void afs_dynroot_depopulate(struct super_block *sb) net->dynroot_sb = NULL; mutex_unlock(&net->proc_cells_lock); - inode_lock(root->d_inode); - - /* Remove all the pins for dirs created for manually added cells */ - list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { - if (subdir->d_fsdata) { - subdir->d_fsdata = NULL; - dput(subdir); + if (root) { + inode_lock(root->d_inode); + + /* Remove all the pins for dirs created for manually added cells */ + list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { + if (subdir->d_fsdata) { + subdir->d_fsdata = NULL; + dput(subdir); + } } - } - inode_unlock(root->d_inode); + inode_unlock(root->d_inode); + } } diff --git a/fs/afs/file.c b/fs/afs/file.c index 6f6ed1605cfe..371d1488cc54 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -311,7 +311,7 @@ int afs_page_filler(void *data, struct page *page) case -ENOBUFS: _debug("cache said ENOBUFS"); - /* fall through */ + fallthrough; default: go_on: req = kzalloc(struct_size(req, array, 1), GFP_KERNEL); diff --git a/fs/afs/flock.c b/fs/afs/flock.c index ffb8575345ca..cb3054c7843e 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -376,7 +376,6 @@ again: spin_unlock(&vnode->lock); return; - /* Fall through */ default: /* Looks like a lock request was withdrawn. */ spin_unlock(&vnode->lock); diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c index 24fd163c6323..97cab12b0a6c 100644 --- a/fs/afs/fs_operation.c +++ b/fs/afs/fs_operation.c @@ -235,6 +235,7 @@ int afs_put_operation(struct afs_operation *op) afs_end_cursor(&op->ac); afs_put_serverlist(op->net, op->server_list); afs_put_volume(op->net, op->volume, afs_volume_trace_put_put_op); + key_put(op->key); kfree(op); return ret; } diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 5d9ef517cf81..e7e98ad63a91 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -161,8 +161,8 @@ responded: } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; server->rtt = rtt_us; alist->preferred = index; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index acb4d0ca2649..1d95ed9dd86e 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -320,7 +320,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->tmp_u = htonl(0); afs_extract_to_tmp(call); } - /* Fall through */ + fallthrough; /* extract the returned data length */ case 1: @@ -348,7 +348,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->bvec[0].bv_page = req->pages[req->index]; iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); - /* Fall through */ + fallthrough; /* extract the returned data */ case 2: @@ -375,7 +375,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) /* Discard any excess data the server gave us */ afs_extract_discard(call, req->actual_len - req->len); call->unmarshall = 3; - /* Fall through */ + fallthrough; case 3: _debug("extract discard %zu/%llu", @@ -388,7 +388,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) no_more_data: call->unmarshall = 4; afs_extract_to_buf(call, (21 + 3 + 6) * 4); - /* Fall through */ + fallthrough; /* extract the metadata */ case 4: @@ -1343,7 +1343,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) case 0: call->unmarshall++; afs_extract_to_buf(call, 12 * 4); - /* Fall through */ + fallthrough; /* extract the returned status record */ case 1: @@ -1356,7 +1356,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) xdr_decode_AFSFetchVolumeStatus(&bp, &op->volstatus.vs); call->unmarshall++; afs_extract_to_tmp(call); - /* Fall through */ + fallthrough; /* extract the volume name length */ case 2: @@ -1371,7 +1371,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the volume name */ case 3: @@ -1385,7 +1385,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the offline message length */ case 4: @@ -1400,7 +1400,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the offline message */ case 5: @@ -1415,7 +1415,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the message of the day length */ case 6: @@ -1430,7 +1430,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the message of the day */ case 7: @@ -1682,7 +1682,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* Extract the capabilities word count */ case 1: @@ -1696,7 +1696,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) call->count2 = count; afs_extract_discard(call, count * sizeof(__be32)); call->unmarshall++; - /* Fall through */ + fallthrough; /* Extract capabilities words */ case 2: @@ -1776,7 +1776,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* Extract the file status count and array in two steps */ case 1: @@ -1794,7 +1794,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_counts: afs_extract_to_buf(call, 21 * sizeof(__be32)); - /* Fall through */ + fallthrough; case 2: _debug("extract status array %u", call->count); @@ -1824,7 +1824,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->count = 0; call->unmarshall++; afs_extract_to_tmp(call); - /* Fall through */ + fallthrough; /* Extract the callback count and array in two steps */ case 3: @@ -1841,7 +1841,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_cbs: afs_extract_to_buf(call, 3 * sizeof(__be32)); - /* Fall through */ + fallthrough; case 4: _debug("extract CB array"); @@ -1870,7 +1870,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, 6 * sizeof(__be32)); call->unmarshall++; - /* Fall through */ + fallthrough; case 5: ret = afs_extract_data(call, false); @@ -1974,7 +1974,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the returned data length */ case 1: @@ -1992,7 +1992,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) acl->size = call->count2; afs_extract_begin(call, acl->data, size); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the returned data */ case 2: @@ -2002,7 +2002,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) afs_extract_to_buf(call, (21 + 6) * 4); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the metadata */ case 3: diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 792ac711985e..18042b7dab6a 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -401,22 +401,24 @@ struct afs_vlserver { #define AFS_VLSERVER_FL_PROBED 0 /* The VL server has been probed */ #define AFS_VLSERVER_FL_PROBING 1 /* VL server is being probed */ #define AFS_VLSERVER_FL_IS_YFS 2 /* Server is YFS not AFS */ +#define AFS_VLSERVER_FL_RESPONDING 3 /* VL server is responding */ rwlock_t lock; /* Lock on addresses */ atomic_t usage; + unsigned int rtt; /* Server's current RTT in uS */ /* Probe state */ wait_queue_head_t probe_wq; atomic_t probe_outstanding; spinlock_t probe_lock; struct { - unsigned int rtt; /* RTT as ktime/64 */ + unsigned int rtt; /* RTT in uS */ u32 abort_code; short error; - bool have_result; - bool responded:1; - bool is_yfs:1; - bool not_yfs:1; - bool local_failure:1; + unsigned short flags; +#define AFS_VLSERVER_PROBE_RESPONDED 0x01 /* At least once response (may be abort) */ +#define AFS_VLSERVER_PROBE_IS_YFS 0x02 /* The peer appears to be YFS */ +#define AFS_VLSERVER_PROBE_NOT_YFS 0x04 /* The peer appears not to be YFS */ +#define AFS_VLSERVER_PROBE_LOCAL_FAILURE 0x08 /* A local failure prevented a probe */ } probe; u16 port; diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 5334f1bd2bca..1d1a8debe472 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -120,42 +120,42 @@ void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code) if (e->error == -ETIMEDOUT || e->error == -ETIME) return; - /* Fall through */ + fallthrough; case -ETIMEDOUT: case -ETIME: if (e->error == -ENOMEM || e->error == -ENONET) return; - /* Fall through */ + fallthrough; case -ENOMEM: case -ENONET: if (e->error == -ERFKILL) return; - /* Fall through */ + fallthrough; case -ERFKILL: if (e->error == -EADDRNOTAVAIL) return; - /* Fall through */ + fallthrough; case -EADDRNOTAVAIL: if (e->error == -ENETUNREACH) return; - /* Fall through */ + fallthrough; case -ENETUNREACH: if (e->error == -EHOSTUNREACH) return; - /* Fall through */ + fallthrough; case -EHOSTUNREACH: if (e->error == -EHOSTDOWN) return; - /* Fall through */ + fallthrough; case -EHOSTDOWN: if (e->error == -ECONNREFUSED) return; - /* Fall through */ + fallthrough; case -ECONNREFUSED: if (e->error == -ECONNRESET) return; - /* Fall through */ + fallthrough; case -ECONNRESET: /* Responded, but call expired. */ if (e->responded) return; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index e817fc740ba0..e8babb62ed44 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -310,6 +310,11 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v) alist->preferred == i ? '>' : '-', &alist->addrs[i].transport); } + seq_printf(m, " info: fl=%lx rtt=%d\n", vlserver->flags, vlserver->rtt); + seq_printf(m, " probe: fl=%x e=%d ac=%d out=%d\n", + vlserver->probe.flags, vlserver->probe.error, + vlserver->probe.abort_code, + atomic_read(&vlserver->probe_outstanding)); return 0; } diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index 6a0935cb822f..d83f13c44b92 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -281,7 +281,7 @@ bool afs_select_fileserver(struct afs_operation *op) case -ETIME: if (op->error != -EDESTADDRREQ) goto iterate_address; - /* Fall through */ + fallthrough; case -ERFKILL: case -EADDRNOTAVAIL: case -ENETUNREACH: diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 8fc8fb406a5a..8be709cb8542 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -568,7 +568,7 @@ static void afs_deliver_to_call(struct afs_call *call) case -EIO: pr_err("kAFS: Call %u in bad state %u\n", call->debug_id, state); - /* Fall through */ + fallthrough; case -ENODATA: case -EBADMSG: case -EMSGSIZE: @@ -669,7 +669,7 @@ long afs_wait_for_call_to_complete(struct afs_call *call, ret = call->ret0; call->ret0 = 0; - /* Fall through */ + fallthrough; case -ECONNABORTED: ac->responded = true; break; @@ -872,7 +872,7 @@ void afs_send_empty_reply(struct afs_call *call) _debug("oom"); rxrpc_kernel_abort_call(net->socket, call->rxcall, RX_USER_ABORT, -ENOMEM, "KOO"); - /* Fall through */ + fallthrough; default: _leave(" [error]"); return; diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c index 8fea54eba0c2..38b2ba1d9ec0 100644 --- a/fs/afs/vl_list.c +++ b/fs/afs/vl_list.c @@ -21,6 +21,7 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len, rwlock_init(&vlserver->lock); init_waitqueue_head(&vlserver->probe_wq); spin_lock_init(&vlserver->probe_lock); + vlserver->rtt = UINT_MAX; vlserver->name_len = name_len; vlserver->port = port; memcpy(vlserver->name, name, name_len); diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index e3aa013c2177..d1c7068b4346 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -11,15 +11,33 @@ #include "internal.h" #include "protocol_yfs.h" -static bool afs_vl_probe_done(struct afs_vlserver *server) + +/* + * Handle the completion of a set of probes. + */ +static void afs_finished_vl_probe(struct afs_vlserver *server) { - if (!atomic_dec_and_test(&server->probe_outstanding)) - return false; + if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) { + server->rtt = UINT_MAX; + clear_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags); + } - wake_up_var(&server->probe_outstanding); clear_bit_unlock(AFS_VLSERVER_FL_PROBING, &server->flags); wake_up_bit(&server->flags, AFS_VLSERVER_FL_PROBING); - return true; +} + +/* + * Handle the completion of a probe RPC call. + */ +static void afs_done_one_vl_probe(struct afs_vlserver *server, bool wake_up) +{ + if (atomic_dec_and_test(&server->probe_outstanding)) { + afs_finished_vl_probe(server); + wake_up = true; + } + + if (wake_up) + wake_up_all(&server->probe_wq); } /* @@ -45,15 +63,20 @@ void afs_vlserver_probe_result(struct afs_call *call) server->probe.error = 0; goto responded; case -ECONNABORTED: - if (!server->probe.responded) { + if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) { server->probe.abort_code = call->abort_code; server->probe.error = ret; } goto responded; case -ENOMEM: case -ENONET: - server->probe.local_failure = true; - afs_io_error(call, afs_io_error_vl_probe_fail); + case -EKEYEXPIRED: + case -EKEYREVOKED: + case -EKEYREJECTED: + server->probe.flags |= AFS_VLSERVER_PROBE_LOCAL_FAILURE; + if (server->probe.error == 0) + server->probe.error = ret; + trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail); goto out; case -ECONNRESET: /* Responded, but call expired. */ case -ERFKILL: @@ -67,12 +90,12 @@ void afs_vlserver_probe_result(struct afs_call *call) default: clear_bit(index, &alist->responded); set_bit(index, &alist->failed); - if (!server->probe.responded && + if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) && (server->probe.error == 0 || server->probe.error == -ETIMEDOUT || server->probe.error == -ETIME)) server->probe.error = ret; - afs_io_error(call, afs_io_error_vl_probe_fail); + trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail); goto out; } @@ -81,39 +104,36 @@ responded: clear_bit(index, &alist->failed); if (call->service_id == YFS_VL_SERVICE) { - server->probe.is_yfs = true; + server->probe.flags |= AFS_VLSERVER_PROBE_IS_YFS; set_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags); alist->addrs[index].srx_service = call->service_id; } else { - server->probe.not_yfs = true; - if (!server->probe.is_yfs) { + server->probe.flags |= AFS_VLSERVER_PROBE_NOT_YFS; + if (!(server->probe.flags & AFS_VLSERVER_PROBE_IS_YFS)) { clear_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags); alist->addrs[index].srx_service = call->service_id; } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; + server->rtt = rtt_us; alist->preferred = index; - have_result = true; } smp_wmb(); /* Set rtt before responded. */ - server->probe.responded = true; + server->probe.flags |= AFS_VLSERVER_PROBE_RESPONDED; set_bit(AFS_VLSERVER_FL_PROBED, &server->flags); + set_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags); + have_result = true; out: spin_unlock(&server->probe_lock); _debug("probe [%u][%u] %pISpc rtt=%u ret=%d", server_index, index, &alist->addrs[index].transport, rtt_us, ret); - have_result |= afs_vl_probe_done(server); - if (have_result) { - server->probe.have_result = true; - wake_up_var(&server->probe.have_result); - wake_up_all(&server->probe_wq); - } + afs_done_one_vl_probe(server, have_result); } /* @@ -151,11 +171,10 @@ static bool afs_do_probe_vlserver(struct afs_net *net, in_progress = true; } else { afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code); + afs_done_one_vl_probe(server, false); } } - if (!in_progress) - afs_vl_probe_done(server); return in_progress; } @@ -193,7 +212,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, { struct wait_queue_entry *waits; struct afs_vlserver *server; - unsigned int rtt = UINT_MAX; + unsigned int rtt = UINT_MAX, rtt_s; bool have_responders = false; int pref = -1, i; @@ -205,7 +224,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, server = vllist->servers[i].server; if (!test_bit(AFS_VLSERVER_FL_PROBING, &server->flags)) __clear_bit(i, &untried); - if (server->probe.responded) + if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) have_responders = true; } } @@ -231,7 +250,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, for (i = 0; i < vllist->nr_servers; i++) { if (test_bit(i, &untried)) { server = vllist->servers[i].server; - if (server->probe.responded) + if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) goto stop; if (test_bit(AFS_VLSERVER_FL_PROBING, &server->flags)) still_probing = true; @@ -249,10 +268,11 @@ stop: for (i = 0; i < vllist->nr_servers; i++) { if (test_bit(i, &untried)) { server = vllist->servers[i].server; - if (server->probe.responded && - server->probe.rtt < rtt) { + rtt_s = READ_ONCE(server->rtt); + if (test_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags) && + rtt_s < rtt) { pref = i; - rtt = server->probe.rtt; + rtt = rtt_s; } remove_wait_queue(&server->probe_wq, &waits[i]); diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index f405ca8b240a..c0458c903b31 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -192,7 +192,8 @@ pick_server: for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; - if (!test_bit(i, &vc->untried) || !s->probe.responded) + if (!test_bit(i, &vc->untried) || + !test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags)) continue; if (s->probe.rtt < rtt) { vc->index = i; @@ -262,10 +263,14 @@ no_more_servers: for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; + if (test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags)) + e.responded = true; afs_prioritise_error(&e, READ_ONCE(s->probe.error), s->probe.abort_code); } + error = e.error; + failed_set_error: vc->error = error; failed: diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index fd82850cd424..dc9327332f06 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -196,7 +196,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) /* Extract the returned uuid, uniquifier, nentries and * blkaddrs size */ - /* Fall through */ + fallthrough; case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -221,7 +221,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) count = min(call->count, 4U); afs_extract_to_buf(call, count * sizeof(__be32)); - /* Fall through - and extract entries */ + fallthrough; /* and extract entries */ case 2: ret = afs_extract_data(call, call->count > 4); if (ret < 0) @@ -324,7 +324,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through - and extract the capabilities word count */ + fallthrough; /* and extract the capabilities word count */ case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -337,7 +337,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call) call->unmarshall++; afs_extract_discard(call, count * sizeof(__be32)); - /* Fall through - and extract capabilities words */ + fallthrough; /* and extract capabilities words */ case 2: ret = afs_extract_data(call, false); if (ret < 0) @@ -436,7 +436,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) /* Extract the returned uuid, uniquifier, fsEndpoints count and * either the first fsEndpoint type or the volEndpoints * count if there are no fsEndpoints. */ - /* Fall through */ + fallthrough; case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -475,7 +475,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) afs_extract_to_buf(call, size); call->unmarshall = 2; - /* Fall through - and extract fsEndpoints[] entries */ + fallthrough; /* and extract fsEndpoints[] entries */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -526,7 +526,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) * extract the type of the next endpoint when we extract the * data of the current one, but this is the first... */ - /* Fall through */ + fallthrough; case 3: ret = afs_extract_data(call, true); if (ret < 0) @@ -552,7 +552,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) afs_extract_to_buf(call, size); call->unmarshall = 4; - /* Fall through - and extract volEndpoints[] entries */ + fallthrough; /* and extract volEndpoints[] entries */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -587,7 +587,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) afs_extract_discard(call, 0); call->unmarshall = 5; - /* Fall through - Done */ + fallthrough; /* Done */ case 5: ret = afs_extract_data(call, false); if (ret < 0) @@ -663,7 +663,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through - and extract the cell name length */ + fallthrough; /* and extract the cell name length */ case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -685,7 +685,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call) afs_extract_begin(call, cell_name, namesz); call->unmarshall++; - /* Fall through - and extract cell name */ + fallthrough; /* and extract cell name */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -694,7 +694,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call) afs_extract_discard(call, call->count2); call->unmarshall++; - /* Fall through - and extract padding */ + fallthrough; /* and extract padding */ case 3: ret = afs_extract_data(call, false); if (ret < 0) diff --git a/fs/afs/write.c b/fs/afs/write.c index a121c247d95a..4b2265cb1891 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -609,7 +609,7 @@ no_more: default: pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret); - /* Fall through */ + fallthrough; case -EACCES: case -EPERM: case -ENOKEY: diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 8c24fdc899e3..3b1239b7e90d 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -373,7 +373,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) req->offset = req->pos & (PAGE_SIZE - 1); afs_extract_to_tmp64(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the returned data length */ case 1: @@ -401,7 +401,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) call->bvec[0].bv_page = req->pages[req->index]; iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); - /* Fall through */ + fallthrough; /* extract the returned data */ case 2: @@ -428,7 +428,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) /* Discard any excess data the server gave us */ afs_extract_discard(call, req->actual_len - req->len); call->unmarshall = 3; - /* Fall through */ + fallthrough; case 3: _debug("extract discard %zu/%llu", @@ -444,7 +444,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); - /* Fall through */ + fallthrough; /* extract the metadata */ case 4: @@ -461,7 +461,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) req->file_size = vp->scb.status.size; call->unmarshall++; - /* Fall through */ + fallthrough; case 5: break; @@ -1262,7 +1262,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) case 0: call->unmarshall++; afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchVolumeStatus)); - /* Fall through */ + fallthrough; /* extract the returned status record */ case 1: @@ -1275,7 +1275,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) xdr_decode_YFSFetchVolumeStatus(&bp, &op->volstatus.vs); call->unmarshall++; afs_extract_to_tmp(call); - /* Fall through */ + fallthrough; /* extract the volume name length */ case 2: @@ -1290,7 +1290,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the volume name */ case 3: @@ -1304,7 +1304,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the offline message length */ case 4: @@ -1319,7 +1319,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the offline message */ case 5: @@ -1334,7 +1334,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the message of the day length */ case 6: @@ -1349,7 +1349,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the message of the day */ case 7: @@ -1363,7 +1363,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) _debug("motd '%s'", p); call->unmarshall++; - /* Fall through */ + fallthrough; case 8: break; @@ -1622,7 +1622,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* Extract the file status count and array in two steps */ case 1: @@ -1640,7 +1640,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_counts: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchStatus)); - /* Fall through */ + fallthrough; case 2: _debug("extract status array %u", call->count); @@ -1670,7 +1670,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->count = 0; call->unmarshall++; afs_extract_to_tmp(call); - /* Fall through */ + fallthrough; /* Extract the callback count and array in two steps */ case 3: @@ -1687,7 +1687,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_cbs: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSCallBack)); - /* Fall through */ + fallthrough; case 4: _debug("extract CB array"); @@ -1716,7 +1716,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync)); call->unmarshall++; - /* Fall through */ + fallthrough; case 5: ret = afs_extract_data(call, false); @@ -1727,7 +1727,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) xdr_decode_YFSVolSync(&bp, &op->volsync); call->unmarshall++; - /* Fall through */ + fallthrough; case 6: break; @@ -1804,7 +1804,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* Extract the file ACL length */ case 1: @@ -1826,7 +1826,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) afs_extract_discard(call, size); } call->unmarshall++; - /* Fall through */ + fallthrough; /* Extract the file ACL */ case 2: @@ -1836,7 +1836,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; - /* Fall through */ + fallthrough; /* Extract the volume ACL length */ case 3: @@ -1858,7 +1858,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) afs_extract_discard(call, size); } call->unmarshall++; - /* Fall through */ + fallthrough; /* Extract the volume ACL */ case 4: @@ -1871,7 +1871,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); call->unmarshall++; - /* Fall through */ + fallthrough; /* extract the metadata */ case 5: @@ -1886,7 +1886,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) xdr_decode_YFSVolSync(&bp, &op->volsync); call->unmarshall++; - /* Fall through */ + fallthrough; case 6: break; @@ -1511,7 +1511,7 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret) * may be already running. Just fail this IO with EINTR. */ ret = -EINTR; - /*FALLTHRU*/ + fallthrough; default: req->ki_complete(req, ret, 0); } diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index f2f9086ebe98..b9c658e0548e 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -576,7 +576,7 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } - len = data_len + extra; + len = data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long); len = PAGE_ALIGN(len); realdatastart = vm_mmap(NULL, 0, len, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0); @@ -590,7 +590,9 @@ static int load_flat_file(struct linux_binprm *bprm, vm_munmap(textpos, text_len); goto err; } - datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN); + datapos = ALIGN(realdatastart + + MAX_SHARED_LIBS * sizeof(unsigned long), + FLAT_DATA_ALIGN); pr_debug("Allocated data+bss+stack (%u bytes): %lx\n", data_len + bss_len + stack_len, datapos); @@ -620,7 +622,7 @@ static int load_flat_file(struct linux_binprm *bprm, memp_size = len; } else { - len = text_len + data_len + extra; + len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32); len = PAGE_ALIGN(len); textpos = vm_mmap(NULL, 0, len, PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0); @@ -635,7 +637,9 @@ static int load_flat_file(struct linux_binprm *bprm, } realdatastart = textpos + ntohl(hdr->data_start); - datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN); + datapos = ALIGN(realdatastart + + MAX_SHARED_LIBS * sizeof(u32), + FLAT_DATA_ALIGN); reloc = (__be32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); @@ -652,9 +656,8 @@ static int load_flat_file(struct linux_binprm *bprm, (text_len + full_data - sizeof(struct flat_hdr)), 0); - if (datapos != realdatastart) - memmove((void *)datapos, (void *)realdatastart, - full_data); + memmove((void *) datapos, (void *) realdatastart, + full_data); #else /* * This is used on MMU systems mainly for testing. @@ -710,7 +713,8 @@ static int load_flat_file(struct linux_binprm *bprm, if (IS_ERR_VALUE(result)) { ret = result; pr_err("Unable to read code+data+bss, errno %d\n", ret); - vm_munmap(textpos, text_len + data_len + extra); + vm_munmap(textpos, text_len + data_len + extra + + MAX_SHARED_LIBS * sizeof(u32)); goto err; } } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 613920c17ac1..ea8aaf36647e 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1798,7 +1798,6 @@ static struct btrfs_block_group *btrfs_create_block_group_cache( cache->fs_info = fs_info; cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start); - set_free_space_tree_thresholds(cache); cache->discard_index = BTRFS_DISCARD_INDEX_UNUSED; @@ -1912,6 +1911,8 @@ static int read_one_block_group(struct btrfs_fs_info *info, if (ret < 0) goto error; + set_free_space_tree_thresholds(cache); + if (need_clear) { /* * When we mount with old space cache, we need to @@ -2132,6 +2133,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, return -ENOMEM; cache->length = size; + set_free_space_tree_thresholds(cache); cache->used = bytes_used; cache->flags = type; cache->last_byte_to_unpin = (u64)-1; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 70e49d8d4f6c..cd392da69b81 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -68,7 +68,7 @@ const char *btrfs_super_csum_driver(u16 csum_type) btrfs_csums[csum_type].name; } -size_t __const btrfs_get_num_csums(void) +size_t __attribute_const__ btrfs_get_num_csums(void) { return ARRAY_SIZE(btrfs_csums); } @@ -1297,6 +1297,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path, btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); + btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin), + eb_rewin, btrfs_header_level(eb_rewin)); btrfs_tree_read_lock(eb_rewin); __tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm); WARN_ON(btrfs_header_nritems(eb_rewin) > @@ -1370,7 +1372,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq) if (!eb) return NULL; - btrfs_tree_read_lock(eb); if (old_root) { btrfs_set_header_bytenr(eb, eb->start); btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV); @@ -1378,6 +1379,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq) btrfs_set_header_level(eb, old_root->level); btrfs_set_header_generation(eb, old_generation); } + btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb, + btrfs_header_level(eb)); + btrfs_tree_read_lock(eb); if (tm) __tree_mod_log_rewind(fs_info, eb, time_seq, tm); else diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9c7e466f27a9..9a72896bed2e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2262,7 +2262,7 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block, int btrfs_super_csum_size(const struct btrfs_super_block *s); const char *btrfs_super_csum_name(u16 csum_type); const char *btrfs_super_csum_driver(u16 csum_type); -size_t __const btrfs_get_num_csums(void); +size_t __attribute_const__ btrfs_get_num_csums(void); /* @@ -2518,7 +2518,7 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes); int btrfs_exclude_logged_extents(struct extent_buffer *eb); int btrfs_cross_ref_exist(struct btrfs_root *root, - u64 objectid, u64 offset, u64 bytenr); + u64 objectid, u64 offset, u64 bytenr, bool strict); struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 parent, u64 root_objectid, @@ -2934,7 +2934,7 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, u64 start, u64 len); noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, - u64 *ram_bytes); + u64 *ram_bytes, bool strict); void __btrfs_del_delalloc_inode(struct btrfs_root *root, struct btrfs_inode *inode); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9ae25f632157..f6bba7eb1fa1 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4551,6 +4551,7 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) cache->io_ctl.inode = NULL; iput(inode); } + ASSERT(cache->io_ctl.pages == NULL); btrfs_put_block_group(cache); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index de6fe176fdfb..e9eedc053fc5 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2306,7 +2306,8 @@ static noinline int check_delayed_ref(struct btrfs_root *root, static noinline int check_committed_ref(struct btrfs_root *root, struct btrfs_path *path, - u64 objectid, u64 offset, u64 bytenr) + u64 objectid, u64 offset, u64 bytenr, + bool strict) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *extent_root = fs_info->extent_root; @@ -2348,9 +2349,13 @@ static noinline int check_committed_ref(struct btrfs_root *root, btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY)) goto out; - /* If extent created before last snapshot => it's definitely shared */ - if (btrfs_extent_generation(leaf, ei) <= - btrfs_root_last_snapshot(&root->root_item)) + /* + * If extent created before last snapshot => it's shared unless the + * snapshot has been deleted. Use the heuristic if strict is false. + */ + if (!strict && + (btrfs_extent_generation(leaf, ei) <= + btrfs_root_last_snapshot(&root->root_item))) goto out; iref = (struct btrfs_extent_inline_ref *)(ei + 1); @@ -2375,7 +2380,7 @@ out: } int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, - u64 bytenr) + u64 bytenr, bool strict) { struct btrfs_path *path; int ret; @@ -2386,7 +2391,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, do { ret = check_committed_ref(root, path, objectid, - offset, bytenr); + offset, bytenr, strict); if (ret && ret != -ENOENT) goto out; @@ -4522,7 +4527,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, return ERR_PTR(-EUCLEAN); } - btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); + btrfs_set_buffer_lockdep_class(owner, buf, level); btrfs_tree_lock(buf); btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 6def411b2eba..a940edb1e64f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5655,9 +5655,9 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, } } -int read_extent_buffer_to_user(const struct extent_buffer *eb, - void __user *dstv, - unsigned long start, unsigned long len) +int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, + void __user *dstv, + unsigned long start, unsigned long len) { size_t cur; size_t offset; @@ -5677,7 +5677,7 @@ int read_extent_buffer_to_user(const struct extent_buffer *eb, cur = min(len, (PAGE_SIZE - offset)); kaddr = page_address(page); - if (copy_to_user(dst, kaddr + offset, cur)) { + if (copy_to_user_nofault(dst, kaddr + offset, cur)) { ret = -EFAULT; break; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 00a88f2eb5ab..30794ae58498 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -241,9 +241,9 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, void read_extent_buffer(const struct extent_buffer *eb, void *dst, unsigned long start, unsigned long len); -int read_extent_buffer_to_user(const struct extent_buffer *eb, - void __user *dst, unsigned long start, - unsigned long len); +int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, + void __user *dst, unsigned long start, + unsigned long len); void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *src); void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb, const void *src); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index bb824c7cb7c7..4507c3d09399 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1571,7 +1571,7 @@ static int check_can_nocow(struct btrfs_inode *inode, loff_t pos, } ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, - NULL, NULL, NULL); + NULL, NULL, NULL, false); if (ret <= 0) { ret = 0; if (!nowait) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index ef0fd7afb0b1..dc82fd0c80cb 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1186,7 +1186,6 @@ static int __btrfs_wait_cache_io(struct btrfs_root *root, ret = update_cache_item(trans, root, inode, path, offset, io_ctl->entries, io_ctl->bitmaps); out: - io_ctl_free(io_ctl); if (ret) { invalidate_inode_pages2(inode->i_mapping); BTRFS_I(inode)->generation = 0; @@ -1347,6 +1346,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, * them out later */ io_ctl_drop_pages(io_ctl); + io_ctl_free(io_ctl); unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, &cached_state); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 8b1f5c8897b7..6b9faf3b0e96 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -22,6 +22,10 @@ void set_free_space_tree_thresholds(struct btrfs_block_group *cache) size_t bitmap_size; u64 num_bitmaps, total_bitmap_size; + if (WARN_ON(cache->length == 0)) + btrfs_warn(cache->fs_info, "block group %llu length is zero", + cache->start); + /* * We convert to bitmaps when the disk space required for using extents * exceeds that required for using bitmaps. diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 51fcd82d41c0..9570458aa847 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1610,7 +1610,7 @@ next_slot: goto out_check; ret = btrfs_cross_ref_exist(root, ino, found_key.offset - - extent_offset, disk_bytenr); + extent_offset, disk_bytenr, false); if (ret) { /* * ret could be -EIO if the above fails to read @@ -2161,11 +2161,8 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio, u64 bio_offset) { struct inode *inode = private_data; - blk_status_t ret = 0; - ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); - BUG_ON(ret); /* -ENOMEM */ - return 0; + return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); } /* @@ -6953,6 +6950,8 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, * @orig_start: (optional) Return the original file offset of the file extent * @orig_len: (optional) Return the original on-disk length of the file extent * @ram_bytes: (optional) Return the ram_bytes of the file extent + * @strict: if true, omit optimizations that might force us into unnecessary + * cow. e.g., don't trust generation number. * * This function will flush ordered extents in the range to ensure proper * nocow checks for (nowait == false) case. @@ -6967,7 +6966,7 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, */ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, - u64 *ram_bytes) + u64 *ram_bytes, bool strict) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_path *path; @@ -7045,8 +7044,9 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, * Do the same check as in btrfs_cross_ref_exist but without the * unnecessary search. */ - if (btrfs_file_extent_generation(leaf, fi) <= - btrfs_root_last_snapshot(&root->root_item)) + if (!strict && + (btrfs_file_extent_generation(leaf, fi) <= + btrfs_root_last_snapshot(&root->root_item))) goto out; backref_offset = btrfs_file_extent_offset(leaf, fi); @@ -7082,7 +7082,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, */ ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)), - key.offset - backref_offset, disk_bytenr); + key.offset - backref_offset, disk_bytenr, + strict); if (ret) { ret = 0; goto out; @@ -7303,7 +7304,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, block_start = em->block_start + (start - em->start); if (can_nocow_extent(inode, start, &len, &orig_start, - &orig_block_len, &ram_bytes) == 1 && + &orig_block_len, &ram_bytes, false) == 1 && btrfs_inc_nocow_writers(fs_info, block_start)) { struct extent_map *em2; @@ -7619,10 +7620,8 @@ static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data, struct bio *bio, u64 offset) { struct inode *inode = private_data; - blk_status_t ret; - ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1); - BUG_ON(ret); /* -ENOMEM */ - return 0; + + return btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1); } static void btrfs_end_dio_bio(struct bio *bio) @@ -10136,7 +10135,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, free_extent_map(em); em = NULL; - ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL); + ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, true); if (ret < 0) { goto out; } else if (ret) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bd3511c5ca81..ac45f022b495 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2086,9 +2086,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, sh.len = item_len; sh.transid = found_transid; - /* copy search result header */ - if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) { - ret = -EFAULT; + /* + * Copy search result header. If we fault then loop again so we + * can fault in the pages and -EFAULT there if there's a + * problem. Otherwise we'll fault and then copy the buffer in + * properly this next time through + */ + if (copy_to_user_nofault(ubuf + *sk_offset, &sh, sizeof(sh))) { + ret = 0; goto out; } @@ -2096,10 +2101,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, if (item_len) { char __user *up = ubuf + *sk_offset; - /* copy the item */ - if (read_extent_buffer_to_user(leaf, up, - item_off, item_len)) { - ret = -EFAULT; + /* + * Copy the item, same behavior as above, but reset the + * * sk_offset so we copy the full thing again. + */ + if (read_extent_buffer_to_user_nofault(leaf, up, + item_off, item_len)) { + ret = 0; + *sk_offset -= sizeof(sh); goto out; } @@ -2184,6 +2193,10 @@ static noinline int search_ioctl(struct inode *inode, key.offset = sk->min_offset; while (1) { + ret = fault_in_pages_writeable(ubuf, *buf_size - sk_offset); + if (ret) + break; + ret = btrfs_search_forward(root, &key, path, sk->min_transid); if (ret != 0) { if (ret > 0) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 5a6cb9db512e..354ab9985a34 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3716,50 +3716,84 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, return 0; } +static void scrub_workers_put(struct btrfs_fs_info *fs_info) +{ + if (refcount_dec_and_mutex_lock(&fs_info->scrub_workers_refcnt, + &fs_info->scrub_lock)) { + struct btrfs_workqueue *scrub_workers = NULL; + struct btrfs_workqueue *scrub_wr_comp = NULL; + struct btrfs_workqueue *scrub_parity = NULL; + + scrub_workers = fs_info->scrub_workers; + scrub_wr_comp = fs_info->scrub_wr_completion_workers; + scrub_parity = fs_info->scrub_parity_workers; + + fs_info->scrub_workers = NULL; + fs_info->scrub_wr_completion_workers = NULL; + fs_info->scrub_parity_workers = NULL; + mutex_unlock(&fs_info->scrub_lock); + + btrfs_destroy_workqueue(scrub_workers); + btrfs_destroy_workqueue(scrub_wr_comp); + btrfs_destroy_workqueue(scrub_parity); + } +} + /* * get a reference count on fs_info->scrub_workers. start worker if necessary */ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, int is_dev_replace) { + struct btrfs_workqueue *scrub_workers = NULL; + struct btrfs_workqueue *scrub_wr_comp = NULL; + struct btrfs_workqueue *scrub_parity = NULL; unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND; int max_active = fs_info->thread_pool_size; + int ret = -ENOMEM; - lockdep_assert_held(&fs_info->scrub_lock); + if (refcount_inc_not_zero(&fs_info->scrub_workers_refcnt)) + return 0; - if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { - ASSERT(fs_info->scrub_workers == NULL); - fs_info->scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", - flags, is_dev_replace ? 1 : max_active, 4); - if (!fs_info->scrub_workers) - goto fail_scrub_workers; - - ASSERT(fs_info->scrub_wr_completion_workers == NULL); - fs_info->scrub_wr_completion_workers = - btrfs_alloc_workqueue(fs_info, "scrubwrc", flags, - max_active, 2); - if (!fs_info->scrub_wr_completion_workers) - goto fail_scrub_wr_completion_workers; + scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", flags, + is_dev_replace ? 1 : max_active, 4); + if (!scrub_workers) + goto fail_scrub_workers; - ASSERT(fs_info->scrub_parity_workers == NULL); - fs_info->scrub_parity_workers = - btrfs_alloc_workqueue(fs_info, "scrubparity", flags, + scrub_wr_comp = btrfs_alloc_workqueue(fs_info, "scrubwrc", flags, max_active, 2); - if (!fs_info->scrub_parity_workers) - goto fail_scrub_parity_workers; + if (!scrub_wr_comp) + goto fail_scrub_wr_completion_workers; + scrub_parity = btrfs_alloc_workqueue(fs_info, "scrubparity", flags, + max_active, 2); + if (!scrub_parity) + goto fail_scrub_parity_workers; + + mutex_lock(&fs_info->scrub_lock); + if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { + ASSERT(fs_info->scrub_workers == NULL && + fs_info->scrub_wr_completion_workers == NULL && + fs_info->scrub_parity_workers == NULL); + fs_info->scrub_workers = scrub_workers; + fs_info->scrub_wr_completion_workers = scrub_wr_comp; + fs_info->scrub_parity_workers = scrub_parity; refcount_set(&fs_info->scrub_workers_refcnt, 1); - } else { - refcount_inc(&fs_info->scrub_workers_refcnt); + mutex_unlock(&fs_info->scrub_lock); + return 0; } - return 0; + /* Other thread raced in and created the workers for us */ + refcount_inc(&fs_info->scrub_workers_refcnt); + mutex_unlock(&fs_info->scrub_lock); + ret = 0; + btrfs_destroy_workqueue(scrub_parity); fail_scrub_parity_workers: - btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers); + btrfs_destroy_workqueue(scrub_wr_comp); fail_scrub_wr_completion_workers: - btrfs_destroy_workqueue(fs_info->scrub_workers); + btrfs_destroy_workqueue(scrub_workers); fail_scrub_workers: - return -ENOMEM; + return ret; } int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, @@ -3770,9 +3804,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, int ret; struct btrfs_device *dev; unsigned int nofs_flag; - struct btrfs_workqueue *scrub_workers = NULL; - struct btrfs_workqueue *scrub_wr_comp = NULL; - struct btrfs_workqueue *scrub_parity = NULL; if (btrfs_fs_closing(fs_info)) return -EAGAIN; @@ -3819,13 +3850,17 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, if (IS_ERR(sctx)) return PTR_ERR(sctx); + ret = scrub_workers_get(fs_info, is_dev_replace); + if (ret) + goto out_free_ctx; + mutex_lock(&fs_info->fs_devices->device_list_mutex); dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true); if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) && !is_dev_replace)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -ENODEV; - goto out_free_ctx; + goto out; } if (!is_dev_replace && !readonly && @@ -3834,7 +3869,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable", rcu_str_deref(dev->name)); ret = -EROFS; - goto out_free_ctx; + goto out; } mutex_lock(&fs_info->scrub_lock); @@ -3843,7 +3878,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EIO; - goto out_free_ctx; + goto out; } down_read(&fs_info->dev_replace.rwsem); @@ -3854,17 +3889,10 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EINPROGRESS; - goto out_free_ctx; + goto out; } up_read(&fs_info->dev_replace.rwsem); - ret = scrub_workers_get(fs_info, is_dev_replace); - if (ret) { - mutex_unlock(&fs_info->scrub_lock); - mutex_unlock(&fs_info->fs_devices->device_list_mutex); - goto out_free_ctx; - } - sctx->readonly = readonly; dev->scrub_ctx = sctx; mutex_unlock(&fs_info->fs_devices->device_list_mutex); @@ -3917,24 +3945,14 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_lock(&fs_info->scrub_lock); dev->scrub_ctx = NULL; - if (refcount_dec_and_test(&fs_info->scrub_workers_refcnt)) { - scrub_workers = fs_info->scrub_workers; - scrub_wr_comp = fs_info->scrub_wr_completion_workers; - scrub_parity = fs_info->scrub_parity_workers; - - fs_info->scrub_workers = NULL; - fs_info->scrub_wr_completion_workers = NULL; - fs_info->scrub_parity_workers = NULL; - } mutex_unlock(&fs_info->scrub_lock); - btrfs_destroy_workqueue(scrub_workers); - btrfs_destroy_workqueue(scrub_wr_comp); - btrfs_destroy_workqueue(scrub_parity); + scrub_workers_put(fs_info); scrub_put_ctx(sctx); return ret; - +out: + scrub_workers_put(fs_info); out_free_ctx: scrub_free_ctx(sctx); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index e529ddb35b87..25967ecaaf0a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -625,6 +625,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, } else if (strncmp(args[0].from, "lzo", 3) == 0) { compress_type = "lzo"; info->compress_type = BTRFS_COMPRESS_LZO; + info->compress_level = 0; btrfs_set_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, NODATACOW); btrfs_clear_opt(info->mount_opt, NODATASUM); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 517b44300a05..7b1fee630f97 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -984,7 +984,7 @@ static int check_inode_item(struct extent_buffer *leaf, /* Note for ROOT_TREE_DIR_ITEM, mkfs could set its transid 0 */ if (btrfs_inode_transid(leaf, iitem) > super_gen + 1) { inode_item_err(leaf, slot, - "invalid inode generation: has %llu expect [0, %llu]", + "invalid inode transid: has %llu expect [0, %llu]", btrfs_inode_transid(leaf, iitem), super_gen + 1); return -EUCLEAN; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 696dd861cc3c..39da9db35278 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3449,11 +3449,13 @@ fail: btrfs_free_path(path); out_unlock: mutex_unlock(&dir->log_mutex); - if (ret == -ENOSPC) { + if (err == -ENOSPC) { btrfs_set_log_full_commit(trans); - ret = 0; - } else if (ret < 0) - btrfs_abort_transaction(trans, ret); + err = 0; + } else if (err < 0 && err != -ENOENT) { + /* ENOENT can be returned if the entry hasn't been fsynced yet */ + btrfs_abort_transaction(trans, err); + } btrfs_end_log_trans(root); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ee96c5869f57..214856c4ccb1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4462,6 +4462,7 @@ int btrfs_uuid_scan_kthread(void *data) goto skip; } update_tree: + btrfs_release_path(path); if (!btrfs_is_empty_uuid(root_item.uuid)) { ret = btrfs_uuid_tree_add(trans, root_item.uuid, BTRFS_UUID_KEY_SUBVOL, @@ -4486,6 +4487,7 @@ update_tree: } skip: + btrfs_release_path(path); if (trans) { ret = btrfs_end_transaction(trans); trans = NULL; @@ -4493,7 +4495,6 @@ skip: break; } - btrfs_release_path(path); if (key.offset < (u64)-1) { key.offset++; } else if (key.type < BTRFS_ROOT_ITEM_KEY) { diff --git a/fs/buffer.c b/fs/buffer.c index 061dd202979d..50bbc99e3d96 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1958,7 +1958,7 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, */ set_buffer_new(bh); set_buffer_unwritten(bh); - /* FALLTHRU */ + fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || offset >= i_size_read(inode)) @@ -3157,6 +3157,15 @@ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags) WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { + /* + * The bh should be mapped, but it might not be if the + * device was hot-removed. Not much we can do but fail the I/O. + */ + if (!buffer_mapped(bh)) { + unlock_buffer(bh); + return -EIO; + } + get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, op_flags, bh); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 55ccccf77cea..034b3f4fdd3a 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -887,8 +887,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) int have = ci->i_snap_caps; if ((have & mask) == mask) { - dout("__ceph_caps_issued_mask ino 0x%lx snap issued %s" - " (mask %s)\n", ci->vfs_inode.i_ino, + dout("__ceph_caps_issued_mask ino 0x%llx snap issued %s" + " (mask %s)\n", ceph_ino(&ci->vfs_inode), ceph_cap_string(have), ceph_cap_string(mask)); return 1; @@ -899,8 +899,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) if (!__cap_is_valid(cap)) continue; if ((cap->issued & mask) == mask) { - dout("__ceph_caps_issued_mask ino 0x%lx cap %p issued %s" - " (mask %s)\n", ci->vfs_inode.i_ino, cap, + dout("__ceph_caps_issued_mask ino 0x%llx cap %p issued %s" + " (mask %s)\n", ceph_ino(&ci->vfs_inode), cap, ceph_cap_string(cap->issued), ceph_cap_string(mask)); if (touch) @@ -911,8 +911,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) /* does a combination of caps satisfy mask? */ have |= cap->issued; if ((have & mask) == mask) { - dout("__ceph_caps_issued_mask ino 0x%lx combo issued %s" - " (mask %s)\n", ci->vfs_inode.i_ino, + dout("__ceph_caps_issued_mask ino 0x%llx combo issued %s" + " (mask %s)\n", ceph_ino(&ci->vfs_inode), ceph_cap_string(cap->issued), ceph_cap_string(mask)); if (touch) { @@ -2872,7 +2872,7 @@ int ceph_get_caps(struct file *filp, int need, int want, struct cap_wait cw; DEFINE_WAIT_FUNC(wait, woken_wake_function); - cw.ino = inode->i_ino; + cw.ino = ceph_ino(inode); cw.tgid = current->tgid; cw.need = need; cw.want = want; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 97539b497e4c..3e3fcda9b276 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -202,7 +202,7 @@ static int caps_show_cb(struct inode *inode, struct ceph_cap *cap, void *p) { struct seq_file *s = p; - seq_printf(s, "0x%-17lx%-17s%-17s\n", inode->i_ino, + seq_printf(s, "0x%-17llx%-17s%-17s\n", ceph_ino(inode), ceph_cap_string(cap->issued), ceph_cap_string(cap->implemented)); return 0; @@ -247,7 +247,7 @@ static int caps_show(struct seq_file *s, void *p) spin_lock(&mdsc->caps_list_lock); list_for_each_entry(cw, &mdsc->cap_wait_list, list) { - seq_printf(s, "%-13d0x%-17lx%-17s%-17s\n", cw->tgid, cw->ino, + seq_printf(s, "%-13d0x%-17llx%-17s%-17s\n", cw->tgid, cw->ino, ceph_cap_string(cw->need), ceph_cap_string(cw->want)); } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 060bdcc5ce32..d72e4a12bb69 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -259,9 +259,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, dentry, dentry, d_inode(dentry)); ctx->pos = di->offset; if (!dir_emit(ctx, dentry->d_name.name, - dentry->d_name.len, - ceph_translate_ino(dentry->d_sb, - d_inode(dentry)->i_ino), + dentry->d_name.len, ceph_present_inode(d_inode(dentry)), d_inode(dentry)->i_mode >> 12)) { dput(dentry); err = 0; @@ -324,18 +322,21 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx) /* always start with . and .. */ if (ctx->pos == 0) { dout("readdir off 0 -> '.'\n"); - if (!dir_emit(ctx, ".", 1, - ceph_translate_ino(inode->i_sb, inode->i_ino), + if (!dir_emit(ctx, ".", 1, ceph_present_inode(inode), inode->i_mode >> 12)) return 0; ctx->pos = 1; } if (ctx->pos == 1) { - ino_t ino = parent_ino(file->f_path.dentry); + u64 ino; + struct dentry *dentry = file->f_path.dentry; + + spin_lock(&dentry->d_lock); + ino = ceph_present_inode(dentry->d_parent->d_inode); + spin_unlock(&dentry->d_lock); + dout("readdir off 1 -> '..'\n"); - if (!dir_emit(ctx, "..", 2, - ceph_translate_ino(inode->i_sb, ino), - inode->i_mode >> 12)) + if (!dir_emit(ctx, "..", 2, ino, inode->i_mode >> 12)) return 0; ctx->pos = 2; } @@ -507,9 +508,6 @@ more: } for (; i < rinfo->dir_nr; i++) { struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i; - struct ceph_vino vino; - ino_t ino; - u32 ftype; BUG_ON(rde->offset < ctx->pos); @@ -519,13 +517,10 @@ more: rde->name_len, rde->name, &rde->inode.in); BUG_ON(!rde->inode.in); - ftype = le32_to_cpu(rde->inode.in->mode) >> 12; - vino.ino = le64_to_cpu(rde->inode.in->ino); - vino.snap = le64_to_cpu(rde->inode.in->snapid); - ino = ceph_vino_to_ino(vino); if (!dir_emit(ctx, rde->name, rde->name_len, - ceph_translate_ino(inode->i_sb, ino), ftype)) { + ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)), + le32_to_cpu(rde->inode.in->mode) >> 12)) { dout("filldir stopping us...\n"); return 0; } @@ -1161,7 +1156,7 @@ retry: if (try_async && op == CEPH_MDS_OP_UNLINK && (req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) { - dout("async unlink on %lu/%.*s caps=%s", dir->i_ino, + dout("async unlink on %llu/%.*s caps=%s", ceph_ino(dir), dentry->d_name.len, dentry->d_name.name, ceph_cap_string(req->r_dir_caps)); set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags); @@ -1745,7 +1740,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) case -ENOENT: if (d_really_is_negative(dentry)) valid = 1; - /* Fallthrough */ + fallthrough; default: break; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d51c3f2fdca0..3f4c993dfc6f 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -252,7 +252,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) case S_IFREG: ceph_fscache_register_inode_cookie(inode); ceph_fscache_file_set_cookie(inode, file); - /* fall through */ + fallthrough; case S_IFDIR: ret = ceph_init_file_info(inode, file, fmode, S_ISDIR(inode->i_mode)); @@ -630,8 +630,8 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, } else { struct dentry *dn; - dout("%s d_adding new inode 0x%llx to 0x%lx/%s\n", __func__, - vino.ino, dir->i_ino, dentry->d_name.name); + dout("%s d_adding new inode 0x%llx to 0x%llx/%s\n", __func__, + vino.ino, ceph_ino(dir), dentry->d_name.name); ceph_dir_clear_ordered(dir); ceph_init_inode_acls(inode, as_ctx); if (inode->i_state & I_NEW) { @@ -2507,6 +2507,7 @@ const struct file_operations ceph_file_fops = { .mmap = ceph_mmap, .fsync = ceph_fsync, .lock = ceph_lock, + .setlease = simple_nosetlease, .flock = ceph_flock, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 357c937699d5..d163fa96cb40 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -41,8 +41,10 @@ static void ceph_inode_work(struct work_struct *work); */ static int ceph_set_ino_cb(struct inode *inode, void *data) { - ceph_inode(inode)->i_vino = *(struct ceph_vino *)data; - inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data); + struct ceph_inode_info *ci = ceph_inode(inode); + + ci->i_vino = *(struct ceph_vino *)data; + inode->i_ino = ceph_vino_to_ino_t(ci->i_vino); inode_set_iversion_raw(inode, 0); return 0; } @@ -50,17 +52,14 @@ static int ceph_set_ino_cb(struct inode *inode, void *data) struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino) { struct inode *inode; - ino_t t = ceph_vino_to_ino(vino); - inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino); + inode = iget5_locked(sb, (unsigned long)vino.ino, ceph_ino_compare, + ceph_set_ino_cb, &vino); if (!inode) return ERR_PTR(-ENOMEM); - if (inode->i_state & I_NEW) - dout("get_inode created new inode %p %llx.%llx ino %llx\n", - inode, ceph_vinop(inode), (u64)inode->i_ino); - dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino, - vino.snap, inode); + dout("get_inode on %llu=%llx.%llx got %p new %d\n", ceph_present_inode(inode), + ceph_vinop(inode), inode, !!(inode->i_state & I_NEW)); return inode; } @@ -2378,7 +2377,7 @@ int ceph_getattr(const struct path *path, struct kstat *stat, } generic_fillattr(inode, stat); - stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino); + stat->ino = ceph_present_inode(inode); /* * btime on newly-allocated inodes is 0, so if this is still set to diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index bc9e95937d7c..658800605bfb 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -372,7 +372,7 @@ struct ceph_quotarealm_inode { struct cap_wait { struct list_head list; - unsigned long ino; + u64 ino; pid_t tgid; int need; int want; diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 198ddde5c1e6..cc2c4d40b022 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -23,12 +23,12 @@ static inline bool ceph_has_realms_with_quotas(struct inode *inode) { struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct super_block *sb = mdsc->fsc->sb; + struct inode *root = d_inode(sb->s_root); if (atomic64_read(&mdsc->quotarealms_count) > 0) return true; /* if root is the real CephFS root, we don't have quota realms */ - if (sb->s_root->d_inode && - (sb->s_root->d_inode->i_ino == CEPH_INO_ROOT)) + if (root && ceph_ino(root) == CEPH_INO_ROOT) return false; /* otherwise, we can't know for sure */ return true; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 4c3c964b1c54..a3995ebe0623 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -457,15 +457,7 @@ ceph_vino(const struct inode *inode) return ceph_inode(inode)->i_vino; } -/* - * ino_t is <64 bits on many architectures, blech. - * - * i_ino (kernel inode) st_ino (userspace) - * i386 32 32 - * x86_64+ino32 64 32 - * x86_64 64 64 - */ -static inline u32 ceph_ino_to_ino32(__u64 vino) +static inline u32 ceph_ino_to_ino32(u64 vino) { u32 ino = vino & 0xffffffff; ino ^= vino >> 32; @@ -475,34 +467,17 @@ static inline u32 ceph_ino_to_ino32(__u64 vino) } /* - * kernel i_ino value + * Inode numbers in cephfs are 64 bits, but inode->i_ino is 32-bits on + * some arches. We generally do not use this value inside the ceph driver, but + * we do want to set it to something, so that generic vfs code has an + * appropriate value for tracepoints and the like. */ -static inline ino_t ceph_vino_to_ino(struct ceph_vino vino) +static inline ino_t ceph_vino_to_ino_t(struct ceph_vino vino) { -#if BITS_PER_LONG == 32 - return ceph_ino_to_ino32(vino.ino); -#else + if (sizeof(ino_t) == sizeof(u32)) + return ceph_ino_to_ino32(vino.ino); return (ino_t)vino.ino; -#endif -} - -/* - * user-visible ino (stat, filldir) - */ -#if BITS_PER_LONG == 32 -static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino) -{ - return ino; -} -#else -static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino) -{ - if (ceph_test_mount_opt(ceph_sb_to_client(sb), INO32)) - ino = ceph_ino_to_ino32(ino); - return ino; } -#endif - /* for printf-style formatting */ #define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap @@ -511,11 +486,34 @@ static inline u64 ceph_ino(struct inode *inode) { return ceph_inode(inode)->i_vino.ino; } + static inline u64 ceph_snap(struct inode *inode) { return ceph_inode(inode)->i_vino.snap; } +/** + * ceph_present_ino - format an inode number for presentation to userland + * @sb: superblock where the inode lives + * @ino: inode number to (possibly) convert + * + * If the user mounted with the ino32 option, then the 64-bit value needs + * to be converted to something that can fit inside 32 bits. Note that + * internal kernel code never uses this value, so this is entirely for + * userland consumption. + */ +static inline u64 ceph_present_ino(struct super_block *sb, u64 ino) +{ + if (unlikely(ceph_test_mount_opt(ceph_sb_to_client(sb), INO32))) + return ceph_ino_to_ino32(ino); + return ino; +} + +static inline u64 ceph_present_inode(struct inode *inode) +{ + return ceph_present_ino(inode->i_sb, ceph_ino(inode)); +} + static inline int ceph_ino_compare(struct inode *inode, void *data) { struct ceph_vino *pvino = (struct ceph_vino *)data; @@ -524,11 +522,16 @@ static inline int ceph_ino_compare(struct inode *inode, void *data) ci->i_vino.snap == pvino->snap; } + static inline struct inode *ceph_find_inode(struct super_block *sb, struct ceph_vino vino) { - ino_t t = ceph_vino_to_ino(vino); - return ilookup5(sb, t, ceph_ino_compare, &vino); + /* + * NB: The hashval will be run through the fs/inode.c hash function + * anyway, so there is no need to squash the inode number down to + * 32-bits first. Just use low-order bits on arches with 32-bit long. + */ + return ilookup5(sb, (unsigned long)vino.ino, ceph_ino_compare, &vino); } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index b296964b8afa..b565d83ba89e 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -2031,4 +2031,19 @@ static inline bool is_smb1_server(struct TCP_Server_Info *server) return strcmp(server->vals->version_string, SMB1_VERSION_STRING) == 0; } +static inline bool is_tcon_dfs(struct cifs_tcon *tcon) +{ + /* + * For SMB1, see MS-CIFS 2.4.55 SMB_COM_TREE_CONNECT_ANDX (0x75) and MS-CIFS 3.3.4.4 DFS + * Subsystem Notifies That a Share Is a DFS Share. + * + * For SMB2+, see MS-SMB2 2.2.10 SMB2 TREE_CONNECT Response and MS-SMB2 3.3.4.14 Server + * Application Updates a Share. + */ + if (!tcon || !tcon->ses || !tcon->ses->server) + return false; + return is_smb1_server(tcon->ses->server) ? tcon->Flags & SMB_SHARE_IS_IN_DFS : + tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT); +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 0e763d2dcf16..0496934feecb 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -581,7 +581,7 @@ should_set_ext_sec_flag(enum securityEnum sectype) if (global_secflags & (CIFSSEC_MAY_KRB5 | CIFSSEC_MAY_NTLMSSP)) return true; - /* Fallthrough */ + fallthrough; default: return false; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a275ee399dce..a5731dd6e656 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1378,25 +1378,25 @@ static int cifs_parse_security_flavors(char *value, return 1; case Opt_sec_krb5i: vol->sign = true; - /* Fallthrough */ + fallthrough; case Opt_sec_krb5: vol->sectype = Kerberos; break; case Opt_sec_ntlmsspi: vol->sign = true; - /* Fallthrough */ + fallthrough; case Opt_sec_ntlmssp: vol->sectype = RawNTLMSSP; break; case Opt_sec_ntlmi: vol->sign = true; - /* Fallthrough */ + fallthrough; case Opt_ntlm: vol->sectype = NTLM; break; case Opt_sec_ntlmv2i: vol->sign = true; - /* Fallthrough */ + fallthrough; case Opt_sec_ntlmv2: vol->sectype = NTLMv2; break; @@ -2187,7 +2187,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->password = NULL; break; } - /* Fallthrough - to Opt_pass below.*/ + fallthrough; /* to Opt_pass below */ case Opt_pass: /* Obtain the value string */ value = strchr(data, '='); @@ -4909,7 +4909,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) if (!tcon) continue; /* Make sure that requests go through new root servers */ - if (tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT)) { + if (is_tcon_dfs(tcon)) { put_root_ses(root_ses); set_root_ses(cifs_sb, ses, &root_ses); } diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 69cd5856621b..de564368a887 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -798,7 +798,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) if ((server->sec_kerberos || server->sec_mskerberos) && (global_secflags & CIFSSEC_MAY_KRB5)) return Kerberos; - /* Fallthrough */ + fallthrough; default: return Unspecified; } @@ -815,7 +815,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) default: break; } - /* Fallthrough - to attempt LANMAN authentication next */ + fallthrough; /* to attempt LANMAN authentication next */ case CIFS_NEGFLAVOR_LANMAN: switch (requested) { case LANMAN: @@ -823,7 +823,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) case Unspecified: if (global_secflags & CIFSSEC_MAY_LANMAN) return LANMAN; - /* Fallthrough */ + fallthrough; default: return Unspecified; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 667d70aa335f..96c172d94fba 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1101,7 +1101,7 @@ smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) if ((server->sec_kerberos || server->sec_mskerberos) && (global_secflags & CIFSSEC_MAY_KRB5)) return Kerberos; - /* Fallthrough */ + fallthrough; default: return Unspecified; } diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index cb733652ecca..ca2273727225 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1688,11 +1688,11 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence) switch (whence) { case 1: offset += file->f_pos; - /* fall through */ + fallthrough; case 0: if (offset >= 0) break; - /* fall through */ + fallthrough; default: return -EINVAL; } @@ -1367,7 +1367,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, ret = dax_load_hole(&xas, mapping, &entry, vmf); goto finish_iomap; } - /*FALLTHRU*/ + fallthrough; default: WARN_ON_ONCE(1); error = -EIO; diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 18d81599522f..002123efc6b0 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -5817,7 +5817,7 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, break; case -EAGAIN: error = 0; - /* fall through */ + fallthrough; default: __put_lkb(ls, lkb); goto out; diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 7d40d78ea864..ae325541884e 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -359,7 +359,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, return z_erofs_extent_lookback(m, m->delta[0]); case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: map->m_flags &= ~EROFS_MAP_ZIPPED; - /* fallthrough */ + fallthrough; case Z_EROFS_VLE_CLUSTER_TYPE_HEAD: map->m_la = (lcn << lclusterbits) | m->clusterofs; break; @@ -416,7 +416,7 @@ int z_erofs_map_blocks_iter(struct inode *inode, case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: if (endoff >= m.clusterofs) map->m_flags &= ~EROFS_MAP_ZIPPED; - /* fallthrough */ + fallthrough; case Z_EROFS_VLE_CLUSTER_TYPE_HEAD: if (endoff >= m.clusterofs) { map->m_la = (m.lcn << lclusterbits) | m.clusterofs; @@ -433,7 +433,7 @@ int z_erofs_map_blocks_iter(struct inode *inode, end = (m.lcn << lclusterbits) | m.clusterofs; map->m_flags |= EROFS_MAP_FULL_MAPPED; m.delta[0] = 1; - /* fallthrough */ + fallthrough; case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: /* get the correspoinding first chunk */ err = z_erofs_extent_lookback(&m, m.delta[0]); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 12eebcdea9c8..8107e06d7f6f 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1994,9 +1994,11 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) * not already there, and calling reverse_path_check() * during ep_insert(). */ - if (list_empty(&epi->ffd.file->f_tfile_llink)) - list_add(&epi->ffd.file->f_tfile_llink, - &tfile_check_list); + if (list_empty(&epi->ffd.file->f_tfile_llink)) { + if (get_file_rcu(epi->ffd.file)) + list_add(&epi->ffd.file->f_tfile_llink, + &tfile_check_list); + } } } mutex_unlock(&ep->mtx); @@ -2040,6 +2042,7 @@ static void clear_tfile_check_list(void) file = list_first_entry(&tfile_check_list, struct file, f_tfile_llink); list_del_init(&file->f_tfile_llink); + fput(file); } INIT_LIST_HEAD(&tfile_check_list); } @@ -2200,25 +2203,22 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, full_check = 1; if (is_file_epoll(tf.file)) { error = -ELOOP; - if (ep_loop_check(ep, tf.file) != 0) { - clear_tfile_check_list(); + if (ep_loop_check(ep, tf.file) != 0) goto error_tgt_fput; - } - } else + } else { + get_file(tf.file); list_add(&tf.file->f_tfile_llink, &tfile_check_list); + } error = epoll_mutex_lock(&ep->mtx, 0, nonblock); - if (error) { -out_del: - list_del(&tf.file->f_tfile_llink); + if (error) goto error_tgt_fput; - } if (is_file_epoll(tf.file)) { tep = tf.file->private_data; error = epoll_mutex_lock(&tep->mtx, 1, nonblock); if (error) { mutex_unlock(&ep->mtx); - goto out_del; + goto error_tgt_fput; } } } @@ -2239,8 +2239,6 @@ out_del: error = ep_insert(ep, epds, tf.file, fd, full_check); } else error = -EEXIST; - if (full_check) - clear_tfile_check_list(); break; case EPOLL_CTL_DEL: if (epi) @@ -2263,8 +2261,10 @@ out_del: mutex_unlock(&ep->mtx); error_tgt_fput: - if (full_check) + if (full_check) { + clear_tfile_check_list(); mutex_unlock(&epmutex); + } fdput(tf); error_fput: diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 80662e1f7889..415c21f0e750 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1241,7 +1241,7 @@ do_indirects: mark_inode_dirty(inode); ext2_free_branches(inode, &nr, &nr+1, 1); } - /* fall through */ + fallthrough; case EXT2_IND_BLOCK: nr = i_data[EXT2_DIND_BLOCK]; if (nr) { @@ -1249,7 +1249,7 @@ do_indirects: mark_inode_dirty(inode); ext2_free_branches(inode, &nr, &nr+1, 2); } - /* fall through */ + fallthrough; case EXT2_DIND_BLOCK: nr = i_data[EXT2_TIND_BLOCK]; if (nr) { diff --git a/fs/ext2/super.c b/fs/ext2/super.c index dda860562ca3..7fab2b3b5b39 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -587,7 +587,7 @@ static int parse_options(char *options, struct super_block *sb, case Opt_xip: ext2_msg(sb, KERN_INFO, "use dax instead of xip"); set_opt(opts->s_mount_opt, XIP); - /* Fall through */ + fallthrough; case Opt_dax: #ifdef CONFIG_FS_DAX ext2_msg(sb, KERN_WARNING, diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 1afa5a4bcb5f..619dd35ddd48 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -110,7 +110,7 @@ config EXT4_KUNIT_TESTS This builds the ext4 KUnit tests. KUnit tests run during boot and output the results to the debug log - in TAP format (http://testanything.org/). Only useful for kernel devs + in TAP format (https://testanything.org/). Only useful for kernel devs running KUnit test harness and are not for inclusion into a production build. diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 1ba46d87cdf1..48c3df47748d 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -413,7 +413,8 @@ verified: * Return buffer_head on success or an ERR_PTR in case of failure. */ struct buffer_head * -ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) +ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group, + bool ignore_locked) { struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -441,6 +442,12 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) return ERR_PTR(-ENOMEM); } + if (ignore_locked && buffer_locked(bh)) { + /* buffer under IO already, return if called for prefetching */ + put_bh(bh); + return NULL; + } + if (bitmap_uptodate(bh)) goto verify; @@ -487,10 +494,11 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) * submit the buffer_head for reading */ set_buffer_new(bh); - trace_ext4_read_block_bitmap_load(sb, block_group); + trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked); bh->b_end_io = ext4_end_bitmap_read; get_bh(bh); - submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh); + submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO | + (ignore_locked ? REQ_RAHEAD : 0), bh); return bh; verify: err = ext4_validate_block_bitmap(sb, desc, block_group, bh); @@ -534,7 +542,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) struct buffer_head *bh; int err; - bh = ext4_read_block_bitmap_nowait(sb, block_group); + bh = ext4_read_block_bitmap_nowait(sb, block_group, false); if (IS_ERR(bh)) return bh; err = ext4_wait_block_bitmap(sb, block_group, bh); diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 16e9b2fda03a..c54ba52f2dd4 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -24,6 +24,7 @@ struct ext4_system_zone { struct rb_node node; ext4_fsblk_t start_blk; unsigned int count; + u32 ino; }; static struct kmem_cache *ext4_system_zone_cachep; @@ -45,7 +46,8 @@ void ext4_exit_system_zone(void) static inline int can_merge(struct ext4_system_zone *entry1, struct ext4_system_zone *entry2) { - if ((entry1->start_blk + entry1->count) == entry2->start_blk) + if ((entry1->start_blk + entry1->count) == entry2->start_blk && + entry1->ino == entry2->ino) return 1; return 0; } @@ -66,9 +68,9 @@ static void release_system_zone(struct ext4_system_blocks *system_blks) */ static int add_system_zone(struct ext4_system_blocks *system_blks, ext4_fsblk_t start_blk, - unsigned int count) + unsigned int count, u32 ino) { - struct ext4_system_zone *new_entry = NULL, *entry; + struct ext4_system_zone *new_entry, *entry; struct rb_node **n = &system_blks->root.rb_node, *node; struct rb_node *parent = NULL, *new_node = NULL; @@ -79,30 +81,21 @@ static int add_system_zone(struct ext4_system_blocks *system_blks, n = &(*n)->rb_left; else if (start_blk >= (entry->start_blk + entry->count)) n = &(*n)->rb_right; - else { - if (start_blk + count > (entry->start_blk + - entry->count)) - entry->count = (start_blk + count - - entry->start_blk); - new_node = *n; - new_entry = rb_entry(new_node, struct ext4_system_zone, - node); - break; - } + else /* Unexpected overlap of system zones. */ + return -EFSCORRUPTED; } - if (!new_entry) { - new_entry = kmem_cache_alloc(ext4_system_zone_cachep, - GFP_KERNEL); - if (!new_entry) - return -ENOMEM; - new_entry->start_blk = start_blk; - new_entry->count = count; - new_node = &new_entry->node; - - rb_link_node(new_node, parent, n); - rb_insert_color(new_node, &system_blks->root); - } + new_entry = kmem_cache_alloc(ext4_system_zone_cachep, + GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + new_entry->start_blk = start_blk; + new_entry->count = count; + new_entry->ino = ino; + new_node = &new_entry->node; + + rb_link_node(new_node, parent, n); + rb_insert_color(new_node, &system_blks->root); /* Can we merge to the left? */ node = rb_prev(new_node); @@ -151,40 +144,6 @@ static void debug_print_tree(struct ext4_sb_info *sbi) printk(KERN_CONT "\n"); } -/* - * Returns 1 if the passed-in block region (start_blk, - * start_blk+count) is valid; 0 if some part of the block region - * overlaps with filesystem metadata blocks. - */ -static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi, - struct ext4_system_blocks *system_blks, - ext4_fsblk_t start_blk, - unsigned int count) -{ - struct ext4_system_zone *entry; - struct rb_node *n; - - if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || - (start_blk + count < start_blk) || - (start_blk + count > ext4_blocks_count(sbi->s_es))) - return 0; - - if (system_blks == NULL) - return 1; - - n = system_blks->root.rb_node; - while (n) { - entry = rb_entry(n, struct ext4_system_zone, node); - if (start_blk + count - 1 < entry->start_blk) - n = n->rb_left; - else if (start_blk >= (entry->start_blk + entry->count)) - n = n->rb_right; - else - return 0; - } - return 1; -} - static int ext4_protect_reserved_inode(struct super_block *sb, struct ext4_system_blocks *system_blks, u32 ino) @@ -214,19 +173,18 @@ static int ext4_protect_reserved_inode(struct super_block *sb, if (n == 0) { i++; } else { - if (!ext4_data_block_valid_rcu(sbi, system_blks, - map.m_pblk, n)) { - err = -EFSCORRUPTED; - __ext4_error(sb, __func__, __LINE__, -err, - map.m_pblk, "blocks %llu-%llu " - "from inode %u overlap system zone", - map.m_pblk, - map.m_pblk + map.m_len - 1, ino); + err = add_system_zone(system_blks, map.m_pblk, n, ino); + if (err < 0) { + if (err == -EFSCORRUPTED) { + __ext4_error(sb, __func__, __LINE__, + -err, map.m_pblk, + "blocks %llu-%llu from inode %u overlap system zone", + map.m_pblk, + map.m_pblk + map.m_len - 1, + ino); + } break; } - err = add_system_zone(system_blks, map.m_pblk, n); - if (err < 0) - break; i += n; } } @@ -262,14 +220,6 @@ int ext4_setup_system_zone(struct super_block *sb) int flex_size = ext4_flex_bg_size(sbi); int ret; - if (!test_opt(sb, BLOCK_VALIDITY)) { - if (sbi->system_blks) - ext4_release_system_zone(sb); - return 0; - } - if (sbi->system_blks) - return 0; - system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL); if (!system_blks) return -ENOMEM; @@ -277,22 +227,25 @@ int ext4_setup_system_zone(struct super_block *sb) for (i=0; i < ngroups; i++) { cond_resched(); if (ext4_bg_has_super(sb, i) && - ((i < 5) || ((i % flex_size) == 0))) - add_system_zone(system_blks, + ((i < 5) || ((i % flex_size) == 0))) { + ret = add_system_zone(system_blks, ext4_group_first_block_no(sb, i), - ext4_bg_num_gdb(sb, i) + 1); + ext4_bg_num_gdb(sb, i) + 1, 0); + if (ret) + goto err; + } gdp = ext4_get_group_desc(sb, i, NULL); ret = add_system_zone(system_blks, - ext4_block_bitmap(sb, gdp), 1); + ext4_block_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, - ext4_inode_bitmap(sb, gdp), 1); + ext4_inode_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group); + sbi->s_itb_per_group, 0); if (ret) goto err; } @@ -341,11 +294,24 @@ void ext4_release_system_zone(struct super_block *sb) call_rcu(&system_blks->rcu, ext4_destroy_system_zone); } -int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, +/* + * Returns 1 if the passed-in block region (start_blk, + * start_blk+count) is valid; 0 if some part of the block region + * overlaps with some other filesystem metadata blocks. + */ +int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, unsigned int count) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_system_blocks *system_blks; - int ret; + struct ext4_system_zone *entry; + struct rb_node *n; + int ret = 1; + + if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || + (start_blk + count < start_blk) || + (start_blk + count > ext4_blocks_count(sbi->s_es))) + return 0; /* * Lock the system zone to prevent it being released concurrently @@ -354,8 +320,22 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, */ rcu_read_lock(); system_blks = rcu_dereference(sbi->system_blks); - ret = ext4_data_block_valid_rcu(sbi, system_blks, start_blk, - count); + if (system_blks == NULL) + goto out_rcu; + + n = system_blks->root.rb_node; + while (n) { + entry = rb_entry(n, struct ext4_system_zone, node); + if (start_blk + count - 1 < entry->start_blk) + n = n->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = n->rb_right; + else { + ret = (entry->ino == inode->i_ino); + break; + } + } +out_rcu: rcu_read_unlock(); return ret; } @@ -374,8 +354,7 @@ int ext4_check_blockref(const char *function, unsigned int line, while (bref < p+max) { blk = le32_to_cpu(*bref++); if (blk && - unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), - blk, 1))) { + unlikely(!ext4_inode_block_valid(inode, blk, 1))) { ext4_error_inode(inode, function, line, blk, "invalid block"); return -EFSCORRUPTED; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 42f5060f3cdf..523e00d7b392 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -434,10 +434,36 @@ struct flex_groups { #define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define EXT4_FL_USER_VISIBLE 0x725BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x624BC0FF /* User modifiable flags */ - -/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ +/* User modifiable flags */ +#define EXT4_FL_USER_MODIFIABLE (EXT4_SECRM_FL | \ + EXT4_UNRM_FL | \ + EXT4_COMPR_FL | \ + EXT4_SYNC_FL | \ + EXT4_IMMUTABLE_FL | \ + EXT4_APPEND_FL | \ + EXT4_NODUMP_FL | \ + EXT4_NOATIME_FL | \ + EXT4_JOURNAL_DATA_FL | \ + EXT4_NOTAIL_FL | \ + EXT4_DIRSYNC_FL | \ + EXT4_TOPDIR_FL | \ + EXT4_EXTENTS_FL | \ + 0x00400000 /* EXT4_EOFBLOCKS_FL */ | \ + EXT4_DAX_FL | \ + EXT4_PROJINHERIT_FL | \ + EXT4_CASEFOLD_FL) + +/* User visible flags */ +#define EXT4_FL_USER_VISIBLE (EXT4_FL_USER_MODIFIABLE | \ + EXT4_DIRTY_FL | \ + EXT4_COMPRBLK_FL | \ + EXT4_NOCOMPR_FL | \ + EXT4_ENCRYPT_FL | \ + EXT4_INDEX_FL | \ + EXT4_VERITY_FL | \ + EXT4_INLINE_DATA_FL) + +/* Flags we can manipulate with through FS_IOC_FSSETXATTR */ #define EXT4_FL_XFLAG_VISIBLE (EXT4_SYNC_FL | \ EXT4_IMMUTABLE_FL | \ EXT4_APPEND_FL | \ @@ -669,8 +695,6 @@ enum { /* * ioctl commands */ -#define EXT4_IOC_GETFLAGS FS_IOC_GETFLAGS -#define EXT4_IOC_SETFLAGS FS_IOC_SETFLAGS #define EXT4_IOC_GETVERSION _IOR('f', 3, long) #define EXT4_IOC_SETVERSION _IOW('f', 4, long) #define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION @@ -687,17 +711,11 @@ enum { #define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64) #define EXT4_IOC_SWAP_BOOT _IO('f', 17) #define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18) -#define EXT4_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY -#define EXT4_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT -#define EXT4_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY /* ioctl codes 19--39 are reserved for fscrypt */ #define EXT4_IOC_CLEAR_ES_CACHE _IO('f', 40) #define EXT4_IOC_GETSTATE _IOW('f', 41, __u32) #define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap) -#define EXT4_IOC_FSGETXATTR FS_IOC_FSGETXATTR -#define EXT4_IOC_FSSETXATTR FS_IOC_FSSETXATTR - #define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32) /* @@ -722,8 +740,6 @@ enum { /* * ioctl commands in 32 bit emulation */ -#define EXT4_IOC32_GETFLAGS FS_IOC32_GETFLAGS -#define EXT4_IOC32_SETFLAGS FS_IOC32_SETFLAGS #define EXT4_IOC32_GETVERSION _IOR('f', 3, int) #define EXT4_IOC32_SETVERSION _IOW('f', 4, int) #define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) @@ -1054,6 +1070,7 @@ struct ext4_inode_info { struct timespec64 i_crtime; /* mballoc */ + atomic_t i_prealloc_active; struct list_head i_prealloc_list; spinlock_t i_prealloc_lock; @@ -1172,6 +1189,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */ +#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000 #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ @@ -1501,10 +1519,13 @@ struct ext4_sb_info { unsigned int s_mb_stats; unsigned int s_mb_order2_reqs; unsigned int s_mb_group_prealloc; + unsigned int s_mb_max_inode_prealloc; unsigned int s_max_dir_size_kb; /* where last allocation was done - for stream allocation */ unsigned long s_mb_last_group; unsigned long s_mb_last_start; + unsigned int s_mb_prefetch; + unsigned int s_mb_prefetch_limit; /* stats for buddy allocator */ atomic_t s_bal_reqs; /* number of reqs with len > 1 */ @@ -1572,6 +1593,8 @@ struct ext4_sb_info { struct ratelimit_state s_err_ratelimit_state; struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; + atomic_t s_warning_count; + atomic_t s_msg_count; /* Encryption context for '-o test_dummy_encryption' */ struct fscrypt_dummy_context s_dummy_enc_ctx; @@ -1585,6 +1608,9 @@ struct ext4_sb_info { #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; #endif + /* Record the errseq of the backing block device */ + errseq_t s_bdev_wb_err; + spinlock_t s_bdev_wb_lock; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -2313,9 +2339,15 @@ struct ext4_lazy_init { struct mutex li_list_mtx; }; +enum ext4_li_mode { + EXT4_LI_MODE_PREFETCH_BBITMAP, + EXT4_LI_MODE_ITABLE, +}; + struct ext4_li_request { struct super_block *lr_super; - struct ext4_sb_info *lr_sbi; + enum ext4_li_mode lr_mode; + ext4_group_t lr_first_not_zeroed; ext4_group_t lr_next_group; struct list_head lr_request; unsigned long lr_next_sched; @@ -2446,7 +2478,8 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb, - ext4_group_t block_group); + ext4_group_t block_group, + bool ignore_locked); extern int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, struct buffer_head *bh); @@ -2651,9 +2684,15 @@ extern int ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); extern int ext4_mb_reserve_blocks(struct super_block *, int); -extern void ext4_discard_preallocations(struct inode *); +extern void ext4_discard_preallocations(struct inode *, unsigned int); extern int __init ext4_init_mballoc(void); extern void ext4_exit_mballoc(void); +extern ext4_group_t ext4_mb_prefetch(struct super_block *sb, + ext4_group_t group, + unsigned int nr, int *cnt); +extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, + unsigned int nr); + extern void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags); @@ -2765,8 +2804,7 @@ extern int ext4_search_dir(struct buffer_head *bh, struct ext4_filename *fname, unsigned int offset, struct ext4_dir_entry_2 **res_dir); -extern int ext4_generic_delete_entry(handle_t *handle, - struct inode *dir, +extern int ext4_generic_delete_entry(struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, void *entry_buf, @@ -2924,12 +2962,6 @@ do { \ #endif -extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb, - __u32 compat); -extern int ext4_update_rocompat_feature(handle_t *handle, - struct super_block *sb, __u32 rocompat); -extern int ext4_update_incompat_feature(handle_t *handle, - struct super_block *sb, __u32 incompat); extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, @@ -3145,6 +3177,7 @@ struct ext4_group_info { (1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT) #define EXT4_GROUP_INFO_IBITMAP_CORRUPT \ (1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT) +#define EXT4_GROUP_INFO_BBITMAP_READ_BIT 4 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) @@ -3159,6 +3192,8 @@ struct ext4_group_info { (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \ (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_TEST_AND_SET_READ(grp) \ + (test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state))) #define EXT4_MAX_CONTENTION 8 #define EXT4_CONTENTION_THRESHOLD 2 @@ -3363,9 +3398,9 @@ extern void ext4_release_system_zone(struct super_block *sb); extern int ext4_setup_system_zone(struct super_block *sb); extern int __init ext4_init_system_zone(void); extern void ext4_exit_system_zone(void); -extern int ext4_data_block_valid(struct ext4_sb_info *sbi, - ext4_fsblk_t start_blk, - unsigned int count); +extern int ext4_inode_block_valid(struct inode *inode, + ext4_fsblk_t start_blk, + unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 0c76cdd44d90..760b9ee49dc0 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -195,6 +195,28 @@ static void ext4_journal_abort_handle(const char *caller, unsigned int line, jbd2_journal_abort_handle(handle); } +static void ext4_check_bdev_write_error(struct super_block *sb) +{ + struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; + struct ext4_sb_info *sbi = EXT4_SB(sb); + int err; + + /* + * If the block device has write error flag, it may have failed to + * async write out metadata buffers in the background. In this case, + * we could read old data from disk and write it out again, which + * may lead to on-disk filesystem inconsistency. + */ + if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) { + spin_lock(&sbi->s_bdev_wb_lock); + err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err); + spin_unlock(&sbi->s_bdev_wb_lock); + if (err) + ext4_error_err(sb, -err, + "Error while async write back metadata"); + } +} + int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct buffer_head *bh) { @@ -202,6 +224,9 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line, might_sleep(); + if (bh->b_bdev->bd_super) + ext4_check_bdev_write_error(bh->b_bdev->bd_super); + if (ext4_handle_valid(handle)) { err = jbd2_journal_get_write_access(handle, bh); if (err) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 221f240eae60..a0481582187a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -100,7 +100,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; @@ -340,7 +340,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) */ if (lblock + len <= lblock) return 0; - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); + return ext4_inode_block_valid(inode, block, len); } static int ext4_valid_extent_idx(struct inode *inode, @@ -348,7 +348,7 @@ static int ext4_valid_extent_idx(struct inode *inode, { ext4_fsblk_t block = ext4_idx_pblock(ext_idx); - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); + return ext4_inode_block_valid(inode, block, 1); } static int ext4_valid_extent_entries(struct inode *inode, @@ -507,14 +507,10 @@ __read_extent_tree_block(const char *function, unsigned int line, } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; - if (!ext4_has_feature_journal(inode->i_sb) || - (inode->i_ino != - le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) { - err = __ext4_ext_check(function, line, inode, - ext_block_hdr(bh), depth, pblk); - if (err) - goto errout; - } + err = __ext4_ext_check(function, line, inode, + ext_block_hdr(bh), depth, pblk); + if (err) + goto errout; set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries @@ -693,10 +689,8 @@ void ext4_ext_drop_refs(struct ext4_ext_path *path) return; depth = path->p_depth; for (i = 0; i <= depth; i++, path++) { - if (path->p_bh) { - brelse(path->p_bh); - path->p_bh = NULL; - } + brelse(path->p_bh); + path->p_bh = NULL; } } @@ -1915,7 +1909,7 @@ out: /* * ext4_ext_insert_extent: - * tries to merge requsted extent into the existing extent or + * tries to merge requested extent into the existing extent or * inserts requested extent as new one into the tree, * creating new leaf in the no-space case. */ @@ -3125,7 +3119,7 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) * * * Splits extent [a, b] into two extents [a, @split) and [@split, b], states - * of which are deterimined by split_flag. + * of which are determined by split_flag. * * There are two cases: * a> the extent are splitted into two extent. @@ -3650,7 +3644,7 @@ static int ext4_split_convert_extents(handle_t *handle, eof_block = map->m_lblk + map->m_len; /* * It is safe to convert extent to initialized via explicit - * zeroout only if extent is fully insde i_size or new_size. + * zeroout only if extent is fully inside i_size or new_size. */ depth = ext_depth(inode); ex = path[depth].p_ext; @@ -4272,7 +4266,7 @@ got_allocated_blocks: * not a good idea to call discard here directly, * but otherwise we'd need to call it every free(). */ - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; ext4_free_blocks(handle, inode, NULL, newblock, @@ -4495,7 +4489,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, } /* - * Round up offset. This is not fallocate, we neet to zero out + * Round up offset. This is not fallocate, we need to zero out * blocks, so convert interior block aligned part of the range to * unwritten and possibly manually zero out unaligned parts of the * range. @@ -5299,7 +5293,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) } down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ret = ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start); @@ -5313,7 +5307,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ret = ext4_ext_shift_extents(inode, handle, punch_stop, punch_stop - punch_start, SHIFT_LEFT); @@ -5445,7 +5439,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) goto out_stop; down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); path = ext4_find_extent(inode, offset_lblk, NULL, 0); if (IS_ERR(path)) { @@ -5579,7 +5573,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, } ex1 = path1[path1->p_depth].p_ext; ex2 = path2[path2->p_depth].p_ext; - /* Do we have somthing to swap ? */ + /* Do we have something to swap ? */ if (unlikely(!ex2 || !ex1)) goto finish; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 129cc1dd6b79..7d61069531d3 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -145,10 +145,9 @@ static int ext4_release_file(struct inode *inode, struct file *filp) /* if we are the last writer on the inode, drop the block reservation */ if ((filp->f_mode & FMODE_WRITE) && (atomic_read(&inode->i_writecount) == 1) && - !EXT4_I(inode)->i_reserved_data_blocks) - { + !EXT4_I(inode)->i_reserved_data_blocks) { down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); } if (is_dx(inode) && filp->private_data) @@ -428,6 +427,10 @@ restart: */ if (*ilock_shared && (!IS_NOSEC(inode) || *extend || !ext4_overwrite_io(inode, offset, count))) { + if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; + } inode_unlock_shared(inode); *ilock_shared = false; inode_lock(inode); @@ -812,7 +815,7 @@ out: return err; } -static int ext4_file_open(struct inode * inode, struct file * filp) +static int ext4_file_open(struct inode *inode, struct file *filp) { int ret; diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 3e133793a5a3..2924261226e0 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -233,7 +233,7 @@ static int __ext4fs_dirhash(const char *name, int len, break; case DX_HASH_HALF_MD4_UNSIGNED: str2hashbuf = str2hashbuf_unsigned; - /* fall through */ + fallthrough; case DX_HASH_HALF_MD4: p = name; while (len > 0) { @@ -247,7 +247,7 @@ static int __ext4fs_dirhash(const char *name, int len, break; case DX_HASH_TEA_UNSIGNED: str2hashbuf = str2hashbuf_unsigned; - /* fall through */ + fallthrough; case DX_HASH_TEA: p = name; while (len > 0) { diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index be2b66eb65f7..80c9f33800be 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -696,7 +696,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; @@ -858,8 +858,7 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, else if (ext4_should_journal_data(inode)) flags |= EXT4_FREE_BLOCKS_FORGET; - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free, - count)) { + if (!ext4_inode_block_valid(inode, block_to_free, count)) { EXT4_ERROR_INODE(inode, "attempt to clear invalid " "blocks %llu len %lu", (unsigned long long) block_to_free, count); @@ -1004,8 +1003,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, if (!nr) continue; /* A hole */ - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), - nr, 1)) { + if (!ext4_inode_block_valid(inode, nr, 1)) { EXT4_ERROR_INODE(inode, "invalid indirect mapped " "block %lu (level %d)", @@ -1182,21 +1180,21 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); i_data[EXT4_IND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_IND_BLOCK: nr = i_data[EXT4_DIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); i_data[EXT4_DIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_DIND_BLOCK: nr = i_data[EXT4_TIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); i_data[EXT4_TIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_TIND_BLOCK: ; } @@ -1436,7 +1434,7 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); i_data[EXT4_IND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_IND_BLOCK: if (++n >= n2) break; @@ -1445,7 +1443,7 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); i_data[EXT4_DIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_DIND_BLOCK: if (++n >= n2) break; @@ -1454,7 +1452,7 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); i_data[EXT4_TIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_TIND_BLOCK: ; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index c3a1ad2db122..75c97bca0815 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -276,7 +276,7 @@ static int ext4_create_inline_data(handle_t *handle, len = 0; } - /* Insert the the xttr entry. */ + /* Insert the xttr entry. */ i.value = value; i.value_len = len; @@ -1706,7 +1706,7 @@ int ext4_delete_inline_entry(handle_t *handle, if (err) goto out; - err = ext4_generic_delete_entry(handle, dir, de_del, bh, + err = ext4_generic_delete_entry(dir, de_del, bh, inline_start, inline_size, 0); if (err) goto out; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 44bad4bb8831..bf596467c234 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -383,7 +383,7 @@ void ext4_da_update_reserve_space(struct inode *inode, */ if ((ei->i_reserved_data_blocks == 0) && !inode_is_open_for_write(inode)) - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); } static int __check_block_validity(struct inode *inode, const char *func, @@ -394,8 +394,7 @@ static int __check_block_validity(struct inode *inode, const char *func, (inode->i_ino == le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) return 0; - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk, - map->m_len)) { + if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock %llu " "(length %d)", (unsigned long) map->m_lblk, @@ -3288,7 +3287,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait) if (PageChecked(page)) return 0; if (journal) - return jbd2_journal_try_to_free_buffers(journal, page, wait); + return jbd2_journal_try_to_free_buffers(journal, page); else return try_to_free_buffers(page); } @@ -4056,7 +4055,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) if (stop_block > first_block) { down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ret = ext4_es_remove_extent(inode, first_block, stop_block - first_block); @@ -4163,7 +4162,7 @@ int ext4_truncate(struct inode *inode) trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) - return 0; + goto out_trace; if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); @@ -4172,16 +4171,14 @@ int ext4_truncate(struct inode *inode) int has_inline = 1; err = ext4_inline_data_truncate(inode, &has_inline); - if (err) - return err; - if (has_inline) - return 0; + if (err || has_inline) + goto out_trace; } /* If we zero-out tail of the page, we have to create jinode for jbd2 */ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { if (ext4_inode_attach_jinode(inode) < 0) - return 0; + goto out_trace; } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) @@ -4190,8 +4187,10 @@ int ext4_truncate(struct inode *inode) credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_trace; + } if (inode->i_size & (inode->i_sb->s_blocksize - 1)) ext4_block_truncate_page(handle, mapping, inode->i_size); @@ -4211,7 +4210,7 @@ int ext4_truncate(struct inode *inode) down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) err = ext4_ext_truncate(handle, inode); @@ -4242,6 +4241,7 @@ out_stop: err = err2; ext4_journal_stop(handle); +out_trace: trace_ext4_truncate_exit(inode); return err; } @@ -4760,7 +4760,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ret = 0; if (ei->i_file_acl && - !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { + !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) { ext4_error_inode(inode, function, line, 0, "iget: bad extended attribute block %llu", ei->i_file_acl); @@ -4901,7 +4901,7 @@ static void __ext4_update_other_inode_time(struct super_block *sb, (inode->i_state & I_DIRTY_TIME)) { struct ext4_inode_info *ei = EXT4_I(inode); - inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED); + inode->i_state &= ~I_DIRTY_TIME; spin_unlock(&inode->i_lock); spin_lock(&ei->i_raw_lock); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 999cf6add39c..36eca3bc036a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -202,7 +202,7 @@ static long swap_inode_boot_loader(struct super_block *sb, reset_inode_seed(inode); reset_inode_seed(inode_bl); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { @@ -819,12 +819,12 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) switch (cmd) { case FS_IOC_GETFSMAP: return ext4_ioc_getfsmap(sb, (void __user *)arg); - case EXT4_IOC_GETFLAGS: + case FS_IOC_GETFLAGS: flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (S_ISREG(inode->i_mode)) flags &= ~EXT4_PROJINHERIT_FL; return put_user(flags, (int __user *) arg); - case EXT4_IOC_SETFLAGS: { + case FS_IOC_SETFLAGS: { int err; if (!inode_owner_or_capable(inode)) @@ -1129,12 +1129,12 @@ resizefs_out: case EXT4_IOC_PRECACHE_EXTENTS: return ext4_ext_precache(inode); - case EXT4_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); - case EXT4_IOC_GET_ENCRYPTION_PWSALT: { + case FS_IOC_GET_ENCRYPTION_PWSALT: { #ifdef CONFIG_FS_ENCRYPTION int err, err2; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -1174,7 +1174,7 @@ resizefs_out: return -EOPNOTSUPP; #endif } - case EXT4_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); @@ -1236,7 +1236,7 @@ resizefs_out: case EXT4_IOC_GET_ES_CACHE: return ext4_ioctl_get_es_cache(filp, arg); - case EXT4_IOC_FSGETXATTR: + case FS_IOC_FSGETXATTR: { struct fsxattr fa; @@ -1247,7 +1247,7 @@ resizefs_out: return -EFAULT; return 0; } - case EXT4_IOC_FSSETXATTR: + case FS_IOC_FSSETXATTR: { struct fsxattr fa, old_fa; int err; @@ -1313,11 +1313,11 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { /* These are just misnamed, they actually get/put from/to user an int */ switch (cmd) { - case EXT4_IOC32_GETFLAGS: - cmd = EXT4_IOC_GETFLAGS; + case FS_IOC32_GETFLAGS: + cmd = FS_IOC_GETFLAGS; break; - case EXT4_IOC32_SETFLAGS: - cmd = EXT4_IOC_SETFLAGS; + case FS_IOC32_SETFLAGS: + cmd = FS_IOC_SETFLAGS; break; case EXT4_IOC32_GETVERSION: cmd = EXT4_IOC_GETVERSION; @@ -1361,9 +1361,9 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_RESIZE_FS: case FITRIM: case EXT4_IOC_PRECACHE_EXTENTS: - case EXT4_IOC_SET_ENCRYPTION_POLICY: - case EXT4_IOC_GET_ENCRYPTION_PWSALT: - case EXT4_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_PWSALT: + case FS_IOC_GET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_POLICY_EX: case FS_IOC_ADD_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY: @@ -1377,8 +1377,8 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_CLEAR_ES_CACHE: case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: - case EXT4_IOC_FSGETXATTR: - case EXT4_IOC_FSSETXATTR: + case FS_IOC_FSGETXATTR: + case FS_IOC_FSSETXATTR: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c0a331e2feb0..132c118d12e1 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -922,7 +922,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) bh[i] = NULL; continue; } - bh[i] = ext4_read_block_bitmap_nowait(sb, group); + bh[i] = ext4_read_block_bitmap_nowait(sb, group, false); if (IS_ERR(bh[i])) { err = PTR_ERR(bh[i]); bh[i] = NULL; @@ -1279,9 +1279,6 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - BUG_ON(e4b->bd_bitmap_page == NULL); - BUG_ON(e4b->bd_buddy_page == NULL); - return 0; err: @@ -1743,10 +1740,6 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, } -/* - * regular allocator, for general purposes allocation - */ - static void ext4_mb_check_limits(struct ext4_allocation_context *ac, struct ext4_buddy *e4b, int finish_group) @@ -2119,13 +2112,11 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); - free = grp->bb_free; - if (free == 0) - return false; - if (cr <= 2 && free < ac->ac_g_ex.fe_len) + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) + free = grp->bb_free; + if (free == 0) return false; fragments = grp->bb_fragments; @@ -2142,8 +2133,10 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ((group % flex_size) == 0)) return false; - if ((ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) || - (free / fragments) >= ac->ac_g_ex.fe_len) + if (free < ac->ac_g_ex.fe_len) + return false; + + if (ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) return true; if (grp->bb_largest_free_order < ac->ac_2order) @@ -2177,6 +2170,7 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, { struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct super_block *sb = ac->ac_sb; + struct ext4_sb_info *sbi = EXT4_SB(sb); bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK; ext4_grpblk_t free; int ret = 0; @@ -2195,7 +2189,25 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { - ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS); + struct ext4_group_desc *gdp = + ext4_get_group_desc(sb, group, NULL); + int ret; + + /* cr=0/1 is a very optimistic search to find large + * good chunks almost for free. If buddy data is not + * ready, then this optimization makes no sense. But + * we never skip the first block group in a flex_bg, + * since this gets used for metadata block allocation, + * and we want to make sure we locate metadata blocks + * in the first block group in the flex_bg if possible. + */ + if (cr < 2 && + (!sbi->s_log_groups_per_flex || + ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) && + !(ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) + return 0; + ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) return ret; } @@ -2209,15 +2221,95 @@ out: return ret; } +/* + * Start prefetching @nr block bitmaps starting at @group. + * Return the next group which needs to be prefetched. + */ +ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, + unsigned int nr, int *cnt) +{ + ext4_group_t ngroups = ext4_get_groups_count(sb); + struct buffer_head *bh; + struct blk_plug plug; + + blk_start_plug(&plug); + while (nr-- > 0) { + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, + NULL); + struct ext4_group_info *grp = ext4_get_group_info(sb, group); + + /* + * Prefetch block groups with free blocks; but don't + * bother if it is marked uninitialized on disk, since + * it won't require I/O to read. Also only try to + * prefetch once, so we avoid getblk() call, which can + * be expensive. + */ + if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) && + EXT4_MB_GRP_NEED_INIT(grp) && + ext4_free_group_clusters(sb, gdp) > 0 && + !(ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { + bh = ext4_read_block_bitmap_nowait(sb, group, true); + if (bh && !IS_ERR(bh)) { + if (!buffer_uptodate(bh) && cnt) + (*cnt)++; + brelse(bh); + } + } + if (++group >= ngroups) + group = 0; + } + blk_finish_plug(&plug); + return group; +} + +/* + * Prefetching reads the block bitmap into the buffer cache; but we + * need to make sure that the buddy bitmap in the page cache has been + * initialized. Note that ext4_mb_init_group() will block if the I/O + * is not yet completed, or indeed if it was not initiated by + * ext4_mb_prefetch did not start the I/O. + * + * TODO: We should actually kick off the buddy bitmap setup in a work + * queue when the buffer I/O is completed, so that we don't block + * waiting for the block allocation bitmap read to finish when + * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator(). + */ +void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, + unsigned int nr) +{ + while (nr-- > 0) { + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, + NULL); + struct ext4_group_info *grp = ext4_get_group_info(sb, group); + + if (!group) + group = ext4_get_groups_count(sb); + group--; + grp = ext4_get_group_info(sb, group); + + if (EXT4_MB_GRP_NEED_INIT(grp) && + ext4_free_group_clusters(sb, gdp) > 0 && + !(ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { + if (ext4_mb_init_group(sb, group, GFP_NOFS)) + break; + } + } +} + static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { - ext4_group_t ngroups, group, i; + ext4_group_t prefetch_grp = 0, ngroups, group, i; int cr = -1; int err = 0, first_err = 0; + unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; struct super_block *sb; struct ext4_buddy e4b; + int lost; sb = ac->ac_sb; sbi = EXT4_SB(sb); @@ -2237,8 +2329,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) goto out; /* - * ac->ac2_order is set only if the fe_len is a power of 2 - * if ac2_order is set we also set criteria to 0 so that we + * ac->ac_2order is set only if the fe_len is a power of 2 + * if ac->ac_2order is set we also set criteria to 0 so that we * try exact allocation using buddy. */ i = fls(ac->ac_g_ex.fe_len); @@ -2282,6 +2374,7 @@ repeat: * from the goal value specified */ group = ac->ac_g_ex.fe_group; + prefetch_grp = group; for (i = 0; i < ngroups; group++, i++) { int ret = 0; @@ -2293,6 +2386,29 @@ repeat: if (group >= ngroups) group = 0; + /* + * Batch reads of the block allocation bitmaps + * to get multiple READs in flight; limit + * prefetching at cr=0/1, otherwise mballoc can + * spend a lot of time loading imperfect groups + */ + if ((prefetch_grp == group) && + (cr > 1 || + prefetch_ios < sbi->s_mb_prefetch_limit)) { + unsigned int curr_ios = prefetch_ios; + + nr = sbi->s_mb_prefetch; + if (ext4_has_feature_flex_bg(sb)) { + nr = (group / sbi->s_mb_prefetch) * + sbi->s_mb_prefetch; + nr = nr + sbi->s_mb_prefetch - group; + } + prefetch_grp = ext4_mb_prefetch(sb, group, + nr, &prefetch_ios); + if (prefetch_ios == curr_ios) + nr = 0; + } + /* This now checks without needing the buddy page */ ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { @@ -2341,22 +2457,24 @@ repeat: * We've been searching too long. Let's try to allocate * the best chunk we've found so far */ - ext4_mb_try_best_found(ac, &e4b); if (ac->ac_status != AC_STATUS_FOUND) { /* * Someone more lucky has already allocated it. * The only thing we can do is just take first * found block(s) - printk(KERN_DEBUG "EXT4-fs: someone won our chunk\n"); */ + lost = atomic_inc_return(&sbi->s_mb_lost_chunks); + mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n", + ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, + ac->ac_b_ex.fe_len, lost); + ac->ac_b_ex.fe_group = 0; ac->ac_b_ex.fe_start = 0; ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; ac->ac_flags |= EXT4_MB_HINT_FIRST; cr = 3; - atomic_inc(&sbi->s_mb_lost_chunks); goto repeat; } } @@ -2367,6 +2485,10 @@ out: mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n", ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status, ac->ac_flags, cr, err); + + if (nr) + ext4_mb_prefetch_fini(sb, prefetch_grp, nr); + return err; } @@ -2439,7 +2561,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); - seq_printf(seq, " ]\n"); + seq_puts(seq, " ]\n"); return 0; } @@ -2613,6 +2735,26 @@ static int ext4_mb_init_backend(struct super_block *sb) goto err_freebuddy; } + if (ext4_has_feature_flex_bg(sb)) { + /* a single flex group is supposed to be read by a single IO */ + sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex; + sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ + } else { + sbi->s_mb_prefetch = 32; + } + if (sbi->s_mb_prefetch > ext4_get_groups_count(sb)) + sbi->s_mb_prefetch = ext4_get_groups_count(sb); + /* now many real IOs to prefetch within a single allocation at cr=0 + * given cr=0 is an CPU-related optimization we shouldn't try to + * load too many groups, at some point we should start to use what + * we've got in memory. + * with an average random access time 5ms, it'd take a second to get + * 200 groups (* N with flex_bg), so let's make this limit 4 + */ + sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4; + if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb)) + sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb); + return 0; err_freebuddy: @@ -2736,6 +2878,7 @@ int ext4_mb_init(struct super_block *sb) sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; + sbi->s_mb_max_inode_prealloc = MB_DEFAULT_MAX_INODE_PREALLOC; /* * The default group preallocation is 512, which for 4k block * sizes translates to 2 megabytes. However for bigalloc file @@ -3090,7 +3233,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (!ext4_data_block_valid(sbi, block, len)) { + if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error @@ -3674,6 +3817,26 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); } +static void ext4_mb_mark_pa_deleted(struct super_block *sb, + struct ext4_prealloc_space *pa) +{ + struct ext4_inode_info *ei; + + if (pa->pa_deleted) { + ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n", + pa->pa_type, pa->pa_pstart, pa->pa_lstart, + pa->pa_len); + return; + } + + pa->pa_deleted = 1; + + if (pa->pa_type == MB_INODE_PA) { + ei = EXT4_I(pa->pa_inode); + atomic_dec(&ei->i_prealloc_active); + } +} + static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; @@ -3706,7 +3869,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, return; } - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); grp_blk = pa->pa_pstart; @@ -3830,6 +3993,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) spin_lock(pa->pa_obj_lock); list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); + atomic_inc(&ei->i_prealloc_active); } /* @@ -4040,7 +4204,7 @@ repeat: } /* seems this one can be freed ... */ - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); /* we can trust pa_free ... */ free += pa->pa_free; @@ -4103,7 +4267,7 @@ out_dbg: * * FIXME!! Make sure it is valid at all the call sites */ -void ext4_discard_preallocations(struct inode *inode) +void ext4_discard_preallocations(struct inode *inode, unsigned int needed) { struct ext4_inode_info *ei = EXT4_I(inode); struct super_block *sb = inode->i_sb; @@ -4121,15 +4285,19 @@ void ext4_discard_preallocations(struct inode *inode) mb_debug(sb, "discard preallocation for inode %lu\n", inode->i_ino); - trace_ext4_discard_preallocations(inode); + trace_ext4_discard_preallocations(inode, + atomic_read(&ei->i_prealloc_active), needed); INIT_LIST_HEAD(&list); + if (needed == 0) + needed = UINT_MAX; + repeat: /* first, collect all pa's in the inode */ spin_lock(&ei->i_prealloc_lock); - while (!list_empty(&ei->i_prealloc_list)) { - pa = list_entry(ei->i_prealloc_list.next, + while (!list_empty(&ei->i_prealloc_list) && needed) { + pa = list_entry(ei->i_prealloc_list.prev, struct ext4_prealloc_space, pa_inode_list); BUG_ON(pa->pa_obj_lock != &ei->i_prealloc_lock); spin_lock(&pa->pa_lock); @@ -4146,10 +4314,11 @@ repeat: } if (pa->pa_deleted == 0) { - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); list_add(&pa->u.pa_tmp_list, &list); + needed--; continue; } @@ -4399,7 +4568,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, ac->ac_g_ex = ac->ac_o_ex; ac->ac_flags = ar->flags; - /* we have to define context: we'll we work with a file or + /* we have to define context: we'll work with a file or * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); @@ -4450,7 +4619,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, BUG_ON(pa->pa_type != MB_GROUP_PA); /* seems this one can be freed ... */ - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); @@ -4549,10 +4718,29 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) } /* + * if per-inode prealloc list is too long, trim some PA + */ +static void ext4_mb_trim_inode_pa(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int count, delta; + + count = atomic_read(&ei->i_prealloc_active); + delta = (sbi->s_mb_max_inode_prealloc >> 2) + 1; + if (count > sbi->s_mb_max_inode_prealloc + delta) { + count -= sbi->s_mb_max_inode_prealloc; + ext4_discard_preallocations(inode, count); + } +} + +/* * release all resource we used in allocation */ static int ext4_mb_release_context(struct ext4_allocation_context *ac) { + struct inode *inode = ac->ac_inode; + struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *pa = ac->ac_pa; if (pa) { @@ -4564,21 +4752,31 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) pa->pa_free -= ac->ac_b_ex.fe_len; pa->pa_len -= ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); + + /* + * We want to add the pa to the right bucket. + * Remove it from the list and while adding + * make sure the list to which we are adding + * doesn't grow big. + */ + if (likely(pa->pa_free)) { + spin_lock(pa->pa_obj_lock); + list_del_rcu(&pa->pa_inode_list); + spin_unlock(pa->pa_obj_lock); + ext4_mb_add_n_trim(ac); + } } - } - if (pa) { - /* - * We want to add the pa to the right bucket. - * Remove it from the list and while adding - * make sure the list to which we are adding - * doesn't grow big. - */ - if ((pa->pa_type == MB_GROUP_PA) && likely(pa->pa_free)) { + + if (pa->pa_type == MB_INODE_PA) { + /* + * treat per-inode prealloc list as a lru list, then try + * to trim the least recently used PA. + */ spin_lock(pa->pa_obj_lock); - list_del_rcu(&pa->pa_inode_list); + list_move(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); - ext4_mb_add_n_trim(ac); } + ext4_mb_put_pa(ac, ac->ac_sb, pa); } if (ac->ac_bitmap_page) @@ -4588,6 +4786,7 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); + ext4_mb_trim_inode_pa(inode); return 0; } @@ -4915,7 +5114,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && - !ext4_data_block_valid(sbi, block, count)) { + !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); goto error_return; diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 6b4d17c2935d..e75b4749aa1c 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -73,6 +73,10 @@ */ #define MB_DEFAULT_GROUP_PREALLOC 512 +/* + * maximum length of inode prealloc list + */ +#define MB_DEFAULT_MAX_INODE_PREALLOC 512 struct ext4_free_data { /* this links the free block information from sb_info */ diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 1ed86fb6c302..0d601b822875 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -686,8 +686,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, out: if (*moved_len) { - ext4_discard_preallocations(orig_inode); - ext4_discard_preallocations(donor_inode); + ext4_discard_preallocations(orig_inode, 0); + ext4_discard_preallocations(donor_inode, 0); } ext4_ext_drop_refs(path); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 56738b538ddf..153a9fbe1dd0 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1396,8 +1396,8 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ - if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, - bh->b_size, offset)) + if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf, + buf_size, offset)) return -1; *res_dir = de; return 1; @@ -1858,7 +1858,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, blocksize, hinfo, map); map -= count; dx_sort_map(map, count); - /* Split the existing block in the middle, size-wise */ + /* Ensure that neither split block is over half full */ size = 0; move = 0; for (i = count-1; i >= 0; i--) { @@ -1868,8 +1868,18 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, size += map[i].size; move++; } - /* map index at which we will split */ - split = count - move; + /* + * map index at which we will split + * + * If the sum of active entries didn't exceed half the block size, just + * split it in half by count; each resulting block will have at least + * half the space free. + */ + if (i > 0) + split = count - move; + else + split = count/2; + hash2 = map[split].hash; continued = hash2 == map[split - 1].hash; dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n", @@ -2455,8 +2465,7 @@ cleanup: * ext4_generic_delete_entry deletes a directory entry by merging it * with the previous entry */ -int ext4_generic_delete_entry(handle_t *handle, - struct inode *dir, +int ext4_generic_delete_entry(struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, void *entry_buf, @@ -2472,7 +2481,7 @@ int ext4_generic_delete_entry(handle_t *handle, de = (struct ext4_dir_entry_2 *)entry_buf; while (i < buf_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, - bh->b_data, bh->b_size, i)) + entry_buf, buf_size, i)) return -EFSCORRUPTED; if (de == de_del) { if (pde) @@ -2517,8 +2526,7 @@ static int ext4_delete_entry(handle_t *handle, if (unlikely(err)) goto out; - err = ext4_generic_delete_entry(handle, dir, de_del, - bh, bh->b_data, + err = ext4_generic_delete_entry(dir, de_del, bh, bh->b_data, dir->i_sb->s_blocksize, csum_size); if (err) goto out; @@ -3193,30 +3201,33 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) * in separate transaction */ retval = dquot_initialize(dir); if (retval) - return retval; + goto out_trace; retval = dquot_initialize(d_inode(dentry)); if (retval) - return retval; + goto out_trace; - retval = -ENOENT; bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); - if (IS_ERR(bh)) - return PTR_ERR(bh); - if (!bh) - goto end_unlink; + if (IS_ERR(bh)) { + retval = PTR_ERR(bh); + goto out_trace; + } + if (!bh) { + retval = -ENOENT; + goto out_trace; + } inode = d_inode(dentry); - retval = -EFSCORRUPTED; - if (le32_to_cpu(de->inode) != inode->i_ino) - goto end_unlink; + if (le32_to_cpu(de->inode) != inode->i_ino) { + retval = -EFSCORRUPTED; + goto out_bh; + } handle = ext4_journal_start(dir, EXT4_HT_DIR, EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); if (IS_ERR(handle)) { retval = PTR_ERR(handle); - handle = NULL; - goto end_unlink; + goto out_bh; } if (IS_DIRSYNC(dir)) @@ -3224,12 +3235,12 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) retval = ext4_delete_entry(handle, dir, de, bh); if (retval) - goto end_unlink; + goto out_handle; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); retval = ext4_mark_inode_dirty(handle, dir); if (retval) - goto end_unlink; + goto out_handle; if (inode->i_nlink == 0) ext4_warning_inode(inode, "Deleting file '%.*s' with no links", dentry->d_name.len, dentry->d_name.name); @@ -3251,10 +3262,11 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) d_invalidate(dentry); #endif -end_unlink: +out_handle: + ext4_journal_stop(handle); +out_bh: brelse(bh); - if (handle) - ext4_journal_stop(handle); +out_trace: trace_ext4_unlink_exit(dentry, retval); return retval; } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index f2df2db0786c..f014c5e473a9 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -140,7 +140,7 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx) return; } ctx->cur_step++; - /* fall-through */ + fallthrough; case STEP_VERITY: if (ctx->enabled_steps & (1 << STEP_VERITY)) { INIT_WORK(&ctx->work, verity_work); @@ -148,7 +148,7 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx) return; } ctx->cur_step++; - /* fall-through */ + fallthrough; default: __read_end_io(ctx->bio); } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0907f907c47d..ea425b49b345 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -66,10 +66,10 @@ static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); static int ext4_commit_super(struct super_block *sb, int sync); -static void ext4_mark_recovery_complete(struct super_block *sb, +static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); -static void ext4_clear_journal_err(struct super_block *sb, - struct ext4_super_block *es); +static int ext4_clear_journal_err(struct super_block *sb, + struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); @@ -744,6 +744,7 @@ void __ext4_msg(struct super_block *sb, struct va_format vaf; va_list args; + atomic_inc(&EXT4_SB(sb)->s_msg_count); if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs")) return; @@ -754,9 +755,12 @@ void __ext4_msg(struct super_block *sb, va_end(args); } -#define ext4_warning_ratelimit(sb) \ - ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), \ - "EXT4-fs warning") +static int ext4_warning_ratelimit(struct super_block *sb) +{ + atomic_inc(&EXT4_SB(sb)->s_warning_count); + return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), + "EXT4-fs warning"); +} void __ext4_warning(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) @@ -1123,6 +1127,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) inode_set_iversion(&ei->vfs_inode, 1); spin_lock_init(&ei->i_raw_lock); INIT_LIST_HEAD(&ei->i_prealloc_list); + atomic_set(&ei->i_prealloc_active, 0); spin_lock_init(&ei->i_prealloc_lock); ext4_es_init_tree(&ei->i_es_tree); rwlock_init(&ei->i_es_lock); @@ -1216,7 +1221,7 @@ void ext4_clear_inode(struct inode *inode) { invalidate_inode_buffers(inode); clear_inode(inode); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { @@ -1288,8 +1293,8 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, if (!page_has_buffers(page)) return 0; if (journal) - return jbd2_journal_try_to_free_buffers(journal, page, - wait & ~__GFP_DIRECT_RECLAIM); + return jbd2_journal_try_to_free_buffers(journal, page); + return try_to_free_buffers(page); } @@ -1522,6 +1527,7 @@ enum { Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, + Opt_prefetch_block_bitmaps, }; static const match_table_t tokens = { @@ -1614,6 +1620,7 @@ static const match_table_t tokens = { {Opt_inlinecrypt, "inlinecrypt"}, {Opt_nombcache, "nombcache"}, {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ + {Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"}, {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1831,6 +1838,8 @@ static const struct mount_opts { {Opt_max_dir_size_kb, 0, MOPT_GTE0}, {Opt_test_dummy_encryption, 0, MOPT_STRING}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, + {Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS, + MOPT_SET}, {Opt_err, 0, 0} }; @@ -3213,15 +3222,34 @@ static void print_daily_error_info(struct timer_list *t) static int ext4_run_li_request(struct ext4_li_request *elr) { struct ext4_group_desc *gdp = NULL; - ext4_group_t group, ngroups; - struct super_block *sb; + struct super_block *sb = elr->lr_super; + ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t group = elr->lr_next_group; unsigned long timeout = 0; + unsigned int prefetch_ios = 0; int ret = 0; - sb = elr->lr_super; - ngroups = EXT4_SB(sb)->s_groups_count; + if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) { + elr->lr_next_group = ext4_mb_prefetch(sb, group, + EXT4_SB(sb)->s_mb_prefetch, &prefetch_ios); + if (prefetch_ios) + ext4_mb_prefetch_fini(sb, elr->lr_next_group, + prefetch_ios); + trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group, + prefetch_ios); + if (group >= elr->lr_next_group) { + ret = 1; + if (elr->lr_first_not_zeroed != ngroups && + !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) { + elr->lr_next_group = elr->lr_first_not_zeroed; + elr->lr_mode = EXT4_LI_MODE_ITABLE; + ret = 0; + } + } + return ret; + } - for (group = elr->lr_next_group; group < ngroups; group++) { + for (; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { ret = 1; @@ -3239,9 +3267,10 @@ static int ext4_run_li_request(struct ext4_li_request *elr) timeout = jiffies; ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); + trace_ext4_lazy_itable_init(sb, group); if (elr->lr_timeout == 0) { timeout = (jiffies - timeout) * - elr->lr_sbi->s_li_wait_mult; + EXT4_SB(elr->lr_super)->s_li_wait_mult; elr->lr_timeout = timeout; } elr->lr_next_sched = jiffies + elr->lr_timeout; @@ -3256,15 +3285,11 @@ static int ext4_run_li_request(struct ext4_li_request *elr) */ static void ext4_remove_li_request(struct ext4_li_request *elr) { - struct ext4_sb_info *sbi; - if (!elr) return; - sbi = elr->lr_sbi; - list_del(&elr->lr_request); - sbi->s_li_request = NULL; + EXT4_SB(elr->lr_super)->s_li_request = NULL; kfree(elr); } @@ -3473,7 +3498,6 @@ static int ext4_li_info_new(void) static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, ext4_group_t start) { - struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_li_request *elr; elr = kzalloc(sizeof(*elr), GFP_KERNEL); @@ -3481,8 +3505,13 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, return NULL; elr->lr_super = sb; - elr->lr_sbi = sbi; - elr->lr_next_group = start; + elr->lr_first_not_zeroed = start; + if (test_opt(sb, PREFETCH_BLOCK_BITMAPS)) + elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP; + else { + elr->lr_mode = EXT4_LI_MODE_ITABLE; + elr->lr_next_group = start; + } /* * Randomize first schedule time of the request to @@ -3512,8 +3541,9 @@ int ext4_register_li_request(struct super_block *sb, goto out; } - if (first_not_zeroed == ngroups || sb_rdonly(sb) || - !test_opt(sb, INIT_INODE_TABLE)) + if (!test_opt(sb, PREFETCH_BLOCK_BITMAPS) && + (first_not_zeroed == ngroups || sb_rdonly(sb) || + !test_opt(sb, INIT_INODE_TABLE))) goto out; elr = ext4_li_request_new(sb, first_not_zeroed); @@ -4710,11 +4740,13 @@ no_journal: ext4_set_resv_clusters(sb); - err = ext4_setup_system_zone(sb); - if (err) { - ext4_msg(sb, KERN_ERR, "failed to initialize system " - "zone (%d)", err); - goto failed_mount4a; + if (test_opt(sb, BLOCK_VALIDITY)) { + err = ext4_setup_system_zone(sb); + if (err) { + ext4_msg(sb, KERN_ERR, "failed to initialize system " + "zone (%d)", err); + goto failed_mount4a; + } } ext4_ext_init(sb); @@ -4777,12 +4809,23 @@ no_journal: } #endif /* CONFIG_QUOTA */ + /* + * Save the original bdev mapping's wb_err value which could be + * used to detect the metadata async write error. + */ + spin_lock_init(&sbi->s_bdev_wb_lock); + if (!sb_rdonly(sb)) + errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, + &sbi->s_bdev_wb_err); + sb->s_bdev->bd_super = sb; EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; if (needs_recovery) { ext4_msg(sb, KERN_INFO, "recovery complete"); - ext4_mark_recovery_complete(sb, es); + err = ext4_mark_recovery_complete(sb, es); + if (err) + goto failed_mount8; } if (EXT4_SB(sb)->s_journal) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) @@ -4816,6 +4859,8 @@ no_journal: ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10); + atomic_set(&sbi->s_warning_count, 0); + atomic_set(&sbi->s_msg_count, 0); kfree(orig_data); return 0; @@ -4825,10 +4870,8 @@ cantfind_ext4: ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto failed_mount; -#ifdef CONFIG_QUOTA failed_mount8: ext4_unregister_sysfs(sb); -#endif failed_mount7: ext4_unregister_li_request(sb); failed_mount6: @@ -4968,7 +5011,8 @@ static journal_t *ext4_get_journal(struct super_block *sb, struct inode *journal_inode; journal_t *journal; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return NULL; journal_inode = ext4_get_journal_inode(sb, journal_inum); if (!journal_inode) @@ -4998,7 +5042,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, struct ext4_super_block *es; struct block_device *bdev; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return NULL; bdev = ext4_blkdev_get(j_dev, sb); if (bdev == NULL) @@ -5089,8 +5134,10 @@ static int ext4_load_journal(struct super_block *sb, dev_t journal_dev; int err = 0; int really_read_only; + int journal_dev_ro; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return -EFSCORRUPTED; if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { @@ -5100,7 +5147,31 @@ static int ext4_load_journal(struct super_block *sb, } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); - really_read_only = bdev_read_only(sb->s_bdev); + if (journal_inum && journal_dev) { + ext4_msg(sb, KERN_ERR, + "filesystem has both journal inode and journal device!"); + return -EINVAL; + } + + if (journal_inum) { + journal = ext4_get_journal(sb, journal_inum); + if (!journal) + return -EINVAL; + } else { + journal = ext4_get_dev_journal(sb, journal_dev); + if (!journal) + return -EINVAL; + } + + journal_dev_ro = bdev_read_only(journal->j_dev); + really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro; + + if (journal_dev_ro && !sb_rdonly(sb)) { + ext4_msg(sb, KERN_ERR, + "journal device read-only, try mounting with '-o ro'"); + err = -EROFS; + goto err_out; + } /* * Are we loading a blank journal or performing recovery after a @@ -5115,27 +5186,14 @@ static int ext4_load_journal(struct super_block *sb, ext4_msg(sb, KERN_ERR, "write access " "unavailable, cannot proceed " "(try mounting with noload)"); - return -EROFS; + err = -EROFS; + goto err_out; } ext4_msg(sb, KERN_INFO, "write access will " "be enabled during recovery"); } } - if (journal_inum && journal_dev) { - ext4_msg(sb, KERN_ERR, "filesystem has both journal " - "and inode journals!"); - return -EINVAL; - } - - if (journal_inum) { - if (!(journal = ext4_get_journal(sb, journal_inum))) - return -EINVAL; - } else { - if (!(journal = ext4_get_dev_journal(sb, journal_dev))) - return -EINVAL; - } - if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); @@ -5155,12 +5213,16 @@ static int ext4_load_journal(struct super_block *sb, if (err) { ext4_msg(sb, KERN_ERR, "error loading journal"); - jbd2_journal_destroy(journal); - return err; + goto err_out; } EXT4_SB(sb)->s_journal = journal; - ext4_clear_journal_err(sb, es); + err = ext4_clear_journal_err(sb, es); + if (err) { + EXT4_SB(sb)->s_journal = NULL; + jbd2_journal_destroy(journal); + return err; + } if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { @@ -5171,6 +5233,10 @@ static int ext4_load_journal(struct super_block *sb, } return 0; + +err_out: + jbd2_journal_destroy(journal); + return err; } static int ext4_commit_super(struct super_block *sb, int sync) @@ -5183,13 +5249,6 @@ static int ext4_commit_super(struct super_block *sb, int sync) return error; /* - * The superblock bh should be mapped, but it might not be if the - * device was hot-removed. Not much we can do but fail the I/O. - */ - if (!buffer_mapped(sbh)) - return error; - - /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock * write time when we are mounting the root file system @@ -5256,26 +5315,32 @@ static int ext4_commit_super(struct super_block *sb, int sync) * remounting) the filesystem readonly, then we will end up with a * consistent fs on disk. Record that fact. */ -static void ext4_mark_recovery_complete(struct super_block *sb, - struct ext4_super_block *es) +static int ext4_mark_recovery_complete(struct super_block *sb, + struct ext4_super_block *es) { + int err; journal_t *journal = EXT4_SB(sb)->s_journal; if (!ext4_has_feature_journal(sb)) { - BUG_ON(journal != NULL); - return; + if (journal != NULL) { + ext4_error(sb, "Journal got removed while the fs was " + "mounted!"); + return -EFSCORRUPTED; + } + return 0; } jbd2_journal_lock_updates(journal); - if (jbd2_journal_flush(journal) < 0) + err = jbd2_journal_flush(journal); + if (err < 0) goto out; if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) { ext4_clear_feature_journal_needs_recovery(sb); ext4_commit_super(sb, 1); } - out: jbd2_journal_unlock_updates(journal); + return err; } /* @@ -5283,14 +5348,17 @@ out: * has recorded an error from a previous lifetime, move that error to the * main filesystem now. */ -static void ext4_clear_journal_err(struct super_block *sb, +static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es) { journal_t *journal; int j_errno; const char *errstr; - BUG_ON(!ext4_has_feature_journal(sb)); + if (!ext4_has_feature_journal(sb)) { + ext4_error(sb, "Journal got removed while the fs was mounted!"); + return -EFSCORRUPTED; + } journal = EXT4_SB(sb)->s_journal; @@ -5315,6 +5383,7 @@ static void ext4_clear_journal_err(struct super_block *sb, jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); } + return 0; } /* @@ -5457,7 +5526,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) { struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); - unsigned long old_sb_flags; + unsigned long old_sb_flags, vfs_flags; struct ext4_mount_options old_opts; int enable_quota = 0; ext4_group_t g; @@ -5500,6 +5569,14 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal && sbi->s_journal->j_task->io_context) journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; + /* + * Some options can be enabled by ext4 and/or by VFS mount flag + * either way we need to make sure it matches in both *flags and + * s_flags. Copy those selected flags from *flags to s_flags + */ + vfs_flags = SB_LAZYTIME | SB_I_VERSION; + sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags); + if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; goto restore_opts; @@ -5553,9 +5630,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); } - if (*flags & SB_LAZYTIME) - sb->s_flags |= SB_LAZYTIME; - if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { err = -EROFS; @@ -5585,8 +5659,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); - if (sbi->s_journal) + if (sbi->s_journal) { + /* + * We let remount-ro finish even if marking fs + * as clean failed... + */ ext4_mark_recovery_complete(sb, es); + } if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); } else { @@ -5629,13 +5708,24 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } /* + * Update the original bdev mapping's wb_err value + * which could be used to detect the metadata async + * write error. + */ + errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, + &sbi->s_bdev_wb_err); + + /* * Mounting a RDONLY partition read-write, so reread * and store the current valid flag. (It may have * been changed by e2fsck since we originally mounted * the partition.) */ - if (sbi->s_journal) - ext4_clear_journal_err(sb, es); + if (sbi->s_journal) { + err = ext4_clear_journal_err(sb, es); + if (err) + goto restore_opts; + } sbi->s_mount_state = le16_to_cpu(es->s_state); err = ext4_setup_super(sb, es, 0); @@ -5665,7 +5755,17 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_register_li_request(sb, first_not_zeroed); } - ext4_setup_system_zone(sb); + /* + * Handle creation of system zone data early because it can fail. + * Releasing of existing data is done when we are sure remount will + * succeed. + */ + if (test_opt(sb, BLOCK_VALIDITY) && !sbi->system_blks) { + err = ext4_setup_system_zone(sb); + if (err) + goto restore_opts; + } + if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { err = ext4_commit_super(sb, 1); if (err) @@ -5686,8 +5786,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } } #endif + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) + ext4_release_system_zone(sb); + + /* + * Some options can be enabled by ext4 and/or by VFS mount flag + * either way we need to make sure it matches in both *flags and + * s_flags. Copy those selected flags from s_flags to *flags + */ + *flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags); - *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); kfree(orig_data); return 0; @@ -5701,6 +5809,8 @@ restore_opts: sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) + ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 6c9fc9e21c13..bfabb799fa45 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -189,6 +189,9 @@ static struct ext4_attr ext4_attr_##_name = { \ #define EXT4_RW_ATTR_SBI_UL(_name,_elname) \ EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname) +#define EXT4_RO_ATTR_SBI_ATOMIC(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_atomic, ext4_sb_info, _elname) + #define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \ static struct ext4_attr ext4_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ @@ -215,6 +218,7 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); +EXT4_RW_ATTR_SBI_UI(mb_max_inode_prealloc, s_mb_max_inode_prealloc); EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error); EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval); @@ -226,6 +230,8 @@ EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst); #ifdef CONFIG_EXT4_DEBUG EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail); #endif +EXT4_RO_ATTR_SBI_ATOMIC(warning_count, s_warning_count); +EXT4_RO_ATTR_SBI_ATOMIC(msg_count, s_msg_count); EXT4_RO_ATTR_ES_UI(errors_count, s_error_count); EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode); EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode); @@ -240,6 +246,8 @@ EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32); EXT4_ATTR(first_error_time, 0444, first_error_time); EXT4_ATTR(last_error_time, 0444, last_error_time); EXT4_ATTR(journal_task, 0444, journal_task); +EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch); +EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit); static unsigned int old_bump_val = 128; EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val); @@ -257,6 +265,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_order2_req), ATTR_LIST(mb_stream_req), ATTR_LIST(mb_group_prealloc), + ATTR_LIST(mb_max_inode_prealloc), ATTR_LIST(max_writeback_mb_bump), ATTR_LIST(extent_max_zeroout_kb), ATTR_LIST(trigger_fs_error), @@ -267,6 +276,8 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(msg_ratelimit_interval_ms), ATTR_LIST(msg_ratelimit_burst), ATTR_LIST(errors_count), + ATTR_LIST(warning_count), + ATTR_LIST(msg_count), ATTR_LIST(first_error_ino), ATTR_LIST(last_error_ino), ATTR_LIST(first_error_block), @@ -283,6 +294,8 @@ static struct attribute *ext4_attrs[] = { #ifdef CONFIG_EXT4_DEBUG ATTR_LIST(simulate_fail), #endif + ATTR_LIST(mb_prefetch), + ATTR_LIST(mb_prefetch_limit), NULL, }; ATTRIBUTE_GROUPS(ext4); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 7d2f6576d954..cba4b877c606 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1356,8 +1356,7 @@ retry: block = 0; while (wsize < bufsize) { - if (bh != NULL) - brelse(bh); + brelse(bh); csize = (bufsize - wsize) > blocksize ? blocksize : bufsize - wsize; bh = ext4_getblk(handle, ea_inode, block, 0); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 16322ea5b463..d9e52a7f3702 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2646,7 +2646,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode, case FI_NEW_INODE: if (set) return; - /* fall through */ + fallthrough; case FI_DATA_EXIST: case FI_INLINE_DOTS: case FI_PIN_FILE: diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 9bbaa2614679..3ad7bdbda5ca 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -618,10 +618,10 @@ pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) switch (dn->max_level) { case 3: base += 2 * indirect_blks; - /* fall through */ + fallthrough; case 2: base += 2 * direct_blks; - /* fall through */ + fallthrough; case 1: base += direct_index; break; diff --git a/fs/fcntl.c b/fs/fcntl.c index 2e4c0fa2074b..19ac5baad50f 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -362,7 +362,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, case F_OFD_SETLK: case F_OFD_SETLKW: #endif - /* Fallthrough */ + fallthrough; case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) @@ -771,7 +771,7 @@ static void send_sigio_to_task(struct task_struct *p, if (!do_send_sig_info(signum, &si, p, type)) break; } - /* fall-through - fall back on the old plain SIGIO signal */ + fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index a605c3dddabc..149227160ff0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -42,7 +42,6 @@ struct wb_writeback_work { long nr_pages; struct super_block *sb; - unsigned long *older_than_this; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; @@ -144,7 +143,9 @@ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } @@ -1122,7 +1123,9 @@ void inode_io_list_del(struct inode *inode) struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); + spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); + spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); @@ -1172,8 +1175,10 @@ void sb_clear_inode_writeback(struct inode *inode) * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ -static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { + assert_spin_locked(&inode->i_lock); + if (!list_empty(&wb->b_dirty)) { struct inode *tail; @@ -1182,6 +1187,14 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); + inode->i_state &= ~I_SYNC_QUEUED; +} + +static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +{ + spin_lock(&inode->i_lock); + redirty_tail_locked(inode, wb); + spin_unlock(&inode->i_lock); } /* @@ -1220,16 +1233,13 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t) #define EXPIRE_DIRTY_ATIME 0x0001 /* - * Move expired (dirtied before work->older_than_this) dirty inodes from + * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, - int flags, - struct wb_writeback_work *work) + unsigned long dirtied_before) { - unsigned long *older_than_this = NULL; - unsigned long expire_time; LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; @@ -1237,21 +1247,15 @@ static int move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; int moved = 0; - if ((flags & EXPIRE_DIRTY_ATIME) == 0) - older_than_this = work->older_than_this; - else if (!work->for_sync) { - expire_time = jiffies - (dirtytime_expire_interval * HZ); - older_than_this = &expire_time; - } while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (older_than_this && - inode_dirtied_after(inode, *older_than_this)) + if (inode_dirtied_after(inode, dirtied_before)) break; list_move(&inode->i_io_list, &tmp); moved++; - if (flags & EXPIRE_DIRTY_ATIME) - set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state); + spin_lock(&inode->i_lock); + inode->i_state |= I_SYNC_QUEUED; + spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) @@ -1289,18 +1293,22 @@ out: * | * +--> dequeue for IO */ -static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) +static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, + unsigned long dirtied_before) { int moved; + unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); - moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); + if (!work->for_sync) + time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, - EXPIRE_DIRTY_ATIME, work); + time_expire_jif); if (moved) wb_io_lists_populated(wb); - trace_writeback_queue_io(wb, work, moved); + trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) @@ -1394,7 +1402,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * writeback is not making progress due to locked * buffers. Skip this inode for now. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); return; } @@ -1414,7 +1422,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* @@ -1422,10 +1430,11 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * such as delayed allocation during submission or metadata * updates after data IO completion. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); + inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); @@ -1472,18 +1481,14 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; - if (inode->i_state & I_DIRTY_TIME) { - if ((dirty & I_DIRTY_INODE) || - wbc->sync_mode == WB_SYNC_ALL || - unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) || - unlikely(time_after(jiffies, - (inode->dirtied_time_when + - dirtytime_expire_interval * HZ)))) { - dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED; - trace_writeback_lazytime(inode); - } - } else - inode->i_state &= ~I_DIRTY_TIME_EXPIRED; + if ((inode->i_state & I_DIRTY_TIME) && + ((dirty & I_DIRTY_INODE) || + wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || + time_after(jiffies, inode->dirtied_time_when + + dirtytime_expire_interval * HZ))) { + dirty |= I_DIRTY_TIME; + trace_writeback_lazytime(inode); + } inode->i_state &= ~dirty; /* @@ -1669,8 +1674,8 @@ static long writeback_sb_inodes(struct super_block *sb, */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); - redirty_tail(inode, wb); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { @@ -1811,7 +1816,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) - queue_io(wb, &work); + queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); @@ -1831,7 +1836,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * - * older_than_this takes precedence over nr_to_write. So we'll only write back + * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, @@ -1839,14 +1844,11 @@ static long wb_writeback(struct bdi_writeback *wb, { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; - unsigned long oldest_jif; + unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; - oldest_jif = jiffies; - work->older_than_this = &oldest_jif; - blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { @@ -1880,14 +1882,14 @@ static long wb_writeback(struct bdi_writeback *wb, * safe. */ if (work->for_kupdate) { - oldest_jif = jiffies - + dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) - oldest_jif = jiffies; + dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) - queue_io(wb, work); + queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else @@ -2289,11 +2291,12 @@ void __mark_inode_dirty(struct inode *inode, int flags) inode->i_state |= flags; /* - * If the inode is being synced, just update its dirty state. - * The unlocker will place the inode on the appropriate - * superblock list, based upon its state. + * If the inode is queued for writeback by flush worker, just + * update its dirty state. Once the flush worker is done with + * the inode it will place it on the appropriate superblock + * list, based upon its state. */ - if (inode->i_state & I_SYNC) + if (inode->i_state & I_SYNC_QUEUED) goto out_unlock_inode; /* diff --git a/fs/fs_context.c b/fs/fs_context.c index 7d5c5dd2b1d5..2834d1afa6e8 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -521,7 +521,7 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) switch (param->type) { case fs_value_is_string: len = 1 + param->size; - /* Fall through */ + fallthrough; case fs_value_is_flag: len += strlen(param->key); break; diff --git a/fs/fsopen.c b/fs/fsopen.c index 2fa3f241b762..27a890aa493a 100644 --- a/fs/fsopen.c +++ b/fs/fsopen.c @@ -412,7 +412,7 @@ SYSCALL_DEFINE5(fsconfig, break; case FSCONFIG_SET_PATH_EMPTY: lookup_flags = LOOKUP_EMPTY; - /* fallthru */ + fallthrough; case FSCONFIG_SET_PATH: param.type = fs_value_is_filename; param.name = getname_flags(_value, lookup_flags, NULL); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 770f3a720db9..0f69fbd4af66 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -746,7 +746,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap, } if (n == 0) break; - /* fall through - To branching from existing tree */ + fallthrough; /* To branching from existing tree */ case ALLOC_GROW_DEPTH: if (i > 1 && i < mp->mp_fheight) gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]); @@ -757,7 +757,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap, state = ALLOC_DATA; if (n == 0) break; - /* fall through - To tree complete, adding data blocks */ + fallthrough; /* To tree complete, adding data blocks */ case ALLOC_DATA: BUG_ON(n > dblks); BUG_ON(mp->mp_bh[end_of_metadata] == NULL); diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index a58333e3980d..3763c9ff1406 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -902,6 +902,36 @@ static void empty_ail1_list(struct gfs2_sbd *sdp) } /** + * drain_bd - drain the buf and databuf queue for a failed transaction + * @tr: the transaction to drain + * + * When this is called, we're taking an error exit for a log write that failed + * but since we bypassed the after_commit functions, we need to remove the + * items from the buf and databuf queue. + */ +static void trans_drain(struct gfs2_trans *tr) +{ + struct gfs2_bufdata *bd; + struct list_head *head; + + if (!tr) + return; + + head = &tr->tr_buf; + while (!list_empty(head)) { + bd = list_first_entry(head, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); + kmem_cache_free(gfs2_bufdata_cachep, bd); + } + head = &tr->tr_databuf; + while (!list_empty(head)) { + bd = list_first_entry(head, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); + kmem_cache_free(gfs2_bufdata_cachep, bd); + } +} + +/** * gfs2_log_flush - flush incore transaction(s) * @sdp: the filesystem * @gl: The glock structure to flush. If NULL, flush the whole incore log @@ -1005,6 +1035,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) out: if (gfs2_withdrawn(sdp)) { + trans_drain(tr); /** * If the tr_list is empty, we're withdrawing during a log * flush that targets a transaction, but the transaction was diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 4b67d47a7e00..6e173ae378c4 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1599,7 +1599,7 @@ static int gfs2_quota_get_state(struct super_block *sb, struct qc_state *state) case GFS2_QUOTA_ON: state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED; state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED; - /*FALLTHRU*/ + fallthrough; case GFS2_QUOTA_ACCOUNT: state->s_state[USRQUOTA].flags |= QCI_ACCT_ENABLED | QCI_SYSFILE; diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index e1c7eb6eb00a..6d4bf7ea7b3b 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -67,6 +67,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, tr->tr_reserved += gfs2_struct2blk(sdp, revokes); INIT_LIST_HEAD(&tr->tr_databuf); INIT_LIST_HEAD(&tr->tr_buf); + INIT_LIST_HEAD(&tr->tr_list); INIT_LIST_HEAD(&tr->tr_ail1_list); INIT_LIST_HEAD(&tr->tr_ail2_list); diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 61eec628805d..0350dc7821bf 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -195,7 +195,7 @@ reread: switch (sbi->s_vhdr->signature) { case cpu_to_be16(HFSPLUS_VOLHEAD_SIGX): set_bit(HFSPLUS_SB_HFSX, &sbi->flags); - /*FALLTHRU*/ + fallthrough; case cpu_to_be16(HFSPLUS_VOLHEAD_SIG): break; case cpu_to_be16(HFSP_WRAP_MAGIC): diff --git a/fs/io-wq.c b/fs/io-wq.c index e92c4724480c..414beb543883 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -925,6 +925,24 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data) return match->nr_running && !match->cancel_all; } +static inline void io_wqe_remove_pending(struct io_wqe *wqe, + struct io_wq_work *work, + struct io_wq_work_node *prev) +{ + unsigned int hash = io_get_work_hash(work); + struct io_wq_work *prev_work = NULL; + + if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) { + if (prev) + prev_work = container_of(prev, struct io_wq_work, list); + if (prev_work && io_get_work_hash(prev_work) == hash) + wqe->hash_tail[hash] = prev_work; + else + wqe->hash_tail[hash] = NULL; + } + wq_list_del(&wqe->work_list, &work->list, prev); +} + static void io_wqe_cancel_pending_work(struct io_wqe *wqe, struct io_cb_cancel_data *match) { @@ -938,8 +956,7 @@ retry: work = container_of(node, struct io_wq_work, list); if (!match->fn(work, match->data)) continue; - - wq_list_del(&wqe->work_list, node, prev); + io_wqe_remove_pending(wqe, work, prev); spin_unlock_irqrestore(&wqe->lock, flags); io_run_cancel(work, wqe); match->nr_pending++; diff --git a/fs/io_uring.c b/fs/io_uring.c index dc506b75659c..522b891dd187 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -540,7 +540,6 @@ enum { REQ_F_ISREG_BIT, REQ_F_COMP_LOCKED_BIT, REQ_F_NEED_CLEANUP_BIT, - REQ_F_OVERFLOW_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, REQ_F_NO_FILE_TABLE_BIT, @@ -583,8 +582,6 @@ enum { REQ_F_COMP_LOCKED = BIT(REQ_F_COMP_LOCKED_BIT), /* needs cleanup */ REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), - /* in overflow list */ - REQ_F_OVERFLOW = BIT(REQ_F_OVERFLOW_BIT), /* already went through poll handler */ REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), /* buffer already selected */ @@ -946,7 +943,8 @@ static void io_get_req_task(struct io_kiocb *req) static inline void io_clean_op(struct io_kiocb *req) { - if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED)) + if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED | + REQ_F_INFLIGHT)) __io_clean_op(req); } @@ -1152,7 +1150,7 @@ static void io_prep_async_work(struct io_kiocb *req) io_req_init_async(req); if (req->flags & REQ_F_ISREG) { - if (def->hash_reg_file) + if (def->hash_reg_file || (req->ctx->flags & IORING_SETUP_IOPOLL)) io_wq_hash_work(&req->work, file_inode(req->file)); } else { if (def->unbound_nonreg_file) @@ -1366,7 +1364,6 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb, compl.list); list_move(&req->compl.list, &list); - req->flags &= ~REQ_F_OVERFLOW; if (cqe) { WRITE_ONCE(cqe->user_data, req->user_data); WRITE_ONCE(cqe->res, req->result); @@ -1419,7 +1416,6 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; } io_clean_op(req); - req->flags |= REQ_F_OVERFLOW; req->result = res; req->compl.cflags = cflags; refcount_inc(&req->refs); @@ -1563,17 +1559,6 @@ static bool io_dismantle_req(struct io_kiocb *req) if (req->file) io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); - if (req->flags & REQ_F_INFLIGHT) { - struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; - - spin_lock_irqsave(&ctx->inflight_lock, flags); - list_del(&req->inflight_entry); - if (waitqueue_active(&ctx->inflight_wait)) - wake_up(&ctx->inflight_wait); - spin_unlock_irqrestore(&ctx->inflight_lock, flags); - } - return io_req_clean_work(req); } @@ -1761,7 +1746,8 @@ static struct io_kiocb *io_req_find_next(struct io_kiocb *req) return __io_req_find_next(req); } -static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb) +static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb, + bool twa_signal_ok) { struct task_struct *tsk = req->task; struct io_ring_ctx *ctx = req->ctx; @@ -1774,7 +1760,7 @@ static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb) * will do the job. */ notify = 0; - if (!(ctx->flags & IORING_SETUP_SQPOLL)) + if (!(ctx->flags & IORING_SETUP_SQPOLL) && twa_signal_ok) notify = TWA_SIGNAL; ret = task_work_add(tsk, cb, notify); @@ -1834,7 +1820,7 @@ static void io_req_task_queue(struct io_kiocb *req) init_task_work(&req->task_work, io_req_task_submit); percpu_ref_get(&req->ctx->refs); - ret = io_req_task_work_add(req, &req->task_work); + ret = io_req_task_work_add(req, &req->task_work, true); if (unlikely(ret)) { struct task_struct *tsk; @@ -2063,6 +2049,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, req = list_first_entry(done, struct io_kiocb, inflight_entry); if (READ_ONCE(req->result) == -EAGAIN) { + req->result = 0; req->iopoll_completed = 0; list_move_tail(&req->inflight_entry, &again); continue; @@ -2308,38 +2295,27 @@ end_req: io_req_complete(req, ret); return false; } - -static void io_rw_resubmit(struct callback_head *cb) -{ - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct io_ring_ctx *ctx = req->ctx; - int err; - - err = io_sq_thread_acquire_mm(ctx, req); - - if (io_resubmit_prep(req, err)) { - refcount_inc(&req->refs); - io_queue_async_work(req); - } - - percpu_ref_put(&ctx->refs); -} #endif static bool io_rw_reissue(struct io_kiocb *req, long res) { #ifdef CONFIG_BLOCK + umode_t mode = file_inode(req->file)->i_mode; int ret; + if (!S_ISBLK(mode) && !S_ISREG(mode)) + return false; if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker()) return false; - init_task_work(&req->task_work, io_rw_resubmit); - percpu_ref_get(&req->ctx->refs); + ret = io_sq_thread_acquire_mm(req->ctx, req); - ret = io_req_task_work_add(req, &req->task_work); - if (!ret) + if (io_resubmit_prep(req, ret)) { + refcount_inc(&req->refs); + io_queue_async_work(req); return true; + } + #endif return false; } @@ -2578,7 +2554,7 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) * IO with EINTR. */ ret = -EINTR; - /* fall through */ + fallthrough; default: kiocb->ki_complete(kiocb, ret, 0); } @@ -2819,22 +2795,15 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, return __io_iov_buffer_select(req, iov, needs_lock); } -static ssize_t io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock) +static ssize_t __io_import_iovec(int rw, struct io_kiocb *req, + struct iovec **iovec, struct iov_iter *iter, + bool needs_lock) { void __user *buf = u64_to_user_ptr(req->rw.addr); size_t sqe_len = req->rw.len; ssize_t ret; u8 opcode; - if (req->io) { - struct io_async_rw *iorw = &req->io->rw; - - *iovec = NULL; - return iov_iter_count(&iorw->iter); - } - opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; @@ -2848,10 +2817,8 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { if (req->flags & REQ_F_BUFFER_SELECT) { buf = io_rw_buffer_select(req, &sqe_len, needs_lock); - if (IS_ERR(buf)) { - *iovec = NULL; + if (IS_ERR(buf)) return PTR_ERR(buf); - } req->rw.len = sqe_len; } @@ -2879,6 +2846,21 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter); } +static ssize_t io_import_iovec(int rw, struct io_kiocb *req, + struct iovec **iovec, struct iov_iter *iter, + bool needs_lock) +{ + if (!req->io) + return __io_import_iovec(rw, req, iovec, iter, needs_lock); + *iovec = NULL; + return iov_iter_count(&req->io->rw.iter); +} + +static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb) +{ + return kiocb->ki_filp->f_mode & FMODE_STREAM ? NULL : &kiocb->ki_pos; +} + /* * For files that don't have ->read_iter() and ->write_iter(), handle them * by looping over ->read() or ->write() manually. @@ -2914,10 +2896,10 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb, if (rw == READ) { nr = file->f_op->read(file, iovec.iov_base, - iovec.iov_len, &kiocb->ki_pos); + iovec.iov_len, io_kiocb_ppos(kiocb)); } else { nr = file->f_op->write(file, iovec.iov_base, - iovec.iov_len, &kiocb->ki_pos); + iovec.iov_len, io_kiocb_ppos(kiocb)); } if (iov_iter_is_bvec(iter)) @@ -3001,11 +2983,8 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw, ssize_t ret; iorw->iter.iov = iorw->fast_iov; - /* reset ->io around the iovec import, we don't want to use it */ - req->io = NULL; - ret = io_import_iovec(rw, req, (struct iovec **) &iorw->iter.iov, + ret = __io_import_iovec(rw, req, (struct iovec **) &iorw->iter.iov, &iorw->iter, !force_nonblock); - req->io = container_of(iorw, struct io_async_ctx, rw); if (unlikely(ret < 0)) return ret; @@ -3061,7 +3040,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, /* submit ref gets dropped, acquire a new one */ refcount_inc(&req->refs); - ret = io_req_task_work_add(req, &req->task_work); + ret = io_req_task_work_add(req, &req->task_work, true); if (unlikely(ret)) { struct task_struct *tsk; @@ -3074,27 +3053,6 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, return 1; } -static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb, - struct wait_page_queue *wait, - wait_queue_func_t func, - void *data) -{ - /* Can't support async wakeup with polled IO */ - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - if (kiocb->ki_filp->f_mode & FMODE_BUF_RASYNC) { - wait->wait.func = func; - wait->wait.private = data; - wait->wait.flags = 0; - INIT_LIST_HEAD(&wait->wait.entry); - kiocb->ki_flags |= IOCB_WAITQ; - kiocb->ki_waitq = wait; - return 0; - } - - return -EOPNOTSUPP; -} - /* * This controls whether a given IO request should be armed for async page * based retry. If we return false here, the request is handed to the async @@ -3109,16 +3067,17 @@ static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb, */ static bool io_rw_should_retry(struct io_kiocb *req) { + struct wait_page_queue *wait = &req->io->rw.wpq; struct kiocb *kiocb = &req->rw.kiocb; - int ret; /* never retry for NOWAIT, we just complete with -EAGAIN */ if (req->flags & REQ_F_NOWAIT) return false; /* Only for buffered IO */ - if (kiocb->ki_flags & IOCB_DIRECT) + if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI)) return false; + /* * just use poll if we can, and don't attempt if the fs doesn't * support callback based unlocks @@ -3126,14 +3085,15 @@ static bool io_rw_should_retry(struct io_kiocb *req) if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC)) return false; - ret = kiocb_wait_page_queue_init(kiocb, &req->io->rw.wpq, - io_async_buf_func, req); - if (!ret) { - io_get_req_task(req); - return true; - } + wait->wait.func = io_async_buf_func; + wait->wait.private = req; + wait->wait.flags = 0; + INIT_LIST_HEAD(&wait->wait.entry); + kiocb->ki_flags |= IOCB_WAITQ; + kiocb->ki_waitq = wait; - return false; + io_get_req_task(req); + return true; } static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) @@ -3161,6 +3121,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + iov_count = iov_iter_count(iter); io_size = ret; req->result = io_size; ret = 0; @@ -3173,8 +3134,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, if (force_nonblock && !io_file_supports_async(req->file, READ)) goto copy_iov; - iov_count = iov_iter_count(iter); - ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), iov_count); if (unlikely(ret)) goto out_free; @@ -3186,14 +3146,21 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, ret = 0; goto out_free; } else if (ret == -EAGAIN) { - if (!force_nonblock) + /* IOPOLL retry should happen for io-wq threads */ + if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) + goto done; + /* no retry on NONBLOCK marked file */ + if (req->file->f_flags & O_NONBLOCK) goto done; + /* some cases will consume bytes even on error returns */ + iov_iter_revert(iter, iov_count - iov_iter_count(iter)); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); if (ret) goto out_free; return -EAGAIN; } else if (ret < 0) { - goto out_free; + /* make sure -ERESTARTSYS -> -EINTR is done */ + goto done; } /* read it all, or we did blocking attempt. no retry. */ @@ -3238,6 +3205,7 @@ done: kiocb_done(kiocb, ret, cs); ret = 0; out_free: + /* it's reportedly faster than delegating the null check to kfree() */ if (iovec) kfree(iovec); return ret; @@ -3276,6 +3244,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + iov_count = iov_iter_count(iter); io_size = ret; req->result = io_size; @@ -3292,8 +3261,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, (req->flags & REQ_F_ISREG)) goto copy_iov; - iov_count = iov_iter_count(iter); - ret = rw_verify_area(WRITE, req->file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), iov_count); if (unlikely(ret)) goto out_free; @@ -3325,15 +3293,25 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, */ if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT)) ret2 = -EAGAIN; + /* no retry on NONBLOCK marked file */ + if (ret2 == -EAGAIN && (req->file->f_flags & O_NONBLOCK)) + goto done; if (!force_nonblock || ret2 != -EAGAIN) { + /* IOPOLL retry should happen for io-wq threads */ + if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) + goto copy_iov; +done: kiocb_done(kiocb, ret2, cs); } else { copy_iov: + /* some cases will consume bytes even on error returns */ + iov_iter_revert(iter, iov_count - iov_iter_count(iter)); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); if (!ret) return -EAGAIN; } out_free: + /* it's reportedly faster than delegating the null check to kfree() */ if (iovec) kfree(iovec); return ret; @@ -4600,6 +4578,7 @@ struct io_poll_table { static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, __poll_t mask, task_work_func_t func) { + bool twa_signal_ok; int ret; /* for instances that support it check for an event match first: */ @@ -4615,12 +4594,20 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, percpu_ref_get(&req->ctx->refs); /* + * If we using the signalfd wait_queue_head for this wakeup, then + * it's not safe to use TWA_SIGNAL as we could be recursing on the + * tsk->sighand->siglock on doing the wakeup. Should not be needed + * either, as the normal wakeup will suffice. + */ + twa_signal_ok = (poll->head != &req->task->sighand->signalfd_wqh); + + /* * If this fails, then the task is exiting. When a task exits, the * work gets canceled, so just cancel this request as well instead * of executing it. We can't safely execute it anyway, as we may not * have the needed state needed for it anyway. */ - ret = io_req_task_work_add(req, &req->task_work); + ret = io_req_task_work_add(req, &req->task_work, twa_signal_ok); if (unlikely(ret)) { struct task_struct *tsk; @@ -4909,12 +4896,20 @@ static bool io_arm_poll_handler(struct io_kiocb *req) struct async_poll *apoll; struct io_poll_table ipt; __poll_t mask, ret; + int rw; if (!req->file || !file_can_poll(req->file)) return false; if (req->flags & REQ_F_POLLED) return false; - if (!def->pollin && !def->pollout) + if (def->pollin) + rw = READ; + else if (def->pollout) + rw = WRITE; + else + return false; + /* if we can't nonblock try, then no point in arming a poll handler */ + if (!io_file_supports_async(req->file, rw)) return false; apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); @@ -4932,6 +4927,12 @@ static bool io_arm_poll_handler(struct io_kiocb *req) mask |= POLLIN | POLLRDNORM; if (def->pollout) mask |= POLLOUT | POLLWRNORM; + + /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ + if ((req->opcode == IORING_OP_RECVMSG) && + (req->sr_msg.msg_flags & MSG_ERRQUEUE)) + mask &= ~POLLIN; + mask |= POLLERR | POLLPRI; ipt.pt._qproc = io_async_queue_proc; @@ -5653,6 +5654,18 @@ static void __io_clean_op(struct io_kiocb *req) } req->flags &= ~REQ_F_NEED_CLEANUP; } + + if (req->flags & REQ_F_INFLIGHT) { + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->inflight_lock, flags); + list_del(&req->inflight_entry); + if (waitqueue_active(&ctx->inflight_wait)) + wake_up(&ctx->inflight_wait); + spin_unlock_irqrestore(&ctx->inflight_lock, flags); + req->flags &= ~REQ_F_INFLIGHT; + } } static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, @@ -7327,7 +7340,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; index = i & IORING_FILE_TABLE_MASK; if (table->files[index]) { - file = io_file_from_index(ctx, index); + file = table->files[index]; err = io_queue_file_removal(data, file); if (err) break; @@ -7356,6 +7369,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, table->files[index] = file; err = io_sqe_file_register(ctx, file, i); if (err) { + table->files[index] = NULL; fput(file); break; } @@ -7455,9 +7469,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, { int ret; - mmgrab(current->mm); - ctx->sqo_mm = current->mm; - if (ctx->flags & IORING_SETUP_SQPOLL) { ret = -EPERM; if (!capable(CAP_SYS_ADMIN)) @@ -7502,10 +7513,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, return 0; err: io_finish_async(ctx); - if (ctx->sqo_mm) { - mmdrop(ctx->sqo_mm); - ctx->sqo_mm = NULL; - } return ret; } @@ -7979,7 +7986,13 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) ACCT_LOCKED); INIT_WORK(&ctx->exit_work, io_ring_exit_work); - queue_work(system_wq, &ctx->exit_work); + /* + * Use system_unbound_wq to avoid spawning tons of event kworkers + * if we're exiting a ton of rings at the same time. It just adds + * noise and overhead, there's no discernable change in runtime + * over using system_wq. + */ + queue_work(system_unbound_wq, &ctx->exit_work); } static int io_uring_release(struct inode *inode, struct file *file) @@ -8063,6 +8076,33 @@ static bool io_timeout_remove_link(struct io_ring_ctx *ctx, return found; } +static bool io_cancel_link_cb(struct io_wq_work *work, void *data) +{ + return io_match_link(container_of(work, struct io_kiocb, work), data); +} + +static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +{ + enum io_wq_cancel cret; + + /* cancel this particular work, if it's running */ + cret = io_wq_cancel_work(ctx->io_wq, &req->work); + if (cret != IO_WQ_CANCEL_NOTFOUND) + return; + + /* find links that hold this pending, cancel those */ + cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_link_cb, req, true); + if (cret != IO_WQ_CANCEL_NOTFOUND) + return; + + /* if we have a poll link holding this pending, cancel that */ + if (io_poll_remove_link(ctx, req)) + return; + + /* final option, timeout link is holding this req pending */ + io_timeout_remove_link(ctx, req); +} + static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct files_struct *files) { @@ -8094,35 +8134,9 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, /* We need to keep going until we don't find a matching req */ if (!cancel_req) break; - - if (cancel_req->flags & REQ_F_OVERFLOW) { - spin_lock_irq(&ctx->completion_lock); - list_del(&cancel_req->compl.list); - cancel_req->flags &= ~REQ_F_OVERFLOW; - - io_cqring_mark_overflow(ctx); - WRITE_ONCE(ctx->rings->cq_overflow, - atomic_inc_return(&ctx->cached_cq_overflow)); - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); - - /* - * Put inflight ref and overflow ref. If that's - * all we had, then we're done with this request. - */ - if (refcount_sub_and_test(2, &cancel_req->refs)) { - io_free_req(cancel_req); - finish_wait(&ctx->inflight_wait, &wait); - continue; - } - } else { - io_wq_cancel_work(ctx->io_wq, &cancel_req->work); - /* could be a link, check and remove if it is */ - if (!io_poll_remove_link(ctx, cancel_req)) - io_timeout_remove_link(ctx, cancel_req); - io_put_req(cancel_req); - } - + /* cancel this request, or head link requests */ + io_attempt_cancel(ctx, cancel_req); + io_put_req(cancel_req); schedule(); finish_wait(&ctx->inflight_wait, &wait); } @@ -8548,6 +8562,9 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, ctx->user = user; ctx->creds = get_current_cred(); + mmgrab(current->mm); + ctx->sqo_mm = current->mm; + /* * Account memory _before_ installing the file descriptor. Once * the descriptor is installed, it can get closed at any time. Also diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index 89f61d93c0bc..107ee80c3568 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -127,7 +127,7 @@ iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length, SEEK_HOLE); if (offset < 0) return length; - /* fall through */ + fallthrough; case IOMAP_HOLE: *(loff_t *)data = offset; return 0; @@ -175,7 +175,7 @@ iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length, SEEK_DATA); if (offset < 0) return length; - /*FALLTHRU*/ + fallthrough; default: *(loff_t *)data = offset; return 0; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index e4944436e733..17fdc482f554 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1285,7 +1285,7 @@ journal_t *jbd2_journal_init_inode(struct inode *inode) * superblock as being NULL to prevent the journal destroy from writing * back a bogus superblock. */ -static void journal_fail_superblock (journal_t *journal) +static void journal_fail_superblock(journal_t *journal) { struct buffer_head *bh = journal->j_sb_buffer; brelse(bh); @@ -1367,8 +1367,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) int ret; /* Buffer got discarded which means block device got invalidated */ - if (!buffer_mapped(bh)) + if (!buffer_mapped(bh)) { + unlock_buffer(bh); return -EIO; + } trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) @@ -1815,7 +1817,7 @@ int jbd2_journal_destroy(journal_t *journal) /** - *int jbd2_journal_check_used_features () - Check if features specified are used. + *int jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -1825,7 +1827,7 @@ int jbd2_journal_destroy(journal_t *journal) * features. Return true (non-zero) if it does. **/ -int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, +int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { journal_superblock_t *sb; @@ -1860,7 +1862,7 @@ int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, * all of a given set of features on this journal. Return true * (non-zero) if it can. */ -int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat, +int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { if (!compat && !ro && !incompat) @@ -1882,7 +1884,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com } /** - * int jbd2_journal_set_features () - Mark a given journal feature in the superblock + * int jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -1893,7 +1895,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com * */ -int jbd2_journal_set_features (journal_t *journal, unsigned long compat, +int jbd2_journal_set_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { #define INCOMPAT_FEATURE_ON(f) \ diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 2ed278f0dced..faa97d748474 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -690,14 +690,11 @@ static int do_one_pass(journal_t *journal, * number. */ if (pass == PASS_SCAN && jbd2_has_feature_checksum(journal)) { - int chksum_err, chksum_seen; struct commit_header *cbh = (struct commit_header *)bh->b_data; unsigned found_chksum = be32_to_cpu(cbh->h_chksum[0]); - chksum_err = chksum_seen = 0; - if (info->end_transaction) { journal->j_failed_commit = info->end_transaction; @@ -705,42 +702,23 @@ static int do_one_pass(journal_t *journal, break; } - if (crc32_sum == found_chksum && - cbh->h_chksum_type == JBD2_CRC32_CHKSUM && - cbh->h_chksum_size == - JBD2_CRC32_CHKSUM_SIZE) - chksum_seen = 1; - else if (!(cbh->h_chksum_type == 0 && - cbh->h_chksum_size == 0 && - found_chksum == 0 && - !chksum_seen)) - /* - * If fs is mounted using an old kernel and then - * kernel with journal_chksum is used then we - * get a situation where the journal flag has - * checksum flag set but checksums are not - * present i.e chksum = 0, in the individual - * commit blocks. - * Hence to avoid checksum failures, in this - * situation, this extra check is added. - */ - chksum_err = 1; - - if (chksum_err) { - info->end_transaction = next_commit_ID; - - if (!jbd2_has_feature_async_commit(journal)) { - journal->j_failed_commit = - next_commit_ID; - brelse(bh); - break; - } - } + /* Neither checksum match nor unused? */ + if (!((crc32_sum == found_chksum && + cbh->h_chksum_type == + JBD2_CRC32_CHKSUM && + cbh->h_chksum_size == + JBD2_CRC32_CHKSUM_SIZE) || + (cbh->h_chksum_type == 0 && + cbh->h_chksum_size == 0 && + found_chksum == 0))) + goto chksum_error; + crc32_sum = ~0; } if (pass == PASS_SCAN && !jbd2_commit_block_csum_verify(journal, bh->b_data)) { + chksum_error: info->end_transaction = next_commit_ID; if (!jbd2_has_feature_async_commit(journal)) { diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index e91aad3637a2..43985738aa86 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2026,6 +2026,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) */ static void __jbd2_journal_unfile_buffer(struct journal_head *jh) { + J_ASSERT_JH(jh, jh->b_transaction != NULL); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + __jbd2_journal_temp_unlink_buffer(jh); jh->b_transaction = NULL; } @@ -2078,10 +2081,6 @@ out: * int jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @page: to try and free - * @gfp_mask: we use the mask to detect how hard should we try to release - * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit - * code to release the buffers. - * * * For all the buffers on this page, * if they are fully written out ordered data, move them onto BUF_CLEAN @@ -2112,11 +2111,11 @@ out: * * Return 0 on failure, 1 on success */ -int jbd2_journal_try_to_free_buffers(journal_t *journal, - struct page *page, gfp_t gfp_mask) +int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page) { struct buffer_head *head; struct buffer_head *bh; + bool has_write_io_error = false; int ret = 0; J_ASSERT(PageLocked(page)); @@ -2141,11 +2140,26 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, jbd2_journal_put_journal_head(jh); if (buffer_jbd(bh)) goto busy; + + /* + * If we free a metadata buffer which has been failed to + * write out, the jbd2 checkpoint procedure will not detect + * this failure and may lead to filesystem inconsistency + * after cleanup journal tail. + */ + if (buffer_write_io_error(bh)) { + pr_err("JBD2: Error while async write back metadata bh %llu.", + (unsigned long long)bh->b_blocknr); + has_write_io_error = true; + } } while ((bh = bh->b_this_page) != head); ret = try_to_free_buffers(page); busy: + if (has_write_io_error) + jbd2_journal_abort(journal, -EIO); + return ret; } @@ -2572,6 +2586,13 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh) was_dirty = test_clear_buffer_jbddirty(bh); __jbd2_journal_temp_unlink_buffer(jh); + + /* + * b_transaction must be set, otherwise the new b_transaction won't + * be holding jh reference + */ + J_ASSERT_JH(jh, jh->b_transaction != NULL); + /* * We set b_transaction here because b_next_transaction will inherit * our jh reference and thus __jbd2_journal_file_buffer() must not diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index ab8cdd9e9325..78858f6e9583 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -341,7 +341,7 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino) rdev = old_decode_dev(je16_to_cpu(jdev.old_id)); else rdev = new_decode_dev(je32_to_cpu(jdev.new_id)); - /* fall through */ + fallthrough; case S_IFSOCK: case S_IFIFO: diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index bccfc40b3a74..2f6f0b140c05 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -1273,7 +1273,7 @@ static int jffs2_do_read_inode_internal(struct jffs2_sb_info *c, dbg_readinode("symlink's target '%s' cached\n", f->target); } - /* fall through... */ + fallthrough; case S_IFBLK: case S_IFCHR: diff --git a/fs/libfs.c b/fs/libfs.c index 4d08edf19c78..e0d42e977d9a 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -137,11 +137,11 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) switch (whence) { case 1: offset += file->f_pos; - /* fall through */ + fallthrough; case 0: if (offset >= 0) break; - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/fs/locks.c b/fs/locks.c index 8fc0542f5132..1f84a03601fe 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1499,7 +1499,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg) switch (arg) { case F_UNLCK: fl->fl_flags &= ~FL_UNLOCK_PENDING; - /* fall through */ + fallthrough; case F_RDLCK: fl->fl_flags &= ~FL_DOWNGRADE_PENDING; } @@ -2525,7 +2525,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, cmd = F_SETLKW; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; - /* Fallthrough */ + fallthrough; case F_SETLKW: file_lock->fl_flags |= FL_SLEEP; } @@ -2656,7 +2656,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, cmd = F_SETLKW64; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; - /* Fallthrough */ + fallthrough; case F_SETLKW64: file_lock->fl_flags |= FL_SLEEP; } diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index d1a0e2c8b1b4..08108b6d2fa1 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -753,7 +753,7 @@ out: case -ENODEV: /* Our extent block devices are unavailable */ set_bit(NFS_LSEG_UNAVAILABLE, &lseg->pls_flags); - /* Fall through */ + fallthrough; case 0: return lseg; default: diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index a12f42e7d8c7..e732580fe47b 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1181,7 +1181,7 @@ int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags) /* A NFSv4 OPEN will revalidate later */ if (server->caps & NFS_CAP_ATOMIC_OPEN) goto out; - /* Fallthrough */ + fallthrough; case S_IFDIR: if (server->flags & NFS_MOUNT_NOCTO) break; diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index a13e69009f19..7f5aa0403e16 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -187,7 +187,7 @@ static int filelayout_async_handle_error(struct rpc_task *task, pnfs_error_mark_layout_for_return(inode, lseg); pnfs_set_lo_fail(lseg); rpc_wake_up(&tbl->slot_tbl_waitq); - /* fall through */ + fallthrough; default: reset: dprintk("%s Retry through MDS. Error %d\n", __func__, diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 965145592750..ff8965d1a4d4 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1133,7 +1133,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, nfs4_delete_deviceid(devid->ld, devid->nfs_client, &devid->deviceid); rpc_wake_up(&tbl->slot_tbl_waitq); - /* fall through */ + fallthrough; default: if (ff_layout_avoid_mds_available_ds(lseg)) return -NFS4ERR_RESET_TO_PNFS; @@ -1260,7 +1260,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, */ if (opnum == OP_READ) break; - /* Fallthrough */ + fallthrough; default: pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode, lseg); diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index 66949da0e827..524812984e2d 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -651,21 +651,21 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: protofamily = AF_INET6; - /* fall through */ + fallthrough; case Opt_xprt_udp: ctx->flags &= ~NFS_MOUNT_TCP; ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; break; case Opt_xprt_tcp6: protofamily = AF_INET6; - /* fall through */ + fallthrough; case Opt_xprt_tcp: ctx->flags |= NFS_MOUNT_TCP; ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; break; case Opt_xprt_rdma6: protofamily = AF_INET6; - /* fall through */ + fallthrough; case Opt_xprt_rdma: /* vector side protocols to TCP */ ctx->flags |= NFS_MOUNT_TCP; @@ -684,13 +684,13 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: mountfamily = AF_INET6; - /* fall through */ + fallthrough; case Opt_xprt_udp: ctx->mount_server.protocol = XPRT_TRANSPORT_UDP; break; case Opt_xprt_tcp6: mountfamily = AF_INET6; - /* fall through */ + fallthrough; case Opt_xprt_tcp: ctx->mount_server.protocol = XPRT_TRANSPORT_TCP; break; @@ -899,9 +899,11 @@ static int nfs23_parse_monolithic(struct fs_context *fc, ctx->version = NFS_DEFAULT_VERSION; switch (data->version) { case 1: - data->namlen = 0; /* fall through */ + data->namlen = 0; + fallthrough; case 2: - data->bsize = 0; /* fall through */ + data->bsize = 0; + fallthrough; case 3: if (data->flags & NFS_MOUNT_VER3) goto out_no_v3; @@ -909,14 +911,14 @@ static int nfs23_parse_monolithic(struct fs_context *fc, memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE); /* Turn off security negotiation */ extra_flags |= NFS_MOUNT_SECFLAVOUR; - /* fall through */ + fallthrough; case 4: if (data->flags & NFS_MOUNT_SECFLAVOUR) goto out_no_sec; - /* fall through */ + fallthrough; case 5: memset(data->context, 0, sizeof(data->context)); - /* fall through */ + fallthrough; case 6: if (data->flags & NFS_MOUNT_VER3) { if (data->root.size > NFS3_FHSIZE || data->root.size == 0) diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 26c94b32d6f4..c6c863382f37 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -108,7 +108,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type) case -EPROTONOSUPPORT: dprintk("NFS_V3_ACL extension not supported; disabling\n"); server->caps &= ~NFS_CAP_ACLS; - /* fall through */ + fallthrough; case -ENOTSUPP: status = -EOPNOTSUPP; default: @@ -228,7 +228,7 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, dprintk("NFS_V3_ACL SETACL RPC not supported" "(will not retry)\n"); server->caps &= ~NFS_CAP_ACLS; - /* fall through */ + fallthrough; case -ENOTSUPP: status = -EOPNOTSUPP; } diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index a33970765467..fdfc77486ace 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -211,7 +211,7 @@ static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) ret = nfs42_proc_llseek(filep, offset, whence); if (ret != -ENOTSUPP) return ret; - /* Fall through */ + fallthrough; default: return nfs_file_llseek(filep, offset, whence); } diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 1e7296395d71..62e6eea5c516 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -520,7 +520,7 @@ static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap, switch (token) { case Opt_find_uid: im->im_type = IDMAP_TYPE_USER; - /* Fall through */ + fallthrough; case Opt_find_gid: im->im_conv = IDMAP_CONV_NAMETOID; ret = match_strlcpy(im->im_name, &substr, IDMAP_NAMESZ); @@ -528,7 +528,7 @@ static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap, case Opt_find_user: im->im_type = IDMAP_TYPE_USER; - /* Fall through */ + fallthrough; case Opt_find_group: im->im_conv = IDMAP_CONV_IDTONAME; ret = match_int(&substr, &im->im_id); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index dbd01548335b..f8946b9468ef 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -483,7 +483,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server, stateid); goto wait_on_recovery; } - /* Fall through */ + fallthrough; case -NFS4ERR_OPENMODE: if (inode) { int err; @@ -534,10 +534,10 @@ static int nfs4_do_handle_exception(struct nfs_server *server, ret = -EBUSY; break; } - /* Fall through */ + fallthrough; case -NFS4ERR_DELAY: nfs_inc_server_stats(server, NFSIOS_DELAY); - /* Fall through */ + fallthrough; case -NFS4ERR_GRACE: case -NFS4ERR_LAYOUTTRYLATER: case -NFS4ERR_RECALLCONFLICT: @@ -1505,7 +1505,7 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode, case NFS4_OPEN_CLAIM_PREVIOUS: if (!test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags)) break; - /* Fall through */ + fallthrough; default: return 0; } @@ -2439,7 +2439,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) case NFS4_OPEN_CLAIM_DELEG_CUR_FH: case NFS4_OPEN_CLAIM_DELEG_PREV_FH: data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0]; - /* Fall through */ + fallthrough; case NFS4_OPEN_CLAIM_FH: task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR]; } @@ -3545,11 +3545,11 @@ static void nfs4_close_done(struct rpc_task *task, void *data) nfs4_free_revoked_stateid(server, &calldata->arg.stateid, task->tk_msg.rpc_cred); - /* Fallthrough */ + fallthrough; case -NFS4ERR_BAD_STATEID: if (calldata->arg.fmode == 0) break; - /* Fallthrough */ + fallthrough; default: task->tk_status = nfs4_async_handle_exception(task, server, task->tk_status, &exception); @@ -6294,7 +6294,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) nfs4_free_revoked_stateid(data->res.server, data->args.stateid, task->tk_msg.rpc_cred); - /* Fallthrough */ + fallthrough; case -NFS4ERR_BAD_STATEID: case -NFS4ERR_STALE_STATEID: case -ETIMEDOUT: @@ -6314,7 +6314,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) data->res.fattr = NULL; goto out_restart; } - /* Fallthrough */ + fallthrough; default: task->tk_status = nfs4_async_handle_exception(task, data->res.server, task->tk_status, @@ -6622,13 +6622,13 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) if (nfs4_update_lock_stateid(calldata->lsp, &calldata->res.stateid)) break; - /* Fall through */ + fallthrough; case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_EXPIRED: nfs4_free_revoked_stateid(calldata->server, &calldata->arg.stateid, task->tk_msg.rpc_cred); - /* Fall through */ + fallthrough; case -NFS4ERR_BAD_STATEID: case -NFS4ERR_STALE_STATEID: if (nfs4_sync_lock_stateid(&calldata->arg.stateid, @@ -8665,7 +8665,7 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata) dprintk("%s Retry: tk_status %d\n", __func__, task->tk_status); rpc_delay(task, NFS4_POLL_RETRY_MIN); task->tk_status = 0; - /* fall through */ + fallthrough; case -NFS4ERR_RETRY_UNCACHED_REP: rpc_restart_call_prepare(task); return; @@ -9113,13 +9113,13 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf switch(task->tk_status) { case 0: wake_up_all(&clp->cl_lock_waitq); - /* Fallthrough */ + fallthrough; case -NFS4ERR_COMPLETE_ALREADY: case -NFS4ERR_WRONG_CRED: /* What to do here? */ break; case -NFS4ERR_DELAY: rpc_delay(task, NFS4_POLL_RETRY_MAX); - /* fall through */ + fallthrough; case -NFS4ERR_RETRY_UNCACHED_REP: return -EAGAIN; case -NFS4ERR_BADSESSION: @@ -9434,10 +9434,10 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) &lrp->args.range, lrp->args.inode)) goto out_restart; - /* Fallthrough */ + fallthrough; default: task->tk_status = 0; - /* Fallthrough */ + fallthrough; case 0: break; case -NFS4ERR_DELAY: diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index b1dba24918f8..4bf10792cb5b 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1530,7 +1530,7 @@ restart: default: pr_err("NFS: %s: unhandled error %d\n", __func__, status); - /* Fall through */ + fallthrough; case -ENOMEM: case -NFS4ERR_DENIED: case -NFS4ERR_RECLAIM_BAD: @@ -1667,7 +1667,7 @@ restart: break; } printk(KERN_ERR "NFS: %s: unhandled error %d\n", __func__, status); - /* Fall through */ + fallthrough; case -ENOENT: case -ENOMEM: case -EACCES: @@ -1683,7 +1683,7 @@ restart: set_bit(ops->state_flag_bit, &state->flags); break; } - /* Fall through */ + fallthrough; case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_OLD_STATEID: @@ -1695,7 +1695,7 @@ restart: case -NFS4ERR_EXPIRED: case -NFS4ERR_NO_GRACE: nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state); - /* Fall through */ + fallthrough; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: @@ -2273,11 +2273,11 @@ again: case -ETIMEDOUT: if (clnt->cl_softrtry) break; - /* Fall through */ + fallthrough; case -NFS4ERR_DELAY: case -EAGAIN: ssleep(1); - /* Fall through */ + fallthrough; case -NFS4ERR_STALE_CLIENTID: dprintk("NFS: %s after status %d, retrying\n", __func__, status); @@ -2289,7 +2289,7 @@ again: } if (clnt->cl_auth->au_flavor == RPC_AUTH_UNIX) break; - /* Fall through */ + fallthrough; case -NFS4ERR_CLID_INUSE: case -NFS4ERR_WRONGSEC: /* No point in retrying if we already used RPC_AUTH_UNIX */ diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6ea4cac41e46..6985cacf4700 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -711,7 +711,7 @@ static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr, case FLUSH_COND_STABLE: if (nfs_reqs_to_commit(cinfo)) break; - /* fall through */ + fallthrough; default: hdr->args.stable = NFS_FILE_SYNC; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 40332c758d84..71f7741126b6 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1541,7 +1541,7 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args, case 0: if (res->lrs_present) res_stateid = &res->stateid; - /* Fallthrough */ + fallthrough; default: arg_stateid = &args->stateid; } diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c index 8ceb6425e01a..d056ad2fdefd 100644 --- a/fs/nfs_common/nfsacl.c +++ b/fs/nfs_common/nfsacl.c @@ -237,7 +237,7 @@ posix_acl_from_nfsacl(struct posix_acl *acl) break; case ACL_MASK: mask = pa; - /* fall through */ + fallthrough; case ACL_OTHER: break; } diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 9bbaa671c079..311e5ce80cfc 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -83,13 +83,13 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, bex->soff = iomap.addr; break; } - /*FALLTHRU*/ + fallthrough; case IOMAP_HOLE: if (seg->iomode == IOMODE_READ) { bex->es = PNFS_BLOCK_NONE_DATA; break; } - /*FALLTHRU*/ + fallthrough; case IOMAP_DELALLOC: default: WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 7fbe9840a03e..052be5bf9ef5 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1119,7 +1119,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback break; case -ESERVERFAULT: ++session->se_cb_seq_nr; - /* Fall through */ + fallthrough; case 1: case -NFS4ERR_BADSESSION: nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status); diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index e12409eca7cc..a97873f2d22b 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -681,7 +681,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) rpc_delay(task, HZ/100); /* 10 mili-seconds */ return 0; } - /* Fallthrough */ + fallthrough; default: /* * Unknown error or non-responding client, we'll need to fence. diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a527da3d8052..eaf50eafa935 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -428,7 +428,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; reclaim = true; - /* fall through */ + fallthrough; case NFS4_OPEN_CLAIM_FH: case NFS4_OPEN_CLAIM_DELEG_CUR_FH: status = do_open_fhandle(rqstp, cstate, open); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 81ed8e8bab3f..c09a2a4281ec 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3117,7 +3117,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, break; default: /* checked by xdr code */ WARN_ON_ONCE(1); - /* fall through */ + fallthrough; case SP4_SSV: status = nfserr_encr_alg_unsupp; goto out_nolock; @@ -4532,7 +4532,7 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, rpc_delay(task, 2 * HZ); return 0; } - /*FALLTHRU*/ + fallthrough; default: return 1; } @@ -4597,6 +4597,8 @@ static bool nfsd_breaker_owns_lease(struct file_lock *fl) if (!i_am_nfsd()) return NULL; rqst = kthread_data(current); + if (!rqst->rq_lease_breaker) + return NULL; clp = *(rqst->rq_lease_breaker); return dl->dl_stid.sc_client == clp; } @@ -5652,7 +5654,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) break; default: printk("unknown stateid type %x\n", s->sc_type); - /* Fallthrough */ + fallthrough; case NFS4_CLOSED_STID: case NFS4_CLOSED_DELEG_STID: status = nfserr_bad_stateid; @@ -6742,7 +6744,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, case NFS4_READW_LT: if (nfsd4_has_session(cstate)) fl_flags |= FL_SLEEP; - /* Fallthrough */ + fallthrough; case NFS4_READ_LT: spin_lock(&fp->fi_lock); nf = find_readable_file_locked(fp); @@ -6754,7 +6756,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, case NFS4_WRITEW_LT: if (nfsd4_has_session(cstate)) fl_flags |= FL_SLEEP; - /* Fallthrough */ + fallthrough; case NFS4_WRITE_LT: spin_lock(&fp->fi_lock); nf = find_writeable_file_locked(fp); @@ -6816,7 +6818,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, break; case FILE_LOCK_DEFERRED: nbl = NULL; - /* Fallthrough */ + fallthrough; case -EAGAIN: /* conflock holds conflicting lock */ status = nfserr_denied; dprintk("NFSD: nfsd4_lock: conflicting lock found!\n"); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 37bc8f5f4514..c81dbbad8792 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -459,7 +459,7 @@ static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp) case FSID_DEV: if (!old_valid_dev(exp_sb(exp)->s_dev)) return false; - /* FALL THROUGH */ + fallthrough; case FSID_MAJOR_MINOR: case FSID_ENCODE_DEV: return exp_sb(exp)->s_type->fs_flags & FS_REQUIRES_DEV; @@ -469,7 +469,7 @@ static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp) case FSID_UUID16: if (!is_root_export(exp)) return false; - /* fall through */ + fallthrough; case FSID_UUID4_INUM: case FSID_UUID16_INUM: return exp->ex_uuid != NULL; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 543bbe0a556e..6e0b066480c5 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -314,7 +314,7 @@ nfsd_proc_create(struct svc_rqst *rqstp) rdev = inode->i_rdev; attr->ia_valid |= ATTR_SIZE; - /* FALLTHROUGH */ + fallthrough; case S_IFIFO: /* this is probably a permission check.. * at least IRIX implements perm checking on diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index b603dfcdd361..f7f6473578af 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -221,7 +221,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change) case NFSD_TEST: if (nn->nfsd_versions) return nn->nfsd_versions[vers]; - /* Fallthrough */ + fallthrough; case NFSD_AVAIL: return nfsd_support_version(vers); } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 7d2933b85b65..aba5af9df328 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1456,7 +1456,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, *created = true; break; } - /* fall through */ + fallthrough; case NFS4_CREATE_EXCLUSIVE4_1: if ( d_inode(dchild)->i_mtime.tv_sec == v_mtime && d_inode(dchild)->i_atime.tv_sec == v_atime @@ -1465,7 +1465,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, *created = true; goto set_attr; } - /* fall through */ + fallthrough; case NFS3_CREATE_GUARDED: err = nfserr_exist; } diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index fb5a9a8a13cf..e516ae389ca5 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -519,7 +519,7 @@ int nilfs_bmap_read(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode) break; case NILFS_IFILE_INO: lockdep_set_class(&bmap->b_sem, &nilfs_bmap_mdt_lock_key); - /* Fall through */ + fallthrough; default: bmap->b_ptr_type = NILFS_BMAP_PTR_VM; bmap->b_last_allocated_key = 0; diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 0b453ef8fae5..2217f904a7cf 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -626,7 +626,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs, !(flags & NILFS_SS_SYNDT)) goto try_next_pseg; state = RF_DSYNC_ST; - /* Fall through */ + fallthrough; case RF_DSYNC_ST: if (!(flags & NILFS_SS_SYNDT)) goto confused; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index a651e821c2de..e3726aca28ed 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1138,7 +1138,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) nilfs_sc_cstage_set(sci, NILFS_ST_DAT); goto dat_stage; } - nilfs_sc_cstage_inc(sci); /* Fall through */ + nilfs_sc_cstage_inc(sci); + fallthrough; case NILFS_ST_GC: if (nilfs_doing_gc()) { head = &sci->sc_gc_inodes; @@ -1159,7 +1160,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } sci->sc_stage.gc_inode_ptr = NULL; } - nilfs_sc_cstage_inc(sci); /* Fall through */ + nilfs_sc_cstage_inc(sci); + fallthrough; case NILFS_ST_FILE: head = &sci->sc_dirty_files; ii = list_prepare_entry(sci->sc_stage.dirty_file_ptr, head, @@ -1186,7 +1188,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } nilfs_sc_cstage_inc(sci); sci->sc_stage.flags |= NILFS_CF_IFILE_STARTED; - /* Fall through */ + fallthrough; case NILFS_ST_IFILE: err = nilfs_segctor_scan_file(sci, sci->sc_root->ifile, &nilfs_sc_file_ops); @@ -1197,13 +1199,14 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) err = nilfs_segctor_create_checkpoint(sci); if (unlikely(err)) break; - /* Fall through */ + fallthrough; case NILFS_ST_CPFILE: err = nilfs_segctor_scan_file(sci, nilfs->ns_cpfile, &nilfs_sc_file_ops); if (unlikely(err)) break; - nilfs_sc_cstage_inc(sci); /* Fall through */ + nilfs_sc_cstage_inc(sci); + fallthrough; case NILFS_ST_SUFILE: err = nilfs_sufile_freev(nilfs->ns_sufile, sci->sc_freesegs, sci->sc_nfreesegs, &ndone); @@ -1219,7 +1222,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - nilfs_sc_cstage_inc(sci); /* Fall through */ + nilfs_sc_cstage_inc(sci); + fallthrough; case NILFS_ST_DAT: dat_stage: err = nilfs_segctor_scan_file(sci, nilfs->ns_dat, @@ -1230,7 +1234,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; } - nilfs_sc_cstage_inc(sci); /* Fall through */ + nilfs_sc_cstage_inc(sci); + fallthrough; case NILFS_ST_SR: if (mode == SC_LSEG_SR) { /* Appending a super root */ diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 559de311deca..3e01d8f2ab90 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1147,7 +1147,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, } switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) { - case FAN_MARK_ADD: /* fallthrough */ + case FAN_MARK_ADD: case FAN_MARK_REMOVE: if (!mask) return -EINVAL; diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c index 1ef24574f481..cea739be77c4 100644 --- a/fs/ocfs2/cluster/quorum.c +++ b/fs/ocfs2/cluster/quorum.c @@ -67,7 +67,7 @@ static void o2quo_fence_self(void) default: WARN_ON(o2nm_single_cluster->cl_fence_method >= O2NM_FENCE_METHODS); - /* fall through */ + fallthrough; case O2NM_FENCE_RESET: printk(KERN_ERR "*** ocfs2 is very sorry to be fencing this " "system by restarting ***\n"); diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c index 819428dfa32f..3ce89216670c 100644 --- a/fs/pstore/zone.c +++ b/fs/pstore/zone.c @@ -1081,7 +1081,6 @@ next_zone: readop = psz_ftrace_read; break; case PSTORE_TYPE_CONSOLE: - fallthrough; case PSTORE_TYPE_PMSG: readop = psz_record_read; break; diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 5444d3c4d93f..47f9e151988b 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -38,7 +38,7 @@ static int check_quotactl_permission(struct super_block *sb, int type, int cmd, if ((type == USRQUOTA && uid_eq(current_euid(), make_kuid(current_user_ns(), id))) || (type == GRPQUOTA && in_egroup_p(make_kgid(current_user_ns(), id)))) break; - /*FALLTHROUGH*/ + fallthrough; default: if (!capable(CAP_SYS_ADMIN)) return -EPERM; diff --git a/fs/romfs/storage.c b/fs/romfs/storage.c index 6b2b4362089e..b57b3ffcbc32 100644 --- a/fs/romfs/storage.c +++ b/fs/romfs/storage.c @@ -217,10 +217,8 @@ int romfs_dev_read(struct super_block *sb, unsigned long pos, size_t limit; limit = romfs_maxsize(sb); - if (pos >= limit) + if (pos >= limit || buflen > limit - pos) return -EIO; - if (buflen > limit - pos) - buflen = limit - pos; #ifdef CONFIG_ROMFS_ON_MTD if (sb->s_mtd) diff --git a/fs/seq_file.c b/fs/seq_file.c index 4e6239f33c06..31219c1db17d 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -295,7 +295,7 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence) switch (whence) { case SEEK_CUR: offset += file->f_pos; - /* fall through */ + fallthrough; case SEEK_SET: if (offset < 0) break; diff --git a/fs/signalfd.c b/fs/signalfd.c index 5b78719be445..456046e15873 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -176,7 +176,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info if (!nonblock) break; ret = -EAGAIN; - /* fall through */ + fallthrough; default: spin_unlock_irq(¤t->sighand->siglock); return ret; diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 76bb1c846845..8a19773b5a0b 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -87,7 +87,11 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length, int error, i; struct bio *bio; - bio = bio_alloc(GFP_NOIO, page_count); + if (page_count <= BIO_MAX_PAGES) + bio = bio_alloc(GFP_NOIO, page_count); + else + bio = bio_kmalloc(GFP_NOIO, page_count); + if (!bio) return -ENOMEM; diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index 22bfda158f7f..6d6cd85c2b4c 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -269,7 +269,7 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops, break; /* No more room on heap so make it un-categorized */ cat = LPROPS_UNCAT; - /* Fall through */ + fallthrough; case LPROPS_UNCAT: list_add(&lprops->list, &c->uncat_list); break; @@ -313,7 +313,7 @@ static void ubifs_remove_from_cat(struct ubifs_info *c, case LPROPS_FREEABLE: c->freeable_cnt -= 1; ubifs_assert(c, c->freeable_cnt >= 0); - /* Fall through */ + fallthrough; case LPROPS_UNCAT: case LPROPS_EMPTY: case LPROPS_FRDI_IDX: diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 6023c97c6da2..25ff91c7e94a 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -52,7 +52,7 @@ static int udf_pc_to_char(struct super_block *sb, unsigned char *from, elen += pc->lengthComponentIdent; break; } - /* Fall through */ + fallthrough; case 2: if (tolen == 0) return -ENAMETOOLONG; diff --git a/fs/ufs/util.h b/fs/ufs/util.h index e1f1b2e868a7..4931bec1a01c 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -42,7 +42,7 @@ ufs_get_fs_state(struct super_block *sb, struct ufs_super_block_first *usb1, case UFS_ST_SUNOS: if (fs32_to_cpu(sb, usb3->fs_postblformat) == UFS_42POSTBLFMT) return fs32_to_cpu(sb, usb1->fs_u0.fs_sun.fs_state); - /* Fall Through - to UFS_ST_SUN */ + fallthrough; /* to UFS_ST_SUN */ case UFS_ST_SUN: return fs32_to_cpu(sb, usb3->fs_un2.fs_sun.fs_state); case UFS_ST_SUNx86: @@ -63,7 +63,7 @@ ufs_set_fs_state(struct super_block *sb, struct ufs_super_block_first *usb1, usb1->fs_u0.fs_sun.fs_state = cpu_to_fs32(sb, value); break; } - /* Fall Through - to UFS_ST_SUN */ + fallthrough; /* to UFS_ST_SUN */ case UFS_ST_SUN: usb3->fs_un2.fs_sun.fs_state = cpu_to_fs32(sb, value); break; @@ -197,7 +197,7 @@ ufs_get_inode_uid(struct super_block *sb, struct ufs_inode *inode) case UFS_UID_EFT: if (inode->ui_u1.oldids.ui_suid == 0xFFFF) return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_uid); - /* Fall through */ + fallthrough; default: return fs16_to_cpu(sb, inode->ui_u1.oldids.ui_suid); } @@ -215,7 +215,7 @@ ufs_set_inode_uid(struct super_block *sb, struct ufs_inode *inode, u32 value) inode->ui_u3.ui_sun.ui_uid = cpu_to_fs32(sb, value); if (value > 0xFFFF) value = 0xFFFF; - /* Fall through */ + fallthrough; default: inode->ui_u1.oldids.ui_suid = cpu_to_fs16(sb, value); break; @@ -231,7 +231,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode) case UFS_UID_EFT: if (inode->ui_u1.oldids.ui_sgid == 0xFFFF) return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid); - /* Fall through */ + fallthrough; default: return fs16_to_cpu(sb, inode->ui_u1.oldids.ui_sgid); } @@ -249,7 +249,7 @@ ufs_set_inode_gid(struct super_block *sb, struct ufs_inode *inode, u32 value) inode->ui_u3.ui_sun.ui_gid = cpu_to_fs32(sb, value); if (value > 0xFFFF) value = 0xFFFF; - /* Fall through */ + fallthrough; default: inode->ui_u1.oldids.ui_sgid = cpu_to_fs16(sb, value); break; diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c index 96bd160da48b..018057546067 100644 --- a/fs/vboxsf/utils.c +++ b/fs/vboxsf/utils.c @@ -226,7 +226,7 @@ int vboxsf_getattr(const struct path *path, struct kstat *kstat, break; case AT_STATX_FORCE_SYNC: sf_i->force_restat = 1; - /* fall-through */ + fallthrough; default: err = vboxsf_inode_revalidate(dentry); } diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 8623c815164a..305d4bc07337 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -653,8 +653,8 @@ xfs_attr_shortform_create( ASSERT(ifp->if_flags & XFS_IFINLINE); } xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK); - hdr = (xfs_attr_sf_hdr_t *)ifp->if_u1.if_data; - hdr->count = 0; + hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data; + memset(hdr, 0, sizeof(*hdr)); hdr->totsize = cpu_to_be16(sizeof(*hdr)); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); } @@ -1036,8 +1036,10 @@ xfs_attr_shortform_verify( * struct xfs_attr_sf_entry has a variable length. * Check the fixed-offset parts of the structure are * within the data buffer. + * xfs_attr_sf_entry is defined with a 1-byte variable + * array at the end, so we must subtract that off. */ - if (((char *)sfep + sizeof(*sfep)) >= endp) + if (((char *)sfep + sizeof(*sfep) - 1) >= endp) return __this_address; /* Don't allow names with known bad length. */ diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index f742a96a2fe1..a6b37db55169 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -688,7 +688,7 @@ xfs_ialloc_ag_alloc( args.minalignslop = igeo->cluster_align - 1; /* Allow space for the inode btree to split. */ - args.minleft = igeo->inobt_maxlevels - 1; + args.minleft = igeo->inobt_maxlevels; if ((error = xfs_alloc_vextent(&args))) return error; @@ -736,7 +736,7 @@ xfs_ialloc_ag_alloc( /* * Allow space for the inode btree to split. */ - args.minleft = igeo->inobt_maxlevels - 1; + args.minleft = igeo->inobt_maxlevels; if ((error = xfs_alloc_vextent(&args))) return error; } diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index e15129647e00..b7e222befb08 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -110,9 +110,9 @@ xfs_trans_log_inode( * to log the timestamps, or will clear already cleared fields in the * worst case. */ - if (inode->i_state & (I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED)) { + if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); - inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED); + inode->i_state &= ~I_DIRTY_TIME; spin_unlock(&inode->i_lock); } diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h index c6df01a2a158..7ad3659c5d2a 100644 --- a/fs/xfs/libxfs/xfs_trans_space.h +++ b/fs/xfs/libxfs/xfs_trans_space.h @@ -58,7 +58,7 @@ #define XFS_IALLOC_SPACE_RES(mp) \ (M_IGEO(mp)->ialloc_blks + \ ((xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1) * \ - (M_IGEO(mp)->inobt_maxlevels - 1))) + M_IGEO(mp)->inobt_maxlevels)) /* * Space reservation values for various transactions. diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 73cafc843cd7..5123f82f2477 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1165,7 +1165,7 @@ xfs_insert_file_space( goto out_trans_cancel; do { - error = xfs_trans_roll_inode(&tp, ip); + error = xfs_defer_finish(&tp); if (error) goto out_trans_cancel; diff --git a/include/drm/drm_hdcp.h b/include/drm/drm_hdcp.h index c6bab4986a65..fe58dbb46962 100644 --- a/include/drm/drm_hdcp.h +++ b/include/drm/drm_hdcp.h @@ -29,6 +29,9 @@ /* Slave address for the HDCP registers in the receiver */ #define DRM_HDCP_DDC_ADDR 0x3A +/* Value to use at the end of the SHA-1 bytestream used for repeaters */ +#define DRM_HDCP_SHA1_TERMINATOR 0x80 + /* HDCP register offsets for HDMI/DVI devices */ #define DRM_HDCP_DDC_BKSV 0x00 #define DRM_HDCP_DDC_RI_PRIME 0x08 diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h index 4fc9a43ac45a..aafd07388eb7 100644 --- a/include/drm/drm_modeset_lock.h +++ b/include/drm/drm_modeset_lock.h @@ -164,6 +164,8 @@ int drm_modeset_lock_all_ctx(struct drm_device *dev, * is 0, so no error checking is necessary */ #define DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, flags, ret) \ + if (!drm_drv_uses_atomic_modeset(dev)) \ + mutex_lock(&dev->mode_config.mutex); \ drm_modeset_acquire_init(&ctx, flags); \ modeset_lock_retry: \ ret = drm_modeset_lock_all_ctx(dev, &ctx); \ @@ -172,6 +174,7 @@ modeset_lock_retry: \ /** * DRM_MODESET_LOCK_ALL_END - Helper to release and cleanup modeset locks + * @dev: drm device * @ctx: local modeset acquire context, will be dereferenced * @ret: local ret/err/etc variable to track error status * @@ -188,7 +191,7 @@ modeset_lock_retry: \ * to that failure. In both of these cases the code between BEGIN/END will not * be run, so the failure will reflect the inability to grab the locks. */ -#define DRM_MODESET_LOCK_ALL_END(ctx, ret) \ +#define DRM_MODESET_LOCK_ALL_END(dev, ctx, ret) \ modeset_lock_fail: \ if (ret == -EDEADLK) { \ ret = drm_modeset_backoff(&ctx); \ @@ -196,6 +199,8 @@ modeset_lock_fail: \ goto modeset_lock_retry; \ } \ drm_modeset_drop_locks(&ctx); \ - drm_modeset_acquire_fini(&ctx); + drm_modeset_acquire_fini(&ctx); \ + if (!drm_drv_uses_atomic_modeset(dev)) \ + mutex_unlock(&dev->mode_config.mutex); #endif /* DRM_MODESET_LOCK_H_ */ diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 64f367044e25..2f98d2fce62e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -279,6 +279,31 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL) +/* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a + * fullsock and its parent fullsock cannot be traced by + * sk_to_full_sk(). + * + * e.g. sock_ops->sk is a request_sock and it is under syncookie mode. + * Its listener-sk is not attached to the rsk_listener. + * In this case, the caller holds the listener-sk (unlocked), + * set its sock_ops->sk to req_sk, and call this SOCK_OPS"_SK" with + * the listener-sk such that the cgroup-bpf-progs of the + * listener-sk will be run. + * + * Regardless of syncookie mode or not, + * calling bpf_setsockopt on listener-sk will not make sense anyway, + * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here. + */ +#define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ + sock_ops, \ + BPF_CGROUP_SOCK_OPS); \ + __ret; \ +}) + #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 55f694b63164..c6d9f2c444f4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -34,6 +34,8 @@ struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; +struct bpf_local_storage; +struct bpf_local_storage_map; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -104,6 +106,25 @@ struct bpf_map_ops { __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); + /* Functions called by bpf_local_storage maps */ + int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, + void *owner, u32 size); + void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, + void *owner, u32 size); + struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); + + /* map_meta_equal must be implemented for maps that can be + * used as an inner map. It is a runtime check to ensure + * an inner map can be inserted to an outer map. + * + * Some properties of the inner map has been used during the + * verification time. When inserting an inner map at the runtime, + * map_meta_equal has to ensure the inserting map has the same + * properties that the verifier has used earlier. + */ + bool (*map_meta_equal)(const struct bpf_map *meta0, + const struct bpf_map *meta1); + /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; @@ -227,6 +248,9 @@ int map_check_no_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type); +bool bpf_map_meta_equal(const struct bpf_map *meta0, + const struct bpf_map *meta1); + extern const struct bpf_map_ops bpf_map_offload_ops; /* function argument constraints */ @@ -309,6 +333,7 @@ struct bpf_func_proto { * for this argument. */ int *ret_btf_id; /* return value btf_id */ + bool (*allowed)(const struct bpf_prog *prog); }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -514,6 +539,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(void); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); +void notrace __bpf_prog_enter_sleepable(void); +void notrace __bpf_prog_exit_sleepable(void); struct bpf_ksym { unsigned long start; @@ -709,6 +736,7 @@ struct bpf_prog_aux { bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; + bool sleepable; enum bpf_tramp_prog_type trampoline_prog_type; struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; @@ -1218,12 +1246,18 @@ typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); +typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, + struct seq_file *seq); +typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, + struct bpf_link_info *info); #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; bpf_iter_attach_target_t attach_target; bpf_iter_detach_target_t detach_target; + bpf_iter_show_fdinfo_t show_fdinfo; + bpf_iter_fill_link_info_t fill_link_info; u32 ctx_arg_info_size; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; @@ -1250,6 +1284,10 @@ int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); +void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, + struct seq_file *seq); +int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, + struct bpf_link_info *info); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); @@ -1340,6 +1378,8 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); +bool btf_struct_ids_match(struct bpf_verifier_log *log, + int off, u32 id, u32 need_type_id); int btf_resolve_helper_id(struct bpf_verifier_log *log, const struct bpf_func_proto *fn, int); @@ -1358,6 +1398,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); struct bpf_prog *bpf_prog_by_id(u32 id); +struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); #else /* !CONFIG_BPF_SYSCALL */ @@ -1637,6 +1678,7 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); +int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else @@ -1658,6 +1700,12 @@ static inline int sock_map_prog_detach(const union bpf_attr *attr, { return -EOPNOTSUPP; } + +static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, + u64 flags) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_STREAM_PARSER */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) @@ -1736,6 +1784,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; +extern const struct bpf_func_proto bpf_copy_from_user_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -1850,4 +1899,7 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +struct btf_id_set; +bool btf_id_set_contains(struct btf_id_set *set, u32 id); + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h new file mode 100644 index 000000000000..b2c9463f36a1 --- /dev/null +++ b/include/linux/bpf_local_storage.h @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2019 Facebook + * Copyright 2020 Google LLC. + */ + +#ifndef _BPF_LOCAL_STORAGE_H +#define _BPF_LOCAL_STORAGE_H + +#include <linux/bpf.h> +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <uapi/linux/btf.h> + +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_map_bucket { + struct hlist_head list; + raw_spinlock_t lock; +}; + +/* Thp map is not the primary owner of a bpf_local_storage_elem. + * Instead, the container object (eg. sk->sk_bpf_storage) is. + * + * The map (bpf_local_storage_map) is for two purposes + * 1. Define the size of the "local storage". It is + * the map's value_size. + * + * 2. Maintain a list to keep track of all elems such + * that they can be cleaned up during the map destruction. + * + * When a bpf local storage is being looked up for a + * particular object, the "bpf_map" pointer is actually used + * as the "key" to search in the list of elem in + * the respective bpf_local_storage owned by the object. + * + * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer + * as the searching key. + */ +struct bpf_local_storage_map { + struct bpf_map map; + /* Lookup elem does not require accessing the map. + * + * Updating/Deleting requires a bucket lock to + * link/unlink the elem from the map. Having + * multiple buckets to improve contention. + */ + struct bpf_local_storage_map_bucket *buckets; + u32 bucket_log; + u16 elem_size; + u16 cache_idx; +}; + +struct bpf_local_storage_data { + /* smap is used as the searching key when looking up + * from the object's bpf_local_storage. + * + * Put it in the same cacheline as the data to minimize + * the number of cachelines access during the cache hit case. + */ + struct bpf_local_storage_map __rcu *smap; + u8 data[] __aligned(8); +}; + +/* Linked to bpf_local_storage and bpf_local_storage_map */ +struct bpf_local_storage_elem { + struct hlist_node map_node; /* Linked to bpf_local_storage_map */ + struct hlist_node snode; /* Linked to bpf_local_storage */ + struct bpf_local_storage __rcu *local_storage; + struct rcu_head rcu; + /* 8 bytes hole */ + /* The data is stored in aother cacheline to minimize + * the number of cachelines access during a cache hit. + */ + struct bpf_local_storage_data sdata ____cacheline_aligned; +}; + +struct bpf_local_storage { + struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; + struct hlist_head list; /* List of bpf_local_storage_elem */ + void *owner; /* The object that owns the above "list" of + * bpf_local_storage_elem. + */ + struct rcu_head rcu; + raw_spinlock_t lock; /* Protect adding/removing from the "list" */ +}; + +/* U16_MAX is much more than enough for sk local storage + * considering a tcp_sock is ~2k. + */ +#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE \ + min_t(u32, \ + (KMALLOC_MAX_SIZE - MAX_BPF_STACK - \ + sizeof(struct bpf_local_storage_elem)), \ + (U16_MAX - sizeof(struct bpf_local_storage_elem))) + +#define SELEM(_SDATA) \ + container_of((_SDATA), struct bpf_local_storage_elem, sdata) +#define SDATA(_SELEM) (&(_SELEM)->sdata) + +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_cache { + spinlock_t idx_lock; + u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; +}; + +#define DEFINE_BPF_STORAGE_CACHE(name) \ +static struct bpf_local_storage_cache name = { \ + .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ +} + +u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); +void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx); + +/* Helper functions for bpf_local_storage */ +int bpf_local_storage_map_alloc_check(union bpf_attr *attr); + +struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); + +struct bpf_local_storage_data * +bpf_local_storage_lookup(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool cacheit_lockit); + +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap); + +int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type); + +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem); + +bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_omem); + +void bpf_selem_unlink(struct bpf_local_storage_elem *selem); + +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem); + +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); + +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, + bool charge_mem); + +int +bpf_local_storage_alloc(void *owner, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem); + +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + void *value, u64 map_flags); + +#endif /* _BPF_LOCAL_STORAGE_H */ diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index af74712af585..aaacb6aafc87 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -17,9 +17,28 @@ #include <linux/lsm_hook_defs.h> #undef LSM_HOOK +struct bpf_storage_blob { + struct bpf_local_storage __rcu *storage; +}; + +extern struct lsm_blob_sizes bpf_lsm_blob_sizes; + int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog); +static inline struct bpf_storage_blob *bpf_inode( + const struct inode *inode) +{ + if (unlikely(!inode->i_security)) + return NULL; + + return inode->i_security + bpf_lsm_blob_sizes.lbs_inode; +} + +extern const struct bpf_func_proto bpf_inode_storage_get_proto; +extern const struct bpf_func_proto bpf_inode_storage_delete_proto; +void bpf_inode_storage_free(struct inode *inode); + #else /* !CONFIG_BPF_LSM */ static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, @@ -28,6 +47,16 @@ static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return -EOPNOTSUPP; } +static inline struct bpf_storage_blob *bpf_inode( + const struct inode *inode) +{ + return NULL; +} + +static inline void bpf_inode_storage_free(struct inode *inode) +{ +} + #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a52a5688418e..2e6f568377f1 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -107,6 +107,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) #endif +#ifdef CONFIG_BPF_LSM +BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) diff --git a/include/linux/btf.h b/include/linux/btf.h index 8b81fbb4497c..a9af5e7a7ece 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -64,8 +64,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, u32 id, u32 *res_id); const struct btf_type * btf_resolve_size(const struct btf *btf, const struct btf_type *type, - u32 *type_size, const struct btf_type **elem_type, - u32 *total_nelems); + u32 *type_size); #define for_each_member(i, struct_type, member) \ for (i = 0, member = btf_type_member(struct_type); \ diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 4867d549e3c1..210b086188a3 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,11 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +struct btf_id_set { + u32 cnt; + u32 ids[]; +}; + #ifdef CONFIG_DEBUG_INFO_BTF #include <linux/compiler.h> /* for __PASTE */ @@ -62,7 +67,7 @@ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ "." #scope " " #name "; \n" \ #name ":; \n" \ -".popsection; \n"); \ +".popsection; \n"); #define BTF_ID_LIST(name) \ __BTF_ID_LIST(name, local) \ @@ -88,12 +93,56 @@ asm( \ ".zero 4 \n" \ ".popsection; \n"); +/* + * The BTF_SET_START/END macros pair defines sorted list of + * BTF IDs plus its members count, with following layout: + * + * BTF_SET_START(list) + * BTF_ID(type1, name1) + * BTF_ID(type2, name2) + * BTF_SET_END(list) + * + * __BTF_ID__set__list: + * .zero 4 + * list: + * __BTF_ID__type1__name1__3: + * .zero 4 + * __BTF_ID__type2__name2__4: + * .zero 4 + * + */ +#define __BTF_SET_START(name, scope) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +"." #scope " __BTF_ID__set__" #name "; \n" \ +"__BTF_ID__set__" #name ":; \n" \ +".zero 4 \n" \ +".popsection; \n"); + +#define BTF_SET_START(name) \ +__BTF_ID_LIST(name, local) \ +__BTF_SET_START(name, local) + +#define BTF_SET_START_GLOBAL(name) \ +__BTF_ID_LIST(name, globl) \ +__BTF_SET_START(name, globl) + +#define BTF_SET_END(name) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".size __BTF_ID__set__" #name ", .-" #name " \n" \ +".popsection; \n"); \ +extern struct btf_id_set name; + #else #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED #define BTF_ID_LIST_GLOBAL(name) u32 name[1]; +#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index ac0c7299d5b8..dd74503f7e5e 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -117,11 +117,18 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv, return true; } +static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter) +{ + iter->bi_bvec_done = 0; + iter->bi_idx++; +} + #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ - bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len)) + (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter), \ + (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter))) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index fcd84e8d88f4..999636d53cf2 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -11,14 +11,14 @@ #define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL #define DEFINE_CEPH_FEATURE(bit, incarnation, name) \ - static const uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ - static const uint64_t CEPH_FEATUREMASK_##name = \ + static const uint64_t __maybe_unused CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t __maybe_unused CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* this bit is ignored but still advertised by release *when* */ #define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \ - static const uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ - static const uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ + static const uint64_t __maybe_unused DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t __maybe_unused DEPRECATED_CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* diff --git a/include/linux/compat.h b/include/linux/compat.h index d38c4d7e83bd..b354ce58966e 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -429,11 +429,11 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; - /* fall through */ + fallthrough; case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; - /* fall through */ + fallthrough; case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; - /* fall through */ + fallthrough; case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; } return copy_to_user(compat, &v, size) ? -EFAULT : 0; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 8f141d4c859c..a911e5d06845 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -956,8 +956,8 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, case CPUFREQ_RELATION_C: return cpufreq_table_find_index_c(policy, target_freq); default: - pr_err("%s: Invalid relation: %d\n", __func__, relation); - return -EINVAL; + WARN_ON_ONCE(1); + return 0; } } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index a2710e654b64..3215023d4852 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -132,6 +132,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, + CPUHP_AP_CLINT_TIMER_STARTING, CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, CPUHP_AP_KVM_STARTING, diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b65909ae4e20..75895e6363b8 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -75,12 +75,13 @@ struct cpuidle_state { }; /* Idle State Flags */ -#define CPUIDLE_FLAG_NONE (0x00) -#define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ -#define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ -#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ -#define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ -#define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ +#define CPUIDLE_FLAG_NONE (0x00) +#define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ +#define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ +#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ +#define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ +#define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ +#define CPUIDLE_FLAG_TLB_FLUSHED BIT(5) /* idle-state flushes TLBs */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 5a3ce2a24794..6e87225600ae 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -73,9 +73,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, } u64 dma_direct_get_required_mask(struct device *dev); -gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, - u64 *phys_mask); -bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 016b96b384bd..52635e91143b 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -522,8 +522,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size); -void *dma_alloc_from_pool(struct device *dev, size_t size, - struct page **ret_page, gfp_t flags); +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t flags, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)); bool dma_free_from_pool(struct device *dev, void *start, size_t size); int diff --git a/include/linux/filter.h b/include/linux/filter.h index 0a355b005bf4..05b4052715b9 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1200,7 +1200,7 @@ static inline u16 bpf_anc_helper(const struct sock_filter *ftest) BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } - /* Fallthrough. */ + fallthrough; default: return ftest->code; } @@ -1236,13 +1236,17 @@ struct bpf_sock_addr_kern { struct bpf_sock_ops_kern { struct sock *sk; - u32 op; union { u32 args[4]; u32 reply; u32 replylong[4]; }; - u32 is_fullsock; + struct sk_buff *syn_skb; + struct sk_buff *skb; + void *skb_data_end; + u8 op; + u8 is_fullsock; + u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that diff --git a/include/linux/fs.h b/include/linux/fs.h index e019ea2f1347..7519ae003a08 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2132,6 +2132,10 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_DONTCACHE Evict inode as soon as it is not used anymore. * + * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. + * Used to detect that mark_inode_dirty() should not move + * inode between dirty lists. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2149,12 +2153,11 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define __I_DIRTY_TIME_EXPIRED 12 -#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) +#define I_SYNC_QUEUED (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/hid.h b/include/linux/hid.h index 875f71132b14..c7044a14200e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -959,34 +959,49 @@ static inline void hid_device_io_stop(struct hid_device *hid) { * @max: maximal valid usage->code to consider later (out parameter) * @type: input event type (EV_KEY, EV_REL, ...) * @c: code which corresponds to this usage and type + * + * The value pointed to by @bit will be set to NULL if either @type is + * an unhandled event type, or if @c is out of range for @type. This + * can be used as an error condition. */ static inline void hid_map_usage(struct hid_input *hidinput, struct hid_usage *usage, unsigned long **bit, int *max, - __u8 type, __u16 c) + __u8 type, unsigned int c) { struct input_dev *input = hidinput->input; - - usage->type = type; - usage->code = c; + unsigned long *bmap = NULL; + unsigned int limit = 0; switch (type) { case EV_ABS: - *bit = input->absbit; - *max = ABS_MAX; + bmap = input->absbit; + limit = ABS_MAX; break; case EV_REL: - *bit = input->relbit; - *max = REL_MAX; + bmap = input->relbit; + limit = REL_MAX; break; case EV_KEY: - *bit = input->keybit; - *max = KEY_MAX; + bmap = input->keybit; + limit = KEY_MAX; break; case EV_LED: - *bit = input->ledbit; - *max = LED_MAX; + bmap = input->ledbit; + limit = LED_MAX; break; } + + if (unlikely(c > limit || !bmap)) { + pr_warn_ratelimited("%s: Invalid code %d type %d\n", + input->name, c, type); + *bit = NULL; + return; + } + + usage->type = type; + usage->code = c; + *max = limit; + *bit = bmap; } /** @@ -1000,7 +1015,8 @@ static inline void hid_map_usage_clear(struct hid_input *hidinput, __u8 type, __u16 c) { hid_map_usage(hidinput, usage, bit, max, type, c); - clear_bit(c, *bit); + if (*bit) + clear_bit(usage->code, *bit); } /** diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 5bda8cf457b6..2a7660843444 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -27,9 +27,18 @@ struct tun_xdp_hdr { #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -bool tun_is_xdp_frame(void *ptr); -void *tun_xdp_to_ptr(void *ptr); -void *tun_ptr_to_xdp(void *ptr); +static inline bool tun_is_xdp_frame(void *ptr) +{ + return (unsigned long)ptr & TUN_XDP_FLAG; +} +static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp) +{ + return (void *)((unsigned long)xdp | TUN_XDP_FLAG); +} +static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr) +{ + return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG); +} void tun_ptr_free(void *ptr); #else #include <linux/err.h> @@ -48,11 +57,11 @@ static inline bool tun_is_xdp_frame(void *ptr) { return false; } -static inline void *tun_xdp_to_ptr(void *ptr) +static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp) { return NULL; } -static inline void *tun_ptr_to_xdp(void *ptr) +static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr) { return NULL; } diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 0ef2d800fda7..84abb30a3fbb 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -75,6 +75,8 @@ static inline size_t inet_diag_msg_attrs_size(void) #ifdef CONFIG_SOCK_CGROUP_DATA + nla_total_size_64bit(sizeof(u64)) /* INET_DIAG_CGROUP_ID */ #endif + + nla_total_size(sizeof(struct inet_diag_sockopt)) + /* INET_DIAG_SOCKOPT */ ; } int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a44789d027cc..dda61d150a13 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -177,17 +177,6 @@ static inline int inet6_sdif(const struct sk_buff *skb) return 0; } -/* can not be used in TCP layer after tcp_v6_fill_cb */ -static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) -{ -#if defined(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) - return true; -#endif - return false; -} - struct tcp6_request_sock { struct tcp_request_sock tcp6rsk_tcp; }; @@ -345,17 +334,6 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return (struct raw6_sock *)sk; } -static inline void inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - int ancestor_size = sizeof(struct inet_sock); - - if (sk_from->sk_family == PF_INET6) - ancestor_size += sizeof(struct ipv6_pinfo); - - __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); -} - #define __ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_only_sock(sk) (__ipv6_only_sock(sk)) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index bd5c55755447..3ed4e8771b64 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -49,17 +49,18 @@ struct irqtrace_events { DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); - extern void trace_hardirqs_on_prepare(void); - extern void trace_hardirqs_off_finish(void); - extern void trace_hardirqs_on(void); - extern void trace_hardirqs_off(void); -# define lockdep_hardirq_context() (this_cpu_read(hardirq_context)) +extern void trace_hardirqs_on_prepare(void); +extern void trace_hardirqs_off_finish(void); +extern void trace_hardirqs_on(void); +extern void trace_hardirqs_off(void); + +# define lockdep_hardirq_context() (raw_cpu_read(hardirq_context)) # define lockdep_softirq_context(p) ((p)->softirq_context) # define lockdep_hardirqs_enabled() (this_cpu_read(hardirqs_enabled)) # define lockdep_softirqs_enabled(p) ((p)->softirqs_enabled) # define lockdep_hardirq_enter() \ do { \ - if (this_cpu_inc_return(hardirq_context) == 1) \ + if (__this_cpu_inc_return(hardirq_context) == 1)\ current->hardirq_threaded = 0; \ } while (0) # define lockdep_hardirq_threaded() \ @@ -68,7 +69,7 @@ do { \ } while (0) # define lockdep_hardirq_exit() \ do { \ - this_cpu_dec(hardirq_context); \ + __this_cpu_dec(hardirq_context); \ } while (0) # define lockdep_softirq_enter() \ do { \ @@ -120,17 +121,17 @@ do { \ #else # define trace_hardirqs_on_prepare() do { } while (0) # define trace_hardirqs_off_finish() do { } while (0) -# define trace_hardirqs_on() do { } while (0) -# define trace_hardirqs_off() do { } while (0) -# define lockdep_hardirq_context() 0 -# define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled() 0 -# define lockdep_softirqs_enabled(p) 0 -# define lockdep_hardirq_enter() do { } while (0) -# define lockdep_hardirq_threaded() do { } while (0) -# define lockdep_hardirq_exit() do { } while (0) -# define lockdep_softirq_enter() do { } while (0) -# define lockdep_softirq_exit() do { } while (0) +# define trace_hardirqs_on() do { } while (0) +# define trace_hardirqs_off() do { } while (0) +# define lockdep_hardirq_context() 0 +# define lockdep_softirq_context(p) 0 +# define lockdep_hardirqs_enabled() 0 +# define lockdep_softirqs_enabled(p) 0 +# define lockdep_hardirq_enter() do { } while (0) +# define lockdep_hardirq_threaded() do { } while (0) +# define lockdep_hardirq_exit() do { } while (0) +# define lockdep_softirq_enter() do { } while (0) +# define lockdep_softirq_exit() do { } while (0) # define lockdep_hrtimer_enter(__hrtimer) false # define lockdep_hrtimer_exit(__context) do { } while (0) # define lockdep_posixtimer_enter() do { } while (0) @@ -181,26 +182,33 @@ do { \ * if !TRACE_IRQFLAGS. */ #ifdef CONFIG_TRACE_IRQFLAGS -#define local_irq_enable() \ - do { trace_hardirqs_on(); raw_local_irq_enable(); } while (0) -#define local_irq_disable() \ - do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0) + +#define local_irq_enable() \ + do { \ + trace_hardirqs_on(); \ + raw_local_irq_enable(); \ + } while (0) + +#define local_irq_disable() \ + do { \ + bool was_disabled = raw_irqs_disabled();\ + raw_local_irq_disable(); \ + if (!was_disabled) \ + trace_hardirqs_off(); \ + } while (0) + #define local_irq_save(flags) \ do { \ raw_local_irq_save(flags); \ - trace_hardirqs_off(); \ + if (!raw_irqs_disabled_flags(flags)) \ + trace_hardirqs_off(); \ } while (0) - #define local_irq_restore(flags) \ do { \ - if (raw_irqs_disabled_flags(flags)) { \ - raw_local_irq_restore(flags); \ - trace_hardirqs_off(); \ - } else { \ + if (!raw_irqs_disabled_flags(flags)) \ trace_hardirqs_on(); \ - raw_local_irq_restore(flags); \ - } \ + raw_local_irq_restore(flags); \ } while (0) #define safe_halt() \ @@ -214,10 +222,7 @@ do { \ #define local_irq_enable() do { raw_local_irq_enable(); } while (0) #define local_irq_disable() do { raw_local_irq_disable(); } while (0) -#define local_irq_save(flags) \ - do { \ - raw_local_irq_save(flags); \ - } while (0) +#define local_irq_save(flags) do { raw_local_irq_save(flags); } while (0) #define local_irq_restore(flags) do { raw_local_irq_restore(flags); } while (0) #define safe_halt() do { raw_safe_halt(); } while (0) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 4aaa29772bb0..08f904943ab2 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1381,7 +1381,7 @@ extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); -extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush (journal_t *); extern void jbd2_journal_lock_updates (journal_t *); diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 19ddd43aee68..cfb62e9f37be 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -86,17 +86,17 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) } /* Last block: affect all 32 bits of (c) */ switch (length) { - case 12: c += (u32)k[11]<<24; /* fall through */ - case 11: c += (u32)k[10]<<16; /* fall through */ - case 10: c += (u32)k[9]<<8; /* fall through */ - case 9: c += k[8]; /* fall through */ - case 8: b += (u32)k[7]<<24; /* fall through */ - case 7: b += (u32)k[6]<<16; /* fall through */ - case 6: b += (u32)k[5]<<8; /* fall through */ - case 5: b += k[4]; /* fall through */ - case 4: a += (u32)k[3]<<24; /* fall through */ - case 3: a += (u32)k[2]<<16; /* fall through */ - case 2: a += (u32)k[1]<<8; /* fall through */ + case 12: c += (u32)k[11]<<24; fallthrough; + case 11: c += (u32)k[10]<<16; fallthrough; + case 10: c += (u32)k[9]<<8; fallthrough; + case 9: c += k[8]; fallthrough; + case 8: b += (u32)k[7]<<24; fallthrough; + case 7: b += (u32)k[6]<<16; fallthrough; + case 6: b += (u32)k[5]<<8; fallthrough; + case 5: b += k[4]; fallthrough; + case 4: a += (u32)k[3]<<24; fallthrough; + case 3: a += (u32)k[2]<<16; fallthrough; + case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ @@ -132,8 +132,8 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) /* Handle the last 3 u32's */ switch (length) { - case 3: c += k[2]; /* fall through */ - case 2: b += k[1]; /* fall through */ + case 3: c += k[2]; fallthrough; + case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 500def620d8f..c25b8e41c0ea 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -186,7 +186,7 @@ * lower_32_bits - return bits 0-31 of a number * @n: the number we're accessing */ -#define lower_32_bits(n) ((u32)(n)) +#define lower_32_bits(n) ((u32)((n) & 0xffffffff)) struct completion; struct pt_regs; diff --git a/include/linux/ksm.h b/include/linux/ksm.h index e48b1e453ff5..161e8164abcf 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -53,8 +53,6 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); void ksm_migrate_page(struct page *newpage, struct page *oldpage); -bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, unsigned long address); #else /* !CONFIG_KSM */ @@ -88,11 +86,6 @@ static inline void rmap_walk_ksm(struct page *page, static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage) { } -static inline bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, unsigned long address) -{ - return false; -} #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 77ccf040a128..5f550eb27f81 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -421,6 +421,7 @@ enum { ATA_HORKAGE_NO_DMA_LOG = (1 << 23), /* don't use DMA for log read */ ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ + ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 62a382d1845b..6a584b3e5c74 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -535,19 +535,27 @@ do { \ DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); +/* + * The below lockdep_assert_*() macros use raw_cpu_read() to access the above + * per-cpu variables. This is required because this_cpu_read() will potentially + * call into preempt/irq-disable and that obviously isn't right. This is also + * correct because when IRQs are enabled, it doesn't matter if we accidentally + * read the value from our previous CPU. + */ + #define lockdep_assert_irqs_enabled() \ do { \ - WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_irqs_disabled() \ do { \ - WARN_ON_ONCE(debug_locks && this_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(debug_locks && raw_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_in_irq() \ do { \ - WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirq_context)); \ + WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirq_context)); \ } while (0) #define lockdep_assert_preemption_enabled() \ @@ -555,7 +563,7 @@ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ debug_locks && \ (preempt_count() != 0 || \ - !this_cpu_read(hardirqs_enabled))); \ + !raw_cpu_read(hardirqs_enabled))); \ } while (0) #define lockdep_assert_preemption_disabled() \ @@ -563,7 +571,7 @@ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ debug_locks && \ (preempt_count() == 0 && \ - this_cpu_read(hardirqs_enabled))); \ + raw_cpu_read(hardirqs_enabled))); \ } while (0) #else diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 898cbf00332a..3a88b699b758 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -358,6 +358,12 @@ static inline int mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, return mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); } +static inline int mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, + u16 regnum, u16 val) +{ + return mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), val); +} + int mdiobus_register_device(struct mdio_device *mdiodev); int mdiobus_unregister_device(struct mdio_device *mdiodev); bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); diff --git a/drivers/net/phy/mdio-i2c.h b/include/linux/mdio/mdio-i2c.h index b1d27f7cd23f..b1d27f7cd23f 100644 --- a/drivers/net/phy/mdio-i2c.h +++ b/include/linux/mdio/mdio-i2c.h diff --git a/drivers/net/phy/mdio-xgene.h b/include/linux/mdio/mdio-xgene.h index 8af93ada8b64..8af93ada8b64 100644 --- a/drivers/net/phy/mdio-xgene.h +++ b/include/linux/mdio/mdio-xgene.h diff --git a/include/linux/mm.h b/include/linux/mm.h index 1983e08f5906..ca6e6a81576b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -157,11 +157,14 @@ static inline void __mm_zero_struct_page(struct page *page) switch (sizeof(struct page)) { case 80: - _pp[9] = 0; /* fallthrough */ + _pp[9] = 0; + fallthrough; case 72: - _pp[8] = 0; /* fallthrough */ + _pp[8] = 0; + fallthrough; case 64: - _pp[7] = 0; /* fallthrough */ + _pp[7] = 0; + fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; @@ -321,6 +324,8 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ +#elif defined(CONFIG_PPC) +# define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index c51a84132d7c..03dee12d2b61 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -3,10 +3,15 @@ #define _LINUX_MMU_CONTEXT_H #include <asm/mmu_context.h> +#include <asm/mmu.h> /* Architectures that care about IRQ state in switch_mm can override this. */ #ifndef switch_mm_irqs_off # define switch_mm_irqs_off switch_mm #endif +#ifndef leave_mm +static inline void leave_mm(int cpu) { } +#endif + #endif diff --git a/include/linux/net.h b/include/linux/net.h index d48ff1180879..7657c6432a69 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -41,6 +41,8 @@ struct net; #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 +#define PROTO_CMSG_DATA_ONLY 0x0001 + #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types @@ -135,6 +137,7 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, struct proto_ops { int family; + unsigned int flags; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0e303f6603f..157e0242e9ee 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -70,6 +70,7 @@ struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; +void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -354,7 +355,7 @@ enum { NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ - NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ + NAPI_STATE_LISTED, /* NAPI added to system lists */ NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */ }; @@ -364,7 +365,7 @@ enum { NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), - NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED), + NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), }; @@ -489,20 +490,6 @@ static inline bool napi_complete(struct napi_struct *n) } /** - * napi_hash_del - remove a NAPI from global table - * @napi: NAPI context - * - * Warning: caller must observe RCU grace period - * before freeing memory containing @napi, if - * this function returns true. - * Note: core networking stack automatically calls it - * from netif_napi_del(). - * Drivers might want to call this helper to combine all - * the needed RCU grace periods into a single one. - */ -bool napi_hash_del(struct napi_struct *napi); - -/** * napi_disable - prevent NAPI from scheduling * @n: NAPI context * @@ -618,7 +605,7 @@ struct netdev_queue { /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; #ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; + struct xsk_buff_pool *pool; #endif /* * write-mostly part @@ -640,10 +627,14 @@ struct netdev_queue { extern int sysctl_fb_tunnels_only_for_init_net; extern int sysctl_devconf_inherit_init_net; +/* + * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns + * == 1 : For initns only + * == 2 : For none. + */ static inline bool net_has_fallback_tunnels(const struct net *net) { - return net == &init_net || - !IS_ENABLED(CONFIG_SYSCTL) || + return (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1) || !sysctl_fb_tunnels_only_for_init_net; } @@ -751,7 +742,7 @@ struct netdev_rx_queue { struct net_device *dev; struct xdp_rxq_info xdp_rxq; #ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; + struct xsk_buff_pool *pool; #endif } ____cacheline_aligned_in_smp; @@ -879,7 +870,7 @@ enum bpf_netdev_command { /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, - XDP_SETUP_XSK_UMEM, + XDP_SETUP_XSK_POOL, }; struct bpf_prog_offload_ops; @@ -913,9 +904,9 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; - /* XDP_SETUP_XSK_UMEM */ + /* XDP_SETUP_XSK_POOL */ struct { - struct xdp_umem *umem; + struct xsk_buff_pool *pool; u16 queue_id; } xsk; }; @@ -2193,6 +2184,22 @@ int netdev_get_num_tc(struct net_device *dev) return dev->num_tc; } +static inline void net_prefetch(void *p) +{ + prefetch(p); +#if L1_CACHE_BYTES < 128 + prefetch((u8 *)p + L1_CACHE_BYTES); +#endif +} + +static inline void net_prefetchw(void *p) +{ + prefetchw(p); +#if L1_CACHE_BYTES < 128 + prefetchw((u8 *)p + L1_CACHE_BYTES); +#endif +} + void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev); int netdev_bind_sb_channel_queue(struct net_device *dev, @@ -2348,12 +2355,26 @@ static inline void netif_tx_napi_add(struct net_device *dev, } /** + * __netif_napi_del - remove a NAPI context + * @napi: NAPI context + * + * Warning: caller must observe RCU grace period before freeing memory + * containing @napi. Drivers might want to call this helper to combine + * all the needed RCU grace periods into a single one. + */ +void __netif_napi_del(struct napi_struct *napi); + +/** * netif_napi_del - remove a NAPI context * @napi: NAPI context * * netif_napi_del() removes a NAPI context from the network device NAPI list */ -void netif_napi_del(struct napi_struct *napi); +static inline void netif_napi_del(struct napi_struct *napi) +{ + __netif_napi_del(napi); + synchronize_net(); +} struct napi_gro_cb { /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ @@ -2777,7 +2798,6 @@ static inline void unregister_netdevice(struct net_device *dev) int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); void netdev_freemem(struct net_device *dev); -void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 1db83c931d9c..0c7d8d1e945d 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -8,9 +8,9 @@ struct ip_conntrack_stat { unsigned int found; unsigned int invalid; - unsigned int ignore; unsigned int insert; unsigned int insert_failed; + unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index 9a33f171aa82..625f491b95de 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -9,6 +9,8 @@ struct ip_ct_sctp { enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; + u8 last_dir; + u8 flags; }; #endif /* _NF_CONNTRACK_SCTP_H */ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 851425c3178f..89016d08f6a2 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -43,8 +43,7 @@ int nfnetlink_has_listeners(struct net *net, unsigned int group); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); -int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, - int flags); +int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid); static inline u16 nfnl_msg_type(u8 subsys, u8 msg_type) { diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index aac42c28fe62..9b67394471e1 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -58,7 +58,6 @@ struct nf_ipv6_ops { int (*output)(struct net *, struct sock *, struct sk_buff *)); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); #if IS_MODULE(CONFIG_IPV6) - int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user); int (*br_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, @@ -117,23 +116,6 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, #include <net/netfilter/ipv6/nf_defrag_ipv6.h> -static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, - u32 user) -{ -#if IS_MODULE(CONFIG_IPV6) - const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); - - if (!v6_ops) - return 1; - - return v6_ops->br_defrag(net, skb, user); -#elif IS_BUILTIN(CONFIG_IPV6) - return nf_ct_frag6_gather(net, skb, user); -#else - return 1; -#endif -} - int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, diff --git a/include/linux/of.h b/include/linux/of.h index 5cf7ae0465d1..481ec0467285 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -929,6 +929,11 @@ static inline int of_machine_is_compatible(const char *compat) return 0; } +static inline int of_remove_property(struct device_node *np, struct property *prop) +{ + return 0; +} + static inline bool of_console_check(const struct device_node *dn, const char *name, int index) { return false; diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h new file mode 100644 index 000000000000..a6440d6ebe95 --- /dev/null +++ b/include/linux/pcs-lynx.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2020 NXP + * Lynx PCS helpers + */ + +#ifndef __LINUX_PCS_LYNX_H +#define __LINUX_PCS_LYNX_H + +#include <linux/mdio.h> +#include <linux/phylink.h> + +struct lynx_pcs { + struct phylink_pcs pcs; + struct mdio_device *mdio; +}; + +struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio); + +void lynx_pcs_destroy(struct lynx_pcs *pcs); + +#endif /* __LINUX_PCS_LYNX_H */ diff --git a/include/linux/mdio-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 9a841aa5982d..351c1c9aedc5 100644 --- a/include/linux/mdio-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -4,8 +4,8 @@ * Synopsys DesignWare XPCS helpers */ -#ifndef __LINUX_MDIO_XPCS_H -#define __LINUX_MDIO_XPCS_H +#ifndef __LINUX_PCS_XPCS_H +#define __LINUX_PCS_XPCS_H #include <linux/phy.h> #include <linux/phylink.h> @@ -29,7 +29,7 @@ struct mdio_xpcs_ops { int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); }; -#if IS_ENABLED(CONFIG_MDIO_XPCS) +#if IS_ENABLED(CONFIG_PCS_XPCS) struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); #else static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) @@ -38,4 +38,4 @@ static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) } #endif -#endif /* __LINUX_MDIO_XPCS_H */ +#endif /* __LINUX_PCS_XPCS_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a124c21e3204..e8cbc2e795d5 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -117,7 +117,9 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ +#ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) +#endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE diff --git a/include/linux/phylink.h b/include/linux/phylink.h index a8e876317e25..d81a714cfbbd 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -402,7 +402,8 @@ void pcs_get_state(struct phylink_pcs *pcs, * For most 10GBASE-R, there is no advertisement. */ int pcs_config(struct phylink_pcs *pcs, unsigned int mode, - phy_interface_t interface, const unsigned long *advertising); + phy_interface_t interface, const unsigned long *advertising, + bool permit_pause_to_mac); /** * pcs_an_restart() - restart 802.3z BaseX autonegotiation @@ -489,4 +490,7 @@ void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs); void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs, struct phylink_link_state *state); + +void phylink_decode_usxgmii_word(struct phylink_link_state *state, + uint16_t lpa); #endif diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index dd00fa41f7e7..8437307cca8c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -36,7 +36,6 @@ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ #define OFF_PTP_SEQUENCE_ID 30 -#define OFF_PTP_CONTROL 32 /* PTPv1 only */ /* Below defines should actually be removed at some point in time. */ #define IP6_HLEN 40 @@ -44,6 +43,30 @@ #define OFF_IHL 14 #define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2) +struct clock_identity { + u8 id[8]; +} __packed; + +struct port_identity { + struct clock_identity clock_identity; + __be16 port_number; +} __packed; + +struct ptp_header { + u8 tsmt; /* transportSpecific | messageType */ + u8 ver; /* reserved | versionPTP */ + __be16 message_length; + u8 domain_number; + u8 reserved1; + u8 flag_field[2]; + __be64 correction; + __be32 reserved2; + struct port_identity source_port_identity; + __be16 sequence_id; + u8 control; + u8 log_message_interval; +} __packed; + #if defined(CONFIG_NET_PTP_CLASSIFY) /** * ptp_classify_raw - classify a PTP packet @@ -57,6 +80,46 @@ */ unsigned int ptp_classify_raw(const struct sk_buff *skb); +/** + * ptp_parse_header - Get pointer to the PTP v2 header + * @skb: packet buffer + * @type: type of the packet (see ptp_classify_raw()) + * + * This function takes care of the VLAN, UDP, IPv4 and IPv6 headers. The length + * is checked. + * + * Note, internally skb_mac_header() is used. Make sure that the @skb is + * initialized accordingly. + * + * Return: Pointer to the ptp v2 header or NULL if not found + */ +struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type); + +/** + * ptp_get_msgtype - Extract ptp message type from given header + * @hdr: ptp header + * @type: type of the packet (see ptp_classify_raw()) + * + * This function returns the message type for a given ptp header. It takes care + * of the different ptp header versions (v1 or v2). + * + * Return: The message type + */ +static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, + unsigned int type) +{ + u8 msgtype; + + if (unlikely(type & PTP_CLASS_V1)) { + /* msg type is located at the control field for ptp v1 */ + msgtype = hdr->control; + } else { + msgtype = hdr->tsmt & 0x0f; + } + + return msgtype; +} + void __init ptp_classifier_init(void); #else static inline void ptp_classifier_init(void) @@ -66,5 +129,10 @@ static inline unsigned int ptp_classify_raw(struct sk_buff *skb) { return PTP_CLASS_NONE; } +static inline struct ptp_header *ptp_parse_header(struct sk_buff *skb, + unsigned int type) +{ + return NULL; +} #endif #endif /* _PTP_CLASSIFY_H_ */ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index cd6a5c7e56eb..56fa55841d39 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -21,6 +21,7 @@ #include <linux/qed/common_hsi.h> #include <linux/qed/qed_chain.h> #include <linux/io-64-nonatomic-lo-hi.h> +#include <net/devlink.h> enum dcbx_protocol_type { DCBX_PROTOCOL_ISCSI, @@ -779,6 +780,11 @@ enum qed_nvm_flash_cmd { QED_NVM_FLASH_CMD_NVM_MAX, }; +struct qed_devlink { + struct qed_dev *cdev; + struct devlink_health_reporter *fw_reporter; +}; + struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); @@ -844,10 +850,9 @@ struct qed_common_ops { struct qed_dev* (*probe)(struct pci_dev *dev, struct qed_probe_params *params); - void (*remove)(struct qed_dev *cdev); + void (*remove)(struct qed_dev *cdev); - int (*set_power_state)(struct qed_dev *cdev, - pci_power_t state); + int (*set_power_state)(struct qed_dev *cdev, pci_power_t state); void (*set_name) (struct qed_dev *cdev, char name[]); @@ -855,50 +860,51 @@ struct qed_common_ops { * PF params required for the call before slowpath_start is * documented within the qed_pf_params structure definition. */ - void (*update_pf_params)(struct qed_dev *cdev, - struct qed_pf_params *params); - int (*slowpath_start)(struct qed_dev *cdev, - struct qed_slowpath_params *params); + void (*update_pf_params)(struct qed_dev *cdev, + struct qed_pf_params *params); - int (*slowpath_stop)(struct qed_dev *cdev); + int (*slowpath_start)(struct qed_dev *cdev, + struct qed_slowpath_params *params); + + int (*slowpath_stop)(struct qed_dev *cdev); /* Requests to use `cnt' interrupts for fastpath. * upon success, returns number of interrupts allocated for fastpath. */ - int (*set_fp_int)(struct qed_dev *cdev, - u16 cnt); + int (*set_fp_int)(struct qed_dev *cdev, u16 cnt); /* Fills `info' with pointers required for utilizing interrupts */ - int (*get_fp_int)(struct qed_dev *cdev, - struct qed_int_info *info); - - u32 (*sb_init)(struct qed_dev *cdev, - struct qed_sb_info *sb_info, - void *sb_virt_addr, - dma_addr_t sb_phy_addr, - u16 sb_id, - enum qed_sb_type type); - - u32 (*sb_release)(struct qed_dev *cdev, - struct qed_sb_info *sb_info, - u16 sb_id, - enum qed_sb_type type); - - void (*simd_handler_config)(struct qed_dev *cdev, - void *token, - int index, - void (*handler)(void *)); - - void (*simd_handler_clean)(struct qed_dev *cdev, - int index); - int (*dbg_grc)(struct qed_dev *cdev, - void *buffer, u32 *num_dumped_bytes); + int (*get_fp_int)(struct qed_dev *cdev, struct qed_int_info *info); + + u32 (*sb_init)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + void *sb_virt_addr, + dma_addr_t sb_phy_addr, + u16 sb_id, + enum qed_sb_type type); + + u32 (*sb_release)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + u16 sb_id, + enum qed_sb_type type); + + void (*simd_handler_config)(struct qed_dev *cdev, + void *token, + int index, + void (*handler)(void *)); + + void (*simd_handler_clean)(struct qed_dev *cdev, int index); + + int (*dbg_grc)(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes); int (*dbg_grc_size)(struct qed_dev *cdev); - int (*dbg_all_data) (struct qed_dev *cdev, void *buffer); + int (*dbg_all_data)(struct qed_dev *cdev, void *buffer); - int (*dbg_all_data_size) (struct qed_dev *cdev); + int (*dbg_all_data_size)(struct qed_dev *cdev); + + int (*report_fatal_error)(struct devlink *devlink, + enum qed_hw_err_type err_type); /** * @brief can_link_change - can the instance change the link or not @@ -1137,6 +1143,10 @@ struct qed_common_ops { * */ int (*set_grc_config)(struct qed_dev *cdev, u32 cfg_id, u32 val); + + struct devlink* (*devlink_register)(struct qed_dev *cdev); + + void (*devlink_unregister)(struct devlink *devlink); }; #define MASK_FIELD(_name, _value) \ diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index d9015aac78c6..aaaac8ac927c 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -82,7 +82,14 @@ static inline void rcu_read_unlock_trace(void) void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); void synchronize_rcu_tasks_trace(void); void rcu_barrier_tasks_trace(void); - +#else +/* + * The BPF JIT forms these addresses even when it doesn't call these + * functions, so provide definitions that result in runtime errors. + */ +static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) { BUG(); } +static inline void rcu_read_lock_trace(void) { BUG(); } +static inline void rcu_read_unlock_trace(void) { BUG(); } #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ #endif /* __LINUX_RCUPDATE_TRACE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 93ecd930efd3..afe01e232935 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1666,7 +1666,7 @@ extern struct task_struct *idle_task(int cpu); * * Return: 1 if @p is an idle task. 0 otherwise. */ -static inline bool is_idle_task(const struct task_struct *p) +static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 917d88edb7b9..a8ec3b6093fc 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,6 +36,9 @@ struct user_struct { defined(CONFIG_NET) || defined(CONFIG_IO_URING) atomic_long_t locked_vm; #endif +#ifdef CONFIG_WATCH_QUEUE + atomic_t nr_watches; /* The number of watches this user currently has */ +#endif /* Miscellaneous per-user rate limit */ struct ratelimit_state ratelimit; diff --git a/include/linux/signal.h b/include/linux/signal.h index 6bb1a3f0258c..7bbc0e9cf084 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -137,11 +137,11 @@ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ b3 = b->sig[3]; b2 = b->sig[2]; \ r->sig[3] = op(a3, b3); \ r->sig[2] = op(a2, b2); \ - /* fall through */ \ + fallthrough; \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ - /* fall through */ \ + fallthrough; \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ @@ -171,9 +171,9 @@ static inline void name(sigset_t *set) \ switch (_NSIG_WORDS) { \ case 4: set->sig[3] = op(set->sig[3]); \ set->sig[2] = op(set->sig[2]); \ - /* fall through */ \ + fallthrough; \ case 2: set->sig[1] = op(set->sig[1]); \ - /* fall through */ \ + fallthrough; \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ @@ -194,7 +194,7 @@ static inline void sigemptyset(sigset_t *set) memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; - /* fall through */ + fallthrough; case 1: set->sig[0] = 0; break; } @@ -207,7 +207,7 @@ static inline void sigfillset(sigset_t *set) memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; - /* fall through */ + fallthrough; case 1: set->sig[0] = -1; break; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46881d902124..ed9bea924dc3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -71,7 +71,7 @@ * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or - * IPv4|UDP where the Next Header field in the IPv6 + * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with @@ -1056,7 +1056,16 @@ void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); + +#ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); +#else +static inline void consume_skb(struct sk_buff *skb) +{ + return kfree_skb(skb); +} +#endif + void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); extern struct kmem_cache *skbuff_head_cache; @@ -2658,7 +2667,7 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. - * get_rps_cpus() for example only access one 64 bytes aligned block : + * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD @@ -3745,19 +3754,19 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 24: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 16: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 20: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 12: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; } diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 1e9ed840b9fc..3119928fc103 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -340,23 +340,6 @@ static inline void sk_psock_update_proto(struct sock *sk, struct sk_psock *psock, struct proto *ops) { - /* Initialize saved callbacks and original proto only once, since this - * function may be called multiple times for a psock, e.g. when - * psock->progs.msg_parser is updated. - * - * Since we've not installed the new proto, psock is not yet in use and - * we can initialize it without synchronization. - */ - if (!psock->sk_proto) { - struct proto *orig = READ_ONCE(sk->sk_prot); - - psock->saved_unhash = orig->unhash; - psock->saved_close = orig->close; - psock->saved_write_space = sk->sk_write_space; - - psock->sk_proto = orig; - } - /* Pairs with lockless read in sk_clone_lock() */ WRITE_ONCE(sk->sk_prot, ops); } diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 49c5d29cd33c..cf27b080e148 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -220,6 +220,9 @@ struct ti_sci_rm_core_ops { u16 *range_start, u16 *range_num); }; +#define TI_SCI_RESASG_SUBTYPE_IR_OUTPUT 0 +#define TI_SCI_RESASG_SUBTYPE_IA_VINT 0xa +#define TI_SCI_RESASG_SUBTYPE_GLOBAL_EVENT_SEVT 0xd /** * struct ti_sci_rm_irq_ops: IRQ management operations * @set_irq: Set an IRQ route between the requested source @@ -556,6 +559,9 @@ u32 ti_sci_get_num_resources(struct ti_sci_resource *res); struct ti_sci_resource * devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, struct device *dev, u32 dev_id, char *of_prop); +struct ti_sci_resource * +devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, + u32 dev_id, u32 sub_type); #else /* CONFIG_TI_SCI_PROTOCOL */ @@ -609,6 +615,13 @@ devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, { return ERR_PTR(-EINVAL); } + +static inline struct ti_sci_resource * +devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, + u32 dev_id, u32 sub_type); +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_TI_SCI_PROTOCOL */ #endif /* __TISCI_PROTOCOL_H */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 14b62d7df942..2f87377e9af7 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -92,6 +92,8 @@ struct tcp_options_received { smc_ok : 1, /* SMC seen on SYN packet */ snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ + u8 saw_unknown:1, /* Received unknown option */ + unused:7; u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ @@ -132,6 +134,7 @@ struct tcp_request_sock { * FastOpen it's the seq# * after data-in-SYN. */ + u8 syn_tos; }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) @@ -237,14 +240,13 @@ struct tcp_sock { repair : 1, frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; - u8 syn_data:1, /* SYN includes data */ + u8 save_syn:2, /* Save headers of SYN packet */ + syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_fastopen_ch:1, /* Active TFO re-enabling probe */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ - save_syn:1, /* Save headers of SYN packet */ - is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ - syn_smc:1; /* SYN includes SMC */ + is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ @@ -391,6 +393,9 @@ struct tcp_sock { #if IS_ENABLED(CONFIG_MPTCP) bool is_mptcp; #endif +#if IS_ENABLED(CONFIG_SMC) + bool syn_smc; /* SYN includes SMC */ +#endif #ifdef CONFIG_TCP_MD5SIG /* TCP AF-Specific parts; only used by MD5 Signature support so far */ @@ -406,7 +411,7 @@ struct tcp_sock { * socket. Used to retransmit SYNACKs etc. */ struct request_sock __rcu *fastopen_rsk; - u32 *saved_syn; + struct saved_syn *saved_syn; }; enum tsq_enum { @@ -484,6 +489,12 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) tp->saved_syn = NULL; } +static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn) +{ + return saved_syn->mac_hdrlen + saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; +} + struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, const struct sk_buff *orig_skb); diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 2e6ca53b9bbd..18e75974d4e3 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGFAULT, PGMAJFAULT, PGLAZYFREED, PGREFILL, + PGREUSE, PGSTEAL_KSWAPD, PGSTEAL_DIRECT, PGSCAN_KSWAPD, diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h index adcc6a97db61..143568d64b20 100644 --- a/include/math-emu/op-common.h +++ b/include/math-emu/op-common.h @@ -308,7 +308,7 @@ do { \ \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO): \ R##_e = X##_e; \ - /* Fall through */ \ + fallthrough; \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL): \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF): \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO): \ @@ -319,7 +319,7 @@ do { \ \ case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL): \ R##_e = Y##_e; \ - /* Fall through */ \ + fallthrough; \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN): \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN): \ case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN): \ @@ -417,7 +417,7 @@ do { \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF): \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO): \ R##_s = X##_s; \ - /* Fall through */ \ + fallthrough; \ \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF): \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \ @@ -431,7 +431,7 @@ do { \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN): \ case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN): \ R##_s = Y##_s; \ - /* Fall through */ \ + fallthrough; \ \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF): \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO): \ @@ -497,7 +497,7 @@ do { \ \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO): \ FP_SET_EXCEPTION(FP_EX_DIVZERO); \ - /* Fall through */ \ + fallthrough; \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO): \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \ R##_c = FP_CLS_INF; \ diff --git a/include/net/addrconf.h b/include/net/addrconf.h index ba3f6c15ad2b..18f783dcd55f 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -97,7 +97,8 @@ bool ipv6_chk_custom_prefix(const struct in6_addr *addr, int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev); -struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr); +struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, + struct net_device *dev); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 91eacbdcf33d..f6abcc0bbd6e 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -59,7 +59,7 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); -u32 rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *); +bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *); int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 5036c94c0503..119f4c9c3a9c 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -3,13 +3,27 @@ #ifndef _BPF_SK_STORAGE_H #define _BPF_SK_STORAGE_H +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/bpf.h> +#include <net/sock.h> +#include <uapi/linux/sock_diag.h> +#include <uapi/linux/btf.h> +#include <linux/bpf_local_storage.h> + struct sock; void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; +extern const struct bpf_func_proto sk_storage_get_btf_proto; +extern const struct bpf_func_proto sk_storage_delete_btf_proto; +struct bpf_local_storage_elem; struct bpf_sk_storage_diag; struct sk_buff; struct nlattr; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d9e6b9fbd95b..c9bce9bba511 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -678,7 +678,10 @@ struct cfg80211_bitrate_mask { u32 legacy; u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; u16 vht_mcs[NL80211_VHT_NSS_MAX]; + u16 he_mcs[NL80211_HE_NSS_MAX]; enum nl80211_txrate_gi gi; + enum nl80211_he_gi he_gi; + enum nl80211_he_ltf he_ltf; } control[NUM_NL80211_BANDS]; }; diff --git a/include/net/devlink.h b/include/net/devlink.h index 8f3c8a443238..eaec0a8cc5ef 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -57,13 +57,30 @@ struct devlink_port_phys_attrs { u32 split_subport_number; /* If the port is split, this is the number of subport. */ }; +/** + * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes + * @controller: Associated controller number + * @pf: Associated PCI PF number for this port. + * @external: when set, indicates if a port is for an external controller + */ struct devlink_port_pci_pf_attrs { - u16 pf; /* Associated PCI PF for this port. */ + u32 controller; + u16 pf; + u8 external:1; }; +/** + * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes + * @controller: Associated controller number + * @pf: Associated PCI PF number for this port. + * @vf: Associated PCI VF for of the PCI PF for this port. + * @external: when set, indicates if a port is for an external controller + */ struct devlink_port_pci_vf_attrs { - u16 pf; /* Associated PCI PF for this port. */ - u16 vf; /* Associated PCI VF for of the PCI PF for this port. */ + u32 controller; + u16 pf; + u16 vf; + u8 external:1; }; /** @@ -73,6 +90,9 @@ struct devlink_port_pci_vf_attrs { * @splittable: indicates if the port can be split. * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink. * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL + * @phys: physical port attributes + * @pci_pf: PCI PF port attributes + * @pci_vf: PCI VF port attributes */ struct devlink_port_attrs { u8 split:1, @@ -1203,9 +1223,10 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port, void devlink_port_type_clear(struct devlink_port *devlink_port); void devlink_port_attrs_set(struct devlink_port *devlink_port, struct devlink_port_attrs *devlink_port_attrs); -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf); -void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, - u16 pf, u16 vf); +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, bool external); +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u16 vf, bool external); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/net/dst.h b/include/net/dst.h index 6ae2e625050d..8ea8812b0b41 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -214,7 +214,7 @@ dst_allfrag(const struct dst_entry *dst) static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { - return dst_metric(dst, RTAX_LOCK) & (1<<metric); + return dst_metric(dst, RTAX_LOCK) & (1 << metric); } static inline void dst_hold(struct dst_entry *dst) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index aa8893c68c50..c738abeb3265 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -86,6 +86,8 @@ struct inet_connection_sock { struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; + __u32 icsk_rto_min; + __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index a3702d1d4875..89163ef8cf4b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -296,13 +296,6 @@ static inline void __inet_sk_copy_descendant(struct sock *sk_to, memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } -#if !(IS_ENABLED(CONFIG_IPV6)) -static inline void inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - __inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock)); -} -#endif int inet_sk_rebuild_header(struct sock *sk); diff --git a/include/net/ip.h b/include/net/ip.h index b09c48d862cc..0f72bf8c0cbf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -151,7 +151,7 @@ int igmp_mc_init(void); int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, - struct ip_options_rcu *opt); + struct ip_options_rcu *opt, u8 tos); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ip_list_rcv(struct list_head *head, struct packet_type *pt, diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9a59a33787cb..d609e957a3ec 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,9 +25,6 @@ #include <linux/ip.h> #include <linux/ipv6.h> /* for struct ipv6hdr */ #include <net/ipv6.h> -#if IS_ENABLED(CONFIG_IP_VS_IPV6) -#include <linux/netfilter_ipv6/ip6_tables.h> -#endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index d7a7f7c81e7b..8fce558b5fea 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -63,6 +63,9 @@ struct ipv6_stub { int encap_type); #endif struct neigh_table *nd_tbl; + + int (*ipv6_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); }; extern const struct ipv6_stub *ipv6_stub __read_mostly; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 66e2bfd165e8..ec148b3e9c41 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3736,7 +3736,7 @@ enum ieee80211_reconfig_type { * decremented, and when they reach 1 the driver must call * ieee80211_csa_finish(). Drivers which use ieee80211_beacon_get() * get the csa counter decremented by mac80211, but must check if it is - * 1 using ieee80211_csa_is_complete() after the beacon has been + * 1 using ieee80211_beacon_counter_is_complete() after the beacon has been * transmitted and then call ieee80211_csa_finish(). * If the CSA count starts as zero or 1, this function will not be called, * since there won't be any time to beacon before the switch anyway. @@ -4763,21 +4763,21 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, */ void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets); -#define IEEE80211_MAX_CSA_COUNTERS_NUM 2 +#define IEEE80211_MAX_CNTDWN_COUNTERS_NUM 2 /** * struct ieee80211_mutable_offsets - mutable beacon offsets * @tim_offset: position of TIM element * @tim_length: size of TIM element - * @csa_counter_offs: array of IEEE80211_MAX_CSA_COUNTERS_NUM offsets - * to CSA counters. This array can contain zero values which + * @cntdwn_counter_offs: array of IEEE80211_MAX_CNTDWN_COUNTERS_NUM offsets + * to countdown counters. This array can contain zero values which * should be ignored. */ struct ieee80211_mutable_offsets { u16 tim_offset; u16 tim_length; - u16 csa_counter_offs[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u16 cntdwn_counter_offs[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; }; /** @@ -4846,31 +4846,31 @@ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, } /** - * ieee80211_csa_update_counter - request mac80211 to decrement the csa counter + * ieee80211_beacon_update_cntdwn - request mac80211 to decrement the beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * The csa counter should be updated after each beacon transmission. + * The beacon counter should be updated after each beacon transmission. * This function is called implicitly when * ieee80211_beacon_get/ieee80211_beacon_get_tim are called, however if the * beacon frames are generated by the device, the driver should call this - * function after each beacon transmission to sync mac80211's csa counters. + * function after each beacon transmission to sync mac80211's beacon countdown. * - * Return: new csa counter value + * Return: new countdown value */ -u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif); +u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif); /** - * ieee80211_csa_set_counter - request mac80211 to set csa counter + * ieee80211_beacon_set_cntdwn - request mac80211 to set beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @counter: the new value for the counter * - * The csa counter can be changed by the device, this API should be + * The beacon countdown can be changed by the device, this API should be * used by the device driver to update csa counter in mac80211. * - * It should never be used together with ieee80211_csa_update_counter(), + * It should never be used together with ieee80211_beacon_update_cntdwn(), * as it will cause a race condition around the counter value. */ -void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); +void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter); /** * ieee80211_csa_finish - notify mac80211 about channel switch @@ -4883,13 +4883,12 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); void ieee80211_csa_finish(struct ieee80211_vif *vif); /** - * ieee80211_csa_is_complete - find out if counters reached 1 + * ieee80211_beacon_cntdwn_is_complete - find out if countdown reached 1 * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * This function returns whether the channel switch counters reached zero. + * This function returns whether the countdown reached zero. */ -bool ieee80211_csa_is_complete(struct ieee80211_vif *vif); - +bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif); /** * ieee80211_proberesp_get - retrieve a Probe Response template diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 9205a76d967a..38e4094960ce 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -494,7 +494,7 @@ int igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index bf9491b77d16..8ceca0e419b3 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -143,6 +143,8 @@ static inline u64 nft_reg_load64(const u32 *sreg) static inline void nft_data_copy(u32 *dst, const struct nft_data *src, unsigned int len) { + if (len % NFT_REG32_SIZE) + dst[len / NFT_REG32_SIZE] = 0; memcpy(dst, src, len); } @@ -1080,6 +1082,8 @@ struct nft_table { flags:8, genmask:2; char *name; + u16 udlen; + u8 *udata; }; void nft_register_chain_type(const struct nft_chain_type *); @@ -1121,6 +1125,8 @@ struct nft_object { u32 genmask:2, use:30; u64 handle; + u16 udlen; + u8 *udata; /* runtime data below here */ const struct nft_object_ops *ops ____cacheline_aligned; unsigned char data[] diff --git a/include/net/netlink.h b/include/net/netlink.h index c0411f14fb53..fdd317f8fde4 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -181,8 +181,6 @@ enum { NLA_S64, NLA_BITFIELD32, NLA_REJECT, - NLA_EXACT_LEN, - NLA_MIN_LEN, __NLA_TYPE_MAX, }; @@ -199,11 +197,11 @@ struct netlink_range_validation_signed { enum nla_policy_validation { NLA_VALIDATE_NONE, NLA_VALIDATE_RANGE, + NLA_VALIDATE_RANGE_WARN_TOO_LONG, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, NLA_VALIDATE_RANGE_PTR, NLA_VALIDATE_FUNCTION, - NLA_VALIDATE_WARN_TOO_LONG, }; /** @@ -222,7 +220,7 @@ enum nla_policy_validation { * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload - * NLA_MIN_LEN Minimum length of attribute payload + * (but see also below with the validation type) * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if @@ -237,11 +235,6 @@ enum nla_policy_validation { * just like "All other" * NLA_BITFIELD32 Unused * NLA_REJECT Unused - * NLA_EXACT_LEN Attribute should have exactly this length, otherwise - * it is rejected or warned about, the latter happening - * if and only if the `validation_type' is set to - * NLA_VALIDATE_WARN_TOO_LONG. - * NLA_MIN_LEN Minimum length of attribute payload * All other Minimum length of attribute payload * * Meaning of validation union: @@ -296,6 +289,11 @@ enum nla_policy_validation { * pointer to a struct netlink_range_validation_signed * that indicates the min/max values. * Use NLA_POLICY_FULL_RANGE_SIGNED(). + * + * NLA_BINARY If the validation type is like the ones for integers + * above, then the min/max length (not value like for + * integers) of the attribute is enforced. + * * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: @@ -309,7 +307,7 @@ enum nla_policy_validation { * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, - * [ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) }, + * [ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)), * [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags), * }; */ @@ -335,9 +333,10 @@ struct nla_policy { * nesting validation starts here. * * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT - * for any types >= this, so need to use NLA_MIN_LEN to get the - * previous pure { .len = xyz } behaviour. The advantage of this - * is that types not specified in the policy will be rejected. + * for any types >= this, so need to use NLA_POLICY_MIN_LEN() to + * get the previous pure { .len = xyz } behaviour. The advantage + * of this is that types not specified in the policy will be + * rejected. * * For completely new families it should be set to 1 so that the * validation is enforced for all attributes. For existing ones @@ -349,12 +348,6 @@ struct nla_policy { }; }; -#define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } -#define NLA_POLICY_EXACT_LEN_WARN(_len) \ - { .type = NLA_EXACT_LEN, .len = _len, \ - .validation_type = NLA_VALIDATE_WARN_TOO_LONG, } -#define NLA_POLICY_MIN_LEN(_len) { .type = NLA_MIN_LEN, .len = _len } - #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) @@ -370,19 +363,21 @@ struct nla_policy { { .type = NLA_BITFIELD32, .bitfield32_valid = valid } #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) -#define NLA_ENSURE_UINT_TYPE(tp) \ +#define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_U8 || tp == NLA_U16 || \ tp == NLA_U32 || tp == NLA_U64 || \ - tp == NLA_MSECS) + tp) + tp == NLA_MSECS || \ + tp == NLA_BINARY) + tp) #define NLA_ENSURE_SINT_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_S16 || \ tp == NLA_S32 || tp == NLA_S64) + tp) -#define NLA_ENSURE_INT_TYPE(tp) \ +#define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 || \ tp == NLA_S16 || tp == NLA_U16 || \ tp == NLA_S32 || tp == NLA_U32 || \ tp == NLA_S64 || tp == NLA_U64 || \ - tp == NLA_MSECS) + tp) + tp == NLA_MSECS || \ + tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ tp != NLA_REJECT && \ @@ -390,14 +385,14 @@ struct nla_policy { tp != NLA_NESTED_ARRAY) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE, \ .min = _min, \ .max = _max \ } #define NLA_POLICY_FULL_RANGE(tp, _range) { \ - .type = NLA_ENSURE_UINT_TYPE(tp), \ + .type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range = _range, \ } @@ -409,13 +404,13 @@ struct nla_policy { } #define NLA_POLICY_MIN(tp, _min) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MIN, \ .min = _min, \ } #define NLA_POLICY_MAX(tp, _max) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ } @@ -427,6 +422,15 @@ struct nla_policy { .len = __VA_ARGS__ + 0, \ } +#define NLA_POLICY_EXACT_LEN(_len) NLA_POLICY_RANGE(NLA_BINARY, _len, _len) +#define NLA_POLICY_EXACT_LEN_WARN(_len) { \ + .type = NLA_BINARY, \ + .validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG, \ + .min = _len, \ + .max = _len \ +} +#define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) + /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 9e36738c1fe1..8e4fcac4df72 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -183,6 +183,7 @@ struct netns_ipv4 { unsigned int sysctl_tcp_fastopen_blackhole_timeout; atomic_t tfo_active_disable_times; unsigned long tfo_active_disable_stamp; + int sysctl_tcp_reflect_tos; int sysctl_udp_wmem_min; int sysctl_udp_rmem_min; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index b2eb8b4ba697..29e41ff3ec93 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -41,6 +41,13 @@ struct request_sock_ops { int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); +struct saved_syn { + u32 mac_hdrlen; + u32 network_hdrlen; + u32 tcp_hdrlen; + u8 data[]; +}; + /* struct request_sock - mini sock to represent a connection request */ struct request_sock { @@ -60,7 +67,7 @@ struct request_sock { struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; - u32 *saved_syn; + struct saved_syn *saved_syn; u32 secid; u32 peer_secid; }; diff --git a/include/net/sock.h b/include/net/sock.h index 064637d1ddf6..7dd3051551fb 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -246,7 +246,7 @@ struct sock_common { /* public: */ }; -struct bpf_sk_storage; +struct bpf_local_storage; /** * struct sock - network layer representation of sockets @@ -517,7 +517,7 @@ struct sock { void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL - struct bpf_sk_storage __rcu *sk_bpf_storage; + struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; }; @@ -1478,7 +1478,7 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { if (!sk_has_account(sk)) return true; - return size<= sk->sk_forward_alloc || + return size <= sk->sk_forward_alloc || __sk_mem_schedule(sk, size, SK_MEM_RECV) || skb_pfmemalloc(skb); } diff --git a/include/net/tcp.h b/include/net/tcp.h index eab6c7510b5b..e85d564446c6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -394,7 +394,7 @@ void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); -void tcp_init_transfer(struct sock *sk, int bpf_op); +void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, @@ -455,7 +455,8 @@ enum tcp_synack_type { struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); @@ -699,7 +700,7 @@ static inline void tcp_fast_path_check(struct sock *sk) static inline u32 tcp_rto_min(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); - u32 rto_min = TCP_RTO_MIN; + u32 rto_min = inet_csk(sk)->icsk_rto_min; if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); @@ -941,16 +942,6 @@ INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); #endif -static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) -{ -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) - return true; -#endif - return false; -} - /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { @@ -2035,7 +2026,8 @@ struct tcp_request_sock_ops { int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; @@ -2233,6 +2225,55 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ +#ifdef CONFIG_CGROUP_BPF +/* Copy the listen sk's HDR_OPT_CB flags to its child. + * + * During 3-Way-HandShake, the synack is usually sent from + * the listen sk with the HDR_OPT_CB flags set so that + * bpf-prog will be called to write the BPF hdr option. + * + * In fastopen, the child sk is used to send synack instead + * of the listen sk. Thus, inheriting the HDR_OPT_CB flags + * from the listen sk gives the bpf-prog a chance to write + * BPF hdr option in the synack pkt during fastopen. + * + * Both fastopen and non-fastopen child will inherit the + * HDR_OPT_CB flags to keep the bpf-prog having a consistent + * behavior when deciding to clear this cb flags (or not) + * during the PASSIVE_ESTABLISHED_CB. + * + * In the future, other cb flags could be inherited here also. + */ +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ + tcp_sk(child)->bpf_sock_ops_cb_flags = + tcp_sk(sk)->bpf_sock_ops_cb_flags & + (BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG); +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ + skops->skb = skb; + skops->skb_data_end = skb->data + end_offset; +} +#else +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ +} +#endif + /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index c9d87cc40c11..1a9559c0cbdd 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -18,25 +18,19 @@ struct xsk_queue; struct xdp_buff; struct xdp_umem { - struct xsk_queue *fq; - struct xsk_queue *cq; - struct xsk_buff_pool *pool; + void *addrs; u64 size; u32 headroom; u32 chunk_size; + u32 chunks; + u32 npgs; struct user_struct *user; refcount_t users; - struct work_struct work; - struct page **pgs; - u32 npgs; - u16 queue_id; - u8 need_wakeup; u8 flags; - int id; - struct net_device *dev; bool zc; - spinlock_t xsk_tx_list_lock; - struct list_head xsk_tx_list; + struct page **pgs; + int id; + struct list_head xsk_dma_list; }; struct xsk_map { @@ -48,10 +42,11 @@ struct xsk_map { struct xdp_sock { /* struct sock must be the first member of struct xdp_sock */ struct sock sk; - struct xsk_queue *rx; + struct xsk_queue *rx ____cacheline_aligned_in_smp; struct net_device *dev; struct xdp_umem *umem; struct list_head flush_node; + struct xsk_buff_pool *pool; u16 queue_id; bool zc; enum { @@ -59,10 +54,9 @@ struct xdp_sock { XSK_BOUND, XSK_UNBOUND, } state; - /* Protects multiple processes in the control path */ - struct mutex mutex; + struct xsk_queue *tx ____cacheline_aligned_in_smp; - struct list_head list; + struct list_head tx_list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths * in the SKB destructor callback. */ @@ -77,6 +71,10 @@ struct xdp_sock { struct list_head map_list; /* Protects map_list */ spinlock_t map_list_lock; + /* Protects multiple processes in the control path */ + struct mutex mutex; + struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */ + struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; #ifdef CONFIG_XDP_SOCKETS diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index ccf848f7efa4..5b1ee8a9976d 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -11,47 +11,50 @@ #ifdef CONFIG_XDP_SOCKETS -void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); -bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); -void xsk_umem_consume_tx_done(struct xdp_umem *umem); -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id); -void xsk_set_rx_need_wakeup(struct xdp_umem *umem); -void xsk_set_tx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_rx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_tx_need_wakeup(struct xdp_umem *umem); -bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem); +void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); +bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); +void xsk_tx_release(struct xsk_buff_pool *pool); +struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, + u16 queue_id); +void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool); +bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool); -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { - return XDP_PACKET_HEADROOM + umem->headroom; + return XDP_PACKET_HEADROOM + pool->headroom; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { - return umem->chunk_size; + return pool->chunk_size; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { - return xsk_umem_get_chunk_size(umem) - xsk_umem_get_headroom(umem); + return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool); } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { - xp_set_rxq_info(umem->pool, rxq); + xp_set_rxq_info(pool, rxq); } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { - xp_dma_unmap(umem->pool, attrs); + xp_dma_unmap(pool, attrs); } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { - return xp_dma_map(umem->pool, dev, attrs, umem->pgs, umem->npgs); + struct xdp_umem *umem = pool->umem; + + return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs); } static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp) @@ -68,14 +71,14 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return xp_get_frame_dma(xskb); } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { - return xp_alloc(umem->pool); + return xp_alloc(pool); } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { - return xp_can_alloc(umem->pool, count); + return xp_can_alloc(pool, count); } static inline void xsk_buff_free(struct xdp_buff *xdp) @@ -85,100 +88,104 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) xp_free(xskb); } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { - return xp_raw_get_dma(umem->pool, addr); + return xp_raw_get_dma(pool, addr); } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { - return xp_raw_get_data(umem->pool, addr); + return xp_raw_get_data(pool, addr); } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + if (!pool->dma_need_sync) + return; + xp_dma_sync_for_cpu(xskb); } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { - xp_dma_sync_for_device(umem->pool, dma, size); + xp_dma_sync_for_device(pool, dma, size); } #else -static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { } -static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, - struct xdp_desc *desc) +static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, + struct xdp_desc *desc) { return false; } -static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) +static inline void xsk_tx_release(struct xsk_buff_pool *pool) { } -static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) +static inline struct xsk_buff_pool * +xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id) { return NULL; } -static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { return false; } -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { return 0; } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { return 0; } @@ -193,12 +200,12 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return 0; } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { return NULL; } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { return false; } @@ -207,21 +214,22 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { return 0; } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { return NULL; } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 6842990e2712..0140d086dc84 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -13,6 +13,8 @@ struct xsk_buff_pool; struct xdp_rxq_info; struct xsk_queue; struct xdp_desc; +struct xdp_umem; +struct xdp_sock; struct device; struct page; @@ -26,34 +28,68 @@ struct xdp_buff_xsk { struct list_head free_list_node; }; +struct xsk_dma_map { + dma_addr_t *dma_pages; + struct device *dev; + struct net_device *netdev; + refcount_t users; + struct list_head list; /* Protected by the RTNL_LOCK */ + u32 dma_pages_cnt; + bool dma_need_sync; +}; + struct xsk_buff_pool { - struct xsk_queue *fq; + /* Members only used in the control path first. */ + struct device *dev; + struct net_device *netdev; + struct list_head xsk_tx_list; + /* Protects modifications to the xsk_tx_list */ + spinlock_t xsk_tx_list_lock; + refcount_t users; + struct xdp_umem *umem; + struct work_struct work; struct list_head free_list; + u32 heads_cnt; + u16 queue_id; + + /* Data path members as close to free_heads at the end as possible. */ + struct xsk_queue *fq ____cacheline_aligned_in_smp; + struct xsk_queue *cq; + /* For performance reasons, each buff pool has its own array of dma_pages + * even when they are identical. + */ dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; u64 chunk_mask; u64 addrs_cnt; u32 free_list_cnt; u32 dma_pages_cnt; - u32 heads_cnt; u32 free_heads_cnt; u32 headroom; u32 chunk_size; u32 frame_len; + u8 cached_need_wakeup; + bool uses_need_wakeup; bool dma_need_sync; bool unaligned; void *addrs; - struct device *dev; struct xdp_buff_xsk *free_heads[]; }; /* AF_XDP core. */ -struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, - u32 chunk_size, u32 headroom, u64 size, - bool unaligned); -void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); +struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, + struct xdp_umem *umem); +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, + u16 queue_id, u16 flags); +int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, + struct net_device *dev, u16 queue_id); void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); +void xp_get_pool(struct xsk_buff_pool *pool); +void xp_put_pool(struct xsk_buff_pool *pool); +void xp_clear_dev(struct xsk_buff_pool *pool); +void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); +void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); @@ -80,9 +116,6 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { - if (!xskb->pool->dma_need_sync) - return; - xp_dma_sync_for_cpu_slow(xskb); } diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index cc41d692ae8e..4c8b99ec8606 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -746,24 +746,29 @@ TRACE_EVENT(ext4_mb_release_group_pa, ); TRACE_EVENT(ext4_discard_preallocations, - TP_PROTO(struct inode *inode), + TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed), - TP_ARGS(inode), + TP_ARGS(inode, len, needed), TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( unsigned int, len ) + __field( unsigned int, needed ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; + __entry->len = len; + __entry->needed = needed; ), - TP_printk("dev %d,%d ino %lu", + TP_printk("dev %d,%d ino %lu len: %u needed %u", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino) + (unsigned long) __entry->ino, __entry->len, + __entry->needed) ); TRACE_EVENT(ext4_mb_discard_preallocations, @@ -1312,18 +1317,34 @@ DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load, TP_ARGS(sb, group) ); -DEFINE_EVENT(ext4__bitmap_load, ext4_read_block_bitmap_load, +DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); -DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, +TRACE_EVENT(ext4_read_block_bitmap_load, + TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch), - TP_PROTO(struct super_block *sb, unsigned long group), + TP_ARGS(sb, group, prefetch), - TP_ARGS(sb, group) + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + __field( bool, prefetch ) + + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + __entry->prefetch = prefetch; + ), + + TP_printk("dev %d,%d group %u prefetch %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group, __entry->prefetch) ); TRACE_EVENT(ext4_direct_IO_enter, @@ -2726,6 +2747,50 @@ TRACE_EVENT(ext4_error, __entry->function, __entry->line) ); +TRACE_EVENT(ext4_prefetch_bitmaps, + TP_PROTO(struct super_block *sb, ext4_group_t group, + ext4_group_t next, unsigned int prefetch_ios), + + TP_ARGS(sb, group, next, prefetch_ios), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + __field( __u32, next ) + __field( __u32, ios ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + __entry->next = next; + __entry->ios = prefetch_ios; + ), + + TP_printk("dev %d,%d group %u next %u ios %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group, __entry->next, __entry->ios) +); + +TRACE_EVENT(ext4_lazy_itable_init, + TP_PROTO(struct super_block *sb, ext4_group_t group), + + TP_ARGS(sb, group), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + ), + + TP_printk("dev %d,%d group %u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 939092dbcb8b..5fb752034386 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -114,6 +114,8 @@ IF_HAVE_PG_IDLE(PG_idle, "idle" ) #if defined(CONFIG_X86) #define __VM_ARCH_SPECIFIC_1 {VM_PAT, "pat" } +#elif defined(CONFIG_PPC) +#define __VM_ARCH_SPECIFIC_1 {VM_SAO, "sao" } #elif defined(CONFIG_PARISC) || defined(CONFIG_IA64) #define __VM_ARCH_SPECIFIC_1 {VM_GROWSUP, "growsup" } #elif !defined(CONFIG_MMU) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 059b6e45a028..3b67d5981224 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -68,21 +68,14 @@ enum rxrpc_client_trace { rxrpc_client_chan_activate, rxrpc_client_chan_disconnect, rxrpc_client_chan_pass, - rxrpc_client_chan_unstarted, rxrpc_client_chan_wait_failed, rxrpc_client_cleanup, - rxrpc_client_count, rxrpc_client_discard, rxrpc_client_duplicate, rxrpc_client_exposed, rxrpc_client_replace, rxrpc_client_to_active, - rxrpc_client_to_culled, rxrpc_client_to_idle, - rxrpc_client_to_inactive, - rxrpc_client_to_upgrade, - rxrpc_client_to_waiting, - rxrpc_client_uncount, }; enum rxrpc_call_trace { @@ -138,11 +131,16 @@ enum rxrpc_recvmsg_trace { }; enum rxrpc_rtt_tx_trace { + rxrpc_rtt_tx_cancel, rxrpc_rtt_tx_data, + rxrpc_rtt_tx_no_slot, rxrpc_rtt_tx_ping, }; enum rxrpc_rtt_rx_trace { + rxrpc_rtt_rx_cancel, + rxrpc_rtt_rx_lost, + rxrpc_rtt_rx_obsolete, rxrpc_rtt_rx_ping_response, rxrpc_rtt_rx_requested_ack, }; @@ -266,29 +264,14 @@ enum rxrpc_tx_point { EM(rxrpc_client_chan_activate, "ChActv") \ EM(rxrpc_client_chan_disconnect, "ChDisc") \ EM(rxrpc_client_chan_pass, "ChPass") \ - EM(rxrpc_client_chan_unstarted, "ChUnst") \ EM(rxrpc_client_chan_wait_failed, "ChWtFl") \ EM(rxrpc_client_cleanup, "Clean ") \ - EM(rxrpc_client_count, "Count ") \ EM(rxrpc_client_discard, "Discar") \ EM(rxrpc_client_duplicate, "Duplic") \ EM(rxrpc_client_exposed, "Expose") \ EM(rxrpc_client_replace, "Replac") \ EM(rxrpc_client_to_active, "->Actv") \ - EM(rxrpc_client_to_culled, "->Cull") \ - EM(rxrpc_client_to_idle, "->Idle") \ - EM(rxrpc_client_to_inactive, "->Inac") \ - EM(rxrpc_client_to_upgrade, "->Upgd") \ - EM(rxrpc_client_to_waiting, "->Wait") \ - E_(rxrpc_client_uncount, "Uncoun") - -#define rxrpc_conn_cache_states \ - EM(RXRPC_CONN_CLIENT_INACTIVE, "Inac") \ - EM(RXRPC_CONN_CLIENT_WAITING, "Wait") \ - EM(RXRPC_CONN_CLIENT_ACTIVE, "Actv") \ - EM(RXRPC_CONN_CLIENT_UPGRADE, "Upgd") \ - EM(RXRPC_CONN_CLIENT_CULLED, "Cull") \ - E_(RXRPC_CONN_CLIENT_IDLE, "Idle") \ + E_(rxrpc_client_to_idle, "->Idle") #define rxrpc_call_traces \ EM(rxrpc_call_connected, "CON") \ @@ -339,10 +322,15 @@ enum rxrpc_tx_point { E_(rxrpc_recvmsg_wait, "WAIT") #define rxrpc_rtt_tx_traces \ + EM(rxrpc_rtt_tx_cancel, "CNCE") \ EM(rxrpc_rtt_tx_data, "DATA") \ + EM(rxrpc_rtt_tx_no_slot, "FULL") \ E_(rxrpc_rtt_tx_ping, "PING") #define rxrpc_rtt_rx_traces \ + EM(rxrpc_rtt_rx_cancel, "CNCL") \ + EM(rxrpc_rtt_rx_obsolete, "OBSL") \ + EM(rxrpc_rtt_rx_lost, "LOST") \ EM(rxrpc_rtt_rx_ping_response, "PONG") \ E_(rxrpc_rtt_rx_requested_ack, "RACK") @@ -584,23 +572,20 @@ TRACE_EVENT(rxrpc_client, __field(int, channel ) __field(int, usage ) __field(enum rxrpc_client_trace, op ) - __field(enum rxrpc_conn_cache_state, cs ) ), TP_fast_assign( - __entry->conn = conn->debug_id; + __entry->conn = conn ? conn->debug_id : 0; __entry->channel = channel; - __entry->usage = atomic_read(&conn->usage); + __entry->usage = conn ? atomic_read(&conn->usage) : -2; __entry->op = op; __entry->cid = conn->proto.cid; - __entry->cs = conn->cache_state; ), - TP_printk("C=%08x h=%2d %s %s i=%08x u=%d", + TP_printk("C=%08x h=%2d %s i=%08x u=%d", __entry->conn, __entry->channel, __print_symbolic(__entry->op, rxrpc_client_traces), - __print_symbolic(__entry->cs, rxrpc_conn_cache_states), __entry->cid, __entry->usage) ); @@ -1087,38 +1072,43 @@ TRACE_EVENT(rxrpc_recvmsg, TRACE_EVENT(rxrpc_rtt_tx, TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_tx_trace why, - rxrpc_serial_t send_serial), + int slot, rxrpc_serial_t send_serial), - TP_ARGS(call, why, send_serial), + TP_ARGS(call, why, slot, send_serial), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_rtt_tx_trace, why ) + __field(int, slot ) __field(rxrpc_serial_t, send_serial ) ), TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; + __entry->slot = slot; __entry->send_serial = send_serial; ), - TP_printk("c=%08x %s sr=%08x", + TP_printk("c=%08x [%d] %s sr=%08x", __entry->call, + __entry->slot, __print_symbolic(__entry->why, rxrpc_rtt_tx_traces), __entry->send_serial) ); TRACE_EVENT(rxrpc_rtt_rx, TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + int slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, u32 rtt, u32 rto), - TP_ARGS(call, why, send_serial, resp_serial, rtt, rto), + TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, rto), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_rtt_rx_trace, why ) + __field(int, slot ) __field(rxrpc_serial_t, send_serial ) __field(rxrpc_serial_t, resp_serial ) __field(u32, rtt ) @@ -1128,14 +1118,16 @@ TRACE_EVENT(rxrpc_rtt_rx, TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; + __entry->slot = slot; __entry->send_serial = send_serial; __entry->resp_serial = resp_serial; __entry->rtt = rtt; __entry->rto = rto; ), - TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%u rto=%u", + TP_printk("c=%08x [%d] %s sr=%08x rr=%08x rtt=%u rto=%u", __entry->call, + __entry->slot, __print_symbolic(__entry->why, rxrpc_rtt_rx_traces), __entry->send_serial, __entry->resp_serial, diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 10f5d1fa7347..e7cbccc7c14c 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -20,7 +20,6 @@ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ - {I_DIRTY_TIME_EXPIRED, "I_DIRTY_TIME_EXPIRED"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) @@ -498,8 +497,9 @@ DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, + unsigned long dirtied_before, int moved), - TP_ARGS(wb, work, moved), + TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) @@ -509,19 +509,17 @@ TRACE_EVENT(writeback_queue_io, __field(ino_t, cgroup_ino) ), TP_fast_assign( - unsigned long *older_than_this = work->older_than_this; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); - __entry->older = older_than_this ? *older_than_this : 0; - __entry->age = older_than_this ? - (jiffies - *older_than_this) * 1000 / HZ : -1; + __entry->older = dirtied_before; + __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, - __entry->older, /* older_than_this in jiffies */ - __entry->age, /* older_than_this in relative milliseconds */ + __entry->older, /* dirtied_before in jiffies */ + __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0480f893facd..8dda13880957 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -155,6 +155,7 @@ enum bpf_map_type { BPF_MAP_TYPE_DEVMAP_HASH, BPF_MAP_TYPE_STRUCT_OPS, BPF_MAP_TYPE_RINGBUF, + BPF_MAP_TYPE_INODE_STORAGE, }; /* Note that tracing related programs such as @@ -345,6 +346,14 @@ enum bpf_link_type { /* The verifier internal test flag. Behavior is undefined */ #define BPF_F_TEST_STATE_FREQ (1U << 3) +/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will + * restrict map and helper usage for such programs. Sleepable BPF programs can + * only be attached to hooks where kernel execution context allows sleeping. + * Such programs are allowed to use helpers that may sleep like + * bpf_copy_from_user(). + */ +#define BPF_F_SLEEPABLE (1U << 4) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * @@ -767,7 +776,7 @@ union bpf_attr { * * Also, note that **bpf_trace_printk**\ () is slow, and should * only be used for debugging purposes. For this reason, a notice - * bloc (spanning several lines) is printed to kernel logs and + * block (spanning several lines) is printed to kernel logs and * states that the helper should not be used "for production use" * the first time this helper is used (or more precisely, when * **trace_printk**\ () buffers are allocated). For passing values @@ -1033,14 +1042,14 @@ union bpf_attr { * * int ret; * struct bpf_tunnel_key key = {}; - * + * * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); * if (ret < 0) * return TC_ACT_SHOT; // drop packet - * + * * if (key.remote_ipv4 != 0x0a000001) * return TC_ACT_SHOT; // drop packet - * + * * return TC_ACT_OK; // accept packet * * This interface can also be used with all encapsulation devices @@ -1147,7 +1156,7 @@ union bpf_attr { * Description * Retrieve the realm or the route, that is to say the * **tclassid** field of the destination for the *skb*. The - * indentifier retrieved is a user-provided tag, similar to the + * identifier retrieved is a user-provided tag, similar to the * one used with the net_cls cgroup (see description for * **bpf_get_cgroup_classid**\ () helper), but here this tag is * held by a route (a destination entry), not by a task. @@ -2807,7 +2816,7 @@ union bpf_attr { * * **-ERANGE** if resulting value was out of range. * - * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags) * Description * Get a bpf-local-storage from a *sk*. * @@ -2823,6 +2832,9 @@ union bpf_attr { * "type". The bpf-local-storage "type" (i.e. the *map*) is * searched against all bpf-local-storages residing at *sk*. * + * *sk* is a kernel **struct sock** pointer for LSM program. + * *sk* is a **struct bpf_sock** pointer for other program types. + * * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be * used such that a new bpf-local-storage will be * created if one does not exist. *value* can be used @@ -2835,7 +2847,7 @@ union bpf_attr { * **NULL** if not found or there was an error in adding * a new bpf-local-storage. * - * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * long bpf_sk_storage_delete(struct bpf_map *map, void *sk) * Description * Delete a bpf-local-storage from a *sk*. * Return @@ -3395,6 +3407,175 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * + * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) + * Description + * Load header option. Support reading a particular TCP header + * option for bpf program (BPF_PROG_TYPE_SOCK_OPS). + * + * If *flags* is 0, it will search the option from the + * sock_ops->skb_data. The comment in "struct bpf_sock_ops" + * has details on what skb_data contains under different + * sock_ops->op. + * + * The first byte of the *searchby_res* specifies the + * kind that it wants to search. + * + * If the searching kind is an experimental kind + * (i.e. 253 or 254 according to RFC6994). It also + * needs to specify the "magic" which is either + * 2 bytes or 4 bytes. It then also needs to + * specify the size of the magic by using + * the 2nd byte which is "kind-length" of a TCP + * header option and the "kind-length" also + * includes the first 2 bytes "kind" and "kind-length" + * itself as a normal TCP header option also does. + * + * For example, to search experimental kind 254 with + * 2 byte magic 0xeB9F, the searchby_res should be + * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. + * + * To search for the standard window scale option (3), + * the searchby_res should be [ 3, 0, 0, .... 0 ]. + * Note, kind-length must be 0 for regular option. + * + * Searching for No-Op (0) and End-of-Option-List (1) are + * not supported. + * + * *len* must be at least 2 bytes which is the minimal size + * of a header option. + * + * Supported flags: + * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the + * saved_syn packet or the just-received syn packet. + * + * Return + * >0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. + * + * **-EINVAL** If param is invalid + * + * **-ENOMSG** The option is not found + * + * **-ENOENT** No syn packet available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used + * + * **-ENOSPC** Not enough space. Only *len* number of + * bytes are copied. + * + * **-EFAULT** Cannot parse the header options in the packet + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) + * Description + * Store header option. The data will be copied + * from buffer *from* with length *len* to the TCP header. + * + * The buffer *from* should have the whole option that + * includes the kind, kind-length, and the actual + * option data. The *len* must be at least kind-length + * long. The kind-length does not have to be 4 byte + * aligned. The kernel will take care of the padding + * and setting the 4 bytes aligned value to th->doff. + * + * This helper will check for duplicated option + * by searching the same option in the outgoing skb. + * + * This helper can only be called during + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** If param is invalid + * + * **-ENOSPC** Not enough space in the header. + * Nothing has been written + * + * **-EEXIST** The option has already existed + * + * **-EFAULT** Cannot parse the existing header options + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) + * Description + * Reserve *len* bytes for the bpf header option. The + * space will be used by bpf_store_hdr_opt() later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * If bpf_reserve_hdr_opt() is called multiple times, + * the total number of bytes will be reserved. + * + * This helper can only be called during + * BPF_SOCK_OPS_HDR_OPT_LEN_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** if param is invalid + * + * **-ENOSPC** Not enough space in the header. + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags) + * Description + * Get a bpf_local_storage from an *inode*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *inode* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this + * helper enforces the key must be an inode and the map must also + * be a **BPF_MAP_TYPE_INODE_STORAGE**. + * + * Underneath, the value is stored locally at *inode* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *inode*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * int bpf_inode_storage_delete(struct bpf_map *map, void *inode) + * Description + * Delete a bpf_local_storage from an *inode*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + * + * long bpf_d_path(struct path *path, char *buf, u32 sz) + * Description + * Return full path for given 'struct path' object, which + * needs to be the kernel BTF 'path' object. The path is + * returned in the provided buffer 'buf' of size 'sz' and + * is zero terminated. + * + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr) + * Description + * Read *size* bytes from user space address *user_ptr* and store + * the data in *dst*. This is a wrapper of copy_from_user(). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3539,6 +3720,13 @@ union bpf_attr { FN(skc_to_tcp_request_sock), \ FN(skc_to_udp6_sock), \ FN(get_task_stack), \ + FN(load_hdr_opt), \ + FN(store_hdr_opt), \ + FN(reserve_hdr_opt), \ + FN(inode_storage_get), \ + FN(inode_storage_delete), \ + FN(d_path), \ + FN(copy_from_user), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -3648,9 +3836,13 @@ enum { BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), }; -/* BPF_FUNC_sk_storage_get flags */ +/* BPF_FUNC_<kernel_obj>_storage_get flags */ enum { - BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0), + BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0), + /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility + * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead. + */ + BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE, }; /* BPF_FUNC_read_branch_records flags. */ @@ -4071,6 +4263,15 @@ struct bpf_link_info { __u64 cgroup_id; __u32 attach_type; } cgroup; + struct { + __aligned_u64 target_name; /* in/out: target_name buffer ptr */ + __u32 target_name_len; /* in/out: target_name buffer len */ + union { + struct { + __u32 map_id; + } map; + }; + } iter; struct { __u32 netns_ino; __u32 attach_type; @@ -4158,6 +4359,36 @@ struct bpf_sock_ops { __u64 bytes_received; __u64 bytes_acked; __bpf_md_ptr(struct bpf_sock *, sk); + /* [skb_data, skb_data_end) covers the whole TCP header. + * + * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received + * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the + * header has not been written. + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have + * been written so far. + * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes + * the 3WHS. + * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes + * the 3WHS. + * + * bpf_load_hdr_opt() can also be used to read a particular option. + */ + __bpf_md_ptr(void *, skb_data); + __bpf_md_ptr(void *, skb_data_end); + __u32 skb_len; /* The total length of a packet. + * It includes the header, options, + * and payload. + */ + __u32 skb_tcp_flags; /* tcp_flags of the header. It provides + * an easy way to check for tcp_flags + * without parsing skb_data. + * + * In particular, the skb_tcp_flags + * will still be available in + * BPF_SOCK_OPS_HDR_OPT_LEN even though + * the outgoing header has not + * been written yet. + */ }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -4166,8 +4397,51 @@ enum { BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), + /* Call bpf for all received TCP headers. The bpf prog will be + * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + * + * It could be used at the client/active side (i.e. connect() side) + * when the server told it that the server was in syncookie + * mode and required the active side to resend the bpf-written + * options. The active side can keep writing the bpf-options until + * it received a valid packet from the server side to confirm + * the earlier packet (and options) has been received. The later + * example patch is using it like this at the active side when the + * server is in syncookie mode. + * + * The bpf prog will usually turn this off in the common cases. + */ + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf when kernel has received a header option that + * the kernel cannot handle. The bpf prog will be called under + * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + */ + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + /* Call bpf when the kernel is writing header options for the + * outgoing packet. The bpf prog will first be called + * to reserve space in a skb under + * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then + * the bpf prog will be called to write the header option(s) + * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB + * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option + * related helpers that will be useful to the bpf programs. + * + * The kernel gets its chance to reserve space and write + * options first before the BPF program does. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ - BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF, + BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; /* List of known BPF sock_ops operators. @@ -4223,6 +4497,63 @@ enum { */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. */ + BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. + * It will be called to handle + * the packets received at + * an already established + * connection. + * + * sock_ops->skb_data: + * Referring to the received skb. + * It covers the TCP header only. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option. + */ + BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the + * header option later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Not available because no header has + * been written yet. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the + * outgoing skb. (e.g. SYN, ACK, FIN). + * + * bpf_reserve_hdr_opt() should + * be used to reserve space. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Referring to the outgoing skb. + * It covers the TCP header + * that has already been written + * by the kernel and the + * earlier bpf-progs. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the outgoing + * skb. (e.g. SYN, ACK, FIN). + * + * bpf_store_hdr_opt() should + * be used to write the + * option. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option that + * has already been written + * by the kernel or the + * earlier bpf-progs. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -4250,6 +4581,63 @@ enum { enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ + TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ + TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ + /* Copy the SYN pkt to optval + * + * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the + * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit + * to only getting from the saved_syn. It can either get the + * syn packet from: + * + * 1. the just-received SYN packet (only available when writing the + * SYNACK). It will be useful when it is not necessary to + * save the SYN packet for latter use. It is also the only way + * to get the SYN during syncookie mode because the syn + * packet cannot be saved during syncookie. + * + * OR + * + * 2. the earlier saved syn which was done by + * bpf_setsockopt(TCP_SAVE_SYN). + * + * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the + * SYN packet is obtained. + * + * If the bpf-prog does not need the IP[46] header, the + * bpf-prog can avoid parsing the IP header by using + * TCP_BPF_SYN. Otherwise, the bpf-prog can get both + * IP[46] and TCP header by using TCP_BPF_SYN_IP. + * + * >0: Total number of bytes copied + * -ENOSPC: Not enough space in optval. Only optlen number of + * bytes is copied. + * -ENOENT: The SYN skb is not available now and the earlier SYN pkt + * is not saved by setsockopt(TCP_SAVE_SYN). + */ + TCP_BPF_SYN = 1005, /* Copy the TCP header */ + TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ + TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ +}; + +enum { + BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0), +}; + +/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + */ +enum { + BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the + * total option spaces + * required for an established + * sk in order to calculate the + * MSS. No skb is actually + * sent. + */ + BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode + * when sending a SYN. + */ }; struct bpf_perf_event_value { diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cfef4245ea5a..40d35145c879 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -458,6 +458,8 @@ enum devlink_attr { DEVLINK_ATTR_PORT_LANES, /* u32 */ DEVLINK_ATTR_PORT_SPLITTABLE, /* u8 */ + DEVLINK_ATTR_PORT_EXTERNAL, /* u8 */ + DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index c7d66755d212..79f9191bbb24 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ +#define GTP_GENL_MCGRP_NAME "gtp" + enum gtp_genl_cmds { GTP_CMD_NEWPDP, GTP_CMD_DELPDP, diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index c1227aecd38f..75a2ac479247 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -455,10 +455,31 @@ enum { enum { MDBA_MDB_EATTR_UNSPEC, MDBA_MDB_EATTR_TIMER, + MDBA_MDB_EATTR_SRC_LIST, + MDBA_MDB_EATTR_GROUP_MODE, __MDBA_MDB_EATTR_MAX }; #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1) +/* per mdb entry source */ +enum { + MDBA_MDB_SRCLIST_UNSPEC, + MDBA_MDB_SRCLIST_ENTRY, + __MDBA_MDB_SRCLIST_MAX +}; +#define MDBA_MDB_SRCLIST_MAX (__MDBA_MDB_SRCLIST_MAX - 1) + +/* per mdb entry per source attributes + * these are embedded in MDBA_MDB_SRCLIST_ENTRY + */ +enum { + MDBA_MDB_SRCATTR_UNSPEC, + MDBA_MDB_SRCATTR_ADDRESS, + MDBA_MDB_SRCATTR_TIMER, + __MDBA_MDB_SRCATTR_MAX +}; +#define MDBA_MDB_SRCATTR_MAX (__MDBA_MDB_SRCATTR_MAX - 1) + /* multicast router types */ enum { MDB_RTR_TYPE_DISABLED, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7fba4de511de..bf4667403cab 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -40,26 +40,197 @@ struct rtnl_link_stats { __u32 rx_nohandler; /* dropped, no handler found */ }; -/* The main device statistics structure */ +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter should not include packets + * dropped by the device which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + */ struct rtnl_link_stats64 { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ - __u64 multicast; /* multicast packets received */ + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; __u64 collisions; /* detailed rx_errors: */ __u64 rx_length_errors; - __u64 rx_over_errors; /* receiver ring buff overflow */ - __u64 rx_crc_errors; /* recved pkt with crc error */ - __u64 rx_frame_errors; /* recv'd frame alignment error */ - __u64 rx_fifo_errors; /* recv'r fifo overrun */ - __u64 rx_missed_errors; /* receiver missed packet */ + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; /* detailed tx_errors */ __u64 tx_aborted_errors; @@ -71,8 +242,7 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; - - __u64 rx_nohandler; /* dropped, no handler found */ + __u64 rx_nohandler; }; /* The struct should be in sync with struct ifmap */ diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h index 060b4d1f3129..a91044328bc9 100644 --- a/include/uapi/linux/if_pppol2tp.h +++ b/include/uapi/linux/if_pppol2tp.h @@ -75,7 +75,7 @@ struct pppol2tpv3in6_addr { }; /* Socket options: - * DEBUG - bitmask of debug message categories + * DEBUG - bitmask of debug message categories (not used) * SENDSEQ - 0 => don't send packets with sequence numbers * 1 => send packets with sequence numbers * RECVSEQ - 0 => receive packet sequence numbers are optional diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 3d0d8231dc19..7d6687618d80 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -135,7 +135,7 @@ struct in_addr { * this socket to prevent accepting spoofed ones. */ #define IP_PMTUDISC_INTERFACE 4 -/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get +/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get * fragmented if they exeed the interface mtu */ #define IP_PMTUDISC_OMIT 5 diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 5ba122c1949a..20ee93f0f876 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -160,6 +160,7 @@ enum { INET_DIAG_ULP_INFO, INET_DIAG_SK_BPF_STORAGES, INET_DIAG_CGROUP_ID, + INET_DIAG_SOCKOPT, __INET_DIAG_MAX, }; @@ -183,6 +184,23 @@ struct inet_diag_meminfo { __u32 idiag_tmem; }; +/* INET_DIAG_SOCKOPT */ + +struct inet_diag_sockopt { + __u8 recverr:1, + is_icsk:1, + freebind:1, + hdrincl:1, + mc_loop:1, + transparent:1, + mc_all:1, + nodefrag:1; + __u8 bind_address_no_port:1, + recverr_rfc4884:1, + defer_connect:1, + unused:5; +}; + /* INET_DIAG_VEGASINFO */ struct tcpvegas_info { diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 61158f5a1a5b..88a0d32b8c07 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -108,7 +108,7 @@ enum { L2TP_ATTR_VLAN_ID, /* u16 (not used) */ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */ - L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags */ + L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags (not used) */ L2TP_ATTR_RECV_SEQ, /* u8 */ L2TP_ATTR_SEND_SEQ, /* u8 */ L2TP_ATTR_LNS_MODE, /* u8 */ @@ -177,7 +177,9 @@ enum l2tp_seqmode { }; /** - * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions + * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions. + * + * Unused. * * @L2TP_MSG_DEBUG: verbose debug (if compiled in) * @L2TP_MSG_CONTROL: userspace - kernel interface diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h index 11c8c1fc1124..1a42f5f9b31b 100644 --- a/include/uapi/linux/mroute.h +++ b/include/uapi/linux/mroute.h @@ -113,8 +113,8 @@ struct igmpmsg { __u32 unused1,unused2; unsigned char im_msgtype; /* What is this */ unsigned char im_mbz; /* Must be zero */ - unsigned char im_vif; /* Interface (this ought to be a vifi_t!) */ - unsigned char unused3; + unsigned char im_vif; /* Low 8 bits of Interface */ + unsigned char im_vif_hi; /* High 8 bits of Interface */ struct in_addr im_src,im_dst; }; @@ -169,6 +169,7 @@ enum { IPMRA_CREPORT_SRC_ADDR, IPMRA_CREPORT_DST_ADDR, IPMRA_CREPORT_PKT, + IPMRA_CREPORT_TABLE, __IPMRA_CREPORT_MAX }; #define IPMRA_CREPORT_MAX (__IPMRA_CREPORT_MAX - 1) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 42f351c1f5c5..3c2469b43742 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -133,7 +133,7 @@ enum nf_tables_msg_types { * @NFTA_LIST_ELEM: list element (NLA_NESTED) */ enum nft_list_attributes { - NFTA_LIST_UNPEC, + NFTA_LIST_UNSPEC, NFTA_LIST_ELEM, __NFTA_LIST_MAX }; @@ -172,6 +172,7 @@ enum nft_table_flags { * @NFTA_TABLE_NAME: name of the table (NLA_STRING) * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32) * @NFTA_TABLE_USE: number of chains in this table (NLA_U32) + * @NFTA_TABLE_USERDATA: user data (NLA_BINARY) */ enum nft_table_attributes { NFTA_TABLE_UNSPEC, @@ -180,6 +181,7 @@ enum nft_table_attributes { NFTA_TABLE_USE, NFTA_TABLE_HANDLE, NFTA_TABLE_PAD, + NFTA_TABLE_USERDATA, __NFTA_TABLE_MAX }; #define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1) @@ -1008,10 +1010,12 @@ enum nft_socket_attributes { * * @NFT_SOCKET_TRANSPARENT: Value of the IP(V6)_TRANSPARENT socket option * @NFT_SOCKET_MARK: Value of the socket mark + * @NFT_SOCKET_WILDCARD: Whether the socket is zero-bound (e.g. 0.0.0.0 or ::0) */ enum nft_socket_keys { NFT_SOCKET_TRANSPARENT, NFT_SOCKET_MARK, + NFT_SOCKET_WILDCARD, __NFT_SOCKET_MAX }; #define NFT_SOCKET_MAX (__NFT_SOCKET_MAX - 1) @@ -1555,6 +1559,7 @@ enum nft_ct_expectation_attributes { * @NFTA_OBJ_DATA: stateful object data (NLA_NESTED) * @NFTA_OBJ_USE: number of references to this expression (NLA_U32) * @NFTA_OBJ_HANDLE: object handle (NLA_U64) + * @NFTA_OBJ_USERDATA: user data (NLA_BINARY) */ enum nft_object_attributes { NFTA_OBJ_UNSPEC, @@ -1565,6 +1570,7 @@ enum nft_object_attributes { NFTA_OBJ_USE, NFTA_OBJ_HANDLE, NFTA_OBJ_PAD, + NFTA_OBJ_USERDATA, __NFTA_OBJ_MAX }; #define NFTA_OBJ_MAX (__NFTA_OBJ_MAX - 1) diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index 262881792671..d8484be72fdc 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -247,7 +247,7 @@ enum ctattr_stats_cpu { CTA_STATS_FOUND, CTA_STATS_NEW, /* no longer used */ CTA_STATS_INVALID, - CTA_STATS_IGNORE, + CTA_STATS_IGNORE, /* no longer used */ CTA_STATS_DELETE, /* no longer used */ CTA_STATS_DELETE_LIST, /* no longer used */ CTA_STATS_INSERT, @@ -256,6 +256,7 @@ enum ctattr_stats_cpu { CTA_STATS_EARLY_DROP, CTA_STATS_ERROR, CTA_STATS_SEARCH_RESTART, + CTA_STATS_CLASH_RESOLVE, __CTA_STATS_MAX, }; #define CTA_STATS_MAX (__CTA_STATS_MAX - 1) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 631f3a997b3c..0584e0d349f0 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -252,9 +252,13 @@ * DOC: SAE authentication offload * * By setting @NL80211_EXT_FEATURE_SAE_OFFLOAD flag drivers can indicate they - * support offloading SAE authentication for WPA3-Personal networks. In - * %NL80211_CMD_CONNECT the password for SAE should be specified using - * %NL80211_ATTR_SAE_PASSWORD. + * support offloading SAE authentication for WPA3-Personal networks in station + * mode. Similarly @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP flag can be set by + * drivers indicating the offload support in AP mode. + * + * The password for SAE should be specified using %NL80211_ATTR_SAE_PASSWORD in + * %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP for station and AP mode + * respectively. */ /** @@ -647,13 +651,9 @@ * authentication/association or not receiving a response from the AP. * Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as * well to remain backwards compatible. - * When establishing a security association, drivers that support 4 way - * handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when - * the 4 way handshake is completed successfully. * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself. - * When a security association was established with the new AP (e.g. if - * the FT protocol was used for roaming or the driver completed the 4 way - * handshake), this event should be followed by an + * When a security association was established on an 802.1X network using + * fast transition, this event should be followed by an * %NL80211_CMD_PORT_AUTHORIZED event. * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify * userspace that a connection was dropped by the AP or due to other @@ -1067,13 +1067,11 @@ * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously * configured PMK for the authenticator address identified by * %NL80211_ATTR_MAC. - * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way - * handshake was completed successfully by the driver. The BSSID is - * specified with %NL80211_ATTR_MAC. Drivers that support 4 way handshake - * offload should send this event after indicating 802.11 association with - * %NL80211_CMD_CONNECT or %NL80211_CMD_ROAM. If the 4 way handshake failed - * %NL80211_CMD_DISCONNECT should be indicated instead. - * + * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates an 802.1X FT roam was + * completed successfully. Drivers that support 4 way handshake offload + * should send this event after indicating 802.1X FT assocation with + * %NL80211_CMD_ROAM. If the 4 way handshake failed %NL80211_CMD_DISCONNECT + * should be indicated instead. * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request * and RX notification. This command is used both as a request to transmit * a control port frame and as a notification that a control port frame @@ -2082,10 +2080,10 @@ enum nl80211_commands { * operation). * @NL80211_ATTR_CSA_IES: Nested set of attributes containing the IE information * for the time while performing a channel switch. - * @NL80211_ATTR_CSA_C_OFF_BEACON: An array of offsets (u16) to the channel - * switch counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL). - * @NL80211_ATTR_CSA_C_OFF_PRESP: An array of offsets (u16) to the channel - * switch counters in the probe response (%NL80211_ATTR_PROBE_RESP). + * @NL80211_ATTR_CNTDWN_OFFS_BEACON: An array of offsets (u16) to the channel + * switch or color change counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL). + * @NL80211_ATTR_CNTDWN_OFFS_PRESP: An array of offsets (u16) to the channel + * switch or color change counters in the probe response (%NL80211_ATTR_PROBE_RESP). * * @NL80211_ATTR_RXMGMT_FLAGS: flags for nl80211_send_mgmt(), u32. * As specified in the &enum nl80211_rxmgmt_flags. @@ -2821,8 +2819,8 @@ enum nl80211_attrs { NL80211_ATTR_CH_SWITCH_COUNT, NL80211_ATTR_CH_SWITCH_BLOCK_TX, NL80211_ATTR_CSA_IES, - NL80211_ATTR_CSA_C_OFF_BEACON, - NL80211_ATTR_CSA_C_OFF_PRESP, + NL80211_ATTR_CNTDWN_OFFS_BEACON, + NL80211_ATTR_CNTDWN_OFFS_PRESP, NL80211_ATTR_RXMGMT_FLAGS, @@ -3009,6 +3007,8 @@ enum nl80211_attrs { #define NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG #define NL80211_ATTR_IFACE_SOCKET_OWNER NL80211_ATTR_SOCKET_OWNER #define NL80211_ATTR_SAE_DATA NL80211_ATTR_AUTH_DATA +#define NL80211_ATTR_CSA_C_OFF_BEACON NL80211_ATTR_CNTDWN_OFFS_BEACON +#define NL80211_ATTR_CSA_C_OFF_PRESP NL80211_ATTR_CNTDWN_OFFS_PRESP /* * Allow user space programs to use #ifdef on new attributes by defining them @@ -3187,6 +3187,18 @@ enum nl80211_he_gi { }; /** + * enum nl80211_he_ltf - HE long training field + * @NL80211_RATE_INFO_HE_1xLTF: 3.2 usec + * @NL80211_RATE_INFO_HE_2xLTF: 6.4 usec + * @NL80211_RATE_INFO_HE_4xLTF: 12.8 usec + */ +enum nl80211_he_ltf { + NL80211_RATE_INFO_HE_1XLTF, + NL80211_RATE_INFO_HE_2XLTF, + NL80211_RATE_INFO_HE_4XLTF, +}; + +/** * enum nl80211_he_ru_alloc - HE RU allocation values * @NL80211_RATE_INFO_HE_RU_ALLOC_26: 26-tone RU allocation * @NL80211_RATE_INFO_HE_RU_ALLOC_52: 52-tone RU allocation @@ -4741,6 +4753,10 @@ enum nl80211_key_attributes { * @NL80211_TXRATE_VHT: VHT rates allowed for TX rate selection, * see &struct nl80211_txrate_vht * @NL80211_TXRATE_GI: configure GI, see &enum nl80211_txrate_gi + * @NL80211_TXRATE_HE: HE rates allowed for TX rate selection, + * see &struct nl80211_txrate_he + * @NL80211_TXRATE_HE_GI: configure HE GI, 0.8us, 1.6us and 3.2us. + * @NL80211_TXRATE_HE_LTF: configure HE LTF, 1XLTF, 2XLTF and 4XLTF. * @__NL80211_TXRATE_AFTER_LAST: internal * @NL80211_TXRATE_MAX: highest TX rate attribute */ @@ -4750,6 +4766,9 @@ enum nl80211_tx_rate_attributes { NL80211_TXRATE_HT, NL80211_TXRATE_VHT, NL80211_TXRATE_GI, + NL80211_TXRATE_HE, + NL80211_TXRATE_HE_GI, + NL80211_TXRATE_HE_LTF, /* keep last */ __NL80211_TXRATE_AFTER_LAST, @@ -4767,6 +4786,15 @@ struct nl80211_txrate_vht { __u16 mcs[NL80211_VHT_NSS_MAX]; }; +#define NL80211_HE_NSS_MAX 8 +/** + * struct nl80211_txrate_he - HE MCS/NSS txrate bitmap + * @mcs: MCS bitmap table for each NSS (array index 0 for 1 stream, etc.) + */ +struct nl80211_txrate_he { + __u16 mcs[NL80211_HE_NSS_MAX]; +}; + enum nl80211_txrate_gi { NL80211_TXRATE_DEFAULT_GI, NL80211_TXRATE_FORCE_SGI, @@ -5821,6 +5849,9 @@ enum nl80211_feature_flags { * handshake with PSK in AP mode (PSK is passed as part of the start AP * command). * + * @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP: Device wants to do SAE authentication + * in AP mode (SAE password is passed as part of the start AP command). + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5878,6 +5909,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS, NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index d7f6af50e200..39df751d0dc4 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -76,7 +76,11 @@ static inline unsigned long bfn_to_pfn(unsigned long bfn) #define bfn_to_local_pfn(bfn) bfn_to_pfn(bfn) /* VIRT <-> GUEST conversion */ -#define virt_to_gfn(v) (pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT)) +#define virt_to_gfn(v) \ + ({ \ + WARN_ON_ONCE(!virt_addr_valid(v)); \ + pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT); \ + }) #define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) /* Only used in PV code. But ARM guests are always HVM. */ diff --git a/init/Kconfig b/init/Kconfig index d6a0b31b13dc..6ecc00e130ff 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1691,6 +1691,7 @@ config BPF_SYSCALL bool "Enable bpf() system call" select BPF select IRQ_WORK + select TASKS_TRACE_RCU default n help Enable the bpf() system call that allows to manipulate eBPF @@ -1710,6 +1711,8 @@ config BPF_JIT_DEFAULT_ON def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON depends on HAVE_EBPF_JIT && BPF_JIT +source "kernel/bpf/preload/Kconfig" + config USERFAULTFD bool "Enable userfaultfd() system call" depends on MMU diff --git a/init/initramfs.c b/init/initramfs.c index e6dbfb767057..1f97c0328a7a 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -297,7 +297,7 @@ static void __init clean_path(char *path, umode_t fmode) { struct kstat st; - if (init_stat(path, &st, AT_SYMLINK_NOFOLLOW) && + if (!init_stat(path, &st, AT_SYMLINK_NOFOLLOW) && (st.mode ^ fmode) & S_IFMT) { if (S_ISDIR(st.mode)) init_rmdir(path); diff --git a/ipc/sem.c b/ipc/sem.c index 8c0244e0365e..f6c30a85dadf 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1691,7 +1691,7 @@ static long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg, int v case IPC_SET: if (copy_semid_from_user(&semid64, p, version)) return -EFAULT; - /* fall through */ + fallthrough; case IPC_RMID: return semctl_down(ns, semid, cmd, &semid64); default: @@ -1805,7 +1805,7 @@ static long compat_ksys_semctl(int semid, int semnum, int cmd, int arg, int vers case IPC_SET: if (copy_compat_semid_from_user(&semid64, p, version)) return -EFAULT; - /* fallthru */ + fallthrough; case IPC_RMID: return semctl_down(ns, semid, cmd, &semid64); default: diff --git a/ipc/shm.c b/ipc/shm.c index f1ed36e3ac9f..e25c7c6106bc 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1179,7 +1179,7 @@ static long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf, int ver case IPC_SET: if (copy_shmid_from_user(&sem64, buf, version)) return -EFAULT; - /* fallthru */ + fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: @@ -1374,7 +1374,7 @@ static long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int versio case IPC_SET: if (copy_compat_shmid_from_user(&sem64, uptr, version)) return -EFAULT; - /* fallthru */ + fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: diff --git a/kernel/Makefile b/kernel/Makefile index 9a20016d4900..22b0760660fc 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -12,7 +12,7 @@ obj-y = fork.o exec_domain.o panic.o \ notifier.o ksysfs.o cred.o reboot.o \ async.o range.o smpboot.o ucount.o regset.o -obj-$(CONFIG_BPFILTER) += usermode_driver.o +obj-$(CONFIG_USERMODE_DRIVER) += usermode_driver.o obj-$(CONFIG_MODULES) += kmod.o obj-$(CONFIG_MULTIUSER) += groups.o diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index a10e2997aa6c..333b3bcfc545 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -681,7 +681,7 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) data->values[i] = AUDIT_UID_UNSET; break; } - /* fall through - if set */ + fallthrough; /* if set */ default: data->values[i] = f->val; } diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index e6eb9c0402da..bdc8cd1b6767 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -5,6 +5,7 @@ CFLAGS_core.o += $(call cc-disable-warning, override-init) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o +obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o @@ -12,6 +13,7 @@ obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o +obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o obj-$(CONFIG_BPF_SYSCALL) += offload.o obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o endif @@ -29,3 +31,4 @@ ifeq ($(CONFIG_BPF_JIT),y) obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o obj-${CONFIG_BPF_LSM} += bpf_lsm.o endif +obj-$(CONFIG_BPF_PRELOAD) += preload/ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 8ff419b632a6..e046fb7d17cd 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -10,6 +10,7 @@ #include <linux/filter.h> #include <linux/perf_event.h> #include <uapi/linux/btf.h> +#include <linux/rcupdate_trace.h> #include "map_in_map.h" @@ -487,6 +488,13 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) vma->vm_pgoff + pgoff); } +static bool array_map_meta_equal(const struct bpf_map *meta0, + const struct bpf_map *meta1) +{ + return meta0->max_entries == meta1->max_entries && + bpf_map_meta_equal(meta0, meta1); +} + struct bpf_iter_seq_array_map_info { struct bpf_map *map; void *percpu_value_buf; @@ -625,6 +633,7 @@ static const struct bpf_iter_seq_info iter_seq_info = { static int array_map_btf_id; const struct bpf_map_ops array_map_ops = { + .map_meta_equal = array_map_meta_equal, .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = array_map_free, @@ -647,6 +656,7 @@ const struct bpf_map_ops array_map_ops = { static int percpu_array_map_btf_id; const struct bpf_map_ops percpu_array_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = array_map_free, @@ -1003,6 +1013,11 @@ static void prog_array_map_free(struct bpf_map *map) fd_array_map_free(map); } +/* prog_array->aux->{type,jited} is a runtime binding. + * Doing static check alone in the verifier is not enough. + * Thus, prog_array_map cannot be used as an inner_map + * and map_meta_equal is not implemented. + */ static int prog_array_map_btf_id; const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, @@ -1101,6 +1116,7 @@ static void perf_event_fd_array_release(struct bpf_map *map, static int perf_event_array_map_btf_id; const struct bpf_map_ops perf_event_array_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = fd_array_map_free, @@ -1137,6 +1153,7 @@ static void cgroup_fd_array_free(struct bpf_map *map) static int cgroup_array_map_btf_id; const struct bpf_map_ops cgroup_array_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = cgroup_fd_array_free, diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c new file mode 100644 index 000000000000..75be02799c0f --- /dev/null +++ b/kernel/bpf/bpf_inode_storage.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019 Facebook + * Copyright 2020 Google LLC. + */ + +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/bpf.h> +#include <linux/bpf_local_storage.h> +#include <net/sock.h> +#include <uapi/linux/sock_diag.h> +#include <uapi/linux/btf.h> +#include <linux/bpf_lsm.h> +#include <linux/btf_ids.h> +#include <linux/fdtable.h> + +DEFINE_BPF_STORAGE_CACHE(inode_cache); + +static struct bpf_local_storage __rcu ** +inode_storage_ptr(void *owner) +{ + struct inode *inode = owner; + struct bpf_storage_blob *bsb; + + bsb = bpf_inode(inode); + if (!bsb) + return NULL; + return &bsb->storage; +} + +static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, + struct bpf_map *map, + bool cacheit_lockit) +{ + struct bpf_local_storage *inode_storage; + struct bpf_local_storage_map *smap; + struct bpf_storage_blob *bsb; + + bsb = bpf_inode(inode); + if (!bsb) + return NULL; + + inode_storage = rcu_dereference(bsb->storage); + if (!inode_storage) + return NULL; + + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(inode_storage, smap, cacheit_lockit); +} + +void bpf_inode_storage_free(struct inode *inode) +{ + struct bpf_local_storage_elem *selem; + struct bpf_local_storage *local_storage; + bool free_inode_storage = false; + struct bpf_storage_blob *bsb; + struct hlist_node *n; + + bsb = bpf_inode(inode); + if (!bsb) + return; + + rcu_read_lock(); + + local_storage = rcu_dereference(bsb->storage); + if (!local_storage) { + rcu_read_unlock(); + return; + } + + /* Netiher the bpf_prog nor the bpf-map's syscall + * could be modifying the local_storage->list now. + * Thus, no elem can be added-to or deleted-from the + * local_storage->list by the bpf_prog or by the bpf-map's syscall. + * + * It is racing with bpf_local_storage_map_free() alone + * when unlinking elem from the local_storage->list and + * the map's bucket->list. + */ + raw_spin_lock_bh(&local_storage->lock); + hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { + /* Always unlink from map before unlinking from + * local_storage. + */ + bpf_selem_unlink_map(selem); + free_inode_storage = bpf_selem_unlink_storage_nolock( + local_storage, selem, false); + } + raw_spin_unlock_bh(&local_storage->lock); + rcu_read_unlock(); + + /* free_inoode_storage should always be true as long as + * local_storage->list was non-empty. + */ + if (free_inode_storage) + kfree_rcu(local_storage, rcu); +} + +static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_local_storage_data *sdata; + struct file *f; + int fd; + + fd = *(int *)key; + f = fget_raw(fd); + if (!f) + return NULL; + + sdata = inode_storage_lookup(f->f_inode, map, true); + fput(f); + return sdata ? sdata->data : NULL; +} + +static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct bpf_local_storage_data *sdata; + struct file *f; + int fd; + + fd = *(int *)key; + f = fget_raw(fd); + if (!f || !inode_storage_ptr(f->f_inode)) + return -EBADF; + + sdata = bpf_local_storage_update(f->f_inode, + (struct bpf_local_storage_map *)map, + value, map_flags); + fput(f); + return PTR_ERR_OR_ZERO(sdata); +} + +static int inode_storage_delete(struct inode *inode, struct bpf_map *map) +{ + struct bpf_local_storage_data *sdata; + + sdata = inode_storage_lookup(inode, map, false); + if (!sdata) + return -ENOENT; + + bpf_selem_unlink(SELEM(sdata)); + + return 0; +} + +static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) +{ + struct file *f; + int fd, err; + + fd = *(int *)key; + f = fget_raw(fd); + if (!f) + return -EBADF; + + err = inode_storage_delete(f->f_inode, map); + fput(f); + return err; +} + +BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, + void *, value, u64, flags) +{ + struct bpf_local_storage_data *sdata; + + if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) + return (unsigned long)NULL; + + /* explicitly check that the inode_storage_ptr is not + * NULL as inode_storage_lookup returns NULL in this case and + * bpf_local_storage_update expects the owner to have a + * valid storage pointer. + */ + if (!inode_storage_ptr(inode)) + return (unsigned long)NULL; + + sdata = inode_storage_lookup(inode, map, true); + if (sdata) + return (unsigned long)sdata->data; + + /* This helper must only called from where the inode is gurranteed + * to have a refcount and cannot be freed. + */ + if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { + sdata = bpf_local_storage_update( + inode, (struct bpf_local_storage_map *)map, value, + BPF_NOEXIST); + return IS_ERR(sdata) ? (unsigned long)NULL : + (unsigned long)sdata->data; + } + + return (unsigned long)NULL; +} + +BPF_CALL_2(bpf_inode_storage_delete, + struct bpf_map *, map, struct inode *, inode) +{ + /* This helper must only called from where the inode is gurranteed + * to have a refcount and cannot be freed. + */ + return inode_storage_delete(inode, map); +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -ENOTSUPP; +} + +static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr) +{ + struct bpf_local_storage_map *smap; + + smap = bpf_local_storage_map_alloc(attr); + if (IS_ERR(smap)) + return ERR_CAST(smap); + + smap->cache_idx = bpf_local_storage_cache_idx_get(&inode_cache); + return &smap->map; +} + +static void inode_storage_map_free(struct bpf_map *map) +{ + struct bpf_local_storage_map *smap; + + smap = (struct bpf_local_storage_map *)map; + bpf_local_storage_cache_idx_free(&inode_cache, smap->cache_idx); + bpf_local_storage_map_free(smap); +} + +static int inode_storage_map_btf_id; +const struct bpf_map_ops inode_storage_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = inode_storage_map_alloc, + .map_free = inode_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_fd_inode_storage_lookup_elem, + .map_update_elem = bpf_fd_inode_storage_update_elem, + .map_delete_elem = bpf_fd_inode_storage_delete_elem, + .map_check_btf = bpf_local_storage_map_check_btf, + .map_btf_name = "bpf_local_storage_map", + .map_btf_id = &inode_storage_map_btf_id, + .map_owner_storage_ptr = inode_storage_ptr, +}; + +BTF_ID_LIST(bpf_inode_storage_btf_ids) +BTF_ID_UNUSED +BTF_ID(struct, inode) + +const struct bpf_func_proto bpf_inode_storage_get_proto = { + .func = bpf_inode_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, + .btf_id = bpf_inode_storage_btf_ids, +}; + +const struct bpf_func_proto bpf_inode_storage_delete_proto = { + .func = bpf_inode_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .btf_id = bpf_inode_storage_btf_ids, +}; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index b6715964b685..30833bbf3019 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -67,6 +67,9 @@ static void bpf_iter_done_stop(struct seq_file *seq) iter_priv->done_stop = true; } +/* maximum visited objects before bailing out */ +#define MAX_ITER_OBJECTS 1000000 + /* bpf_seq_read, a customized and simpler version for bpf iterator. * no_llseek is assumed for this file. * The following are differences from seq_read(): @@ -79,7 +82,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, { struct seq_file *seq = file->private_data; size_t n, offs, copied = 0; - int err = 0; + int err = 0, num_objs = 0; void *p; mutex_lock(&seq->lock); @@ -135,6 +138,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, while (1) { loff_t pos = seq->index; + num_objs++; offs = seq->count; p = seq->op->next(seq, p, &seq->index); if (pos == seq->index) { @@ -153,6 +157,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, if (seq->count >= size) break; + if (num_objs >= MAX_ITER_OBJECTS) { + if (offs == 0) { + err = -EAGAIN; + seq->op->stop(seq, p); + goto done; + } + break; + } + err = seq->op->show(seq, p); if (err > 0) { bpf_iter_dec_seq_num(seq); @@ -377,10 +390,68 @@ out_unlock: return ret; } +static void bpf_iter_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_iter_link *iter_link = + container_of(link, struct bpf_iter_link, link); + bpf_iter_show_fdinfo_t show_fdinfo; + + seq_printf(seq, + "target_name:\t%s\n", + iter_link->tinfo->reg_info->target); + + show_fdinfo = iter_link->tinfo->reg_info->show_fdinfo; + if (show_fdinfo) + show_fdinfo(&iter_link->aux, seq); +} + +static int bpf_iter_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_iter_link *iter_link = + container_of(link, struct bpf_iter_link, link); + char __user *ubuf = u64_to_user_ptr(info->iter.target_name); + bpf_iter_fill_link_info_t fill_link_info; + u32 ulen = info->iter.target_name_len; + const char *target_name; + u32 target_len; + + if (!ulen ^ !ubuf) + return -EINVAL; + + target_name = iter_link->tinfo->reg_info->target; + target_len = strlen(target_name); + info->iter.target_name_len = target_len + 1; + + if (ubuf) { + if (ulen >= target_len + 1) { + if (copy_to_user(ubuf, target_name, target_len + 1)) + return -EFAULT; + } else { + char zero = '\0'; + + if (copy_to_user(ubuf, target_name, ulen - 1)) + return -EFAULT; + if (put_user(zero, ubuf + ulen - 1)) + return -EFAULT; + return -ENOSPC; + } + } + + fill_link_info = iter_link->tinfo->reg_info->fill_link_info; + if (fill_link_info) + return fill_link_info(&iter_link->aux, info); + + return 0; +} + static const struct bpf_link_ops bpf_iter_link_lops = { .release = bpf_iter_link_release, .dealloc = bpf_iter_link_dealloc, .update_prog = bpf_iter_link_replace, + .show_fdinfo = bpf_iter_link_show_fdinfo, + .fill_link_info = bpf_iter_link_fill_link_info, }; bool bpf_link_is_iter(struct bpf_link *link) diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c new file mode 100644 index 000000000000..ffa7d11fc2bd --- /dev/null +++ b/kernel/bpf/bpf_local_storage.c @@ -0,0 +1,600 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/bpf.h> +#include <linux/btf_ids.h> +#include <linux/bpf_local_storage.h> +#include <net/sock.h> +#include <uapi/linux/sock_diag.h> +#include <uapi/linux/btf.h> + +#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) + +static struct bpf_local_storage_map_bucket * +select_bucket(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) +{ + return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; +} + +static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) +{ + struct bpf_map *map = &smap->map; + + if (!map->ops->map_local_storage_charge) + return 0; + + return map->ops->map_local_storage_charge(smap, owner, size); +} + +static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, + u32 size) +{ + struct bpf_map *map = &smap->map; + + if (map->ops->map_local_storage_uncharge) + map->ops->map_local_storage_uncharge(smap, owner, size); +} + +static struct bpf_local_storage __rcu ** +owner_storage(struct bpf_local_storage_map *smap, void *owner) +{ + struct bpf_map *map = &smap->map; + + return map->ops->map_owner_storage_ptr(owner); +} + +static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed(&selem->snode); +} + +static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed(&selem->map_node); +} + +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, + void *value, bool charge_mem) +{ + struct bpf_local_storage_elem *selem; + + if (charge_mem && mem_charge(smap, owner, smap->elem_size)) + return NULL; + + selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (selem) { + if (value) + memcpy(SDATA(selem)->data, value, smap->map.value_size); + return selem; + } + + if (charge_mem) + mem_uncharge(smap, owner, smap->elem_size); + + return NULL; +} + +/* local_storage->lock must be held and selem->local_storage == local_storage. + * The caller must ensure selem->smap is still valid to be + * dereferenced for its smap->elem_size and smap->cache_idx. + */ +bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_mem) +{ + struct bpf_local_storage_map *smap; + bool free_local_storage; + void *owner; + + smap = rcu_dereference(SDATA(selem)->smap); + owner = local_storage->owner; + + /* All uncharging on the owner must be done first. + * The owner may be freed once the last selem is unlinked + * from local_storage. + */ + if (uncharge_mem) + mem_uncharge(smap, owner, smap->elem_size); + + free_local_storage = hlist_is_singular_node(&selem->snode, + &local_storage->list); + if (free_local_storage) { + mem_uncharge(smap, owner, sizeof(struct bpf_local_storage)); + local_storage->owner = NULL; + + /* After this RCU_INIT, owner may be freed and cannot be used */ + RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); + + /* local_storage is not freed now. local_storage->lock is + * still held and raw_spin_unlock_bh(&local_storage->lock) + * will be done by the caller. + * + * Although the unlock will be done under + * rcu_read_lock(), it is more intutivie to + * read if kfree_rcu(local_storage, rcu) is done + * after the raw_spin_unlock_bh(&local_storage->lock). + * + * Hence, a "bool free_local_storage" is returned + * to the caller which then calls the kfree_rcu() + * after unlock. + */ + } + hlist_del_init_rcu(&selem->snode); + if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == + SDATA(selem)) + RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); + + kfree_rcu(selem, rcu); + + return free_local_storage; +} + +static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) +{ + struct bpf_local_storage *local_storage; + bool free_local_storage = false; + + if (unlikely(!selem_linked_to_storage(selem))) + /* selem has already been unlinked from sk */ + return; + + local_storage = rcu_dereference(selem->local_storage); + raw_spin_lock_bh(&local_storage->lock); + if (likely(selem_linked_to_storage(selem))) + free_local_storage = bpf_selem_unlink_storage_nolock( + local_storage, selem, true); + raw_spin_unlock_bh(&local_storage->lock); + + if (free_local_storage) + kfree_rcu(local_storage, rcu); +} + +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem) +{ + RCU_INIT_POINTER(selem->local_storage, local_storage); + hlist_add_head(&selem->snode, &local_storage->list); +} + +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) +{ + struct bpf_local_storage_map *smap; + struct bpf_local_storage_map_bucket *b; + + if (unlikely(!selem_linked_to_map(selem))) + /* selem has already be unlinked from smap */ + return; + + smap = rcu_dereference(SDATA(selem)->smap); + b = select_bucket(smap, selem); + raw_spin_lock_bh(&b->lock); + if (likely(selem_linked_to_map(selem))) + hlist_del_init_rcu(&selem->map_node); + raw_spin_unlock_bh(&b->lock); +} + +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) +{ + struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem); + + raw_spin_lock_bh(&b->lock); + RCU_INIT_POINTER(SDATA(selem)->smap, smap); + hlist_add_head_rcu(&selem->map_node, &b->list); + raw_spin_unlock_bh(&b->lock); +} + +void bpf_selem_unlink(struct bpf_local_storage_elem *selem) +{ + /* Always unlink from map before unlinking from local_storage + * because selem will be freed after successfully unlinked from + * the local_storage. + */ + bpf_selem_unlink_map(selem); + __bpf_selem_unlink_storage(selem); +} + +struct bpf_local_storage_data * +bpf_local_storage_lookup(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool cacheit_lockit) +{ + struct bpf_local_storage_data *sdata; + struct bpf_local_storage_elem *selem; + + /* Fast path (cache hit) */ + sdata = rcu_dereference(local_storage->cache[smap->cache_idx]); + if (sdata && rcu_access_pointer(sdata->smap) == smap) + return sdata; + + /* Slow path (cache miss) */ + hlist_for_each_entry_rcu(selem, &local_storage->list, snode) + if (rcu_access_pointer(SDATA(selem)->smap) == smap) + break; + + if (!selem) + return NULL; + + sdata = SDATA(selem); + if (cacheit_lockit) { + /* spinlock is needed to avoid racing with the + * parallel delete. Otherwise, publishing an already + * deleted sdata to the cache will become a use-after-free + * problem in the next bpf_local_storage_lookup(). + */ + raw_spin_lock_bh(&local_storage->lock); + if (selem_linked_to_storage(selem)) + rcu_assign_pointer(local_storage->cache[smap->cache_idx], + sdata); + raw_spin_unlock_bh(&local_storage->lock); + } + + return sdata; +} + +static int check_flags(const struct bpf_local_storage_data *old_sdata, + u64 map_flags) +{ + if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) + /* elem already exists */ + return -EEXIST; + + if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) + /* elem doesn't exist, cannot update it */ + return -ENOENT; + + return 0; +} + +int bpf_local_storage_alloc(void *owner, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem) +{ + struct bpf_local_storage *prev_storage, *storage; + struct bpf_local_storage **owner_storage_ptr; + int err; + + err = mem_charge(smap, owner, sizeof(*storage)); + if (err) + return err; + + storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN); + if (!storage) { + err = -ENOMEM; + goto uncharge; + } + + INIT_HLIST_HEAD(&storage->list); + raw_spin_lock_init(&storage->lock); + storage->owner = owner; + + bpf_selem_link_storage_nolock(storage, first_selem); + bpf_selem_link_map(smap, first_selem); + + owner_storage_ptr = + (struct bpf_local_storage **)owner_storage(smap, owner); + /* Publish storage to the owner. + * Instead of using any lock of the kernel object (i.e. owner), + * cmpxchg will work with any kernel object regardless what + * the running context is, bh, irq...etc. + * + * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) + * is protected by the storage->lock. Hence, when freeing + * the owner->storage, the storage->lock must be held before + * setting owner->storage ptr to NULL. + */ + prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); + if (unlikely(prev_storage)) { + bpf_selem_unlink_map(first_selem); + err = -EAGAIN; + goto uncharge; + + /* Note that even first_selem was linked to smap's + * bucket->list, first_selem can be freed immediately + * (instead of kfree_rcu) because + * bpf_local_storage_map_free() does a + * synchronize_rcu() before walking the bucket->list. + * Hence, no one is accessing selem from the + * bucket->list under rcu_read_lock(). + */ + } + + return 0; + +uncharge: + kfree(storage); + mem_uncharge(smap, owner, sizeof(*storage)); + return err; +} + +/* sk cannot be going away because it is linking new elem + * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). + * Otherwise, it will become a leak (and other memory issues + * during map destruction). + */ +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + void *value, u64 map_flags) +{ + struct bpf_local_storage_data *old_sdata = NULL; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage *local_storage; + int err; + + /* BPF_EXIST and BPF_NOEXIST cannot be both set */ + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || + /* BPF_F_LOCK can only be used in a value with spin_lock */ + unlikely((map_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(&smap->map))) + return ERR_PTR(-EINVAL); + + local_storage = rcu_dereference(*owner_storage(smap, owner)); + if (!local_storage || hlist_empty(&local_storage->list)) { + /* Very first elem for the owner */ + err = check_flags(NULL, map_flags); + if (err) + return ERR_PTR(err); + + selem = bpf_selem_alloc(smap, owner, value, true); + if (!selem) + return ERR_PTR(-ENOMEM); + + err = bpf_local_storage_alloc(owner, smap, selem); + if (err) { + kfree(selem); + mem_uncharge(smap, owner, smap->elem_size); + return ERR_PTR(err); + } + + return SDATA(selem); + } + + if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { + /* Hoping to find an old_sdata to do inline update + * such that it can avoid taking the local_storage->lock + * and changing the lists. + */ + old_sdata = + bpf_local_storage_lookup(local_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + return ERR_PTR(err); + if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) { + copy_map_value_locked(&smap->map, old_sdata->data, + value, false); + return old_sdata; + } + } + + raw_spin_lock_bh(&local_storage->lock); + + /* Recheck local_storage->list under local_storage->lock */ + if (unlikely(hlist_empty(&local_storage->list))) { + /* A parallel del is happening and local_storage is going + * away. It has just been checked before, so very + * unlikely. Return instead of retry to keep things + * simple. + */ + err = -EAGAIN; + goto unlock_err; + } + + old_sdata = bpf_local_storage_lookup(local_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + goto unlock_err; + + if (old_sdata && (map_flags & BPF_F_LOCK)) { + copy_map_value_locked(&smap->map, old_sdata->data, value, + false); + selem = SELEM(old_sdata); + goto unlock; + } + + /* local_storage->lock is held. Hence, we are sure + * we can unlink and uncharge the old_sdata successfully + * later. Hence, instead of charging the new selem now + * and then uncharge the old selem later (which may cause + * a potential but unnecessary charge failure), avoid taking + * a charge at all here (the "!old_sdata" check) and the + * old_sdata will not be uncharged later during + * bpf_selem_unlink_storage_nolock(). + */ + selem = bpf_selem_alloc(smap, owner, value, !old_sdata); + if (!selem) { + err = -ENOMEM; + goto unlock_err; + } + + /* First, link the new selem to the map */ + bpf_selem_link_map(smap, selem); + + /* Second, link (and publish) the new selem to local_storage */ + bpf_selem_link_storage_nolock(local_storage, selem); + + /* Third, remove old selem, SELEM(old_sdata) */ + if (old_sdata) { + bpf_selem_unlink_map(SELEM(old_sdata)); + bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), + false); + } + +unlock: + raw_spin_unlock_bh(&local_storage->lock); + return SDATA(selem); + +unlock_err: + raw_spin_unlock_bh(&local_storage->lock); + return ERR_PTR(err); +} + +u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) +{ + u64 min_usage = U64_MAX; + u16 i, res = 0; + + spin_lock(&cache->idx_lock); + + for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { + if (cache->idx_usage_counts[i] < min_usage) { + min_usage = cache->idx_usage_counts[i]; + res = i; + + /* Found a free cache_idx */ + if (!min_usage) + break; + } + } + cache->idx_usage_counts[res]++; + + spin_unlock(&cache->idx_lock); + + return res; +} + +void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx) +{ + spin_lock(&cache->idx_lock); + cache->idx_usage_counts[idx]--; + spin_unlock(&cache->idx_lock); +} + +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap) +{ + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map_bucket *b; + unsigned int i; + + /* Note that this map might be concurrently cloned from + * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone + * RCU read section to finish before proceeding. New RCU + * read sections should be prevented via bpf_map_inc_not_zero. + */ + synchronize_rcu(); + + /* bpf prog and the userspace can no longer access this map + * now. No new selem (of this map) can be added + * to the owner->storage or to the map bucket's list. + * + * The elem of this map can be cleaned up here + * or when the storage is freed e.g. + * by bpf_sk_storage_free() during __sk_destruct(). + */ + for (i = 0; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + + rcu_read_lock(); + /* No one is adding to b->list now */ + while ((selem = hlist_entry_safe( + rcu_dereference_raw(hlist_first_rcu(&b->list)), + struct bpf_local_storage_elem, map_node))) { + bpf_selem_unlink(selem); + cond_resched_rcu(); + } + rcu_read_unlock(); + } + + /* While freeing the storage we may still need to access the map. + * + * e.g. when bpf_sk_storage_free() has unlinked selem from the map + * which then made the above while((selem = ...)) loop + * exit immediately. + * + * However, while freeing the storage one still needs to access the + * smap->elem_size to do the uncharging in + * bpf_selem_unlink_storage_nolock(). + * + * Hence, wait another rcu grace period for the storage to be freed. + */ + synchronize_rcu(); + + kvfree(smap->buckets); + kfree(smap); +} + +int bpf_local_storage_map_alloc_check(union bpf_attr *attr) +{ + if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || + !(attr->map_flags & BPF_F_NO_PREALLOC) || + attr->max_entries || + attr->key_size != sizeof(int) || !attr->value_size || + /* Enforce BTF for userspace sk dumping */ + !attr->btf_key_type_id || !attr->btf_value_type_id) + return -EINVAL; + + if (!bpf_capable()) + return -EPERM; + + if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) + return -E2BIG; + + return 0; +} + +struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) +{ + struct bpf_local_storage_map *smap; + unsigned int i; + u32 nbuckets; + u64 cost; + int ret; + + smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); + if (!smap) + return ERR_PTR(-ENOMEM); + bpf_map_init_from_attr(&smap->map, attr); + + nbuckets = roundup_pow_of_two(num_possible_cpus()); + /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ + nbuckets = max_t(u32, 2, nbuckets); + smap->bucket_log = ilog2(nbuckets); + cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); + + ret = bpf_map_charge_init(&smap->map.memory, cost); + if (ret < 0) { + kfree(smap); + return ERR_PTR(ret); + } + + smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, + GFP_USER | __GFP_NOWARN); + if (!smap->buckets) { + bpf_map_charge_finish(&smap->map.memory); + kfree(smap); + return ERR_PTR(-ENOMEM); + } + + for (i = 0; i < nbuckets; i++) { + INIT_HLIST_HEAD(&smap->buckets[i].list); + raw_spin_lock_init(&smap->buckets[i].lock); + } + + smap->elem_size = + sizeof(struct bpf_local_storage_elem) + attr->value_size; + + return smap; +} + +int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + u32 int_data; + + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; + + int_data = *(u32 *)(key_type + 1); + if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) + return -EINVAL; + + return 0; +} diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index fb278144e9fd..9cd1428c7199 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -11,6 +11,8 @@ #include <linux/bpf_lsm.h> #include <linux/kallsyms.h> #include <linux/bpf_verifier.h> +#include <net/bpf_sk_storage.h> +#include <linux/bpf_local_storage.h> /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -45,10 +47,27 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return 0; } +static const struct bpf_func_proto * +bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_inode_storage_get: + return &bpf_inode_storage_get_proto; + case BPF_FUNC_inode_storage_delete: + return &bpf_inode_storage_delete_proto; + case BPF_FUNC_sk_storage_get: + return &sk_storage_get_btf_proto; + case BPF_FUNC_sk_storage_delete: + return &sk_storage_delete_btf_proto; + default: + return tracing_prog_func_proto(func_id, prog); + } +} + const struct bpf_prog_ops lsm_prog_ops = { }; const struct bpf_verifier_ops lsm_verifier_ops = { - .get_func_proto = tracing_prog_func_proto, + .get_func_proto = bpf_lsm_func_proto, .is_valid_access = btf_ctx_access, }; diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 969c5d47f81f..4c3b543bb33b 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -298,8 +298,7 @@ static int check_zero_holes(const struct btf_type *t, void *data) return -EINVAL; mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize, - NULL, NULL); + mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); if (IS_ERR(mtype)) return PTR_ERR(mtype); prev_mend = moff + msize; @@ -396,8 +395,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, u32 msize; mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize, - NULL, NULL); + mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); if (IS_ERR(mtype)) { err = PTR_ERR(mtype); goto reset_unlock; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 91afdd4c82e3..f9ac6935ab3c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -21,6 +21,8 @@ #include <linux/btf_ids.h> #include <linux/skmsg.h> #include <linux/perf_event.h> +#include <linux/bsearch.h> +#include <linux/btf_ids.h> #include <net/sock.h> /* BTF (BPF Type Format) is the meta data format which describes @@ -1079,23 +1081,27 @@ static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env) * *type_size: (x * y * sizeof(u32)). Hence, *type_size always * corresponds to the return type. * *elem_type: u32 + * *elem_id: id of u32 * *total_nelems: (x * y). Hence, individual elem size is * (*type_size / *total_nelems) + * *type_id: id of type if it's changed within the function, 0 if not * * type: is not an array (e.g. const struct X) * return type: type "struct X" * *type_size: sizeof(struct X) * *elem_type: same as return type ("struct X") + * *elem_id: 0 * *total_nelems: 1 + * *type_id: id of type if it's changed within the function, 0 if not */ -const struct btf_type * -btf_resolve_size(const struct btf *btf, const struct btf_type *type, - u32 *type_size, const struct btf_type **elem_type, - u32 *total_nelems) +static const struct btf_type * +__btf_resolve_size(const struct btf *btf, const struct btf_type *type, + u32 *type_size, const struct btf_type **elem_type, + u32 *elem_id, u32 *total_nelems, u32 *type_id) { const struct btf_type *array_type = NULL; - const struct btf_array *array; - u32 i, size, nelems = 1; + const struct btf_array *array = NULL; + u32 i, size, nelems = 1, id = 0; for (i = 0; i < MAX_RESOLVE_DEPTH; i++) { switch (BTF_INFO_KIND(type->info)) { @@ -1116,6 +1122,7 @@ btf_resolve_size(const struct btf *btf, const struct btf_type *type, case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + id = type->type; type = btf_type_by_id(btf, type->type); break; @@ -1146,10 +1153,21 @@ resolved: *total_nelems = nelems; if (elem_type) *elem_type = type; + if (elem_id) + *elem_id = array ? array->type : 0; + if (type_id && id) + *type_id = id; return array_type ? : type; } +const struct btf_type * +btf_resolve_size(const struct btf *btf, const struct btf_type *type, + u32 *type_size) +{ + return __btf_resolve_size(btf, type, type_size, NULL, NULL, NULL, NULL); +} + /* The input param "type_id" must point to a needs_resolve type */ static const struct btf_type *btf_type_id_resolve(const struct btf *btf, u32 *type_id) @@ -3870,16 +3888,22 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return true; } -int btf_struct_access(struct bpf_verifier_log *log, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, - u32 *next_btf_id) +enum bpf_struct_walk_result { + /* < 0 error */ + WALK_SCALAR = 0, + WALK_PTR, + WALK_STRUCT, +}; + +static int btf_struct_walk(struct bpf_verifier_log *log, + const struct btf_type *t, int off, int size, + u32 *next_btf_id) { u32 i, moff, mtrue_end, msize = 0, total_nelems = 0; const struct btf_type *mtype, *elem_type = NULL; const struct btf_member *member; const char *tname, *mname; - u32 vlen; + u32 vlen, elem_id, mid; again: tname = __btf_name_by_offset(btf_vmlinux, t->name_off); @@ -3915,14 +3939,13 @@ again: /* Only allow structure for now, can be relaxed for * other types later. */ - elem_type = btf_type_skip_modifiers(btf_vmlinux, - array_elem->type, NULL); - if (!btf_type_is_struct(elem_type)) + t = btf_type_skip_modifiers(btf_vmlinux, array_elem->type, + NULL); + if (!btf_type_is_struct(t)) goto error; - off = (off - moff) % elem_type->size; - return btf_struct_access(log, elem_type, off, size, atype, - next_btf_id); + off = (off - moff) % t->size; + goto again; error: bpf_log(log, "access beyond struct %s at off %u size %u\n", @@ -3951,7 +3974,7 @@ error: */ if (off <= moff && BITS_ROUNDUP_BYTES(end_bit) <= off + size) - return SCALAR_VALUE; + return WALK_SCALAR; /* off may be accessing a following member * @@ -3973,11 +3996,13 @@ error: break; /* type of the field */ + mid = member->type; mtype = btf_type_by_id(btf_vmlinux, member->type); mname = __btf_name_by_offset(btf_vmlinux, member->name_off); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize, - &elem_type, &total_nelems); + mtype = __btf_resolve_size(btf_vmlinux, mtype, &msize, + &elem_type, &elem_id, &total_nelems, + &mid); if (IS_ERR(mtype)) { bpf_log(log, "field %s doesn't have size\n", mname); return -EFAULT; @@ -3991,7 +4016,7 @@ error: if (btf_type_is_array(mtype)) { u32 elem_idx; - /* btf_resolve_size() above helps to + /* __btf_resolve_size() above helps to * linearize a multi-dimensional array. * * The logic here is treating an array @@ -4039,6 +4064,7 @@ error: elem_idx = (off - moff) / msize; moff += elem_idx * msize; mtype = elem_type; + mid = elem_id; } /* the 'off' we're looking for is either equal to start @@ -4048,6 +4074,12 @@ error: /* our field must be inside that union or struct */ t = mtype; + /* return if the offset matches the member offset */ + if (off == moff) { + *next_btf_id = mid; + return WALK_STRUCT; + } + /* adjust offset we're looking for */ off -= moff; goto again; @@ -4063,11 +4095,10 @@ error: mname, moff, tname, off, size); return -EACCES; } - stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id); if (btf_type_is_struct(stype)) { *next_btf_id = id; - return PTR_TO_BTF_ID; + return WALK_PTR; } } @@ -4084,12 +4115,84 @@ error: return -EACCES; } - return SCALAR_VALUE; + return WALK_SCALAR; } bpf_log(log, "struct %s doesn't have field at offset %d\n", tname, off); return -EINVAL; } +int btf_struct_access(struct bpf_verifier_log *log, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype __maybe_unused, + u32 *next_btf_id) +{ + int err; + u32 id; + + do { + err = btf_struct_walk(log, t, off, size, &id); + + switch (err) { + case WALK_PTR: + /* If we found the pointer or scalar on t+off, + * we're done. + */ + *next_btf_id = id; + return PTR_TO_BTF_ID; + case WALK_SCALAR: + return SCALAR_VALUE; + case WALK_STRUCT: + /* We found nested struct, so continue the search + * by diving in it. At this point the offset is + * aligned with the new type, so set it to 0. + */ + t = btf_type_by_id(btf_vmlinux, id); + off = 0; + break; + default: + /* It's either error or unknown return value.. + * scream and leave. + */ + if (WARN_ONCE(err > 0, "unknown btf_struct_walk return value")) + return -EINVAL; + return err; + } + } while (t); + + return -EINVAL; +} + +bool btf_struct_ids_match(struct bpf_verifier_log *log, + int off, u32 id, u32 need_type_id) +{ + const struct btf_type *type; + int err; + + /* Are we already done? */ + if (need_type_id == id && off == 0) + return true; + +again: + type = btf_type_by_id(btf_vmlinux, id); + if (!type) + return false; + err = btf_struct_walk(log, type, off, 1, &id); + if (err != WALK_STRUCT) + return false; + + /* We found nested struct object. If it matches + * the requested ID, we're done. Otherwise let's + * continue the search with offset 0 in the new + * type. + */ + if (need_type_id != id) { + off = 0; + goto again; + } + + return true; +} + int btf_resolve_helper_id(struct bpf_verifier_log *log, const struct bpf_func_proto *fn, int arg) { @@ -4661,3 +4764,15 @@ u32 btf_id(const struct btf *btf) { return btf->id; } + +static int btf_id_cmp_func(const void *a, const void *b) +{ + const int *pa = a, *pb = b; + + return *pa - *pb; +} + +bool btf_id_set_contains(struct btf_id_set *set, u32 id) +{ + return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; +} diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 83ff127ef7ae..e21de4f1754c 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1794,7 +1794,7 @@ static bool cg_sockopt_is_valid_access(int off, int size, return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT; case offsetof(struct bpf_sockopt, optname): - /* fallthrough */ + fallthrough; case offsetof(struct bpf_sockopt, level): if (size != size_default) return false; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index f1c46529929b..7e1a8ad0c32a 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -79,8 +79,6 @@ struct bpf_cpu_map { static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list); -static int bq_flush_to_queue(struct xdp_bulk_queue *bq); - static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) { u32 value_size = attr->value_size; @@ -279,7 +277,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, break; default: bpf_warn_invalid_xdp_action(act); - /* fallthrough */ + fallthrough; case XDP_DROP: xdp_return_frame(xdpf); stats->drop++; @@ -658,6 +656,7 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) static int cpu_map_btf_id; const struct bpf_map_ops cpu_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = cpu_map_alloc, .map_free = cpu_map_free, .map_delete_elem = cpu_map_delete_elem, @@ -669,7 +668,7 @@ const struct bpf_map_ops cpu_map_ops = { .map_btf_id = &cpu_map_btf_id, }; -static int bq_flush_to_queue(struct xdp_bulk_queue *bq) +static void bq_flush_to_queue(struct xdp_bulk_queue *bq) { struct bpf_cpu_map_entry *rcpu = bq->obj; unsigned int processed = 0, drops = 0; @@ -678,7 +677,7 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq) int i; if (unlikely(!bq->count)) - return 0; + return; q = rcpu->queue; spin_lock(&q->producer_lock); @@ -701,13 +700,12 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq) /* Feedback loop via tracepoints */ trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu); - return 0; } /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) +static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); @@ -728,8 +726,6 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) if (!bq->flush_node.prev) list_add(&bq->flush_node, flush_list); - - return 0; } int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 10abb06065bb..2b5ca93c17de 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -341,14 +341,14 @@ bool dev_map_can_have_prog(struct bpf_map *map) return false; } -static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) +static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; int sent = 0, drops = 0, err = 0; int i; if (unlikely(!bq->count)) - return 0; + return; for (i = 0; i < bq->count; i++) { struct xdp_frame *xdpf = bq->q[i]; @@ -369,7 +369,7 @@ out: trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err); bq->dev_rx = NULL; __list_del_clearprev(&bq->flush_node); - return 0; + return; error: /* If ndo_xdp_xmit fails with an errno, no frames have been * xmit'ed and it's our responsibility to them free all. @@ -421,8 +421,8 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, - struct net_device *dev_rx) +static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, + struct net_device *dev_rx) { struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); @@ -441,8 +441,6 @@ static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, if (!bq->flush_node.prev) list_add(&bq->flush_node, flush_list); - - return 0; } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, @@ -462,7 +460,8 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, if (unlikely(!xdpf)) return -EOVERFLOW; - return bq_enqueue(dev, xdpf, dev_rx); + bq_enqueue(dev, xdpf, dev_rx); + return 0; } static struct xdp_buff *dev_map_run_prog(struct net_device *dev, @@ -751,6 +750,7 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, static int dev_map_btf_id; const struct bpf_map_ops dev_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, @@ -764,6 +764,7 @@ const struct bpf_map_ops dev_map_ops = { static int dev_map_hash_map_btf_id; const struct bpf_map_ops dev_map_hash_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_hash_get_next_key, diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 78dfff6a501b..fe0e06284d33 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -9,6 +9,7 @@ #include <linux/rculist_nulls.h> #include <linux/random.h> #include <uapi/linux/btf.h> +#include <linux/rcupdate_trace.h> #include "percpu_freelist.h" #include "bpf_lru_list.h" #include "map_in_map.h" @@ -577,8 +578,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) struct htab_elem *l; u32 hash, key_size; - /* Must be called with rcu_read_lock. */ - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); key_size = map->key_size; @@ -941,7 +941,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); key_size = map->key_size; @@ -1032,7 +1032,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); key_size = map->key_size; @@ -1220,7 +1220,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) u32 hash, key_size; int ret = -ENOENT; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); key_size = map->key_size; @@ -1252,7 +1252,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) u32 hash, key_size; int ret = -ENOENT; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); key_size = map->key_size; @@ -1810,6 +1810,7 @@ static const struct bpf_iter_seq_info iter_seq_info = { static int htab_map_btf_id; const struct bpf_map_ops htab_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, @@ -1827,6 +1828,7 @@ const struct bpf_map_ops htab_map_ops = { static int htab_lru_map_btf_id; const struct bpf_map_ops htab_lru_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, @@ -1947,6 +1949,7 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key, static int htab_percpu_map_btf_id; const struct bpf_map_ops htab_percpu_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, @@ -1963,6 +1966,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { static int htab_lru_percpu_map_btf_id; const struct bpf_map_ops htab_lru_percpu_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index be43ab3e619f..5cc7425ee476 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -601,6 +601,28 @@ const struct bpf_func_proto bpf_event_output_data_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +BPF_CALL_3(bpf_copy_from_user, void *, dst, u32, size, + const void __user *, user_ptr) +{ + int ret = copy_from_user(dst, user_ptr, size); + + if (unlikely(ret)) { + memset(dst, 0, size); + ret = -EFAULT; + } + + return ret; +} + +const struct bpf_func_proto bpf_copy_from_user_proto = { + .func = bpf_copy_from_user, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + const struct bpf_func_proto bpf_get_current_task_proto __weak; const struct bpf_func_proto bpf_probe_read_user_proto __weak; const struct bpf_func_proto bpf_probe_read_user_str_proto __weak; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index fb878ba3f22f..b48a56f53495 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -20,6 +20,7 @@ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include "preload/bpf_preload.h" enum bpf_type { BPF_TYPE_UNSPEC = 0, @@ -369,9 +370,10 @@ static struct dentry * bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) { /* Dots in names (e.g. "/sys/fs/bpf/foo.bar") are reserved for future - * extensions. + * extensions. That allows popoulate_bpffs() create special files. */ - if (strchr(dentry->d_name.name, '.')) + if ((dir->i_mode & S_IALLUGO) && + strchr(dentry->d_name.name, '.')) return ERR_PTR(-EPERM); return simple_lookup(dir, dentry, flags); @@ -409,6 +411,27 @@ static const struct inode_operations bpf_dir_iops = { .unlink = simple_unlink, }; +/* pin iterator link into bpffs */ +static int bpf_iter_link_pin_kernel(struct dentry *parent, + const char *name, struct bpf_link *link) +{ + umode_t mode = S_IFREG | S_IRUSR; + struct dentry *dentry; + int ret; + + inode_lock(parent->d_inode); + dentry = lookup_one_len(name, parent, strlen(name)); + if (IS_ERR(dentry)) { + inode_unlock(parent->d_inode); + return PTR_ERR(dentry); + } + ret = bpf_mkobj_ops(dentry, mode, link, &bpf_link_iops, + &bpf_iter_fops); + dput(dentry); + inode_unlock(parent->d_inode); + return ret; +} + static int bpf_obj_do_pin(const char __user *pathname, void *raw, enum bpf_type type) { @@ -638,6 +661,91 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) return 0; } +struct bpf_preload_ops *bpf_preload_ops; +EXPORT_SYMBOL_GPL(bpf_preload_ops); + +static bool bpf_preload_mod_get(void) +{ + /* If bpf_preload.ko wasn't loaded earlier then load it now. + * When bpf_preload is built into vmlinux the module's __init + * function will populate it. + */ + if (!bpf_preload_ops) { + request_module("bpf_preload"); + if (!bpf_preload_ops) + return false; + } + /* And grab the reference, so the module doesn't disappear while the + * kernel is interacting with the kernel module and its UMD. + */ + if (!try_module_get(bpf_preload_ops->owner)) { + pr_err("bpf_preload module get failed.\n"); + return false; + } + return true; +} + +static void bpf_preload_mod_put(void) +{ + if (bpf_preload_ops) + /* now user can "rmmod bpf_preload" if necessary */ + module_put(bpf_preload_ops->owner); +} + +static DEFINE_MUTEX(bpf_preload_lock); + +static int populate_bpffs(struct dentry *parent) +{ + struct bpf_preload_info objs[BPF_PRELOAD_LINKS] = {}; + struct bpf_link *links[BPF_PRELOAD_LINKS] = {}; + int err = 0, i; + + /* grab the mutex to make sure the kernel interactions with bpf_preload + * UMD are serialized + */ + mutex_lock(&bpf_preload_lock); + + /* if bpf_preload.ko wasn't built into vmlinux then load it */ + if (!bpf_preload_mod_get()) + goto out; + + if (!bpf_preload_ops->info.tgid) { + /* preload() will start UMD that will load BPF iterator programs */ + err = bpf_preload_ops->preload(objs); + if (err) + goto out_put; + for (i = 0; i < BPF_PRELOAD_LINKS; i++) { + links[i] = bpf_link_by_id(objs[i].link_id); + if (IS_ERR(links[i])) { + err = PTR_ERR(links[i]); + goto out_put; + } + } + for (i = 0; i < BPF_PRELOAD_LINKS; i++) { + err = bpf_iter_link_pin_kernel(parent, + objs[i].link_name, links[i]); + if (err) + goto out_put; + /* do not unlink successfully pinned links even + * if later link fails to pin + */ + links[i] = NULL; + } + /* finish() will tell UMD process to exit */ + err = bpf_preload_ops->finish(); + if (err) + goto out_put; + } +out_put: + bpf_preload_mod_put(); +out: + mutex_unlock(&bpf_preload_lock); + for (i = 0; i < BPF_PRELOAD_LINKS && err; i++) + if (!IS_ERR_OR_NULL(links[i])) + bpf_link_put(links[i]); + return err; +} + static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; @@ -654,8 +762,8 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) inode = sb->s_root->d_inode; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; + populate_bpffs(sb->s_root); inode->i_mode |= S_ISVTX | opts->mode; - return 0; } @@ -705,6 +813,8 @@ static int __init bpf_init(void) { int ret; + mutex_init(&bpf_preload_lock); + ret = sysfs_create_mount_point(fs_kobj, "bpf"); if (ret) return ret; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 44474bf3ab7a..00e32f2ec3e6 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -732,6 +732,7 @@ static int trie_check_btf(const struct bpf_map *map, static int trie_map_btf_id; const struct bpf_map_ops trie_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = trie_alloc, .map_free = trie_free, .map_get_next_key = trie_get_next_key, diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 17738c93bec8..39ab0b68cade 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -17,23 +17,17 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) if (IS_ERR(inner_map)) return inner_map; - /* prog_array->aux->{type,jited} is a runtime binding. - * Doing static check alone in the verifier is not enough. - */ - if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY || - inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || - inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE || - inner_map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { - fdput(f); - return ERR_PTR(-ENOTSUPP); - } - /* Does not support >1 level map-in-map */ if (inner_map->inner_map_meta) { fdput(f); return ERR_PTR(-EINVAL); } + if (!inner_map->ops->map_meta_equal) { + fdput(f); + return ERR_PTR(-ENOTSUPP); + } + if (map_value_has_spin_lock(inner_map)) { fdput(f); return ERR_PTR(-ENOTSUPP); @@ -81,15 +75,14 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, return meta0->map_type == meta1->map_type && meta0->key_size == meta1->key_size && meta0->value_size == meta1->value_size && - meta0->map_flags == meta1->map_flags && - meta0->max_entries == meta1->max_entries; + meta0->map_flags == meta1->map_flags; } void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file /* not used */, int ufd) { - struct bpf_map *inner_map; + struct bpf_map *inner_map, *inner_map_meta; struct fd f; f = fdget(ufd); @@ -97,7 +90,8 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, if (IS_ERR(inner_map)) return inner_map; - if (bpf_map_meta_equal(map->inner_map_meta, inner_map)) + inner_map_meta = map->inner_map_meta; + if (inner_map_meta->ops->map_meta_equal(inner_map_meta, inner_map)) bpf_map_inc(inner_map); else inner_map = ERR_PTR(-EINVAL); diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h index a507bf6ef8b9..bcb7534afb3c 100644 --- a/kernel/bpf/map_in_map.h +++ b/kernel/bpf/map_in_map.h @@ -11,8 +11,6 @@ struct bpf_map; struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd); void bpf_map_meta_free(struct bpf_map *map_meta); -bool bpf_map_meta_equal(const struct bpf_map *meta0, - const struct bpf_map *meta1); void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file, int ufd); void bpf_map_fd_put_ptr(void *ptr); diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index af86048e5afd..6a9542af4212 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -149,6 +149,19 @@ static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux) bpf_map_put_with_uref(aux->map); } +void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, + struct seq_file *seq) +{ + seq_printf(seq, "map_id:\t%u\n", aux->map->id); +} + +int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, + struct bpf_link_info *info) +{ + info->iter.map.map_id = aux->map->id; + return 0; +} + DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta, struct bpf_map *map, void *key, void *value) @@ -156,6 +169,8 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = { .target = "bpf_map_elem", .attach_target = bpf_iter_attach_map, .detach_target = bpf_iter_detach_map, + .show_fdinfo = bpf_iter_map_show_fdinfo, + .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_map_elem, key), diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig new file mode 100644 index 000000000000..ace49111d3a3 --- /dev/null +++ b/kernel/bpf/preload/Kconfig @@ -0,0 +1,26 @@ +# SPDX-License-Identifier: GPL-2.0-only +config USERMODE_DRIVER + bool + default n + +menuconfig BPF_PRELOAD + bool "Preload BPF file system with kernel specific program and map iterators" + depends on BPF + # The dependency on !COMPILE_TEST prevents it from being enabled + # in allmodconfig or allyesconfig configurations + depends on !COMPILE_TEST + select USERMODE_DRIVER + help + This builds kernel module with several embedded BPF programs that are + pinned into BPF FS mount point as human readable files that are + useful in debugging and introspection of BPF programs and maps. + +if BPF_PRELOAD +config BPF_PRELOAD_UMD + tristate "bpf_preload kernel module with user mode driver" + depends on CC_CAN_LINK + depends on m || CC_CAN_LINK_STATIC + default m + help + This builds bpf_preload kernel module with embedded user mode driver. +endif diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile new file mode 100644 index 000000000000..12c7b62b9b6e --- /dev/null +++ b/kernel/bpf/preload/Makefile @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: GPL-2.0 + +LIBBPF_SRCS = $(srctree)/tools/lib/bpf/ +LIBBPF_A = $(obj)/libbpf.a +LIBBPF_OUT = $(abspath $(obj)) + +$(LIBBPF_A): + $(Q)$(MAKE) -C $(LIBBPF_SRCS) OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a + +userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi \ + -I $(srctree)/tools/lib/ -Wno-unused-result + +userprogs := bpf_preload_umd + +bpf_preload_umd-objs := iterators/iterators.o +bpf_preload_umd-userldlibs := $(LIBBPF_A) -lelf -lz + +$(obj)/bpf_preload_umd: $(LIBBPF_A) + +$(obj)/bpf_preload_umd_blob.o: $(obj)/bpf_preload_umd + +obj-$(CONFIG_BPF_PRELOAD_UMD) += bpf_preload.o +bpf_preload-objs += bpf_preload_kern.o bpf_preload_umd_blob.o diff --git a/kernel/bpf/preload/bpf_preload.h b/kernel/bpf/preload/bpf_preload.h new file mode 100644 index 000000000000..2f9932276f2e --- /dev/null +++ b/kernel/bpf/preload/bpf_preload.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_PRELOAD_H +#define _BPF_PRELOAD_H + +#include <linux/usermode_driver.h> +#include "iterators/bpf_preload_common.h" + +struct bpf_preload_ops { + struct umd_info info; + int (*preload)(struct bpf_preload_info *); + int (*finish)(void); + struct module *owner; +}; +extern struct bpf_preload_ops *bpf_preload_ops; +#define BPF_PRELOAD_LINKS 2 +#endif diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c new file mode 100644 index 000000000000..79c5772465f1 --- /dev/null +++ b/kernel/bpf/preload/bpf_preload_kern.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/init.h> +#include <linux/module.h> +#include <linux/pid.h> +#include <linux/fs.h> +#include <linux/sched/signal.h> +#include "bpf_preload.h" + +extern char bpf_preload_umd_start; +extern char bpf_preload_umd_end; + +static int preload(struct bpf_preload_info *obj); +static int finish(void); + +static struct bpf_preload_ops umd_ops = { + .info.driver_name = "bpf_preload", + .preload = preload, + .finish = finish, + .owner = THIS_MODULE, +}; + +static int preload(struct bpf_preload_info *obj) +{ + int magic = BPF_PRELOAD_START; + loff_t pos = 0; + int i, err; + ssize_t n; + + err = fork_usermode_driver(&umd_ops.info); + if (err) + return err; + + /* send the start magic to let UMD proceed with loading BPF progs */ + n = kernel_write(umd_ops.info.pipe_to_umh, + &magic, sizeof(magic), &pos); + if (n != sizeof(magic)) + return -EPIPE; + + /* receive bpf_link IDs and names from UMD */ + pos = 0; + for (i = 0; i < BPF_PRELOAD_LINKS; i++) { + n = kernel_read(umd_ops.info.pipe_from_umh, + &obj[i], sizeof(*obj), &pos); + if (n != sizeof(*obj)) + return -EPIPE; + } + return 0; +} + +static int finish(void) +{ + int magic = BPF_PRELOAD_END; + struct pid *tgid; + loff_t pos = 0; + ssize_t n; + + /* send the last magic to UMD. It will do a normal exit. */ + n = kernel_write(umd_ops.info.pipe_to_umh, + &magic, sizeof(magic), &pos); + if (n != sizeof(magic)) + return -EPIPE; + tgid = umd_ops.info.tgid; + wait_event(tgid->wait_pidfd, thread_group_exited(tgid)); + umd_ops.info.tgid = NULL; + return 0; +} + +static int __init load_umd(void) +{ + int err; + + err = umd_load_blob(&umd_ops.info, &bpf_preload_umd_start, + &bpf_preload_umd_end - &bpf_preload_umd_start); + if (err) + return err; + bpf_preload_ops = &umd_ops; + return err; +} + +static void __exit fini_umd(void) +{ + bpf_preload_ops = NULL; + /* kill UMD in case it's still there due to earlier error */ + kill_pid(umd_ops.info.tgid, SIGKILL, 1); + umd_ops.info.tgid = NULL; + umd_unload_blob(&umd_ops.info); +} +late_initcall(load_umd); +module_exit(fini_umd); +MODULE_LICENSE("GPL"); diff --git a/kernel/bpf/preload/bpf_preload_umd_blob.S b/kernel/bpf/preload/bpf_preload_umd_blob.S new file mode 100644 index 000000000000..f1f40223b5c3 --- /dev/null +++ b/kernel/bpf/preload/bpf_preload_umd_blob.S @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + .section .init.rodata, "a" + .global bpf_preload_umd_start +bpf_preload_umd_start: + .incbin "kernel/bpf/preload/bpf_preload_umd" + .global bpf_preload_umd_end +bpf_preload_umd_end: diff --git a/kernel/bpf/preload/iterators/.gitignore b/kernel/bpf/preload/iterators/.gitignore new file mode 100644 index 000000000000..ffdb70230c8b --- /dev/null +++ b/kernel/bpf/preload/iterators/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +/.output diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile new file mode 100644 index 000000000000..28fa8c1440f4 --- /dev/null +++ b/kernel/bpf/preload/iterators/Makefile @@ -0,0 +1,57 @@ +# SPDX-License-Identifier: GPL-2.0 +OUTPUT := .output +CLANG ?= clang +LLC ?= llc +LLVM_STRIP ?= llvm-strip +DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) +LIBBPF_SRC := $(abspath ../../../../tools/lib/bpf) +BPFOBJ := $(OUTPUT)/libbpf.a +BPF_INCLUDE := $(OUTPUT) +INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../../../tools/lib) \ + -I$(abspath ../../../../tools/include/uapi) +CFLAGS := -g -Wall + +abs_out := $(abspath $(OUTPUT)) +ifeq ($(V),1) +Q = +msg = +else +Q = @ +msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; +MAKEFLAGS += --no-print-directory +submake_extras := feature_display=0 +endif + +.DELETE_ON_ERROR: + +.PHONY: all clean + +all: iterators.skel.h + +clean: + $(call msg,CLEAN) + $(Q)rm -rf $(OUTPUT) iterators + +iterators.skel.h: $(OUTPUT)/iterators.bpf.o | $(BPFTOOL) + $(call msg,GEN-SKEL,$@) + $(Q)$(BPFTOOL) gen skeleton $< > $@ + + +$(OUTPUT)/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) + $(call msg,BPF,$@) + $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \ + -c $(filter %.c,$^) -o $@ && \ + $(LLVM_STRIP) -g $@ + +$(OUTPUT): + $(call msg,MKDIR,$@) + $(Q)mkdir -p $(OUTPUT) + +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \ + OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + +$(DEFAULT_BPFTOOL): + $(Q)$(MAKE) $(submake_extras) -C ../../../../tools/bpf/bpftool \ + prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install diff --git a/kernel/bpf/preload/iterators/README b/kernel/bpf/preload/iterators/README new file mode 100644 index 000000000000..7fd6d39a9ad2 --- /dev/null +++ b/kernel/bpf/preload/iterators/README @@ -0,0 +1,4 @@ +WARNING: +If you change "iterators.bpf.c" do "make -j" in this directory to rebuild "iterators.skel.h". +Make sure to have clang 10 installed. +See Documentation/bpf/bpf_devel_QA.rst diff --git a/kernel/bpf/preload/iterators/bpf_preload_common.h b/kernel/bpf/preload/iterators/bpf_preload_common.h new file mode 100644 index 000000000000..8464d1a48c05 --- /dev/null +++ b/kernel/bpf/preload/iterators/bpf_preload_common.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_PRELOAD_COMMON_H +#define _BPF_PRELOAD_COMMON_H + +#define BPF_PRELOAD_START 0x5555 +#define BPF_PRELOAD_END 0xAAAA + +struct bpf_preload_info { + char link_name[16]; + int link_id; +}; + +#endif diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c new file mode 100644 index 000000000000..5ded550b2ed6 --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.bpf.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record) +struct seq_file; +struct bpf_iter_meta { + struct seq_file *seq; + __u64 session_id; + __u64 seq_num; +}; + +struct bpf_map { + __u32 id; + char name[16]; + __u32 max_entries; +}; + +struct bpf_iter__bpf_map { + struct bpf_iter_meta *meta; + struct bpf_map *map; +}; + +struct btf_type { + __u32 name_off; +}; + +struct btf_header { + __u32 str_len; +}; + +struct btf { + const char *strings; + struct btf_type **types; + struct btf_header hdr; +}; + +struct bpf_prog_aux { + __u32 id; + char name[16]; + const char *attach_func_name; + struct bpf_prog *linked_prog; + struct bpf_func_info *func_info; + struct btf *btf; +}; + +struct bpf_prog { + struct bpf_prog_aux *aux; +}; + +struct bpf_iter__bpf_prog { + struct bpf_iter_meta *meta; + struct bpf_prog *prog; +}; +#pragma clang attribute pop + +static const char *get_name(struct btf *btf, long btf_id, const char *fallback) +{ + struct btf_type **types, *t; + unsigned int name_off; + const char *str; + + if (!btf) + return fallback; + str = btf->strings; + types = btf->types; + bpf_probe_read_kernel(&t, sizeof(t), types + btf_id); + name_off = BPF_CORE_READ(t, name_off); + if (name_off >= btf->hdr.str_len) + return fallback; + return str + name_off; +} + +SEC("iter/bpf_map") +int dump_bpf_map(struct bpf_iter__bpf_map *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + __u64 seq_num = ctx->meta->seq_num; + struct bpf_map *map = ctx->map; + + if (!map) + return 0; + + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " id name max_entries\n"); + + BPF_SEQ_PRINTF(seq, "%4u %-16s%6d\n", map->id, map->name, map->max_entries); + return 0; +} + +SEC("iter/bpf_prog") +int dump_bpf_prog(struct bpf_iter__bpf_prog *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + __u64 seq_num = ctx->meta->seq_num; + struct bpf_prog *prog = ctx->prog; + struct bpf_prog_aux *aux; + + if (!prog) + return 0; + + aux = prog->aux; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " id name attached\n"); + + BPF_SEQ_PRINTF(seq, "%4u %-16s %s %s\n", aux->id, + get_name(aux->btf, aux->func_info[0].type_id, aux->name), + aux->attach_func_name, aux->linked_prog->aux->name); + return 0; +} +char LICENSE[] SEC("license") = "GPL"; diff --git a/kernel/bpf/preload/iterators/iterators.c b/kernel/bpf/preload/iterators/iterators.c new file mode 100644 index 000000000000..b7ff87939172 --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <argp.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/resource.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include <sys/mount.h> +#include "iterators.skel.h" +#include "bpf_preload_common.h" + +int to_kernel = -1; +int from_kernel = 0; + +static int send_link_to_kernel(struct bpf_link *link, const char *link_name) +{ + struct bpf_preload_info obj = {}; + struct bpf_link_info info = {}; + __u32 info_len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &info, &info_len); + if (err) + return err; + obj.link_id = info.id; + if (strlen(link_name) >= sizeof(obj.link_name)) + return -E2BIG; + strcpy(obj.link_name, link_name); + if (write(to_kernel, &obj, sizeof(obj)) != sizeof(obj)) + return -EPIPE; + return 0; +} + +int main(int argc, char **argv) +{ + struct rlimit rlim = { RLIM_INFINITY, RLIM_INFINITY }; + struct iterators_bpf *skel; + int err, magic; + int debug_fd; + + debug_fd = open("/dev/console", O_WRONLY | O_NOCTTY | O_CLOEXEC); + if (debug_fd < 0) + return 1; + to_kernel = dup(1); + close(1); + dup(debug_fd); + /* now stdin and stderr point to /dev/console */ + + read(from_kernel, &magic, sizeof(magic)); + if (magic != BPF_PRELOAD_START) { + printf("bad start magic %d\n", magic); + return 1; + } + setrlimit(RLIMIT_MEMLOCK, &rlim); + /* libbpf opens BPF object and loads it into the kernel */ + skel = iterators_bpf__open_and_load(); + if (!skel) { + /* iterators.skel.h is little endian. + * libbpf doesn't support automatic little->big conversion + * of BPF bytecode yet. + * The program load will fail in such case. + */ + printf("Failed load could be due to wrong endianness\n"); + return 1; + } + err = iterators_bpf__attach(skel); + if (err) + goto cleanup; + + /* send two bpf_link IDs with names to the kernel */ + err = send_link_to_kernel(skel->links.dump_bpf_map, "maps.debug"); + if (err) + goto cleanup; + err = send_link_to_kernel(skel->links.dump_bpf_prog, "progs.debug"); + if (err) + goto cleanup; + + /* The kernel will proceed with pinnging the links in bpffs. + * UMD will wait on read from pipe. + */ + read(from_kernel, &magic, sizeof(magic)); + if (magic != BPF_PRELOAD_END) { + printf("bad final magic %d\n", magic); + err = -EINVAL; + } +cleanup: + iterators_bpf__destroy(skel); + + return err != 0; +} diff --git a/kernel/bpf/preload/iterators/iterators.skel.h b/kernel/bpf/preload/iterators/iterators.skel.h new file mode 100644 index 000000000000..c3171357dc4f --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.skel.h @@ -0,0 +1,410 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* THIS FILE IS AUTOGENERATED! */ +#ifndef __ITERATORS_BPF_SKEL_H__ +#define __ITERATORS_BPF_SKEL_H__ + +#include <stdlib.h> +#include <bpf/libbpf.h> + +struct iterators_bpf { + struct bpf_object_skeleton *skeleton; + struct bpf_object *obj; + struct { + struct bpf_map *rodata; + } maps; + struct { + struct bpf_program *dump_bpf_map; + struct bpf_program *dump_bpf_prog; + } progs; + struct { + struct bpf_link *dump_bpf_map; + struct bpf_link *dump_bpf_prog; + } links; + struct iterators_bpf__rodata { + char dump_bpf_map____fmt[35]; + char dump_bpf_map____fmt_1[14]; + char dump_bpf_prog____fmt[32]; + char dump_bpf_prog____fmt_2[17]; + } *rodata; +}; + +static void +iterators_bpf__destroy(struct iterators_bpf *obj) +{ + if (!obj) + return; + if (obj->skeleton) + bpf_object__destroy_skeleton(obj->skeleton); + free(obj); +} + +static inline int +iterators_bpf__create_skeleton(struct iterators_bpf *obj); + +static inline struct iterators_bpf * +iterators_bpf__open_opts(const struct bpf_object_open_opts *opts) +{ + struct iterators_bpf *obj; + + obj = (typeof(obj))calloc(1, sizeof(*obj)); + if (!obj) + return NULL; + if (iterators_bpf__create_skeleton(obj)) + goto err; + if (bpf_object__open_skeleton(obj->skeleton, opts)) + goto err; + + return obj; +err: + iterators_bpf__destroy(obj); + return NULL; +} + +static inline struct iterators_bpf * +iterators_bpf__open(void) +{ + return iterators_bpf__open_opts(NULL); +} + +static inline int +iterators_bpf__load(struct iterators_bpf *obj) +{ + return bpf_object__load_skeleton(obj->skeleton); +} + +static inline struct iterators_bpf * +iterators_bpf__open_and_load(void) +{ + struct iterators_bpf *obj; + + obj = iterators_bpf__open(); + if (!obj) + return NULL; + if (iterators_bpf__load(obj)) { + iterators_bpf__destroy(obj); + return NULL; + } + return obj; +} + +static inline int +iterators_bpf__attach(struct iterators_bpf *obj) +{ + return bpf_object__attach_skeleton(obj->skeleton); +} + +static inline void +iterators_bpf__detach(struct iterators_bpf *obj) +{ + return bpf_object__detach_skeleton(obj->skeleton); +} + +static inline int +iterators_bpf__create_skeleton(struct iterators_bpf *obj) +{ + struct bpf_object_skeleton *s; + + s = (typeof(s))calloc(1, sizeof(*s)); + if (!s) + return -1; + obj->skeleton = s; + + s->sz = sizeof(*s); + s->name = "iterators_bpf"; + s->obj = &obj->obj; + + /* maps */ + s->map_cnt = 1; + s->map_skel_sz = sizeof(*s->maps); + s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz); + if (!s->maps) + goto err; + + s->maps[0].name = "iterator.rodata"; + s->maps[0].map = &obj->maps.rodata; + s->maps[0].mmaped = (void **)&obj->rodata; + + /* programs */ + s->prog_cnt = 2; + s->prog_skel_sz = sizeof(*s->progs); + s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz); + if (!s->progs) + goto err; + + s->progs[0].name = "dump_bpf_map"; + s->progs[0].prog = &obj->progs.dump_bpf_map; + s->progs[0].link = &obj->links.dump_bpf_map; + + s->progs[1].name = "dump_bpf_prog"; + s->progs[1].prog = &obj->progs.dump_bpf_prog; + s->progs[1].link = &obj->links.dump_bpf_prog; + + s->data_sz = 7128; + s->data = (void *)"\ +\x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x18\x18\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0f\0\ +\x0e\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\ +\x1a\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\ +\x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\xb7\x03\0\0\x23\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x61\x71\0\ +\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\0\0\0\0\0\ +\x0f\x12\0\0\0\0\0\0\x7b\x2a\xf0\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\x7b\x1a\xf8\ +\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\ +\0\x18\x02\0\0\x23\0\0\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\x0e\0\0\0\xb7\x05\0\0\x18\ +\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\x79\x12\0\0\0\0\ +\0\0\x79\x26\0\0\0\0\0\0\x79\x11\x08\0\0\0\0\0\x15\x01\x3b\0\0\0\0\0\x79\x17\0\ +\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\ +\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x02\0\0\x31\0\0\0\0\0\0\0\0\0\ +\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x7b\x6a\xc8\ +\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xb7\x03\0\0\x04\0\0\0\ +\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\x71\x28\0\0\0\0\0\x79\x78\x30\0\0\ +\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\0\x61\x11\ +\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\0\x03\0\0\0\x0f\x13\0\0\0\0\0\0\ +\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\xb7\x02\0\ +\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\0\0\0\0\ +\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\xb7\x02\0\ +\0\x04\0\0\0\x85\0\0\0\x04\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\ +\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\xbf\x69\0\0\0\ +\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\ +\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\x1a\xe8\xff\ +\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\x79\xa1\xc8\xff\0\0\0\ +\0\x18\x02\0\0\x51\0\0\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\x11\0\0\0\xb7\x05\0\0\x20\ +\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\x20\x20\x69\x64\ +\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\ +\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\ +\x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\ +\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0\x47\x50\x4c\0\x9f\ +\xeb\x01\0\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\0\x05\0\0\0\0\0\0\0\0\0\ +\x02\x02\0\0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\ +\0\0\0\x04\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\ +\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\ +\0\0\0\x20\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xa3\0\0\0\x03\0\0\x04\x18\0\ +\0\0\xb1\0\0\0\x09\0\0\0\0\0\0\0\xb5\0\0\0\x0b\0\0\0\x40\0\0\0\xc0\0\0\0\x0b\0\ +\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xc8\0\0\0\0\0\0\x07\0\0\0\0\xd1\0\0\ +\0\0\0\0\x08\x0c\0\0\0\xd7\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\x98\x01\0\0\x03\ +\0\0\x04\x18\0\0\0\xa0\x01\0\0\x0e\0\0\0\0\0\0\0\xa3\x01\0\0\x11\0\0\0\x20\0\0\ +\0\xa8\x01\0\0\x0e\0\0\0\xa0\0\0\0\xb4\x01\0\0\0\0\0\x08\x0f\0\0\0\xba\x01\0\0\ +\0\0\0\x01\x04\0\0\0\x20\0\0\0\xc7\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\ +\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xcc\x01\0\0\0\0\0\x01\x04\ +\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x30\x02\0\0\x02\0\0\x04\x10\0\0\0\ +\x13\0\0\0\x03\0\0\0\0\0\0\0\x43\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\ +\x18\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x48\x02\0\0\x01\0\ +\0\x0c\x16\0\0\0\x94\x02\0\0\x01\0\0\x04\x08\0\0\0\x9d\x02\0\0\x19\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\x02\x1a\0\0\0\xee\x02\0\0\x06\0\0\x04\x38\0\0\0\xa0\x01\0\0\ +\x0e\0\0\0\0\0\0\0\xa3\x01\0\0\x11\0\0\0\x20\0\0\0\xfb\x02\0\0\x1b\0\0\0\xc0\0\ +\0\0\x0c\x03\0\0\x15\0\0\0\0\x01\0\0\x18\x03\0\0\x1d\0\0\0\x40\x01\0\0\x22\x03\ +\0\0\x1e\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\ +\0\0\0\0\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x6c\x03\0\0\x02\0\ +\0\x04\x08\0\0\0\x7a\x03\0\0\x0e\0\0\0\0\0\0\0\x83\x03\0\0\x0e\0\0\0\x20\0\0\0\ +\x22\x03\0\0\x03\0\0\x04\x18\0\0\0\x8d\x03\0\0\x1b\0\0\0\0\0\0\0\x95\x03\0\0\ +\x21\0\0\0\x40\0\0\0\x9b\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\ +\0\0\0\0\0\0\0\0\x02\x24\0\0\0\x9f\x03\0\0\x01\0\0\x04\x04\0\0\0\xaa\x03\0\0\ +\x0e\0\0\0\0\0\0\0\x13\x04\0\0\x01\0\0\x04\x04\0\0\0\x1c\x04\0\0\x0e\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x92\x04\0\0\0\0\0\ +\x0e\x25\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\ +\xa6\x04\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\ +\x12\0\0\0\x20\0\0\0\xbc\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\ +\0\0\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xd1\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xe8\x04\0\0\0\0\0\x0e\ +\x2d\0\0\0\x01\0\0\0\xf0\x04\0\0\x04\0\0\x0f\0\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\ +\0\x28\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\ +\0\0\x11\0\0\0\xf8\x04\0\0\x01\0\0\x0f\0\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\ +\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\ +\x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\ +\x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\ +\x30\x3a\x30\0\x2f\x77\x2f\x6e\x65\x74\x2d\x6e\x65\x78\x74\x2f\x6b\x65\x72\x6e\ +\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\ +\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\ +\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\ +\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\ +\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\ +\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\ +\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x6c\x6f\x6e\x67\x20\ +\x6c\x6f\x6e\x67\x20\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x30\x3a\ +\x31\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\ +\x61\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\ +\x21\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\ +\x5f\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\ +\x65\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\ +\x20\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\ +\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\ +\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\ +\x74\x72\x69\x65\x73\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\ +\x64\0\x6e\x61\x6d\x65\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\ +\x75\x33\x32\0\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\ +\x72\0\x5f\x5f\x41\x52\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\ +\x5f\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\ +\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\ +\x2c\x20\x6d\x61\x70\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\ +\x65\x2c\x20\x6d\x61\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\ +\x29\x3b\0\x7d\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\ +\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\ +\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\ +\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\ +\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\ +\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\ +\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\ +\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\ +\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ +\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\ +\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\ +\x63\x5f\x6e\x61\x6d\x65\0\x6c\x69\x6e\x6b\x65\x64\x5f\x70\x72\x6f\x67\0\x66\ +\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\ +\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\ +\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\ +\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\ +\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\ +\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\ +\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\ +\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\ +\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\ +\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\ +\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\ +\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\ +\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\ +\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\ +\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\ +\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\ +\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\ +\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\ +\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\ +\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\ +\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\ +\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\ +\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\ +\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\ +\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x9f\xeb\x01\0\x20\0\0\0\0\0\0\0\x24\0\ +\0\0\x24\0\0\0\x44\x02\0\0\x68\x02\0\0\xa4\x01\0\0\x08\0\0\0\x31\0\0\0\x01\0\0\ +\0\0\0\0\0\x07\0\0\0\x56\x02\0\0\x01\0\0\0\0\0\0\0\x17\0\0\0\x10\0\0\0\x31\0\0\ +\0\x09\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x40\x01\0\x08\0\0\0\x42\0\0\0\x7b\ +\0\0\0\x24\x40\x01\0\x10\0\0\0\x42\0\0\0\xf2\0\0\0\x1d\x48\x01\0\x18\0\0\0\x42\ +\0\0\0\x13\x01\0\0\x06\x50\x01\0\x20\0\0\0\x42\0\0\0\x22\x01\0\0\x1d\x44\x01\0\ +\x28\0\0\0\x42\0\0\0\x47\x01\0\0\x06\x5c\x01\0\x38\0\0\0\x42\0\0\0\x5a\x01\0\0\ +\x03\x60\x01\0\x70\0\0\0\x42\0\0\0\xe0\x01\0\0\x02\x68\x01\0\xf0\0\0\0\x42\0\0\ +\0\x2e\x02\0\0\x01\x70\x01\0\x56\x02\0\0\x1a\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\ +\x1e\x84\x01\0\x08\0\0\0\x42\0\0\0\x7b\0\0\0\x24\x84\x01\0\x10\0\0\0\x42\0\0\0\ +\x64\x02\0\0\x1f\x8c\x01\0\x18\0\0\0\x42\0\0\0\x88\x02\0\0\x06\x98\x01\0\x20\0\ +\0\0\x42\0\0\0\xa1\x02\0\0\x0e\xa4\x01\0\x28\0\0\0\x42\0\0\0\x22\x01\0\0\x1d\ +\x88\x01\0\x30\0\0\0\x42\0\0\0\x47\x01\0\0\x06\xa8\x01\0\x40\0\0\0\x42\0\0\0\ +\xb3\x02\0\0\x03\xac\x01\0\x80\0\0\0\x42\0\0\0\x26\x03\0\0\x02\xb4\x01\0\xb8\0\ +\0\0\x42\0\0\0\x61\x03\0\0\x06\x08\x01\0\xd0\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\ +\xd8\0\0\0\x42\0\0\0\xb2\x03\0\0\x0f\x14\x01\0\xe0\0\0\0\x42\0\0\0\xc7\x03\0\0\ +\x2d\x18\x01\0\xf0\0\0\0\x42\0\0\0\xfe\x03\0\0\x0d\x10\x01\0\0\x01\0\0\x42\0\0\ +\0\0\0\0\0\0\0\0\0\x08\x01\0\0\x42\0\0\0\xc7\x03\0\0\x02\x18\x01\0\x20\x01\0\0\ +\x42\0\0\0\x25\x04\0\0\x0d\x1c\x01\0\x38\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x40\ +\x01\0\0\x42\0\0\0\x25\x04\0\0\x0d\x1c\x01\0\x58\x01\0\0\x42\0\0\0\x25\x04\0\0\ +\x0d\x1c\x01\0\x60\x01\0\0\x42\0\0\0\x53\x04\0\0\x1b\x20\x01\0\x68\x01\0\0\x42\ +\0\0\0\x53\x04\0\0\x06\x20\x01\0\x70\x01\0\0\x42\0\0\0\x76\x04\0\0\x0d\x28\x01\ +\0\x78\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x80\x01\0\0\x42\0\0\0\x26\x03\0\0\x02\ +\xb4\x01\0\xf8\x01\0\0\x42\0\0\0\x2e\x02\0\0\x01\xc4\x01\0\x10\0\0\0\x31\0\0\0\ +\x07\0\0\0\0\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\ +\0\0\0\x10\0\0\0\x02\0\0\0\xee\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x1e\x01\0\0\0\ +\0\0\0\x70\0\0\0\x0d\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xee\0\0\0\0\0\ +\0\0\xa0\0\0\0\x0d\0\0\0\x1e\x01\0\0\0\0\0\0\x56\x02\0\0\x12\0\0\0\0\0\0\0\x14\ +\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x14\0\ +\0\0\xee\0\0\0\0\0\0\0\x20\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\ +\0\x1e\x01\0\0\0\0\0\0\x80\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1a\0\0\ +\0\xee\0\0\0\0\0\0\0\xa8\0\0\0\x1a\0\0\0\x59\x03\0\0\0\0\0\0\xb0\0\0\0\x1a\0\0\ +\0\x5d\x03\0\0\0\0\0\0\xc0\0\0\0\x1f\0\0\0\x8b\x03\0\0\0\0\0\0\xd8\0\0\0\x20\0\ +\0\0\xee\0\0\0\0\0\0\0\xf0\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x24\0\ +\0\0\x3e\0\0\0\0\0\0\0\x50\x01\0\0\x1a\0\0\0\xee\0\0\0\0\0\0\0\x60\x01\0\0\x20\ +\0\0\0\x4d\x04\0\0\0\0\0\0\x88\x01\0\0\x1a\0\0\0\x1e\x01\0\0\0\0\0\0\x98\x01\0\ +\0\x1a\0\0\0\x8e\x04\0\0\0\0\0\0\xa0\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd6\0\0\0\0\0\x02\0\x70\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\xc8\0\0\0\0\0\x02\0\xf0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\xcf\0\0\0\0\0\x03\0\x78\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xc1\0\0\0\0\0\x03\0\x80\ +\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xba\0\0\0\0\0\x03\0\xf8\x01\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\x14\0\0\0\x01\0\x04\0\0\0\0\0\0\0\0\0\x23\0\0\0\0\0\0\0\xf4\0\0\0\ +\x01\0\x04\0\x23\0\0\0\0\0\0\0\x0e\0\0\0\0\0\0\0\x28\0\0\0\x01\0\x04\0\x31\0\0\ +\0\0\0\0\0\x20\0\0\0\0\0\0\0\xdd\0\0\0\x01\0\x04\0\x51\0\0\0\0\0\0\0\x11\0\0\0\ +\0\0\0\0\0\0\0\0\x03\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\x03\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\xb2\0\0\0\x11\0\x05\0\0\0\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\x3d\0\0\0\x12\ +\0\x02\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\x5b\0\0\0\x12\0\x03\0\0\0\0\0\0\0\0\ +\0\x08\x02\0\0\0\0\0\0\x48\0\0\0\0\0\0\0\x01\0\0\0\x0c\0\0\0\xc8\0\0\0\0\0\0\0\ +\x01\0\0\0\x0c\0\0\0\x50\0\0\0\0\0\0\0\x01\0\0\0\x0c\0\0\0\xd0\x01\0\0\0\0\0\0\ +\x01\0\0\0\x0c\0\0\0\xf0\x03\0\0\0\0\0\0\x0a\0\0\0\x0c\0\0\0\xfc\x03\0\0\0\0\0\ +\0\x0a\0\0\0\x0c\0\0\0\x08\x04\0\0\0\0\0\0\x0a\0\0\0\x0c\0\0\0\x14\x04\0\0\0\0\ +\0\0\x0a\0\0\0\x0c\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\x0d\0\0\0\x2c\0\0\0\0\0\0\ +\0\0\0\0\0\x0a\0\0\0\x3c\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x50\0\0\0\0\0\0\0\0\0\ +\0\0\x0a\0\0\0\x60\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\x70\0\0\0\0\0\0\0\0\0\0\0\ +\x0a\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\x90\0\0\0\0\0\0\0\0\0\0\0\x0a\0\ +\0\0\xa0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xb0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\ +\xc0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xd0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xe8\0\ +\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xf8\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x08\x01\0\0\ +\0\0\0\0\0\0\0\0\x0b\0\0\0\x18\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x28\x01\0\0\0\ +\0\0\0\0\0\0\0\x0b\0\0\0\x38\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x48\x01\0\0\0\0\ +\0\0\0\0\0\0\x0b\0\0\0\x58\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x68\x01\0\0\0\0\0\ +\0\0\0\0\0\x0b\0\0\0\x78\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x88\x01\0\0\0\0\0\0\ +\0\0\0\0\x0b\0\0\0\x98\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa8\x01\0\0\0\0\0\0\0\ +\0\0\0\x0b\0\0\0\xb8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc8\x01\0\0\0\0\0\0\0\0\ +\0\0\x0b\0\0\0\xd8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xe8\x01\0\0\0\0\0\0\0\0\0\ +\0\x0b\0\0\0\xf8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x28\x02\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x38\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x48\x02\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x58\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x68\x02\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x78\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x94\x02\0\0\0\0\0\0\0\0\0\0\ +\x0a\0\0\0\xa4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xb4\x02\0\0\0\0\0\0\0\0\0\0\ +\x0a\0\0\0\xc4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xd4\x02\0\0\0\0\0\0\0\0\0\0\ +\x0a\0\0\0\xe4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xf4\x02\0\0\0\0\0\0\0\0\0\0\ +\x0a\0\0\0\x0c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x1c\x03\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x2c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x3c\x03\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x4c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x5c\x03\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x6c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x7c\x03\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x8c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x9c\x03\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\xac\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xbc\x03\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\xcc\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xdc\x03\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\xec\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xfc\x03\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x0c\x04\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x1c\x04\0\0\0\0\0\0\0\0\0\0\ +\x0b\0\0\0\x4e\x4f\x41\x42\x43\x44\x4d\0\x2e\x74\x65\x78\x74\0\x2e\x72\x65\x6c\ +\x2e\x42\x54\x46\x2e\x65\x78\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\ +\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\ +\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\ +\x61\x70\0\x2e\x72\x65\x6c\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\ +\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x2e\x72\x65\x6c\x69\x74\ +\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x2e\x6c\x6c\x76\x6d\x5f\x61\x64\ +\x64\x72\x73\x69\x67\0\x6c\x69\x63\x65\x6e\x73\x65\0\x2e\x73\x74\x72\x74\x61\ +\x62\0\x2e\x73\x79\x6d\x74\x61\x62\0\x2e\x72\x6f\x64\x61\x74\x61\0\x2e\x72\x65\ +\x6c\x2e\x42\x54\x46\0\x4c\x49\x43\x45\x4e\x53\x45\0\x4c\x42\x42\x31\x5f\x37\0\ +\x4c\x42\x42\x31\x5f\x36\0\x4c\x42\x42\x30\x5f\x34\0\x4c\x42\x42\x31\x5f\x33\0\ +\x4c\x42\x42\x30\x5f\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\ +\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\ +\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x4e\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\ +\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\x6d\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\x01\0\0\0\0\0\0\x08\ +\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa1\0\0\0\ +\x01\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x48\x03\0\0\0\0\0\0\x62\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x89\0\0\0\x01\0\0\0\x03\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xaa\x03\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xad\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\xae\x03\0\0\0\0\0\0\x34\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\xe2\x0c\0\0\0\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\x99\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\x11\0\0\0\ +\0\0\0\x80\x01\0\0\0\0\0\0\x0e\0\0\0\x0d\0\0\0\x08\0\0\0\0\0\0\0\x18\0\0\0\0\0\ +\0\0\x4a\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x90\x12\0\0\0\0\0\0\ +\x20\0\0\0\0\0\0\0\x08\0\0\0\x02\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x69\ +\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb0\x12\0\0\0\0\0\0\x20\0\0\0\ +\0\0\0\0\x08\0\0\0\x03\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\xa9\0\0\0\x09\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd0\x12\0\0\0\0\0\0\x50\0\0\0\0\0\0\0\ +\x08\0\0\0\x06\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x07\0\0\0\x09\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x13\0\0\0\0\0\0\xe0\x03\0\0\0\0\0\0\x08\0\0\ +\0\x07\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x7b\0\0\0\x03\x4c\xff\x6f\0\0\ +\0\x80\0\0\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x91\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\x07\x17\0\0\0\0\0\0\x0a\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0"; + + return 0; +err: + bpf_object__destroy_skeleton(s); + return -1; +} + +#endif /* __ITERATORS_BPF_SKEL_H__ */ diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 44184f82916a..0ee2347ba510 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -257,6 +257,7 @@ static int queue_stack_map_get_next_key(struct bpf_map *map, void *key, static int queue_map_btf_id; const struct bpf_map_ops queue_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = queue_stack_map_alloc_check, .map_alloc = queue_stack_map_alloc, .map_free = queue_stack_map_free, @@ -273,6 +274,7 @@ const struct bpf_map_ops queue_map_ops = { static int stack_map_btf_id; const struct bpf_map_ops stack_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = queue_stack_map_alloc_check, .map_alloc = queue_stack_map_alloc, .map_free = queue_stack_map_free, diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 90b29c5b1da7..5a2ba1182493 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -351,6 +351,7 @@ static int reuseport_array_get_next_key(struct bpf_map *map, void *key, static int reuseport_array_map_btf_id; const struct bpf_map_ops reuseport_array_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = reuseport_array_alloc_check, .map_alloc = reuseport_array_alloc, .map_free = reuseport_array_free, diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 002f8a5c9e51..31cb04a4dd2d 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -287,6 +287,7 @@ static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp, static int ringbuf_map_btf_id; const struct bpf_map_ops ringbuf_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = ringbuf_map_alloc, .map_free = ringbuf_map_free, .map_mmap = ringbuf_map_mmap, diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4fd830a62be2..a2fa006f430e 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -213,11 +213,13 @@ static int stack_map_get_build_id_32(void *page_addr, phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr)); - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !stack_map_parse_build_id(page_addr, build_id, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } return -EINVAL; } @@ -236,11 +238,13 @@ static int stack_map_get_build_id_64(void *page_addr, phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr)); - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !stack_map_parse_build_id(page_addr, build_id, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } return -EINVAL; } @@ -835,6 +839,7 @@ static void stack_map_free(struct bpf_map *map) static int stack_trace_map_btf_id; const struct bpf_map_ops stack_trace_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = stack_map_alloc, .map_free = stack_map_free, .map_get_next_key = stack_map_get_next_key, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 86299a292214..178c147350f5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -29,6 +29,7 @@ #include <linux/bpf_lsm.h> #include <linux/poll.h> #include <linux/bpf-netns.h> +#include <linux/rcupdate_trace.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -90,6 +91,7 @@ int bpf_check_uarg_tail_zero(void __user *uaddr, } const struct bpf_map_ops bpf_map_offload_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, @@ -157,10 +159,11 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, if (bpf_map_is_dev_bound(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || - map->map_type == BPF_MAP_TYPE_SOCKHASH || - map->map_type == BPF_MAP_TYPE_SOCKMAP || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP) { + return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { return bpf_fd_array_map_update_elem(map, f.file, key, value, flags); @@ -768,7 +771,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && - map->map_type != BPF_MAP_TYPE_SK_STORAGE) + map->map_type != BPF_MAP_TYPE_SK_STORAGE && + map->map_type != BPF_MAP_TYPE_INODE_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { @@ -1728,10 +1732,14 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) btf_put(prog->aux->btf); bpf_prog_free_linfo(prog); - if (deferred) - call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); - else + if (deferred) { + if (prog->aux->sleepable) + call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); + else + call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); + } else { __bpf_prog_put_rcu(&prog->aux->rcu); + } } static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) @@ -2029,7 +2037,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; - /* fallthrough */ + fallthrough; default: return 0; } @@ -2101,6 +2109,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | + BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32)) return -EINVAL; @@ -2156,6 +2165,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) } prog->aux->offload_requested = !!attr->prog_ifindex; + prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; err = security_bpf_prog_alloc(prog->aux); if (err) @@ -2634,7 +2644,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, u32 ulen = info->raw_tracepoint.tp_name_len; size_t tp_len = strlen(tp_name); - if (ulen && !ubuf) + if (!ulen ^ !ubuf) return -EINVAL; info->raw_tracepoint.tp_name_len = tp_len + 1; @@ -4014,40 +4024,50 @@ static int link_detach(union bpf_attr *attr) return ret; } -static int bpf_link_inc_not_zero(struct bpf_link *link) +static struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { - return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? 0 : -ENOENT; + return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT); } -#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id - -static int bpf_link_get_fd_by_id(const union bpf_attr *attr) +struct bpf_link *bpf_link_by_id(u32 id) { struct bpf_link *link; - u32 id = attr->link_id; - int fd, err; - if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + if (!id) + return ERR_PTR(-ENOENT); spin_lock_bh(&link_idr_lock); - link = idr_find(&link_idr, id); /* before link is "settled", ID is 0, pretend it doesn't exist yet */ + link = idr_find(&link_idr, id); if (link) { if (link->id) - err = bpf_link_inc_not_zero(link); + link = bpf_link_inc_not_zero(link); else - err = -EAGAIN; + link = ERR_PTR(-EAGAIN); } else { - err = -ENOENT; + link = ERR_PTR(-ENOENT); } spin_unlock_bh(&link_idr_lock); + return link; +} - if (err) - return err; +#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id + +static int bpf_link_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_link *link; + u32 id = attr->link_id; + int fd; + + if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + link = bpf_link_by_id(id); + if (IS_ERR(link)) + return PTR_ERR(link); fd = bpf_link_new_fd(link); if (fd < 0) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 232df29793e9..99af4cea1102 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -29,8 +29,9 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns, rcu_read_lock(); retry: - pid = idr_get_next(&ns->idr, tid); + pid = find_ge_pid(*tid, ns); if (pid) { + *tid = pid_nr_ns(pid, ns); task = get_pid_task(pid, PIDTYPE_PID); if (!task) { ++*tid; @@ -178,10 +179,11 @@ again: f = fcheck_files(curr_files, curr_fd); if (!f) continue; + if (!get_file_rcu(f)) + continue; /* set info->fd */ info->fd = curr_fd; - get_file(f); rcu_read_unlock(); return f; } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 9be85aa4ec5f..7dd523a7e32d 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -7,6 +7,8 @@ #include <linux/rbtree_latch.h> #include <linux/perf_event.h> #include <linux/btf.h> +#include <linux/rcupdate_trace.h> +#include <linux/rcupdate_wait.h> /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -210,9 +212,12 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) * updates to trampoline would change the code from underneath the * preempted task. Hence wait for tasks to voluntarily schedule or go * to userspace. + * The same trampoline can hold both sleepable and non-sleepable progs. + * synchronize_rcu_tasks_trace() is needed to make sure all sleepable + * programs finish executing. + * Wait for these two grace periods together. */ - - synchronize_rcu_tasks(); + synchronize_rcu_mult(call_rcu_tasks, call_rcu_tasks_trace); err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2, &tr->func.model, flags, tprogs, @@ -344,7 +349,14 @@ void bpf_trampoline_put(struct bpf_trampoline *tr) if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) goto out; bpf_image_ksym_del(&tr->ksym); - /* wait for tasks to get out of trampoline before freeing it */ + /* This code will be executed when all bpf progs (both sleepable and + * non-sleepable) went through + * bpf_prog_put()->call_rcu[_tasks_trace]()->bpf_prog_free_deferred(). + * Hence no need for another synchronize_rcu_tasks_trace() here, + * but synchronize_rcu_tasks() is still needed, since trampoline + * may not have had any sleepable programs and we need to wait + * for tasks to get out of trampoline code before freeing it. + */ synchronize_rcu_tasks(); bpf_jit_free_exec(tr->image); hlist_del(&tr->hlist); @@ -394,6 +406,17 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) rcu_read_unlock(); } +void notrace __bpf_prog_enter_sleepable(void) +{ + rcu_read_lock_trace(); + might_fault(); +} + +void notrace __bpf_prog_exit_sleepable(void) +{ + rcu_read_unlock_trace(); +} + int __weak arch_prepare_bpf_trampoline(void *image, void *image_end, const struct btf_func_model *m, u32 flags, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ef938f17b944..86fdebb5ffd8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -21,6 +21,7 @@ #include <linux/ctype.h> #include <linux/error-injection.h> #include <linux/bpf_lsm.h> +#include <linux/btf_ids.h> #include "disasm.h" @@ -2625,11 +2626,19 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, #define MAX_PACKET_OFF 0xffff +static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) +{ + return prog->aux->linked_prog ? prog->aux->linked_prog->type + : prog->type; +} + static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_access_type t) { - switch (env->prog->type) { + enum bpf_prog_type prog_type = resolve_prog_type(env->prog); + + switch (prog_type) { /* Program types only with direct read access go here! */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: @@ -3872,6 +3881,33 @@ static int int_ptr_type_to_size(enum bpf_arg_type type) return -EINVAL; } +static int resolve_map_arg_type(struct bpf_verifier_env *env, + const struct bpf_call_arg_meta *meta, + enum bpf_arg_type *arg_type) +{ + if (!meta->map_ptr) { + /* kernel subsystem misconfigured verifier */ + verbose(env, "invalid map_ptr to access map->type\n"); + return -EACCES; + } + + switch (meta->map_ptr->map_type) { + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + if (*arg_type == ARG_PTR_TO_MAP_VALUE) { + *arg_type = ARG_PTR_TO_SOCKET; + } else { + verbose(env, "invalid arg_type for sockmap/sockhash\n"); + return -EINVAL; + } + break; + + default: + break; + } + return 0; +} + static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn) @@ -3904,6 +3940,14 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return -EACCES; } + if (arg_type == ARG_PTR_TO_MAP_VALUE || + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || + arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { + err = resolve_map_arg_type(env, meta, &arg_type); + if (err) + return err; + } + if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE || arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || @@ -3960,16 +4004,21 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, goto err_type; } } else if (arg_type == ARG_PTR_TO_BTF_ID) { + bool ids_match = false; + expected_type = PTR_TO_BTF_ID; if (type != expected_type) goto err_type; if (!fn->check_btf_id) { if (reg->btf_id != meta->btf_id) { - verbose(env, "Helper has type %s got %s in R%d\n", - kernel_type_name(meta->btf_id), - kernel_type_name(reg->btf_id), regno); - - return -EACCES; + ids_match = btf_struct_ids_match(&env->log, reg->off, reg->btf_id, + meta->btf_id); + if (!ids_match) { + verbose(env, "Helper has type %s got %s in R%d\n", + kernel_type_name(meta->btf_id), + kernel_type_name(reg->btf_id), regno); + return -EACCES; + } } } else if (!fn->check_btf_id(reg->btf_id, arg)) { verbose(env, "Helper does not support %s in R%d\n", @@ -3977,7 +4026,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return -EACCES; } - if (!tnum_is_const(reg->var_off) || reg->var_off.value || reg->off) { + if ((reg->off && !ids_match) || !tnum_is_const(reg->var_off) || reg->var_off.value) { verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n", regno); return -EACCES; @@ -4143,6 +4192,38 @@ err_type: return -EACCES; } +static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) +{ + enum bpf_attach_type eatype = env->prog->expected_attach_type; + enum bpf_prog_type type = resolve_prog_type(env->prog); + + if (func_id != BPF_FUNC_map_update_elem) + return false; + + /* It's not possible to get access to a locked struct sock in these + * contexts, so updating is safe. + */ + switch (type) { + case BPF_PROG_TYPE_TRACING: + if (eatype == BPF_TRACE_ITER) + return true; + break; + case BPF_PROG_TYPE_SOCKET_FILTER: + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_XDP: + case BPF_PROG_TYPE_SK_REUSEPORT: + case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_SK_LOOKUP: + return true; + default: + break; + } + + verbose(env, "cannot update sockmap in this context\n"); + return false; +} + static int check_map_func_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, int func_id) { @@ -4214,7 +4295,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && - func_id != BPF_FUNC_map_lookup_elem) + func_id != BPF_FUNC_map_lookup_elem && + !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_SOCKHASH: @@ -4223,7 +4305,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && - func_id != BPF_FUNC_map_lookup_elem) + func_id != BPF_FUNC_map_lookup_elem && + !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: @@ -4242,6 +4325,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_sk_storage_delete) goto error; break; + case BPF_MAP_TYPE_INODE_STORAGE: + if (func_id != BPF_FUNC_inode_storage_get && + func_id != BPF_FUNC_inode_storage_delete) + goto error; + break; default: break; } @@ -4315,6 +4403,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto error; break; + case BPF_FUNC_inode_storage_get: + case BPF_FUNC_inode_storage_delete: + if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE) + goto error; + break; default: break; } @@ -4775,6 +4868,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } + if (fn->allowed && !fn->allowed(env->prog)) { + verbose(env, "helper call is not allowed in probe\n"); + return -EINVAL; + } + /* With LD_ABS/IND some JITs save/restore skb from r1. */ changes_data = bpf_helper_changes_pkt_data(fn->func); if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { @@ -5236,7 +5334,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, off_reg == dst_reg ? dst : src); return -EACCES; } - /* fall-through */ + fallthrough; default: break; } @@ -5732,6 +5830,67 @@ static void scalar_min_max_or(struct bpf_reg_state *dst_reg, __update_reg_bounds(dst_reg); } +static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_subreg_is_const(src_reg->var_off); + bool dst_known = tnum_subreg_is_const(dst_reg->var_off); + struct tnum var32_off = tnum_subreg(dst_reg->var_off); + s32 smin_val = src_reg->s32_min_value; + + /* Assuming scalar64_min_max_xor will be called so it is safe + * to skip updating register for known case. + */ + if (src_known && dst_known) + return; + + /* We get both minimum and maximum from the var32_off. */ + dst_reg->u32_min_value = var32_off.value; + dst_reg->u32_max_value = var32_off.value | var32_off.mask; + + if (dst_reg->s32_min_value >= 0 && smin_val >= 0) { + /* XORing two positive sign numbers gives a positive, + * so safe to cast u32 result into s32. + */ + dst_reg->s32_min_value = dst_reg->u32_min_value; + dst_reg->s32_max_value = dst_reg->u32_max_value; + } else { + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } +} + +static void scalar_min_max_xor(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_is_const(src_reg->var_off); + bool dst_known = tnum_is_const(dst_reg->var_off); + s64 smin_val = src_reg->smin_value; + + if (src_known && dst_known) { + /* dst_reg->var_off.value has been updated earlier */ + __mark_reg_known(dst_reg, dst_reg->var_off.value); + return; + } + + /* We get both minimum and maximum from the var_off. */ + dst_reg->umin_value = dst_reg->var_off.value; + dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; + + if (dst_reg->smin_value >= 0 && smin_val >= 0) { + /* XORing two positive sign numbers gives a positive, + * so safe to cast u64 result into s64. + */ + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } else { + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } + + __update_reg_bounds(dst_reg); +} + static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, u64 umin_val, u64 umax_val) { @@ -6040,6 +6199,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, scalar32_min_max_or(dst_reg, &src_reg); scalar_min_max_or(dst_reg, &src_reg); break; + case BPF_XOR: + dst_reg->var_off = tnum_xor(dst_reg->var_off, src_reg.var_off); + scalar32_min_max_xor(dst_reg, &src_reg); + scalar_min_max_xor(dst_reg, &src_reg); + break; case BPF_LSH: if (umax_val >= insn_bitness) { /* Shifts greater than 31 or 63 are undefined. @@ -7287,7 +7451,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) u8 mode = BPF_MODE(insn->code); int i, err; - if (!may_access_skb(env->prog->type)) { + if (!may_access_skb(resolve_prog_type(env->prog))) { verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); return -EINVAL; } @@ -7375,11 +7539,12 @@ static int check_return_code(struct bpf_verifier_env *env) const struct bpf_prog *prog = env->prog; struct bpf_reg_state *reg; struct tnum range = tnum_range(0, 1); + enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; /* LSM and struct_ops func-ptr's return type could be "void" */ - if ((env->prog->type == BPF_PROG_TYPE_STRUCT_OPS || - env->prog->type == BPF_PROG_TYPE_LSM) && + if ((prog_type == BPF_PROG_TYPE_STRUCT_OPS || + prog_type == BPF_PROG_TYPE_LSM) && !prog->aux->attach_func_proto->type) return 0; @@ -7398,7 +7563,7 @@ static int check_return_code(struct bpf_verifier_env *env) return -EACCES; } - switch (env->prog->type) { + switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || @@ -9154,6 +9319,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_prog *prog) { + enum bpf_prog_type prog_type = resolve_prog_type(prog); /* * Validate that trace type programs use preallocated hash maps. * @@ -9171,8 +9337,8 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, * now, but warnings are emitted so developers are made aware of * the unsafety and can fix their programs before this is enforced. */ - if (is_tracing_prog_type(prog->type) && !is_preallocated_map(map)) { - if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { + if (is_tracing_prog_type(prog_type) && !is_preallocated_map(map)) { + if (prog_type == BPF_PROG_TYPE_PERF_EVENT) { verbose(env, "perf_event programs can only use preallocated hash map\n"); return -EINVAL; } @@ -9184,8 +9350,8 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n"); } - if ((is_tracing_prog_type(prog->type) || - prog->type == BPF_PROG_TYPE_SOCKET_FILTER) && + if ((is_tracing_prog_type(prog_type) || + prog_type == BPF_PROG_TYPE_SOCKET_FILTER) && map_value_has_spin_lock(map)) { verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); return -EINVAL; @@ -9202,6 +9368,23 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } + if (prog->aux->sleepable) + switch (map->map_type) { + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_LRU_HASH: + case BPF_MAP_TYPE_ARRAY: + if (!is_preallocated_map(map)) { + verbose(env, + "Sleepable programs can only use preallocated hash maps\n"); + return -EINVAL; + } + break; + default: + verbose(env, + "Sleepable programs can only use array and hash maps\n"); + return -EINVAL; + } + return 0; } @@ -9897,7 +10080,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); env->prog->aux->num_exentries++; - } else if (env->prog->type != BPF_PROG_TYPE_STRUCT_OPS) { + } else if (resolve_prog_type(env->prog) != BPF_PROG_TYPE_STRUCT_OPS) { verbose(env, "Writes through BTF pointers are not allowed\n"); return -EINVAL; } @@ -10820,6 +11003,37 @@ static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr) return -EINVAL; } +/* non exhaustive list of sleepable bpf_lsm_*() functions */ +BTF_SET_START(btf_sleepable_lsm_hooks) +#ifdef CONFIG_BPF_LSM +BTF_ID(func, bpf_lsm_bprm_committed_creds) +#else +BTF_ID_UNUSED +#endif +BTF_SET_END(btf_sleepable_lsm_hooks) + +static int check_sleepable_lsm_hook(u32 btf_id) +{ + return btf_id_set_contains(&btf_sleepable_lsm_hooks, btf_id); +} + +/* list of non-sleepable functions that are otherwise on + * ALLOW_ERROR_INJECTION list + */ +BTF_SET_START(btf_non_sleepable_error_inject) +/* Three functions below can be called from sleepable and non-sleepable context. + * Assume non-sleepable from bpf safety point of view. + */ +BTF_ID(func, __add_to_page_cache_locked) +BTF_ID(func, should_fail_alloc_page) +BTF_ID(func, should_failslab) +BTF_SET_END(btf_non_sleepable_error_inject) + +static int check_non_sleepable_error_inject(u32 btf_id) +{ + return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id); +} + static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; @@ -10837,6 +11051,12 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) long addr; u64 key; + if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING && + prog->type != BPF_PROG_TYPE_LSM) { + verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n"); + return -EINVAL; + } + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) return check_struct_ops_btf_id(env); @@ -10988,7 +11208,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) default: if (!prog_extension) return -EINVAL; - /* fallthrough */ + fallthrough; case BPF_MODIFY_RETURN: case BPF_LSM_MAC: case BPF_TRACE_FENTRY: @@ -11045,13 +11265,36 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) } } - if (prog->expected_attach_type == BPF_MODIFY_RETURN) { + if (prog->aux->sleepable) { + ret = -EINVAL; + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + /* fentry/fexit/fmod_ret progs can be sleepable only if they are + * attached to ALLOW_ERROR_INJECTION and are not in denylist. + */ + if (!check_non_sleepable_error_inject(btf_id) && + within_error_injection_list(addr)) + ret = 0; + break; + case BPF_PROG_TYPE_LSM: + /* LSM progs check that they are attached to bpf_lsm_*() funcs. + * Only some of them are sleepable. + */ + if (check_sleepable_lsm_hook(btf_id)) + ret = 0; + break; + default: + break; + } + if (ret) + verbose(env, "%s is not sleepable\n", + prog->aux->attach_func_name); + } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) { ret = check_attach_modify_return(prog, addr); if (ret) verbose(env, "%s() is not modifiable\n", prog->aux->attach_func_name); } - if (ret) goto out; tr->func.addr = (void *)addr; diff --git a/kernel/capability.c b/kernel/capability.c index 1444f3954d75..7c59b096c98a 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -93,7 +93,7 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) break; case _LINUX_CAPABILITY_VERSION_2: warn_deprecated_v2(); - /* fall through - v3 is otherwise equivalent to v2. */ + fallthrough; /* v3 is otherwise equivalent to v2 */ case _LINUX_CAPABILITY_VERSION_3: *tocopy = _LINUX_CAPABILITY_U32S_3; break; diff --git a/kernel/compat.c b/kernel/compat.c index b8d2800bb4b7..05adfd6fa8bf 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -255,11 +255,11 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat) return -EFAULT; switch (_NSIG_WORDS) { case 4: set->sig[3] = v.sig[6] | (((long)v.sig[7]) << 32 ); - /* fall through */ + fallthrough; case 3: set->sig[2] = v.sig[4] | (((long)v.sig[5]) << 32 ); - /* fall through */ + fallthrough; case 2: set->sig[1] = v.sig[2] | (((long)v.sig[3]) << 32 ); - /* fall through */ + fallthrough; case 1: set->sig[0] = v.sig[0] | (((long)v.sig[1]) << 32 ); } #else diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index a790026e42d0..cc3c43dfec44 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -1046,14 +1046,14 @@ int gdb_serial_stub(struct kgdb_state *ks) return DBG_PASS_EVENT; } #endif - /* Fall through */ + fallthrough; case 'C': /* Exception passing */ tmp = gdb_cmd_exception_pass(ks); if (tmp > 0) goto default_handle; if (tmp == 0) break; - /* Fall through - on tmp < 0 */ + fallthrough; /* on tmp < 0 */ case 'c': /* Continue packet */ case 's': /* Single step packet */ if (kgdb_contthread && kgdb_contthread != current) { @@ -1062,7 +1062,7 @@ int gdb_serial_stub(struct kgdb_state *ks) break; } dbg_activate_sw_breakpoints(); - /* Fall through - to default processing */ + fallthrough; /* to default processing */ default: default_handle: error = kgdb_arch_handle_exception(ks->ex_vector, diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c index 750497b0003a..f877a0a0d7cf 100644 --- a/kernel/debug/kdb/kdb_keyboard.c +++ b/kernel/debug/kdb/kdb_keyboard.c @@ -173,11 +173,11 @@ int kdb_get_kbd_char(void) case KT_LATIN: if (isprint(keychar)) break; /* printable characters */ - /* fall through */ + fallthrough; case KT_SPEC: if (keychar == K_ENTER) break; - /* fall through */ + fallthrough; default: return -1; /* ignore unprintables */ } diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 004c5b6c87f8..6226502ce049 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -432,7 +432,7 @@ int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size) *word = w8; break; } - /* fall through */ + fallthrough; default: diag = KDB_BADWIDTH; kdb_printf("kdb_getphysword: bad width %ld\n", (long) size); @@ -481,7 +481,7 @@ int kdb_getword(unsigned long *word, unsigned long addr, size_t size) *word = w8; break; } - /* fall through */ + fallthrough; default: diag = KDB_BADWIDTH; kdb_printf("kdb_getword: bad width %ld\n", (long) size); @@ -525,7 +525,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size) diag = kdb_putarea(addr, w8); break; } - /* fall through */ + fallthrough; default: diag = KDB_BADWIDTH; kdb_printf("kdb_putword: bad width %ld\n", (long) size); diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index bb0041e99659..db6ef07aec3b 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -43,7 +43,7 @@ u64 dma_direct_get_required_mask(struct device *dev) return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; } -gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, +static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, u64 *phys_limit) { u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit); @@ -68,7 +68,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, return 0; } -bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) +static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) { return phys_to_dma_direct(dev, phys) + size - 1 <= min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); @@ -161,8 +161,13 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, size = PAGE_ALIGN(size); if (dma_should_alloc_from_pool(dev, gfp, attrs)) { - ret = dma_alloc_from_pool(dev, size, &page, gfp); - if (!ret) + u64 phys_mask; + + gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, + &phys_mask); + page = dma_alloc_from_pool(dev, size, &ret, gfp, + dma_coherent_ok); + if (!page) return NULL; goto done; } diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 6bc74a2d5127..1281c0f0442b 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -3,7 +3,9 @@ * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2020 Google LLC */ +#include <linux/cma.h> #include <linux/debugfs.h> +#include <linux/dma-contiguous.h> #include <linux/dma-direct.h> #include <linux/dma-noncoherent.h> #include <linux/init.h> @@ -55,11 +57,34 @@ static void dma_atomic_pool_size_add(gfp_t gfp, size_t size) pool_size_kernel += size; } +static bool cma_in_zone(gfp_t gfp) +{ + unsigned long size; + phys_addr_t end; + struct cma *cma; + + cma = dev_get_cma_area(NULL); + if (!cma) + return false; + + size = cma_get_size(cma); + if (!size) + return false; + + /* CMA can't cross zone boundaries, see cma_activate_area() */ + end = cma_get_base(cma) + size - 1; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + return end <= DMA_BIT_MASK(zone_dma_bits); + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return end <= DMA_BIT_MASK(32); + return true; +} + static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, gfp_t gfp) { unsigned int order; - struct page *page; + struct page *page = NULL; void *addr; int ret = -ENOMEM; @@ -68,7 +93,11 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, do { pool_size = 1 << (PAGE_SHIFT + order); - page = alloc_pages(gfp, order); + if (cma_in_zone(gfp)) + page = dma_alloc_from_contiguous(NULL, 1 << order, + order, false); + if (!page) + page = alloc_pages(gfp, order); } while (!page && order-- > 0); if (!page) goto out; @@ -196,93 +225,75 @@ static int __init dma_atomic_pool_init(void) } postcore_initcall(dma_atomic_pool_init); -static inline struct gen_pool *dma_guess_pool_from_device(struct device *dev) +static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp) { - u64 phys_mask; - gfp_t gfp; - - gfp = dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, - &phys_mask); - if (IS_ENABLED(CONFIG_ZONE_DMA) && gfp == GFP_DMA) + if (prev == NULL) { + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return atomic_pool_dma32; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + return atomic_pool_dma; + return atomic_pool_kernel; + } + if (prev == atomic_pool_kernel) + return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma; + if (prev == atomic_pool_dma32) return atomic_pool_dma; - if (IS_ENABLED(CONFIG_ZONE_DMA32) && gfp == GFP_DMA32) - return atomic_pool_dma32; - return atomic_pool_kernel; + return NULL; } -static inline struct gen_pool *dma_get_safer_pool(struct gen_pool *bad_pool) +static struct page *__dma_alloc_from_pool(struct device *dev, size_t size, + struct gen_pool *pool, void **cpu_addr, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) { - if (bad_pool == atomic_pool_kernel) - return atomic_pool_dma32 ? : atomic_pool_dma; + unsigned long addr; + phys_addr_t phys; - if (bad_pool == atomic_pool_dma32) - return atomic_pool_dma; + addr = gen_pool_alloc(pool, size); + if (!addr) + return NULL; - return NULL; -} + phys = gen_pool_virt_to_phys(pool, addr); + if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) { + gen_pool_free(pool, addr, size); + return NULL; + } -static inline struct gen_pool *dma_guess_pool(struct device *dev, - struct gen_pool *bad_pool) -{ - if (bad_pool) - return dma_get_safer_pool(bad_pool); + if (gen_pool_avail(pool) < atomic_pool_size) + schedule_work(&atomic_pool_work); - return dma_guess_pool_from_device(dev); + *cpu_addr = (void *)addr; + memset(*cpu_addr, 0, size); + return pfn_to_page(__phys_to_pfn(phys)); } -void *dma_alloc_from_pool(struct device *dev, size_t size, - struct page **ret_page, gfp_t flags) +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t gfp, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) { struct gen_pool *pool = NULL; - unsigned long val = 0; - void *ptr = NULL; - phys_addr_t phys; - - while (1) { - pool = dma_guess_pool(dev, pool); - if (!pool) { - WARN(1, "Failed to get suitable pool for %s\n", - dev_name(dev)); - break; - } - - val = gen_pool_alloc(pool, size); - if (!val) - continue; - - phys = gen_pool_virt_to_phys(pool, val); - if (dma_coherent_ok(dev, phys, size)) - break; - - gen_pool_free(pool, val, size); - val = 0; - } - - - if (val) { - *ret_page = pfn_to_page(__phys_to_pfn(phys)); - ptr = (void *)val; - memset(ptr, 0, size); + struct page *page; - if (gen_pool_avail(pool) < atomic_pool_size) - schedule_work(&atomic_pool_work); + while ((pool = dma_guess_pool(pool, gfp))) { + page = __dma_alloc_from_pool(dev, size, pool, cpu_addr, + phys_addr_ok); + if (page) + return page; } - return ptr; + WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev)); + return NULL; } bool dma_free_from_pool(struct device *dev, void *start, size_t size) { struct gen_pool *pool = NULL; - while (1) { - pool = dma_guess_pool(dev, pool); - if (!pool) - return false; - - if (gen_pool_has_addr(pool, (unsigned long)start, size)) { - gen_pool_free(pool, (unsigned long)start, size); - return true; - } + while ((pool = dma_guess_pool(pool, 0))) { + if (!gen_pool_has_addr(pool, (unsigned long)start, size)) + continue; + gen_pool_free(pool, (unsigned long)start, size); + return true; } + + return false; } diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 9852e0d62d95..fcae019158ca 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -65,7 +65,8 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, syscall_enter_audit(regs, syscall); - return ret ? : syscall; + /* The above might have changed the syscall number */ + return ret ? : syscall_get_nr(current, regs); } noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall) diff --git a/kernel/events/core.c b/kernel/events/core.c index 5bfe8e3c6e44..7ed5248f0445 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10034,7 +10034,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, case IF_SRC_KERNELADDR: case IF_SRC_KERNEL: kernel = 1; - /* fall through */ + fallthrough; case IF_SRC_FILEADDR: case IF_SRC_FILE: diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 649fd53dc9ad..0e18aaf23a7b 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -205,7 +205,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, try_to_free_swap(old_page); page_vma_mapped_walk_done(&pvmw); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page)) munlock_vma_page(old_page); put_page(old_page); diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index 3110c77230c7..bb4b680e8455 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -4,6 +4,7 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" depends on DEBUG_FS + depends on !CC_IS_GCC || GCC_VERSION < 100000 select CONSTRUCTORS if !UML default n help diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index a8e14c80b405..762a928e18f9 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -173,7 +173,7 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags __irq_wake_thread(desc, action); - /* Fall through - to add to randomness */ + fallthrough; /* to add to randomness */ case IRQ_HANDLED: *flags |= action->flags; break; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 52ac5391dcc6..5df903fccb60 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -271,7 +271,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); - /* fall through */ + fallthrough; case IRQ_SET_MASK_OK_NOCOPY: irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); @@ -868,7 +868,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags) case IRQ_SET_MASK_OK_DONE: irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK); irqd_set(&desc->irq_data, flags); - /* fall through */ + fallthrough; case IRQ_SET_MASK_OK_NOCOPY: flags = irqd_get_trigger_type(&desc->irq_data); diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 30cc217b8631..651a4ad6d711 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -380,6 +380,13 @@ int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, unsigned int cpu, bit; struct cpumap *cm; + /* + * Not required in theory, but matrix_find_best_cpu() uses + * for_each_cpu() which ignores the cpumask on UP . + */ + if (cpumask_empty(msk)) + return -EINVAL; + cpu = matrix_find_best_cpu(m, msk); if (cpu == UINT_MAX) return -ENOSPC; diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 95cb74f73292..4fb15fa96734 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -684,12 +684,12 @@ bool kallsyms_show_value(const struct cred *cred) case 0: if (kallsyms_for_perf()) return true; - /* fallthrough */ + fallthrough; case 1: if (security_capable(cred, &init_user_ns, CAP_SYSLOG, CAP_OPT_NOAUDIT) == 0) return true; - /* fallthrough */ + fallthrough; default: return false; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 2fad21d345b0..54b74fabf40c 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3756,7 +3756,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip) skip_checks: /* we'll do an OFF -> ON transition: */ - this_cpu_write(hardirqs_enabled, 1); + __this_cpu_write(hardirqs_enabled, 1); trace->hardirq_enable_ip = ip; trace->hardirq_enable_event = ++trace->irq_events; debug_atomic_inc(hardirqs_on_events); @@ -3795,7 +3795,7 @@ void noinstr lockdep_hardirqs_off(unsigned long ip) /* * We have done an ON -> OFF transition: */ - this_cpu_write(hardirqs_enabled, 0); + __this_cpu_write(hardirqs_enabled, 0); trace->hardirq_disable_ip = ip; trace->hardirq_disable_event = ++trace->irq_events; debug_atomic_inc(hardirqs_off_events); @@ -4977,6 +4977,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, { unsigned long flags; + trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); + if (unlikely(current->lockdep_recursion)) { /* XXX allow trylock from NMI ?!? */ if (lockdep_nmi() && !trylock) { @@ -5001,7 +5003,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, check_flags(flags); current->lockdep_recursion++; - trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); __lock_acquire(lock, subclass, trylock, read, check, irqs_disabled_flags(flags), nest_lock, ip, 0, 0); lockdep_recursion_finish(); @@ -5013,13 +5014,15 @@ void lock_release(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; + trace_lock_release(lock, ip); + if (unlikely(current->lockdep_recursion)) return; raw_local_irq_save(flags); check_flags(flags); + current->lockdep_recursion++; - trace_lock_release(lock, ip); if (__lock_release(lock, ip)) check_chain_key(current); lockdep_recursion_finish(); @@ -5205,8 +5208,6 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip) hlock->holdtime_stamp = now; } - trace_lock_acquired(lock, ip); - stats = get_lock_stats(hlock_class(hlock)); if (waittime) { if (hlock->read) @@ -5225,6 +5226,8 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; + trace_lock_acquired(lock, ip); + if (unlikely(!lock_stat || !debug_locks)) return; @@ -5234,7 +5237,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion++; - trace_lock_contended(lock, ip); __lock_contended(lock, ip); lockdep_recursion_finish(); raw_local_irq_restore(flags); @@ -5245,6 +5247,8 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; + trace_lock_contended(lock, ip); + if (unlikely(!lock_stat || !debug_locks)) return; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index f33769f97aca..e7aa57fb2fdc 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -659,7 +659,7 @@ static void power_down(void) break; case HIBERNATION_PLATFORM: hibernation_platform_enter(); - /* Fall through */ + fallthrough; case HIBERNATION_SHUTDOWN: if (pm_power_off) kernel_power_off(); diff --git a/kernel/power/qos.c b/kernel/power/qos.c index db0bed2cae26..ec7e1e85923e 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -119,7 +119,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, * and add, then see if the aggregate has changed. */ plist_del(node, &c->list); - /* fall through */ + fallthrough; case PM_QOS_ADD_REQ: plist_node_init(node, new_value); plist_add(node, &c->list); @@ -188,7 +188,7 @@ bool pm_qos_update_flags(struct pm_qos_flags *pqf, break; case PM_QOS_UPDATE_REQ: pm_qos_flags_remove_req(pqf, req); - /* fall through */ + fallthrough; case PM_QOS_ADD_REQ: req->flags = val; INIT_LIST_HEAD(&req->node); diff --git a/kernel/relay.c b/kernel/relay.c index 72fe443ea78f..fb4e0c530c08 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -197,6 +197,7 @@ free_buf: static void relay_destroy_channel(struct kref *kref) { struct rchan *chan = container_of(kref, struct rchan, kref); + free_percpu(chan->buf); kfree(chan); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8471a0f7eb32..2d95dc3f4644 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2320,7 +2320,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) state = possible; break; } - /* Fall-through */ + fallthrough; case possible: do_set_cpus_allowed(p, cpu_possible_mask); state = fail; diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 6bf34986f45c..f324dc36fc43 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -54,17 +54,18 @@ __setup("hlt", cpu_idle_nopoll_setup); static noinline int __cpuidle cpu_idle_poll(void) { + trace_cpu_idle(0, smp_processor_id()); + stop_critical_timings(); rcu_idle_enter(); - trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); - stop_critical_timings(); while (!tif_need_resched() && - (cpu_idle_force_poll || tick_check_broadcast_expired())) + (cpu_idle_force_poll || tick_check_broadcast_expired())) cpu_relax(); - start_critical_timings(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); + rcu_idle_exit(); + start_critical_timings(); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); return 1; } @@ -90,9 +91,14 @@ void __cpuidle default_idle_call(void) if (current_clr_polling_and_test()) { local_irq_enable(); } else { + + trace_cpu_idle(1, smp_processor_id()); stop_critical_timings(); + rcu_idle_enter(); arch_cpu_idle(); + rcu_idle_exit(); start_critical_timings(); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } } @@ -158,7 +164,6 @@ static void cpuidle_idle_call(void) if (cpuidle_not_available(drv, dev)) { tick_nohz_idle_stop_tick(); - rcu_idle_enter(); default_idle_call(); goto exit_idle; @@ -178,21 +183,17 @@ static void cpuidle_idle_call(void) u64 max_latency_ns; if (idle_should_enter_s2idle()) { - rcu_idle_enter(); entered_state = call_cpuidle_s2idle(drv, dev); if (entered_state > 0) goto exit_idle; - rcu_idle_exit(); - max_latency_ns = U64_MAX; } else { max_latency_ns = dev->forced_idle_latency_limit_ns; } tick_nohz_idle_stop_tick(); - rcu_idle_enter(); next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns); call_cpuidle(drv, dev, next_state); @@ -209,8 +210,6 @@ static void cpuidle_idle_call(void) else tick_nohz_idle_retain_tick(); - rcu_idle_enter(); - entered_state = call_cpuidle(drv, dev, next_state); /* * Give the governor an opportunity to reflect on the outcome @@ -226,8 +225,6 @@ exit_idle: */ if (WARN_ON_ONCE(irqs_disabled())) local_irq_enable(); - - rcu_idle_exit(); } /* diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 007b0a6b0152..1bd7e3af904f 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1219,13 +1219,13 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what, case sa_rootdomain: if (!atomic_read(&d->rd->refcount)) free_rootdomain(&d->rd->rcu); - /* Fall through */ + fallthrough; case sa_sd: free_percpu(d->sd); - /* Fall through */ + fallthrough; case sa_sd_storage: __sdt_free(cpu_map); - /* Fall through */ + fallthrough; case sa_none: break; } diff --git a/kernel/signal.c b/kernel/signal.c index 42b67d2cea37..a38b3edc6851 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -851,7 +851,7 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info, */ if (!sid || sid == task_session(current)) break; - /* fall through */ + fallthrough; default: return -EPERM; } diff --git a/kernel/sys.c b/kernel/sys.c index ca11af9d815d..ab6c409b1159 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1753,7 +1753,7 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) if (who == RUSAGE_CHILDREN) break; - /* fall through */ + fallthrough; case RUSAGE_SELF: thread_group_cputime_adjusted(p, &tgutime, &tgstime); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 287862f91717..09e70ee2332e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -204,8 +204,7 @@ static int max_extfrag_threshold = 1000; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL) static int bpf_stats_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; static int saved_val; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index c4038511d5c9..95b6a708b040 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -377,7 +377,7 @@ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); - /* fall through */ + fallthrough; default: return false; } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 07709ac30439..bf540f5a4115 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -439,12 +439,12 @@ static struct pid *good_sigevent(sigevent_t * event) rtn = pid_task(pid, PIDTYPE_PID); if (!rtn || !same_thread_group(rtn, current)) return NULL; - /* FALLTHRU */ + fallthrough; case SIGEV_SIGNAL: case SIGEV_THREAD: if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX) return NULL; - /* FALLTHRU */ + fallthrough; case SIGEV_NONE: return pid; default: diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index e51778c312f1..36d7464c8962 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -381,7 +381,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) switch (mode) { case TICK_BROADCAST_FORCE: tick_broadcast_forced = 1; - /* fall through */ + fallthrough; case TICK_BROADCAST_ON: cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { diff --git a/kernel/time/timer.c b/kernel/time/timer.c index a16764b0116e..a50364df1054 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -666,7 +666,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) case ODEBUG_STATE_ACTIVE: WARN_ON(1); - /* fall through */ + fallthrough; default: return false; } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7ba62d68885a..4b3a42fc3b24 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -745,7 +745,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) #endif case BLKTRACESTART: start = 1; - /* fall through */ + fallthrough; case BLKTRACESTOP: ret = __blk_trace_startstop(q, start); break; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a8d4f253ed77..b2a5380eb187 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1098,6 +1098,52 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = { .arg1_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz) +{ + long len; + char *p; + + if (!sz) + return 0; + + p = d_path(path, buf, sz); + if (IS_ERR(p)) { + len = PTR_ERR(p); + } else { + len = buf + sz - p; + memmove(buf, p, len); + } + + return len; +} + +BTF_SET_START(btf_allowlist_d_path) +BTF_ID(func, vfs_truncate) +BTF_ID(func, vfs_fallocate) +BTF_ID(func, dentry_open) +BTF_ID(func, vfs_getattr) +BTF_ID(func, filp_close) +BTF_SET_END(btf_allowlist_d_path) + +static bool bpf_d_path_allowed(const struct bpf_prog *prog) +{ + return btf_id_set_contains(&btf_allowlist_d_path, prog->aux->attach_btf_id); +} + +BTF_ID_LIST(bpf_d_path_btf_ids) +BTF_ID(struct, path) + +static const struct bpf_func_proto bpf_d_path_proto = { + .func = bpf_d_path, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .btf_id = bpf_d_path_btf_ids, + .allowed = bpf_d_path_allowed, +}; + const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1182,6 +1228,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_jiffies64_proto; case BPF_FUNC_get_task_stack: return &bpf_get_task_stack_proto; + case BPF_FUNC_copy_from_user: + return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; default: return NULL; } @@ -1579,6 +1627,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return prog->expected_attach_type == BPF_TRACE_ITER ? &bpf_seq_write_proto : NULL; + case BPF_FUNC_d_path: + return &bpf_d_path_proto; default: return raw_tp_prog_func_proto(func_id, prog); } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index bf44f6bbd0c3..78a678eeb140 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -499,7 +499,7 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, ptr++; break; } - /* fall through */ + fallthrough; default: parse_error(pe, FILT_ERR_TOO_MANY_PREDS, next - str); @@ -1273,7 +1273,7 @@ static int parse_pred(const char *str, void *data, switch (op) { case OP_NE: pred->not = 1; - /* Fall through */ + fallthrough; case OP_GLOB: case OP_EQ: break; diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index f74020f6bd9d..0ef8f65bd2d7 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -393,6 +393,7 @@ static void free_watch(struct rcu_head *rcu) struct watch *watch = container_of(rcu, struct watch, rcu); put_watch_queue(rcu_access_pointer(watch->queue)); + atomic_dec(&watch->cred->user->nr_watches); put_cred(watch->cred); } @@ -452,6 +453,13 @@ int add_watch_to_object(struct watch *watch, struct watch_list *wlist) watch->cred = get_current_cred(); rcu_assign_pointer(watch->watch_list, wlist); + if (atomic_inc_return(&watch->cred->user->nr_watches) > + task_rlimit(current, RLIMIT_NOFILE)) { + atomic_dec(&watch->cred->user->nr_watches); + put_cred(watch->cred); + return -EAGAIN; + } + spin_lock_bh(&wqueue->lock); kref_get(&wqueue->usage); kref_get(&watch->usage); diff --git a/lib/Makefile b/lib/Makefile index e290fc5707ea..a4a4c6864f51 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -15,11 +15,16 @@ KCOV_INSTRUMENT_debugobjects.o := n KCOV_INSTRUMENT_dynamic_debug.o := n KCOV_INSTRUMENT_fault-inject.o := n +# string.o implements standard library functions like memset/memcpy etc. +# Use -ffreestanding to ensure that the compiler does not try to "optimize" +# them into calls to themselves. +CFLAGS_string.o := -ffreestanding + # Early boot use of cmdline, don't instrument it ifdef CONFIG_AMD_MEM_ENCRYPT KASAN_SANITIZE_string.o := n -CFLAGS_string.o := -fno-stack-protector +CFLAGS_string.o += -fno-stack-protector endif # Used by KCSAN while enabled, avoid recursion. diff --git a/lib/bootconfig.c b/lib/bootconfig.c index a5f701161f6b..2c905a91d4eb 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -817,7 +817,7 @@ int __init xbc_init(char *buf, const char **emsg, int *epos) q - 2); break; } - /* Fall through */ + /* fall through */ case '=': ret = xbc_parse_kv(&p, q, c); break; diff --git a/lib/glob.c b/lib/glob.c index 0ba3ea86b546..52e3ed7e4a9b 100644 --- a/lib/glob.c +++ b/lib/glob.c @@ -102,7 +102,7 @@ bool __pure glob_match(char const *pat, char const *str) break; case '\\': d = *pat++; - /*FALLTHROUGH*/ + /* fall through */ default: /* Literal character */ literal: if (c == d) { diff --git a/lib/nlattr.c b/lib/nlattr.c index bc5b5cf608c4..80ff9fe83696 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -124,6 +124,7 @@ void nla_get_range_unsigned(const struct nla_policy *pt, range->max = U8_MAX; break; case NLA_U16: + case NLA_BINARY: range->max = U16_MAX; break; case NLA_U32: @@ -140,6 +141,7 @@ void nla_get_range_unsigned(const struct nla_policy *pt, switch (pt->validation_type) { case NLA_VALIDATE_RANGE: + case NLA_VALIDATE_RANGE_WARN_TOO_LONG: range->min = pt->min; range->max = pt->max; break; @@ -157,9 +159,10 @@ void nla_get_range_unsigned(const struct nla_policy *pt, } } -static int nla_validate_int_range_unsigned(const struct nla_policy *pt, - const struct nlattr *nla, - struct netlink_ext_ack *extack) +static int nla_validate_range_unsigned(const struct nla_policy *pt, + const struct nlattr *nla, + struct netlink_ext_ack *extack, + unsigned int validate) { struct netlink_range_validation range; u64 value; @@ -178,15 +181,39 @@ static int nla_validate_int_range_unsigned(const struct nla_policy *pt, case NLA_MSECS: value = nla_get_u64(nla); break; + case NLA_BINARY: + value = nla_len(nla); + break; default: return -EINVAL; } nla_get_range_unsigned(pt, &range); + if (pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG && + pt->type == NLA_BINARY && value > range.max) { + pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", + current->comm, pt->type); + if (validate & NL_VALIDATE_STRICT_ATTRS) { + NL_SET_ERR_MSG_ATTR(extack, nla, + "invalid attribute length"); + return -EINVAL; + } + + /* this assumes min <= max (don't validate against min) */ + return 0; + } + if (value < range.min || value > range.max) { - NL_SET_ERR_MSG_ATTR(extack, nla, - "integer out of range"); + bool binary = pt->type == NLA_BINARY; + + if (binary) + NL_SET_ERR_MSG_ATTR(extack, nla, + "binary attribute size out of range"); + else + NL_SET_ERR_MSG_ATTR(extack, nla, + "integer out of range"); + return -ERANGE; } @@ -274,7 +301,8 @@ static int nla_validate_int_range_signed(const struct nla_policy *pt, static int nla_validate_int_range(const struct nla_policy *pt, const struct nlattr *nla, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + unsigned int validate) { switch (pt->type) { case NLA_U8: @@ -282,7 +310,8 @@ static int nla_validate_int_range(const struct nla_policy *pt, case NLA_U32: case NLA_U64: case NLA_MSECS: - return nla_validate_int_range_unsigned(pt, nla, extack); + case NLA_BINARY: + return nla_validate_range_unsigned(pt, nla, extack, validate); case NLA_S8: case NLA_S16: case NLA_S32: @@ -313,10 +342,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype, BUG_ON(pt->type > NLA_TYPE_MAX); - if ((nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) || - (pt->type == NLA_EXACT_LEN && - pt->validation_type == NLA_VALIDATE_WARN_TOO_LONG && - attrlen != pt->len)) { + if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, type); if (validate & NL_VALIDATE_STRICT_ATTRS) { @@ -449,19 +475,10 @@ static int validate_nla(const struct nlattr *nla, int maxtype, "Unsupported attribute"); return -EINVAL; } - /* fall through */ - case NLA_MIN_LEN: if (attrlen < pt->len) goto out_err; break; - case NLA_EXACT_LEN: - if (pt->validation_type != NLA_VALIDATE_WARN_TOO_LONG) { - if (attrlen != pt->len) - goto out_err; - break; - } - /* fall through */ default: if (pt->len) minlen = pt->len; @@ -479,9 +496,10 @@ static int validate_nla(const struct nlattr *nla, int maxtype, break; case NLA_VALIDATE_RANGE_PTR: case NLA_VALIDATE_RANGE: + case NLA_VALIDATE_RANGE_WARN_TOO_LONG: case NLA_VALIDATE_MIN: case NLA_VALIDATE_MAX: - err = nla_validate_int_range(pt, nla, extack); + err = nla_validate_int_range(pt, nla, extack, validate); if (err) return err; break; @@ -816,8 +834,7 @@ EXPORT_SYMBOL(__nla_reserve); struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { - if (nla_need_padding_for_64bit(skb)) - nla_align_64bit(skb, padattr); + nla_align_64bit(skb, padattr); return __nla_reserve(skb, attrtype, attrlen); } diff --git a/lib/vsprintf.c b/lib/vsprintf.c index c155769559ab..afb9521ddf91 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1681,7 +1681,8 @@ char *uuid_string(char *buf, char *end, const u8 *addr, switch (*(++fmt)) { case 'L': - uc = true; /* fall-through */ + uc = true; + /* fall through */ case 'l': index = guid_index; break; @@ -2218,7 +2219,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); - /* Fallthrough */ + /* fall through */ case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': @@ -2467,7 +2468,7 @@ qualifier: * utility, treat it as any other invalid or * unsupported format specifier. */ - /* Fall-through */ + /* fall through */ default: WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c index 9f336bc07ed6..65a1aad8c223 100644 --- a/lib/xz/xz_dec_lzma2.c +++ b/lib/xz/xz_dec_lzma2.c @@ -1043,7 +1043,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, s->lzma2.sequence = SEQ_LZMA_PREPARE; - /* Fall through */ + /* fall through */ case SEQ_LZMA_PREPARE: if (s->lzma2.compressed < RC_INIT_BYTES) @@ -1055,7 +1055,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, s->lzma2.compressed -= RC_INIT_BYTES; s->lzma2.sequence = SEQ_LZMA_RUN; - /* Fall through */ + /* fall through */ case SEQ_LZMA_RUN: /* diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c index bd1d182419d7..32ab2a08b7cb 100644 --- a/lib/xz/xz_dec_stream.c +++ b/lib/xz/xz_dec_stream.c @@ -583,7 +583,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) if (ret != XZ_OK) return ret; - /* Fall through */ + /* fall through */ case SEQ_BLOCK_START: /* We need one byte of input to continue. */ @@ -608,7 +608,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) s->temp.pos = 0; s->sequence = SEQ_BLOCK_HEADER; - /* Fall through */ + /* fall through */ case SEQ_BLOCK_HEADER: if (!fill_temp(s, b)) @@ -620,7 +620,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) s->sequence = SEQ_BLOCK_UNCOMPRESS; - /* Fall through */ + /* fall through */ case SEQ_BLOCK_UNCOMPRESS: ret = dec_block(s, b); @@ -629,7 +629,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) s->sequence = SEQ_BLOCK_PADDING; - /* Fall through */ + /* fall through */ case SEQ_BLOCK_PADDING: /* @@ -651,7 +651,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) s->sequence = SEQ_BLOCK_CHECK; - /* Fall through */ + /* fall through */ case SEQ_BLOCK_CHECK: if (s->check_type == XZ_CHECK_CRC32) { @@ -675,7 +675,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) s->sequence = SEQ_INDEX_PADDING; - /* Fall through */ + /* fall through */ case SEQ_INDEX_PADDING: while ((s->index.size + (b->in_pos - s->in_start)) @@ -699,7 +699,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) s->sequence = SEQ_INDEX_CRC32; - /* Fall through */ + /* fall through */ case SEQ_INDEX_CRC32: ret = crc32_validate(s, b); @@ -709,7 +709,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) s->temp.size = STREAM_HEADER_SIZE; s->sequence = SEQ_STREAM_FOOTER; - /* Fall through */ + /* fall through */ case SEQ_STREAM_FOOTER: if (!fill_temp(s, b)) diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c index 269ee9a796c1..db6761ea4deb 100644 --- a/lib/zstd/decompress.c +++ b/lib/zstd/decompress.c @@ -442,7 +442,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx *dctx, const void *src, size_t srcSize case set_repeat: if (dctx->litEntropy == 0) return ERROR(dictionary_corrupted); - /* fall-through */ + /* fall through */ case set_compressed: if (srcSize < 5) return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */ @@ -2309,7 +2309,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB switch (zds->stage) { case zdss_init: ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */ - /* fall-through */ + /* fall through */ case zdss_loadHeader: { size_t const hSize = ZSTD_getFrameParams(&zds->fParams, zds->headerBuffer, zds->lhSize); @@ -2376,7 +2376,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB } zds->stage = zdss_read; } - /* fall through */ + /* fall through */ case zdss_read: { size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx); @@ -2405,7 +2405,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB zds->stage = zdss_load; /* pass-through */ } - /* fall through */ + /* fall through */ case zdss_load: { size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx); @@ -2438,7 +2438,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB /* pass-through */ } } - /* fall through */ + /* fall through */ case zdss_flush: { size_t const toFlushSize = zds->outEnd - zds->outStart; diff --git a/mm/filemap.c b/mm/filemap.c index 1aaea26556cc..054d93a86f8a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -827,10 +827,10 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -static int __add_to_page_cache_locked(struct page *page, - struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask, - void **shadowp) +noinline int __add_to_page_cache_locked(struct page *page, + struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask, + void **shadowp) { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); @@ -381,22 +381,13 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, } /* - * FOLL_FORCE or a forced COW break can write even to unwritable pte's, - * but only after we've gone through a COW cycle and they are dirty. + * FOLL_FORCE can write to even unwritable pte's, but only + * after we've gone through a COW cycle and they are dirty. */ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) { - return pte_write(pte) || ((flags & FOLL_COW) && pte_dirty(pte)); -} - -/* - * A (separate) COW fault might break the page the other way and - * get_user_pages() would return the page from what is now the wrong - * VM. So we need to force a COW break at GUP time even for reads. - */ -static inline bool should_force_cow_break(struct vm_area_struct *vma, unsigned int flags) -{ - return is_cow_mapping(vma->vm_flags) && (flags & (FOLL_GET | FOLL_PIN)); + return pte_write(pte) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -843,7 +834,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, goto unmap; *page = pte_page(*pte); } - if (unlikely(!try_get_page(*page))) { + if (unlikely(!try_grab_page(*page, gup_flags))) { ret = -ENOMEM; goto unmap; } @@ -1067,11 +1058,9 @@ static long __get_user_pages(struct mm_struct *mm, goto out; } if (is_vm_hugetlb_page(vma)) { - if (should_force_cow_break(vma, foll_flags)) - foll_flags |= FOLL_WRITE; i = follow_hugetlb_page(mm, vma, pages, vmas, &start, &nr_pages, i, - foll_flags, locked); + gup_flags, locked); if (locked && *locked == 0) { /* * We've got a VM_FAULT_RETRY @@ -1085,10 +1074,6 @@ static long __get_user_pages(struct mm_struct *mm, continue; } } - - if (should_force_cow_break(vma, foll_flags)) - foll_flags |= FOLL_WRITE; - retry: /* * If we have a pending SIGKILL, don't keep faulting pages and @@ -2689,19 +2674,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, return -EFAULT; /* - * The FAST_GUP case requires FOLL_WRITE even for pure reads, - * because get_user_pages() may need to cause an early COW in - * order to avoid confusing the normal COW routines. So only - * targets that are already writable are safe to do by just - * looking at the page tables. - * - * NOTE! With FOLL_FAST_ONLY we allow read-only gup_fast() here, - * because there is no slow path to fall back on. But you'd - * better be careful about possible COW pages - you'll get _a_ - * COW page, but not necessarily the one you intended to get - * depending on what COW event happens after this. COW may break - * the page copy in a random direction. - * * Disable interrupts. The nested form is used, in order to allow * full, general purpose use of this routine. * @@ -2714,8 +2686,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, */ if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && gup_fast_permitted(start, end)) { unsigned long fast_flags = gup_flags; - if (!(gup_flags & FOLL_FAST_ONLY)) - fast_flags |= FOLL_WRITE; local_irq_save(flags); gup_pgd_range(addr, end, fast_flags, pages, &nr_pinned); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2ccff8472cd4..7ff29cc3d55c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1291,12 +1291,13 @@ fallback: } /* - * FOLL_FORCE or a forced COW break can write even to unwritable pmd's, - * but only after we've gone through a COW cycle and they are dirty. + * FOLL_FORCE can write to even unwritable pmd's, but only + * after we've gone through a COW cycle and they are dirty. */ static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) { - return pmd_write(pmd) || ((flags & FOLL_COW) && pmd_dirty(pmd)); + return pmd_write(pmd) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index aabf65d4d91b..1f87aec9ab5c 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -655,7 +655,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events", buf); cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_show; - cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]), + cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]); cft->flags = CFTYPE_NOT_ON_ROOT; /* Add the events.local file */ @@ -664,7 +664,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_local_show; cft->file_offset = offsetof(struct hugetlb_cgroup, - events_local_file[idx]), + events_local_file[idx]); cft->flags = CFTYPE_NOT_ON_ROOT; /* NULL terminate the last cft */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 15a9af791014..e749e568e1ea 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -466,7 +466,7 @@ int __khugepaged_enter(struct mm_struct *mm) return -ENOMEM; /* __khugepaged_exit() must not run from under us */ - VM_BUG_ON_MM(khugepaged_test_exit(mm), mm); + VM_BUG_ON_MM(atomic_read(&mm->mm_users) == 0, mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { free_mm_slot(mm_slot); return 0; @@ -2453,6 +2453,10 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, if (vma_is_dax(vma)) return 0; +#ifdef VM_SAO + if (*vm_flags & VM_SAO) + return 0; +#endif #ifdef VM_SPARC_ADI if (*vm_flags & VM_SPARC_ADI) return 0; @@ -2657,31 +2661,6 @@ again: goto again; } -bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, - unsigned long address) -{ -#ifdef CONFIG_DEBUG_VM - if (WARN_ON(is_zero_pfn(page_to_pfn(page))) || - WARN_ON(!page_mapped(page)) || - WARN_ON(!PageLocked(page))) { - dump_page(page, "reuse_ksm_page"); - return false; - } -#endif - - if (PageSwapCache(page) || !page_stable_node(page)) - return false; - /* Prohibit parallel get_ksm_page() */ - if (!page_ref_freeze(page, 1)) - return false; - - page_move_anon_rmap(page, vma); - page->index = linear_page_index(vma, address); - page_ref_unfreeze(page, 1); - - return true; -} #ifdef CONFIG_MIGRATION void ksm_migrate_page(struct page *newpage, struct page *oldpage) { diff --git a/mm/memory.c b/mm/memory.c index 3a7779d9891d..148eafb8cbb1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2622,6 +2622,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf) if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); + count_vm_event(PGREUSE); } /* @@ -2927,50 +2928,25 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * not dirty accountable. */ if (PageAnon(vmf->page)) { - int total_map_swapcount; - if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) || - page_count(vmf->page) != 1)) + struct page *page = vmf->page; + + /* PageKsm() doesn't necessarily raise the page refcount */ + if (PageKsm(page) || page_count(page) != 1) + goto copy; + if (!trylock_page(page)) + goto copy; + if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) { + unlock_page(page); goto copy; - if (!trylock_page(vmf->page)) { - get_page(vmf->page); - pte_unmap_unlock(vmf->pte, vmf->ptl); - lock_page(vmf->page); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); - if (!pte_same(*vmf->pte, vmf->orig_pte)) { - update_mmu_tlb(vma, vmf->address, vmf->pte); - unlock_page(vmf->page); - pte_unmap_unlock(vmf->pte, vmf->ptl); - put_page(vmf->page); - return 0; - } - put_page(vmf->page); - } - if (PageKsm(vmf->page)) { - bool reused = reuse_ksm_page(vmf->page, vmf->vma, - vmf->address); - unlock_page(vmf->page); - if (!reused) - goto copy; - wp_page_reuse(vmf); - return VM_FAULT_WRITE; - } - if (reuse_swap_page(vmf->page, &total_map_swapcount)) { - if (total_map_swapcount == 1) { - /* - * The page is all ours. Move it to - * our anon_vma so the rmap code will - * not search our parent or siblings. - * Protected against the rmap code by - * the page lock. - */ - page_move_anon_rmap(vmf->page, vma); - } - unlock_page(vmf->page); - wp_page_reuse(vmf); - return VM_FAULT_WRITE; } - unlock_page(vmf->page); + /* + * Ok, we've got the only map reference, and the only + * page count reference, and the page is locked, + * it's dark out, and we're wearing sunglasses. Hit it. + */ + wp_page_reuse(vmf); + unlock_page(page); + return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); @@ -4247,6 +4223,9 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vmf->vma, vmf->address, vmf->pte); } else { + /* Skip spurious TLB flush for retried page fault */ + if (vmf->flags & FAULT_FLAG_TRIED) + goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0e2bab486fea..0608f7f1236d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1302,6 +1302,11 @@ static void free_pcppages_bulk(struct zone *zone, int count, struct page *page, *tmp; LIST_HEAD(head); + /* + * Ensure proper count is passed which otherwise would stuck in the + * below while (list_empty(list)) loop. + */ + count = min(pcp->count, count); while (count) { struct list_head *list; @@ -3477,7 +3482,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ -static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return __should_fail_alloc_page(gfp_mask, order); } @@ -7888,7 +7893,7 @@ int __meminit init_per_zone_wmark_min(void) return 0; } -core_initcall(init_per_zone_wmark_min) +postcore_initcall(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so diff --git a/mm/rodata_test.c b/mm/rodata_test.c index 2a99df7beeb3..2613371945b7 100644 --- a/mm/rodata_test.c +++ b/mm/rodata_test.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "rodata_test: " fmt +#include <linux/rodata_test.h> #include <linux/uaccess.h> #include <asm/sections.h> diff --git a/mm/vmalloc.c b/mm/vmalloc.c index b482d240f9a2..be4724b916b3 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -104,6 +104,8 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); + + cond_resched(); } while (pmd++, addr = next, addr != end); } diff --git a/mm/vmstat.c b/mm/vmstat.c index e670f910cd2f..4f7b4ee6aa12 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1241,6 +1241,7 @@ const char * const vmstat_text[] = { "pglazyfreed", "pgrefill", + "pgreuse", "pgsteal_kswapd", "pgsteal_direct", "pgscan_kswapd", diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 3dd7c972677b..ec8408d1638f 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -367,7 +367,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCSHWTSTAMP: if (!net_eq(dev_net(dev), &init_net)) break; - /* fall through */ + fallthrough; case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 3debad93be1a..bc8807d9281f 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -520,7 +520,7 @@ static void xen_9pfs_front_changed(struct xenbus_device *dev, case XenbusStateClosed: if (dev->state == XenbusStateClosed) break; - /* fall through - Missed the backend's CLOSING state */ + fallthrough; /* Missed the backend's CLOSING state */ case XenbusStateClosing: xenbus_frontend_closed(dev); break; diff --git a/net/atm/common.c b/net/atm/common.c index 84367b844b14..1cfa9bf1d187 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -297,7 +297,7 @@ static int adjust_tp(struct atm_trafprm *tp, unsigned char aal) break; default: pr_warn("AAL problems ... (%d)\n", aal); - /* fall through */ + fallthrough; case ATM_AAL5: max_sdu = ATM_MAX_AAL5_PDU; } @@ -417,7 +417,7 @@ static int __vcc_connect(struct atm_vcc *vcc, struct atm_dev *dev, short vpi, case ATM_NO_AAL: /* ATM_AAL5 is also used in the "0 for default" case */ vcc->qos.aal = ATM_AAL5; - /* fall through */ + fallthrough; case ATM_AAL5: error = atm_init_aal5(vcc); vcc->stats = &dev->stats.aal5; diff --git a/net/atm/lec.c b/net/atm/lec.c index 875fc0bc1780..b570ef919c28 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -380,7 +380,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) if (mesg->content.normal.no_source_le_narp) break; - /* FALL THROUGH */ + fallthrough; case l_arp_update: lec_arp_update(priv, mesg->content.normal.mac_addr, mesg->content.normal.atm_addr, diff --git a/net/atm/resources.c b/net/atm/resources.c index 94bdc6527ee8..53236986dfe0 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -266,7 +266,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *buf, int __user *sioc_len, goto done; } } - /* fall through */ + fallthrough; case ATM_SETESIF: { unsigned char esi[ESI_LEN]; @@ -288,7 +288,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *buf, int __user *sioc_len, error = -EPERM; goto done; } - /* fall through */ + fallthrough; case ATM_GETSTAT: size = sizeof(struct atm_dev_stats); error = fetch_stats(dev, buf, cmd == ATM_GETSTATZ); @@ -361,7 +361,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *buf, int __user *sioc_len, error = -EINVAL; goto done; } - /* fall through */ + fallthrough; case ATM_SETCIRANGE: case SONET_GETSTATZ: case SONET_SETDIAG: @@ -371,7 +371,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *buf, int __user *sioc_len, error = -EPERM; goto done; } - /* fall through */ + fallthrough; default: if (IS_ENABLED(CONFIG_COMPAT) && compat) { #ifdef CONFIG_COMPAT diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index a4faf5f904d9..206d0b424712 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -27,6 +27,7 @@ #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/pkt_sched.h> +#include <linux/prandom.h> #include <linux/printk.h> #include <linux/random.h> #include <linux/rculist.h> diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index d35aca0e969a..79a7dfc32e76 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -20,6 +20,7 @@ #include <linux/kref.h> #include <linux/netdevice.h> #include <linux/nl80211.h> +#include <linux/prandom.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 0f8495b9eeb1..8c1148fc73d7 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -20,6 +20,7 @@ #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/netdevice.h> +#include <linux/prandom.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> @@ -881,6 +882,12 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, ntohl(ogm_packet->seqno), ogm_throughput, ogm_packet->ttl, ogm_packet->version, ntohs(ogm_packet->tvlv_len)); + if (batadv_is_my_mac(bat_priv, ogm_packet->orig)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: originator packet from ourself\n"); + return; + } + /* If the throughput metric is 0, immediately drop the packet. No need * to create orig_node / neigh_node for an unusable route. */ @@ -1008,11 +1015,6 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; - ogm_packet = (struct batadv_ogm2_packet *)skb->data; - - if (batadv_is_my_mac(bat_priv, ogm_packet->orig)) - goto free_skb; - batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_RX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES, skb->len + ETH_HLEN); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 91a04ca373dc..ab6cec3c7586 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -437,7 +437,10 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, skb->len + ETH_HLEN); - netif_rx(skb); + if (in_interrupt()) + netif_rx(skb); + else + netif_rx_ni(skb); out: if (primary_if) batadv_hardif_put(primary_if); @@ -1795,7 +1798,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, ret = queue_work(batadv_event_workqueue, &backbone_gw->report_work); - /* backbone_gw is unreferenced in the report work function function + /* backbone_gw is unreferenced in the report work function * if queue_work() call was successful */ if (!ret) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 9fdbe3068153..9a47ef8b95c4 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -306,7 +306,7 @@ free: * set *skb to merged packet; 2) Packet is buffered: Return true and set *skb * to NULL; 3) Error: Return false and free skb. * - * Return: true when the packet is merged or buffered, false when skb is not not + * Return: true when the packet is merged or buffered, false when skb is not * used. */ bool batadv_frag_skb_buffer(struct sk_buff **skb, diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index a18dcc686dc3..ef3f85b576c4 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -703,8 +703,10 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, chaddr_offset = *header_len + BATADV_DHCP_CHADDR_OFFSET; /* store the client address if the message is going to a client */ - if (ret == BATADV_DHCP_TO_CLIENT && - pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) { + if (ret == BATADV_DHCP_TO_CLIENT) { + if (!pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) + return BATADV_DHCP_NO; + /* check if the DHCP packet carries an Ethernet DHCP */ p = skb->data + *header_len + BATADV_DHCP_HTYPE_OFFSET; if (*p != BATADV_DHCP_HTYPE_ETHERNET) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index fa06b51c0144..dad99641df2a 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -599,7 +599,7 @@ out: /* report to the other components the maximum amount of bytes that * batman-adv can send over the wire (without considering the payload * overhead). For example, this value is used by TT to compute the - * maximum local table table size + * maximum local table size */ atomic_set(&bat_priv->packet_size_max, min_mtu); @@ -977,23 +977,6 @@ static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) } /** - * batadv_hardif_remove_interfaces() - Remove all hard interfaces - */ -void batadv_hardif_remove_interfaces(void) -{ - struct batadv_hard_iface *hard_iface, *hard_iface_tmp; - - rtnl_lock(); - list_for_each_entry_safe(hard_iface, hard_iface_tmp, - &batadv_hardif_list, list) { - list_del_rcu(&hard_iface->list); - batadv_hardif_generation++; - batadv_hardif_remove_interface(hard_iface); - } - rtnl_unlock(); -} - -/** * batadv_hard_if_event_softif() - Handle events for soft interfaces * @event: NETDEV_* event to handle * @net_dev: net_device which generated an event diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index bad2e50135e8..b1855d9d0b06 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -100,7 +100,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, struct net *net, const char *iface_name); void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, enum batadv_hard_if_cleanup autodel); -void batadv_hardif_remove_interfaces(void); int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); void batadv_hardif_release(struct kref *ref); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 519c08c2cfba..70fee9b42e25 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -137,7 +137,6 @@ static void __exit batadv_exit(void) batadv_netlink_unregister(); rtnl_link_unregister(&batadv_link_ops); unregister_netdevice_notifier(&batadv_hard_if_notifier); - batadv_hardif_remove_interfaces(); flush_workqueue(batadv_event_workqueue); destroy_workqueue(batadv_event_workqueue); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 0393bb9ed3d0..a47dc332d796 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2020.3" +#define BATADV_SOURCE_VERSION "2020.4" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index bdc4a1fba1c6..1622c3f5898f 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -207,7 +207,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; /* TODO: ask the bridge if a multicast router is present (the bridge - * is capable of performing proper RFC4286 multicast multicast router + * is capable of performing proper RFC4286 multicast router * discovery) instead of searching for a ff02::2 listener here */ ret = br_multicast_list_adjacent(dev, &bridge_mcast_list); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 48d707850f3e..61ddd6d709a0 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -26,8 +26,8 @@ #include <linux/lockdep.h> #include <linux/net.h> #include <linux/netdevice.h> +#include <linux/prandom.h> #include <linux/printk.h> -#include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@ -250,7 +250,7 @@ static void batadv_nc_path_put(struct batadv_nc_path *nc_path) /** * batadv_nc_packet_free() - frees nc packet * @nc_packet: the nc packet to free - * @dropped: whether the packet is freed because is is dropped + * @dropped: whether the packet is freed because is dropped */ static void batadv_nc_packet_free(struct batadv_nc_packet *nc_packet, bool dropped) diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index d267b94800d6..87017332b567 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -461,7 +461,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, /** * batadv_forw_packet_free() - free a forwarding packet * @forw_packet: The packet to free - * @dropped: whether the packet is freed because is is dropped + * @dropped: whether the packet is freed because is dropped * * This frees a forwarding packet and releases any resources it might * have claimed. diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 23833a0ba5e6..9d3974ba11ed 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -649,7 +649,7 @@ static void batadv_softif_destroy_vlan(struct batadv_priv *bat_priv, /** * batadv_interface_add_vid() - ndo_add_vid API implementation * @dev: the netdev of the mesh interface - * @proto: protocol of the the vlan id + * @proto: protocol of the vlan id * @vid: identifier of the new vlan * * Set up all the internal structures for handling the new vlan on top of the @@ -707,7 +707,7 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto, /** * batadv_interface_kill_vid() - ndo_kill_vid API implementation * @dev: the netdev of the mesh interface - * @proto: protocol of the the vlan id + * @proto: protocol of the vlan id * @vid: identifier of the deleted vlan * * Destroy all the internal structures used to handle the vlan identified by vid diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ed519efa3c36..965336a3b89d 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1492,7 +1492,7 @@ struct batadv_tp_vars { /** @unacked_lock: protect unacked_list */ spinlock_t unacked_lock; - /** @last_recv_time: time time (jiffies) a msg was received */ + /** @last_recv_time: time (jiffies) a msg was received */ unsigned long last_recv_time; /** @refcount: number of context where the object is used */ @@ -1996,7 +1996,7 @@ struct batadv_tt_change_node { */ struct batadv_tt_req_node { /** - * @addr: mac address address of the originator this request was sent to + * @addr: mac address of the originator this request was sent to */ u8 addr[ETH_ALEN]; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 99eb8c6c0fbc..a66f211726e7 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -425,7 +425,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: is_l2 = true; - /* fall through */ + fallthrough; case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_XMIT: diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig index 73d0b12789f1..8ad0233ce497 100644 --- a/net/bpfilter/Kconfig +++ b/net/bpfilter/Kconfig @@ -2,6 +2,7 @@ menuconfig BPFILTER bool "BPF based packet filtering framework (BPFILTER)" depends on NET && BPF && INET + select USERMODE_DRIVER help This builds experimental bpfilter framework that is aiming to provide netfilter compatible functionality via BPF diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index da5ed4cf9233..67e0976aeed2 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -77,10 +77,67 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip) #endif } +static int __mdb_fill_srcs(struct sk_buff *skb, + struct net_bridge_port_group *p) +{ + struct net_bridge_group_src *ent; + struct nlattr *nest, *nest_ent; + + if (hlist_empty(&p->src_list)) + return 0; + + nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST); + if (!nest) + return -EMSGSIZE; + + hlist_for_each_entry_rcu(ent, &p->src_list, node, + lockdep_is_held(&p->port->br->multicast_lock)) { + nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY); + if (!nest_ent) + goto out_cancel_err; + switch (ent->addr.proto) { + case htons(ETH_P_IP): + if (nla_put_in_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, + ent->addr.u.ip4)) { + nla_nest_cancel(skb, nest_ent); + goto out_cancel_err; + } + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + if (nla_put_in6_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, + &ent->addr.u.ip6)) { + nla_nest_cancel(skb, nest_ent); + goto out_cancel_err; + } + break; +#endif + default: + nla_nest_cancel(skb, nest_ent); + continue; + } + if (nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER, + br_timer_value(&ent->timer))) { + nla_nest_cancel(skb, nest_ent); + goto out_cancel_err; + } + nla_nest_end(skb, nest_ent); + } + + nla_nest_end(skb, nest); + + return 0; + +out_cancel_err: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int __mdb_fill_info(struct sk_buff *skb, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *p) { + bool dump_srcs_mode = false; struct timer_list *mtimer; struct nlattr *nest_ent; struct br_mdb_entry e; @@ -119,6 +176,23 @@ static int __mdb_fill_info(struct sk_buff *skb, nla_nest_cancel(skb, nest_ent); return -EMSGSIZE; } + switch (mp->addr.proto) { + case htons(ETH_P_IP): + dump_srcs_mode = !!(p && mp->br->multicast_igmp_version == 3); + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + dump_srcs_mode = !!(p && mp->br->multicast_mld_version == 2); + break; +#endif + } + if (dump_srcs_mode && + (__mdb_fill_srcs(skb, p) || + nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, p->filter_mode))) { + nla_nest_cancel(skb, nest_ent); + return -EMSGSIZE; + } + nla_nest_end(skb, nest_ent); return 0; @@ -127,7 +201,7 @@ static int __mdb_fill_info(struct sk_buff *skb, static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { - int idx = 0, s_idx = cb->args[1], err = 0; + int idx = 0, s_idx = cb->args[1], err = 0, pidx = 0, s_pidx = cb->args[2]; struct net_bridge *br = netdev_priv(dev); struct net_bridge_mdb_entry *mp; struct nlattr *nest, *nest2; @@ -152,7 +226,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, break; } - if (mp->host_joined) { + if (!s_pidx && mp->host_joined) { err = __mdb_fill_info(skb, mp, NULL); if (err) { nla_nest_cancel(skb, nest2); @@ -164,13 +238,19 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, pp = &p->next) { if (!p->port) continue; + if (pidx < s_pidx) + goto skip_pg; err = __mdb_fill_info(skb, mp, p); if (err) { nla_nest_cancel(skb, nest2); goto out; } +skip_pg: + pidx++; } + pidx = 0; + s_pidx = 0; nla_nest_end(skb, nest2); skip: idx++; @@ -178,6 +258,7 @@ skip: out: cb->args[1] = idx; + cb->args[2] = pidx; nla_nest_end(skb, nest); return err; } @@ -263,14 +344,15 @@ out: static int nlmsg_populate_mdb_fill(struct sk_buff *skb, struct net_device *dev, - struct br_mdb_entry *entry, u32 pid, - u32 seq, int type, unsigned int flags) + struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + int type) { struct nlmsghdr *nlh; struct br_port_msg *bpm; struct nlattr *nest, *nest2; - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0); + nlh = nlmsg_put(skb, 0, 0, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; @@ -285,7 +367,7 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb, if (nest2 == NULL) goto end; - if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(*entry), entry)) + if (__mdb_fill_info(skb, mp, pg)) goto end; nla_nest_end(skb, nest2); @@ -300,10 +382,49 @@ cancel: return -EMSGSIZE; } -static inline size_t rtnl_mdb_nlmsg_size(void) +static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg) { - return NLMSG_ALIGN(sizeof(struct br_port_msg)) - + nla_total_size(sizeof(struct br_mdb_entry)); + size_t nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) + + nla_total_size(sizeof(struct br_mdb_entry)) + + nla_total_size(sizeof(u32)); + struct net_bridge_group_src *ent; + size_t addr_size = 0; + + if (!pg) + goto out; + + switch (pg->addr.proto) { + case htons(ETH_P_IP): + if (pg->port->br->multicast_igmp_version == 2) + goto out; + addr_size = sizeof(__be32); + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + if (pg->port->br->multicast_mld_version == 1) + goto out; + addr_size = sizeof(struct in6_addr); + break; +#endif + } + + /* MDBA_MDB_EATTR_GROUP_MODE */ + nlmsg_size += nla_total_size(sizeof(u8)); + + /* MDBA_MDB_EATTR_SRC_LIST nested attr */ + if (!hlist_empty(&pg->src_list)) + nlmsg_size += nla_total_size(0); + + hlist_for_each_entry(ent, &pg->src_list, node) { + /* MDBA_MDB_SRCLIST_ENTRY nested attr + + * MDBA_MDB_SRCATTR_ADDRESS + MDBA_MDB_SRCATTR_TIMER + */ + nlmsg_size += nla_total_size(0) + + nla_total_size(addr_size) + + nla_total_size(sizeof(u32)); + } +out: + return nlmsg_size; } struct br_mdb_complete_info { @@ -341,21 +462,22 @@ err: static void br_mdb_switchdev_host_port(struct net_device *dev, struct net_device *lower_dev, - struct br_mdb_entry *entry, int type) + struct net_bridge_mdb_entry *mp, + int type) { struct switchdev_obj_port_mdb mdb = { .obj = { .id = SWITCHDEV_OBJ_ID_HOST_MDB, .flags = SWITCHDEV_F_DEFER, }, - .vid = entry->vid, + .vid = mp->addr.vid, }; - if (entry->addr.proto == htons(ETH_P_IP)) - ip_eth_mc_map(entry->addr.u.ip4, mdb.addr); + if (mp->addr.proto == htons(ETH_P_IP)) + ip_eth_mc_map(mp->addr.u.ip4, mdb.addr); #if IS_ENABLED(CONFIG_IPV6) else - ipv6_eth_mc_map(&entry->addr.u.ip6, mdb.addr); + ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr); #endif mdb.obj.orig_dev = dev; @@ -370,17 +492,19 @@ static void br_mdb_switchdev_host_port(struct net_device *dev, } static void br_mdb_switchdev_host(struct net_device *dev, - struct br_mdb_entry *entry, int type) + struct net_bridge_mdb_entry *mp, int type) { struct net_device *lower_dev; struct list_head *iter; netdev_for_each_lower_dev(dev, lower_dev, iter) - br_mdb_switchdev_host_port(dev, lower_dev, entry, type); + br_mdb_switchdev_host_port(dev, lower_dev, mp, type); } -static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, - struct br_mdb_entry *entry, int type) +void br_mdb_notify(struct net_device *dev, + struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + int type) { struct br_mdb_complete_info *complete_info; struct switchdev_obj_port_mdb mdb = { @@ -388,44 +512,45 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, .id = SWITCHDEV_OBJ_ID_PORT_MDB, .flags = SWITCHDEV_F_DEFER, }, - .vid = entry->vid, + .vid = mp->addr.vid, }; - struct net_device *port_dev; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; - port_dev = __dev_get_by_index(net, entry->ifindex); - if (entry->addr.proto == htons(ETH_P_IP)) - ip_eth_mc_map(entry->addr.u.ip4, mdb.addr); + if (pg) { + if (mp->addr.proto == htons(ETH_P_IP)) + ip_eth_mc_map(mp->addr.u.ip4, mdb.addr); #if IS_ENABLED(CONFIG_IPV6) - else - ipv6_eth_mc_map(&entry->addr.u.ip6, mdb.addr); + else + ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr); #endif - - mdb.obj.orig_dev = port_dev; - if (p && port_dev && type == RTM_NEWMDB) { - complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); - if (complete_info) { - complete_info->port = p; - __mdb_entry_to_br_ip(entry, &complete_info->ip); + mdb.obj.orig_dev = pg->port->dev; + switch (type) { + case RTM_NEWMDB: + complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); + if (!complete_info) + break; + complete_info->port = pg->port; + complete_info->ip = mp->addr; mdb.obj.complete_priv = complete_info; mdb.obj.complete = br_mdb_complete; - if (switchdev_port_obj_add(port_dev, &mdb.obj, NULL)) + if (switchdev_port_obj_add(pg->port->dev, &mdb.obj, NULL)) kfree(complete_info); + break; + case RTM_DELMDB: + switchdev_port_obj_del(pg->port->dev, &mdb.obj); + break; } - } else if (p && port_dev && type == RTM_DELMDB) { - switchdev_port_obj_del(port_dev, &mdb.obj); + } else { + br_mdb_switchdev_host(dev, mp, type); } - if (!p) - br_mdb_switchdev_host(dev, entry, type); - - skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC); + skb = nlmsg_new(rtnl_mdb_nlmsg_size(pg), GFP_ATOMIC); if (!skb) goto errout; - err = nlmsg_populate_mdb_fill(skb, dev, entry, 0, 0, type, NTF_SELF); + err = nlmsg_populate_mdb_fill(skb, dev, mp, pg, type); if (err < 0) { kfree_skb(skb); goto errout; @@ -437,26 +562,6 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } -void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, - struct br_ip *group, int type, u8 flags) -{ - struct br_mdb_entry entry; - - memset(&entry, 0, sizeof(entry)); - if (port) - entry.ifindex = port->dev->ifindex; - else - entry.ifindex = dev->ifindex; - entry.addr.proto = group->proto; - entry.addr.u.ip4 = group->u.ip4; -#if IS_ENABLED(CONFIG_IPV6) - entry.addr.u.ip6 = group->u.ip6; -#endif - entry.vid = group->vid; - __mdb_entry_fill_flags(&entry, flags); - __br_mdb_notify(dev, port, &entry, type); -} - static int nlmsg_populate_rtr_fill(struct sk_buff *skb, struct net_device *dev, int ifindex, u32 pid, @@ -600,7 +705,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, } static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, - struct br_ip *group, unsigned char state) + struct br_ip *group, struct br_mdb_entry *entry) { struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; @@ -619,12 +724,13 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, /* host join */ if (!port) { /* don't allow any flags for host-joined groups */ - if (state) + if (entry->state) return -EINVAL; if (mp->host_joined) return -EEXIST; br_multicast_host_join(mp, false); + br_mdb_notify(br->dev, mp, NULL, RTM_NEWMDB); return 0; } @@ -638,12 +744,14 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, break; } - p = br_multicast_new_port_group(port, group, *pp, state, NULL); + p = br_multicast_new_port_group(port, group, *pp, entry->state, NULL, + MCAST_EXCLUDE); if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); - if (state == MDB_TEMPORARY) + if (entry->state == MDB_TEMPORARY) mod_timer(&p->timer, now + br->multicast_membership_interval); + br_mdb_notify(br->dev, mp, p, RTM_NEWMDB); return 0; } @@ -672,7 +780,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, __mdb_entry_to_br_ip(entry, &ip); spin_lock_bh(&br->multicast_lock); - ret = br_mdb_add_group(br, p, &ip, entry->state); + ret = br_mdb_add_group(br, p, &ip, entry); spin_unlock_bh(&br->multicast_lock); return ret; } @@ -717,12 +825,9 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, err = __br_mdb_add(net, br, entry); if (err) break; - __br_mdb_notify(dev, p, entry, RTM_NEWMDB); } } else { err = __br_mdb_add(net, br, entry); - if (!err) - __br_mdb_notify(dev, p, entry, RTM_NEWMDB); } return err; @@ -750,6 +855,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (entry->ifindex == mp->br->dev->ifindex && mp->host_joined) { br_multicast_host_leave(mp, false); err = 0; + br_mdb_notify(br->dev, mp, NULL, RTM_DELMDB); if (!mp->ports && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); goto unlock; @@ -764,16 +870,8 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (p->port->state == BR_STATE_DISABLED) goto unlock; - __mdb_entry_fill_flags(entry, p->flags); - rcu_assign_pointer(*pp, p->next); - hlist_del_init(&p->mglist); - del_timer(&p->timer); - kfree_rcu(p, rcu); + br_multicast_del_pg(mp, p, pp); err = 0; - - if (!mp->ports && !mp->host_joined && - netif_running(br->dev)) - mod_timer(&mp->timer, jiffies); break; } @@ -820,13 +918,9 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; err = __br_mdb_del(br, entry); - if (!err) - __br_mdb_notify(dev, p, entry, RTM_DELMDB); } } else { err = __br_mdb_del(br, entry); - if (!err) - __br_mdb_notify(dev, p, entry, RTM_DELMDB); } return err; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 4c4a93abde68..33adf44ef7ec 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -50,6 +50,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, __be32 group, __u16 vid, const unsigned char *src); +static void br_multicast_port_group_rexmit(struct timer_list *t); static void __del_port_router(struct net_bridge_port *p); #if IS_ENABLED(CONFIG_IPV6) @@ -139,6 +140,29 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, return br_mdb_ip_get_rcu(br, &ip); } +static void br_multicast_destroy_mdb_entry(struct net_bridge_mcast_gc *gc) +{ + struct net_bridge_mdb_entry *mp; + + mp = container_of(gc, struct net_bridge_mdb_entry, mcast_gc); + WARN_ON(!hlist_unhashed(&mp->mdb_node)); + WARN_ON(mp->ports); + + del_timer_sync(&mp->timer); + kfree_rcu(mp, rcu); +} + +static void br_multicast_del_mdb_entry(struct net_bridge_mdb_entry *mp) +{ + struct net_bridge *br = mp->br; + + rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode, + br_mdb_rht_params); + hlist_del_init_rcu(&mp->mdb_node); + hlist_add_head(&mp->mcast_gc.gc_node, &br->mcast_gc_list); + queue_work(system_long_wq, &br->mcast_gc_work); +} + static void br_multicast_group_expired(struct timer_list *t) { struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer); @@ -152,23 +176,71 @@ static void br_multicast_group_expired(struct timer_list *t) if (mp->ports) goto out; + br_multicast_del_mdb_entry(mp); +out: + spin_unlock(&br->multicast_lock); +} - rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode, - br_mdb_rht_params); - hlist_del_rcu(&mp->mdb_node); +static void br_multicast_destroy_group_src(struct net_bridge_mcast_gc *gc) +{ + struct net_bridge_group_src *src; - kfree_rcu(mp, rcu); + src = container_of(gc, struct net_bridge_group_src, mcast_gc); + WARN_ON(!hlist_unhashed(&src->node)); -out: - spin_unlock(&br->multicast_lock); + del_timer_sync(&src->timer); + kfree_rcu(src, rcu); } -static void br_multicast_del_pg(struct net_bridge *br, - struct net_bridge_port_group *pg) +static void br_multicast_del_group_src(struct net_bridge_group_src *src) { + struct net_bridge *br = src->pg->port->br; + + hlist_del_init_rcu(&src->node); + src->pg->src_ents--; + hlist_add_head(&src->mcast_gc.gc_node, &br->mcast_gc_list); + queue_work(system_long_wq, &br->mcast_gc_work); +} + +static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc) +{ + struct net_bridge_port_group *pg; + + pg = container_of(gc, struct net_bridge_port_group, mcast_gc); + WARN_ON(!hlist_unhashed(&pg->mglist)); + WARN_ON(!hlist_empty(&pg->src_list)); + + del_timer_sync(&pg->rexmit_timer); + del_timer_sync(&pg->timer); + kfree_rcu(pg, rcu); +} + +void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + struct net_bridge_port_group __rcu **pp) +{ + struct net_bridge *br = pg->port->br; + struct net_bridge_group_src *ent; + struct hlist_node *tmp; + + rcu_assign_pointer(*pp, pg->next); + hlist_del_init(&pg->mglist); + hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) + br_multicast_del_group_src(ent); + br_mdb_notify(br->dev, mp, pg, RTM_DELMDB); + hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list); + queue_work(system_long_wq, &br->mcast_gc_work); + + if (!mp->ports && !mp->host_joined && netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); +} + +static void br_multicast_find_del_pg(struct net_bridge *br, + struct net_bridge_port_group *pg) +{ + struct net_bridge_port_group __rcu **pp; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; - struct net_bridge_port_group __rcu **pp; mp = br_mdb_ip_get(br, &pg->addr); if (WARN_ON(!mp)) @@ -180,17 +252,7 @@ static void br_multicast_del_pg(struct net_bridge *br, if (p != pg) continue; - rcu_assign_pointer(*pp, p->next); - hlist_del_init(&p->mglist); - del_timer(&p->timer); - br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB, - p->flags); - kfree_rcu(p, rcu); - - if (!mp->ports && !mp->host_joined && - netif_running(br->dev)) - mod_timer(&mp->timer, jiffies); - + br_multicast_del_pg(mp, pg, pp); return; } @@ -200,35 +262,95 @@ static void br_multicast_del_pg(struct net_bridge *br, static void br_multicast_port_group_expired(struct timer_list *t) { struct net_bridge_port_group *pg = from_timer(pg, t, timer); + struct net_bridge_group_src *src_ent; struct net_bridge *br = pg->port->br; + struct hlist_node *tmp; + bool changed; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || timer_pending(&pg->timer) || hlist_unhashed(&pg->mglist) || pg->flags & MDB_PG_FLAGS_PERMANENT) goto out; - br_multicast_del_pg(br, pg); + changed = !!(pg->filter_mode == MCAST_EXCLUDE); + pg->filter_mode = MCAST_INCLUDE; + hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) { + if (!timer_pending(&src_ent->timer)) { + br_multicast_del_group_src(src_ent); + changed = true; + } + } + + if (hlist_empty(&pg->src_list)) { + br_multicast_find_del_pg(br, pg); + } else if (changed) { + struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->addr); + if (WARN_ON(!mp)) + goto out; + br_mdb_notify(br->dev, mp, pg, RTM_NEWMDB); + } out: spin_unlock(&br->multicast_lock); } -static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, - __be32 group, - u8 *igmp_type) +static void br_multicast_gc(struct hlist_head *head) { + struct net_bridge_mcast_gc *gcent; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(gcent, tmp, head, gc_node) { + hlist_del_init(&gcent->gc_node); + gcent->destroy(gcent); + } +} + +static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, + struct net_bridge_port_group *pg, + __be32 ip_dst, __be32 group, + bool with_srcs, bool over_lmqt, + u8 sflag, u8 *igmp_type, + bool *need_rexmit) +{ + struct net_bridge_port *p = pg ? pg->port : NULL; + struct net_bridge_group_src *ent; + size_t pkt_size, igmp_hdr_size; + unsigned long now = jiffies; struct igmpv3_query *ihv3; - size_t igmp_hdr_size; + void *csum_start = NULL; + __sum16 *csum = NULL; struct sk_buff *skb; struct igmphdr *ih; struct ethhdr *eth; + unsigned long lmqt; struct iphdr *iph; + u16 lmqt_srcs = 0; igmp_hdr_size = sizeof(*ih); - if (br->multicast_igmp_version == 3) + if (br->multicast_igmp_version == 3) { igmp_hdr_size = sizeof(*ihv3); - skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) + - igmp_hdr_size + 4); + if (pg && with_srcs) { + lmqt = now + (br->multicast_last_member_interval * + br->multicast_last_member_count); + hlist_for_each_entry(ent, &pg->src_list, node) { + if (over_lmqt == time_after(ent->timer.expires, + lmqt) && + ent->src_query_rexmit_cnt > 0) + lmqt_srcs++; + } + + if (!lmqt_srcs) + return NULL; + igmp_hdr_size += lmqt_srcs * sizeof(__be32); + } + } + + pkt_size = sizeof(*eth) + sizeof(*iph) + 4 + igmp_hdr_size; + if ((p && pkt_size > p->dev->mtu) || + pkt_size > br->dev->mtu) + return NULL; + + skb = netdev_alloc_skb_ip_align(br->dev, pkt_size); if (!skb) goto out; @@ -238,29 +360,24 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, eth = eth_hdr(skb); ether_addr_copy(eth->h_source, br->dev->dev_addr); - eth->h_dest[0] = 1; - eth->h_dest[1] = 0; - eth->h_dest[2] = 0x5e; - eth->h_dest[3] = 0; - eth->h_dest[4] = 0; - eth->h_dest[5] = 1; + ip_eth_mc_map(ip_dst, eth->h_dest); eth->h_proto = htons(ETH_P_IP); skb_put(skb, sizeof(*eth)); skb_set_network_header(skb, skb->len); iph = ip_hdr(skb); + iph->tot_len = htons(pkt_size - sizeof(*eth)); iph->version = 4; iph->ihl = 6; iph->tos = 0xc0; - iph->tot_len = htons(sizeof(*iph) + igmp_hdr_size + 4); iph->id = 0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->protocol = IPPROTO_IGMP; iph->saddr = br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR) ? inet_select_addr(br->dev, 0, RT_SCOPE_LINK) : 0; - iph->daddr = htonl(INADDR_ALLHOSTS_GROUP); + iph->daddr = ip_dst; ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -280,7 +397,8 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, (HZ / IGMP_TIMER_SCALE); ih->group = group; ih->csum = 0; - ih->csum = ip_compute_csum((void *)ih, sizeof(*ih)); + csum = &ih->csum; + csum_start = (void *)ih; break; case 3: ihv3 = igmpv3_query_hdr(skb); @@ -290,15 +408,40 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, (HZ / IGMP_TIMER_SCALE); ihv3->group = group; ihv3->qqic = br->multicast_query_interval / HZ; - ihv3->nsrcs = 0; + ihv3->nsrcs = htons(lmqt_srcs); ihv3->resv = 0; - ihv3->suppress = 0; + ihv3->suppress = sflag; ihv3->qrv = 2; ihv3->csum = 0; - ihv3->csum = ip_compute_csum((void *)ihv3, sizeof(*ihv3)); + csum = &ihv3->csum; + csum_start = (void *)ihv3; + if (!pg || !with_srcs) + break; + + lmqt_srcs = 0; + hlist_for_each_entry(ent, &pg->src_list, node) { + if (over_lmqt == time_after(ent->timer.expires, + lmqt) && + ent->src_query_rexmit_cnt > 0) { + ihv3->srcs[lmqt_srcs++] = ent->addr.u.ip4; + ent->src_query_rexmit_cnt--; + if (need_rexmit && ent->src_query_rexmit_cnt) + *need_rexmit = true; + } + } + if (WARN_ON(lmqt_srcs != ntohs(ihv3->nsrcs))) { + kfree_skb(skb); + return NULL; + } break; } + if (WARN_ON(!csum || !csum_start)) { + kfree_skb(skb); + return NULL; + } + + *csum = ip_compute_csum(csum_start, igmp_hdr_size); skb_put(skb, igmp_hdr_size); __skb_pull(skb, sizeof(*eth)); @@ -308,23 +451,54 @@ out: #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, - const struct in6_addr *grp, - u8 *igmp_type) -{ + struct net_bridge_port_group *pg, + const struct in6_addr *ip6_dst, + const struct in6_addr *group, + bool with_srcs, bool over_llqt, + u8 sflag, u8 *igmp_type, + bool *need_rexmit) +{ + struct net_bridge_port *p = pg ? pg->port : NULL; + struct net_bridge_group_src *ent; + size_t pkt_size, mld_hdr_size; + unsigned long now = jiffies; struct mld2_query *mld2q; + void *csum_start = NULL; unsigned long interval; + __sum16 *csum = NULL; struct ipv6hdr *ip6h; struct mld_msg *mldq; - size_t mld_hdr_size; struct sk_buff *skb; + unsigned long llqt; struct ethhdr *eth; + u16 llqt_srcs = 0; u8 *hopopt; mld_hdr_size = sizeof(*mldq); - if (br->multicast_mld_version == 2) + if (br->multicast_mld_version == 2) { mld_hdr_size = sizeof(*mld2q); - skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) + - 8 + mld_hdr_size); + if (pg && with_srcs) { + llqt = now + (br->multicast_last_member_interval * + br->multicast_last_member_count); + hlist_for_each_entry(ent, &pg->src_list, node) { + if (over_llqt == time_after(ent->timer.expires, + llqt) && + ent->src_query_rexmit_cnt > 0) + llqt_srcs++; + } + + if (!llqt_srcs) + return NULL; + mld_hdr_size += llqt_srcs * sizeof(struct in6_addr); + } + } + + pkt_size = sizeof(*eth) + sizeof(*ip6h) + 8 + mld_hdr_size; + if ((p && pkt_size > p->dev->mtu) || + pkt_size > br->dev->mtu) + return NULL; + + skb = netdev_alloc_skb_ip_align(br->dev, pkt_size); if (!skb) goto out; @@ -346,7 +520,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h->payload_len = htons(8 + mld_hdr_size); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; - ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); + ip6h->daddr = *ip6_dst; if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, &ip6h->saddr)) { kfree_skb(skb); @@ -371,7 +545,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, /* ICMPv6 */ skb_set_transport_header(skb, skb->len); - interval = ipv6_addr_any(grp) ? + interval = ipv6_addr_any(group) ? br->multicast_query_response_interval : br->multicast_last_member_interval; *igmp_type = ICMPV6_MGM_QUERY; @@ -383,12 +557,9 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, mldq->mld_cksum = 0; mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval)); mldq->mld_reserved = 0; - mldq->mld_mca = *grp; - mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - sizeof(*mldq), IPPROTO_ICMPV6, - csum_partial(mldq, - sizeof(*mldq), - 0)); + mldq->mld_mca = *group; + csum = &mldq->mld_cksum; + csum_start = (void *)mldq; break; case 2: mld2q = (struct mld2_query *)icmp6_hdr(skb); @@ -398,21 +569,43 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, mld2q->mld2q_cksum = 0; mld2q->mld2q_resv1 = 0; mld2q->mld2q_resv2 = 0; - mld2q->mld2q_suppress = 0; + mld2q->mld2q_suppress = sflag; mld2q->mld2q_qrv = 2; - mld2q->mld2q_nsrcs = 0; + mld2q->mld2q_nsrcs = htons(llqt_srcs); mld2q->mld2q_qqic = br->multicast_query_interval / HZ; - mld2q->mld2q_mca = *grp; - mld2q->mld2q_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - sizeof(*mld2q), - IPPROTO_ICMPV6, - csum_partial(mld2q, - sizeof(*mld2q), - 0)); + mld2q->mld2q_mca = *group; + csum = &mld2q->mld2q_cksum; + csum_start = (void *)mld2q; + if (!pg || !with_srcs) + break; + + llqt_srcs = 0; + hlist_for_each_entry(ent, &pg->src_list, node) { + if (over_llqt == time_after(ent->timer.expires, + llqt) && + ent->src_query_rexmit_cnt > 0) { + mld2q->mld2q_srcs[llqt_srcs++] = ent->addr.u.ip6; + ent->src_query_rexmit_cnt--; + if (need_rexmit && ent->src_query_rexmit_cnt) + *need_rexmit = true; + } + } + if (WARN_ON(llqt_srcs != ntohs(mld2q->mld2q_nsrcs))) { + kfree_skb(skb); + return NULL; + } break; } - skb_put(skb, mld_hdr_size); + if (WARN_ON(!csum || !csum_start)) { + kfree_skb(skb); + return NULL; + } + + *csum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, mld_hdr_size, + IPPROTO_ICMPV6, + csum_partial(csum_start, mld_hdr_size, 0)); + skb_put(skb, mld_hdr_size); __skb_pull(skb, sizeof(*eth)); out: @@ -421,16 +614,39 @@ out: #endif static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, - struct br_ip *addr, - u8 *igmp_type) + struct net_bridge_port_group *pg, + struct br_ip *ip_dst, + struct br_ip *group, + bool with_srcs, bool over_lmqt, + u8 sflag, u8 *igmp_type, + bool *need_rexmit) { - switch (addr->proto) { + __be32 ip4_dst; + + switch (group->proto) { case htons(ETH_P_IP): - return br_ip4_multicast_alloc_query(br, addr->u.ip4, igmp_type); + ip4_dst = ip_dst ? ip_dst->u.ip4 : htonl(INADDR_ALLHOSTS_GROUP); + return br_ip4_multicast_alloc_query(br, pg, + ip4_dst, group->u.ip4, + with_srcs, over_lmqt, + sflag, igmp_type, + need_rexmit); #if IS_ENABLED(CONFIG_IPV6) - case htons(ETH_P_IPV6): - return br_ip6_multicast_alloc_query(br, &addr->u.ip6, - igmp_type); + case htons(ETH_P_IPV6): { + struct in6_addr ip6_dst; + + if (ip_dst) + ip6_dst = ip_dst->u.ip6; + else + ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0, + htonl(1)); + + return br_ip6_multicast_alloc_query(br, pg, + &ip6_dst, &group->u.ip6, + with_srcs, over_lmqt, + sflag, igmp_type, + need_rexmit); + } #endif } return NULL; @@ -457,6 +673,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, mp->br = br; mp->addr = *group; + mp->mcast_gc.destroy = br_multicast_destroy_mdb_entry; timer_setup(&mp->timer, br_multicast_group_expired, 0); err = rhashtable_lookup_insert_fast(&br->mdb_hash_tbl, &mp->rhnode, br_mdb_rht_params); @@ -470,12 +687,97 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, return mp; } +static void br_multicast_group_src_expired(struct timer_list *t) +{ + struct net_bridge_group_src *src = from_timer(src, t, timer); + struct net_bridge_port_group *pg; + struct net_bridge *br = src->br; + + spin_lock(&br->multicast_lock); + if (hlist_unhashed(&src->node) || !netif_running(br->dev) || + timer_pending(&src->timer)) + goto out; + + pg = src->pg; + if (pg->filter_mode == MCAST_INCLUDE) { + br_multicast_del_group_src(src); + if (!hlist_empty(&pg->src_list)) + goto out; + br_multicast_find_del_pg(br, pg); + } +out: + spin_unlock(&br->multicast_lock); +} + +static struct net_bridge_group_src * +br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip) +{ + struct net_bridge_group_src *ent; + + switch (ip->proto) { + case htons(ETH_P_IP): + hlist_for_each_entry(ent, &pg->src_list, node) + if (ip->u.ip4 == ent->addr.u.ip4) + return ent; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + hlist_for_each_entry(ent, &pg->src_list, node) + if (!ipv6_addr_cmp(&ent->addr.u.ip6, &ip->u.ip6)) + return ent; + break; +#endif + } + + return NULL; +} + +static struct net_bridge_group_src * +br_multicast_new_group_src(struct net_bridge_port_group *pg, struct br_ip *src_ip) +{ + struct net_bridge_group_src *grp_src; + + if (unlikely(pg->src_ents >= PG_SRC_ENT_LIMIT)) + return NULL; + + switch (src_ip->proto) { + case htons(ETH_P_IP): + if (ipv4_is_zeronet(src_ip->u.ip4) || + ipv4_is_multicast(src_ip->u.ip4)) + return NULL; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + if (ipv6_addr_any(&src_ip->u.ip6) || + ipv6_addr_is_multicast(&src_ip->u.ip6)) + return NULL; + break; +#endif + } + + grp_src = kzalloc(sizeof(*grp_src), GFP_ATOMIC); + if (unlikely(!grp_src)) + return NULL; + + grp_src->pg = pg; + grp_src->br = pg->port->br; + grp_src->addr = *src_ip; + grp_src->mcast_gc.destroy = br_multicast_destroy_group_src; + timer_setup(&grp_src->timer, br_multicast_group_src_expired, 0); + + hlist_add_head_rcu(&grp_src->node, &pg->src_list); + pg->src_ents++; + + return grp_src; +} + struct net_bridge_port_group *br_multicast_new_port_group( struct net_bridge_port *port, struct br_ip *group, struct net_bridge_port_group __rcu *next, unsigned char flags, - const unsigned char *src) + const unsigned char *src, + u8 filter_mode) { struct net_bridge_port_group *p; @@ -486,9 +788,13 @@ struct net_bridge_port_group *br_multicast_new_port_group( p->addr = *group; p->port = port; p->flags = flags; + p->filter_mode = filter_mode; + p->mcast_gc.destroy = br_multicast_destroy_port_group; + INIT_HLIST_HEAD(&p->src_list); rcu_assign_pointer(p->next, next); - hlist_add_head(&p->mglist, &port->mglist); timer_setup(&p->timer, br_multicast_port_group_expired, 0); + timer_setup(&p->rexmit_timer, br_multicast_port_group_rexmit, 0); + hlist_add_head(&p->mglist, &port->mglist); if (src) memcpy(p->eth_addr, src, ETH_ALEN); @@ -516,8 +822,7 @@ void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify) if (!mp->host_joined) { mp->host_joined = true; if (notify) - br_mdb_notify(mp->br->dev, NULL, &mp->addr, - RTM_NEWMDB, 0); + br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB); } mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval); } @@ -529,13 +834,15 @@ void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify) mp->host_joined = false; if (notify) - br_mdb_notify(mp->br->dev, NULL, &mp->addr, RTM_DELMDB, 0); + br_mdb_notify(mp->br->dev, mp, NULL, RTM_DELMDB); } static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group, - const unsigned char *src) + const unsigned char *src, + u8 filter_mode, + bool igmpv2_mldv1) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; @@ -567,14 +874,16 @@ static int br_multicast_add_group(struct net_bridge *br, break; } - p = br_multicast_new_port_group(port, group, *pp, 0, src); + p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode); if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); - br_mdb_notify(br->dev, port, group, RTM_NEWMDB, 0); + br_mdb_notify(br->dev, mp, p, RTM_NEWMDB); found: - mod_timer(&p->timer, now + br->multicast_membership_interval); + if (igmpv2_mldv1) + mod_timer(&p->timer, now + br->multicast_membership_interval); + out: err = 0; @@ -587,9 +896,11 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, __u16 vid, - const unsigned char *src) + const unsigned char *src, + bool igmpv2) { struct br_ip br_group; + u8 filter_mode; if (ipv4_is_local_multicast(group)) return 0; @@ -598,8 +909,10 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, br_group.u.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; + filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE; - return br_multicast_add_group(br, port, &br_group, src); + return br_multicast_add_group(br, port, &br_group, src, filter_mode, + igmpv2); } #if IS_ENABLED(CONFIG_IPV6) @@ -607,9 +920,11 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, const struct in6_addr *group, __u16 vid, - const unsigned char *src) + const unsigned char *src, + bool mldv1) { struct br_ip br_group; + u8 filter_mode; if (ipv6_addr_is_ll_all_nodes(group)) return 0; @@ -618,8 +933,10 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, br_group.u.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; + filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE; - return br_multicast_add_group(br, port, &br_group, src); + return br_multicast_add_group(br, port, &br_group, src, filter_mode, + mldv1); } #endif @@ -711,12 +1028,21 @@ static void br_multicast_select_own_querier(struct net_bridge *br, static void __br_multicast_send_query(struct net_bridge *br, struct net_bridge_port *port, - struct br_ip *ip) -{ + struct net_bridge_port_group *pg, + struct br_ip *ip_dst, + struct br_ip *group, + bool with_srcs, + u8 sflag, + bool *need_rexmit) +{ + bool over_lmqt = !!sflag; struct sk_buff *skb; u8 igmp_type; - skb = br_multicast_alloc_query(br, ip, &igmp_type); +again_under_lmqt: + skb = br_multicast_alloc_query(br, pg, ip_dst, group, with_srcs, + over_lmqt, sflag, &igmp_type, + need_rexmit); if (!skb) return; @@ -727,8 +1053,13 @@ static void __br_multicast_send_query(struct net_bridge *br, NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, dev_net(port->dev), NULL, skb, NULL, skb->dev, br_dev_queue_push_xmit); + + if (over_lmqt && with_srcs && sflag) { + over_lmqt = false; + goto again_under_lmqt; + } } else { - br_multicast_select_own_querier(br, ip, skb); + br_multicast_select_own_querier(br, group, skb); br_multicast_count(br, port, skb, igmp_type, BR_MCAST_DIR_RX); netif_rx(skb); @@ -764,7 +1095,8 @@ static void br_multicast_send_query(struct net_bridge *br, if (!other_query || timer_pending(&other_query->timer)) return; - __br_multicast_send_query(br, port, &br_group); + __br_multicast_send_query(br, port, NULL, NULL, &br_group, false, 0, + NULL); time = jiffies; time += own_query->startup_sent < br->multicast_startup_query_count ? @@ -809,6 +1141,44 @@ static void br_ip6_multicast_port_query_expired(struct timer_list *t) } #endif +static void br_multicast_port_group_rexmit(struct timer_list *t) +{ + struct net_bridge_port_group *pg = from_timer(pg, t, rexmit_timer); + struct bridge_mcast_other_query *other_query = NULL; + struct net_bridge *br = pg->port->br; + bool need_rexmit = false; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) || + !br_opt_get(br, BROPT_MULTICAST_ENABLED) || + !br_opt_get(br, BROPT_MULTICAST_QUERIER)) + goto out; + + if (pg->addr.proto == htons(ETH_P_IP)) + other_query = &br->ip4_other_query; +#if IS_ENABLED(CONFIG_IPV6) + else + other_query = &br->ip6_other_query; +#endif + + if (!other_query || timer_pending(&other_query->timer)) + goto out; + + if (pg->grp_query_rexmit_cnt) { + pg->grp_query_rexmit_cnt--; + __br_multicast_send_query(br, pg->port, pg, &pg->addr, + &pg->addr, false, 1, NULL); + } + __br_multicast_send_query(br, pg->port, pg, &pg->addr, + &pg->addr, true, 0, &need_rexmit); + + if (pg->grp_query_rexmit_cnt || need_rexmit) + mod_timer(&pg->rexmit_timer, jiffies + + br->multicast_last_member_interval); +out: + spin_unlock(&br->multicast_lock); +} + static void br_mc_disabled_update(struct net_device *dev, bool value) { struct switchdev_attr attr = { @@ -847,13 +1217,16 @@ void br_multicast_del_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; + HLIST_HEAD(deleted_head); struct hlist_node *n; /* Take care of the remaining groups, only perm ones should be left */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) - br_multicast_del_pg(br, pg); + br_multicast_find_del_pg(br, pg); + hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); + br_multicast_gc(&deleted_head); del_timer_sync(&port->multicast_router_timer); free_percpu(port->mcast_stats); } @@ -901,7 +1274,7 @@ void br_multicast_disable_port(struct net_bridge_port *port) spin_lock(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) if (!(pg->flags & MDB_PG_FLAGS_PERMANENT)) - br_multicast_del_pg(br, pg); + br_multicast_find_del_pg(br, pg); __del_port_router(port); @@ -913,20 +1286,561 @@ void br_multicast_disable_port(struct net_bridge_port *port) spin_unlock(&br->multicast_lock); } +static int __grp_src_delete_marked(struct net_bridge_port_group *pg) +{ + struct net_bridge_group_src *ent; + struct hlist_node *tmp; + int deleted = 0; + + hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) + if (ent->flags & BR_SGRP_F_DELETE) { + br_multicast_del_group_src(ent); + deleted++; + } + + return deleted; +} + +static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg) +{ + struct bridge_mcast_other_query *other_query = NULL; + struct net_bridge *br = pg->port->br; + u32 lmqc = br->multicast_last_member_count; + unsigned long lmqt, lmi, now = jiffies; + struct net_bridge_group_src *ent; + + if (!netif_running(br->dev) || + !br_opt_get(br, BROPT_MULTICAST_ENABLED)) + return; + + if (pg->addr.proto == htons(ETH_P_IP)) + other_query = &br->ip4_other_query; +#if IS_ENABLED(CONFIG_IPV6) + else + other_query = &br->ip6_other_query; +#endif + + lmqt = now + br_multicast_lmqt(br); + hlist_for_each_entry(ent, &pg->src_list, node) { + if (ent->flags & BR_SGRP_F_SEND) { + ent->flags &= ~BR_SGRP_F_SEND; + if (ent->timer.expires > lmqt) { + if (br_opt_get(br, BROPT_MULTICAST_QUERIER) && + other_query && + !timer_pending(&other_query->timer)) + ent->src_query_rexmit_cnt = lmqc; + mod_timer(&ent->timer, lmqt); + } + } + } + + if (!br_opt_get(br, BROPT_MULTICAST_QUERIER) || + !other_query || timer_pending(&other_query->timer)) + return; + + __br_multicast_send_query(br, pg->port, pg, &pg->addr, + &pg->addr, true, 1, NULL); + + lmi = now + br->multicast_last_member_interval; + if (!timer_pending(&pg->rexmit_timer) || + time_after(pg->rexmit_timer.expires, lmi)) + mod_timer(&pg->rexmit_timer, lmi); +} + +static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg) +{ + struct bridge_mcast_other_query *other_query = NULL; + struct net_bridge *br = pg->port->br; + unsigned long now = jiffies, lmi; + + if (!netif_running(br->dev) || + !br_opt_get(br, BROPT_MULTICAST_ENABLED)) + return; + + if (pg->addr.proto == htons(ETH_P_IP)) + other_query = &br->ip4_other_query; +#if IS_ENABLED(CONFIG_IPV6) + else + other_query = &br->ip6_other_query; +#endif + + if (br_opt_get(br, BROPT_MULTICAST_QUERIER) && + other_query && !timer_pending(&other_query->timer)) { + lmi = now + br->multicast_last_member_interval; + pg->grp_query_rexmit_cnt = br->multicast_last_member_count - 1; + __br_multicast_send_query(br, pg->port, pg, &pg->addr, + &pg->addr, false, 0, NULL); + if (!timer_pending(&pg->rexmit_timer) || + time_after(pg->rexmit_timer.expires, lmi)) + mod_timer(&pg->rexmit_timer, lmi); + } + + if (pg->filter_mode == MCAST_EXCLUDE && + (!timer_pending(&pg->timer) || + time_after(pg->timer.expires, now + br_multicast_lmqt(br)))) + mod_timer(&pg->timer, now + br_multicast_lmqt(br)); +} + +/* State Msg type New state Actions + * INCLUDE (A) IS_IN (B) INCLUDE (A+B) (B)=GMI + * INCLUDE (A) ALLOW (B) INCLUDE (A+B) (B)=GMI + * EXCLUDE (X,Y) ALLOW (A) EXCLUDE (X+A,Y-A) (A)=GMI + */ +static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->port->br; + struct net_bridge_group_src *ent; + unsigned long now = jiffies; + bool changed = false; + struct br_ip src_ip; + u32 src_idx; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.u, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (!ent) { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) + changed = true; + } + + if (ent) + mod_timer(&ent->timer, now + br_multicast_gmi(br)); + srcs += src_size; + } + + return changed; +} + +/* State Msg type New state Actions + * INCLUDE (A) IS_EX (B) EXCLUDE (A*B,B-A) (B-A)=0 + * Delete (A-B) + * Group Timer=GMI + */ +static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + struct br_ip src_ip; + u32 src_idx; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags |= BR_SGRP_F_DELETE; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.u, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) + ent->flags &= ~BR_SGRP_F_DELETE; + else + br_multicast_new_group_src(pg, &src_ip); + srcs += src_size; + } + + __grp_src_delete_marked(pg); +} + +/* State Msg type New state Actions + * EXCLUDE (X,Y) IS_EX (A) EXCLUDE (A-Y,Y*A) (A-X-Y)=GMI + * Delete (X-A) + * Delete (Y-A) + * Group Timer=GMI + */ +static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->port->br; + struct net_bridge_group_src *ent; + unsigned long now = jiffies; + bool changed = false; + struct br_ip src_ip; + u32 src_idx; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags |= BR_SGRP_F_DELETE; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.u, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags &= ~BR_SGRP_F_DELETE; + } else { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) { + mod_timer(&ent->timer, + now + br_multicast_gmi(br)); + changed = true; + } + } + srcs += src_size; + } + + if (__grp_src_delete_marked(pg)) + changed = true; + + return changed; +} + +static bool br_multicast_isexc(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->port->br; + bool changed = false; + + switch (pg->filter_mode) { + case MCAST_INCLUDE: + __grp_src_isexc_incl(pg, srcs, nsrcs, src_size); + changed = true; + break; + case MCAST_EXCLUDE: + changed = __grp_src_isexc_excl(pg, srcs, nsrcs, src_size); + break; + } + + pg->filter_mode = MCAST_EXCLUDE; + mod_timer(&pg->timer, jiffies + br_multicast_gmi(br)); + + return changed; +} + +/* State Msg type New state Actions + * INCLUDE (A) TO_IN (B) INCLUDE (A+B) (B)=GMI + * Send Q(G,A-B) + */ +static bool __grp_src_toin_incl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->port->br; + u32 src_idx, to_send = pg->src_ents; + struct net_bridge_group_src *ent; + unsigned long now = jiffies; + bool changed = false; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags |= BR_SGRP_F_SEND; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.u, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags &= ~BR_SGRP_F_SEND; + to_send--; + } else { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) + changed = true; + } + if (ent) + mod_timer(&ent->timer, now + br_multicast_gmi(br)); + srcs += src_size; + } + + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + return changed; +} + +/* State Msg type New state Actions + * EXCLUDE (X,Y) TO_IN (A) EXCLUDE (X+A,Y-A) (A)=GMI + * Send Q(G,X-A) + * Send Q(G) + */ +static bool __grp_src_toin_excl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->port->br; + u32 src_idx, to_send = pg->src_ents; + struct net_bridge_group_src *ent; + unsigned long now = jiffies; + bool changed = false; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + if (timer_pending(&ent->timer)) + ent->flags |= BR_SGRP_F_SEND; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.u, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + if (timer_pending(&ent->timer)) { + ent->flags &= ~BR_SGRP_F_SEND; + to_send--; + } + } else { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) + changed = true; + } + if (ent) + mod_timer(&ent->timer, now + br_multicast_gmi(br)); + srcs += src_size; + } + + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + __grp_send_query_and_rexmit(pg); + + return changed; +} + +static bool br_multicast_toin(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + bool changed = false; + + switch (pg->filter_mode) { + case MCAST_INCLUDE: + changed = __grp_src_toin_incl(pg, srcs, nsrcs, src_size); + break; + case MCAST_EXCLUDE: + changed = __grp_src_toin_excl(pg, srcs, nsrcs, src_size); + break; + } + + return changed; +} + +/* State Msg type New state Actions + * INCLUDE (A) TO_EX (B) EXCLUDE (A*B,B-A) (B-A)=0 + * Delete (A-B) + * Send Q(G,A*B) + * Group Timer=GMI + */ +static void __grp_src_toex_incl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + u32 src_idx, to_send = 0; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.u, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags = (ent->flags & ~BR_SGRP_F_DELETE) | + BR_SGRP_F_SEND; + to_send++; + } else { + br_multicast_new_group_src(pg, &src_ip); + } + srcs += src_size; + } + + __grp_src_delete_marked(pg); + if (to_send) + __grp_src_query_marked_and_rexmit(pg); +} + +/* State Msg type New state Actions + * EXCLUDE (X,Y) TO_EX (A) EXCLUDE (A-Y,Y*A) (A-X-Y)=Group Timer + * Delete (X-A) + * Delete (Y-A) + * Send Q(G,A-Y) + * Group Timer=GMI + */ +static bool __grp_src_toex_excl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + u32 src_idx, to_send = 0; + bool changed = false; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.u, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags &= ~BR_SGRP_F_DELETE; + } else { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) { + mod_timer(&ent->timer, pg->timer.expires); + changed = true; + } + } + if (ent && timer_pending(&ent->timer)) { + ent->flags |= BR_SGRP_F_SEND; + to_send++; + } + srcs += src_size; + } + + if (__grp_src_delete_marked(pg)) + changed = true; + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + return changed; +} + +static bool br_multicast_toex(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->port->br; + bool changed = false; + + switch (pg->filter_mode) { + case MCAST_INCLUDE: + __grp_src_toex_incl(pg, srcs, nsrcs, src_size); + changed = true; + break; + case MCAST_EXCLUDE: + __grp_src_toex_excl(pg, srcs, nsrcs, src_size); + break; + } + + pg->filter_mode = MCAST_EXCLUDE; + mod_timer(&pg->timer, jiffies + br_multicast_gmi(br)); + + return changed; +} + +/* State Msg type New state Actions + * INCLUDE (A) BLOCK (B) INCLUDE (A) Send Q(G,A*B) + */ +static void __grp_src_block_incl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + u32 src_idx, to_send = 0; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags &= ~BR_SGRP_F_SEND; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.u, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags |= BR_SGRP_F_SEND; + to_send++; + } + srcs += src_size; + } + + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + if (pg->filter_mode == MCAST_INCLUDE && hlist_empty(&pg->src_list)) + br_multicast_find_del_pg(pg->port->br, pg); +} + +/* State Msg type New state Actions + * EXCLUDE (X,Y) BLOCK (A) EXCLUDE (X+(A-Y),Y) (A-X-Y)=Group Timer + * Send Q(G,A-Y) + */ +static bool __grp_src_block_excl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + u32 src_idx, to_send = 0; + bool changed = false; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags &= ~BR_SGRP_F_SEND; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.u, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (!ent) { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) { + mod_timer(&ent->timer, pg->timer.expires); + changed = true; + } + } + if (ent && timer_pending(&ent->timer)) { + ent->flags |= BR_SGRP_F_SEND; + to_send++; + } + srcs += src_size; + } + + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + return changed; +} + +static bool br_multicast_block(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + bool changed = false; + + switch (pg->filter_mode) { + case MCAST_INCLUDE: + __grp_src_block_incl(pg, srcs, nsrcs, src_size); + break; + case MCAST_EXCLUDE: + changed = __grp_src_block_excl(pg, srcs, nsrcs, src_size); + break; + } + + return changed; +} + +static struct net_bridge_port_group * +br_multicast_find_port(struct net_bridge_mdb_entry *mp, + struct net_bridge_port *p, + const unsigned char *src) +{ + struct net_bridge *br __maybe_unused = mp->br; + struct net_bridge_port_group *pg; + + for (pg = mlock_dereference(mp->ports, br); + pg; + pg = mlock_dereference(pg->next, br)) + if (br_port_group_equal(pg, p, src)) + return pg; + + return NULL; +} + static int br_ip4_multicast_igmp3_report(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { + bool igmpv2 = br->multicast_igmp_version == 2; + struct net_bridge_mdb_entry *mdst; + struct net_bridge_port_group *pg; const unsigned char *src; struct igmpv3_report *ih; struct igmpv3_grec *grec; - int i; - int len; - int num; - int type; - int err = 0; + int i, len, num, type; + bool changed = false; __be32 group; + int err = 0; u16 nsrcs; ih = igmpv3_report_hdr(skb); @@ -947,7 +1861,6 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, if (!ip_mc_may_pull(skb, len)) return -EINVAL; - /* We treat this as an IGMPv2 report for now. */ switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: @@ -962,16 +1875,62 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, } src = eth_hdr(skb)->h_source; - if ((type == IGMPV3_CHANGE_TO_INCLUDE || - type == IGMPV3_MODE_IS_INCLUDE) && - nsrcs == 0) { - br_ip4_multicast_leave_group(br, port, group, vid, src); + if (nsrcs == 0 && + (type == IGMPV3_CHANGE_TO_INCLUDE || + type == IGMPV3_MODE_IS_INCLUDE)) { + if (!port || igmpv2) { + br_ip4_multicast_leave_group(br, port, group, vid, src); + continue; + } } else { err = br_ip4_multicast_add_group(br, port, group, vid, - src); + src, igmpv2); if (err) break; } + + if (!port || igmpv2) + continue; + + spin_lock_bh(&br->multicast_lock); + mdst = br_mdb_ip4_get(br, group, vid); + if (!mdst) + goto unlock_continue; + pg = br_multicast_find_port(mdst, port, src); + if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) + goto unlock_continue; + /* reload grec */ + grec = (void *)(skb->data + len - sizeof(*grec) - (nsrcs * 4)); + switch (type) { + case IGMPV3_ALLOW_NEW_SOURCES: + changed = br_multicast_isinc_allow(pg, grec->grec_src, + nsrcs, sizeof(__be32)); + break; + case IGMPV3_MODE_IS_INCLUDE: + changed = br_multicast_isinc_allow(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + case IGMPV3_MODE_IS_EXCLUDE: + changed = br_multicast_isexc(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + case IGMPV3_CHANGE_TO_INCLUDE: + changed = br_multicast_toin(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + case IGMPV3_CHANGE_TO_EXCLUDE: + changed = br_multicast_toex(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + case IGMPV3_BLOCK_OLD_SOURCES: + changed = br_multicast_block(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + } + if (changed) + br_mdb_notify(br->dev, mdst, pg, RTM_NEWMDB); +unlock_continue: + spin_unlock_bh(&br->multicast_lock); } return err; @@ -983,14 +1942,16 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + bool mldv1 = br->multicast_mld_version == 1; + struct net_bridge_mdb_entry *mdst; + struct net_bridge_port_group *pg; unsigned int nsrcs_offset; const unsigned char *src; struct icmp6hdr *icmp6h; struct mld2_grec *grec; unsigned int grec_len; - int i; - int len; - int num; + bool changed = false; + int i, len, num; int err = 0; if (!ipv6_mc_may_pull(skb, sizeof(*icmp6h))) @@ -1024,7 +1985,6 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, grec = (struct mld2_grec *)(skb->data + len); len += grec_len; - /* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: @@ -1042,15 +2002,61 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE || grec->grec_type == MLD2_MODE_IS_INCLUDE) && nsrcs == 0) { - br_ip6_multicast_leave_group(br, port, &grec->grec_mca, - vid, src); + if (!port || mldv1) { + br_ip6_multicast_leave_group(br, port, + &grec->grec_mca, + vid, src); + continue; + } } else { err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid, - src); + src, mldv1); if (err) break; } + + if (!port || mldv1) + continue; + + spin_lock_bh(&br->multicast_lock); + mdst = br_mdb_ip6_get(br, &grec->grec_mca, vid); + if (!mdst) + goto unlock_continue; + pg = br_multicast_find_port(mdst, port, src); + if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) + goto unlock_continue; + switch (grec->grec_type) { + case MLD2_ALLOW_NEW_SOURCES: + changed = br_multicast_isinc_allow(pg, grec->grec_src, + nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_MODE_IS_INCLUDE: + changed = br_multicast_isinc_allow(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_MODE_IS_EXCLUDE: + changed = br_multicast_isexc(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_CHANGE_TO_INCLUDE: + changed = br_multicast_toin(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_CHANGE_TO_EXCLUDE: + changed = br_multicast_toex(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_BLOCK_OLD_SOURCES: + changed = br_multicast_block(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + } + if (changed) + br_mdb_notify(br->dev, mdst, pg, RTM_NEWMDB); +unlock_continue: + spin_unlock_bh(&br->multicast_lock); } return err; @@ -1245,7 +2251,8 @@ static void br_ip4_multicast_query(struct net_bridge *br, } } else if (transport_len >= sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); - if (ih3->nsrcs) + if (ih3->nsrcs || + (br->multicast_igmp_version == 3 && group && ih3->suppress)) goto out; max_delay = ih3->code ? @@ -1280,7 +2287,9 @@ static void br_ip4_multicast_query(struct net_bridge *br, pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : - try_to_del_timer_sync(&p->timer) >= 0) + try_to_del_timer_sync(&p->timer) >= 0 && + (br->multicast_igmp_version == 2 || + p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } @@ -1330,6 +2339,10 @@ static int br_ip6_multicast_query(struct net_bridge *br, mld2q = (struct mld2_query *)icmp6_hdr(skb); if (!mld2q->mld2q_nsrcs) group = &mld2q->mld2q_mca; + if (br->multicast_mld_version == 2 && + !ipv6_addr_any(&mld2q->mld2q_mca) && + mld2q->mld2q_suppress) + goto out; max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); } @@ -1363,7 +2376,9 @@ static int br_ip6_multicast_query(struct net_bridge *br, pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : - try_to_del_timer_sync(&p->timer) >= 0) + try_to_del_timer_sync(&p->timer) >= 0 && + (br->multicast_mld_version == 1 || + p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } @@ -1407,16 +2422,8 @@ br_multicast_leave_group(struct net_bridge *br, if (p->flags & MDB_PG_FLAGS_PERMANENT) break; - rcu_assign_pointer(*pp, p->next); - hlist_del_init(&p->mglist); - del_timer(&p->timer); - kfree_rcu(p, rcu); - br_mdb_notify(br->dev, port, group, RTM_DELMDB, - p->flags | MDB_PG_FLAGS_FAST_LEAVE); - - if (!mp->ports && !mp->host_joined && - netif_running(br->dev)) - mod_timer(&mp->timer, jiffies); + p->flags |= MDB_PG_FLAGS_FAST_LEAVE; + br_multicast_del_pg(mp, p, pp); } goto out; } @@ -1425,7 +2432,8 @@ br_multicast_leave_group(struct net_bridge *br, goto out; if (br_opt_get(br, BROPT_MULTICAST_QUERIER)) { - __br_multicast_send_query(br, port, &mp->addr); + __br_multicast_send_query(br, port, NULL, NULL, &mp->addr, + false, 0, NULL); time = jiffies + br->multicast_last_member_count * br->multicast_last_member_interval; @@ -1627,7 +2635,8 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - err = br_ip4_multicast_add_group(br, port, ih->group, vid, src); + err = br_ip4_multicast_add_group(br, port, ih->group, vid, src, + true); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: err = br_ip4_multicast_igmp3_report(br, port, skb, vid); @@ -1706,7 +2715,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid, - src); + src, true); break; case ICMPV6_MLD2_REPORT: err = br_ip6_multicast_mld2_report(br, port, skb, vid); @@ -1781,6 +2790,19 @@ static void br_ip6_multicast_query_expired(struct timer_list *t) } #endif +static void br_multicast_gc_work(struct work_struct *work) +{ + struct net_bridge *br = container_of(work, struct net_bridge, + mcast_gc_work); + HLIST_HEAD(deleted_head); + + spin_lock_bh(&br->multicast_lock); + hlist_move_list(&br->mcast_gc_list, &deleted_head); + spin_unlock_bh(&br->multicast_lock); + + br_multicast_gc(&deleted_head); +} + void br_multicast_init(struct net_bridge *br) { br->hash_max = BR_MULTICAST_DEFAULT_HASH_MAX; @@ -1821,6 +2843,8 @@ void br_multicast_init(struct net_bridge *br) br_ip6_multicast_query_expired, 0); #endif INIT_HLIST_HEAD(&br->mdb_list); + INIT_HLIST_HEAD(&br->mcast_gc_list); + INIT_WORK(&br->mcast_gc_work, br_multicast_gc_work); } static void br_ip4_multicast_join_snoopers(struct net_bridge *br) @@ -1924,18 +2948,18 @@ void br_multicast_stop(struct net_bridge *br) void br_multicast_dev_del(struct net_bridge *br) { struct net_bridge_mdb_entry *mp; + HLIST_HEAD(deleted_head); struct hlist_node *tmp; spin_lock_bh(&br->multicast_lock); - hlist_for_each_entry_safe(mp, tmp, &br->mdb_list, mdb_node) { - del_timer(&mp->timer); - rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode, - br_mdb_rht_params); - hlist_del_rcu(&mp->mdb_node); - kfree_rcu(mp, rcu); - } + hlist_for_each_entry_safe(mp, tmp, &br->mdb_list, mdb_node) + br_multicast_del_mdb_entry(mp); + hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); + br_multicast_gc(&deleted_head); + cancel_work_sync(&br->mcast_gc_work); + rcu_barrier(); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 147d52596e17..8a71c60fa357 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1095,8 +1095,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, [IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 }, [IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 }, - [IFLA_BR_MULTI_BOOLOPT] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct br_boolopt_multi) }, + [IFLA_BR_MULTI_BOOLOPT] = + NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)), }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index baa1500f384f..a23d2bae56e1 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -214,26 +214,61 @@ struct net_bridge_fdb_entry { #define MDB_PG_FLAGS_OFFLOAD BIT(1) #define MDB_PG_FLAGS_FAST_LEAVE BIT(2) +#define PG_SRC_ENT_LIMIT 32 + +#define BR_SGRP_F_DELETE BIT(0) +#define BR_SGRP_F_SEND BIT(1) + +struct net_bridge_mcast_gc { + struct hlist_node gc_node; + void (*destroy)(struct net_bridge_mcast_gc *gc); +}; + +struct net_bridge_group_src { + struct hlist_node node; + + struct br_ip addr; + struct net_bridge_port_group *pg; + u8 flags; + u8 src_query_rexmit_cnt; + struct timer_list timer; + + struct net_bridge *br; + struct net_bridge_mcast_gc mcast_gc; + struct rcu_head rcu; +}; + struct net_bridge_port_group { struct net_bridge_port *port; struct net_bridge_port_group __rcu *next; - struct hlist_node mglist; - struct rcu_head rcu; - struct timer_list timer; struct br_ip addr; unsigned char eth_addr[ETH_ALEN] __aligned(2); unsigned char flags; + unsigned char filter_mode; + unsigned char grp_query_rexmit_cnt; + + struct hlist_head src_list; + unsigned int src_ents; + struct timer_list timer; + struct timer_list rexmit_timer; + struct hlist_node mglist; + + struct net_bridge_mcast_gc mcast_gc; + struct rcu_head rcu; }; struct net_bridge_mdb_entry { struct rhash_head rhnode; struct net_bridge *br; struct net_bridge_port_group __rcu *ports; - struct rcu_head rcu; - struct timer_list timer; struct br_ip addr; bool host_joined; + + struct timer_list timer; struct hlist_node mdb_node; + + struct net_bridge_mcast_gc mcast_gc; + struct rcu_head rcu; }; struct net_bridge_port { @@ -406,6 +441,7 @@ struct net_bridge { struct rhashtable mdb_hash_tbl; + struct hlist_head mcast_gc_list; struct hlist_head mdb_list; struct hlist_head router_list; @@ -419,6 +455,7 @@ struct net_bridge { struct bridge_mcast_own_query ip6_own_query; struct bridge_mcast_querier ip6_querier; #endif /* IS_ENABLED(CONFIG_IPV6) */ + struct work_struct mcast_gc_work; #endif struct timer_list hello_timer; @@ -766,13 +803,17 @@ br_multicast_new_group(struct net_bridge *br, struct br_ip *group); struct net_bridge_port_group * br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, struct net_bridge_port_group __rcu *next, - unsigned char flags, const unsigned char *src); + unsigned char flags, const unsigned char *src, + u8 filter_mode); int br_mdb_hash_init(struct net_bridge *br); void br_mdb_hash_fini(struct net_bridge *br); -void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, - struct br_ip *group, int type, u8 flags); +void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, int type); void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, int type); +void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + struct net_bridge_port_group __rcu **pp); void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p, const struct sk_buff *skb, u8 type, u8 dir); int br_multicast_init_stats(struct net_bridge *br); @@ -836,6 +877,19 @@ static inline int br_multicast_igmp_type(const struct sk_buff *skb) { return BR_INPUT_SKB_CB(skb)->igmp; } + +static inline unsigned long br_multicast_lmqt(const struct net_bridge *br) +{ + return br->multicast_last_member_interval * + br->multicast_last_member_count; +} + +static inline unsigned long br_multicast_gmi(const struct net_bridge *br) +{ + /* use the RFC default of 2 for QRV */ + return 2 * br->multicast_query_interval + + br->multicast_query_response_interval; +} #else static inline int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index f9092c71225f..d2b8737f9fc0 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1884,8 +1884,8 @@ out_err: } static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = { - [BRIDGE_VLANDB_ENTRY_INFO] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct bridge_vlan_info) }, + [BRIDGE_VLANDB_ENTRY_INFO] = + NLA_POLICY_EXACT_LEN(sizeof(struct bridge_vlan_info)), [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 0d6d20c9105e..8f68afda5f81 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -15,7 +15,6 @@ #include <linux/netfilter_bridge/ebt_stp.h> #define BPDU_TYPE_CONFIG 0 -#define BPDU_TYPE_TCN 0x80 struct stp_header { u8 dsap; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 1641f414d1ba..ebe33b60efd6 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2238,6 +2238,10 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, struct ebt_table *t; struct net *net = sock_net(sk); + if ((cmd == EBT_SO_GET_INFO || cmd == EBT_SO_GET_INIT_INFO) && + *len != sizeof(struct compat_ebt_replace)) + return -EINVAL; + if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 809673222382..8d033a75a766 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -168,6 +168,7 @@ static unsigned int nf_ct_br_defrag4(struct sk_buff *skb, static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, const struct nf_hook_state *state) { +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) u16 zone_id = NF_CT_DEFAULT_ZONE_ID; enum ip_conntrack_info ctinfo; struct br_input_skb_cb cb; @@ -180,14 +181,17 @@ static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, br_skb_cb_save(skb, &cb, sizeof(struct inet6_skb_parm)); - err = nf_ipv6_br_defrag(state->net, skb, - IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); + err = nf_ct_frag6_gather(state->net, skb, + IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); /* queued */ if (err == -EINPROGRESS) return NF_STOLEN; br_skb_cb_restore(skb, &cb, IP6CB(skb)->frag_max_size); return err == 0 ? NF_ACCEPT : NF_DROP; +#else + return NF_ACCEPT; +#endif } static int nf_ct_br_ip_check(const struct sk_buff *skb) diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index ce2767e9cec6..7b0af33bdb97 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -116,7 +116,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt) if (segmented) { if (rfml->incomplete_frm == NULL) { /* Initial Segment */ - if (cfpkt_peek_head(pkt, rfml->seghead, 6) < 0) + if (cfpkt_peek_head(pkt, rfml->seghead, 6) != 0) goto out; rfml->pdu_size = get_unaligned_le16(rfml->seghead+4); @@ -233,7 +233,7 @@ static int cfrfml_transmit(struct cflayer *layr, struct cfpkt *pkt) if (cfpkt_getlen(pkt) > rfml->fragment_size + RFM_HEAD_SIZE) err = cfpkt_peek_head(pkt, head, 6); - if (err < 0) + if (err != 0) goto out; while (cfpkt_getlen(frontpkt) > rfml->fragment_size + RFM_HEAD_SIZE) { diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c index d0a4d0ac7045..9cef9496a707 100644 --- a/net/caif/cfsrvl.c +++ b/net/caif/cfsrvl.c @@ -21,7 +21,6 @@ #define SRVL_FLOW_OFF 0x81 #define SRVL_FLOW_ON 0x80 #define SRVL_SET_PIN 0x82 -#define SRVL_CTRL_PKT_SIZE 1 #define container_obj(layr) container_of(layr, struct cfsrvl, layer) diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 78ff9b3f1d40..1be4c898b2fa 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -398,6 +398,7 @@ static int j1939_sk_init(struct sock *sk) spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); sk->sk_destruct = j1939_sk_sock_destruct; + sk->sk_protocol = CAN_J1939; return 0; } @@ -466,6 +467,14 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out_release_sock; } + if (!ndev->ml_priv) { + netdev_warn_once(ndev, + "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); + dev_put(ndev); + ret = -ENODEV; + goto out_release_sock; + } + priv = j1939_netdev_start(ndev); dev_put(ndev); if (IS_ERR(priv)) { @@ -553,6 +562,11 @@ static int j1939_sk_connect(struct socket *sock, struct sockaddr *uaddr, static void j1939_sk_sock2sockaddr_can(struct sockaddr_can *addr, const struct j1939_sock *jsk, int peer) { + /* There are two holes (2 bytes and 3 bytes) to clear to avoid + * leaking kernel information to user space. + */ + memset(addr, 0, J1939_MIN_NAMELEN); + addr->can_family = AF_CAN; addr->can_ifindex = jsk->ifindex; addr->can_addr.j1939.pgn = jsk->addr.pgn; @@ -1072,7 +1086,7 @@ static int j1939_sk_send_loop(struct j1939_priv *priv, struct sock *sk, break; case -ERESTARTSYS: ret = -EINTR; - /* fall through */ + fallthrough; case -EAGAIN: /* OK */ if (todo_size != size) ret = size - todo_size; diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 9f99af5b0b11..0cec4152f979 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -352,17 +352,16 @@ void j1939_session_skb_queue(struct j1939_session *session, skb_queue_tail(&session->skb_queue, skb); } -static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +static struct +sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, + unsigned int offset_start) { struct j1939_priv *priv = session->priv; + struct j1939_sk_buff_cb *do_skcb; struct sk_buff *skb = NULL; struct sk_buff *do_skb; - struct j1939_sk_buff_cb *do_skcb; - unsigned int offset_start; unsigned long flags; - offset_start = session->pkt.dpo * 7; - spin_lock_irqsave(&session->skb_queue.lock, flags); skb_queue_walk(&session->skb_queue, do_skb) { do_skcb = j1939_skb_to_cb(do_skb); @@ -382,6 +381,14 @@ static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) return skb; } +static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +{ + unsigned int offset_start; + + offset_start = session->pkt.dpo * 7; + return j1939_session_skb_find_by_offset(session, offset_start); +} + /* see if we are receiver * returns 0 for broadcasts, although we will receive them */ @@ -716,10 +723,12 @@ static int j1939_session_tx_rts(struct j1939_session *session) return ret; session->last_txcmd = dat[0]; - if (dat[0] == J1939_TP_CMD_BAM) + if (dat[0] == J1939_TP_CMD_BAM) { j1939_tp_schedule_txtimer(session, 50); - - j1939_tp_set_rxtimeout(session, 1250); + j1939_tp_set_rxtimeout(session, 250); + } else { + j1939_tp_set_rxtimeout(session, 1250); + } netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); @@ -766,7 +775,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) int ret = 0; u8 dat[8]; - se_skb = j1939_session_skb_find(session); + se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7); if (!se_skb) return -ENOBUFS; @@ -787,6 +796,18 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (len > 7) len = 7; + if (offset + len > se_skb->len) { + netdev_err_once(priv->ndev, + "%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n", + __func__, session, skcb->offset, se_skb->len , session->pkt.tx); + return -EOVERFLOW; + } + + if (!len) { + ret = -ENOBUFS; + break; + } + memcpy(&dat[1], &tpdat[offset], len); ret = j1939_tp_tx_dat(session, dat, len + 1); if (ret < 0) { @@ -839,7 +860,7 @@ static int j1939_xtp_txnext_transmiter(struct j1939_session *session) return ret; } - /* fall through */ + fallthrough; case J1939_TP_CMD_CTS: case 0xff: /* did some data */ case J1939_ETP_CMD_DPO: @@ -1055,9 +1076,9 @@ static void __j1939_session_cancel(struct j1939_session *session, lockdep_assert_held(&session->priv->active_session_list_lock); session->err = j1939_xtp_abort_to_errno(priv, err); + session->state = J1939_SESSION_WAITING_ABORT; /* do not send aborts on incoming broadcasts */ if (!j1939_cb_is_broadcast(&session->skcb)) { - session->state = J1939_SESSION_WAITING_ABORT; j1939_xtp_tx_abort(priv, &session->skcb, !session->transmission, err, session->skcb.addr.pgn); @@ -1120,6 +1141,9 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) * cleanup including propagation of the error to user space. */ break; + case -EOVERFLOW: + j1939_session_cancel(session, J1939_XTP_ABORT_ECTS_TOO_BIG); + break; case 0: session->tx_retry = 0; break; @@ -1651,8 +1675,12 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb, return; } session = j1939_xtp_rx_rts_session_new(priv, skb); - if (!session) + if (!session) { + if (cmd == J1939_TP_CMD_BAM && j1939_sk_recv_match(priv, skcb)) + netdev_info(priv->ndev, "%s: failed to create TP BAM session\n", + __func__); return; + } } else { if (j1939_xtp_rx_rts_session_active(session, skb)) { j1939_session_put(session); @@ -1661,11 +1689,15 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb, } session->last_cmd = cmd; - j1939_tp_set_rxtimeout(session, 1250); - - if (cmd != J1939_TP_CMD_BAM && !session->transmission) { - j1939_session_txtimer_cancel(session); - j1939_tp_schedule_txtimer(session, 0); + if (cmd == J1939_TP_CMD_BAM) { + if (!session->transmission) + j1939_tp_set_rxtimeout(session, 750); + } else { + if (!session->transmission) { + j1939_session_txtimer_cancel(session); + j1939_tp_schedule_txtimer(session, 0); + } + j1939_tp_set_rxtimeout(session, 1250); } j1939_session_put(session); @@ -1716,6 +1748,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, int offset; int nbytes; bool final = false; + bool remain = false; bool do_cts_eoma = false; int packet; @@ -1731,12 +1764,12 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, case J1939_ETP_CMD_DPO: if (skcb->addr.type == J1939_ETP) break; - /* fall through */ - case J1939_TP_CMD_BAM: /* fall through */ + fallthrough; + case J1939_TP_CMD_BAM: case J1939_TP_CMD_CTS: /* fall through */ if (skcb->addr.type != J1939_ETP) break; - /* fall through */ + fallthrough; default: netdev_info(priv->ndev, "%s: 0x%p: last %02x\n", __func__, session, session->last_cmd); @@ -1750,7 +1783,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, __func__, session); goto out_session_cancel; } - se_skb = j1939_session_skb_find(session); + + se_skb = j1939_session_skb_find_by_offset(session, packet * 7); if (!se_skb) { netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__, session); @@ -1769,7 +1803,20 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, } tpdat = se_skb->data; - memcpy(&tpdat[offset], &dat[1], nbytes); + if (!session->transmission) { + memcpy(&tpdat[offset], &dat[1], nbytes); + } else { + int err; + + err = memcmp(&tpdat[offset], &dat[1], nbytes); + if (err) + netdev_err_once(priv->ndev, + "%s: 0x%p: Data of RX-looped back packet (%*ph) doesn't match TX data (%*ph)!\n", + __func__, session, + nbytes, &dat[1], + nbytes, &tpdat[offset]); + } + if (packet == session->pkt.rx) session->pkt.rx++; @@ -1777,6 +1824,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, j1939_cb_is_broadcast(&session->skcb)) { if (session->pkt.rx >= session->pkt.total) final = true; + else + remain = true; } else { /* never final, an EOMA must follow */ if (session->pkt.rx >= session->pkt.last) @@ -1784,7 +1833,11 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, } if (final) { + j1939_session_timers_cancel(session); j1939_session_completed(session); + } else if (remain) { + if (!session->transmission) + j1939_tp_set_rxtimeout(session, 750); } else if (do_cts_eoma) { j1939_tp_set_rxtimeout(session, 1250); if (!session->transmission) @@ -1829,6 +1882,13 @@ static void j1939_xtp_rx_dat(struct j1939_priv *priv, struct sk_buff *skb) else j1939_xtp_rx_dat_one(session, skb); } + + if (j1939_cb_is_broadcast(skcb)) { + session = j1939_session_get_by_addr(priv, &skcb->addr, false, + false); + if (session) + j1939_xtp_rx_dat_one(session, skb); + } } /* j1939 main intf */ @@ -1905,8 +1965,8 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) switch (cmd) { case J1939_ETP_CMD_RTS: extd = J1939_ETP; - /* fall through */ - case J1939_TP_CMD_BAM: /* fall through */ + fallthrough; + case J1939_TP_CMD_BAM: case J1939_TP_CMD_RTS: /* fall through */ if (skcb->addr.type != extd) return; @@ -1920,14 +1980,14 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) if (j1939_tp_im_transmitter(skcb)) j1939_xtp_rx_rts(priv, skb, true); - if (j1939_tp_im_receiver(skcb)) + if (j1939_tp_im_receiver(skcb) || j1939_cb_is_broadcast(skcb)) j1939_xtp_rx_rts(priv, skb, false); break; case J1939_ETP_CMD_CTS: extd = J1939_ETP; - /* fall through */ + fallthrough; case J1939_TP_CMD_CTS: if (skcb->addr.type != extd) return; @@ -1954,7 +2014,7 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) case J1939_ETP_CMD_EOMA: extd = J1939_ETP; - /* fall through */ + fallthrough; case J1939_TP_CMD_EOMA: if (skcb->addr.type != extd) return; @@ -1984,20 +2044,20 @@ int j1939_tp_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); - if (!j1939_tp_im_involved_anydir(skcb)) + if (!j1939_tp_im_involved_anydir(skcb) && !j1939_cb_is_broadcast(skcb)) return 0; switch (skcb->addr.pgn) { case J1939_ETP_PGN_DAT: skcb->addr.type = J1939_ETP; - /* fall through */ + fallthrough; case J1939_TP_PGN_DAT: j1939_xtp_rx_dat(priv, skb); break; case J1939_ETP_PGN_CTL: skcb->addr.type = J1939_ETP; - /* fall through */ + fallthrough; case J1939_TP_PGN_CTL: if (skb->len < 8) return 0; /* Don't care. Nothing to extract here */ @@ -2017,6 +2077,10 @@ void j1939_simple_recv(struct j1939_priv *priv, struct sk_buff *skb) if (!skb->sk) return; + if (skb->sk->sk_family != AF_CAN || + skb->sk->sk_protocol != CAN_J1939) + return; + j1939_session_list_lock(priv); session = j1939_session_get_simple(priv, skb); j1939_session_list_unlock(priv); diff --git a/net/ceph/ceph_hash.c b/net/ceph/ceph_hash.c index 81e1e006c540..16a47c0eef37 100644 --- a/net/ceph/ceph_hash.c +++ b/net/ceph/ceph_hash.c @@ -50,35 +50,35 @@ unsigned int ceph_str_hash_rjenkins(const char *str, unsigned int length) switch (len) { case 11: c = c + ((__u32)k[10] << 24); - /* fall through */ + fallthrough; case 10: c = c + ((__u32)k[9] << 16); - /* fall through */ + fallthrough; case 9: c = c + ((__u32)k[8] << 8); /* the first byte of c is reserved for the length */ - /* fall through */ + fallthrough; case 8: b = b + ((__u32)k[7] << 24); - /* fall through */ + fallthrough; case 7: b = b + ((__u32)k[6] << 16); - /* fall through */ + fallthrough; case 6: b = b + ((__u32)k[5] << 8); - /* fall through */ + fallthrough; case 5: b = b + k[4]; - /* fall through */ + fallthrough; case 4: a = a + ((__u32)k[3] << 24); - /* fall through */ + fallthrough; case 3: a = a + ((__u32)k[2] << 16); - /* fall through */ + fallthrough; case 2: a = a + ((__u32)k[1] << 8); - /* fall through */ + fallthrough; case 1: a = a + k[0]; /* case 0: nothing left to add */ diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 07e5614eb3f1..7057f8db4f99 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -987,7 +987,7 @@ int crush_do_rule(const struct crush_map *map, case CRUSH_RULE_CHOOSELEAF_FIRSTN: case CRUSH_RULE_CHOOSE_FIRSTN: firstn = 1; - /* fall through */ + fallthrough; case CRUSH_RULE_CHOOSELEAF_INDEP: case CRUSH_RULE_CHOOSE_INDEP: if (wsize == 0) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 27d6ab11f9ee..bdfd66ba3843 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -412,7 +412,7 @@ static void ceph_sock_state_change(struct sock *sk) switch (sk->sk_state) { case TCP_CLOSE: dout("%s TCP_CLOSE\n", __func__); - /* fall through */ + fallthrough; case TCP_CLOSE_WAIT: dout("%s TCP_CLOSE_WAIT\n", __func__); con_sock_state_closing(con); @@ -2751,7 +2751,7 @@ more: switch (ret) { case -EBADMSG: con->error_msg = "bad crc/signature"; - /* fall through */ + fallthrough; case -EBADE: ret = -EIO; break; diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 3d8c8015e976..d633a0aeaa55 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1307,7 +1307,7 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, * request had a non-zero tid. Work around this weirdness * by allocating a new message. */ - /* fall through */ + fallthrough; case CEPH_MSG_MON_MAP: case CEPH_MSG_MDS_MAP: case CEPH_MSG_OSD_MAP: diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index e4fbcad6e7d8..7901ab6c79fd 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -3854,7 +3854,7 @@ static void scan_requests(struct ceph_osd *osd, if (!force_resend && !force_resend_writes) break; - /* fall through */ + fallthrough; case CALC_TARGET_NEED_RESEND: cancel_linger_map_check(lreq); /* @@ -3891,7 +3891,7 @@ static void scan_requests(struct ceph_osd *osd, !force_resend_writes)) break; - /* fall through */ + fallthrough; case CALC_TARGET_NEED_RESEND: cancel_map_check(req); unlink_request(osd, req); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index b988f48153a4..a0d1a3265b71 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -7,97 +7,14 @@ #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf_ids.h> +#include <linux/bpf_local_storage.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> +#include <linux/btf_ids.h> -#define SK_STORAGE_CREATE_FLAG_MASK \ - (BPF_F_NO_PREALLOC | BPF_F_CLONE) - -struct bucket { - struct hlist_head list; - raw_spinlock_t lock; -}; - -/* Thp map is not the primary owner of a bpf_sk_storage_elem. - * Instead, the sk->sk_bpf_storage is. - * - * The map (bpf_sk_storage_map) is for two purposes - * 1. Define the size of the "sk local storage". It is - * the map's value_size. - * - * 2. Maintain a list to keep track of all elems such - * that they can be cleaned up during the map destruction. - * - * When a bpf local storage is being looked up for a - * particular sk, the "bpf_map" pointer is actually used - * as the "key" to search in the list of elem in - * sk->sk_bpf_storage. - * - * Hence, consider sk->sk_bpf_storage is the mini-map - * with the "bpf_map" pointer as the searching key. - */ -struct bpf_sk_storage_map { - struct bpf_map map; - /* Lookup elem does not require accessing the map. - * - * Updating/Deleting requires a bucket lock to - * link/unlink the elem from the map. Having - * multiple buckets to improve contention. - */ - struct bucket *buckets; - u32 bucket_log; - u16 elem_size; - u16 cache_idx; -}; - -struct bpf_sk_storage_data { - /* smap is used as the searching key when looking up - * from sk->sk_bpf_storage. - * - * Put it in the same cacheline as the data to minimize - * the number of cachelines access during the cache hit case. - */ - struct bpf_sk_storage_map __rcu *smap; - u8 data[] __aligned(8); -}; - -/* Linked to bpf_sk_storage and bpf_sk_storage_map */ -struct bpf_sk_storage_elem { - struct hlist_node map_node; /* Linked to bpf_sk_storage_map */ - struct hlist_node snode; /* Linked to bpf_sk_storage */ - struct bpf_sk_storage __rcu *sk_storage; - struct rcu_head rcu; - /* 8 bytes hole */ - /* The data is stored in aother cacheline to minimize - * the number of cachelines access during a cache hit. - */ - struct bpf_sk_storage_data sdata ____cacheline_aligned; -}; - -#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata) -#define SDATA(_SELEM) (&(_SELEM)->sdata) -#define BPF_SK_STORAGE_CACHE_SIZE 16 - -static DEFINE_SPINLOCK(cache_idx_lock); -static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE]; - -struct bpf_sk_storage { - struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE]; - struct hlist_head list; /* List of bpf_sk_storage_elem */ - struct sock *sk; /* The sk that owns the the above "list" of - * bpf_sk_storage_elem. - */ - struct rcu_head rcu; - raw_spinlock_t lock; /* Protect adding/removing from the "list" */ -}; - -static struct bucket *select_bucket(struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) -{ - return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; -} +DEFINE_BPF_STORAGE_CACHE(sk_cache); static int omem_charge(struct sock *sk, unsigned int size) { @@ -111,445 +28,38 @@ static int omem_charge(struct sock *sk, unsigned int size) return -ENOMEM; } -static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem) -{ - return !hlist_unhashed(&selem->snode); -} - -static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem) -{ - return !hlist_unhashed(&selem->map_node); -} - -static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, - struct sock *sk, void *value, - bool charge_omem) -{ - struct bpf_sk_storage_elem *selem; - - if (charge_omem && omem_charge(sk, smap->elem_size)) - return NULL; - - selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (selem) { - if (value) - memcpy(SDATA(selem)->data, value, smap->map.value_size); - return selem; - } - - if (charge_omem) - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - - return NULL; -} - -/* sk_storage->lock must be held and selem->sk_storage == sk_storage. - * The caller must ensure selem->smap is still valid to be - * dereferenced for its smap->elem_size and smap->cache_idx. - */ -static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_elem *selem, - bool uncharge_omem) -{ - struct bpf_sk_storage_map *smap; - bool free_sk_storage; - struct sock *sk; - - smap = rcu_dereference(SDATA(selem)->smap); - sk = sk_storage->sk; - - /* All uncharging on sk->sk_omem_alloc must be done first. - * sk may be freed once the last selem is unlinked from sk_storage. - */ - if (uncharge_omem) - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - - free_sk_storage = hlist_is_singular_node(&selem->snode, - &sk_storage->list); - if (free_sk_storage) { - atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc); - sk_storage->sk = NULL; - /* After this RCU_INIT, sk may be freed and cannot be used */ - RCU_INIT_POINTER(sk->sk_bpf_storage, NULL); - - /* sk_storage is not freed now. sk_storage->lock is - * still held and raw_spin_unlock_bh(&sk_storage->lock) - * will be done by the caller. - * - * Although the unlock will be done under - * rcu_read_lock(), it is more intutivie to - * read if kfree_rcu(sk_storage, rcu) is done - * after the raw_spin_unlock_bh(&sk_storage->lock). - * - * Hence, a "bool free_sk_storage" is returned - * to the caller which then calls the kfree_rcu() - * after unlock. - */ - } - hlist_del_init_rcu(&selem->snode); - if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) == - SDATA(selem)) - RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL); - - kfree_rcu(selem, rcu); - - return free_sk_storage; -} - -static void selem_unlink_sk(struct bpf_sk_storage_elem *selem) -{ - struct bpf_sk_storage *sk_storage; - bool free_sk_storage = false; - - if (unlikely(!selem_linked_to_sk(selem))) - /* selem has already been unlinked from sk */ - return; - - sk_storage = rcu_dereference(selem->sk_storage); - raw_spin_lock_bh(&sk_storage->lock); - if (likely(selem_linked_to_sk(selem))) - free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); - raw_spin_unlock_bh(&sk_storage->lock); - - if (free_sk_storage) - kfree_rcu(sk_storage, rcu); -} - -static void __selem_link_sk(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_elem *selem) -{ - RCU_INIT_POINTER(selem->sk_storage, sk_storage); - hlist_add_head(&selem->snode, &sk_storage->list); -} - -static void selem_unlink_map(struct bpf_sk_storage_elem *selem) -{ - struct bpf_sk_storage_map *smap; - struct bucket *b; - - if (unlikely(!selem_linked_to_map(selem))) - /* selem has already be unlinked from smap */ - return; - - smap = rcu_dereference(SDATA(selem)->smap); - b = select_bucket(smap, selem); - raw_spin_lock_bh(&b->lock); - if (likely(selem_linked_to_map(selem))) - hlist_del_init_rcu(&selem->map_node); - raw_spin_unlock_bh(&b->lock); -} - -static void selem_link_map(struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) -{ - struct bucket *b = select_bucket(smap, selem); - - raw_spin_lock_bh(&b->lock); - RCU_INIT_POINTER(SDATA(selem)->smap, smap); - hlist_add_head_rcu(&selem->map_node, &b->list); - raw_spin_unlock_bh(&b->lock); -} - -static void selem_unlink(struct bpf_sk_storage_elem *selem) -{ - /* Always unlink from map before unlinking from sk_storage - * because selem will be freed after successfully unlinked from - * the sk_storage. - */ - selem_unlink_map(selem); - selem_unlink_sk(selem); -} - -static struct bpf_sk_storage_data * -__sk_storage_lookup(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_map *smap, - bool cacheit_lockit) -{ - struct bpf_sk_storage_data *sdata; - struct bpf_sk_storage_elem *selem; - - /* Fast path (cache hit) */ - sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]); - if (sdata && rcu_access_pointer(sdata->smap) == smap) - return sdata; - - /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) - if (rcu_access_pointer(SDATA(selem)->smap) == smap) - break; - - if (!selem) - return NULL; - - sdata = SDATA(selem); - if (cacheit_lockit) { - /* spinlock is needed to avoid racing with the - * parallel delete. Otherwise, publishing an already - * deleted sdata to the cache will become a use-after-free - * problem in the next __sk_storage_lookup(). - */ - raw_spin_lock_bh(&sk_storage->lock); - if (selem_linked_to_sk(selem)) - rcu_assign_pointer(sk_storage->cache[smap->cache_idx], - sdata); - raw_spin_unlock_bh(&sk_storage->lock); - } - - return sdata; -} - -static struct bpf_sk_storage_data * +static struct bpf_local_storage_data * sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) { - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_map *smap; sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage) return NULL; - smap = (struct bpf_sk_storage_map *)map; - return __sk_storage_lookup(sk_storage, smap, cacheit_lockit); -} - -static int check_flags(const struct bpf_sk_storage_data *old_sdata, - u64 map_flags) -{ - if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) - /* elem already exists */ - return -EEXIST; - - if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) - /* elem doesn't exist, cannot update it */ - return -ENOENT; - - return 0; -} - -static int sk_storage_alloc(struct sock *sk, - struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *first_selem) -{ - struct bpf_sk_storage *prev_sk_storage, *sk_storage; - int err; - - err = omem_charge(sk, sizeof(*sk_storage)); - if (err) - return err; - - sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN); - if (!sk_storage) { - err = -ENOMEM; - goto uncharge; - } - INIT_HLIST_HEAD(&sk_storage->list); - raw_spin_lock_init(&sk_storage->lock); - sk_storage->sk = sk; - - __selem_link_sk(sk_storage, first_selem); - selem_link_map(smap, first_selem); - /* Publish sk_storage to sk. sk->sk_lock cannot be acquired. - * Hence, atomic ops is used to set sk->sk_bpf_storage - * from NULL to the newly allocated sk_storage ptr. - * - * From now on, the sk->sk_bpf_storage pointer is protected - * by the sk_storage->lock. Hence, when freeing - * the sk->sk_bpf_storage, the sk_storage->lock must - * be held before setting sk->sk_bpf_storage to NULL. - */ - prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage, - NULL, sk_storage); - if (unlikely(prev_sk_storage)) { - selem_unlink_map(first_selem); - err = -EAGAIN; - goto uncharge; - - /* Note that even first_selem was linked to smap's - * bucket->list, first_selem can be freed immediately - * (instead of kfree_rcu) because - * bpf_sk_storage_map_free() does a - * synchronize_rcu() before walking the bucket->list. - * Hence, no one is accessing selem from the - * bucket->list under rcu_read_lock(). - */ - } - - return 0; - -uncharge: - kfree(sk_storage); - atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc); - return err; -} - -/* sk cannot be going away because it is linking new elem - * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). - * Otherwise, it will become a leak (and other memory issues - * during map destruction). - */ -static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, - struct bpf_map *map, - void *value, - u64 map_flags) -{ - struct bpf_sk_storage_data *old_sdata = NULL; - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_map *smap; - int err; - - /* BPF_EXIST and BPF_NOEXIST cannot be both set */ - if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || - /* BPF_F_LOCK can only be used in a value with spin_lock */ - unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) - return ERR_PTR(-EINVAL); - - smap = (struct bpf_sk_storage_map *)map; - sk_storage = rcu_dereference(sk->sk_bpf_storage); - if (!sk_storage || hlist_empty(&sk_storage->list)) { - /* Very first elem for this sk */ - err = check_flags(NULL, map_flags); - if (err) - return ERR_PTR(err); - - selem = selem_alloc(smap, sk, value, true); - if (!selem) - return ERR_PTR(-ENOMEM); - - err = sk_storage_alloc(sk, smap, selem); - if (err) { - kfree(selem); - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - return ERR_PTR(err); - } - - return SDATA(selem); - } - - if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { - /* Hoping to find an old_sdata to do inline update - * such that it can avoid taking the sk_storage->lock - * and changing the lists. - */ - old_sdata = __sk_storage_lookup(sk_storage, smap, false); - err = check_flags(old_sdata, map_flags); - if (err) - return ERR_PTR(err); - if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) { - copy_map_value_locked(map, old_sdata->data, - value, false); - return old_sdata; - } - } - - raw_spin_lock_bh(&sk_storage->lock); - - /* Recheck sk_storage->list under sk_storage->lock */ - if (unlikely(hlist_empty(&sk_storage->list))) { - /* A parallel del is happening and sk_storage is going - * away. It has just been checked before, so very - * unlikely. Return instead of retry to keep things - * simple. - */ - err = -EAGAIN; - goto unlock_err; - } - - old_sdata = __sk_storage_lookup(sk_storage, smap, false); - err = check_flags(old_sdata, map_flags); - if (err) - goto unlock_err; - - if (old_sdata && (map_flags & BPF_F_LOCK)) { - copy_map_value_locked(map, old_sdata->data, value, false); - selem = SELEM(old_sdata); - goto unlock; - } - - /* sk_storage->lock is held. Hence, we are sure - * we can unlink and uncharge the old_sdata successfully - * later. Hence, instead of charging the new selem now - * and then uncharge the old selem later (which may cause - * a potential but unnecessary charge failure), avoid taking - * a charge at all here (the "!old_sdata" check) and the - * old_sdata will not be uncharged later during __selem_unlink_sk(). - */ - selem = selem_alloc(smap, sk, value, !old_sdata); - if (!selem) { - err = -ENOMEM; - goto unlock_err; - } - - /* First, link the new selem to the map */ - selem_link_map(smap, selem); - - /* Second, link (and publish) the new selem to sk_storage */ - __selem_link_sk(sk_storage, selem); - - /* Third, remove old selem, SELEM(old_sdata) */ - if (old_sdata) { - selem_unlink_map(SELEM(old_sdata)); - __selem_unlink_sk(sk_storage, SELEM(old_sdata), false); - } - -unlock: - raw_spin_unlock_bh(&sk_storage->lock); - return SDATA(selem); - -unlock_err: - raw_spin_unlock_bh(&sk_storage->lock); - return ERR_PTR(err); + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit); } static int sk_storage_delete(struct sock *sk, struct bpf_map *map) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; sdata = sk_storage_lookup(sk, map, false); if (!sdata) return -ENOENT; - selem_unlink(SELEM(sdata)); + bpf_selem_unlink(SELEM(sdata)); return 0; } -static u16 cache_idx_get(void) -{ - u64 min_usage = U64_MAX; - u16 i, res = 0; - - spin_lock(&cache_idx_lock); - - for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) { - if (cache_idx_usage_counts[i] < min_usage) { - min_usage = cache_idx_usage_counts[i]; - res = i; - - /* Found a free cache_idx */ - if (!min_usage) - break; - } - } - cache_idx_usage_counts[res]++; - - spin_unlock(&cache_idx_lock); - - return res; -} - -static void cache_idx_free(u16 idx) -{ - spin_lock(&cache_idx_lock); - cache_idx_usage_counts[idx]--; - spin_unlock(&cache_idx_lock); -} - /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage *sk_storage; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage *sk_storage; bool free_sk_storage = false; struct hlist_node *n; @@ -565,7 +75,7 @@ void bpf_sk_storage_free(struct sock *sk) * Thus, no elem can be added-to or deleted-from the * sk_storage->list by the bpf_prog or by the bpf-map's syscall. * - * It is racing with bpf_sk_storage_map_free() alone + * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the sk_storage->list and * the map's bucket->list. */ @@ -574,8 +84,9 @@ void bpf_sk_storage_free(struct sock *sk) /* Always unlink from map before unlinking from * sk_storage. */ - selem_unlink_map(selem); - free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + bpf_selem_unlink_map(selem); + free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage, + selem, true); } raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); @@ -584,132 +95,24 @@ void bpf_sk_storage_free(struct sock *sk) kfree_rcu(sk_storage, rcu); } -static void bpf_sk_storage_map_free(struct bpf_map *map) -{ - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage_map *smap; - struct bucket *b; - unsigned int i; - - smap = (struct bpf_sk_storage_map *)map; - - cache_idx_free(smap->cache_idx); - - /* Note that this map might be concurrently cloned from - * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone - * RCU read section to finish before proceeding. New RCU - * read sections should be prevented via bpf_map_inc_not_zero. - */ - synchronize_rcu(); - - /* bpf prog and the userspace can no longer access this map - * now. No new selem (of this map) can be added - * to the sk->sk_bpf_storage or to the map bucket's list. - * - * The elem of this map can be cleaned up here - * or - * by bpf_sk_storage_free() during __sk_destruct(). - */ - for (i = 0; i < (1U << smap->bucket_log); i++) { - b = &smap->buckets[i]; - - rcu_read_lock(); - /* No one is adding to b->list now */ - while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)), - struct bpf_sk_storage_elem, - map_node))) { - selem_unlink(selem); - cond_resched_rcu(); - } - rcu_read_unlock(); - } - - /* bpf_sk_storage_free() may still need to access the map. - * e.g. bpf_sk_storage_free() has unlinked selem from the map - * which then made the above while((selem = ...)) loop - * exited immediately. - * - * However, the bpf_sk_storage_free() still needs to access - * the smap->elem_size to do the uncharging in - * __selem_unlink_sk(). - * - * Hence, wait another rcu grace period for the - * bpf_sk_storage_free() to finish. - */ - synchronize_rcu(); - - kvfree(smap->buckets); - kfree(map); -} - -/* U16_MAX is much more than enough for sk local storage - * considering a tcp_sock is ~2k. - */ -#define MAX_VALUE_SIZE \ - min_t(u32, \ - (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \ - (U16_MAX - sizeof(struct bpf_sk_storage_elem))) - -static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) +static void sk_storage_map_free(struct bpf_map *map) { - if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK || - !(attr->map_flags & BPF_F_NO_PREALLOC) || - attr->max_entries || - attr->key_size != sizeof(int) || !attr->value_size || - /* Enforce BTF for userspace sk dumping */ - !attr->btf_key_type_id || !attr->btf_value_type_id) - return -EINVAL; - - if (!bpf_capable()) - return -EPERM; + struct bpf_local_storage_map *smap; - if (attr->value_size > MAX_VALUE_SIZE) - return -E2BIG; - - return 0; + smap = (struct bpf_local_storage_map *)map; + bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); + bpf_local_storage_map_free(smap); } -static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) +static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr) { - struct bpf_sk_storage_map *smap; - unsigned int i; - u32 nbuckets; - u64 cost; - int ret; - - smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); - if (!smap) - return ERR_PTR(-ENOMEM); - bpf_map_init_from_attr(&smap->map, attr); - - nbuckets = roundup_pow_of_two(num_possible_cpus()); - /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ - nbuckets = max_t(u32, 2, nbuckets); - smap->bucket_log = ilog2(nbuckets); - cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); - - ret = bpf_map_charge_init(&smap->map.memory, cost); - if (ret < 0) { - kfree(smap); - return ERR_PTR(ret); - } - - smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, - GFP_USER | __GFP_NOWARN); - if (!smap->buckets) { - bpf_map_charge_finish(&smap->map.memory); - kfree(smap); - return ERR_PTR(-ENOMEM); - } + struct bpf_local_storage_map *smap; - for (i = 0; i < nbuckets; i++) { - INIT_HLIST_HEAD(&smap->buckets[i].list); - raw_spin_lock_init(&smap->buckets[i].lock); - } - - smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; - smap->cache_idx = cache_idx_get(); + smap = bpf_local_storage_map_alloc(attr); + if (IS_ERR(smap)) + return ERR_CAST(smap); + smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); return &smap->map; } @@ -719,26 +122,9 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, - const struct btf *btf, - const struct btf_type *key_type, - const struct btf_type *value_type) -{ - u32 int_data; - - if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) - return -EINVAL; - - int_data = *(u32 *)(key_type + 1); - if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) - return -EINVAL; - - return 0; -} - static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; @@ -756,14 +142,16 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { - sdata = sk_storage_update(sock->sk, map, value, map_flags); + sdata = bpf_local_storage_update( + sock->sk, (struct bpf_local_storage_map *)map, value, + map_flags); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } @@ -787,14 +175,14 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) return err; } -static struct bpf_sk_storage_elem * +static struct bpf_local_storage_elem * bpf_sk_storage_clone_elem(struct sock *newsk, - struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { - struct bpf_sk_storage_elem *copy_selem; + struct bpf_local_storage_elem *copy_selem; - copy_selem = selem_alloc(smap, newsk, NULL, true); + copy_selem = bpf_selem_alloc(smap, newsk, NULL, true); if (!copy_selem) return NULL; @@ -810,9 +198,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk, int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) { - struct bpf_sk_storage *new_sk_storage = NULL; - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage *new_sk_storage = NULL; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; int ret = 0; RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); @@ -824,8 +212,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) goto out; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { - struct bpf_sk_storage_elem *copy_selem; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_elem *copy_selem; + struct bpf_local_storage_map *smap; struct bpf_map *map; smap = rcu_dereference(SDATA(selem)->smap); @@ -833,7 +221,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) continue; /* Note that for lockless listeners adding new element - * here can race with cleanup in bpf_sk_storage_map_free. + * here can race with cleanup in bpf_local_storage_map_free. * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ @@ -849,10 +237,10 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) } if (new_sk_storage) { - selem_link_map(smap, copy_selem); - __selem_link_sk(new_sk_storage, copy_selem); + bpf_selem_link_map(smap, copy_selem); + bpf_selem_link_storage_nolock(new_sk_storage, copy_selem); } else { - ret = sk_storage_alloc(newsk, smap, copy_selem); + ret = bpf_local_storage_alloc(newsk, smap, copy_selem); if (ret) { kfree(copy_selem); atomic_sub(smap->elem_size, @@ -861,7 +249,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) goto out; } - new_sk_storage = rcu_dereference(copy_selem->sk_storage); + new_sk_storage = + rcu_dereference(copy_selem->local_storage); } bpf_map_put(map); } @@ -879,7 +268,7 @@ out: BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; if (flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; @@ -895,7 +284,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, * destruction). */ refcount_inc_not_zero(&sk->sk_refcnt)) { - sdata = sk_storage_update(sk, map, value, BPF_NOEXIST); + sdata = bpf_local_storage_update( + sk, (struct bpf_local_storage_map *)map, value, + BPF_NOEXIST); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ @@ -920,18 +311,44 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) return -ENOENT; } +static int sk_storage_charge(struct bpf_local_storage_map *smap, + void *owner, u32 size) +{ + return omem_charge(owner, size); +} + +static void sk_storage_uncharge(struct bpf_local_storage_map *smap, + void *owner, u32 size) +{ + struct sock *sk = owner; + + atomic_sub(size, &sk->sk_omem_alloc); +} + +static struct bpf_local_storage __rcu ** +sk_storage_ptr(void *owner) +{ + struct sock *sk = owner; + + return &sk->sk_bpf_storage; +} + static int sk_storage_map_btf_id; const struct bpf_map_ops sk_storage_map_ops = { - .map_alloc_check = bpf_sk_storage_map_alloc_check, - .map_alloc = bpf_sk_storage_map_alloc, - .map_free = bpf_sk_storage_map_free, + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = sk_storage_map_alloc, + .map_free = sk_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, - .map_check_btf = bpf_sk_storage_map_check_btf, - .map_btf_name = "bpf_sk_storage_map", + .map_check_btf = bpf_local_storage_map_check_btf, + .map_btf_name = "bpf_local_storage_map", .map_btf_id = &sk_storage_map_btf_id, + .map_local_storage_charge = sk_storage_charge, + .map_local_storage_uncharge = sk_storage_uncharge, + .map_owner_storage_ptr = sk_storage_ptr, }; const struct bpf_func_proto bpf_sk_storage_get_proto = { @@ -962,6 +379,30 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { .arg2_type = ARG_PTR_TO_SOCKET, }; +BTF_ID_LIST(sk_storage_btf_ids) +BTF_ID_UNUSED +BTF_ID(struct, sock) + +const struct bpf_func_proto sk_storage_get_btf_proto = { + .func = bpf_sk_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, + .btf_id = sk_storage_btf_ids, +}; + +const struct bpf_func_proto sk_storage_delete_btf_proto = { + .func = bpf_sk_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .btf_id = sk_storage_btf_ids, +}; + struct bpf_sk_storage_diag { u32 nr_maps; struct bpf_map *maps[]; @@ -1022,7 +463,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) u32 nr_maps = 0; int rem, err; - /* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as + /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as * the map_alloc_check() side also does. */ if (!bpf_capable()) @@ -1072,13 +513,13 @@ err_free: } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); -static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb) +static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) { struct nlattr *nla_stg, *nla_value; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_map *smap; /* It cannot exceed max nlattr's payload */ - BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE); + BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE); nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); if (!nla_stg) @@ -1114,9 +555,9 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; @@ -1169,8 +610,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_data *sdata; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; @@ -1197,8 +638,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, saved_len = skb->len; for (i = 0; i < diag->nr_maps; i++) { - sdata = __sk_storage_lookup(sk_storage, - (struct bpf_sk_storage_map *)diag->maps[i], + sdata = bpf_local_storage_lookup(sk_storage, + (struct bpf_local_storage_map *)diag->maps[i], false); if (!sdata) @@ -1235,19 +676,19 @@ struct bpf_iter_seq_sk_storage_map_info { unsigned skip_elems; }; -static struct bpf_sk_storage_elem * +static struct bpf_local_storage_elem * bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, - struct bpf_sk_storage_elem *prev_selem) + struct bpf_local_storage_elem *prev_selem) { - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; u32 skip_elems = info->skip_elems; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_map *smap; u32 bucket_id = info->bucket_id; u32 i, count, n_buckets; - struct bucket *b; + struct bpf_local_storage_map_bucket *b; - smap = (struct bpf_sk_storage_map *)info->map; + smap = (struct bpf_local_storage_map *)info->map; n_buckets = 1U << smap->bucket_log; if (bucket_id >= n_buckets) return NULL; @@ -1257,7 +698,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, count = 0; while (selem) { selem = hlist_entry_safe(selem->map_node.next, - struct bpf_sk_storage_elem, map_node); + struct bpf_local_storage_elem, map_node); if (!selem) { /* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; @@ -1265,7 +706,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, skip_elems = 0; break; } - sk_storage = rcu_dereference_raw(selem->sk_storage); + sk_storage = rcu_dereference_raw(selem->local_storage); if (sk_storage) { info->skip_elems = skip_elems + count; return selem; @@ -1278,7 +719,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, raw_spin_lock_bh(&b->lock); count = 0; hlist_for_each_entry(selem, &b->list, map_node) { - sk_storage = rcu_dereference_raw(selem->sk_storage); + sk_storage = rcu_dereference_raw(selem->local_storage); if (sk_storage && count >= skip_elems) { info->bucket_id = i; info->skip_elems = count; @@ -1297,7 +738,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) { - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage_elem *selem; selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); if (!selem) @@ -1330,11 +771,11 @@ DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, void *value) static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, - struct bpf_sk_storage_elem *selem) + struct bpf_local_storage_elem *selem) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter__bpf_sk_storage_map ctx = {}; - struct bpf_sk_storage *sk_storage; + struct bpf_local_storage *sk_storage; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret = 0; @@ -1345,8 +786,8 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, ctx.meta = &meta; ctx.map = info->map; if (selem) { - sk_storage = rcu_dereference_raw(selem->sk_storage); - ctx.sk = sk_storage->sk; + sk_storage = rcu_dereference_raw(selem->local_storage); + ctx.sk = sk_storage->owner; ctx.value = SDATA(selem)->data; } ret = bpf_iter_run_prog(prog, &ctx); @@ -1363,13 +804,13 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; - struct bpf_sk_storage_map *smap; - struct bucket *b; + struct bpf_local_storage_map *smap; + struct bpf_local_storage_map_bucket *b; if (!v) { (void)__bpf_sk_storage_map_seq_show(seq, v); } else { - smap = (struct bpf_sk_storage_map *)info->map; + smap = (struct bpf_local_storage_map *)info->map; b = &smap->buckets[info->bucket_id]; raw_spin_unlock_bh(&b->lock); } @@ -1437,6 +878,8 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { .target = "bpf_sk_storage_map", .attach_target = bpf_iter_attach_map, .detach_target = bpf_iter_detach_map, + .show_fdinfo = bpf_iter_map_show_fdinfo, + .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), diff --git a/net/core/datagram.c b/net/core/datagram.c index 639745d4f3b9..9fcaa544f11a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -623,10 +623,11 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, while (length && iov_iter_count(from)) { struct page *pages[MAX_SKB_FRAGS]; + struct page *last_head = NULL; size_t start; ssize_t copied; unsigned long truesize; - int n = 0; + int refs, n = 0; if (frag == MAX_SKB_FRAGS) return -EMSGSIZE; @@ -649,13 +650,37 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } - while (copied) { + for (refs = 0; copied != 0; start = 0) { int size = min_t(int, copied, PAGE_SIZE - start); - skb_fill_page_desc(skb, frag++, pages[n], start, size); - start = 0; + struct page *head = compound_head(pages[n]); + + start += (pages[n] - head) << PAGE_SHIFT; copied -= size; n++; + if (frag) { + skb_frag_t *last = &skb_shinfo(skb)->frags[frag - 1]; + + if (head == skb_frag_page(last) && + start == skb_frag_off(last) + skb_frag_size(last)) { + skb_frag_size_add(last, size); + /* We combined this page, we need to release + * a reference. Since compound pages refcount + * is shared among many pages, batch the refcount + * adjustments to limit false sharing. + */ + last_head = head; + refs++; + continue; + } + } + if (refs) { + page_ref_sub(last_head, refs); + refs = 0; + } + skb_fill_page_desc(skb, frag++, head, start, size); } + if (refs) + page_ref_sub(last_head, refs); } return 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 7df6c9617321..03624192862a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4690,10 +4690,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, break; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(skb->dev, xdp_prog, act); - /* fall through */ + fallthrough; case XDP_DROP: do_drop: kfree_skb(skb); @@ -6293,7 +6293,7 @@ EXPORT_SYMBOL(__napi_schedule); * @n: napi context * * Test if NAPI routine is already running, and if not mark - * it as running. This is used as a condition variable + * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ @@ -6533,8 +6533,7 @@ EXPORT_SYMBOL(napi_busy_loop); static void napi_hash_add(struct napi_struct *napi) { - if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) || - test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) + if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock(&napi_hash_lock); @@ -6555,20 +6554,14 @@ static void napi_hash_add(struct napi_struct *napi) /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ -bool napi_hash_del(struct napi_struct *napi) +static void napi_hash_del(struct napi_struct *napi) { - bool rcu_sync_needed = false; - spin_lock(&napi_hash_lock); - if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) { - rcu_sync_needed = true; - hlist_del_rcu(&napi->napi_hash_node); - } + hlist_del_init_rcu(&napi->napi_hash_node); + spin_unlock(&napi_hash_lock); - return rcu_sync_needed; } -EXPORT_SYMBOL_GPL(napi_hash_del); static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) { @@ -6600,7 +6593,11 @@ static void init_gro_hash(struct napi_struct *napi) void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { + if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) + return; + INIT_LIST_HEAD(&napi->poll_list); + INIT_HLIST_NODE(&napi->napi_hash_node); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; init_gro_hash(napi); @@ -6612,12 +6609,13 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; - list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif set_bit(NAPI_STATE_SCHED, &napi->state); + set_bit(NAPI_STATE_NPSVC, &napi->state); + list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); } EXPORT_SYMBOL(netif_napi_add); @@ -6652,18 +6650,19 @@ static void flush_gro_hash(struct napi_struct *napi) } /* Must be called in process context */ -void netif_napi_del(struct napi_struct *napi) +void __netif_napi_del(struct napi_struct *napi) { - might_sleep(); - if (napi_hash_del(napi)) - synchronize_net(); - list_del_init(&napi->dev_list); + if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) + return; + + napi_hash_del(napi); + list_del_rcu(&napi->dev_list); napi_free_frags(napi); flush_gro_hash(napi); napi->gro_bitmask = 0; } -EXPORT_SYMBOL(netif_napi_del); +EXPORT_SYMBOL(__netif_napi_del); static int napi_poll(struct napi_struct *n, struct list_head *repoll) { @@ -8742,13 +8741,15 @@ struct bpf_xdp_link { int flags; }; -static enum bpf_xdp_mode dev_xdp_mode(u32 flags) +static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags) { if (flags & XDP_FLAGS_HW_MODE) return XDP_MODE_HW; if (flags & XDP_FLAGS_DRV_MODE) return XDP_MODE_DRV; - return XDP_MODE_SKB; + if (flags & XDP_FLAGS_SKB_MODE) + return XDP_MODE_SKB; + return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB; } static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) @@ -8896,7 +8897,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack return -EINVAL; } - mode = dev_xdp_mode(flags); + mode = dev_xdp_mode(dev, flags); /* can't replace attached link */ if (dev_xdp_link(dev, mode)) { NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); @@ -8913,10 +8914,6 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Active program does not match expected"); return -EEXIST; } - if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { - NL_SET_ERR_MSG(extack, "XDP program already attached"); - return -EBUSY; - } /* put effective new program into new_prog */ if (link) @@ -8927,6 +8924,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB ? XDP_MODE_DRV : XDP_MODE_SKB; + if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { + NL_SET_ERR_MSG(extack, "XDP program already attached"); + return -EBUSY; + } if (!offload && dev_xdp_prog(dev, other_mode)) { NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); return -EEXIST; @@ -8984,7 +8985,7 @@ static int dev_xdp_detach_link(struct net_device *dev, ASSERT_RTNL(); - mode = dev_xdp_mode(link->flags); + mode = dev_xdp_mode(dev, link->flags); if (dev_xdp_link(dev, mode) != link) return -EINVAL; @@ -9080,7 +9081,7 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, goto out_unlock; } - mode = dev_xdp_mode(xdp_link->flags); + mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, xdp_link->flags, new_prog); @@ -9164,7 +9165,7 @@ out_put_dev: int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags) { - enum bpf_xdp_mode mode = dev_xdp_mode(flags); + enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags); struct bpf_prog *new_prog = NULL, *old_prog = NULL; int err; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index b2cf9b7bb7b8..205e92e604ef 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -322,7 +322,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) err = net_hwtstamp_validate(ifr); if (err) return err; - /* fall through */ + fallthrough; /* * Unknown or private ioctl @@ -478,7 +478,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCSIFTXQLEN: if (!capable(CAP_NET_ADMIN)) return -EPERM; - /* fall through */ + fallthrough; /* * These ioctl calls: * - require local superuser power. @@ -503,7 +503,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCSHWTSTAMP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - /* fall through */ + fallthrough; case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: dev_load(net, ifr->ifr_name); diff --git a/net/core/devlink.c b/net/core/devlink.c index e674f0f46dc2..19037f114307 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -523,15 +523,20 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, return -EMSGSIZE; switch (devlink_port->attrs.flavour) { case DEVLINK_PORT_FLAVOUR_PCI_PF: - if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, - attrs->pci_pf.pf)) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_pf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf)) + return -EMSGSIZE; + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PCI_VF: - if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, - attrs->pci_vf.pf) || - nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, - attrs->pci_vf.vf)) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_vf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf)) + return -EMSGSIZE; + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: @@ -4063,7 +4068,7 @@ static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id) { lockdep_assert_held(&devlink->lock); - if (WARN_ON(xa_load(&devlink->snapshot_ids, id))) + if (xa_load(&devlink->snapshot_ids, id)) return -EEXIST; return xa_err(xa_store(&devlink->snapshot_ids, id, xa_mk_value(0), @@ -5895,6 +5900,7 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) continue; + mutex_lock(&devlink->lock); list_for_each_entry(port, &devlink->port_list, list) { mutex_lock(&port->reporters_lock); list_for_each_entry(reporter, &port->reporter_list, list) { @@ -5909,12 +5915,14 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, NLM_F_MULTI); if (err) { mutex_unlock(&port->reporters_lock); + mutex_unlock(&devlink->lock); goto out; } idx++; } mutex_unlock(&port->reporters_lock); } + mutex_unlock(&devlink->lock); } out: mutex_unlock(&devlink_mutex); @@ -6196,8 +6204,8 @@ devlink_trap_action_get_from_info(struct genl_info *info, val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]); switch (val) { - case DEVLINK_TRAP_ACTION_DROP: /* fall-through */ - case DEVLINK_TRAP_ACTION_TRAP: /* fall-through */ + case DEVLINK_TRAP_ACTION_DROP: + case DEVLINK_TRAP_ACTION_TRAP: case DEVLINK_TRAP_ACTION_MIRROR: *p_trap_action = val; break; @@ -7555,11 +7563,11 @@ int devlink_port_register(struct devlink *devlink, devlink_port->index = port_index; devlink_port->registered = true; spin_lock_init(&devlink_port->type_lock); + INIT_LIST_HEAD(&devlink_port->reporter_list); + mutex_init(&devlink_port->reporters_lock); list_add_tail(&devlink_port->list, &devlink->port_list); INIT_LIST_HEAD(&devlink_port->param_list); mutex_unlock(&devlink->lock); - INIT_LIST_HEAD(&devlink_port->reporter_list); - mutex_init(&devlink_port->reporters_lock); INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); devlink_port_type_warn_schedule(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); @@ -7576,13 +7584,13 @@ void devlink_port_unregister(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; - WARN_ON(!list_empty(&devlink_port->reporter_list)); - mutex_destroy(&devlink_port->reporters_lock); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); mutex_lock(&devlink->lock); list_del(&devlink_port->list); mutex_unlock(&devlink->lock); + WARN_ON(!list_empty(&devlink_port->reporter_list)); + mutex_destroy(&devlink_port->reporters_lock); } EXPORT_SYMBOL_GPL(devlink_port_unregister); @@ -7600,14 +7608,8 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } -/** - * devlink_port_type_eth_set - Set port type to Ethernet - * - * @devlink_port: devlink port - * @netdev: related netdevice - */ -void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev) +static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, + struct net_device *netdev) { const struct net_device_ops *ops = netdev->netdev_ops; @@ -7641,6 +7643,24 @@ void devlink_port_type_eth_set(struct devlink_port *devlink_port, err = ops->ndo_get_port_parent_id(netdev, &ppid); WARN_ON(err != -EOPNOTSUPP); } +} + +/** + * devlink_port_type_eth_set - Set port type to Ethernet + * + * @devlink_port: devlink port + * @netdev: related netdevice + */ +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ + if (netdev) + devlink_port_type_netdev_checks(devlink_port, netdev); + else + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); @@ -7712,9 +7732,12 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set); * devlink_port_attrs_pci_pf_set - Set PCI PF port attributes * * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance * @pf: associated PF for the devlink port instance + * @external: indicates if the port is for an external controller */ -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf) +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; @@ -7723,8 +7746,9 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf) DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) return; - + attrs->pci_pf.controller = controller; attrs->pci_pf.pf = pf; + attrs->pci_pf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); @@ -7732,11 +7756,13 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); * devlink_port_attrs_pci_vf_set - Set PCI VF port attributes * * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance * @pf: associated PF for the devlink port instance * @vf: associated VF of a PF for the devlink port instance + * @external: indicates if the port is for an external controller */ -void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, - u16 pf, u16 vf) +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u16 vf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; @@ -7745,8 +7771,10 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) return; + attrs->pci_vf.controller = controller; attrs->pci_vf.pf = pf; attrs->pci_vf.vf = vf; + attrs->pci_vf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); @@ -7777,9 +7805,23 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, WARN_ON(1); return -EINVAL; case DEVLINK_PORT_FLAVOUR_PCI_PF: + if (attrs->pci_pf.external) { + n = snprintf(name, len, "c%u", attrs->pci_pf.controller); + if (n >= len) + return -EINVAL; + len -= n; + name += n; + } n = snprintf(name, len, "pf%u", attrs->pci_pf.pf); break; case DEVLINK_PORT_FLAVOUR_PCI_VF: + if (attrs->pci_vf.external) { + n = snprintf(name, len, "c%u", attrs->pci_vf.controller); + if (n >= len) + return -EINVAL; + len -= n; + name += n; + } n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index b09bebeadf0b..9704522b0872 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1189,7 +1189,7 @@ static int net_dm_alert_mode_get_from_info(struct genl_info *info, val = nla_get_u8(info->attrs[NET_DM_ATTR_ALERT_MODE]); switch (val) { - case NET_DM_ALERT_MODE_SUMMARY: /* fall-through */ + case NET_DM_ALERT_MODE_SUMMARY: case NET_DM_ALERT_MODE_PACKET: *p_alert_mode = val; break; diff --git a/net/core/filter.c b/net/core/filter.c index 7124f0fe6974..2ad9c0ef1946 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4459,6 +4459,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, } else { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + unsigned long timeout; if (optlen != sizeof(int)) return -EINVAL; @@ -4480,6 +4481,20 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, tp->snd_ssthresh = val; } break; + case TCP_BPF_DELACK_MAX: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_DELACK_MAX || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_delack_max = timeout; + break; + case TCP_BPF_RTO_MIN: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_RTO_MIN || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_rto_min = timeout; + break; case TCP_SAVE_SYN: if (val < 0 || val > 1) ret = -EINVAL; @@ -4550,9 +4565,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, tp = tcp_sk(sk); if (optlen <= 0 || !tp->saved_syn || - optlen > tp->saved_syn[0]) + optlen > tcp_saved_syn_len(tp->saved_syn)) goto err_clear; - memcpy(optval, tp->saved_syn + 1, optlen); + memcpy(optval, tp->saved_syn->data, optlen); break; default: goto err_clear; @@ -4654,9 +4669,99 @@ static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .arg5_type = ARG_CONST_SIZE, }; +static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, + int optname, const u8 **start) +{ + struct sk_buff *syn_skb = bpf_sock->syn_skb; + const u8 *hdr_start; + int ret; + + if (syn_skb) { + /* sk is a request_sock here */ + + if (optname == TCP_BPF_SYN) { + hdr_start = syn_skb->data; + ret = tcp_hdrlen(syn_skb); + } else if (optname == TCP_BPF_SYN_IP) { + hdr_start = skb_network_header(syn_skb); + ret = skb_network_header_len(syn_skb) + + tcp_hdrlen(syn_skb); + } else { + /* optname == TCP_BPF_SYN_MAC */ + hdr_start = skb_mac_header(syn_skb); + ret = skb_mac_header_len(syn_skb) + + skb_network_header_len(syn_skb) + + tcp_hdrlen(syn_skb); + } + } else { + struct sock *sk = bpf_sock->sk; + struct saved_syn *saved_syn; + + if (sk->sk_state == TCP_NEW_SYN_RECV) + /* synack retransmit. bpf_sock->syn_skb will + * not be available. It has to resort to + * saved_syn (if it is saved). + */ + saved_syn = inet_reqsk(sk)->saved_syn; + else + saved_syn = tcp_sk(sk)->saved_syn; + + if (!saved_syn) + return -ENOENT; + + if (optname == TCP_BPF_SYN) { + hdr_start = saved_syn->data + + saved_syn->mac_hdrlen + + saved_syn->network_hdrlen; + ret = saved_syn->tcp_hdrlen; + } else if (optname == TCP_BPF_SYN_IP) { + hdr_start = saved_syn->data + + saved_syn->mac_hdrlen; + ret = saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; + } else { + /* optname == TCP_BPF_SYN_MAC */ + + /* TCP_SAVE_SYN may not have saved the mac hdr */ + if (!saved_syn->mac_hdrlen) + return -ENOENT; + + hdr_start = saved_syn->data; + ret = saved_syn->mac_hdrlen + + saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; + } + } + + *start = hdr_start; + return ret; +} + BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { + if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && + optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { + int ret, copy_len = 0; + const u8 *start; + + ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start); + if (ret > 0) { + copy_len = ret; + if (optlen < copy_len) { + copy_len = optlen; + ret = -ENOSPC; + } + + memcpy(optval, start, copy_len); + } + + /* Zero out unused buffer at the end */ + memset(optval + copy_len, 0, optlen - copy_len); + + return ret; + } + return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); } @@ -6150,6 +6255,232 @@ static const struct bpf_func_proto bpf_sk_assign_proto = { .arg3_type = ARG_ANYTHING, }; +static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend, + u8 search_kind, const u8 *magic, + u8 magic_len, bool *eol) +{ + u8 kind, kind_len; + + *eol = false; + + while (op < opend) { + kind = op[0]; + + if (kind == TCPOPT_EOL) { + *eol = true; + return ERR_PTR(-ENOMSG); + } else if (kind == TCPOPT_NOP) { + op++; + continue; + } + + if (opend - op < 2 || opend - op < op[1] || op[1] < 2) + /* Something is wrong in the received header. + * Follow the TCP stack's tcp_parse_options() + * and just bail here. + */ + return ERR_PTR(-EFAULT); + + kind_len = op[1]; + if (search_kind == kind) { + if (!magic_len) + return op; + + if (magic_len > kind_len - 2) + return ERR_PTR(-ENOMSG); + + if (!memcmp(&op[2], magic, magic_len)) + return op; + } + + op += kind_len; + } + + return ERR_PTR(-ENOMSG); +} + +BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + void *, search_res, u32, len, u64, flags) +{ + bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN; + const u8 *op, *opend, *magic, *search = search_res; + u8 search_kind, search_len, copy_len, magic_len; + int ret; + + /* 2 byte is the minimal option len except TCPOPT_NOP and + * TCPOPT_EOL which are useless for the bpf prog to learn + * and this helper disallow loading them also. + */ + if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN) + return -EINVAL; + + search_kind = search[0]; + search_len = search[1]; + + if (search_len > len || search_kind == TCPOPT_NOP || + search_kind == TCPOPT_EOL) + return -EINVAL; + + if (search_kind == TCPOPT_EXP || search_kind == 253) { + /* 16 or 32 bit magic. +2 for kind and kind length */ + if (search_len != 4 && search_len != 6) + return -EINVAL; + magic = &search[2]; + magic_len = search_len - 2; + } else { + if (search_len) + return -EINVAL; + magic = NULL; + magic_len = 0; + } + + if (load_syn) { + ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op); + if (ret < 0) + return ret; + + opend = op + ret; + op += sizeof(struct tcphdr); + } else { + if (!bpf_sock->skb || + bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB) + /* This bpf_sock->op cannot call this helper */ + return -EPERM; + + opend = bpf_sock->skb_data_end; + op = bpf_sock->skb->data + sizeof(struct tcphdr); + } + + op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len, + &eol); + if (IS_ERR(op)) + return PTR_ERR(op); + + copy_len = op[1]; + ret = copy_len; + if (copy_len > len) { + ret = -ENOSPC; + copy_len = len; + } + + memcpy(search_res, op, copy_len); + return ret; +} + +static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { + .func = bpf_sock_ops_load_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + const void *, from, u32, len, u64, flags) +{ + u8 new_kind, new_kind_len, magic_len = 0, *opend; + const u8 *op, *new_op, *magic = NULL; + struct sk_buff *skb; + bool eol; + + if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB) + return -EPERM; + + if (len < 2 || flags) + return -EINVAL; + + new_op = from; + new_kind = new_op[0]; + new_kind_len = new_op[1]; + + if (new_kind_len > len || new_kind == TCPOPT_NOP || + new_kind == TCPOPT_EOL) + return -EINVAL; + + if (new_kind_len > bpf_sock->remaining_opt_len) + return -ENOSPC; + + /* 253 is another experimental kind */ + if (new_kind == TCPOPT_EXP || new_kind == 253) { + if (new_kind_len < 4) + return -EINVAL; + /* Match for the 2 byte magic also. + * RFC 6994: the magic could be 2 or 4 bytes. + * Hence, matching by 2 byte only is on the + * conservative side but it is the right + * thing to do for the 'search-for-duplication' + * purpose. + */ + magic = &new_op[2]; + magic_len = 2; + } + + /* Check for duplication */ + skb = bpf_sock->skb; + op = skb->data + sizeof(struct tcphdr); + opend = bpf_sock->skb_data_end; + + op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len, + &eol); + if (!IS_ERR(op)) + return -EEXIST; + + if (PTR_ERR(op) != -ENOMSG) + return PTR_ERR(op); + + if (eol) + /* The option has been ended. Treat it as no more + * header option can be written. + */ + return -ENOSPC; + + /* No duplication found. Store the header option. */ + memcpy(opend, from, new_kind_len); + + bpf_sock->remaining_opt_len -= new_kind_len; + bpf_sock->skb_data_end += new_kind_len; + + return 0; +} + +static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { + .func = bpf_sock_ops_store_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + u32, len, u64, flags) +{ + if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB) + return -EPERM; + + if (flags || len < 2) + return -EINVAL; + + if (len > bpf_sock->remaining_opt_len) + return -ENOSPC; + + bpf_sock->remaining_opt_len -= len; + + return 0; +} + +static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { + .func = bpf_sock_ops_reserve_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -6179,6 +6510,9 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_lwt_seg6_adjust_srh || func == bpf_lwt_seg6_action || #endif +#ifdef CONFIG_INET + func == bpf_sock_ops_store_hdr_opt || +#endif func == bpf_lwt_in_push_encap || func == bpf_lwt_xmit_push_encap) return true; @@ -6550,6 +6884,12 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_INET + case BPF_FUNC_load_hdr_opt: + return &bpf_sock_ops_load_hdr_opt_proto; + case BPF_FUNC_store_hdr_opt: + return &bpf_sock_ops_store_hdr_opt_proto; + case BPF_FUNC_reserve_hdr_opt: + return &bpf_sock_ops_reserve_hdr_opt_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ @@ -7349,6 +7689,20 @@ static bool sock_ops_is_valid_access(int off, int size, return false; info->reg_type = PTR_TO_SOCKET_OR_NULL; break; + case offsetof(struct bpf_sock_ops, skb_data): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET; + break; + case offsetof(struct bpf_sock_ops, skb_data_end): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET_END; + break; + case offsetof(struct bpf_sock_ops, skb_tcp_flags): + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, + size_default); default: if (size != size_default) return false; @@ -8317,15 +8671,31 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ + int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + fullsock_reg = reg; \ + jmp += 2; \ + } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ - si->dst_reg, si->src_reg, \ + fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ - *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 2); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ + if (si->dst_reg == si->src_reg) \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ @@ -8334,6 +8704,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, OBJ_FIELD), \ si->dst_reg, si->dst_reg, \ offsetof(OBJ, OBJ_FIELD)); \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_JMP_A(1); \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + } \ + } while (0) + +#define SOCK_OPS_GET_SK() \ + do { \ + int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + fullsock_reg = reg; \ + jmp += 2; \ + } \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, \ + is_fullsock), \ + fullsock_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + is_fullsock)); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ + if (si->dst_reg == si->src_reg) \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, sk),\ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, sk));\ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_JMP_A(1); \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + } \ } while (0) #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ @@ -8391,17 +8804,22 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; switch (si->off) { - case offsetof(struct bpf_sock_ops, op) ... + case offsetof(struct bpf_sock_ops, op): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + op), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, op)); + break; + + case offsetof(struct bpf_sock_ops, replylong[0]) ... offsetof(struct bpf_sock_ops, replylong[3]): - BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) != - sizeof_field(struct bpf_sock_ops_kern, op)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != sizeof_field(struct bpf_sock_ops_kern, reply)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; - off -= offsetof(struct bpf_sock_ops, op); - off += offsetof(struct bpf_sock_ops_kern, op); + off -= offsetof(struct bpf_sock_ops, replylong[0]); + off += offsetof(struct bpf_sock_ops_kern, replylong[0]); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, off); @@ -8620,17 +9038,50 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); break; case offsetof(struct bpf_sock_ops, sk): - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct bpf_sock_ops_kern, - is_fullsock), + SOCK_OPS_GET_SK(); + break; + case offsetof(struct bpf_sock_ops, skb_data_end): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb_data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, - is_fullsock)); + skb_data_end)); + break; + case offsetof(struct bpf_sock_ops, skb_data): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct bpf_sock_ops_kern, sk), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), + si->dst_reg, si->dst_reg, + offsetof(struct sk_buff, data)); + break; + case offsetof(struct bpf_sock_ops, skb_len): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), si->dst_reg, si->src_reg, - offsetof(struct bpf_sock_ops_kern, sk)); + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), + si->dst_reg, si->dst_reg, + offsetof(struct sk_buff, len)); + break; + case offsetof(struct bpf_sock_ops, skb_tcp_flags): + off = offsetof(struct sk_buff, cb); + off += offsetof(struct tcp_skb_cb, tcp_flags); + *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb, + tcp_flags), + si->dst_reg, si->dst_reg, off); break; } return insn - insn_buf; @@ -9174,7 +9625,7 @@ sk_reuseport_is_valid_access(int off, int size, case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) return false; - /* fall through */ + fallthrough; case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): case bpf_ctx_range(struct sk_reuseport_md, bind_inany): case bpf_ctx_range(struct sk_reuseport_md, len): diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 093e90e52bc2..c310c7c1cef7 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -162,7 +162,7 @@ static void poll_napi(struct net_device *dev) struct napi_struct *napi; int cpu = smp_processor_id(); - list_for_each_entry(napi, &dev->napi_list, dev_list) { + list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) { poll_one_napi(napi); smp_store_release(&napi->poll_owner, -1); @@ -297,7 +297,7 @@ static int netpoll_owner_active(struct net_device *dev) { struct napi_struct *napi; - list_for_each_entry(napi, &dev->napi_list, dev_list) { + list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (napi->poll_owner == smp_processor_id()) return 1; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index b53b6d38c4df..44fdbb9c6e53 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3430,7 +3430,7 @@ xmit_more: net_info_ratelimited("%s xmit error: %d\n", pkt_dev->odevname, ret); pkt_dev->errors++; - /* fall through */ + fallthrough; case NETDEV_TX_BUSY: /* Retry it next time */ refcount_dec(&(pkt_dev->skb->users)); @@ -3699,7 +3699,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) cpu_to_node(cpu), "kpktgend_%d", cpu); if (IS_ERR(p)) { - pr_err("kernel_thread() failed for cpu %d\n", t->cpu); + pr_err("kthread_create_on_node() failed for cpu %d\n", t->cpu); list_del(&t->th_list); kfree(t); return PTR_ERR(p); diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index d964a5147f22..e33fde06d528 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -107,6 +107,36 @@ unsigned int ptp_classify_raw(const struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ptp_classify_raw); +struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type) +{ + u8 *ptr = skb_mac_header(skb); + + if (type & PTP_CLASS_VLAN) + ptr += VLAN_HLEN; + + switch (type & PTP_CLASS_PMASK) { + case PTP_CLASS_IPV4: + ptr += IPV4_HLEN(ptr) + UDP_HLEN; + break; + case PTP_CLASS_IPV6: + ptr += IP6_HLEN + UDP_HLEN; + break; + case PTP_CLASS_L2: + break; + default: + return NULL; + } + + ptr += ETH_HLEN; + + /* Ensure that the entire header is present in this packet. */ + if (ptr + sizeof(struct ptp_header) > skb->data + skb->len) + return NULL; + + return (struct ptp_header *)ptr; +} +EXPORT_SYMBOL_GPL(ptp_parse_header); + void __init ptp_classifier_init(void) { static struct sock_filter ptp_filter[] __initdata = { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7e2e502ef519..bfd748346f20 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -820,6 +820,7 @@ void skb_tx_error(struct sk_buff *skb) } EXPORT_SYMBOL(skb_tx_error); +#ifdef CONFIG_TRACEPOINTS /** * consume_skb - free an skbuff * @skb: buffer to free @@ -837,6 +838,7 @@ void consume_skb(struct sk_buff *skb) __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); +#endif /** * consume_stateless_skb - free an skbuff, assuming it is stateless @@ -5418,8 +5420,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb) skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; - - if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short)))) goto err_free; vhdr = (struct vlan_hdr *)skb->data; @@ -5953,8 +5955,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, size = SKB_WITH_OVERHEAD(ksize(data)); memcpy((struct skb_shared_info *)(data + size), - skb_shinfo(skb), offsetof(struct skb_shared_info, - frags[skb_shinfo(skb)->nr_frags])); + skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { kfree(data); return -ENOMEM; @@ -5987,9 +5988,13 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); - if (k == 0) { - /* split line is in frag list */ - pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask); + /* split line is in frag list */ + if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) { + /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ + if (skb_has_frag_list(skb)) + kfree_skb_list(skb_shinfo(skb)->frag_list); + kfree(data); + return -ENOMEM; } skb_release_data(skb); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 6a32a1fd34f8..4b5f7c8fecd1 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -494,14 +494,34 @@ end: struct sk_psock *sk_psock_init(struct sock *sk, int node) { - struct sk_psock *psock = kzalloc_node(sizeof(*psock), - GFP_ATOMIC | __GFP_NOWARN, - node); - if (!psock) - return NULL; + struct sk_psock *psock; + struct proto *prot; + + write_lock_bh(&sk->sk_callback_lock); + + if (inet_csk_has_ulp(sk)) { + psock = ERR_PTR(-EINVAL); + goto out; + } + + if (sk->sk_user_data) { + psock = ERR_PTR(-EBUSY); + goto out; + } + psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node); + if (!psock) { + psock = ERR_PTR(-ENOMEM); + goto out; + } + + prot = READ_ONCE(sk->sk_prot); psock->sk = sk; - psock->eval = __SK_NONE; + psock->eval = __SK_NONE; + psock->sk_proto = prot; + psock->saved_unhash = prot->unhash; + psock->saved_close = prot->close; + psock->saved_write_space = sk->sk_write_space; INIT_LIST_HEAD(&psock->link); spin_lock_init(&psock->link_lock); @@ -516,6 +536,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) rcu_assign_sk_user_data_nocopy(sk, psock); sock_hold(sk); +out: + write_unlock_bh(&sk->sk_callback_lock); return psock; } EXPORT_SYMBOL_GPL(sk_psock_init); @@ -772,7 +794,6 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, sk_psock_skb_redirect(skb); break; case __SK_DROP: - /* fall-through */ default: out_free: kfree_skb(skb); diff --git a/net/core/sock.c b/net/core/sock.c index e4f40b175acb..ba9e7d91e2ef 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -413,18 +413,6 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return 0; } -static void sock_warn_obsolete_bsdism(const char *name) -{ - static int warned; - static char warncomm[TASK_COMM_LEN]; - if (strcmp(warncomm, current->comm) && warned < 5) { - strcpy(warncomm, current->comm); - pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n", - warncomm, name); - warned++; - } -} - static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { @@ -984,7 +972,6 @@ set_sndbuf: break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("setsockopt"); break; case SO_PASSCRED: @@ -1008,7 +995,7 @@ set_sndbuf: break; case SO_TIMESTAMPING_NEW: sock_set_flag(sk, SOCK_TSTAMP_NEW); - /* fall through */ + fallthrough; case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; @@ -1387,7 +1374,6 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("getsockopt"); break; case SO_TIMESTAMP_OLD: @@ -3254,7 +3240,7 @@ void sk_common_release(struct sock *sk) sk->sk_prot->destroy(sk); /* - * Observation: when sock_common_release is called, processes have + * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 119f52a99dc1..078386d7d9a2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -184,8 +184,6 @@ static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock) { struct proto *prot; - sock_owned_by_me(sk); - switch (sk->sk_type) { case SOCK_STREAM: prot = tcp_bpf_get_proto(sk, psock); @@ -272,8 +270,8 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, } } else { psock = sk_psock_init(sk, map->numa_node); - if (!psock) { - ret = -ENOMEM; + if (IS_ERR(psock)) { + ret = PTR_ERR(psock); goto out_progs; } } @@ -322,8 +320,8 @@ static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk) if (!psock) { psock = sk_psock_init(sk, map->numa_node); - if (!psock) - return -ENOMEM; + if (IS_ERR(psock)) + return PTR_ERR(psock); } ret = sock_map_init_proto(sk, psock); @@ -478,8 +476,6 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; - if (inet_csk_has_ulp(sk)) - return -EINVAL; link = sk_psock_init_link(); if (!link) @@ -563,10 +559,12 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) return false; } -static int sock_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static int sock_hash_update_common(struct bpf_map *map, void *key, + struct sock *sk, u64 flags); + +int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, + u64 flags) { - u32 idx = *(u32 *)key; struct socket *sock; struct sock *sk; int ret; @@ -595,14 +593,38 @@ static int sock_map_update_elem(struct bpf_map *map, void *key, sock_map_sk_acquire(sk); if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; + else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) + ret = sock_map_update_common(map, *(u32 *)key, sk, flags); else - ret = sock_map_update_common(map, idx, sk, flags); + ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: fput(sock->file); return ret; } +static int sock_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + struct sock *sk = (struct sock *)value; + int ret; + + if (!sock_map_sk_is_suitable(sk)) + return -EOPNOTSUPP; + + local_bh_disable(); + bh_lock_sock(sk); + if (!sock_map_sk_state_allowed(sk)) + ret = -EOPNOTSUPP; + else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) + ret = sock_map_update_common(map, *(u32 *)key, sk, flags); + else + ret = sock_hash_update_common(map, key, sk, flags); + bh_unlock_sock(sk); + local_bh_enable(); + return ret; +} + BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops, struct bpf_map *, map, void *, key, u64, flags) { @@ -683,6 +705,7 @@ const struct bpf_func_proto bpf_msg_redirect_map_proto = { static int sock_map_btf_id; const struct bpf_map_ops sock_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_map_alloc, .map_free = sock_map_free, .map_get_next_key = sock_map_get_next_key, @@ -855,8 +878,6 @@ static int sock_hash_update_common(struct bpf_map *map, void *key, WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL; - if (inet_csk_has_ulp(sk)) - return -EINVAL; link = sk_psock_init_link(); if (!link) @@ -915,45 +936,6 @@ out_free: return ret; } -static int sock_hash_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) -{ - struct socket *sock; - struct sock *sk; - int ret; - u64 ufd; - - if (map->value_size == sizeof(u64)) - ufd = *(u64 *)value; - else - ufd = *(u32 *)value; - if (ufd > S32_MAX) - return -EINVAL; - - sock = sockfd_lookup(ufd, &ret); - if (!sock) - return ret; - sk = sock->sk; - if (!sk) { - ret = -EINVAL; - goto out; - } - if (!sock_map_sk_is_suitable(sk)) { - ret = -EOPNOTSUPP; - goto out; - } - - sock_map_sk_acquire(sk); - if (!sock_map_sk_state_allowed(sk)) - ret = -EOPNOTSUPP; - else - ret = sock_hash_update_common(map, key, sk, flags); - sock_map_sk_release(sk); -out: - fput(sock->file); - return ret; -} - static int sock_hash_get_next_key(struct bpf_map *map, void *key, void *key_next) { @@ -1219,10 +1201,11 @@ const struct bpf_func_proto bpf_msg_redirect_hash_proto = { static int sock_hash_map_btf_id; const struct bpf_map_ops sock_hash_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_hash_alloc, .map_free = sock_hash_free, .map_get_next_key = sock_hash_get_next_key, - .map_update_elem = sock_hash_update_elem, + .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_hash_delete_elem, .map_lookup_elem = sock_hash_lookup, .map_lookup_elem_sys_only = sock_hash_lookup_sys, diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 6ada114bbcca..d86d8d11cfe4 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -22,7 +22,7 @@ #include <net/busy_poll.h> #include <net/pkt_sched.h> -static int two __maybe_unused = 2; +static int two = 2; static int three = 3; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; @@ -546,7 +546,7 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, { .procname = "devconf_inherit_init_net", @@ -587,6 +587,19 @@ static struct ctl_table netns_core_table[] = { { } }; +static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str) +{ + /* fallback tunnels for initns only */ + if (!strncmp(str, "initns", 6)) + sysctl_fb_tunnels_only_for_init_net = 1; + /* no fallback tunnels anywhere */ + else if (!strncmp(str, "none", 4)) + sysctl_fb_tunnels_only_for_init_net = 2; + + return 1; +} +__setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup); + static __net_init int sysctl_core_net_init(struct net *net) { struct ctl_table *tbl; diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 0a72510d5de1..8f3dd3b1d2d0 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -274,7 +274,7 @@ void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb) /** * dccp_ackvec_clear_state - Perform house-keeping / garbage-collection * This routine is called when the peer acknowledges the receipt of Ack Vectors - * up to and including @ackno. While based on on section A.3 of RFC 4340, here + * up to and including @ackno. While based on section A.3 of RFC 4340, here * are additional precautions to prevent corrupted buffer state. In particular, * we use tail_ackno to identify outdated records; it always marks the earliest * packet of group (2) in 11.4.2. diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index aef72f6a2829..b9ee1a4a8955 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -608,7 +608,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, */ if (hc->rx_x_recv > 0) break; - /* fall through */ + fallthrough; case CCID3_FBACK_PERIODIC: delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback); if (delta <= 0) diff --git a/net/dccp/feat.c b/net/dccp/feat.c index afc071ea1271..788dd629c420 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -1407,7 +1407,8 @@ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * Negotiation during connection setup */ case DCCP_LISTEN: - server = true; /* fall through */ + server = true; + fallthrough; case DCCP_REQUESTING: switch (opt) { case DCCPO_CHANGE_L: diff --git a/net/dccp/input.c b/net/dccp/input.c index bd9cfdb67436..2cbb757a894f 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -64,7 +64,7 @@ static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb) */ if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT) break; - /* fall through */ + fallthrough; case DCCP_REQUESTING: case DCCP_ACTIVE_CLOSEREQ: dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED); @@ -76,7 +76,7 @@ static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb) queued = 1; dccp_fin(sk, skb); dccp_set_state(sk, DCCP_PASSIVE_CLOSE); - /* fall through */ + fallthrough; case DCCP_PASSIVE_CLOSE: /* * Retransmitted Close: we have already enqueued the first one. @@ -113,7 +113,7 @@ static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) queued = 1; dccp_fin(sk, skb); dccp_set_state(sk, DCCP_PASSIVE_CLOSEREQ); - /* fall through */ + fallthrough; case DCCP_PASSIVE_CLOSEREQ: sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); } @@ -530,7 +530,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, case DCCP_PKT_DATA: if (sk->sk_state == DCCP_RESPOND) break; - /* fall through */ + fallthrough; case DCCP_PKT_DATAACK: case DCCP_PKT_ACK: /* @@ -684,7 +684,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* Step 8: if using Ack Vectors, mark packet acknowledgeable */ dccp_handle_ackvec_processing(sk, skb); dccp_deliver_input_to_ccids(sk, skb); - /* fall through */ + fallthrough; case DCCP_RESPOND: queued = dccp_rcv_respond_partopen_state_process(sk, skb, dh, len); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 9c28c8251125..bb3d70664dde 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -495,7 +495,8 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - rcu_dereference(ireq->ireq_opt)); + rcu_dereference(ireq->ireq_opt), + inet_sk(sk)->tos); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -537,7 +538,8 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) local_bh_disable(); bh_lock_sock(ctl_sk); err = ip_build_and_send_pkt(skb, ctl_sk, - rxiph->daddr, rxiph->saddr, NULL); + rxiph->daddr, rxiph->saddr, NULL, + inet_sk(ctl_sk)->tos); bh_unlock_sock(ctl_sk); if (net_xmit_eval(err) == 0) { @@ -731,7 +733,7 @@ int dccp_invalid_packet(struct sk_buff *skb) return 1; } /* - * If P.Data Offset is too too large for packet, drop packet and return + * If P.Data Offset is too large for packet, drop packet and return */ if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) { DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff); diff --git a/net/dccp/options.c b/net/dccp/options.c index 51aaba7a5d45..d24cad05001e 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -225,7 +225,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * interested. The RX CCID need not parse Ack Vectors, * since it is only interested in clearing old state. */ - /* fall through */ + fallthrough; case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, pkt_type, opt, value, len)) diff --git a/net/dccp/output.c b/net/dccp/output.c index 6433187a5cc4..50e6d5699bb2 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -62,7 +62,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) switch (dcb->dccpd_type) { case DCCP_PKT_DATA: set_ack = 0; - /* fall through */ + fallthrough; case DCCP_PKT_DATAACK: case DCCP_PKT_RESET: break; @@ -72,12 +72,12 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) /* Use ISS on the first (non-retransmitted) Request. */ if (icsk->icsk_retransmits == 0) dcb->dccpd_seq = dp->dccps_iss; - /* fall through */ + fallthrough; case DCCP_PKT_SYNC: case DCCP_PKT_SYNCACK: ackno = dcb->dccpd_ack_seq; - /* fall through */ + fallthrough; default: /* * Set owner/destructor: some skbs are allocated via @@ -481,7 +481,7 @@ struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *rcv_skb) case DCCP_RESET_CODE_PACKET_ERROR: dhr->dccph_reset_data[0] = rxdh->dccph_type; break; - case DCCP_RESET_CODE_OPTION_ERROR: /* fall through */ + case DCCP_RESET_CODE_OPTION_ERROR: case DCCP_RESET_CODE_MANDATORY_ERROR: memcpy(dhr->dccph_reset_data, dcb->dccpd_reset_data, 3); break; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index d148ab1530e5..6d705d90c614 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -101,7 +101,7 @@ void dccp_set_state(struct sock *sk, const int state) if (inet_csk(sk)->icsk_bind_hash != NULL && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); - /* fall through */ + fallthrough; default: if (oldstate == DCCP_OPEN) DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); @@ -834,7 +834,7 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, case DCCP_PKT_CLOSEREQ: if (!(flags & MSG_PEEK)) dccp_finish_passive_close(sk); - /* fall through */ + fallthrough; case DCCP_PKT_RESET: dccp_pr_debug("found fin (%s) ok!\n", dccp_packet_name(dh->dccph_type)); @@ -960,7 +960,7 @@ static void dccp_terminate_connection(struct sock *sk) case DCCP_PARTOPEN: dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); - /* fall through */ + fallthrough; case DCCP_OPEN: dccp_send_close(sk, 1); @@ -969,7 +969,7 @@ static void dccp_terminate_connection(struct sock *sk) next_state = DCCP_ACTIVE_CLOSEREQ; else next_state = DCCP_CLOSING; - /* fall through */ + fallthrough; default: dccp_set_state(sk, next_state); } diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 0e06dfc32273..927c796d7682 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -85,7 +85,7 @@ static void dccp_retransmit_timer(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); /* - * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was + * More than 4MSL (8 minutes) has passed, a RESET(aborted) was * sent, no need to retransmit, this sock is dead. */ if (dccp_write_timeout(sk)) diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 3b53d766789d..5dbd45dc35ad 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -623,12 +623,12 @@ static void dn_destroy_sock(struct sock *sk) goto disc_reject; case DN_RUN: scp->state = DN_DI; - /* fall through */ + fallthrough; case DN_DI: case DN_DR: disc_reject: dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation); - /* fall through */ + fallthrough; case DN_NC: case DN_NR: case DN_RJ: @@ -642,7 +642,7 @@ disc_reject: break; default: printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n"); - /* fall through */ + fallthrough; case DN_O: dn_stop_slow_timer(sk); diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index c68503a18025..c97bdca5ec30 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -483,7 +483,7 @@ static void dn_nsp_disc_conf(struct sock *sk, struct sk_buff *skb) break; case DN_RUN: sk->sk_shutdown |= SHUTDOWN_MASK; - /* fall through */ + fallthrough; case DN_CC: scp->state = DN_CN; } diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 33fefb0aebca..4086f9c746af 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -156,7 +156,7 @@ static void dn_rehash_zone(struct dn_zone *dz) default: printk(KERN_DEBUG "DECnet: dn_rehash_zone: BUG! %d\n", old_divisor); - /* fall through */ + fallthrough; case 256: new_divisor = 1024; new_hashmask = 0x3FF; diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index deae519bdeec..67b5ab2657b7 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -75,7 +75,7 @@ static void strip_it(char *str) case '\r': case ':': *str = 0; - /* Fallthrough */ + fallthrough; case 0: return; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 41d60eeefdbd..4987f94a8f52 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1784,7 +1784,7 @@ int dsa_slave_create(struct dsa_port *port) rtnl_lock(); ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN); rtnl_unlock(); - if (ret) + if (ret && ret != -EOPNOTSUPP) dev_warn(ds->dev, "nonfatal error %d setting MTU on port %d\n", ret, port->index); @@ -1792,8 +1792,9 @@ int dsa_slave_create(struct dsa_port *port) ret = dsa_slave_phy_setup(slave_dev); if (ret) { - netdev_err(master, "error %d setting up slave PHY for %s\n", - ret, slave_dev->name); + netdev_err(slave_dev, + "error %d setting up PHY for tree %d, switch %d, port %d\n", + ret, ds->dst->index, ds->index, port->index); goto out_gcells; } @@ -2009,7 +2010,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, switchdev_work->event = event; switch (event) { - case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */ + case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: if (dsa_slave_switchdev_fdb_work_init(switchdev_work, ptr)) goto err_fdb_work_init; diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 9ef54cdcf662..9ecda09ecb11 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -223,7 +223,7 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); for (i = from_channel; i < old_total; i++) - if (xdp_get_umem_from_qid(dev, i)) { + if (xsk_get_pool_from_qid(dev, i)) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets"); return -EINVAL; } diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 4e632dc987d8..495635f152ba 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -224,7 +224,9 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) DECLARE_BITMAP(wanted_diff_mask, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(active_diff_mask, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(old_active, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(old_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(new_active, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(new_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT); struct nlattr *tb[ETHTOOL_A_FEATURES_MAX + 1]; @@ -250,6 +252,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); ethnl_features_to_bitmap(old_active, dev->features); + ethnl_features_to_bitmap(old_wanted, dev->wanted_features); ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT, tb[ETHTOOL_A_FEATURES_WANTED], netdev_features_strings, info->extack); @@ -261,17 +264,15 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) goto out_rtnl; } - /* set req_wanted bits not in req_mask from old_active */ + /* set req_wanted bits not in req_mask from old_wanted */ bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT); - bitmap_andnot(new_active, old_active, req_mask, NETDEV_FEATURE_COUNT); - bitmap_or(req_wanted, new_active, req_wanted, NETDEV_FEATURE_COUNT); - if (bitmap_equal(req_wanted, old_active, NETDEV_FEATURE_COUNT)) { - ret = 0; - goto out_rtnl; + bitmap_andnot(new_wanted, old_wanted, req_mask, NETDEV_FEATURE_COUNT); + bitmap_or(req_wanted, new_wanted, req_wanted, NETDEV_FEATURE_COUNT); + if (!bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) { + dev->wanted_features &= ~dev->hw_features; + dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features; + __netdev_update_features(dev); } - - dev->wanted_features = ethnl_bitmap_to_features(req_wanted); - __netdev_update_features(dev); ethnl_features_to_bitmap(new_active, dev->features); mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 441794e0034f..328d15cd4006 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1706,7 +1706,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, min(channels.rx_count, channels.tx_count); to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count); for (i = from_channel; i < to_channel; i++) - if (xdp_get_umem_from_qid(dev, i)) + if (xsk_get_pool_from_qid(dev, i)) return -EINVAL; ret = dev->ethtool_ops->set_channels(dev, &channels); @@ -1861,23 +1861,18 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) id.data ? (id.data * HZ) : MAX_SCHEDULE_TIMEOUT); } else { /* Driver expects to be called at twice the frequency in rc */ - int n = rc * 2, i, interval = HZ / n; + int n = rc * 2, interval = HZ / n; + u64 count = n * id.data, i = 0; - /* Count down seconds */ do { - /* Count down iterations per second */ - i = n; - do { - rtnl_lock(); - rc = ops->set_phys_id(dev, - (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); - rtnl_unlock(); - if (rc) - break; - schedule_timeout_interruptible(interval); - } while (!signal_pending(current) && --i != 0); - } while (!signal_pending(current) && - (id.data == 0 || --id.data != 0)); + rtnl_lock(); + rc = ops->set_phys_id(dev, + (i++ & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); + rtnl_unlock(); + if (rc) + break; + schedule_timeout_interruptible(interval); + } while (!signal_pending(current) && (!id.data || i < count)); } rtnl_lock(); @@ -3025,13 +3020,14 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) case TCP_V4_FLOW: case TCP_V6_FLOW: match->key.basic.ip_proto = IPPROTO_TCP; + match->mask.basic.ip_proto = 0xff; break; case UDP_V4_FLOW: case UDP_V6_FLOW: match->key.basic.ip_proto = IPPROTO_UDP; + match->mask.basic.ip_proto = 0xff; break; } - match->mask.basic.ip_proto = 0xff; match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] = diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index bbe9b3b2d395..be6f06adefe0 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -195,7 +195,7 @@ static int lowpan_frag_rx_handlers_result(struct sk_buff *skb, net_warn_ratelimited("%s: received unknown dispatch\n", __func__); - /* fall-through */ + fallthrough; default: /* all others failure */ return NET_RX_DROP; diff --git a/net/ieee802154/6lowpan/rx.c b/net/ieee802154/6lowpan/rx.c index b34d050c9687..517e6493f5d1 100644 --- a/net/ieee802154/6lowpan/rx.c +++ b/net/ieee802154/6lowpan/rx.c @@ -35,11 +35,11 @@ static int lowpan_rx_handlers_result(struct sk_buff *skb, lowpan_rx_result res) net_warn_ratelimited("%s: received unknown dispatch\n", __func__); - /* fall-through */ + fallthrough; case RX_DROP_UNUSABLE: kfree_skb(skb); - /* fall-through */ + fallthrough; case RX_DROP: return NET_RX_DROP; case RX_QUEUED: diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 60db5a6487cc..87983e70f03f 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -661,13 +661,13 @@ config TCP_CONG_BBR BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to maximize network utilization and minimize queues. It builds an explicit - model of the the bottleneck delivery rate and path round-trip - propagation delay. It tolerates packet loss and delay unrelated to - congestion. It can operate over LAN, WAN, cellular, wifi, or cable - modem links. It can coexist with flows that use loss-based congestion - control, and can operate with shallow buffers, deep buffers, - bufferbloat, policers, or AQM schemes that do not provide a delay - signal. It requires the fq ("Fair Queue") pacing packet scheduler. + model of the bottleneck delivery rate and path round-trip propagation + delay. It tolerates packet loss and delay unrelated to congestion. It + can operate over LAN, WAN, cellular, wifi, or cable modem links. It can + coexist with flows that use loss-based congestion control, and can + operate with shallow buffers, deep buffers, bufferbloat, policers, or + AQM schemes that do not provide a delay signal. It requires the fq + ("Fair Queue") pacing packet scheduler. choice prompt "Default TCP congestion control" diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4307503a6f0b..b7260c8cef2e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1017,6 +1017,7 @@ static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon const struct proto_ops inet_stream_ops = { .family = PF_INET, + .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 2eb71579f4d2..471d33a0d095 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -498,7 +498,7 @@ static void cipso_v4_doi_free_rcu(struct rcu_head *entry) /** * cipso_v4_doi_remove - Remove an existing DOI from the CIPSO protocol engine * @doi: the DOI value - * @audit_secid: the LSM secid to use in the audit message + * @audit_info: NetLabel audit information * * Description: * Removes a DOI definition from the CIPSO engine. The NetLabel routines will diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index c89b46fec153..ffc5332f1390 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2121,7 +2121,8 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, head, tb_hlist) + hlist_for_each_entry_rcu(tb, head, tb_hlist, + lockdep_rtnl_is_held()) __fib_info_notify_update(net, tb, info); } } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index abd083415f89..5308cfa3de62 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -237,7 +237,7 @@ static struct sk_buff *fou_gro_receive(struct sock *sk, /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel - * header to the outer L3 tunnel header, or we are are simply + * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ @@ -429,7 +429,7 @@ next_proto: /* We can clear the encap_mark for GUE as we are essentially doing * one of two possible things. We are either adding an L4 tunnel - * header to the outer L3 tunnel header, or we are are simply + * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index cf36f955bfe6..8f2e974a1e4d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -690,9 +690,9 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_unlock(); } - tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) | + tos = icmp_pointers[type].error ? (RT_TOS(iph->tos) | IPTOS_PREC_INTERNETCONTROL) : - iph->tos; + iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt)) @@ -784,7 +784,7 @@ EXPORT_SYMBOL(icmp_ndo_send); static void icmp_socket_deliver(struct sk_buff *skb, u32 info) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; const struct net_protocol *ipprot; int protocol = iph->protocol; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 4a98dd736270..93816d47e55a 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -125,6 +125,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, bool net_admin) { const struct inet_sock *inet = inet_sk(sk); + struct inet_diag_sockopt inet_sockopt; if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown)) goto errout; @@ -180,6 +181,22 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); + memset(&inet_sockopt, 0, sizeof(inet_sockopt)); + inet_sockopt.recverr = inet->recverr; + inet_sockopt.is_icsk = inet->is_icsk; + inet_sockopt.freebind = inet->freebind; + inet_sockopt.hdrincl = inet->hdrincl; + inet_sockopt.mc_loop = inet->mc_loop; + inet_sockopt.transparent = inet->transparent; + inet_sockopt.mc_all = inet->mc_all; + inet_sockopt.nodefrag = inet->nodefrag; + inet_sockopt.bind_address_no_port = inet->bind_address_no_port; + inet_sockopt.recverr_rfc4884 = inet->recverr_rfc4884; + inet_sockopt.defer_connect = inet->defer_connect; + if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt), + &inet_sockopt)) + goto errout; + return 0; errout: return 1; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 239e54474b65..8cbe74313f38 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -228,7 +228,7 @@ static void inet_unhash2(struct inet_hashinfo *h, struct sock *sk) static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const __be32 daddr, - const int dif, const int sdif, bool exact_dif) + const int dif, const int sdif) { int score = -1; @@ -277,15 +277,13 @@ static struct sock *inet_lhash2_lookup(struct net *net, const __be32 daddr, const unsigned short hnum, const int dif, const int sdif) { - bool exact_dif = inet_exact_dif_match(net, skb); struct inet_connection_sock *icsk; struct sock *sk, *result = NULL; int score, hiscore = 0; inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) { sk = (struct sock *)icsk; - score = compute_score(sk, net, hnum, daddr, - dif, sdif, exact_dif); + score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 948747aac4e2..da1b5038bdfd 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -47,32 +47,32 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, unsigned char *iph = skb_network_header(skb); memcpy(&(IPCB(skb)->opt), opt, sizeof(struct ip_options)); - memcpy(iph+sizeof(struct iphdr), opt->__data, opt->optlen); + memcpy(iph + sizeof(struct iphdr), opt->__data, opt->optlen); opt = &(IPCB(skb)->opt); if (opt->srr) - memcpy(iph+opt->srr+iph[opt->srr+1]-4, &daddr, 4); + memcpy(iph + opt->srr + iph[opt->srr + 1] - 4, &daddr, 4); if (!is_frag) { if (opt->rr_needaddr) - ip_rt_get_source(iph+opt->rr+iph[opt->rr+2]-5, skb, rt); + ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt); if (opt->ts_needaddr) - ip_rt_get_source(iph+opt->ts+iph[opt->ts+2]-9, skb, rt); + ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt); if (opt->ts_needtime) { __be32 midtime; midtime = inet_current_timestamp(); - memcpy(iph+opt->ts+iph[opt->ts+2]-5, &midtime, 4); + memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4); } return; } if (opt->rr) { - memset(iph+opt->rr, IPOPT_NOP, iph[opt->rr+1]); + memset(iph + opt->rr, IPOPT_NOP, iph[opt->rr + 1]); opt->rr = 0; opt->rr_needaddr = 0; } if (opt->ts) { - memset(iph+opt->ts, IPOPT_NOP, iph[opt->ts+1]); + memset(iph + opt->ts, IPOPT_NOP, iph[opt->ts + 1]); opt->ts = 0; opt->ts_needaddr = opt->ts_needtime = 0; } @@ -495,26 +495,29 @@ EXPORT_SYMBOL(ip_options_compile); void ip_options_undo(struct ip_options *opt) { if (opt->srr) { - unsigned char *optptr = opt->__data+opt->srr-sizeof(struct iphdr); - memmove(optptr+7, optptr+3, optptr[1]-7); - memcpy(optptr+3, &opt->faddr, 4); + unsigned char *optptr = opt->__data + opt->srr - sizeof(struct iphdr); + + memmove(optptr + 7, optptr + 3, optptr[1] - 7); + memcpy(optptr + 3, &opt->faddr, 4); } if (opt->rr_needaddr) { - unsigned char *optptr = opt->__data+opt->rr-sizeof(struct iphdr); + unsigned char *optptr = opt->__data + opt->rr - sizeof(struct iphdr); + optptr[2] -= 4; - memset(&optptr[optptr[2]-1], 0, 4); + memset(&optptr[optptr[2] - 1], 0, 4); } if (opt->ts) { - unsigned char *optptr = opt->__data+opt->ts-sizeof(struct iphdr); + unsigned char *optptr = opt->__data + opt->ts - sizeof(struct iphdr); + if (opt->ts_needtime) { optptr[2] -= 4; - memset(&optptr[optptr[2]-1], 0, 4); - if ((optptr[3]&0xF) == IPOPT_TS_PRESPEC) + memset(&optptr[optptr[2] - 1], 0, 4); + if ((optptr[3] & 0xF) == IPOPT_TS_PRESPEC) optptr[2] -= 4; } if (opt->ts_needaddr) { optptr[2] -= 4; - memset(&optptr[optptr[2]-1], 0, 4); + memset(&optptr[optptr[2] - 1], 0, 4); } } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 61f802d5350c..5fb536ff51f0 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -142,7 +142,8 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) * */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, - __be32 saddr, __be32 daddr, struct ip_options_rcu *opt) + __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, + u8 tos) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); @@ -155,7 +156,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; - iph->tos = inet->tos; + iph->tos = tos; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; @@ -996,7 +997,7 @@ static int __ip_append_data(struct sock *sk, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; + maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1351,7 +1352,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (cork->flags & IPCORK_OPT) opt = cork->opt; - if (!(rt->dst.dev->features&NETIF_F_SG)) + if (!(rt->dst.dev->features & NETIF_F_SG)) return -EOPNOTSUPP; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1536,7 +1537,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, ip_select_ident(net, skb, sk); if (opt) { - iph->ihl += opt->optlen>>2; + iph->ihl += opt->optlen >> 2; ip_options_build(skb, opt, cork->addr, rt, 0); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index d2c223554ff7..ec6036713e2c 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1124,8 +1124,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, dev_put(dev); err = -EINVAL; - if (sk->sk_bound_dev_if && - (!midx || midx != sk->sk_bound_dev_if)) + if (sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if) break; inet->uc_index = ifindex; @@ -1189,7 +1188,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, err = -EINVAL; if (sk->sk_bound_dev_if && mreq.imr_ifindex != sk->sk_bound_dev_if && - (!midx || midx != sk->sk_bound_dev_if)) + midx != sk->sk_bound_dev_if) break; inet->mc_index = mreq.imr_ifindex; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 876fd6ff1ff9..939792a38814 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1038,10 +1038,13 @@ static int ipmr_cache_report(struct mr_table *mrt, memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr)); msg->im_msgtype = assert; msg->im_mbz = 0; - if (assert == IGMPMSG_WRVIFWHOLE) + if (assert == IGMPMSG_WRVIFWHOLE) { msg->im_vif = vifi; - else + msg->im_vif_hi = vifi >> 8; + } else { msg->im_vif = mrt->mroute_reg_vif_num; + msg->im_vif_hi = mrt->mroute_reg_vif_num >> 8; + } ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); @@ -1054,6 +1057,7 @@ static int ipmr_cache_report(struct mr_table *mrt, ip_hdr(skb)->protocol = 0; msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; + msg->im_vif_hi = vifi >> 8; skb_dst_set(skb, dst_clone(skb_dst(pkt))); /* Add our header */ igmp = skb_put(skb, sizeof(struct igmphdr)); @@ -2396,6 +2400,7 @@ static size_t igmpmsg_netlink_msgsize(size_t payloadlen) + nla_total_size(4) /* IPMRA_CREPORT_VIF_ID */ + nla_total_size(4) /* IPMRA_CREPORT_SRC_ADDR */ + nla_total_size(4) /* IPMRA_CREPORT_DST_ADDR */ + + nla_total_size(4) /* IPMRA_CREPORT_TABLE */ /* IPMRA_CREPORT_PKT */ + nla_total_size(payloadlen) ; @@ -2427,11 +2432,12 @@ static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt) rtgenm = nlmsg_data(nlh); rtgenm->rtgen_family = RTNL_FAMILY_IPMR; if (nla_put_u8(skb, IPMRA_CREPORT_MSGTYPE, msg->im_msgtype) || - nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif) || + nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif | (msg->im_vif_hi << 8)) || nla_put_in_addr(skb, IPMRA_CREPORT_SRC_ADDR, msg->im_src.s_addr) || nla_put_in_addr(skb, IPMRA_CREPORT_DST_ADDR, - msg->im_dst.s_addr)) + msg->im_dst.s_addr) || + nla_put_u32(skb, IPMRA_CREPORT_TABLE, mrt->id)) goto nla_put_failure; nla = nla_reserve(skb, IPMRA_CREPORT_PKT, payloadlen); diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 7afde8828b4c..3f248a19faa3 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -3,7 +3,7 @@ * nf_nat_pptp.c * * NAT support for PPTP (Point to Point Tunneling Protocol). - * PPTP is a a protocol for creating virtual private networks. + * PPTP is a protocol for creating virtual private networks. * It is a specification defined by Microsoft and some vendors * working with Microsoft. PPTP is built on top of a modified * version of the Internet Generic Routing Encapsulation Protocol. diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index cc8049b100b2..bf9d4cd2d6e5 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -133,12 +133,9 @@ static struct nexthop *nexthop_alloc(void) static struct nh_group *nexthop_grp_alloc(u16 num_nh) { - size_t sz = offsetof(struct nexthop, nh_grp) - + sizeof(struct nh_group) - + sizeof(struct nh_grp_entry) * num_nh; struct nh_group *nhg; - nhg = kzalloc(sz, GFP_KERNEL); + nhg = kzalloc(struct_size(nhg, nh_entries, num_nh), GFP_KERNEL); if (nhg) nhg->num_nh = num_nh; @@ -279,7 +276,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, case AF_INET: fib_nh = &nhi->fib_nh; if (fib_nh->fib_nh_gw_family && - nla_put_u32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) + nla_put_be32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) goto nla_put_failure; break; @@ -446,7 +443,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], unsigned int i, j; u8 nhg_fdb = 0; - if (len & (sizeof(struct nexthop_grp) - 1)) { + if (!len || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, "Invalid length for nexthop group attribute"); return -EINVAL; @@ -800,7 +797,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, return; } - newg->has_v4 = nhg->has_v4; + newg->has_v4 = false; newg->mpath = nhg->mpath; newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; @@ -809,12 +806,18 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, nhges = nhg->nh_entries; new_nhges = newg->nh_entries; for (i = 0, j = 0; i < nhg->num_nh; ++i) { + struct nh_info *nhi; + /* current nexthop getting removed */ if (nhg->nh_entries[i].nh == nh) { newg->num_nh--; continue; } + nhi = rtnl_dereference(nhges[i].nh->nh_info); + if (nhi->family == AF_INET) + newg->has_v4 = true; + list_del(&nhges[i].nh_list); new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; @@ -961,6 +964,23 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old, return 0; } +static void nh_group_v4_update(struct nh_group *nhg) +{ + struct nh_grp_entry *nhges; + bool has_v4 = false; + int i; + + nhges = nhg->nh_entries; + for (i = 0; i < nhg->num_nh; i++) { + struct nh_info *nhi; + + nhi = rtnl_dereference(nhges[i].nh->nh_info); + if (nhi->family == AF_INET) + has_v4 = true; + } + nhg->has_v4 = has_v4; +} + static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) @@ -984,6 +1004,21 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, rcu_assign_pointer(old->nh_info, newi); rcu_assign_pointer(new->nh_info, oldi); + /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially + * update IPv4 indication in all the groups using the nexthop. + */ + if (oldi->family == AF_INET && newi->family == AF_INET6) { + struct nh_grp_entry *nhge; + + list_for_each_entry(nhge, &old->grp_list, nh_list) { + struct nexthop *nhp = nhge->nh_parent; + struct nh_group *nhg; + + nhg = rtnl_dereference(nhp->nh_grp); + nh_group_v4_update(nhg); + } + } + return 0; } @@ -1101,7 +1136,7 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh, while (1) { struct nexthop *nh; - next = rtnl_dereference(*pp); + next = *pp; if (!next) break; @@ -1187,6 +1222,9 @@ static struct nexthop *nexthop_create_group(struct net *net, struct nexthop *nh; int i; + if (WARN_ON(!num_nh)) + return ERR_PTR(-EINVAL); + nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index df6fbefe44d4..248856b301c4 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -293,7 +293,8 @@ EXPORT_SYMBOL_GPL(ping_close); /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, - struct sockaddr *uaddr, int addr_len) { + struct sockaddr *uaddr, int addr_len) +{ struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; @@ -310,10 +311,10 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); - if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) chk_addr_ret = RTN_LOCAL; + else + chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); if ((!inet_can_nonlocal_bind(net, isk) && chk_addr_ret != RTN_LOCAL) || @@ -383,20 +384,6 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) } } -static void ping_clear_saddr(struct sock *sk, int dif) -{ - sk->sk_bound_dev_if = dif; - if (sk->sk_family == AF_INET) { - struct inet_sock *isk = inet_sk(sk); - isk->inet_rcv_saddr = isk->inet_saddr = 0; -#if IS_ENABLED(CONFIG_IPV6) - } else if (sk->sk_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr)); - memset(&np->saddr, 0, sizeof(np->saddr)); -#endif - } -} /* * We need our own bind because there are no privileged id's == local ports. * Moreover, we don't allow binding to multi- and broadcast addresses. @@ -420,12 +407,13 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto out; err = -EADDRINUSE; - ping_set_saddr(sk, uaddr); snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port); if (ping_get_port(sk, snum) != 0) { - ping_clear_saddr(sk, dif); + /* Restore possibly modified sk->sk_bound_dev_if by ping_check_bind_addr(). */ + sk->sk_bound_dev_if = dif; goto out; } + ping_set_saddr(sk, uaddr); pr_debug("after bind(): num = %hu, dif = %d\n", isk->inet_num, @@ -647,7 +635,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, } int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, - void *user_icmph, size_t icmph_len) { + void *user_icmph, size_t icmph_len) +{ u8 type, code; if (len > 0xFFFF) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 6fd4330287c2..1170653a89cd 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -260,11 +260,12 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) err = EHOSTUNREACH; if (code > NR_ICMP_UNREACH) break; - err = icmp_err_convert[code].errno; - harderr = icmp_err_convert[code].fatal; if (code == ICMP_FRAG_NEEDED) { harderr = inet->pmtudisc != IP_PMTUDISC_DONT; err = EMSGSIZE; + } else { + err = icmp_err_convert[code].errno; + harderr = icmp_err_convert[code].fatal; } } @@ -610,7 +611,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } else if (!ipc.oif) { ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { - /* oif is set, packet is to local broadcast and + /* oif is set, packet is to local broadcast * and uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8ca6bcab7b03..2c05b863ae43 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -623,7 +623,7 @@ static inline u32 fnhe_hashfun(__be32 daddr) u32 hval; net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd)); - hval = jhash_1word((__force u32) daddr, fnhe_hashrnd); + hval = jhash_1word((__force u32)daddr, fnhe_hashrnd); return hash_32(hval, FNHE_HASH_SHIFT); } @@ -1013,13 +1013,14 @@ out: kfree_skb(skb); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; - u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; + u32 old_mtu; if (ip_mtu_locked(dst)) return; + old_mtu = ipv4_mtu(dst); if (old_mtu < mtu) return; @@ -1061,7 +1062,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; u32 mark = IP4_REPLY_MARK(net, skb->mark); @@ -1078,7 +1079,7 @@ EXPORT_SYMBOL_GPL(ipv4_update_pmtu); static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; @@ -1096,7 +1097,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct dst_entry *odst = NULL; @@ -1126,7 +1127,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) new = true; } - __ip_rt_update_pmtu((struct rtable *) xfrm_dst_path(&rt->dst), &fl4, mtu); + __ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) @@ -1151,7 +1152,7 @@ EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; @@ -1167,7 +1168,7 @@ EXPORT_SYMBOL_GPL(ipv4_redirect); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct net *net = sock_net(sk); @@ -1307,7 +1308,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) static unsigned int ipv4_mtu(const struct dst_entry *dst) { - const struct rtable *rt = (const struct rtable *) dst; + const struct rtable *rt = (const struct rtable *)dst; unsigned int mtu = rt->rt_pmtu; if (!mtu || time_after_eq(jiffies, rt->dst.expires)) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index f0794f0232ba..c375c126f436 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -286,11 +286,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb) { + struct tcp_request_sock *treq; struct request_sock *req; #ifdef CONFIG_MPTCP - struct tcp_request_sock *treq; - if (sk_is_mptcp(sk)) ops = &mptcp_subflow_request_sock_ops; #endif @@ -299,8 +298,9 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, if (!req) return NULL; -#if IS_ENABLED(CONFIG_MPTCP) treq = tcp_rsk(req); + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; +#if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); if (treq->is_mptcp) { int err = mptcp_subflow_init_cookie_req(req, sk, skb); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 54023a46db04..3e5f4f2e705e 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1330,6 +1330,15 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &comp_sack_nr_max, }, { + .procname = "tcp_reflect_tos", + .data = &init_net.ipv4.sysctl_tcp_reflect_tos, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { .procname = "udp_rmem_min", .data = &init_net.ipv4.sysctl_udp_rmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_rmem_min), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 31f3b858db81..57a568875539 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -418,6 +418,8 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_rto_min = TCP_RTO_MIN; + icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); @@ -2685,6 +2687,8 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_backoff = 0; icsk->icsk_probes_out = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_rto_min = TCP_RTO_MIN; + icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd = TCP_INIT_CWND; tp->snd_cwnd_cnt = 0; @@ -3207,7 +3211,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, break; case TCP_SAVE_SYN: - if (val < 0 || val > 1) + /* 0: disable, 1: enable, 2: start from ether_header */ + if (val < 0 || val > 2) err = -EINVAL; else tp->save_syn = val; @@ -3788,20 +3793,21 @@ static int do_tcp_getsockopt(struct sock *sk, int level, lock_sock(sk); if (tp->saved_syn) { - if (len < tp->saved_syn[0]) { - if (put_user(tp->saved_syn[0], optlen)) { + if (len < tcp_saved_syn_len(tp->saved_syn)) { + if (put_user(tcp_saved_syn_len(tp->saved_syn), + optlen)) { release_sock(sk); return -EFAULT; } release_sock(sk); return -EINVAL; } - len = tp->saved_syn[0]; + len = tcp_saved_syn_len(tp->saved_syn); if (put_user(len, optlen)) { release_sock(sk); return -EFAULT; } - if (copy_to_user(optval, tp->saved_syn + 1, len)) { + if (copy_to_user(optval, tp->saved_syn->data, len)) { release_sock(sk); return -EFAULT; } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 7aa68f4aae6c..37f4cb2bba5c 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -567,10 +567,9 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], prot[TCP_BPF_TX].sendpage = tcp_bpf_sendpage; } -static void tcp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops) +static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops) { - if (sk->sk_family == AF_INET6 && - unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) { + if (unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) { spin_lock_bh(&tcpv6_prot_lock); if (likely(ops != tcpv6_prot_saved)) { tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV6], ops); @@ -603,13 +602,11 @@ struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock) int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE; - if (!psock->sk_proto) { - struct proto *ops = READ_ONCE(sk->sk_prot); - - if (tcp_bpf_assert_proto_ops(ops)) + if (sk->sk_family == AF_INET6) { + if (tcp_bpf_assert_proto_ops(psock->sk_proto)) return ERR_PTR(-EINVAL); - tcp_bpf_check_v6_needs_rebuild(sk, ops); + tcp_bpf_check_v6_needs_rebuild(psock->sk_proto); } return &tcp_bpf_prots[family][config]; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 09b62de04eea..af2814c9342a 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -295,7 +295,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ - tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); + tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 184ea556f50e..3658ad84f0c6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -138,6 +138,69 @@ void clean_acked_data_flush(void) EXPORT_SYMBOL_GPL(clean_acked_data_flush); #endif +#ifdef CONFIG_CGROUP_BPF +static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb) +{ + bool unknown_opt = tcp_sk(sk)->rx_opt.saw_unknown && + BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG); + bool parse_all_opt = BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG); + struct bpf_sock_ops_kern sock_ops; + + if (likely(!unknown_opt && !parse_all_opt)) + return; + + /* The skb will be handled in the + * bpf_skops_established() or + * bpf_skops_write_hdr_opt(). + */ + switch (sk->sk_state) { + case TCP_SYN_RECV: + case TCP_SYN_SENT: + case TCP_LISTEN: + return; + } + + sock_owned_by_me(sk); + + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + sock_ops.op = BPF_SOCK_OPS_PARSE_HDR_OPT_CB; + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb)); + + BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); +} + +static void bpf_skops_established(struct sock *sk, int bpf_op, + struct sk_buff *skb) +{ + struct bpf_sock_ops_kern sock_ops; + + sock_owned_by_me(sk); + + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + sock_ops.op = bpf_op; + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ + if (skb) + bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb)); + + BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); +} +#else +static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb) +{ +} + +static void bpf_skops_established(struct sock *sk, int bpf_op, + struct sk_buff *skb) +{ +} +#endif + static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, unsigned int len) { @@ -3801,7 +3864,7 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, foc->exp = exp_opt; } -static void smc_parse_options(const struct tcphdr *th, +static bool smc_parse_options(const struct tcphdr *th, struct tcp_options_received *opt_rx, const unsigned char *ptr, int opsize) @@ -3810,10 +3873,13 @@ static void smc_parse_options(const struct tcphdr *th, if (static_branch_unlikely(&tcp_have_smc)) { if (th->syn && !(opsize & 1) && opsize >= TCPOLEN_EXP_SMC_BASE && - get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC) + get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC) { opt_rx->smc_ok = 1; + return true; + } } #endif + return false; } /* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped @@ -3874,6 +3940,7 @@ void tcp_parse_options(const struct net *net, ptr = (const unsigned char *)(th + 1); opt_rx->saw_tstamp = 0; + opt_rx->saw_unknown = 0; while (length > 0) { int opcode = *ptr++; @@ -3964,15 +4031,21 @@ void tcp_parse_options(const struct net *net, */ if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE && get_unaligned_be16(ptr) == - TCPOPT_FASTOPEN_MAGIC) + TCPOPT_FASTOPEN_MAGIC) { tcp_parse_fastopen_option(opsize - TCPOLEN_EXP_FASTOPEN_BASE, ptr + 2, th->syn, foc, true); - else - smc_parse_options(th, opt_rx, ptr, - opsize); + break; + } + + if (smc_parse_options(th, opt_rx, ptr, opsize)) + break; + + opt_rx->saw_unknown = 1; break; + default: + opt_rx->saw_unknown = 1; } ptr += opsize-2; length -= opsize; @@ -5590,6 +5663,8 @@ syn_challenge: goto discard; } + bpf_skops_parse_hdr(sk, skb); + return true; discard: @@ -5798,7 +5873,7 @@ discard: } EXPORT_SYMBOL(tcp_rcv_established); -void tcp_init_transfer(struct sock *sk, int bpf_op) +void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -5819,7 +5894,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op) tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); tp->snd_cwnd_stamp = tcp_jiffies32; - tcp_call_bpf(sk, bpf_op, 0, NULL); + bpf_skops_established(sk, bpf_op, skb); tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); } @@ -5838,7 +5913,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id(sk, skb); } - tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); + tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, skb); /* Prevent spurious tcp_cwnd_restart() on first data * packet. @@ -6310,7 +6385,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } else { tcp_try_undo_spurious_syn(sk); tp->retrans_stamp = 0; - tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); + tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, + skb); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } smp_mb(); @@ -6599,13 +6675,27 @@ static void tcp_reqsk_record_syn(const struct sock *sk, { if (tcp_sk(sk)->save_syn) { u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb); - u32 *copy; + struct saved_syn *saved_syn; + u32 mac_hdrlen; + void *base; + + if (tcp_sk(sk)->save_syn == 2) { /* Save full header. */ + base = skb_mac_header(skb); + mac_hdrlen = skb_mac_header_len(skb); + len += mac_hdrlen; + } else { + base = skb_network_header(skb); + mac_hdrlen = 0; + } - copy = kmalloc(len + sizeof(u32), GFP_ATOMIC); - if (copy) { - copy[0] = len; - memcpy(©[1], skb_network_header(skb), len); - req->saved_syn = copy; + saved_syn = kmalloc(struct_size(saved_syn, data, len), + GFP_ATOMIC); + if (saved_syn) { + saved_syn->mac_hdrlen = mac_hdrlen; + saved_syn->network_hdrlen = skb_network_header_len(skb); + saved_syn->tcp_hdrlen = tcp_hdrlen(skb); + memcpy(saved_syn->data, base, len); + req->saved_syn = saved_syn; } } } @@ -6744,6 +6834,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->txhash = net_tx_rndhash(); + tcp_rsk(req)->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; tcp_openreq_init_rwin(req, sk, dst); sk_rx_queue_set(req_to_sk(req), skb); if (!want_cookie) { @@ -6752,7 +6843,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } if (fastopen_sk) { af_ops->send_synack(fastopen_sk, dst, &fl, req, - &foc, TCP_SYNACK_FASTOPEN); + &foc, TCP_SYNACK_FASTOPEN, skb); /* Add the child socket directly into the accept queue */ if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { reqsk_fastopen_remove(fastopen_sk, req, false); @@ -6770,7 +6861,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_timeout_init((struct sock *)req)); af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : - TCP_SYNACK_COOKIE); + TCP_SYNACK_COOKIE, + skb); if (want_cookie) { reqsk_free(req); return 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5084333b5ab6..ace48b2790ff 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -575,7 +575,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is - * is already accepted it is treated as a connected one below. + * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; @@ -965,18 +965,23 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; int err = -1; struct sk_buff *skb; + u8 tos; /* First, grab a route. */ if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req, foc, synack_type); + skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); + + tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tcp_rsk(req)->syn_tos : inet_sk(sk)->tos; if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); @@ -984,7 +989,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - rcu_dereference(ireq->ireq_opt)); + rcu_dereference(ireq->ireq_opt), + tos & ~INET_ECN_MASK); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1529,6 +1535,10 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = prandom_u32(); + /* Set ToS of the new socket based upon the value of incoming SYN. */ + if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) + newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; + if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); if (!dst) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 495dda2449fe..56c306e3cd2f 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -548,6 +548,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fastopen_req = NULL; RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); + bpf_skops_init_child(sk, newsk); tcp_bpf_clone(sk, newsk); __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 85ff417bda7f..ab79d36ed07f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -438,6 +438,7 @@ struct tcp_out_options { u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u8 hash_size; /* bytes in hash_location */ + u8 bpf_opt_len; /* length of BPF hdr option */ __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ @@ -452,6 +453,145 @@ static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts) #endif } +#ifdef CONFIG_CGROUP_BPF +static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb, + enum tcp_synack_type synack_type) +{ + if (unlikely(!skb)) + return BPF_WRITE_HDR_TCP_CURRENT_MSS; + + if (unlikely(synack_type == TCP_SYNACK_COOKIE)) + return BPF_WRITE_HDR_TCP_SYNACK_COOKIE; + + return 0; +} + +/* req, syn_skb and synack_type are used when writing synack */ +static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts, + unsigned int *remaining) +{ + struct bpf_sock_ops_kern sock_ops; + int err; + + if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) || + !*remaining) + return; + + /* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */ + + /* init sock_ops */ + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + + sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB; + + if (req) { + /* The listen "sk" cannot be passed here because + * it is not locked. It would not make too much + * sense to do bpf_setsockopt(listen_sk) based + * on individual connection request also. + * + * Thus, "req" is passed here and the cgroup-bpf-progs + * of the listen "sk" will be run. + * + * "req" is also used here for fastopen even the "sk" here is + * a fullsock "child" sk. It is to keep the behavior + * consistent between fastopen and non-fastopen on + * the bpf programming side. + */ + sock_ops.sk = (struct sock *)req; + sock_ops.syn_skb = syn_skb; + } else { + sock_owned_by_me(sk); + + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + } + + sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); + sock_ops.remaining_opt_len = *remaining; + /* tcp_current_mss() does not pass a skb */ + if (skb) + bpf_skops_init_skb(&sock_ops, skb, 0); + + err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); + + if (err || sock_ops.remaining_opt_len == *remaining) + return; + + opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len; + /* round up to 4 bytes */ + opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3; + + *remaining -= opts->bpf_opt_len; +} + +static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts) +{ + u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len; + struct bpf_sock_ops_kern sock_ops; + int err; + + if (likely(!max_opt_len)) + return; + + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + + sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB; + + if (req) { + sock_ops.sk = (struct sock *)req; + sock_ops.syn_skb = syn_skb; + } else { + sock_owned_by_me(sk); + + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + } + + sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); + sock_ops.remaining_opt_len = max_opt_len; + first_opt_off = tcp_hdrlen(skb) - max_opt_len; + bpf_skops_init_skb(&sock_ops, skb, first_opt_off); + + err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); + + if (err) + nr_written = 0; + else + nr_written = max_opt_len - sock_ops.remaining_opt_len; + + if (nr_written < max_opt_len) + memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP, + max_opt_len - nr_written); +} +#else +static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts, + unsigned int *remaining) +{ +} + +static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts) +{ +} +#endif + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -691,6 +831,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, } } + bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); + return MAX_TCP_OPTION_SPACE - remaining; } @@ -701,7 +843,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -758,6 +901,9 @@ static unsigned int tcp_synack_options(const struct sock *sk, smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); + bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, + synack_type, opts, &remaining); + return MAX_TCP_OPTION_SPACE - remaining; } @@ -826,6 +972,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } + if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp, + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) { + unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + + bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); + + size = MAX_TCP_OPTION_SPACE - remaining; + } + return size; } @@ -1213,6 +1368,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, } #endif + /* BPF prog is the last one writing header option */ + bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts); + INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check, tcp_v6_send_check, tcp_v4_send_check, sk, skb); @@ -3336,20 +3494,20 @@ int tcp_send_synack(struct sock *sk) } /** - * tcp_make_synack - Prepare a SYN-ACK. - * sk: listener socket - * dst: dst entry attached to the SYNACK - * req: request_sock pointer - * foc: cookie for tcp fast open - * synack_type: Type of synback to prepare - * - * Allocate one skb and build a SYNACK packet. - * @dst is consumed : Caller should not use it again. + * tcp_make_synack - Allocate one skb and build a SYNACK packet. + * @sk: listener socket + * @dst: dst entry attached to the SYNACK. It is consumed and caller + * should not use it again. + * @req: request_sock pointer + * @foc: cookie for tcp fast open + * @synack_type: Type of synack to prepare + * @syn_skb: SYN packet just received. It could be NULL for rtx case. */ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); @@ -3408,8 +3566,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + /* bpf program will be interested in the tcp_flags */ + TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc, synack_type) + sizeof(*th); + foc, synack_type, + syn_skb) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -3441,6 +3602,9 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_unlock(); #endif + bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, + synack_type, &opts); + skb->skb_mstamp_ns = now; tcp_add_tx_delay(skb, tp); @@ -3741,6 +3905,8 @@ void tcp_send_delayed_ack(struct sock *sk) ato = min(ato, max_ato); } + ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max); + /* Stay within the limit we were given */ timeout = jiffies + ato; @@ -3934,7 +4100,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) int res; tcp_rsk(req)->txhash = net_tx_rndhash(); - res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL); + res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, + NULL); if (!res) { __TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 6cebf412d590..5842081bc8a2 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -10,7 +10,7 @@ #include <net/tcp.h> /* These factors derived from the recommended values in the aer: - * .01 and and 7/8. + * .01 and 7/8. */ #define TCP_SCALABLE_AI_CNT 100U #define TCP_SCALABLE_MD_SCALE 3 diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e88efba07551..09f0a23d1a01 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1170,7 +1170,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { /* oif is set, packet is to local broadcast and - * and uc_index is set. oif is most likely set + * uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. * If so, we want to allow the send using the uc_index. diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index eddd973e6575..7a94791efc1a 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -22,10 +22,9 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base) prot->close = sock_map_close; } -static void udp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops) +static void udp_bpf_check_v6_needs_rebuild(struct proto *ops) { - if (sk->sk_family == AF_INET6 && - unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) { + if (unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) { spin_lock_bh(&udpv6_prot_lock); if (likely(ops != udpv6_prot_saved)) { udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops); @@ -46,8 +45,8 @@ struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock) { int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6; - if (!psock->sk_proto) - udp_bpf_check_v6_needs_rebuild(sk, READ_ONCE(sk->sk_prot)); + if (sk->sk_family == AF_INET6) + udp_bpf_check_v6_needs_rebuild(psock->sk_proto); return &udp_bpf_prots[family]; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8e761b8c47c6..01146b66d666 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1893,12 +1893,13 @@ EXPORT_SYMBOL(ipv6_chk_addr); * 2. does the address exist on the specific device * (skip_dev_check = false) */ -int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, - const struct net_device *dev, bool skip_dev_check, - int strict, u32 banned_flags) +static struct net_device * +__ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, bool skip_dev_check, + int strict, u32 banned_flags) { unsigned int hash = inet6_addr_hash(net, addr); - const struct net_device *l3mdev; + struct net_device *l3mdev, *ndev; struct inet6_ifaddr *ifp; u32 ifp_flags; @@ -1909,10 +1910,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, dev = NULL; hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) + ndev = ifp->idev->dev; + if (!net_eq(dev_net(ndev), net)) continue; - if (l3mdev_master_dev_rcu(ifp->idev->dev) != l3mdev) + if (l3mdev_master_dev_rcu(ndev) != l3mdev) continue; /* Decouple optimistic from tentative for evaluation here. @@ -1923,15 +1925,23 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, : ifp->flags; if (ipv6_addr_equal(&ifp->addr, addr) && !(ifp_flags&banned_flags) && - (!dev || ifp->idev->dev == dev || + (!dev || ndev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { rcu_read_unlock(); - return 1; + return ndev; } } rcu_read_unlock(); - return 0; + return NULL; +} + +int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, bool skip_dev_check, + int strict, u32 banned_flags) +{ + return __ipv6_chk_addr_and_flags(net, addr, dev, skip_dev_check, + strict, banned_flags) ? 1 : 0; } EXPORT_SYMBOL(ipv6_chk_addr_and_flags); @@ -1990,35 +2000,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix); * * The caller should be protected by RCU, or RTNL. */ -struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr) +struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, + struct net_device *dev) { - unsigned int hash = inet6_addr_hash(net, addr); - struct inet6_ifaddr *ifp, *result = NULL; - struct net_device *dev = NULL; - - rcu_read_lock(); - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (net_eq(dev_net(ifp->idev->dev), net) && - ipv6_addr_equal(&ifp->addr, addr)) { - result = ifp; - break; - } - } - - if (!result) { - struct rt6_info *rt; - - rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); - if (rt) { - dev = rt->dst.dev; - ip6_rt_put(rt); - } - } else { - dev = result->idev->dev; - } - rcu_read_unlock(); - - return dev; + return __ipv6_chk_addr_and_flags(net, addr, dev, !dev, 1, + IFA_F_TENTATIVE); } EXPORT_SYMBOL(ipv6_dev_find); diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 9ebf3fe0d2b1..c70c192bc91b 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -191,6 +191,13 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt, return -EAFNOSUPPORT; } +static int eafnosupport_ipv6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)) +{ + kfree_skb(skb); + return -EAFNOSUPPORT; +} + const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, @@ -201,6 +208,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6, .fib6_nh_init = eafnosupport_fib6_nh_init, .ip6_del_rt = eafnosupport_ip6_del_rt, + .ipv6_fragment = eafnosupport_ipv6_fragment, }; EXPORT_SYMBOL_GPL(ipv6_stub); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0306509ab063..e648fbebb167 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -661,6 +661,7 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, const struct proto_ops inet6_stream_ops = { .family = PF_INET6, + .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, @@ -1026,6 +1027,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .xfrm6_rcv_encap = xfrm6_rcv_encap, #endif .nd_tbl = &nd_tbl, + .ipv6_fragment = ip6_fragment, }; static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 2d3add9e6116..55c290d55605 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -94,7 +94,7 @@ EXPORT_SYMBOL(__inet6_lookup_established); static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const struct in6_addr *daddr, - const int dif, const int sdif, bool exact_dif) + const int dif, const int sdif) { int score = -1; @@ -138,15 +138,13 @@ static struct sock *inet6_lhash2_lookup(struct net *net, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif) { - bool exact_dif = inet6_exact_dif_match(net, skb); struct inet_connection_sock *icsk; struct sock *sk, *result = NULL; int score, hiscore = 0; inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) { sk = (struct sock *)icsk; - score = compute_score(sk, net, hnum, daddr, dif, sdif, - exact_dif); + score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 25a90f3f705c..44d68ed70f24 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1812,10 +1812,14 @@ static struct fib6_node *fib6_repair_tree(struct net *net, children = 0; child = NULL; - if (fn_r) - child = fn_r, children |= 1; - if (fn_l) - child = fn_l, children |= 2; + if (fn_r) { + child = fn_r; + children |= 1; + } + if (fn_l) { + child = fn_l; + children |= 2; + } if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index f635914f42ec..a0217e5bf3bc 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -915,7 +915,15 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb, struct metadata_dst *tun_dst, bool log_ecn_err) { - return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate, + int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb); + + dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate; + if (tpi->proto == htons(ETH_P_IP)) + dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate; + + return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_err); } EXPORT_SYMBOL(ip6_tnl_rcv); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 409e79b84a83..6d0e942d082d 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -245,9 +245,6 @@ static const struct nf_ipv6_ops ipv6ops = { .route_input = ip6_route_input, .fragment = ip6_fragment, .reroute = nf_ip6_reroute, -#if IS_MODULE(CONFIG_IPV6) && IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - .br_defrag = nf_ct_frag6_gather, -#endif #if IS_MODULE(CONFIG_IPV6) .br_fragment = br_ip6_fragment, #endif diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c index 9ee077bf4f49..787c74aa85e3 100644 --- a/net/ipv6/netfilter/ip6t_NPT.c +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -77,16 +77,43 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, return true; } +static struct ipv6hdr *icmpv6_bounced_ipv6hdr(struct sk_buff *skb, + struct ipv6hdr *_bounced_hdr) +{ + if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) + return NULL; + + if (!icmpv6_is_err(icmp6_hdr(skb)->icmp6_type)) + return NULL; + + return skb_header_pointer(skb, + skb_transport_offset(skb) + sizeof(struct icmp6hdr), + sizeof(struct ipv6hdr), + _bounced_hdr); +} + static unsigned int ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_npt_tginfo *npt = par->targinfo; + struct ipv6hdr _bounced_hdr; + struct ipv6hdr *bounced_hdr; + struct in6_addr bounced_pfx; if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) { icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, saddr)); return NF_DROP; } + + /* rewrite dst addr of bounced packet which was sent to dst range */ + bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr); + if (bounced_hdr) { + ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->daddr, npt->src_pfx_len); + if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0) + ip6t_npt_map_pfx(npt, &bounced_hdr->daddr); + } + return XT_CONTINUE; } @@ -94,12 +121,24 @@ static unsigned int ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_npt_tginfo *npt = par->targinfo; + struct ipv6hdr _bounced_hdr; + struct ipv6hdr *bounced_hdr; + struct in6_addr bounced_pfx; if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) { icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, daddr)); return NF_DROP; } + + /* rewrite src addr of bounced packet which was sent from dst range */ + bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr); + if (bounced_hdr) { + ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->saddr, npt->src_pfx_len); + if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0) + ip6t_npt_map_pfx(npt, &bounced_hdr->saddr); + } + return XT_CONTINUE; } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index fac2135aa47b..5b60a4bdd36a 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -21,6 +21,7 @@ #include <net/calipso.h> #endif +static int two = 2; static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_min; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; @@ -150,7 +151,7 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, { .procname = "seg6_flowlabel", diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 305870a72352..862058dce6d0 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -501,7 +501,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = tcp_inet6_sk(sk); @@ -509,13 +510,14 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; int err = -ENOMEM; + u8 tclass; /* First, grab a route. */ if (!dst && (dst = inet6_csk_route_req(sk, fl6, req, IPPROTO_TCP)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req, foc, synack_type); + skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, @@ -527,9 +529,12 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); opt = ireq->ipv6_opt; + tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tcp_rsk(req)->syn_tos : np->tclass; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass, + err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, + tclass & ~INET_ECN_MASK, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); @@ -958,8 +963,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass, - priority); + ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, + tclass & ~INET_ECN_MASK, priority); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS(net, TCP_MIB_OUTRSTS); @@ -1067,8 +1072,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) label = ip6_flowlabel(ipv6h); } - tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, - label, priority); + tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, + ipv6_get_dsfield(ipv6h), label, priority); #ifdef CONFIG_TCP_MD5SIG out: @@ -1121,7 +1126,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), - 0, 0, sk->sk_priority); + ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority); } @@ -1309,6 +1314,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * if (np->repflow) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); + /* Set ToS of the new socket based upon the value of incoming SYN. */ + if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) + newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; + /* Clone native IPv6 options from listening socket (if any) Yes, keeping reference count would be much more clever, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 6ee9851ac7c6..a95af62acb52 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -418,7 +418,7 @@ static void iucv_sock_close(struct sock *sk) sk->sk_state = IUCV_DISCONN; sk->sk_state_change(sk); } - /* fall through */ + fallthrough; case IUCV_DISCONN: sk->sk_state = IUCV_CLOSING; @@ -433,7 +433,7 @@ static void iucv_sock_close(struct sock *sk) iucv_sock_in_state(sk, IUCV_CLOSED, 0), timeo); } - /* fall through */ + fallthrough; case IUCV_CLOSING: sk->sk_state = IUCV_CLOSED; @@ -444,7 +444,7 @@ static void iucv_sock_close(struct sock *sk) skb_queue_purge(&iucv->send_skb_q); skb_queue_purge(&iucv->backlog_skb_q); - /* fall through */ + fallthrough; default: iucv_sever_path(sk, 1); @@ -2111,10 +2111,10 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, kfree_skb(skb); break; } - /* fall through - and receive non-zero length data */ + fallthrough; /* and receive non-zero length data */ case (AF_IUCV_FLAG_SHT): /* shutdown request */ - /* fall through - and receive zero length data */ + fallthrough; /* and receive zero length data */ case 0: /* plain data frame */ IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class; diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile index 399a7e5db2f4..cf8f27071d3f 100644 --- a/net/l2tp/Makefile +++ b/net/l2tp/Makefile @@ -5,6 +5,8 @@ obj-$(CONFIG_L2TP) += l2tp_core.o +CFLAGS_l2tp_core.o += -I$(src) + # Build l2tp as modules if L2TP is M obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_PPPOL2TP)) += l2tp_ppp.o obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip.o diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 701fc72ad9f4..7de05be4fc33 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -61,6 +61,10 @@ #include <linux/atomic.h> #include "l2tp_core.h" +#include "trace.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" #define L2TP_DRV_VERSION "V2.0" @@ -116,11 +120,6 @@ static bool l2tp_sk_is_v6(struct sock *sk) } #endif -static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) -{ - return sk->sk_user_data; -} - static inline struct l2tp_net *l2tp_pernet(const struct net *net) { return net_generic(net, l2tp_net_id); @@ -151,23 +150,30 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { + trace_free_tunnel(tunnel); sock_put(tunnel->sock); /* the tunnel is freed in the socket destructor */ } static void l2tp_session_free(struct l2tp_session *session) { - struct l2tp_tunnel *tunnel = session->tunnel; + trace_free_session(session); + if (session->tunnel) + l2tp_tunnel_dec_refcount(session->tunnel); + kfree(session); +} - if (tunnel) { +struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk) +{ + struct l2tp_tunnel *tunnel = sk->sk_user_data; + + if (tunnel) if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) - goto out; - l2tp_tunnel_dec_refcount(tunnel); - } + return NULL; -out: - kfree(session); + return tunnel; } +EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) { @@ -381,6 +387,8 @@ int l2tp_session_register(struct l2tp_session *session, hlist_add_head(&session->hlist, head); write_unlock_bh(&tunnel->hlist_lock); + trace_register_session(session); + return 0; err_tlock_pnlock: @@ -409,10 +417,6 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n", - session->name, ns, L2TP_SKB_CB(skbp)->ns, - skb_queue_len(&session->reorder_q)); atomic_long_inc(&session->stats.rx_oos_packets); goto out; } @@ -445,9 +449,7 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff * /* Bump our Nr */ session->nr++; session->nr &= session->nr_max; - - l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated nr to %hu\n", - session->name, session->nr); + trace_session_seqnum_update(session); } /* call private receive handler */ @@ -472,37 +474,27 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) start: spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skb, tmp) { - if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) { + struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); + + /* If the packet has been pending on the queue for too long, discard it */ + if (time_after(jiffies, cb->expires)) { atomic_long_inc(&session->stats.rx_seq_discards); atomic_long_inc(&session->stats.rx_errors); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: oos pkt %u len %d discarded (too old), waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + trace_session_pkt_expired(session, cb->ns); session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); continue; } - if (L2TP_SKB_CB(skb)->has_seq) { + if (cb->has_seq) { if (session->reorder_skip) { - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: advancing nr to next pkt: %u -> %u", - session->name, session->nr, - L2TP_SKB_CB(skb)->ns); session->reorder_skip = 0; - session->nr = L2TP_SKB_CB(skb)->ns; + session->nr = cb->ns; + trace_session_seqnum_reset(session); } - if (L2TP_SKB_CB(skb)->ns != session->nr) { - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: holding oos pkt %u len %d, waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + if (cb->ns != session->nr) goto out; - } } __skb_unlink(skb, &session->reorder_q); @@ -535,14 +527,13 @@ static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr) */ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) { - if (!l2tp_seq_check_rx_window(session, L2TP_SKB_CB(skb)->ns)) { + struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); + + if (!l2tp_seq_check_rx_window(session, cb->ns)) { /* Packet sequence number is outside allowed window. * Discard it. */ - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: pkt %u len %d discarded, outside window, nr=%u\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr); + trace_session_pkt_outside_rx_window(session, cb->ns); goto discard; } @@ -559,10 +550,10 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) * is seen. After nr_oos_count_max in-sequence packets, reset the * sequence number to re-enable packet reception. */ - if (L2TP_SKB_CB(skb)->ns == session->nr) { + if (cb->ns == session->nr) { skb_queue_tail(&session->reorder_q, skb); } else { - u32 nr_oos = L2TP_SKB_CB(skb)->ns; + u32 nr_oos = cb->ns; u32 nr_next = (session->nr_oos + 1) & session->nr_max; if (nr_oos == nr_next) @@ -573,17 +564,10 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) session->nr_oos = nr_oos; if (session->nr_oos_count > session->nr_oos_count_max) { session->reorder_skip = 1; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: %d oos packets received. Resetting sequence numbers\n", - session->name, session->nr_oos_count); } if (!session->reorder_skip) { atomic_long_inc(&session->stats.rx_seq_discards); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: oos pkt %u len %d discarded, waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + trace_session_pkt_oos(session, cb->ns); goto discard; } skb_queue_tail(&session->reorder_q, skb); @@ -660,16 +644,14 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, int length) { struct l2tp_tunnel *tunnel = session->tunnel; - u32 ns = 0, nr = 0; int offset; /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: cookie mismatch (%u/%u). Discarding.\n", - tunnel->name, tunnel->tunnel_id, - session->session_id); + pr_warn_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", + tunnel->name, tunnel->tunnel_id, + session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } @@ -686,32 +668,21 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, L2TP_SKB_CB(skb)->has_seq = 0; if (tunnel->version == L2TP_HDR_VER_2) { if (hdrflags & L2TP_HDRFLAG_S) { - ns = ntohs(*(__be16 *)ptr); - ptr += 2; - nr = ntohs(*(__be16 *)ptr); - ptr += 2; - /* Store L2TP info in the skb */ - L2TP_SKB_CB(skb)->ns = ns; + L2TP_SKB_CB(skb)->ns = ntohs(*(__be16 *)ptr); L2TP_SKB_CB(skb)->has_seq = 1; + ptr += 2; + /* Skip past nr in the header */ + ptr += 2; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: recv data ns=%u, nr=%u, session nr=%u\n", - session->name, ns, nr, session->nr); } } else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = ntohl(*(__be32 *)ptr); if (l2h & 0x40000000) { - ns = l2h & 0x00ffffff; - /* Store L2TP info in the skb */ - L2TP_SKB_CB(skb)->ns = ns; + L2TP_SKB_CB(skb)->ns = l2h & 0x00ffffff; L2TP_SKB_CB(skb)->has_seq = 1; - - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: recv data ns=%u, session nr=%u\n", - session->name, ns, session->nr); } ptr += 4; } @@ -722,9 +693,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * configure it so. */ if (!session->lns_mode && !session->send_seq) { - l2tp_info(session, L2TP_MSG_SEQ, - "%s: requested to enable seq numbers by LNS\n", - session->name); + trace_session_seqnum_lns_enable(session); session->send_seq = 1; l2tp_session_set_header_len(session, tunnel->version); } @@ -733,9 +702,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { - l2tp_warn(session, L2TP_MSG_SEQ, - "%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -746,15 +714,12 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * LAC is broken. Discard the frame. */ if (!session->lns_mode && session->send_seq) { - l2tp_info(session, L2TP_MSG_SEQ, - "%s: requested to disable seq numbers by LNS\n", - session->name); + trace_session_seqnum_lns_disable(session); session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version); } else if (session->send_seq) { - l2tp_warn(session, L2TP_MSG_SEQ, - "%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -816,9 +781,6 @@ static void l2tp_session_queue_purge(struct l2tp_session *session) { struct sk_buff *skb = NULL; - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) - return; - while ((skb = skb_dequeue(&session->reorder_q))) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); @@ -847,22 +809,11 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: recv short packet (len=%d)\n", - tunnel->name, skb->len); + pr_warn_ratelimited("%s: recv short packet (len=%d)\n", + tunnel->name, skb->len); goto error; } - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto error; - - pr_debug("%s: recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length); - } - /* Point to L2TP header */ optr = skb->data; ptr = skb->data; @@ -873,9 +824,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Check protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; if (version != tunnel->version) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); + pr_warn_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", + tunnel->name, version, tunnel->version); goto error; } @@ -883,12 +833,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) length = skb->len; /* If type is control packet, it is handled by userspace. */ - if (hdrflags & L2TP_HDRFLAG_T) { - l2tp_dbg(tunnel, L2TP_MSG_DATA, - "%s: recv control packet, len=%d\n", - tunnel->name, length); + if (hdrflags & L2TP_HDRFLAG_T) goto error; - } /* Skip flags */ ptr += 2; @@ -917,9 +863,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); + pr_warn_ratelimited("%s: no session found (%u/%u). Passing up.\n", + tunnel->name, tunnel_id, session_id); goto error; } @@ -949,12 +894,17 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; + /* Note that this is called from the encap_rcv hook inside an + * RCU-protected region, but without the socket being locked. + * Hence we use rcu_dereference_sk_user_data to access the + * tunnel data structure rather the usual l2tp_sk_to_tunnel + * accessor function. + */ tunnel = rcu_dereference_sk_user_data(sk); if (!tunnel) goto pass_up; - - l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n", - tunnel->name, skb->len); + if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) + goto pass_up; if (l2tp_udp_recv_core(tunnel, skb)) goto pass_up; @@ -993,8 +943,7 @@ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf) *bufp++ = 0; session->ns++; session->ns &= 0xffff; - l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated ns to %u\n", - session->name, session->ns); + trace_session_seqnum_update(session); } return bufp - optr; @@ -1030,9 +979,7 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) l2h = 0x40000000 | session->ns; session->ns++; session->ns &= 0xffffff; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: updated ns to %u\n", - session->name, session->ns); + trace_session_seqnum_update(session); } *((__be32 *)bufp) = htonl(l2h); @@ -1042,74 +989,39 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) return bufp - optr; } -static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, - struct flowi *fl, size_t data_len) +/* Queue the packet to IP for output: tunnel socket lock must be held */ +static int l2tp_xmit_queue(struct l2tp_tunnel *tunnel, struct sk_buff *skb, struct flowi *fl) { - struct l2tp_tunnel *tunnel = session->tunnel; - unsigned int len = skb->len; - int error; - - /* Debug */ - if (session->send_seq) - l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes, ns=%u\n", - session->name, data_len, session->ns - 1); - else - l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes\n", - session->name, data_len); - - if (session->debug & L2TP_MSG_DATA) { - int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; - unsigned char *datap = skb->data + uhlen; - - pr_debug("%s: xmit\n", session->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, - datap, min_t(size_t, 32, len - uhlen)); - } + int err; - /* Queue the packet to IP for output */ skb->ignore_df = 1; skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) - error = inet6_csk_xmit(tunnel->sock, skb, NULL); + err = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif - error = ip_queue_xmit(tunnel->sock, skb, fl); + err = ip_queue_xmit(tunnel->sock, skb, fl); - /* Update stats */ - if (error >= 0) { - atomic_long_inc(&tunnel->stats.tx_packets); - atomic_long_add(len, &tunnel->stats.tx_bytes); - atomic_long_inc(&session->stats.tx_packets); - atomic_long_add(len, &session->stats.tx_bytes); - } else { - atomic_long_inc(&tunnel->stats.tx_errors); - atomic_long_inc(&session->stats.tx_errors); - } + return err >= 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } -/* If caller requires the skb to have a ppp header, the header must be - * inserted in the skb data before calling this function. - */ -int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len) +static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb) { - int data_len = skb->len; struct l2tp_tunnel *tunnel = session->tunnel; + unsigned int data_len = skb->len; struct sock *sk = tunnel->sock; - struct flowi *fl; - struct udphdr *uh; - struct inet_sock *inet; - int headroom; - int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; - int udp_len; + int headroom, uhlen, udp_len; int ret = NET_XMIT_SUCCESS; + struct inet_sock *inet; + struct udphdr *uh; /* Check that there's enough headroom in the skb to insert IP, * UDP and L2TP headers. If not enough, expand it to * make room. Adjust truesize. */ - headroom = NET_SKB_PAD + sizeof(struct iphdr) + - uhlen + hdr_len; + uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(*uh) : 0; + headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + session->hdr_len; if (skb_cow_head(skb, headroom)) { kfree_skb(skb); return NET_XMIT_DROP; @@ -1117,14 +1029,13 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Setup L2TP header */ if (tunnel->version == L2TP_HDR_VER_2) - l2tp_build_l2tpv2_header(session, __skb_push(skb, hdr_len)); + l2tp_build_l2tpv2_header(session, __skb_push(skb, session->hdr_len)); else - l2tp_build_l2tpv3_header(session, __skb_push(skb, hdr_len)); + l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); /* Reset skb netfilter state */ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | - IPSKB_REROUTED); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); bh_lock_sock(sk); @@ -1144,7 +1055,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len } inet = inet_sk(sk); - fl = &inet->cork.fl; switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* Setup UDP header */ @@ -1153,7 +1063,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len uh = udp_hdr(skb); uh->source = inet->inet_sport; uh->dest = inet->inet_dport; - udp_len = uhlen + hdr_len + data_len; + udp_len = uhlen + session->hdr_len + data_len; uh->len = htons(udp_len); /* Calculate UDP checksum if configured to do so */ @@ -1172,12 +1082,34 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len break; } - l2tp_xmit_core(session, skb, fl, data_len); + ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); + out_unlock: bh_unlock_sock(sk); return ret; } + +/* If caller requires the skb to have a ppp header, the header must be + * inserted in the skb data before calling this function. + */ +int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb) +{ + unsigned int len = skb->len; + int ret; + + ret = l2tp_xmit_core(session, skb); + if (ret == NET_XMIT_SUCCESS) { + atomic_long_inc(&session->tunnel->stats.tx_packets); + atomic_long_add(len, &session->tunnel->stats.tx_bytes); + atomic_long_inc(&session->stats.tx_packets); + atomic_long_add(len, &session->stats.tx_bytes); + } else { + atomic_long_inc(&session->tunnel->stats.tx_errors); + atomic_long_inc(&session->stats.tx_errors); + } + return ret; +} EXPORT_SYMBOL_GPL(l2tp_xmit_skb); /***************************************************************************** @@ -1190,13 +1122,11 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); */ static void l2tp_tunnel_destruct(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); if (!tunnel) goto end; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); - /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: @@ -1255,34 +1185,16 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) struct hlist_node *tmp; struct l2tp_session *session; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing all sessions...\n", - tunnel->name); - write_lock_bh(&tunnel->hlist_lock); tunnel->acpt_newsess = false; for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { again: hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) { session = hlist_entry(walk, struct l2tp_session, hlist); - - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: closing session\n", session->name); - hlist_del_init(&session->hlist); - if (test_and_set_bit(0, &session->dead)) - goto again; - write_unlock_bh(&tunnel->hlist_lock); - - l2tp_session_unhash(session); - l2tp_session_queue_purge(session); - - if (session->session_close) - (*session->session_close)(session); - - l2tp_session_dec_refcount(session); - + l2tp_session_delete(session); write_lock_bh(&tunnel->hlist_lock); /* Now restart from the beginning of this hash @@ -1299,7 +1211,7 @@ again: /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) l2tp_tunnel_delete(tunnel); @@ -1464,7 +1376,7 @@ out: static struct lock_class_key l2tp_socket_class; -int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, +int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp) { struct l2tp_tunnel *tunnel = NULL; @@ -1483,16 +1395,12 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 tunnel->version = version; tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; - tunnel->debug = L2TP_DEFAULT_DEBUG_FLAGS; tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); rwlock_init(&tunnel->hlist_lock); tunnel->acpt_newsess = true; - if (cfg) - tunnel->debug = cfg->debug; - tunnel->encap = encap; refcount_set(&tunnel->ref_count, 1); @@ -1597,6 +1505,8 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; + trace_register_tunnel(tunnel); + if (tunnel->fd >= 0) sockfd_put(sock); @@ -1617,6 +1527,7 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_register); void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { + trace_delete_tunnel(tunnel); l2tp_tunnel_inc_refcount(tunnel); queue_work(l2tp_wq, &tunnel->del_work); } @@ -1628,6 +1539,7 @@ void l2tp_session_delete(struct l2tp_session *session) if (test_and_set_bit(0, &session->dead)) return; + trace_delete_session(session); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) @@ -1686,12 +1598,8 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn INIT_HLIST_NODE(&session->hlist); INIT_HLIST_NODE(&session->global_hlist); - /* Inherit debug options from tunnel */ - session->debug = tunnel->debug; - if (cfg) { session->pwtype = cfg->pw_type; - session->debug = cfg->debug; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 3468d6b177a0..cb21d906343e 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -51,7 +51,6 @@ struct l2tp_session_cfg { unsigned int lns_mode:1; /* behave as LNS? * LAC enables sequence numbers under LNS control. */ - int debug; /* bitmask of debug message categories */ u16 l2specific_type; /* Layer 2 specific type */ u8 cookie[8]; /* optional cookie */ int cookie_len; /* 0, 4 or 8 bytes */ @@ -66,6 +65,7 @@ struct l2tp_session_cfg { * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into * an additional per-net ("global") hashlist. */ +#define L2TP_SESSION_NAME_MAX 32 struct l2tp_session { int magic; /* should be L2TP_SESSION_MAGIC */ long dead; @@ -90,14 +90,13 @@ struct l2tp_session { struct hlist_node hlist; /* hash list node */ refcount_t ref_count; - char name[32]; /* for logging */ + char name[L2TP_SESSION_NAME_MAX]; /* for logging */ char ifname[IFNAMSIZ]; unsigned int recv_seq:1; /* expect receive packets with sequence numbers? */ unsigned int send_seq:1; /* send packets with sequence numbers? */ unsigned int lns_mode:1; /* behave as LNS? * LAC enables sequence numbers under LNS control. */ - int debug; /* bitmask of debug message categories */ int reorder_timeout; /* configured reorder timeout (in jiffies) */ int reorder_skip; /* set if skip to next nr */ enum l2tp_pwtype pwtype; @@ -131,7 +130,6 @@ struct l2tp_session { /* L2TP tunnel configuration */ struct l2tp_tunnel_cfg { - int debug; /* bitmask of debug message categories */ enum l2tp_encap_type encap; /* Used only for kernel-created sockets */ @@ -154,6 +152,7 @@ struct l2tp_tunnel_cfg { * Maintains a hashlist of sessions belonging to the tunnel instance. * Is linked into a per-net list of tunnels. */ +#define L2TP_TUNNEL_NAME_MAX 20 struct l2tp_tunnel { int magic; /* Should be L2TP_TUNNEL_MAGIC */ @@ -170,8 +169,7 @@ struct l2tp_tunnel { u32 peer_tunnel_id; int version; /* 2=>L2TPv2, 3=>L2TPv3 */ - char name[20]; /* for logging */ - int debug; /* bitmask of debug message categories */ + char name[L2TP_TUNNEL_NAME_MAX]; /* for logging */ enum l2tp_encap_type encap; struct l2tp_stats stats; @@ -237,7 +235,7 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, * Creation of a new instance is a two-step process: create, then register. * Destruction is triggered using the *_delete functions, and completes asynchronously. */ -int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, +int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp); int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, @@ -263,8 +261,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); /* Transmit path helpers for sending packets over the tunnel socket. */ void l2tp_session_set_header_len(struct l2tp_session *session, int version); -int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, - int hdr_len); +int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb); /* Pseudowire management. * Pseudowires should register with l2tp core on module init, and unregister @@ -276,6 +273,11 @@ void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); /* IOCTL helper for IP encap modules. */ int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg); +/* Extract the tunnel structure from a socket's sk_user_data pointer, + * validating the tunnel magic feather. + */ +struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk); + static inline int l2tp_get_l2specific_len(struct l2tp_session *session) { switch (session->l2specific_type) { @@ -337,19 +339,6 @@ static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, str return 0; } -#define l2tp_printk(ptr, type, func, fmt, ...) \ -do { \ - if (((ptr)->debug) & (type)) \ - func(fmt, ##__VA_ARGS__); \ -} while (0) - -#define l2tp_warn(ptr, type, fmt, ...) \ - l2tp_printk(ptr, type, pr_warn, fmt, ##__VA_ARGS__) -#define l2tp_info(ptr, type, fmt, ...) \ - l2tp_printk(ptr, type, pr_info, fmt, ##__VA_ARGS__) -#define l2tp_dbg(ptr, type, fmt, ...) \ - l2tp_printk(ptr, type, pr_debug, fmt, ##__VA_ARGS__) - #define MODULE_ALIAS_L2TP_PWTYPE(type) \ MODULE_ALIAS("net-l2tp-type-" __stringify(type)) diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 96cb9601c21b..bca75bef8282 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -167,7 +167,7 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) tunnel->sock ? refcount_read(&tunnel->sock->sk_refcnt) : 0, refcount_read(&tunnel->ref_count)); seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n", - tunnel->debug, + 0, atomic_long_read(&tunnel->stats.tx_packets), atomic_long_read(&tunnel->stats.tx_bytes), atomic_long_read(&tunnel->stats.tx_errors), @@ -192,7 +192,7 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", - session->debug, + 0, jiffies_to_msecs(session->reorder_timeout)); seq_printf(m, " offset 0 l2specific %hu/%hu\n", session->l2specific_type, l2tp_get_l2specific_len(session)); diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 7ed2b4eced94..6cd97c75445c 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -76,7 +76,7 @@ static netdev_tx_t l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev struct l2tp_eth *priv = netdev_priv(dev); struct l2tp_session *session = priv->session; unsigned int len = skb->len; - int ret = l2tp_xmit_skb(session, skb, session->hdr_len); + int ret = l2tp_xmit_skb(session, skb); if (likely(ret == NET_XMIT_SUCCESS)) { atomic_long_add(len, &priv->tx_bytes); @@ -128,17 +128,6 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, struct net_device *dev; struct l2tp_eth *priv; - if (session->debug & L2TP_MSG_DATA) { - unsigned int length; - - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto error; - - pr_debug("%s: eth recv\n", session->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length); - } - if (!pskb_may_pull(skb, ETH_HLEN)) goto error; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index df2a35b5714a..97ae1255fcb6 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -118,7 +118,6 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; - int length; if (!pskb_may_pull(skb, 4)) goto discard; @@ -147,20 +146,6 @@ static int l2tp_ip_recv(struct sk_buff *skb) if (!tunnel) goto discard_sess; - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto discard_sess; - - /* Point to L2TP header */ - optr = skb->data; - ptr = skb->data; - ptr += 4; - pr_debug("%s: ip recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); - } - if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; @@ -248,8 +233,8 @@ static void l2tp_ip_close(struct sock *sk, long timeout) static void l2tp_ip_destroy_sock(struct sock *sk) { + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); struct sk_buff *skb; - struct l2tp_tunnel *tunnel = sk->sk_user_data; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index bc757bc7e264..e5e5036257b0 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -131,7 +131,6 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct ipv6hdr *iph; - int length; if (!pskb_may_pull(skb, 4)) goto discard; @@ -160,20 +159,6 @@ static int l2tp_ip6_recv(struct sk_buff *skb) if (!tunnel) goto discard_sess; - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto discard_sess; - - /* Point to L2TP header */ - optr = skb->data; - ptr = skb->data; - ptr += 4; - pr_debug("%s: ip recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); - } - if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; @@ -262,7 +247,7 @@ static void l2tp_ip6_close(struct sock *sk, long timeout) static void l2tp_ip6_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = sk->sk_user_data; + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); lock_sock(sk); ip6_flush_pending_frames(sk); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index def78eebca4c..83c015f7f20d 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -229,14 +229,11 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info goto out; } - if (attrs[L2TP_ATTR_DEBUG]) - cfg.debug = nla_get_u32(attrs[L2TP_ATTR_DEBUG]); - ret = -EINVAL; switch (cfg.encap) { case L2TP_ENCAPTYPE_UDP: case L2TP_ENCAPTYPE_IP: - ret = l2tp_tunnel_create(net, fd, proto_version, tunnel_id, + ret = l2tp_tunnel_create(fd, proto_version, tunnel_id, peer_tunnel_id, &cfg, &tunnel); break; } @@ -307,9 +304,6 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info goto out; } - if (info->attrs[L2TP_ATTR_DEBUG]) - tunnel->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_MODIFY); @@ -400,7 +394,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla if (nla_put_u8(skb, L2TP_ATTR_PROTO_VERSION, tunnel->version) || nla_put_u32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id) || nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) || - nla_put_u32(skb, L2TP_ATTR_DEBUG, tunnel->debug) || + nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) || nla_put_u16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap)) goto nla_put_failure; @@ -605,9 +599,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf cfg.ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]); } - if (info->attrs[L2TP_ATTR_DEBUG]) - cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - if (info->attrs[L2TP_ATTR_RECV_SEQ]) cfg.recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); @@ -689,9 +680,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf goto out; } - if (info->attrs[L2TP_ATTR_DEBUG]) - session->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - if (info->attrs[L2TP_ATTR_RECV_SEQ]) session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); @@ -730,7 +718,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl nla_put_u32(skb, L2TP_ATTR_SESSION_ID, session->session_id) || nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) || nla_put_u32(skb, L2TP_ATTR_PEER_SESSION_ID, session->peer_session_id) || - nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) || + nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) || nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype)) goto nla_put_failure; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 13c3153b40d6..aea85f91f059 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -237,17 +237,9 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int if (sk->sk_state & PPPOX_BOUND) { struct pppox_sock *po; - l2tp_dbg(session, L2TP_MSG_DATA, - "%s: recv %d byte data frame, passing to ppp\n", - session->name, data_len); - po = pppox_sk(sk); ppp_input(&po->chan, skb); } else { - l2tp_dbg(session, L2TP_MSG_DATA, - "%s: recv %d byte data frame, passing to L2TP socket\n", - session->name, data_len); - if (sock_queue_rcv_skb(sk, skb) < 0) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); @@ -259,7 +251,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int no_sock: rcu_read_unlock(); - l2tp_info(session, L2TP_MSG_DATA, "%s: no socket\n", session->name); + pr_warn_ratelimited("%s: no socket in recv\n", session->name); kfree_skb(skb); } @@ -324,7 +316,7 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, } local_bh_disable(); - l2tp_xmit_skb(session, skb, session->hdr_len); + l2tp_xmit_skb(session, skb); local_bh_enable(); sock_put(sk); @@ -383,7 +375,7 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb->data[1] = PPP_UI; local_bh_disable(); - l2tp_xmit_skb(session, skb, session->hdr_len); + l2tp_xmit_skb(session, skb); local_bh_enable(); sock_put(sk); @@ -710,7 +702,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (!tunnel) { struct l2tp_tunnel_cfg tcfg = { .encap = L2TP_ENCAPTYPE_UDP, - .debug = 0, }; /* Prevent l2tp_tunnel_register() from trying to set up @@ -721,7 +712,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, goto end; } - error = l2tp_tunnel_create(sock_net(sk), info.fd, + error = l2tp_tunnel_create(info.fd, info.version, info.tunnel_id, info.peer_tunnel_id, &tcfg, @@ -840,8 +831,6 @@ out_no_ppp: drop_refcnt = false; sk->sk_state = PPPOX_CONNECTED; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n", - session->name); end: if (error) { @@ -1076,6 +1065,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, if (!session) return -ENOTCONN; + if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) + return -EBADF; + /* Not defined for tunnels */ if (!session->session_id && !session->peer_session_id) return -ENOSYS; @@ -1090,6 +1082,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, if (!session) return -ENOTCONN; + if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) + return -EBADF; + /* Not defined for tunnels */ if (!session->session_id && !session->peer_session_id) return -ENOSYS; @@ -1103,6 +1098,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, if (!session) return -ENOTCONN; + if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) + return -EBADF; + /* Session 0 represents the parent tunnel */ if (!session->session_id && !session->peer_session_id) { u32 session_id; @@ -1157,9 +1155,7 @@ static int pppol2tp_tunnel_setsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_DEBUG: - tunnel->debug = val; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: set debug=%x\n", - tunnel->name, tunnel->debug); + /* Tunnel debug flags option is deprecated */ break; default: @@ -1185,9 +1181,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk, break; } session->recv_seq = !!val; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set recv_seq=%d\n", - session->name, session->recv_seq); break; case PPPOL2TP_SO_SENDSEQ: @@ -1203,9 +1196,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk, PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } l2tp_session_set_header_len(session, session->tunnel->version); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set send_seq=%d\n", - session->name, session->send_seq); break; case PPPOL2TP_SO_LNSMODE: @@ -1214,22 +1204,14 @@ static int pppol2tp_session_setsockopt(struct sock *sk, break; } session->lns_mode = !!val; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set lns_mode=%d\n", - session->name, session->lns_mode); break; case PPPOL2TP_SO_DEBUG: - session->debug = val; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: set debug=%x\n", - session->name, session->debug); + /* Session debug flags option is deprecated */ break; case PPPOL2TP_SO_REORDERTO: session->reorder_timeout = msecs_to_jiffies(val); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set reorder_timeout=%d\n", - session->name, session->reorder_timeout); break; default: @@ -1297,9 +1279,8 @@ static int pppol2tp_tunnel_getsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_DEBUG: - *val = tunnel->debug; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: get debug=%x\n", - tunnel->name, tunnel->debug); + /* Tunnel debug flags option is deprecated */ + *val = 0; break; default: @@ -1321,32 +1302,23 @@ static int pppol2tp_session_getsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_RECVSEQ: *val = session->recv_seq; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get recv_seq=%d\n", session->name, *val); break; case PPPOL2TP_SO_SENDSEQ: *val = session->send_seq; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get send_seq=%d\n", session->name, *val); break; case PPPOL2TP_SO_LNSMODE: *val = session->lns_mode; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get lns_mode=%d\n", session->name, *val); break; case PPPOL2TP_SO_DEBUG: - *val = session->debug; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: get debug=%d\n", - session->name, *val); + /* Session debug flags option is deprecated */ + *val = 0; break; case PPPOL2TP_SO_REORDERTO: *val = (int)jiffies_to_msecs(session->reorder_timeout); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get reorder_timeout=%d\n", session->name, *val); break; default: @@ -1534,7 +1506,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N', refcount_read(&tunnel->ref_count) - 1); seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n", - tunnel->debug, + 0, atomic_long_read(&tunnel->stats.tx_packets), atomic_long_read(&tunnel->stats.tx_bytes), atomic_long_read(&tunnel->stats.tx_errors), @@ -1580,7 +1552,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", - session->debug, + 0, jiffies_to_msecs(session->reorder_timeout)); seq_printf(m, " %hu/%hu %ld/%ld/%ld %ld/%ld/%ld\n", session->nr, session->ns, diff --git a/net/l2tp/trace.h b/net/l2tp/trace.h new file mode 100644 index 000000000000..8596eaa12a2e --- /dev/null +++ b/net/l2tp/trace.h @@ -0,0 +1,211 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM l2tp + +#if !defined(_TRACE_L2TP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_L2TP_H + +#include <linux/tracepoint.h> +#include <linux/l2tp.h> +#include "l2tp_core.h" + +#define encap_type_name(e) { L2TP_ENCAPTYPE_##e, #e } +#define show_encap_type_name(val) \ + __print_symbolic(val, \ + encap_type_name(UDP), \ + encap_type_name(IP)) + +#define pw_type_name(p) { L2TP_PWTYPE_##p, #p } +#define show_pw_type_name(val) \ + __print_symbolic(val, \ + pw_type_name(ETH_VLAN), \ + pw_type_name(ETH), \ + pw_type_name(PPP), \ + pw_type_name(PPP_AC), \ + pw_type_name(IP)) + +DECLARE_EVENT_CLASS(tunnel_only_evt, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel), + TP_STRUCT__entry( + __array(char, name, L2TP_TUNNEL_NAME_MAX) + ), + TP_fast_assign( + memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); + ), + TP_printk("%s", __entry->name) +); + +DECLARE_EVENT_CLASS(session_only_evt, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + ), + TP_printk("%s", __entry->name) +); + +TRACE_EVENT(register_tunnel, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel), + TP_STRUCT__entry( + __array(char, name, L2TP_TUNNEL_NAME_MAX) + __field(int, fd) + __field(u32, tid) + __field(u32, ptid) + __field(int, version) + __field(enum l2tp_encap_type, encap) + ), + TP_fast_assign( + memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); + __entry->fd = tunnel->fd; + __entry->tid = tunnel->tunnel_id; + __entry->ptid = tunnel->peer_tunnel_id; + __entry->version = tunnel->version; + __entry->encap = tunnel->encap; + ), + TP_printk("%s: type=%s encap=%s version=L2TPv%d tid=%u ptid=%u fd=%d", + __entry->name, + __entry->fd > 0 ? "managed" : "unmanaged", + show_encap_type_name(__entry->encap), + __entry->version, + __entry->tid, + __entry->ptid, + __entry->fd) +); + +DEFINE_EVENT(tunnel_only_evt, delete_tunnel, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel) +); + +DEFINE_EVENT(tunnel_only_evt, free_tunnel, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel) +); + +TRACE_EVENT(register_session, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + __field(u32, tid) + __field(u32, ptid) + __field(u32, sid) + __field(u32, psid) + __field(enum l2tp_pwtype, pwtype) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + __entry->tid = session->tunnel ? session->tunnel->tunnel_id : 0; + __entry->ptid = session->tunnel ? session->tunnel->peer_tunnel_id : 0; + __entry->sid = session->session_id; + __entry->psid = session->peer_session_id; + __entry->pwtype = session->pwtype; + ), + TP_printk("%s: pseudowire=%s sid=%u psid=%u tid=%u ptid=%u", + __entry->name, + show_pw_type_name(__entry->pwtype), + __entry->sid, + __entry->psid, + __entry->sid, + __entry->psid) +); + +DEFINE_EVENT(session_only_evt, delete_session, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_only_evt, free_session, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_only_evt, session_seqnum_lns_enable, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_only_evt, session_seqnum_lns_disable, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DECLARE_EVENT_CLASS(session_seqnum_evt, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + __field(u32, ns) + __field(u32, nr) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + __entry->ns = session->ns; + __entry->nr = session->nr; + ), + TP_printk("%s: ns=%u nr=%u", + __entry->name, + __entry->ns, + __entry->nr) +); + +DEFINE_EVENT(session_seqnum_evt, session_seqnum_update, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_seqnum_evt, session_seqnum_reset, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DECLARE_EVENT_CLASS(session_pkt_discard_evt, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + __field(u32, pkt_ns) + __field(u32, my_nr) + __field(u32, reorder_q_len) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + __entry->pkt_ns = pkt_ns, + __entry->my_nr = session->nr; + __entry->reorder_q_len = skb_queue_len(&session->reorder_q); + ), + TP_printk("%s: pkt_ns=%u my_nr=%u reorder_q_len=%u", + __entry->name, + __entry->pkt_ns, + __entry->my_nr, + __entry->reorder_q_len) +); + +DEFINE_EVENT(session_pkt_discard_evt, session_pkt_expired, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns) +); + +DEFINE_EVENT(session_pkt_discard_evt, session_pkt_outside_rx_window, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns) +); + +DEFINE_EVENT(session_pkt_discard_evt, session_pkt_oos, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns) +); + +#endif /* _TRACE_L2TP_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace +#include <trace/define_trace.h> diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index e71ca5aec684..864326f150e2 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -154,7 +154,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu); /** - * l3mdev_fib_table - get FIB table id associated with an L3 + * l3mdev_fib_table_rcu - get FIB table id associated with an L3 * master interface * @dev: targeted interface */ diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 313ba97acae3..cd4cf84a7f99 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -350,7 +350,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, sta->sta.addr, tid); /* We have no API to update the timeout value in the * driver so reject the timeout update if the timeout - * changed. If if did not change, i.e., no real update, + * changed. If it did not change, i.e., no real update, * just reply with success. */ rcu_read_lock(); diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 366f76c9003d..314973033d03 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -405,18 +405,14 @@ ieee80211_calc_legacy_rate_duration(u16 bitrate, bool short_pre, return duration; } -u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, - struct ieee80211_rx_status *status, - int len) +static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw, + struct ieee80211_rx_status *status, + u32 *overhead) { - struct ieee80211_supported_band *sband; - const struct ieee80211_rate *rate; bool sgi = status->enc_flags & RX_ENC_FLAG_SHORT_GI; - bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE; int bw, streams; int group, idx; u32 duration; - bool cck; switch (status->bw) { case RATE_INFO_BW_20: @@ -437,20 +433,6 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, } switch (status->encoding) { - case RX_ENC_LEGACY: - if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ)) - return 0; - - sband = hw->wiphy->bands[status->band]; - if (!sband || status->rate_idx >= sband->n_bitrates) - return 0; - - rate = &sband->bitrates[status->rate_idx]; - cck = rate->flags & IEEE80211_RATE_MANDATORY_B; - - return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp, - cck, len); - case RX_ENC_VHT: streams = status->nss; idx = status->rate_idx; @@ -477,51 +459,144 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, duration = airtime_mcs_groups[group].duration[idx]; duration <<= airtime_mcs_groups[group].shift; + *overhead = 36 + (streams << 2); + + return duration; +} + + +u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, + struct ieee80211_rx_status *status, + int len) +{ + struct ieee80211_supported_band *sband; + u32 duration, overhead = 0; + + if (status->encoding == RX_ENC_LEGACY) { + const struct ieee80211_rate *rate; + bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE; + bool cck; + + if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ)) + return 0; + + sband = hw->wiphy->bands[status->band]; + if (!sband || status->rate_idx >= sband->n_bitrates) + return 0; + + rate = &sband->bitrates[status->rate_idx]; + cck = rate->flags & IEEE80211_RATE_MANDATORY_B; + + return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp, + cck, len); + } + + duration = ieee80211_get_rate_duration(hw, status, &overhead); + if (!duration) + return 0; + duration *= len; duration /= AVG_PKT_SIZE; duration /= 1024; - duration += 36 + (streams << 2); - - return duration; + return duration + overhead; } EXPORT_SYMBOL_GPL(ieee80211_calc_rx_airtime); -static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw, - struct ieee80211_tx_rate *rate, - u8 band, int len) +static bool ieee80211_fill_rate_info(struct ieee80211_hw *hw, + struct ieee80211_rx_status *stat, u8 band, + struct rate_info *ri) { - struct ieee80211_rx_status stat = { - .band = band, - }; + struct ieee80211_supported_band *sband = hw->wiphy->bands[band]; + int i; - if (rate->idx < 0 || !rate->count) + if (!ri || !sband) + return false; + + stat->bw = ri->bw; + stat->nss = ri->nss; + stat->rate_idx = ri->mcs; + + if (ri->flags & RATE_INFO_FLAGS_HE_MCS) + stat->encoding = RX_ENC_HE; + else if (ri->flags & RATE_INFO_FLAGS_VHT_MCS) + stat->encoding = RX_ENC_VHT; + else if (ri->flags & RATE_INFO_FLAGS_MCS) + stat->encoding = RX_ENC_HT; + else + stat->encoding = RX_ENC_LEGACY; + + if (ri->flags & RATE_INFO_FLAGS_SHORT_GI) + stat->enc_flags |= RX_ENC_FLAG_SHORT_GI; + + stat->he_gi = ri->he_gi; + + if (stat->encoding != RX_ENC_LEGACY) + return true; + + stat->rate_idx = 0; + for (i = 0; i < sband->n_bitrates; i++) { + if (ri->legacy != sband->bitrates[i].bitrate) + continue; + + stat->rate_idx = i; + return true; + } + + return false; +} + +static int ieee80211_fill_rx_status(struct ieee80211_rx_status *stat, + struct ieee80211_hw *hw, + struct ieee80211_tx_rate *rate, + struct rate_info *ri, u8 band, int len) +{ + memset(stat, 0, sizeof(*stat)); + stat->band = band; + + if (ieee80211_fill_rate_info(hw, stat, band, ri)) return 0; + if (rate->idx < 0 || !rate->count) + return -1; + if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) - stat.bw = RATE_INFO_BW_80; + stat->bw = RATE_INFO_BW_80; else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) - stat.bw = RATE_INFO_BW_40; + stat->bw = RATE_INFO_BW_40; else - stat.bw = RATE_INFO_BW_20; + stat->bw = RATE_INFO_BW_20; - stat.enc_flags = 0; + stat->enc_flags = 0; if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE) - stat.enc_flags |= RX_ENC_FLAG_SHORTPRE; + stat->enc_flags |= RX_ENC_FLAG_SHORTPRE; if (rate->flags & IEEE80211_TX_RC_SHORT_GI) - stat.enc_flags |= RX_ENC_FLAG_SHORT_GI; + stat->enc_flags |= RX_ENC_FLAG_SHORT_GI; - stat.rate_idx = rate->idx; + stat->rate_idx = rate->idx; if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { - stat.encoding = RX_ENC_VHT; - stat.rate_idx = ieee80211_rate_get_vht_mcs(rate); - stat.nss = ieee80211_rate_get_vht_nss(rate); + stat->encoding = RX_ENC_VHT; + stat->rate_idx = ieee80211_rate_get_vht_mcs(rate); + stat->nss = ieee80211_rate_get_vht_nss(rate); } else if (rate->flags & IEEE80211_TX_RC_MCS) { - stat.encoding = RX_ENC_HT; + stat->encoding = RX_ENC_HT; } else { - stat.encoding = RX_ENC_LEGACY; + stat->encoding = RX_ENC_LEGACY; } + return 0; +} + +static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw, + struct ieee80211_tx_rate *rate, + struct rate_info *ri, + u8 band, int len) +{ + struct ieee80211_rx_status stat; + + if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len)) + return 0; + return ieee80211_calc_rx_airtime(hw, &stat, len); } @@ -536,7 +611,7 @@ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_tx_rate *rate = &info->status.rates[i]; u32 cur_duration; - cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate, + cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate, NULL, info->band, len); if (!cur_duration) break; @@ -572,26 +647,41 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, if (pubsta) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + struct ieee80211_rx_status stat; struct ieee80211_tx_rate *rate = &sta->tx_stats.last_rate; - u32 airtime; + struct rate_info *ri = &sta->tx_stats.last_rate_info; + u32 duration, overhead; + u8 agg_shift; - if (!(rate->flags & (IEEE80211_TX_RC_VHT_MCS | - IEEE80211_TX_RC_MCS))) - ampdu = false; + if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len)) + return 0; + if (stat.encoding == RX_ENC_LEGACY || !ampdu) + return ieee80211_calc_rx_airtime(hw, &stat, len); + + duration = ieee80211_get_rate_duration(hw, &stat, &overhead); /* * Assume that HT/VHT transmission on any AC except VO will * use aggregation. Since we don't have reliable reporting - * of aggregation length, assume an average of 16. + * of aggregation length, assume an average size based on the + * tx rate. * This will not be very accurate, but much better than simply - * assuming un-aggregated tx. + * assuming un-aggregated tx in all cases. */ - airtime = ieee80211_calc_tx_airtime_rate(hw, rate, band, - ampdu ? len * 16 : len); - if (ampdu) - airtime /= 16; - - return airtime; + if (duration > 400) /* <= VHT20 MCS2 1S */ + agg_shift = 1; + else if (duration > 250) /* <= VHT20 MCS3 1S or MCS1 2S */ + agg_shift = 2; + else if (duration > 150) /* <= VHT20 MCS5 1S or MCS3 2S */ + agg_shift = 3; + else + agg_shift = 4; + + duration *= len; + duration /= AVG_PKT_SIZE; + duration /= 1024; + + return duration + (overhead >> agg_shift); } if (!conf) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 87fddd84c621..b4e39e31a985 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -826,9 +826,9 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, memcpy(new->data, resp, resp_len); if (csa) - memcpy(new->csa_counter_offsets, csa->counter_offsets_presp, + memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_presp, csa->n_counter_offsets_presp * - sizeof(new->csa_counter_offsets[0])); + sizeof(new->cntdwn_counter_offsets[0])); rcu_assign_pointer(sdata->u.ap.probe_resp, new); if (old) @@ -926,10 +926,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, new->tail_len = new_tail_len; if (csa) { - new->csa_current_counter = csa->count; - memcpy(new->csa_counter_offsets, csa->counter_offsets_beacon, + new->cntdwn_current_counter = csa->count; + memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_beacon, csa->n_counter_offsets_beacon * - sizeof(new->csa_counter_offsets[0])); + sizeof(new->cntdwn_counter_offsets[0])); } /* copy in head */ @@ -3186,9 +3186,9 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, break; if ((params->n_counter_offsets_beacon > - IEEE80211_MAX_CSA_COUNTERS_NUM) || + IEEE80211_MAX_CNTDWN_COUNTERS_NUM) || (params->n_counter_offsets_presp > - IEEE80211_MAX_CSA_COUNTERS_NUM)) + IEEE80211_MAX_CNTDWN_COUNTERS_NUM)) return -EINVAL; csa.counter_offsets_beacon = params->counter_offsets_beacon; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 53632c2f5217..c0963969a465 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -145,9 +145,9 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata, *pos++ = csa_settings->block_tx ? 1 : 0; *pos++ = ieee80211_frequency_to_channel( csa_settings->chandef.chan->center_freq); - presp->csa_counter_offsets[0] = (pos - presp->head); + presp->cntdwn_counter_offsets[0] = (pos - presp->head); *pos++ = csa_settings->count; - presp->csa_current_counter = csa_settings->count; + presp->cntdwn_current_counter = csa_settings->count; } /* put the remaining rates in WLAN_EID_EXT_SUPP_RATES */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 0b1eaec6649f..6bf879660a93 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -259,15 +259,15 @@ struct beacon_data { u8 *head, *tail; int head_len, tail_len; struct ieee80211_meshconf_ie *meshconf; - u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM]; - u8 csa_current_counter; + u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; + u8 cntdwn_current_counter; struct rcu_head rcu_head; }; struct probe_resp { struct rcu_head rcu_head; int len; - u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; u8 data[]; }; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index b4a2efe8e83a..523380aed92e 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1168,7 +1168,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT; } - local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM; + local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CNTDWN_COUNTERS_NUM; /* * We use the number of queues for feature tests (QoS, HT) internally diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 7ecd801a943b..ce5825d6f1d1 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -672,7 +672,7 @@ void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh) * @hdr: 802.11 frame header * @fc: frame control field * @meshda: destination address in the mesh - * @meshsa: source address address in the mesh. Same as TA, as frame is + * @meshsa: source address in the mesh. Same as TA, as frame is * locally originated. * * Return the length of the 802.11 (does not include a mesh control header) @@ -864,8 +864,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) *pos++ = 0x0; *pos++ = ieee80211_frequency_to_channel( csa->settings.chandef.chan->center_freq); - bcn->csa_current_counter = csa->settings.count; - bcn->csa_counter_offsets[0] = hdr_len + 6; + bcn->cntdwn_current_counter = csa->settings.count; + bcn->cntdwn_counter_offsets[0] = hdr_len + 6; *pos++ = csa->settings.count; *pos++ = WLAN_EID_CHAN_SWITCH_PARAM; *pos++ = 6; diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index f470d1a7ce9b..1ac7b8c374c9 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -916,7 +916,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, if (beacon) for (i = 0; i < params->n_csa_offsets; i++) data[params->csa_offsets[i]] = - beacon->csa_current_counter; + beacon->cntdwn_current_counter; rcu_read_unlock(); } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 9d398c9daa4c..d5010116cf4d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -524,7 +524,7 @@ struct ieee80211_sta_rx_stats { * @status_stats.retry_failed: # of frames that failed after retry * @status_stats.retry_count: # of retries attempted * @status_stats.lost_packets: # of lost packets - * @status_stats.last_tdls_pkt_time: timestamp of last TDLS packet + * @status_stats.last_pkt_time: timestamp of last ACKed packet * @status_stats.msdu_retries: # of MSDU retries * @status_stats.msdu_failed: # of failed MSDUs * @status_stats.last_ack: last ack timestamp (jiffies) @@ -597,7 +597,7 @@ struct sta_info { unsigned long filtered; unsigned long retry_failed, retry_count; unsigned int lost_packets; - unsigned long last_tdls_pkt_time; + unsigned long last_pkt_time; u64 msdu_retries[IEEE80211_NUM_TIDS + 1]; u64 msdu_failed[IEEE80211_NUM_TIDS + 1]; unsigned long last_ack; @@ -611,6 +611,7 @@ struct sta_info { u64 packets[IEEE80211_NUM_ACS]; u64 bytes[IEEE80211_NUM_ACS]; struct ieee80211_tx_rate last_rate; + struct rate_info last_rate_info; u64 msdu[IEEE80211_NUM_TIDS + 1]; } tx_stats; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index adb1d30ce06e..0794396a7988 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -755,12 +755,16 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, * - current throughput (higher value for higher tpt)? */ #define STA_LOST_PKT_THRESHOLD 50 +#define STA_LOST_PKT_TIME HZ /* 1 sec since last ACK */ #define STA_LOST_TDLS_PKT_THRESHOLD 10 #define STA_LOST_TDLS_PKT_TIME (10*HZ) /* 10secs since last ACK */ static void ieee80211_lost_packet(struct sta_info *sta, struct ieee80211_tx_info *info) { + unsigned long pkt_time = STA_LOST_PKT_TIME; + unsigned int pkt_thr = STA_LOST_PKT_THRESHOLD; + /* If driver relies on its own algorithm for station kickout, skip * mac80211 packet loss mechanism. */ @@ -773,21 +777,20 @@ static void ieee80211_lost_packet(struct sta_info *sta, return; sta->status_stats.lost_packets++; - if (!sta->sta.tdls && - sta->status_stats.lost_packets < STA_LOST_PKT_THRESHOLD) - return; + if (sta->sta.tdls) { + pkt_time = STA_LOST_TDLS_PKT_TIME; + pkt_thr = STA_LOST_PKT_THRESHOLD; + } /* * If we're in TDLS mode, make sure that all STA_LOST_TDLS_PKT_THRESHOLD * of the last packets were lost, and that no ACK was received in the * last STA_LOST_TDLS_PKT_TIME ms, before triggering the CQM packet-loss * mechanism. + * For non-TDLS, use STA_LOST_PKT_THRESHOLD and STA_LOST_PKT_TIME */ - if (sta->sta.tdls && - (sta->status_stats.lost_packets < STA_LOST_TDLS_PKT_THRESHOLD || - time_before(jiffies, - sta->status_stats.last_tdls_pkt_time + - STA_LOST_TDLS_PKT_TIME))) + if (sta->status_stats.lost_packets < pkt_thr || + !time_after(jiffies, sta->status_stats.last_pkt_time + pkt_time)) return; cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr, @@ -1033,9 +1036,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, sta->status_stats.lost_packets = 0; /* Track when last TDLS packet was ACKed */ - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = - jiffies; + sta->status_stats.last_pkt_time = jiffies; } else if (noack_success) { /* nothing to do here, do not account as lost */ } else { @@ -1137,9 +1138,17 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, struct ieee80211_tx_info *info = status->info; struct ieee80211_sta *pubsta = status->sta; struct ieee80211_supported_band *sband; + struct sta_info *sta; int retry_count; bool acked, noack_success; + if (pubsta) { + sta = container_of(pubsta, struct sta_info, sta); + + if (status->rate) + sta->tx_stats.last_rate_info = *status->rate; + } + if (status->skb) return __ieee80211_tx_status(hw, status); @@ -1154,10 +1163,6 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED); if (pubsta) { - struct sta_info *sta; - - sta = container_of(pubsta, struct sta_info, sta); - if (!acked && !noack_success) sta->status_stats.retry_failed++; sta->status_stats.retry_count += retry_count; @@ -1168,9 +1173,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; - /* Track when last TDLS packet was ACKed */ - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = jiffies; + /* Track when last packet was ACKed */ + sta->status_stats.last_pkt_time = jiffies; } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { return; } else if (noack_success) { @@ -1259,8 +1263,7 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = jiffies; + sta->status_stats.last_pkt_time = jiffies; } else { ieee80211_lost_packet(sta, info); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index dca01d7e6e3e..d2136007e2eb 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4538,14 +4538,14 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, return 0; } -static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, - struct beacon_data *beacon) +static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata, + struct beacon_data *beacon) { struct probe_resp *resp; u8 *beacon_data; size_t beacon_data_len; int i; - u8 count = beacon->csa_current_counter; + u8 count = beacon->cntdwn_current_counter; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: @@ -4565,36 +4565,36 @@ static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, } rcu_read_lock(); - for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; ++i) { + for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; ++i) { resp = rcu_dereference(sdata->u.ap.probe_resp); - if (beacon->csa_counter_offsets[i]) { - if (WARN_ON_ONCE(beacon->csa_counter_offsets[i] >= + if (beacon->cntdwn_counter_offsets[i]) { + if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[i] >= beacon_data_len)) { rcu_read_unlock(); return; } - beacon_data[beacon->csa_counter_offsets[i]] = count; + beacon_data[beacon->cntdwn_counter_offsets[i]] = count; } if (sdata->vif.type == NL80211_IFTYPE_AP && resp) - resp->data[resp->csa_counter_offsets[i]] = count; + resp->data[resp->cntdwn_counter_offsets[i]] = count; } rcu_read_unlock(); } -static u8 __ieee80211_csa_update_counter(struct beacon_data *beacon) +static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon) { - beacon->csa_current_counter--; + beacon->cntdwn_current_counter--; /* the counter should never reach 0 */ - WARN_ON_ONCE(!beacon->csa_current_counter); + WARN_ON_ONCE(!beacon->cntdwn_current_counter); - return beacon->csa_current_counter; + return beacon->cntdwn_current_counter; } -u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) +u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; @@ -4612,15 +4612,15 @@ u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) if (!beacon) goto unlock; - count = __ieee80211_csa_update_counter(beacon); + count = __ieee80211_beacon_update_cntdwn(beacon); unlock: rcu_read_unlock(); return count; } -EXPORT_SYMBOL(ieee80211_csa_update_counter); +EXPORT_SYMBOL(ieee80211_beacon_update_cntdwn); -void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter) +void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; @@ -4637,15 +4637,15 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter) if (!beacon) goto unlock; - if (counter < beacon->csa_current_counter) - beacon->csa_current_counter = counter; + if (counter < beacon->cntdwn_current_counter) + beacon->cntdwn_current_counter = counter; unlock: rcu_read_unlock(); } -EXPORT_SYMBOL(ieee80211_csa_set_counter); +EXPORT_SYMBOL(ieee80211_beacon_set_cntdwn); -bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) +bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; @@ -4688,20 +4688,21 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) goto out; } - if (!beacon->csa_counter_offsets[0]) + if (!beacon->cntdwn_counter_offsets[0]) goto out; - if (WARN_ON_ONCE(beacon->csa_counter_offsets[0] > beacon_data_len)) + if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[0] > beacon_data_len)) goto out; - if (beacon_data[beacon->csa_counter_offsets[0]] == 1) + if (beacon_data[beacon->cntdwn_counter_offsets[0]] == 1) ret = true; + out: rcu_read_unlock(); return ret; } -EXPORT_SYMBOL(ieee80211_csa_is_complete); +EXPORT_SYMBOL(ieee80211_beacon_cntdwn_is_complete); static int ieee80211_beacon_protect(struct sk_buff *skb, struct ieee80211_local *local, @@ -4761,11 +4762,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, beacon = rcu_dereference(ap->beacon); if (beacon) { - if (beacon->csa_counter_offsets[0]) { + if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) - __ieee80211_csa_update_counter(beacon); + ieee80211_beacon_update_cntdwn(vif); - ieee80211_set_csa(sdata, beacon); + ieee80211_set_beacon_cntdwn(sdata, beacon); } /* @@ -4809,11 +4810,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (!beacon) goto out; - if (beacon->csa_counter_offsets[0]) { + if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) - __ieee80211_csa_update_counter(beacon); + __ieee80211_beacon_update_cntdwn(beacon); - ieee80211_set_csa(sdata, beacon); + ieee80211_set_beacon_cntdwn(sdata, beacon); } skb = dev_alloc_skb(local->tx_headroom + beacon->head_len + @@ -4833,16 +4834,16 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (!beacon) goto out; - if (beacon->csa_counter_offsets[0]) { + if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) /* TODO: For mesh csa_counter is in TU, so * decrementing it by one isn't correct, but * for now we leave it consistent with overall * mac80211's behavior. */ - __ieee80211_csa_update_counter(beacon); + __ieee80211_beacon_update_cntdwn(beacon); - ieee80211_set_csa(sdata, beacon); + ieee80211_set_beacon_cntdwn(sdata, beacon); } if (ifmsh->sync_ops) @@ -4874,13 +4875,13 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (offs && beacon) { int i; - for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; i++) { - u16 csa_off = beacon->csa_counter_offsets[i]; + for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; i++) { + u16 csa_off = beacon->cntdwn_counter_offsets[i]; if (!csa_off) continue; - offs->csa_counter_offs[i] = csa_off_base + csa_off; + offs->cntdwn_counter_offs[i] = csa_off_base + csa_off; } } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 6fdd0c9f865a..f2868a8a50c3 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1516,7 +1516,7 @@ static void mpls_ifdown(struct net_device *dev, int event) case NETDEV_DOWN: case NETDEV_UNREGISTER: nh_flags |= RTNH_F_DEAD; - /* fall through */ + fallthrough; case NETDEV_CHANGE: nh_flags |= RTNH_F_LINKDOWN; break; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index c8820c4156e6..2c208d2e65cd 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -384,8 +384,8 @@ mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = { [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, - [MPTCP_PM_ADDR_ATTR_ADDR6] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct in6_addr), }, + [MPTCP_PM_ADDR_ATTR_ADDR6] = + NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16 }, [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32 }, [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32 }, diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8c1d1a595701..683196225f91 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -24,8 +24,6 @@ #include "protocol.h" #include "mib.h" -#define MPTCP_SAME_STATE TCP_MAX_STATES - #if IS_ENABLED(CONFIG_MPTCP_IPV6) struct mptcp6_sock { struct mptcp_sock msk; @@ -193,7 +191,6 @@ static void mptcp_check_data_fin_ack(struct sock *sk) sk->sk_state_change(sk); break; case TCP_CLOSING: - fallthrough; case TCP_LAST_ACK: inet_sk_state_store(sk, TCP_CLOSE); sk->sk_state_change(sk); @@ -725,8 +722,10 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, if (!psize) return -EINVAL; - if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) + if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) { + iov_iter_revert(&msg->msg_iter, psize); return -ENOMEM; + } } else { offset = dfrag->offset; psize = min_t(size_t, dfrag->data_len, avail_size); @@ -737,8 +736,11 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, */ ret = do_tcp_sendpages(ssk, page, offset, psize, msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT); - if (ret <= 0) + if (ret <= 0) { + if (!retransmission) + iov_iter_revert(&msg->msg_iter, psize); return ret; + } frag_truesize += ret; if (!retransmission) { @@ -887,7 +889,6 @@ restart: goto out; } -wait_for_sndbuf: __mptcp_flush_join_list(msk); ssk = mptcp_subflow_get_send(msk); while (!sk_stream_memory_free(sk) || @@ -977,7 +978,7 @@ wait_for_sndbuf: */ mptcp_set_timeout(sk, ssk); release_sock(ssk); - goto wait_for_sndbuf; + goto restart; } } } @@ -1388,7 +1389,9 @@ static void mptcp_worker(struct work_struct *work) struct mptcp_data_frag *dfrag; u64 orig_write_seq; size_t copied = 0; - struct msghdr msg; + struct msghdr msg = { + .msg_flags = MSG_DONTWAIT, + }; long timeo = 0; lock_sock(sk); @@ -1421,7 +1424,6 @@ static void mptcp_worker(struct work_struct *work) lock_sock(ssk); - msg.msg_flags = MSG_DONTWAIT; orig_len = dfrag->data_len; orig_offset = dfrag->offset; orig_write_seq = dfrag->data_seq; @@ -1535,7 +1537,7 @@ static void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; - /* fall through */ + fallthrough; case TCP_SYN_SENT: tcp_disconnect(ssk, O_NONBLOCK); break; diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 1f387be7827b..f1be3e3f6425 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -474,7 +474,7 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp) switch (nd->state) { case ncsi_dev_state_suspend: nd->state = ncsi_dev_state_suspend_select; - /* Fall through */ + fallthrough; case ncsi_dev_state_suspend_select: ndp->pending_req_num = 1; @@ -1302,7 +1302,7 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) switch (nd->state) { case ncsi_dev_state_probe: nd->state = ncsi_dev_state_probe_deselect; - /* Fall through */ + fallthrough; case ncsi_dev_state_probe_deselect: ndp->pending_req_num = 8; diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 2c1593089ede..eb0e329f9b8d 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -29,7 +29,6 @@ if IP_VS config IP_VS_IPV6 bool "IPv6 support for IPVS" depends on IPV6 = y || IP_VS = IPV6 - select IP6_NF_IPTABLES select NF_DEFRAG_IPV6 help Add IPv6 support to IPVS. diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 678c5b14841c..8dbfd84322a8 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2508,6 +2508,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len) /* Set timeout values for (tcp tcpfin udp) */ ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg); goto out_unlock; + } else if (!len) { + /* No more commands with len == 0 below */ + ret = -EINVAL; + goto out_unlock; } usvc_compat = (struct ip_vs_service_user *)arg; @@ -2584,9 +2588,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len) break; case IP_VS_SO_SET_DELDEST: ret = ip_vs_del_dest(svc, &udest); - break; - default: - ret = -EINVAL; } out_unlock: diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 32b028853a7c..dc2e7da2742a 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -315,7 +315,7 @@ tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) switch (skb->ip_summed) { case CHECKSUM_NONE: skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); - /* fall through */ + fallthrough; case CHECKSUM_COMPLETE: #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 153d89647c87..68260d91c988 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -318,7 +318,7 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) case CHECKSUM_NONE: skb->csum = skb_checksum(skb, udphoff, skb->len - udphoff, 0); - /* fall through */ + fallthrough; case CHECKSUM_COMPLETE: #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 5b97d233f89b..234b7cab37c3 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -859,7 +859,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) out: nf_conntrack_double_unlock(hash, reply_hash); - NF_CT_STAT_INC(net, insert_failed); local_bh_enable(); return -EEXIST; } @@ -909,6 +908,7 @@ static void __nf_conntrack_insert_prepare(struct nf_conn *ct) tstamp->start = ktime_get_real_ns(); } +/* caller must hold locks to prevent concurrent changes */ static int __nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h) { @@ -922,23 +922,21 @@ static int __nf_ct_resolve_clash(struct sk_buff *skb, if (nf_ct_is_dying(ct)) return NF_DROP; - if (!atomic_inc_not_zero(&ct->ct_general.use)) - return NF_DROP; - if (((ct->status & IPS_NAT_DONE_MASK) == 0) || nf_ct_match(ct, loser_ct)) { struct net *net = nf_ct_net(ct); + nf_conntrack_get(&ct->ct_general); + nf_ct_acct_merge(ct, ctinfo, loser_ct); nf_ct_add_to_dying_list(loser_ct); nf_conntrack_put(&loser_ct->ct_general); nf_ct_set(skb, ct, ctinfo); - NF_CT_STAT_INC(net, insert_failed); + NF_CT_STAT_INC(net, clash_resolve); return NF_ACCEPT; } - nf_ct_put(ct); return NF_DROP; } @@ -998,6 +996,8 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &nf_conntrack_hash[repl_idx]); + + NF_CT_STAT_INC(net, clash_resolve); return NF_ACCEPT; } @@ -1027,10 +1027,10 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) * * Failing that, the new, unconfirmed conntrack is still added to the table * provided that the collision only occurs in the ORIGINAL direction. - * The new entry will be added after the existing one in the hash list, + * The new entry will be added only in the non-clashing REPLY direction, * so packets in the ORIGINAL direction will continue to match the existing * entry. The new entry will also have a fixed timeout so it expires -- - * due to the collision, it will not see bidirectional traffic. + * due to the collision, it will only see reply traffic. * * Returns NF_DROP if the clash could not be resolved. */ @@ -1725,10 +1725,8 @@ nf_conntrack_handle_icmp(struct nf_conn *tmpl, else return NF_ACCEPT; - if (ret <= 0) { + if (ret <= 0) NF_CT_STAT_INC_ATOMIC(state->net, error); - NF_CT_STAT_INC_ATOMIC(state->net, invalid); - } return ret; } @@ -1802,10 +1800,8 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) if (tmpl || ctinfo == IP_CT_UNTRACKED) { /* Previously seen (loopback or untracked)? Ignore. */ if ((tmpl && !nf_ct_is_template(tmpl)) || - ctinfo == IP_CT_UNTRACKED) { - NF_CT_STAT_INC_ATOMIC(state->net, ignore); + ctinfo == IP_CT_UNTRACKED) return NF_ACCEPT; - } skb->_nfct = 0; } @@ -1813,7 +1809,6 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) dataoff = get_l4proto(skb, skb_network_offset(skb), state->pf, &protonum); if (dataoff <= 0) { pr_debug("not prepared to track yet or error occurred\n"); - NF_CT_STAT_INC_ATOMIC(state->net, error); NF_CT_STAT_INC_ATOMIC(state->net, invalid); ret = NF_ACCEPT; goto out; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 832eabecfbdd..89d99f6dfd0a 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2509,7 +2509,6 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || - nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) || nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || nla_put_be32(skb, CTA_STATS_INSERT_FAILED, htonl(st->insert_failed)) || @@ -2517,7 +2516,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) || nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) || nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, - htonl(st->search_restart))) + htonl(st->search_restart)) || + nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE, + htonl(st->clash_resolve))) goto nla_put_failure; nlmsg_end(skb, nlh); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 1f44d523b512..5105d4250012 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Connection tracking support for PPTP (Point to Point Tunneling Protocol). - * PPTP is a a protocol for creating virtual private networks. + * PPTP is a protocol for creating virtual private networks. * It is a specification defined by Microsoft and some vendors * working with Microsoft. PPTP is built on top of a modified * version of the Internet Generic Routing Encapsulation Protocol. diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 4f897b14b606..810cca24b399 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -62,6 +62,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, }; +#define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 + #define sNO SCTP_CONNTRACK_NONE #define sCL SCTP_CONNTRACK_CLOSED #define sCW SCTP_CONNTRACK_COOKIE_WAIT @@ -369,6 +371,7 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, u_int32_t offset, count; unsigned int *timeouts; unsigned long map[256 / sizeof(unsigned long)] = { 0 }; + bool ignore = false; if (sctp_error(skb, dataoff, state)) return -NF_ACCEPT; @@ -427,15 +430,39 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* Sec 8.5.1 (D) */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; - } else if (sch->type == SCTP_CID_HEARTBEAT || - sch->type == SCTP_CID_HEARTBEAT_ACK) { + } else if (sch->type == SCTP_CID_HEARTBEAT) { + if (ct->proto.sctp.vtag[dir] == 0) { + pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir); + ct->proto.sctp.vtag[dir] = sh->vtag; + } else if (sh->vtag != ct->proto.sctp.vtag[dir]) { + if (test_bit(SCTP_CID_DATA, map) || ignore) + goto out_unlock; + + ct->proto.sctp.flags |= SCTP_FLAG_HEARTBEAT_VTAG_FAILED; + ct->proto.sctp.last_dir = dir; + ignore = true; + continue; + } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { + ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; + } + } else if (sch->type == SCTP_CID_HEARTBEAT_ACK) { if (ct->proto.sctp.vtag[dir] == 0) { pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir); ct->proto.sctp.vtag[dir] = sh->vtag; } else if (sh->vtag != ct->proto.sctp.vtag[dir]) { - pr_debug("Verification tag check failed\n"); - goto out_unlock; + if (test_bit(SCTP_CID_DATA, map) || ignore) + goto out_unlock; + + if ((ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) == 0 || + ct->proto.sctp.last_dir == dir) + goto out_unlock; + + ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; + ct->proto.sctp.vtag[dir] = sh->vtag; + ct->proto.sctp.vtag[!dir] = 0; + } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { + ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } } @@ -470,6 +497,10 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } spin_unlock_bh(&ct->lock); + /* allow but do not refresh timeout */ + if (ignore) + return NF_ACCEPT; + timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 6892e497781c..e8c86ee4c1c4 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1152,7 +1152,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, && (old_state == TCP_CONNTRACK_SYN_RECV || old_state == TCP_CONNTRACK_ESTABLISHED) && new_state == TCP_CONNTRACK_ESTABLISHED) { - /* Set ASSURED if we see see valid ack in ESTABLISHED + /* Set ASSURED if we see valid ack in ESTABLISHED after SYN_RECV or a valid answer for a picked up connection. */ set_bit(IPS_ASSURED_BIT, &ct->status); diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 760ca2422816..af402f458ee0 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -81,18 +81,6 @@ static bool udp_error(struct sk_buff *skb, return false; } -static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct, - struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - u32 extra_jiffies) -{ - if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY && - ct->status & IPS_NAT_CLASH)) - nf_ct_kill(ct); - else - nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies); -} - /* Returns verdict for packet, and may modify conntracktype */ int nf_conntrack_udp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -124,12 +112,15 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, extra); + /* never set ASSURED for IPS_NAT_CLASH, they time out soon */ + if (unlikely((ct->status & IPS_NAT_CLASH))) + return NF_ACCEPT; + /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, - timeouts[UDP_CT_UNREPLIED]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } @@ -206,12 +197,15 @@ int nf_conntrack_udplite_packet(struct nf_conn *ct, if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_REPLIED]); + + if (unlikely((ct->status & IPS_NAT_CLASH))) + return NF_ACCEPT; + /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, - timeouts[UDP_CT_UNREPLIED]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index a604f43e3e6b..0ff39740797d 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -435,11 +435,11 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", nr_conntracks, - 0, + st->clash_resolve, /* was: searched */ st->found, 0, st->invalid, - st->ignore, + 0, 0, 0, st->insert, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d878e34e3354..84c0c1aaae99 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -650,6 +650,8 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_TABLE_FLAGS] = { .type = NLA_U32 }, [NFTA_TABLE_HANDLE] = { .type = NLA_U64 }, + [NFTA_TABLE_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN } }; static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, @@ -676,6 +678,11 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, NFTA_TABLE_PAD)) goto nla_put_failure; + if (table->udata) { + if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata)) + goto nla_put_failure; + } + nlmsg_end(skb, nlh); return 0; @@ -815,11 +822,11 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0, family, table); if (err < 0) - goto err; + goto err_fill_table_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_table_info: kfree_skb(skb2); return err; } @@ -977,8 +984,9 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, int family = nfmsg->nfgen_family; const struct nlattr *attr; struct nft_table *table; - u32 flags = 0; struct nft_ctx ctx; + u32 flags = 0; + u16 udlen = 0; int err; lockdep_assert_held(&net->nft.commit_mutex); @@ -1014,6 +1022,16 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (table->name == NULL) goto err_strdup; + if (nla[NFTA_TABLE_USERDATA]) { + udlen = nla_len(nla[NFTA_TABLE_USERDATA]); + table->udata = kzalloc(udlen, GFP_KERNEL); + if (table->udata == NULL) + goto err_table_udata; + + nla_memcpy(table->udata, nla[NFTA_TABLE_USERDATA], udlen); + table->udlen = udlen; + } + err = rhltable_init(&table->chains_ht, &nft_chain_ht_params); if (err) goto err_chain_ht; @@ -1036,6 +1054,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, err_trans: rhltable_destroy(&table->chains_ht); err_chain_ht: + kfree(table->udata); +err_table_udata: kfree(table->name); err_strdup: kfree(table); @@ -1563,11 +1583,11 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0, family, table, chain); if (err < 0) - goto err; + goto err_fill_chain_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_chain_info: kfree_skb(skb2); return err; } @@ -2018,8 +2038,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (nla[NFTA_CHAIN_NAME]) { chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); } else { - if (!(flags & NFT_CHAIN_BINDING)) - return -EINVAL; + if (!(flags & NFT_CHAIN_BINDING)) { + err = -EINVAL; + goto err1; + } snprintf(name, sizeof(name), "__chain%llu", ++chain_id); chain->name = kstrdup(name, GFP_KERNEL); @@ -3006,11 +3028,11 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, family, table, chain, rule, NULL); if (err < 0) - goto err; + goto err_fill_rule_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_rule_info: kfree_skb(skb2); return err; } @@ -3768,7 +3790,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; } - if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) + if (set->udata && + nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_SET_DESC); @@ -3965,11 +3988,11 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, err = nf_tables_fill_set(skb2, &ctx, set, NFT_MSG_NEWSET, 0); if (err < 0) - goto err; + goto err_fill_set_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_set_info: kfree_skb(skb2); return err; } @@ -4857,24 +4880,18 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) - goto err1; + return err; err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, NFT_MSG_NEWSETELEM, 0, set, &elem); if (err < 0) - goto err2; + goto err_fill_setelem; - err = nfnetlink_unicast(skb, ctx->net, ctx->portid, MSG_DONTWAIT); - /* This avoids a loop in nfnetlink. */ - if (err < 0) - goto err1; + return nfnetlink_unicast(skb, ctx->net, ctx->portid); - return 0; -err2: +err_fill_setelem: kfree_skb(skb); -err1: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return err; } /* called with rcu_read_lock held */ @@ -5733,6 +5750,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = { [NFTA_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_OBJ_DATA] = { .type = NLA_NESTED }, [NFTA_OBJ_HANDLE] = { .type = NLA_U64}, + [NFTA_OBJ_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN }, }; static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, @@ -5880,6 +5899,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, struct nft_object *obj; struct nft_ctx ctx; u32 objtype; + u16 udlen; int err; if (!nla[NFTA_OBJ_TYPE] || @@ -5924,7 +5944,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { err = PTR_ERR(obj); - goto err1; + goto err_init; } obj->key.table = table; obj->handle = nf_tables_alloc_handle(table); @@ -5932,32 +5952,44 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL); if (!obj->key.name) { err = -ENOMEM; - goto err2; + goto err_strdup; + } + + if (nla[NFTA_OBJ_USERDATA]) { + udlen = nla_len(nla[NFTA_OBJ_USERDATA]); + obj->udata = kzalloc(udlen, GFP_KERNEL); + if (obj->udata == NULL) + goto err_userdata; + + nla_memcpy(obj->udata, nla[NFTA_OBJ_USERDATA], udlen); + obj->udlen = udlen; } err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj); if (err < 0) - goto err3; + goto err_trans; err = rhltable_insert(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); if (err < 0) - goto err4; + goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); table->use++; return 0; -err4: +err_obj_ht: /* queued in transaction log */ INIT_LIST_HEAD(&obj->list); return err; -err3: +err_trans: kfree(obj->key.name); -err2: +err_userdata: + kfree(obj->udata); +err_strdup: if (obj->ops->destroy) obj->ops->destroy(&ctx, obj); kfree(obj); -err1: +err_init: module_put(type->owner); return err; } @@ -5989,6 +6021,10 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, NFTA_OBJ_PAD)) goto nla_put_failure; + if (obj->udata && + nla_put(skb, NFTA_OBJ_USERDATA, obj->udlen, obj->udata)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -6179,10 +6215,11 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, family, table, obj, reset); if (err < 0) - goto err; + goto err_fill_obj_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_obj_info: kfree_skb(skb2); return err; } @@ -7042,10 +7079,11 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, NFT_MSG_NEWFLOWTABLE, 0, family, flowtable, &flowtable->hook_list); if (err < 0) - goto err; + goto err_fill_flowtable_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_flowtable_info: kfree_skb(skb2); return err; } @@ -7231,10 +7269,11 @@ static int nf_tables_getgen(struct net *net, struct sock *nlsk, err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid, nlh->nlmsg_seq); if (err < 0) - goto err; + goto err_fill_gen_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_gen_info: kfree_skb(skb2); return err; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 5f24edf95830..3a2e64e13b22 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -149,10 +149,15 @@ int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error) } EXPORT_SYMBOL_GPL(nfnetlink_set_err); -int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, - int flags) +int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid) { - return netlink_unicast(net->nfnl, skb, portid, flags); + int err; + + err = nlmsg_unicast(net->nfnl, skb, portid); + if (err == -EAGAIN) + err = -ENOBUFS; + + return err; } EXPORT_SYMBOL_GPL(nfnetlink_unicast); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index f02992419850..b35e8d9a5b37 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -356,8 +356,7 @@ __nfulnl_send(struct nfulnl_instance *inst) goto out; } } - nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, - MSG_DONTWAIT); + nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid); out: inst->qlen = 0; inst->skb = NULL; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index dadfc06245a3..d1d8bca03b4f 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -681,7 +681,7 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, *packet_id_ptr = htonl(entry->id); /* nfnetlink_unicast will either free the nskb or add it to a socket */ - err = nfnetlink_unicast(nskb, net, queue->peer_portid, MSG_DONTWAIT); + err = nfnetlink_unicast(nskb, net, queue->peer_portid); if (err < 0) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 6428856ccbec..8e56f353ff35 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -27,8 +27,6 @@ struct nft_xt_match_priv { void *info; }; -static refcount_t nft_compat_pending_destroy = REFCOUNT_INIT(1); - static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, const char *tablename) { @@ -215,6 +213,17 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return 0; } +static void nft_compat_wait_for_destructors(void) +{ + /* xtables matches or targets can have side effects, e.g. + * creation/destruction of /proc files. + * The xt ->destroy functions are run asynchronously from + * work queue. If we have pending invocations we thus + * need to wait for those to finish. + */ + nf_tables_trans_destroy_flush_work(); +} + static int nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -238,14 +247,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv); - /* xtables matches or targets can have side effects, e.g. - * creation/destruction of /proc files. - * The xt ->destroy functions are run asynchronously from - * work queue. If we have pending invocations we thus - * need to wait for those to finish. - */ - if (refcount_read(&nft_compat_pending_destroy) > 1) - nf_tables_trans_destroy_flush_work(); + nft_compat_wait_for_destructors(); ret = xt_check_target(&par, size, proto, inv); if (ret < 0) @@ -260,7 +262,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, static void __nft_mt_tg_destroy(struct module *me, const struct nft_expr *expr) { - refcount_dec(&nft_compat_pending_destroy); module_put(me); kfree(expr->ops); } @@ -468,6 +469,8 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); + nft_compat_wait_for_destructors(); + return xt_check_match(&par, size, proto, inv); } @@ -716,14 +719,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { static struct nft_expr_type nft_match_type; -static void nft_mt_tg_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - enum nft_trans_phase phase) -{ - if (phase == NFT_TRANS_COMMIT) - refcount_inc(&nft_compat_pending_destroy); -} - static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -762,7 +757,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, ops->type = &nft_match_type; ops->eval = nft_match_eval; ops->init = nft_match_init; - ops->deactivate = nft_mt_tg_deactivate, ops->destroy = nft_match_destroy; ops->dump = nft_match_dump; ops->validate = nft_match_validate; @@ -853,7 +847,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); ops->init = nft_target_init; ops->destroy = nft_target_destroy; - ops->deactivate = nft_mt_tg_deactivate, ops->dump = nft_target_dump; ops->validate = nft_target_validate; ops->data = target; @@ -917,8 +910,6 @@ static void __exit nft_compat_module_exit(void) nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); - - WARN_ON_ONCE(refcount_read(&nft_compat_pending_destroy) != 1); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 07782836fad6..3c48cdc8935d 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -44,7 +44,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; @@ -141,7 +141,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr, err = ipv4_find_option(nft_net(pkt), skb, &offset, priv->type); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 3b9b97aa4b32..3a6c84fb2c90 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -102,7 +102,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || - ct->status & IPS_SEQ_ADJUST) + ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH)) goto out; if (!nf_ct_is_confirmed(ct)) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index ed7cb9f747f6..7a2e59638499 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -87,7 +87,9 @@ void nft_payload_eval(const struct nft_expr *expr, u32 *dest = ®s->data[priv->dreg]; int offset; - dest[priv->len / NFT_REG32_SIZE] = 0; + if (priv->len % NFT_REG32_SIZE) + dest[priv->len / NFT_REG32_SIZE] = 0; + switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: if (!skb_mac_header_was_set(skb)) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 4b2834fd17b2..217ab3644c25 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -218,11 +218,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_set_ext **ext) { + bool overlap = false, dup_end_left = false, dup_end_right = false; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); struct nft_rbtree_elem *rbe; struct rb_node *parent, **p; - bool overlap = false; int d; /* Detect overlaps as we descend the tree. Set the flag in these cases: @@ -238,24 +238,44 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, * * b1. _ _ __>| !_ _ __| (insert end before existing start) * b2. _ _ ___| !_ _ _>| (insert end after existing start) - * b3. _ _ ___! >|_ _ __| (insert start after existing end) + * b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf) + * '--' no nodes falling in this range + * b4. >|_ _ ! (insert start before existing start) * * Case a3. resolves to b3.: * - if the inserted start element is the leftmost, because the '0' * element in the tree serves as end element - * - otherwise, if an existing end is found. Note that end elements are - * always inserted after corresponding start elements. + * - otherwise, if an existing end is found immediately to the left. If + * there are existing nodes in between, we need to further descend the + * tree before we can conclude the new start isn't causing an overlap + * + * or to b4., which, preceded by a3., means we already traversed one or + * more existing intervals entirely, from the right. * * For a new, rightmost pair of elements, we'll hit cases b3. and b2., * in that order. * * The flag is also cleared in two special cases: * - * b4. |__ _ _!|<_ _ _ (insert start right before existing end) - * b5. |__ _ >|!__ _ _ (insert end right after existing start) + * b5. |__ _ _!|<_ _ _ (insert start right before existing end) + * b6. |__ _ >|!__ _ _ (insert end right after existing start) * * which always happen as last step and imply that no further * overlapping is possible. + * + * Another special case comes from the fact that start elements matching + * an already existing start element are allowed: insertion is not + * performed but we return -EEXIST in that case, and the error will be + * cleared by the caller if NLM_F_EXCL is not present in the request. + * This way, request for insertion of an exact overlap isn't reported as + * error to userspace if not desired. + * + * However, if the existing start matches a pre-existing start, but the + * end element doesn't match the corresponding pre-existing end element, + * we need to report a partial overlap. This is a local condition that + * can be noticed without need for a tracking flag, by checking for a + * local duplicated end for a corresponding start, from left and right, + * separately. */ parent = NULL; @@ -272,26 +292,41 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (nft_rbtree_interval_start(new)) { if (nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) + !nft_set_elem_expired(&rbe->ext) && !*p) overlap = false; } else { + if (dup_end_left && !*p) + return -ENOTEMPTY; + overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, genmask) && !nft_set_elem_expired(&rbe->ext); + + if (overlap) { + dup_end_right = true; + continue; + } } } else if (d > 0) { p = &parent->rb_right; if (nft_rbtree_interval_end(new)) { + if (dup_end_right && !*p) + return -ENOTEMPTY; + overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, genmask) && !nft_set_elem_expired(&rbe->ext); - } else if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask) && + + if (overlap) { + dup_end_left = true; + continue; + } + } else if (nft_set_elem_active(&rbe->ext, genmask) && !nft_set_elem_expired(&rbe->ext)) { - overlap = true; + overlap = nft_rbtree_interval_end(rbe); } } else { if (nft_rbtree_interval_end(rbe) && @@ -316,6 +351,8 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, p = &parent->rb_left; } } + + dup_end_left = dup_end_right = false; } if (overlap) diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 637ce3e8c575..a28aca5124ce 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -14,6 +14,25 @@ struct nft_socket { }; }; +static void nft_socket_wildcard(const struct nft_pktinfo *pkt, + struct nft_regs *regs, struct sock *sk, + u32 *dest) +{ + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + nft_reg_store8(dest, inet_sk(sk)->inet_rcv_saddr == 0); + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + nft_reg_store8(dest, ipv6_addr_any(&sk->sk_v6_rcv_saddr)); + break; +#endif + default: + regs->verdict.code = NFT_BREAK; + return; + } +} + static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -59,6 +78,13 @@ static void nft_socket_eval(const struct nft_expr *expr, return; } break; + case NFT_SOCKET_WILDCARD: + if (!sk_fullsock(sk)) { + regs->verdict.code = NFT_BREAK; + return; + } + nft_socket_wildcard(pkt, regs, sk, dest); + break; default: WARN_ON(1); regs->verdict.code = NFT_BREAK; @@ -97,6 +123,7 @@ static int nft_socket_init(const struct nft_ctx *ctx, priv->key = ntohl(nla_get_u32(tb[NFTA_SOCKET_KEY])); switch(priv->key) { case NFT_SOCKET_TRANSPARENT: + case NFT_SOCKET_WILDCARD: len = sizeof(u8); break; case NFT_SOCKET_MARK: diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c index 713fb38541df..8928ec56c388 100644 --- a/net/netfilter/xt_HMARK.c +++ b/net/netfilter/xt_HMARK.c @@ -276,7 +276,7 @@ hmark_pkt_set_htuple_ipv4(const struct sk_buff *skb, struct hmark_tuple *t, return 0; /* follow-up fragments don't contain ports, skip all fragments */ - if (ip->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(ip)) return 0; hmark_set_tuple_ports(skb, (ip->ihl * 4) + nhoff, t, info); diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 19bef176145e..606411869698 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -640,7 +640,7 @@ static void __net_exit recent_proc_net_exit(struct net *net) struct recent_table *t; /* recent_net_exit() is called before recent_mt_destroy(). Make sure - * that the parent xt_recent proc entry is is empty before trying to + * that the parent xt_recent proc entry is empty before trying to * remove it. */ spin_lock_bh(&recent_lock); diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index 249da67d50a2..1a98247ab148 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -426,7 +426,7 @@ void calipso_doi_free(struct calipso_doi *doi_def) /** * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine * @doi: the DOI value - * @audit_secid: the LSM secid to use in the audit message + * @audit_info: NetLabel audit information * * Description: * Removes a DOI definition from the CALIPSO engine. The NetLabel routines will @@ -595,7 +595,7 @@ int calipso_req_setattr(struct request_sock *req, /** * calipso_req_delattr - Delete the CALIPSO option from a request socket - * @reg: the request socket + * @req: the request socket * * Description: * Removes the CALIPSO option from a request socket, if present. diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index d07de2c0fbc7..dc8c39f51f7d 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -85,6 +85,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry) kfree(netlbl_domhsh_addr6_entry(iter6)); } #endif /* IPv6 */ + kfree(ptr->def.addrsel); } kfree(ptr->domain); kfree(ptr); @@ -537,6 +538,8 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, goto add_return; } #endif /* IPv6 */ + /* cleanup the new entry since we've moved everything over */ + netlbl_domhsh_free_entry(&entry->rcu); } else ret_val = -EINVAL; @@ -580,6 +583,12 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, { int ret_val = 0; struct audit_buffer *audit_buf; + struct netlbl_af4list *iter4; + struct netlbl_domaddr4_map *map4; +#if IS_ENABLED(CONFIG_IPV6) + struct netlbl_af6list *iter6; + struct netlbl_domaddr6_map *map6; +#endif /* IPv6 */ if (entry == NULL) return -ENOENT; @@ -597,49 +606,40 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, ret_val = -ENOENT; spin_unlock(&netlbl_domhsh_lock); + if (ret_val) + return ret_val; + audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info); if (audit_buf != NULL) { audit_log_format(audit_buf, - " nlbl_domain=%s res=%u", - entry->domain ? entry->domain : "(default)", - ret_val == 0 ? 1 : 0); + " nlbl_domain=%s res=1", + entry->domain ? entry->domain : "(default)"); audit_log_end(audit_buf); } - if (ret_val == 0) { - struct netlbl_af4list *iter4; - struct netlbl_domaddr4_map *map4; -#if IS_ENABLED(CONFIG_IPV6) - struct netlbl_af6list *iter6; - struct netlbl_domaddr6_map *map6; -#endif /* IPv6 */ - - switch (entry->def.type) { - case NETLBL_NLTYPE_ADDRSELECT: - netlbl_af4list_foreach_rcu(iter4, - &entry->def.addrsel->list4) { - map4 = netlbl_domhsh_addr4_entry(iter4); - cipso_v4_doi_putdef(map4->def.cipso); - } + switch (entry->def.type) { + case NETLBL_NLTYPE_ADDRSELECT: + netlbl_af4list_foreach_rcu(iter4, &entry->def.addrsel->list4) { + map4 = netlbl_domhsh_addr4_entry(iter4); + cipso_v4_doi_putdef(map4->def.cipso); + } #if IS_ENABLED(CONFIG_IPV6) - netlbl_af6list_foreach_rcu(iter6, - &entry->def.addrsel->list6) { - map6 = netlbl_domhsh_addr6_entry(iter6); - calipso_doi_putdef(map6->def.calipso); - } + netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) { + map6 = netlbl_domhsh_addr6_entry(iter6); + calipso_doi_putdef(map6->def.calipso); + } #endif /* IPv6 */ - break; - case NETLBL_NLTYPE_CIPSOV4: - cipso_v4_doi_putdef(entry->def.cipso); - break; + break; + case NETLBL_NLTYPE_CIPSOV4: + cipso_v4_doi_putdef(entry->def.cipso); + break; #if IS_ENABLED(CONFIG_IPV6) - case NETLBL_NLTYPE_CALIPSO: - calipso_doi_putdef(entry->def.calipso); - break; + case NETLBL_NLTYPE_CALIPSO: + calipso_doi_putdef(entry->def.calipso); + break; #endif /* IPv6 */ - } - call_rcu(&entry->rcu, netlbl_domhsh_free_entry); } + call_rcu(&entry->rcu, netlbl_domhsh_free_entry); return ret_val; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b5f30d7d30d0..f9efd2c1cb50 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -353,7 +353,7 @@ static void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); - if (skb_queue_empty(&sk->sk_receive_queue)) + if (skb_queue_empty_lockless(&sk->sk_receive_queue)) clear_bit(NETLINK_S_CONGESTED, &nlk->state); if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); @@ -848,7 +848,7 @@ retry: * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap in the user namespace @user_ns. + * message has the capability @cap in the user namespace @user_ns. */ bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) @@ -867,7 +867,7 @@ EXPORT_SYMBOL(__netlink_ns_capable); * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap in the user namespace @user_ns. + * message has the capability @cap in the user namespace @user_ns. */ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *user_ns, int cap) @@ -883,7 +883,7 @@ EXPORT_SYMBOL(netlink_ns_capable); * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap in all user namespaces. + * message has the capability @cap in all user namespaces. */ bool netlink_capable(const struct sk_buff *skb, int cap) { @@ -898,7 +898,7 @@ EXPORT_SYMBOL(netlink_capable); * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap over the network namespace of + * message has the capability @cap over the network namespace of * the socket we received the message from. */ bool netlink_net_capable(const struct sk_buff *skb, int cap) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 1eb65a7a27fd..3a718e327515 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -222,7 +222,7 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) family->mcgrp_offset = first_id; - /* if still initializing, can't and don't need to to realloc bitmaps */ + /* if still initializing, can't and don't need to realloc bitmaps */ if (!init_net.genl_sock) return 0; diff --git a/net/netlink/policy.c b/net/netlink/policy.c index f6491853c797..62f977fa645a 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -51,6 +51,9 @@ static int add_policy(struct nl_policy_dump **statep, if (!state) return -ENOMEM; + memset(&state->policies[state->n_alloc], 0, + flex_array_size(state, policies, n_alloc - state->n_alloc)); + state->policies[state->n_alloc].policy = policy; state->policies[state->n_alloc].maxtype = maxtype; state->n_alloc = n_alloc; @@ -185,7 +188,7 @@ send_attribute: goto next; case NLA_NESTED: type = NL_ATTR_TYPE_NESTED; - /* fall through */ + fallthrough; case NLA_NESTED_ARRAY: if (pt->type == NLA_NESTED_ARRAY) type = NL_ATTR_TYPE_NESTED_ARRAY; @@ -251,12 +254,6 @@ send_attribute: pt->bitfield32_valid)) goto nla_put_failure; break; - case NLA_EXACT_LEN: - type = NL_ATTR_TYPE_BINARY; - if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len) || - nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, pt->len)) - goto nla_put_failure; - break; case NLA_STRING: case NLA_NUL_STRING: case NLA_BINARY: @@ -266,14 +263,27 @@ send_attribute: type = NL_ATTR_TYPE_NUL_STRING; else type = NL_ATTR_TYPE_BINARY; - if (pt->len && nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, - pt->len)) - goto nla_put_failure; - break; - case NLA_MIN_LEN: - type = NL_ATTR_TYPE_BINARY; - if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len)) + + if (pt->validation_type == NLA_VALIDATE_RANGE || + pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG) { + struct netlink_range_validation range; + + nla_get_range_unsigned(pt, &range); + + if (range.min && + nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, + range.min)) + goto nla_put_failure; + + if (range.max < U16_MAX && + nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, + range.max)) + goto nla_put_failure; + } else if (pt->len && + nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, + pt->len)) { goto nla_put_failure; + } break; case NLA_FLAG: type = NL_ATTR_TYPE_FLAG; diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c index 2bef3779f893..69e58906c32b 100644 --- a/net/netrom/nr_in.c +++ b/net/netrom/nr_in.c @@ -122,7 +122,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb, case NR_DISCREQ: nr_write_internal(sk, NR_DISCACK); - /* fall through */ + fallthrough; case NR_DISCACK: nr_disconnect(sk, 0); break; diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 0891ee02ca4f..78da5eab252a 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -263,7 +263,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, case 3: re_sort_routes(nr_node, 0, 1); re_sort_routes(nr_node, 1, 2); - /* fall through */ + fallthrough; case 2: re_sort_routes(nr_node, 0, 1); case 1: @@ -356,7 +356,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n switch (i) { case 0: nr_node->routes[0] = nr_node->routes[1]; - /* fall through */ + fallthrough; case 1: nr_node->routes[1] = nr_node->routes[2]; case 2: @@ -479,7 +479,7 @@ static int nr_dec_obs(void) switch (i) { case 0: s->routes[0] = s->routes[1]; - /* Fallthrough */ + fallthrough; case 1: s->routes[1] = s->routes[2]; case 2: @@ -526,7 +526,7 @@ void nr_rt_device_down(struct net_device *dev) switch (i) { case 0: t->routes[0] = t->routes[1]; - /* fall through */ + fallthrough; case 1: t->routes[1] = t->routes[2]; case 2: diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index 304b1a9bb18a..5971fb6f51cc 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -38,9 +38,6 @@ #define DIGITAL_GB_BIT 0x02 -#define DIGITAL_NFC_DEP_REQ_RES_HEADROOM 2 /* SoD: [SB (NFC-A)] + LEN */ -#define DIGITAL_NFC_DEP_REQ_RES_TAILROOM 2 /* EoD: 2-byte CRC */ - #define DIGITAL_NFC_DEP_PFB_TYPE(pfb) ((pfb) & 0xE0) #define DIGITAL_NFC_DEP_PFB_TIMEOUT_BIT 0x10 diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2611657f40ca..855f2c155956 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -9,7 +9,6 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/openvswitch.h> -#include <linux/netfilter_ipv6.h> #include <linux/sctp.h> #include <linux/tcp.h> #include <linux/udp.h> @@ -742,7 +741,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb) +static int ovs_vport_output(struct net *net, struct sock *sk, + struct sk_buff *skb) { struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage); struct vport *vport = data->vport; @@ -848,13 +848,9 @@ static void ovs_fragment(struct net *net, struct vport *vport, ip_do_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else if (key->eth.type == htons(ETH_P_IPV6)) { - const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); unsigned long orig_dst; struct rt6_info ovs_rt; - if (!v6ops) - goto err; - prepare_frag(vport, skb, orig_network_offset, ovs_key_mac_proto(key)); memset(&ovs_rt, 0, sizeof(ovs_rt)); @@ -866,7 +862,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, skb_dst_set_noref(skb, &ovs_rt.dst); IP6CB(skb)->frag_max_size = mru; - v6ops->fragment(net, skb->sk, skb, ovs_vport_output); + ipv6_stub->ipv6_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else { WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", @@ -925,7 +921,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, upcall.mru = OVS_CB(skb)->mru; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; - a = nla_next(a, &rem)) { + a = nla_next(a, &rem)) { switch (nla_type(a)) { case OVS_USERSPACE_ATTR_USERDATA: upcall.userdata = a; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 98d393e70de3..a3f1204f1ed2 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -778,7 +778,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, } } /* Non-ICMP, fall thru to initialize if needed. */ - /* fall through */ + fallthrough; case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. @@ -1540,7 +1540,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, switch (type) { case OVS_CT_ATTR_FORCE_COMMIT: info->force = true; - /* fall through. */ + fallthrough; case OVS_CT_ATTR_COMMIT: info->commit = true; break; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 6e47ef7ef036..00df39b736ed 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -182,7 +182,7 @@ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) head = vport_hash_bucket(dp, port_no); hlist_for_each_entry_rcu(vport, head, dp_hash_node, - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { if (vport->port_no == port_no) return vport; } @@ -254,7 +254,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) error = ovs_execute_actions(dp, skb, sf_acts, key); if (unlikely(error)) net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n", - ovs_dp_name(dp), error); + ovs_dp_name(dp), error); stats_counter = &stats->n_hit; @@ -302,7 +302,7 @@ err: static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_key *key, const struct dp_upcall_info *upcall_info, - uint32_t cutlen) + uint32_t cutlen) { unsigned int gso_type = skb_shinfo(skb)->gso_type; struct sw_flow_key later_key; @@ -1080,11 +1080,12 @@ error: } /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */ -static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net, - const struct nlattr *a, - const struct sw_flow_key *key, - const struct sw_flow_mask *mask, - bool log) +static noinline_for_stack +struct sw_flow_actions *get_flow_actions(struct net *net, + const struct nlattr *a, + const struct sw_flow_key *key, + const struct sw_flow_mask *mask, + bool log) { struct sw_flow_actions *acts; struct sw_flow_key masked_key; @@ -1383,7 +1384,8 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_flow_genl_family, reply, info); } else { - netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply)); + netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, + PTR_ERR(reply)); } } @@ -1513,7 +1515,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, int err; ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family, - flags, cmd); + flags, cmd); if (!ovs_header) goto error; @@ -1572,11 +1574,13 @@ static struct datapath *lookup_datapath(struct net *net, return dp ? dp : ERR_PTR(-ENODEV); } -static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info) +static void ovs_dp_reset_user_features(struct sk_buff *skb, + struct genl_info *info) { struct datapath *dp; - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), info->userhdr, + info->attrs); if (IS_ERR(dp)) return; @@ -2075,7 +2079,7 @@ static unsigned int ovs_get_max_headroom(struct datapath *dp) for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { dev = vport->dev; dev_headroom = netdev_get_fwd_headroom(dev); if (dev_headroom > max_headroom) @@ -2093,10 +2097,11 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) int i; dp->max_headroom = new_headroom; - for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) + for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, - lockdep_ovsl_is_held()) + lockdep_ovsl_is_held()) netdev_set_rx_headroom(vport->dev, new_headroom); + } } static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) @@ -2476,13 +2481,19 @@ error: static int __net_init ovs_init_net(struct net *net) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + int err; INIT_LIST_HEAD(&ovs_net->dps); INIT_WORK(&ovs_net->dp_notify_work, ovs_dp_notify_wq); INIT_DELAYED_WORK(&ovs_net->masks_rebalance, ovs_dp_masks_rebalance); + + err = ovs_ct_init(net); + if (err) + return err; + schedule_delayed_work(&ovs_net->masks_rebalance, msecs_to_jiffies(DP_MASKS_REBALANCE_INTERVAL)); - return ovs_ct_init(net); + return 0; } static void __net_exit list_vports_from_net(struct net *net, struct net *dnet, @@ -2551,7 +2562,8 @@ static int __init dp_init(void) { int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > + sizeof_field(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 03942c30d83e..b03d142ec82e 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -675,7 +675,7 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) case -EINVAL: memset(&key->ip, 0, sizeof(key->ip)); memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr)); - /* fall-through */ + fallthrough; case -EPROTO: skb->transport_header = skb->network_header; error = 0; diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index e2235849a57e..87c286ad660e 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -111,12 +111,16 @@ static void flow_free(struct sw_flow *flow) if (ovs_identifier_is_key(&flow->id)) kfree(flow->id.unmasked_key); if (flow->sf_acts) - ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts); + ovs_nla_free_flow_actions((struct sw_flow_actions __force *) + flow->sf_acts); /* We open code this to make sure cpu 0 is always considered */ - for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) + for (cpu = 0; cpu < nr_cpu_ids; + cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, (struct sw_flow_stats __force *)flow->stats[cpu]); + } + kmem_cache_free(flow_cache, flow); } @@ -164,7 +168,6 @@ static struct table_instance *table_instance_alloc(int new_size) ti->n_buckets = new_size; ti->node_ver = 0; - ti->keep_flows = false; get_random_bytes(&ti->hash_seed, sizeof(u32)); return ti; @@ -192,7 +195,7 @@ static void tbl_mask_array_reset_counters(struct mask_array *ma) * zero based counter we store the value at reset, and subtract it * later when processing. */ - for (i = 0; i < ma->max; i++) { + for (i = 0; i < ma->max; i++) { ma->masks_usage_zero_cntr[i] = 0; for_each_possible_cpu(cpu) { @@ -273,7 +276,7 @@ static int tbl_mask_array_add_mask(struct flow_table *tbl, if (ma_count >= ma->max) { err = tbl_mask_array_realloc(tbl, ma->max + - MASK_ARRAY_SIZE_MIN); + MASK_ARRAY_SIZE_MIN); if (err) return err; @@ -288,7 +291,7 @@ static int tbl_mask_array_add_mask(struct flow_table *tbl, BUG_ON(ovsl_dereference(ma->masks[ma_count])); rcu_assign_pointer(ma->masks[ma_count], new); - WRITE_ONCE(ma->count, ma_count +1); + WRITE_ONCE(ma->count, ma_count + 1); return 0; } @@ -309,10 +312,10 @@ static void tbl_mask_array_del_mask(struct flow_table *tbl, return; found: - WRITE_ONCE(ma->count, ma_count -1); + WRITE_ONCE(ma->count, ma_count - 1); - rcu_assign_pointer(ma->masks[i], ma->masks[ma_count -1]); - RCU_INIT_POINTER(ma->masks[ma_count -1], NULL); + rcu_assign_pointer(ma->masks[i], ma->masks[ma_count - 1]); + RCU_INIT_POINTER(ma->masks[ma_count - 1], NULL); kfree_rcu(mask, rcu); @@ -448,26 +451,23 @@ free_mask_cache: static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu) { - struct table_instance *ti = container_of(rcu, struct table_instance, rcu); + struct table_instance *ti; + ti = container_of(rcu, struct table_instance, rcu); __table_instance_destroy(ti); } static void table_instance_flow_free(struct flow_table *table, - struct table_instance *ti, - struct table_instance *ufid_ti, - struct sw_flow *flow, - bool count) + struct table_instance *ti, + struct table_instance *ufid_ti, + struct sw_flow *flow) { hlist_del_rcu(&flow->flow_table.node[ti->node_ver]); - if (count) - table->count--; + table->count--; if (ovs_identifier_is_ufid(&flow->id)) { hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]); - - if (count) - table->ufid_count--; + table->ufid_count--; } flow_mask_remove(table, flow->mask); @@ -480,22 +480,25 @@ void table_instance_flow_flush(struct flow_table *table, { int i; - if (ti->keep_flows) - return; - for (i = 0; i < ti->n_buckets; i++) { - struct sw_flow *flow; struct hlist_head *head = &ti->buckets[i]; struct hlist_node *n; + struct sw_flow *flow; hlist_for_each_entry_safe(flow, n, head, flow_table.node[ti->node_ver]) { table_instance_flow_free(table, ti, ufid_ti, - flow, false); + flow); ovs_flow_free(flow, true); } } + + if (WARN_ON(table->count != 0 || + table->ufid_count != 0)) { + table->count = 0; + table->ufid_count = 0; + } } static void table_instance_destroy(struct table_instance *ti, @@ -596,8 +599,6 @@ static void flow_table_copy_flows(struct table_instance *old, lockdep_ovsl_is_held()) table_instance_insert(new, flow); } - - old->keep_flows = true; } static struct table_instance *table_instance_rehash(struct table_instance *ti, @@ -632,8 +633,6 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table) rcu_assign_pointer(flow_table->ti, new_ti); rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti); flow_table->last_rehash = jiffies; - flow_table->count = 0; - flow_table->ufid_count = 0; table_instance_flow_flush(flow_table, old_ti, old_ufid_ti); table_instance_destroy(old_ti, old_ufid_ti); @@ -661,7 +660,7 @@ static int flow_key_start(const struct sw_flow_key *key) return 0; else return rounddown(offsetof(struct sw_flow_key, phy), - sizeof(long)); + sizeof(long)); } static bool cmp_key(const struct sw_flow_key *key1, @@ -673,7 +672,7 @@ static bool cmp_key(const struct sw_flow_key *key1, long diffs = 0; int i; - for (i = key_start; i < key_end; i += sizeof(long)) + for (i = key_start; i < key_end; i += sizeof(long)) diffs |= *cp1++ ^ *cp2++; return diffs == 0; @@ -713,7 +712,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, (*n_mask_hit)++; hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver], - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { if (flow->mask == mask && flow->flow_table.hash == hash && flow_cmp_masked_key(flow, &masked_key, &mask->range)) return flow; @@ -897,7 +896,8 @@ static bool ovs_flow_cmp_ufid(const struct sw_flow *flow, return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len); } -bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match) +bool ovs_flow_cmp(const struct sw_flow *flow, + const struct sw_flow_match *match) { if (ovs_identifier_is_ufid(&flow->id)) return flow_cmp_masked_key(flow, match->key, &match->range); @@ -916,7 +916,7 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl, hash = ufid_hash(ufid); head = find_bucket(ti, hash); hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver], - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { if (flow->ufid_table.hash == hash && ovs_flow_cmp_ufid(flow, ufid)) return flow; @@ -950,7 +950,7 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti); BUG_ON(table->count == 0); - table_instance_flow_free(table, ti, ufid_ti, flow, true); + table_instance_flow_free(table, ti, ufid_ti, flow); } static struct sw_flow_mask *mask_alloc(void) @@ -1107,7 +1107,7 @@ void ovs_flow_masks_rebalance(struct flow_table *table) if (!masks_and_count) return; - for (i = 0; i < ma->max; i++) { + for (i = 0; i < ma->max; i++) { struct sw_flow_mask *mask; unsigned int start; int cpu; diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 6e7d4ac59353..d8fb7a3a3dfd 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -53,7 +53,6 @@ struct table_instance { struct rcu_head rcu; int node_ver; u32 hash_seed; - bool keep_flows; }; struct flow_table { diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 0d44c5c013fa..82d801f063b7 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -98,7 +98,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct vport *vport; hlist_for_each_entry_rcu(vport, bucket, hash_node, - lockdep_ovsl_is_held()) + lockdep_ovsl_is_held()) if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; @@ -118,7 +118,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) * vport_free(). */ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, - const struct vport_parms *parms) + const struct vport_parms *parms) { struct vport *vport; size_t alloc_size; @@ -397,7 +397,8 @@ int ovs_vport_get_upcall_portids(const struct vport *vport, * * Returns the portid of the target socket. Must be called with rcu_read_lock. */ -u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb) +u32 ovs_vport_find_upcall_portid(const struct vport *vport, + struct sk_buff *skb) { struct vport_portids *ids; u32 ids_index; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 479c257ded73..af6c93ed9fa0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -177,7 +177,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) -#define BLOCK_PRIV(x) ((void *)((char *)(x) + BLOCK_O2PRIV(x))) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, @@ -2170,7 +2169,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; - unsigned short macoff, netoff, hdrlen; + unsigned short macoff, hdrlen; + unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; @@ -2239,6 +2239,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } macoff = netoff - maclen; } + if (netoff > USHRT_MAX) { + atomic_inc(&po->tp_drops); + goto drop_n_restore; + } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && @@ -4061,7 +4065,7 @@ static int packet_notifier(struct notifier_block *this, case NETDEV_UNREGISTER: if (po->mclist) packet_dev_mclist_delete(dev, &po->mclist); - /* fallthrough */ + fallthrough; case NETDEV_DOWN: if (dev->ifindex == po->ifindex) { diff --git a/net/phonet/pep.c b/net/phonet/pep.c index e47d09aca4af..a1525916885a 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -368,7 +368,7 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) err = -EINVAL; goto out; } - /* fall through */ + fallthrough; case PNS_PEP_DISABLE_REQ: atomic_set(&pn->tx_credits, 0); pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC); @@ -385,7 +385,7 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) case PNS_PIPE_ALIGNED_DATA: __skb_pull(skb, 1); - /* fall through */ + fallthrough; case PNS_PIPE_DATA: __skb_pull(skb, 3); /* Pipe data header */ if (!pn_flow_safe(pn->rx_fc)) { @@ -417,11 +417,11 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) err = pipe_rcv_created(sk, skb); if (err) break; - /* fall through */ + fallthrough; case PNS_PIPE_RESET_IND: if (!pn->init_enable) break; - /* fall through */ + fallthrough; case PNS_PIPE_ENABLED_IND: if (!pn_flow_safe(pn->tx_fc)) { atomic_set(&pn->tx_credits, 1); @@ -555,7 +555,7 @@ static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb) switch (hdr->message_id) { case PNS_PIPE_ALIGNED_DATA: __skb_pull(skb, 1); - /* fall through */ + fallthrough; case PNS_PIPE_DATA: __skb_pull(skb, 3); /* Pipe data header */ if (!pn_flow_safe(pn->rx_fc)) { diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index b4c0db0b7d31..90c558f89d46 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -692,23 +692,25 @@ static void qrtr_port_remove(struct qrtr_sock *ipc) */ static int qrtr_port_assign(struct qrtr_sock *ipc, int *port) { + u32 min_port; int rc; mutex_lock(&qrtr_port_lock); if (!*port) { - rc = idr_alloc(&qrtr_ports, ipc, - QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET + 1, - GFP_ATOMIC); - if (rc >= 0) - *port = rc; + min_port = QRTR_MIN_EPH_SOCKET; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, QRTR_MAX_EPH_SOCKET, GFP_ATOMIC); + if (!rc) + *port = min_port; } else if (*port < QRTR_MIN_EPH_SOCKET && !capable(CAP_NET_ADMIN)) { rc = -EACCES; } else if (*port == QRTR_PORT_CTRL) { - rc = idr_alloc(&qrtr_ports, ipc, 0, 1, GFP_ATOMIC); + min_port = 0; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, 0, GFP_ATOMIC); } else { - rc = idr_alloc(&qrtr_ports, ipc, *port, *port + 1, GFP_ATOMIC); - if (rc >= 0) - *port = rc; + min_port = *port; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, *port, GFP_ATOMIC); + if (!rc) + *port = min_port; } mutex_unlock(&qrtr_port_lock); diff --git a/net/rds/send.c b/net/rds/send.c index 9a529a01cdc6..985d0b7713ac 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -934,7 +934,7 @@ static int rds_rm_size(struct msghdr *msg, int num_sgs, case RDS_CMSG_ZCOPY_COOKIE: zcopy_cookie = true; - /* fall through */ + fallthrough; case RDS_CMSG_RDMA_DEST: case RDS_CMSG_RDMA_MAP: diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c index 0d4fab2be82b..6af786d66b03 100644 --- a/net/rose/rose_in.c +++ b/net/rose/rose_in.c @@ -216,7 +216,7 @@ static int rose_state4_machine(struct sock *sk, struct sk_buff *skb, int framety switch (frametype) { case ROSE_RESET_REQUEST: rose_write_internal(sk, ROSE_RESET_CONFIRMATION); - /* fall through */ + fallthrough; case ROSE_RESET_CONFIRMATION: rose_stop_timer(sk); rose_start_idletimer(sk); diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 5277631fa14c..6e35703ff353 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -343,7 +343,7 @@ static int rose_del_node(struct rose_route_struct *rose_route, case 0: rose_node->neighbour[0] = rose_node->neighbour[1]; - /* fall through */ + fallthrough; case 1: rose_node->neighbour[1] = rose_node->neighbour[2]; @@ -505,7 +505,7 @@ void rose_rt_device_down(struct net_device *dev) switch (i) { case 0: t->neighbour[0] = t->neighbour[1]; - /* fall through */ + fallthrough; case 1: t->neighbour[1] = t->neighbour[2]; case 2: diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index e6725a6de015..0a2f4817ec6c 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -246,7 +246,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) ret = 0; break; } - /* Fall through */ + fallthrough; default: ret = -EBUSY; break; @@ -308,9 +308,10 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, key = NULL; /* a no-security key */ memset(&p, 0, sizeof(p)); - p.user_call_ID = user_call_ID; - p.tx_total_len = tx_total_len; - p.interruptibility = interruptibility; + p.user_call_ID = user_call_ID; + p.tx_total_len = tx_total_len; + p.interruptibility = interruptibility; + p.kernel = true; memset(&cp, 0, sizeof(cp)); cp.local = rx->local; @@ -545,7 +546,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) rx->local = local; rx->sk.sk_state = RXRPC_CLIENT_BOUND; - /* Fall through */ + fallthrough; case RXRPC_CLIENT_BOUND: if (!m->msg_name && @@ -553,7 +554,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) m->msg_name = &rx->connect_srx; m->msg_namelen = sizeof(rx->connect_srx); } - /* Fall through */ + fallthrough; case RXRPC_SERVER_BOUND: case RXRPC_SERVER_LISTENING: ret = rxrpc_do_sendmsg(rx, m, len); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 6d29a3603a3e..cd5a80b34738 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -76,14 +76,12 @@ struct rxrpc_net { struct work_struct service_conn_reaper; struct timer_list service_conn_reap_timer; - unsigned int nr_client_conns; - unsigned int nr_active_client_conns; - bool kill_all_client_conns; bool live; + + bool kill_all_client_conns; + atomic_t nr_client_conns; spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ spinlock_t client_conn_discard_lock; /* Prevent multiple discarders */ - struct list_head waiting_client_conns; - struct list_head active_client_conns; struct list_head idle_client_conns; struct work_struct client_conn_reaper; struct timer_list client_conn_reap_timer; @@ -275,8 +273,8 @@ struct rxrpc_local { struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ - struct rb_root client_conns; /* Client connections by socket params */ - spinlock_t client_conns_lock; /* Lock for client_conns */ + struct rb_root client_bundles; /* Client connection bundles by socket params */ + spinlock_t client_bundles_lock; /* Lock for client_bundles */ spinlock_t lock; /* access lock */ rwlock_t services_lock; /* lock for services list */ int debug_id; /* debug ID for printks */ @@ -353,10 +351,7 @@ struct rxrpc_conn_parameters { enum rxrpc_conn_flag { RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */ RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */ - RXRPC_CONN_IN_CLIENT_CONNS, /* Conn is in local->client_conns */ - RXRPC_CONN_EXPOSED, /* Conn has extra ref for exposure */ RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */ - RXRPC_CONN_COUNTED, /* Counted by rxrpc_nr_client_conns */ RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */ RXRPC_CONN_FINAL_ACK_0, /* Need final ACK for channel 0 */ RXRPC_CONN_FINAL_ACK_1, /* Need final ACK for channel 1 */ @@ -377,19 +372,6 @@ enum rxrpc_conn_event { }; /* - * The connection cache state. - */ -enum rxrpc_conn_cache_state { - RXRPC_CONN_CLIENT_INACTIVE, /* Conn is not yet listed */ - RXRPC_CONN_CLIENT_WAITING, /* Conn is on wait list, waiting for capacity */ - RXRPC_CONN_CLIENT_ACTIVE, /* Conn is on active list, doing calls */ - RXRPC_CONN_CLIENT_UPGRADE, /* Conn is on active list, probing for upgrade */ - RXRPC_CONN_CLIENT_CULLED, /* Conn is culled and delisted, doing calls */ - RXRPC_CONN_CLIENT_IDLE, /* Conn is on idle list, doing mostly nothing */ - RXRPC_CONN__NR_CACHE_STATES -}; - -/* * The connection protocol state. */ enum rxrpc_conn_proto_state { @@ -405,6 +387,23 @@ enum rxrpc_conn_proto_state { }; /* + * RxRPC client connection bundle. + */ +struct rxrpc_bundle { + struct rxrpc_conn_parameters params; + atomic_t usage; + unsigned int debug_id; + bool try_upgrade; /* True if the bundle is attempting upgrade */ + bool alloc_conn; /* True if someone's getting a conn */ + unsigned short alloc_error; /* Error from last conn allocation */ + spinlock_t channel_lock; + struct rb_node local_node; /* Node in local->client_conns */ + struct list_head waiting_calls; /* Calls waiting for channels */ + unsigned long avail_chans; /* Mask of available channels */ + struct rxrpc_connection *conns[4]; /* The connections in the bundle (max 4) */ +}; + +/* * RxRPC connection definition * - matched by { local, peer, epoch, conn_id, direction } * - each connection can only handle four simultaneous calls @@ -417,10 +416,7 @@ struct rxrpc_connection { struct rcu_head rcu; struct list_head cache_link; - spinlock_t channel_lock; - unsigned char active_chans; /* Mask of active channels */ -#define RXRPC_ACTIVE_CHANS_MASK ((1 << RXRPC_MAXCALLS) - 1) - struct list_head waiting_calls; /* Calls waiting for channels */ + unsigned char act_chans; /* Mask of active channels */ struct rxrpc_channel { unsigned long final_ack_at; /* Time at which to issue final ACK */ struct rxrpc_call __rcu *call; /* Active call */ @@ -437,10 +433,8 @@ struct rxrpc_connection { struct timer_list timer; /* Conn event timer */ struct work_struct processor; /* connection event processor */ - union { - struct rb_node client_node; /* Node in local->client_conns */ - struct rb_node service_node; /* Node in peer->service_conns */ - }; + struct rxrpc_bundle *bundle; /* Client connection bundle */ + struct rb_node service_node; /* Node in peer->service_conns */ struct list_head proc_link; /* link in procfs list */ struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ @@ -452,7 +446,6 @@ struct rxrpc_connection { unsigned long events; unsigned long idle_timestamp; /* Time at which last became idle */ spinlock_t state_lock; /* state-change lock */ - enum rxrpc_conn_cache_state cache_state; enum rxrpc_conn_proto_state state; /* current state of connection */ u32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ @@ -464,6 +457,7 @@ struct rxrpc_connection { u8 security_size; /* security header size */ u8 security_ix; /* security type */ u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ + u8 bundle_shift; /* Index into bundle->avail_chans */ short error; /* Local error code */ }; @@ -488,12 +482,13 @@ enum rxrpc_call_flag { RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ - RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ RXRPC_CALL_RX_UNDERRUN, /* Got data underrun */ RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ + RXRPC_CALL_KERNEL, /* The call was made by the kernel */ + RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ }; /* @@ -578,7 +573,7 @@ struct rxrpc_call { struct work_struct processor; /* Event processor */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ - struct list_head chan_wait_link; /* Link in conn->waiting_calls */ + struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */ struct hlist_node error_link; /* link in error distribution list */ struct list_head accept_link; /* Link in rx->acceptq */ struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ @@ -673,9 +668,13 @@ struct rxrpc_call { rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */ rxrpc_seq_t ackr_seen; /* Highest packet shown seen */ - /* ping management */ - rxrpc_serial_t ping_serial; /* Last ping sent */ - ktime_t ping_time; /* Time last ping sent */ + /* RTT management */ + rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ + ktime_t rtt_sent_at[4]; /* Time packet sent */ + unsigned long rtt_avail; /* Mask of available slots in bits 0-3, + * Mask of pending samples in 8-11 */ +#define RXRPC_CALL_RTT_AVAIL_MASK 0xf +#define RXRPC_CALL_RTT_PEND_SHIFT 8 /* transmission-phase ACK management */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ @@ -724,6 +723,7 @@ struct rxrpc_call_params { u32 normal; /* Max time since last call packet (msec) */ } timeouts; u8 nr_timeouts; /* Number of timeouts specified */ + bool kernel; /* T if kernel is making the call */ enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */ }; @@ -812,18 +812,19 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) /* * conn_client.c */ -extern unsigned int rxrpc_max_client_connections; extern unsigned int rxrpc_reap_client_connections; extern unsigned long rxrpc_conn_idle_client_expiry; extern unsigned long rxrpc_conn_idle_client_fast_expiry; extern struct idr rxrpc_client_conn_ids; void rxrpc_destroy_client_conn_ids(void); +struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *); +void rxrpc_put_bundle(struct rxrpc_bundle *); int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, gfp_t); void rxrpc_expose_client_call(struct rxrpc_call *); -void rxrpc_disconnect_client_call(struct rxrpc_call *); +void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_put_client_conn(struct rxrpc_connection *); void rxrpc_discard_expired_client_conns(struct work_struct *); void rxrpc_destroy_all_client_connections(struct rxrpc_net *); @@ -849,7 +850,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_connection(struct rxrpc_connection *); bool rxrpc_queue_conn(struct rxrpc_connection *); void rxrpc_see_connection(struct rxrpc_connection *); -void rxrpc_get_connection(struct rxrpc_connection *); +struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *); struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *); void rxrpc_put_service_conn(struct rxrpc_connection *); void rxrpc_service_connection_reaper(struct work_struct *); @@ -1037,7 +1038,7 @@ static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call, /* * rtt.c */ -void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, +void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool); void rxrpc_peer_init_rtt(struct rxrpc_peer *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 032ed76c0166..ef160566aa9a 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -622,7 +622,7 @@ int rxrpc_reject_call(struct rxrpc_sock *rx) case RXRPC_CALL_SERVER_ACCEPTING: __rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, -ECONNABORTED); abort = true; - /* fall through */ + fallthrough; case RXRPC_CALL_COMPLETE: ret = call->error; goto out_discard; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 38a46167523f..c8015c76a81c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -41,6 +41,11 @@ const char *const rxrpc_call_completions[NR__RXRPC_CALL_COMPLETIONS] = { struct kmem_cache *rxrpc_call_jar; +static struct semaphore rxrpc_call_limiter = + __SEMAPHORE_INITIALIZER(rxrpc_call_limiter, 1000); +static struct semaphore rxrpc_kernel_call_limiter = + __SEMAPHORE_INITIALIZER(rxrpc_kernel_call_limiter, 1000); + static void rxrpc_call_timer_expired(struct timer_list *t) { struct rxrpc_call *call = from_timer(call, t, timer); @@ -153,6 +158,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; call->rxnet = rxnet; + call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK; atomic_inc(&rxnet->nr_calls); return call; @@ -209,6 +215,34 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) } /* + * Wait for a call slot to become available. + */ +static struct semaphore *rxrpc_get_call_slot(struct rxrpc_call_params *p, gfp_t gfp) +{ + struct semaphore *limiter = &rxrpc_call_limiter; + + if (p->kernel) + limiter = &rxrpc_kernel_call_limiter; + if (p->interruptibility == RXRPC_UNINTERRUPTIBLE) { + down(limiter); + return limiter; + } + return down_interruptible(limiter) < 0 ? NULL : limiter; +} + +/* + * Release a call slot. + */ +static void rxrpc_put_call_slot(struct rxrpc_call *call) +{ + struct semaphore *limiter = &rxrpc_call_limiter; + + if (test_bit(RXRPC_CALL_KERNEL, &call->flags)) + limiter = &rxrpc_kernel_call_limiter; + up(limiter); +} + +/* * Set up a call for the given parameters. * - Called with the socket lock held, which it must release. * - If it returns a call, the call's lock will need releasing by the caller. @@ -224,15 +258,21 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, { struct rxrpc_call *call, *xcall; struct rxrpc_net *rxnet; + struct semaphore *limiter; struct rb_node *parent, **pp; const void *here = __builtin_return_address(0); int ret; _enter("%p,%lx", rx, p->user_call_ID); + limiter = rxrpc_get_call_slot(p, gfp); + if (!limiter) + return ERR_PTR(-ERESTARTSYS); + call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id); if (IS_ERR(call)) { release_sock(&rx->sk); + up(limiter); _leave(" = %ld", PTR_ERR(call)); return call; } @@ -242,6 +282,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, atomic_read(&call->usage), here, (const void *)p->user_call_ID); + if (p->kernel) + __set_bit(RXRPC_CALL_KERNEL, &call->flags); /* We need to protect a partially set up call against the user as we * will be acting outside the socket lock. @@ -470,6 +512,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) BUG(); spin_unlock_bh(&call->lock); + rxrpc_put_call_slot(call); + del_timer_sync(&call->timer); /* Make sure we don't get any more notifications */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index f2a1a5dbb5a7..0e4e1879c24d 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -1,63 +1,15 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* Client connection-specific management code. * - * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2016, 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Client connections need to be cached for a little while after they've made a * call so as to handle retransmitted DATA packets in case the server didn't * receive the final ACK or terminating ABORT we sent it. * - * Client connections can be in one of a number of cache states: - * - * (1) INACTIVE - The connection is not held in any list and may not have been - * exposed to the world. If it has been previously exposed, it was - * discarded from the idle list after expiring. - * - * (2) WAITING - The connection is waiting for the number of client conns to - * drop below the maximum capacity. Calls may be in progress upon it from - * when it was active and got culled. - * - * The connection is on the rxrpc_waiting_client_conns list which is kept - * in to-be-granted order. Culled conns with waiters go to the back of - * the queue just like new conns. - * - * (3) ACTIVE - The connection has at least one call in progress upon it, it - * may freely grant available channels to new calls and calls may be - * waiting on it for channels to become available. - * - * The connection is on the rxnet->active_client_conns list which is kept - * in activation order for culling purposes. - * - * rxrpc_nr_active_client_conns is held incremented also. - * - * (4) UPGRADE - As for ACTIVE, but only one call may be in progress and is - * being used to probe for service upgrade. - * - * (5) CULLED - The connection got summarily culled to try and free up - * capacity. Calls currently in progress on the connection are allowed to - * continue, but new calls will have to wait. There can be no waiters in - * this state - the conn would have to go to the WAITING state instead. - * - * (6) IDLE - The connection has no calls in progress upon it and must have - * been exposed to the world (ie. the EXPOSED flag must be set). When it - * expires, the EXPOSED flag is cleared and the connection transitions to - * the INACTIVE state. - * - * The connection is on the rxnet->idle_client_conns list which is kept in - * order of how soon they'll expire. - * * There are flags of relevance to the cache: * - * (1) EXPOSED - The connection ID got exposed to the world. If this flag is - * set, an extra ref is added to the connection preventing it from being - * reaped when it has no calls outstanding. This flag is cleared and the - * ref dropped when a conn is discarded from the idle list. - * - * This allows us to move terminal call state retransmission to the - * connection and to discard the call immediately we think it is done - * with. It also give us a chance to reuse the connection. - * * (2) DONT_REUSE - The connection should be discarded as soon as possible and * should not be reused. This is set when an exclusive connection is used * or a call ID counter overflows. @@ -78,7 +30,6 @@ #include "ar-internal.h" -__read_mostly unsigned int rxrpc_max_client_connections = 1000; __read_mostly unsigned int rxrpc_reap_client_connections = 900; __read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ; __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; @@ -89,8 +40,6 @@ __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); -static void rxrpc_cull_active_client_conns(struct rxrpc_net *); - /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The @@ -162,13 +111,50 @@ void rxrpc_destroy_client_conn_ids(void) } /* + * Allocate a connection bundle. + */ +static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, + gfp_t gfp) +{ + struct rxrpc_bundle *bundle; + + bundle = kzalloc(sizeof(*bundle), gfp); + if (bundle) { + bundle->params = *cp; + rxrpc_get_peer(bundle->params.peer); + atomic_set(&bundle->usage, 1); + spin_lock_init(&bundle->channel_lock); + INIT_LIST_HEAD(&bundle->waiting_calls); + } + return bundle; +} + +struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle) +{ + atomic_inc(&bundle->usage); + return bundle; +} + +void rxrpc_put_bundle(struct rxrpc_bundle *bundle) +{ + unsigned int d = bundle->debug_id; + unsigned int u = atomic_dec_return(&bundle->usage); + + _debug("PUT B=%x %u", d, u); + if (u == 0) { + rxrpc_put_peer(bundle->params.peer); + kfree(bundle); + } +} + +/* * Allocate a client connection. */ static struct rxrpc_connection * -rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) +rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) { struct rxrpc_connection *conn; - struct rxrpc_net *rxnet = cp->local->rxnet; + struct rxrpc_net *rxnet = bundle->params.local->rxnet; int ret; _enter(""); @@ -180,15 +166,11 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) } atomic_set(&conn->usage, 1); - if (cp->exclusive) - __set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - if (cp->upgrade) - __set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); - - conn->params = *cp; + conn->bundle = bundle; + conn->params = bundle->params; conn->out_clientflag = RXRPC_CLIENT_INITIATED; conn->state = RXRPC_CONN_CLIENT; - conn->service_id = cp->service_id; + conn->service_id = conn->params.service_id; ret = rxrpc_get_client_connection_id(conn, gfp); if (ret < 0) @@ -207,14 +189,16 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - /* We steal the caller's peer ref. */ - cp->peer = NULL; + rxrpc_get_bundle(bundle); + rxrpc_get_peer(conn->params.peer); rxrpc_get_local(conn->params.local); key_get(conn->params.key); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, atomic_read(&conn->usage), __builtin_return_address(0)); + + atomic_inc(&rxnet->nr_client_conns); trace_rxrpc_client(conn, -1, rxrpc_client_alloc); _leave(" = %p", conn); return conn; @@ -234,13 +218,18 @@ error_0: */ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) { - struct rxrpc_net *rxnet = conn->params.local->rxnet; + struct rxrpc_net *rxnet; int id_cursor, id, distance, limit; + if (!conn) + goto dont_reuse; + + rxnet = conn->params.local->rxnet; if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags)) goto dont_reuse; - if (conn->proto.epoch != rxnet->epoch) + if (conn->state != RXRPC_CONN_CLIENT || + conn->proto.epoch != rxnet->epoch) goto mark_dont_reuse; /* The IDR tree gets very expensive on memory if the connection IDs are @@ -254,7 +243,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) distance = id - id_cursor; if (distance < 0) distance = -distance; - limit = max(rxrpc_max_client_connections * 4, 1024U); + limit = max_t(unsigned long, atomic_read(&rxnet->nr_conns) * 4, 1024); if (distance > limit) goto mark_dont_reuse; @@ -267,277 +256,248 @@ dont_reuse: } /* - * Create or find a client connection to use for a call. - * - * If we return with a connection, the call will be on its waiting list. It's - * left to the caller to assign a channel and wake up the call. + * Look up the conn bundle that matches the connection parameters, adding it if + * it doesn't yet exist. */ -static int rxrpc_get_client_conn(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) +static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *cp, + gfp_t gfp) { - struct rxrpc_connection *conn, *candidate = NULL; + static atomic_t rxrpc_bundle_id; + struct rxrpc_bundle *bundle, *candidate; struct rxrpc_local *local = cp->local; struct rb_node *p, **pp, *parent; long diff; - int ret = -ENOMEM; - _enter("{%d,%lx},", call->debug_id, call->user_call_ID); + _enter("{%px,%x,%u,%u}", + cp->peer, key_serial(cp->key), cp->security_level, cp->upgrade); - cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp); - if (!cp->peer) - goto error; + if (cp->exclusive) + return rxrpc_alloc_bundle(cp, gfp); - call->cong_cwnd = cp->peer->cong_cwnd; - if (call->cong_cwnd >= call->cong_ssthresh) - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; - else - call->cong_mode = RXRPC_CALL_SLOW_START; + /* First, see if the bundle is already there. */ + _debug("search 1"); + spin_lock(&local->client_bundles_lock); + p = local->client_bundles.rb_node; + while (p) { + bundle = rb_entry(p, struct rxrpc_bundle, local_node); - /* If the connection is not meant to be exclusive, search the available - * connections to see if the connection we want to use already exists. - */ - if (!cp->exclusive) { - _debug("search 1"); - spin_lock(&local->client_conns_lock); - p = local->client_conns.rb_node; - while (p) { - conn = rb_entry(p, struct rxrpc_connection, client_node); - -#define cmp(X) ((long)conn->params.X - (long)cp->X) - diff = (cmp(peer) ?: - cmp(key) ?: - cmp(security_level) ?: - cmp(upgrade)); +#define cmp(X) ((long)bundle->params.X - (long)cp->X) + diff = (cmp(peer) ?: + cmp(key) ?: + cmp(security_level) ?: + cmp(upgrade)); #undef cmp - if (diff < 0) { - p = p->rb_left; - } else if (diff > 0) { - p = p->rb_right; - } else { - if (rxrpc_may_reuse_conn(conn) && - rxrpc_get_connection_maybe(conn)) - goto found_extant_conn; - /* The connection needs replacing. It's better - * to effect that when we have something to - * replace it with so that we don't have to - * rebalance the tree twice. - */ - break; - } - } - spin_unlock(&local->client_conns_lock); - } - - /* There wasn't a connection yet or we need an exclusive connection. - * We need to create a candidate and then potentially redo the search - * in case we're racing with another thread also trying to connect on a - * shareable connection. - */ - _debug("new conn"); - candidate = rxrpc_alloc_client_connection(cp, gfp); - if (IS_ERR(candidate)) { - ret = PTR_ERR(candidate); - goto error_peer; + if (diff < 0) + p = p->rb_left; + else if (diff > 0) + p = p->rb_right; + else + goto found_bundle; } + spin_unlock(&local->client_bundles_lock); + _debug("not found"); - /* Add the call to the new connection's waiting list in case we're - * going to have to wait for the connection to come live. It's our - * connection, so we want first dibs on the channel slots. We would - * normally have to take channel_lock but we do this before anyone else - * can see the connection. - */ - list_add(&call->chan_wait_link, &candidate->waiting_calls); - - if (cp->exclusive) { - call->conn = candidate; - call->security = candidate->security; - call->security_ix = candidate->security_ix; - call->service_id = candidate->service_id; - _leave(" = 0 [exclusive %d]", candidate->debug_id); - return 0; - } + /* It wasn't. We need to add one. */ + candidate = rxrpc_alloc_bundle(cp, gfp); + if (!candidate) + return NULL; - /* Publish the new connection for userspace to find. We need to redo - * the search before doing this lest we race with someone else adding a - * conflicting instance. - */ _debug("search 2"); - spin_lock(&local->client_conns_lock); - - pp = &local->client_conns.rb_node; + spin_lock(&local->client_bundles_lock); + pp = &local->client_bundles.rb_node; parent = NULL; while (*pp) { parent = *pp; - conn = rb_entry(parent, struct rxrpc_connection, client_node); + bundle = rb_entry(parent, struct rxrpc_bundle, local_node); -#define cmp(X) ((long)conn->params.X - (long)candidate->params.X) +#define cmp(X) ((long)bundle->params.X - (long)cp->X) diff = (cmp(peer) ?: cmp(key) ?: cmp(security_level) ?: cmp(upgrade)); #undef cmp - if (diff < 0) { + if (diff < 0) pp = &(*pp)->rb_left; - } else if (diff > 0) { + else if (diff > 0) pp = &(*pp)->rb_right; - } else { - if (rxrpc_may_reuse_conn(conn) && - rxrpc_get_connection_maybe(conn)) - goto found_extant_conn; - /* The old connection is from an outdated epoch. */ - _debug("replace conn"); - clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags); - rb_replace_node(&conn->client_node, - &candidate->client_node, - &local->client_conns); - trace_rxrpc_client(conn, -1, rxrpc_client_replace); - goto candidate_published; - } + else + goto found_bundle_free; } - _debug("new conn"); - rb_link_node(&candidate->client_node, parent, pp); - rb_insert_color(&candidate->client_node, &local->client_conns); - -candidate_published: - set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); - call->conn = candidate; - call->security = candidate->security; - call->security_ix = candidate->security_ix; - call->service_id = candidate->service_id; - spin_unlock(&local->client_conns_lock); - _leave(" = 0 [new %d]", candidate->debug_id); - return 0; + _debug("new bundle"); + candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id); + rb_link_node(&candidate->local_node, parent, pp); + rb_insert_color(&candidate->local_node, &local->client_bundles); + rxrpc_get_bundle(candidate); + spin_unlock(&local->client_bundles_lock); + _leave(" = %u [new]", candidate->debug_id); + return candidate; + +found_bundle_free: + kfree(candidate); +found_bundle: + rxrpc_get_bundle(bundle); + spin_unlock(&local->client_bundles_lock); + _leave(" = %u [found]", bundle->debug_id); + return bundle; +} - /* We come here if we found a suitable connection already in existence. - * Discard any candidate we may have allocated, and try to get a - * channel on this one. - */ -found_extant_conn: - _debug("found conn"); - spin_unlock(&local->client_conns_lock); +/* + * Create or find a client bundle to use for a call. + * + * If we return with a connection, the call will be on its waiting list. It's + * left to the caller to assign a channel and wake up the call. + */ +static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx, + struct rxrpc_call *call, + struct rxrpc_conn_parameters *cp, + struct sockaddr_rxrpc *srx, + gfp_t gfp) +{ + struct rxrpc_bundle *bundle; - if (candidate) { - trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate); - rxrpc_put_connection(candidate); - candidate = NULL; - } + _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - spin_lock(&conn->channel_lock); - call->conn = conn; - call->security = conn->security; - call->security_ix = conn->security_ix; - call->service_id = conn->service_id; - list_add_tail(&call->chan_wait_link, &conn->waiting_calls); - spin_unlock(&conn->channel_lock); - _leave(" = 0 [extant %d]", conn->debug_id); - return 0; + cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp); + if (!cp->peer) + goto error; + + call->cong_cwnd = cp->peer->cong_cwnd; + if (call->cong_cwnd >= call->cong_ssthresh) + call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + else + call->cong_mode = RXRPC_CALL_SLOW_START; + if (cp->upgrade) + __set_bit(RXRPC_CALL_UPGRADE, &call->flags); + + /* Find the client connection bundle. */ + bundle = rxrpc_look_up_bundle(cp, gfp); + if (!bundle) + goto error; + + /* Get this call queued. Someone else may activate it whilst we're + * lining up a new connection, but that's fine. + */ + spin_lock(&bundle->channel_lock); + list_add_tail(&call->chan_wait_link, &bundle->waiting_calls); + spin_unlock(&bundle->channel_lock); + + _leave(" = [B=%x]", bundle->debug_id); + return bundle; -error_peer: - rxrpc_put_peer(cp->peer); - cp->peer = NULL; error: - _leave(" = %d", ret); - return ret; + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); } /* - * Activate a connection. + * Allocate a new connection and add it into a bundle. */ -static void rxrpc_activate_conn(struct rxrpc_net *rxnet, - struct rxrpc_connection *conn) +static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) + __releases(bundle->channel_lock) { - if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) { - trace_rxrpc_client(conn, -1, rxrpc_client_to_upgrade); - conn->cache_state = RXRPC_CONN_CLIENT_UPGRADE; - } else { - trace_rxrpc_client(conn, -1, rxrpc_client_to_active); - conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE; - } - rxnet->nr_active_client_conns++; - list_move_tail(&conn->cache_link, &rxnet->active_client_conns); -} + struct rxrpc_connection *candidate = NULL, *old = NULL; + bool conflict; + int i; -/* - * Attempt to animate a connection for a new call. - * - * If it's not exclusive, the connection is in the endpoint tree, and we're in - * the conn's list of those waiting to grab a channel. There is, however, a - * limit on the number of live connections allowed at any one time, so we may - * have to wait for capacity to become available. - * - * Note that a connection on the waiting queue might *also* have active - * channels if it has been culled to make space and then re-requested by a new - * call. - */ -static void rxrpc_animate_client_conn(struct rxrpc_net *rxnet, - struct rxrpc_connection *conn) -{ - unsigned int nr_conns; + _enter(""); - _enter("%d,%d", conn->debug_id, conn->cache_state); + conflict = bundle->alloc_conn; + if (!conflict) + bundle->alloc_conn = true; + spin_unlock(&bundle->channel_lock); + if (conflict) { + _leave(" [conf]"); + return; + } - if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE || - conn->cache_state == RXRPC_CONN_CLIENT_UPGRADE) - goto out; + candidate = rxrpc_alloc_client_connection(bundle, gfp); - spin_lock(&rxnet->client_conn_cache_lock); + spin_lock(&bundle->channel_lock); + bundle->alloc_conn = false; - nr_conns = rxnet->nr_client_conns; - if (!test_and_set_bit(RXRPC_CONN_COUNTED, &conn->flags)) { - trace_rxrpc_client(conn, -1, rxrpc_client_count); - rxnet->nr_client_conns = nr_conns + 1; + if (IS_ERR(candidate)) { + bundle->alloc_error = PTR_ERR(candidate); + spin_unlock(&bundle->channel_lock); + _leave(" [err %ld]", PTR_ERR(candidate)); + return; } - switch (conn->cache_state) { - case RXRPC_CONN_CLIENT_ACTIVE: - case RXRPC_CONN_CLIENT_UPGRADE: - case RXRPC_CONN_CLIENT_WAITING: - break; - - case RXRPC_CONN_CLIENT_INACTIVE: - case RXRPC_CONN_CLIENT_CULLED: - case RXRPC_CONN_CLIENT_IDLE: - if (nr_conns >= rxrpc_max_client_connections) - goto wait_for_capacity; - goto activate_conn; + bundle->alloc_error = 0; + + for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) { + unsigned int shift = i * RXRPC_MAXCALLS; + int j; + + old = bundle->conns[i]; + if (!rxrpc_may_reuse_conn(old)) { + if (old) + trace_rxrpc_client(old, -1, rxrpc_client_replace); + candidate->bundle = rxrpc_get_bundle(bundle); + candidate->bundle_shift = shift; + bundle->conns[i] = candidate; + for (j = 0; j < RXRPC_MAXCALLS; j++) + set_bit(shift + j, &bundle->avail_chans); + candidate = NULL; + break; + } - default: - BUG(); + old = NULL; } -out_unlock: - spin_unlock(&rxnet->client_conn_cache_lock); -out: - _leave(" [%d]", conn->cache_state); - return; + spin_unlock(&bundle->channel_lock); + + if (candidate) { + _debug("discard C=%x", candidate->debug_id); + trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate); + rxrpc_put_connection(candidate); + } -activate_conn: - _debug("activate"); - rxrpc_activate_conn(rxnet, conn); - goto out_unlock; - -wait_for_capacity: - _debug("wait"); - trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting); - conn->cache_state = RXRPC_CONN_CLIENT_WAITING; - list_move_tail(&conn->cache_link, &rxnet->waiting_client_conns); - goto out_unlock; + rxrpc_put_connection(old); + _leave(""); } /* - * Deactivate a channel. + * Add a connection to a bundle if there are no usable connections or we have + * connections waiting for extra capacity. */ -static void rxrpc_deactivate_one_channel(struct rxrpc_connection *conn, - unsigned int channel) +static void rxrpc_maybe_add_conn(struct rxrpc_bundle *bundle, gfp_t gfp) { - struct rxrpc_channel *chan = &conn->channels[channel]; + struct rxrpc_call *call; + int i, usable; - rcu_assign_pointer(chan->call, NULL); - conn->active_chans &= ~(1 << channel); + _enter(""); + + spin_lock(&bundle->channel_lock); + + /* See if there are any usable connections. */ + usable = 0; + for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) + if (rxrpc_may_reuse_conn(bundle->conns[i])) + usable++; + + if (!usable && !list_empty(&bundle->waiting_calls)) { + call = list_first_entry(&bundle->waiting_calls, + struct rxrpc_call, chan_wait_link); + if (test_bit(RXRPC_CALL_UPGRADE, &call->flags)) + bundle->try_upgrade = true; + } + + if (!usable) + goto alloc_conn; + + if (!bundle->avail_chans && + !bundle->try_upgrade && + !list_empty(&bundle->waiting_calls) && + usable < ARRAY_SIZE(bundle->conns)) + goto alloc_conn; + + spin_unlock(&bundle->channel_lock); + _leave(""); + return; + +alloc_conn: + return rxrpc_add_conn_to_bundle(bundle, gfp); } /* @@ -549,35 +509,42 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, unsigned int channel) { struct rxrpc_channel *chan = &conn->channels[channel]; - struct rxrpc_call *call = list_entry(conn->waiting_calls.next, + struct rxrpc_bundle *bundle = conn->bundle; + struct rxrpc_call *call = list_entry(bundle->waiting_calls.next, struct rxrpc_call, chan_wait_link); u32 call_id = chan->call_counter + 1; + _enter("C=%x,%u", conn->debug_id, channel); + trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate); /* Cancel the final ACK on the previous call if it hasn't been sent yet * as the DATA packet will implicitly ACK it. */ clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags); - - write_lock_bh(&call->state_lock); - call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; - write_unlock_bh(&call->state_lock); + clear_bit(conn->bundle_shift + channel, &bundle->avail_chans); rxrpc_see_call(call); list_del_init(&call->chan_wait_link); - conn->active_chans |= 1 << channel; call->peer = rxrpc_get_peer(conn->params.peer); + call->conn = rxrpc_get_connection(conn); call->cid = conn->proto.cid | channel; call->call_id = call_id; + call->security = conn->security; + call->security_ix = conn->security_ix; + call->service_id = conn->service_id; trace_rxrpc_connect_call(call); _net("CONNECT call %08x:%08x as call %d on conn %d", call->cid, call->call_id, call->debug_id, conn->debug_id); - /* Paired with the read barrier in rxrpc_wait_for_channel(). This - * orders cid and epoch in the connection wrt to call_id without the - * need to take the channel_lock. + write_lock_bh(&call->state_lock); + call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; + write_unlock_bh(&call->state_lock); + + /* Paired with the read barrier in rxrpc_connect_call(). This orders + * cid and epoch in the connection wrt to call_id without the need to + * take the channel_lock. * * We provisionally assign a callNumber at this point, but we don't * confirm it until the call is about to be exposed. @@ -586,101 +553,137 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, * at the call ID through a connection channel. */ smp_wmb(); - chan->call_id = call_id; - chan->call_debug_id = call->debug_id; + + chan->call_id = call_id; + chan->call_debug_id = call->debug_id; rcu_assign_pointer(chan->call, call); wake_up(&call->waitq); } /* + * Remove a connection from the idle list if it's on it. + */ +static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn) +{ + struct rxrpc_net *rxnet = bundle->params.local->rxnet; + bool drop_ref; + + if (!list_empty(&conn->cache_link)) { + drop_ref = false; + spin_lock(&rxnet->client_conn_cache_lock); + if (!list_empty(&conn->cache_link)) { + list_del_init(&conn->cache_link); + drop_ref = true; + } + spin_unlock(&rxnet->client_conn_cache_lock); + if (drop_ref) + rxrpc_put_connection(conn); + } +} + +/* * Assign channels and callNumbers to waiting calls with channel_lock * held by caller. */ -static void rxrpc_activate_channels_locked(struct rxrpc_connection *conn) +static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle) { - u8 avail, mask; - - switch (conn->cache_state) { - case RXRPC_CONN_CLIENT_ACTIVE: - mask = RXRPC_ACTIVE_CHANS_MASK; - break; - case RXRPC_CONN_CLIENT_UPGRADE: - mask = 0x01; - break; - default: - return; - } + struct rxrpc_connection *conn; + unsigned long avail, mask; + unsigned int channel, slot; - while (!list_empty(&conn->waiting_calls) && - (avail = ~conn->active_chans, - avail &= mask, - avail != 0)) - rxrpc_activate_one_channel(conn, __ffs(avail)); + if (bundle->try_upgrade) + mask = 1; + else + mask = ULONG_MAX; + + while (!list_empty(&bundle->waiting_calls)) { + avail = bundle->avail_chans & mask; + if (!avail) + break; + channel = __ffs(avail); + clear_bit(channel, &bundle->avail_chans); + + slot = channel / RXRPC_MAXCALLS; + conn = bundle->conns[slot]; + if (!conn) + break; + + if (bundle->try_upgrade) + set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); + rxrpc_unidle_conn(bundle, conn); + + channel &= (RXRPC_MAXCALLS - 1); + conn->act_chans |= 1 << channel; + rxrpc_activate_one_channel(conn, channel); + } } /* * Assign channels and callNumbers to waiting calls. */ -static void rxrpc_activate_channels(struct rxrpc_connection *conn) +static void rxrpc_activate_channels(struct rxrpc_bundle *bundle) { - _enter("%d", conn->debug_id); + _enter("B=%x", bundle->debug_id); - trace_rxrpc_client(conn, -1, rxrpc_client_activate_chans); + trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans); - if (conn->active_chans == RXRPC_ACTIVE_CHANS_MASK) + if (!bundle->avail_chans) return; - spin_lock(&conn->channel_lock); - rxrpc_activate_channels_locked(conn); - spin_unlock(&conn->channel_lock); + spin_lock(&bundle->channel_lock); + rxrpc_activate_channels_locked(bundle); + spin_unlock(&bundle->channel_lock); _leave(""); } /* * Wait for a callNumber and a channel to be granted to a call. */ -static int rxrpc_wait_for_channel(struct rxrpc_call *call, gfp_t gfp) +static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle, + struct rxrpc_call *call, gfp_t gfp) { + DECLARE_WAITQUEUE(myself, current); int ret = 0; _enter("%d", call->debug_id); - if (!call->call_id) { - DECLARE_WAITQUEUE(myself, current); + if (!gfpflags_allow_blocking(gfp)) { + rxrpc_maybe_add_conn(bundle, gfp); + rxrpc_activate_channels(bundle); + ret = bundle->alloc_error ?: -EAGAIN; + goto out; + } - if (!gfpflags_allow_blocking(gfp)) { - ret = -EAGAIN; - goto out; + add_wait_queue_exclusive(&call->waitq, &myself); + for (;;) { + rxrpc_maybe_add_conn(bundle, gfp); + rxrpc_activate_channels(bundle); + ret = bundle->alloc_error; + if (ret < 0) + break; + + switch (call->interruptibility) { + case RXRPC_INTERRUPTIBLE: + case RXRPC_PREINTERRUPTIBLE: + set_current_state(TASK_INTERRUPTIBLE); + break; + case RXRPC_UNINTERRUPTIBLE: + default: + set_current_state(TASK_UNINTERRUPTIBLE); + break; } - - add_wait_queue_exclusive(&call->waitq, &myself); - for (;;) { - switch (call->interruptibility) { - case RXRPC_INTERRUPTIBLE: - case RXRPC_PREINTERRUPTIBLE: - set_current_state(TASK_INTERRUPTIBLE); - break; - case RXRPC_UNINTERRUPTIBLE: - default: - set_current_state(TASK_UNINTERRUPTIBLE); - break; - } - if (call->call_id) - break; - if ((call->interruptibility == RXRPC_INTERRUPTIBLE || - call->interruptibility == RXRPC_PREINTERRUPTIBLE) && - signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } - schedule(); + if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_AWAIT_CONN) + break; + if ((call->interruptibility == RXRPC_INTERRUPTIBLE || + call->interruptibility == RXRPC_PREINTERRUPTIBLE) && + signal_pending(current)) { + ret = -ERESTARTSYS; + break; } - remove_wait_queue(&call->waitq, &myself); - __set_current_state(TASK_RUNNING); + schedule(); } - - /* Paired with the write barrier in rxrpc_activate_one_channel(). */ - smp_rmb(); + remove_wait_queue(&call->waitq, &myself); + __set_current_state(TASK_RUNNING); out: _leave(" = %d", ret); @@ -697,52 +700,49 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, struct sockaddr_rxrpc *srx, gfp_t gfp) { + struct rxrpc_bundle *bundle; struct rxrpc_net *rxnet = cp->local->rxnet; - int ret; + int ret = 0; _enter("{%d,%lx},", call->debug_id, call->user_call_ID); rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper); - rxrpc_cull_active_client_conns(rxnet); - ret = rxrpc_get_client_conn(rx, call, cp, srx, gfp); - if (ret < 0) + bundle = rxrpc_prep_call(rx, call, cp, srx, gfp); + if (IS_ERR(bundle)) { + ret = PTR_ERR(bundle); goto out; + } - rxrpc_animate_client_conn(rxnet, call->conn); - rxrpc_activate_channels(call->conn); - - ret = rxrpc_wait_for_channel(call, gfp); - if (ret < 0) { - trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed); - rxrpc_disconnect_client_call(call); - goto out; + if (call->state == RXRPC_CALL_CLIENT_AWAIT_CONN) { + ret = rxrpc_wait_for_channel(bundle, call, gfp); + if (ret < 0) + goto wait_failed; } - spin_lock_bh(&call->conn->params.peer->lock); - hlist_add_head_rcu(&call->error_link, - &call->conn->params.peer->error_targets); - spin_unlock_bh(&call->conn->params.peer->lock); +granted_channel: + /* Paired with the write barrier in rxrpc_activate_one_channel(). */ + smp_rmb(); out: + rxrpc_put_bundle(bundle); _leave(" = %d", ret); return ret; -} -/* - * Note that a connection is about to be exposed to the world. Once it is - * exposed, we maintain an extra ref on it that stops it from being summarily - * discarded before it's (a) had a chance to deal with retransmission and (b) - * had a chance at re-use (the per-connection security negotiation is - * expensive). - */ -static void rxrpc_expose_client_conn(struct rxrpc_connection *conn, - unsigned int channel) -{ - if (!test_and_set_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { - trace_rxrpc_client(conn, channel, rxrpc_client_exposed); - rxrpc_get_connection(conn); +wait_failed: + spin_lock(&bundle->channel_lock); + list_del_init(&call->chan_wait_link); + spin_unlock(&bundle->channel_lock); + + if (call->state != RXRPC_CALL_CLIENT_AWAIT_CONN) { + ret = 0; + goto granted_channel; } + + trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed); + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_disconnect_client_call(bundle, call); + goto out; } /* @@ -764,7 +764,7 @@ void rxrpc_expose_client_call(struct rxrpc_call *call) chan->call_counter++; if (chan->call_counter >= INT_MAX) set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - rxrpc_expose_client_conn(conn, channel); + trace_rxrpc_client(conn, channel, rxrpc_client_exposed); } } @@ -773,62 +773,56 @@ void rxrpc_expose_client_call(struct rxrpc_call *call) */ static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet) { - unsigned long now = jiffies; - unsigned long reap_at = now + rxrpc_conn_idle_client_expiry; + if (!rxnet->kill_all_client_conns) { + unsigned long now = jiffies; + unsigned long reap_at = now + rxrpc_conn_idle_client_expiry; - if (rxnet->live) - timer_reduce(&rxnet->client_conn_reap_timer, reap_at); + if (rxnet->live) + timer_reduce(&rxnet->client_conn_reap_timer, reap_at); + } } /* * Disconnect a client call. */ -void rxrpc_disconnect_client_call(struct rxrpc_call *call) +void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call *call) { - struct rxrpc_connection *conn = call->conn; + struct rxrpc_connection *conn; struct rxrpc_channel *chan = NULL; - struct rxrpc_net *rxnet = conn->params.local->rxnet; - unsigned int channel = -1; + struct rxrpc_net *rxnet = bundle->params.local->rxnet; + unsigned int channel; + bool may_reuse; u32 cid; - spin_lock(&conn->channel_lock); - set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + _enter("c=%x", call->debug_id); - cid = call->cid; - if (cid) { - channel = cid & RXRPC_CHANNELMASK; - chan = &conn->channels[channel]; - } - trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); + spin_lock(&bundle->channel_lock); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); /* Calls that have never actually been assigned a channel can simply be - * discarded. If the conn didn't get used either, it will follow - * immediately unless someone else grabs it in the meantime. + * discarded. */ - if (!list_empty(&call->chan_wait_link)) { + conn = call->conn; + if (!conn) { _debug("call is waiting"); ASSERTCMP(call->call_id, ==, 0); ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags)); list_del_init(&call->chan_wait_link); - - trace_rxrpc_client(conn, channel, rxrpc_client_chan_unstarted); - - /* We must deactivate or idle the connection if it's now - * waiting for nothing. - */ - spin_lock(&rxnet->client_conn_cache_lock); - if (conn->cache_state == RXRPC_CONN_CLIENT_WAITING && - list_empty(&conn->waiting_calls) && - !conn->active_chans) - goto idle_connection; goto out; } + cid = call->cid; + channel = cid & RXRPC_CHANNELMASK; + chan = &conn->channels[channel]; + trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); + if (rcu_access_pointer(chan->call) != call) { - spin_unlock(&conn->channel_lock); + spin_unlock(&bundle->channel_lock); BUG(); } + may_reuse = rxrpc_may_reuse_conn(conn); + /* If a client call was exposed to the world, we save the result for * retransmission. * @@ -841,14 +835,21 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { _debug("exposed %u,%u", call->call_id, call->abort_code); __rxrpc_disconnect_call(conn, call); + + if (test_and_clear_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) { + trace_rxrpc_client(conn, channel, rxrpc_client_to_active); + bundle->try_upgrade = false; + if (may_reuse) + rxrpc_activate_channels_locked(bundle); + } + } /* See if we can pass the channel directly to another call. */ - if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE && - !list_empty(&conn->waiting_calls)) { + if (may_reuse && !list_empty(&bundle->waiting_calls)) { trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass); rxrpc_activate_one_channel(conn, channel); - goto out_2; + goto out; } /* Schedule the final ACK to be transmitted in a short while so that it @@ -865,128 +866,95 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) rxrpc_reduce_conn_timer(conn, final_ack_at); } - /* Things are more complex and we need the cache lock. We might be - * able to simply idle the conn or it might now be lurking on the wait - * list. It might even get moved back to the active list whilst we're - * waiting for the lock. - */ - spin_lock(&rxnet->client_conn_cache_lock); - - switch (conn->cache_state) { - case RXRPC_CONN_CLIENT_UPGRADE: - /* Deal with termination of a service upgrade probe. */ - if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { - clear_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); - trace_rxrpc_client(conn, channel, rxrpc_client_to_active); - conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE; - rxrpc_activate_channels_locked(conn); - } - /* fall through */ - case RXRPC_CONN_CLIENT_ACTIVE: - if (list_empty(&conn->waiting_calls)) { - rxrpc_deactivate_one_channel(conn, channel); - if (!conn->active_chans) { - rxnet->nr_active_client_conns--; - goto idle_connection; - } - goto out; - } - - trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass); - rxrpc_activate_one_channel(conn, channel); - goto out; + /* Deactivate the channel. */ + rcu_assign_pointer(chan->call, NULL); + set_bit(conn->bundle_shift + channel, &conn->bundle->avail_chans); + conn->act_chans &= ~(1 << channel); - case RXRPC_CONN_CLIENT_CULLED: - rxrpc_deactivate_one_channel(conn, channel); - ASSERT(list_empty(&conn->waiting_calls)); - if (!conn->active_chans) - goto idle_connection; - goto out; + /* If no channels remain active, then put the connection on the idle + * list for a short while. Give it a ref to stop it going away if it + * becomes unbundled. + */ + if (!conn->act_chans) { + trace_rxrpc_client(conn, channel, rxrpc_client_to_idle); + conn->idle_timestamp = jiffies; - case RXRPC_CONN_CLIENT_WAITING: - rxrpc_deactivate_one_channel(conn, channel); - goto out; + rxrpc_get_connection(conn); + spin_lock(&rxnet->client_conn_cache_lock); + list_move_tail(&conn->cache_link, &rxnet->idle_client_conns); + spin_unlock(&rxnet->client_conn_cache_lock); - default: - BUG(); + rxrpc_set_client_reap_timer(rxnet); } out: - spin_unlock(&rxnet->client_conn_cache_lock); -out_2: - spin_unlock(&conn->channel_lock); + spin_unlock(&bundle->channel_lock); _leave(""); return; +} -idle_connection: - /* As no channels remain active, the connection gets deactivated - * immediately or moved to the idle list for a short while. - */ - if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { - trace_rxrpc_client(conn, channel, rxrpc_client_to_idle); - conn->idle_timestamp = jiffies; - conn->cache_state = RXRPC_CONN_CLIENT_IDLE; - list_move_tail(&conn->cache_link, &rxnet->idle_client_conns); - if (rxnet->idle_client_conns.next == &conn->cache_link && - !rxnet->kill_all_client_conns) - rxrpc_set_client_reap_timer(rxnet); - } else { - trace_rxrpc_client(conn, channel, rxrpc_client_to_inactive); - conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; - list_del_init(&conn->cache_link); +/* + * Remove a connection from a bundle. + */ +static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) +{ + struct rxrpc_bundle *bundle = conn->bundle; + struct rxrpc_local *local = bundle->params.local; + unsigned int bindex; + bool need_drop = false; + int i; + + _enter("C=%x", conn->debug_id); + + spin_lock(&bundle->channel_lock); + bindex = conn->bundle_shift / RXRPC_MAXCALLS; + if (bundle->conns[bindex] == conn) { + _debug("clear slot %u", bindex); + bundle->conns[bindex] = NULL; + for (i = 0; i < RXRPC_MAXCALLS; i++) + clear_bit(conn->bundle_shift + i, &bundle->avail_chans); + need_drop = true; } - goto out; + spin_unlock(&bundle->channel_lock); + + /* If there are no more connections, remove the bundle */ + if (!bundle->avail_chans) { + _debug("maybe unbundle"); + spin_lock(&local->client_bundles_lock); + + for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) + if (bundle->conns[i]) + break; + if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) { + _debug("erase bundle"); + rb_erase(&bundle->local_node, &local->client_bundles); + } + + spin_unlock(&local->client_bundles_lock); + if (i == ARRAY_SIZE(bundle->conns)) + rxrpc_put_bundle(bundle); + } + + if (need_drop) + rxrpc_put_connection(conn); + _leave(""); } /* * Clean up a dead client connection. */ -static struct rxrpc_connection * -rxrpc_put_one_client_conn(struct rxrpc_connection *conn) +static void rxrpc_kill_client_conn(struct rxrpc_connection *conn) { - struct rxrpc_connection *next = NULL; struct rxrpc_local *local = conn->params.local; struct rxrpc_net *rxnet = local->rxnet; - unsigned int nr_conns; - trace_rxrpc_client(conn, -1, rxrpc_client_cleanup); + _enter("C=%x", conn->debug_id); - if (test_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags)) { - spin_lock(&local->client_conns_lock); - if (test_and_clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, - &conn->flags)) - rb_erase(&conn->client_node, &local->client_conns); - spin_unlock(&local->client_conns_lock); - } + trace_rxrpc_client(conn, -1, rxrpc_client_cleanup); + atomic_dec(&rxnet->nr_client_conns); rxrpc_put_client_connection_id(conn); - - ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_INACTIVE); - - if (test_bit(RXRPC_CONN_COUNTED, &conn->flags)) { - trace_rxrpc_client(conn, -1, rxrpc_client_uncount); - spin_lock(&rxnet->client_conn_cache_lock); - nr_conns = --rxnet->nr_client_conns; - - if (nr_conns < rxrpc_max_client_connections && - !list_empty(&rxnet->waiting_client_conns)) { - next = list_entry(rxnet->waiting_client_conns.next, - struct rxrpc_connection, cache_link); - rxrpc_get_connection(next); - rxrpc_activate_conn(rxnet, next); - } - - spin_unlock(&rxnet->client_conn_cache_lock); - } - rxrpc_kill_connection(conn); - if (next) - rxrpc_activate_channels(next); - - /* We need to get rid of the temporary ref we took upon next, but we - * can't call rxrpc_put_connection() recursively. - */ - return next; } /* @@ -998,63 +966,12 @@ void rxrpc_put_client_conn(struct rxrpc_connection *conn) unsigned int debug_id = conn->debug_id; int n; - do { - n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here); - if (n > 0) - return; + n = atomic_dec_return(&conn->usage); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here); + if (n <= 0) { ASSERTCMP(n, >=, 0); - - conn = rxrpc_put_one_client_conn(conn); - } while (conn); -} - -/* - * Kill the longest-active client connections to make room for new ones. - */ -static void rxrpc_cull_active_client_conns(struct rxrpc_net *rxnet) -{ - struct rxrpc_connection *conn; - unsigned int nr_conns = rxnet->nr_client_conns; - unsigned int nr_active, limit; - - _enter(""); - - ASSERTCMP(nr_conns, >=, 0); - if (nr_conns < rxrpc_max_client_connections) { - _leave(" [ok]"); - return; + rxrpc_kill_client_conn(conn); } - limit = rxrpc_reap_client_connections; - - spin_lock(&rxnet->client_conn_cache_lock); - nr_active = rxnet->nr_active_client_conns; - - while (nr_active > limit) { - ASSERT(!list_empty(&rxnet->active_client_conns)); - conn = list_entry(rxnet->active_client_conns.next, - struct rxrpc_connection, cache_link); - ASSERTIFCMP(conn->cache_state != RXRPC_CONN_CLIENT_ACTIVE, - conn->cache_state, ==, RXRPC_CONN_CLIENT_UPGRADE); - - if (list_empty(&conn->waiting_calls)) { - trace_rxrpc_client(conn, -1, rxrpc_client_to_culled); - conn->cache_state = RXRPC_CONN_CLIENT_CULLED; - list_del_init(&conn->cache_link); - } else { - trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting); - conn->cache_state = RXRPC_CONN_CLIENT_WAITING; - list_move_tail(&conn->cache_link, - &rxnet->waiting_client_conns); - } - - nr_active--; - } - - rxnet->nr_active_client_conns = nr_active; - spin_unlock(&rxnet->client_conn_cache_lock); - ASSERTCMP(nr_active, >=, 0); - _leave(" [culled]"); } /* @@ -1088,7 +1005,7 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work) /* We keep an estimate of what the number of conns ought to be after * we've discarded some so that we don't overdo the discarding. */ - nr_conns = rxnet->nr_client_conns; + nr_conns = atomic_read(&rxnet->nr_client_conns); next: spin_lock(&rxnet->client_conn_cache_lock); @@ -1098,7 +1015,6 @@ next: conn = list_entry(rxnet->idle_client_conns.next, struct rxrpc_connection, cache_link); - ASSERT(test_bit(RXRPC_CONN_EXPOSED, &conn->flags)); if (!rxnet->kill_all_client_conns) { /* If the number of connections is over the reap limit, we @@ -1120,18 +1036,13 @@ next: } trace_rxrpc_client(conn, -1, rxrpc_client_discard); - if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags)) - BUG(); - conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; list_del_init(&conn->cache_link); spin_unlock(&rxnet->client_conn_cache_lock); - /* When we cleared the EXPOSED flag, we took on responsibility for the - * reference that that had on the usage count. We deal with that here. - * If someone re-sets the flag and re-gets the ref, that's fine. - */ - rxrpc_put_connection(conn); + rxrpc_unbundle_conn(conn); + rxrpc_put_connection(conn); /* Drop the ->cache_link ref */ + nr_conns--; goto next; @@ -1145,8 +1056,7 @@ not_yet_expired: */ _debug("not yet"); if (!rxnet->kill_all_client_conns) - timer_reduce(&rxnet->client_conn_reap_timer, - conn_expires_at); + timer_reduce(&rxnet->client_conn_reap_timer, conn_expires_at); out: spin_unlock(&rxnet->client_conn_cache_lock); @@ -1181,37 +1091,26 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local) { struct rxrpc_connection *conn, *tmp; struct rxrpc_net *rxnet = local->rxnet; - unsigned int nr_active; LIST_HEAD(graveyard); _enter(""); spin_lock(&rxnet->client_conn_cache_lock); - nr_active = rxnet->nr_active_client_conns; list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns, cache_link) { if (conn->params.local == local) { - ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_IDLE); - trace_rxrpc_client(conn, -1, rxrpc_client_discard); - if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags)) - BUG(); - conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; list_move(&conn->cache_link, &graveyard); - nr_active--; } } - rxnet->nr_active_client_conns = nr_active; spin_unlock(&rxnet->client_conn_cache_lock); - ASSERTCMP(nr_active, >=, 0); while (!list_empty(&graveyard)) { conn = list_entry(graveyard.next, struct rxrpc_connection, cache_link); list_del_init(&conn->cache_link); - rxrpc_put_connection(conn); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 447f55ca6886..0628dad2bdea 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -157,12 +157,12 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, _enter("{%d},%x", conn->debug_id, conn->abort_code); - spin_lock(&conn->channel_lock); + spin_lock(&conn->bundle->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { call = rcu_dereference_protected( conn->channels[i].call, - lockdep_is_held(&conn->channel_lock)); + lockdep_is_held(&conn->bundle->channel_lock)); if (call) { if (compl == RXRPC_CALL_LOCALLY_ABORTED) trace_rxrpc_abort(call->debug_id, @@ -179,7 +179,7 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, } } - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); _leave(""); } @@ -210,6 +210,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, conn->error = error; conn->abort_code = abort_code; conn->state = RXRPC_CONN_LOCALLY_ABORTED; + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); spin_unlock_bh(&conn->state_lock); msg.msg_name = &conn->params.peer->srx.transport; @@ -319,6 +320,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, conn->error = -ECONNABORTED; conn->abort_code = abort_code; conn->state = RXRPC_CONN_REMOTELY_ABORTED; + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); return -ECONNABORTED; @@ -339,7 +341,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, if (ret < 0) return ret; - spin_lock(&conn->channel_lock); + spin_lock(&conn->bundle->channel_lock); spin_lock(&conn->state_lock); if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { @@ -349,12 +351,12 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, rxrpc_call_is_secure( rcu_dereference_protected( conn->channels[loop].call, - lockdep_is_held(&conn->channel_lock))); + lockdep_is_held(&conn->bundle->channel_lock))); } else { spin_unlock(&conn->state_lock); } - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); return 0; default: diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 8cbe0bf20ed5..3bcbe0665f91 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -41,8 +41,6 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) conn = kzalloc(sizeof(struct rxrpc_connection), gfp); if (conn) { INIT_LIST_HEAD(&conn->cache_link); - spin_lock_init(&conn->channel_lock); - INIT_LIST_HEAD(&conn->waiting_calls); timer_setup(&conn->timer, &rxrpc_connection_timer, 0); INIT_WORK(&conn->processor, &rxrpc_process_connection); INIT_LIST_HEAD(&conn->proc_link); @@ -219,11 +217,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) } if (rxrpc_is_client_call(call)) - return rxrpc_disconnect_client_call(call); + return rxrpc_disconnect_client_call(conn->bundle, call); - spin_lock(&conn->channel_lock); + spin_lock(&conn->bundle->channel_lock); __rxrpc_disconnect_call(conn, call); - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); conn->idle_timestamp = jiffies; @@ -292,12 +290,13 @@ void rxrpc_see_connection(struct rxrpc_connection *conn) /* * Get a ref on a connection. */ -void rxrpc_get_connection(struct rxrpc_connection *conn) +struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(&conn->usage); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here); + return conn; } /* @@ -365,6 +364,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) conn->security->clear(conn); key_put(conn->params.key); key_put(conn->server_key); + rxrpc_put_bundle(conn->bundle); rxrpc_put_peer(conn->params.peer); if (atomic_dec_and_test(&conn->params.local->rxnet->nr_conns)) diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 21da48e3d2e5..6c847720494f 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -8,6 +8,12 @@ #include <linux/slab.h> #include "ar-internal.h" +static struct rxrpc_bundle rxrpc_service_dummy_bundle = { + .usage = ATOMIC_INIT(1), + .debug_id = UINT_MAX, + .channel_lock = __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock), +}; + /* * Find a service connection under RCU conditions. * @@ -127,6 +133,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn */ conn->state = RXRPC_CONN_SERVICE_PREALLOC; atomic_set(&conn->usage, 2); + conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle); atomic_inc(&rxnet->nr_conns); write_lock(&rxnet->conn_lock); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 767579328a06..667c44aa5a63 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -608,36 +608,57 @@ unlock: } /* - * Process a requested ACK. + * See if there's a cached RTT probe to complete. */ -static void rxrpc_input_requested_ack(struct rxrpc_call *call, - ktime_t resp_time, - rxrpc_serial_t orig_serial, - rxrpc_serial_t ack_serial) +static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, + ktime_t resp_time, + rxrpc_serial_t acked_serial, + rxrpc_serial_t ack_serial, + enum rxrpc_rtt_rx_trace type) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; + rxrpc_serial_t orig_serial; + unsigned long avail; ktime_t sent_at; - int ix; + bool matched = false; + int i; - for (ix = 0; ix < RXRPC_RXTX_BUFF_SIZE; ix++) { - skb = call->rxtx_buffer[ix]; - if (!skb) - continue; + avail = READ_ONCE(call->rtt_avail); + smp_rmb(); /* Read avail bits before accessing data. */ - sent_at = skb->tstamp; - smp_rmb(); /* Read timestamp before serial. */ - sp = rxrpc_skb(skb); - if (sp->hdr.serial != orig_serial) + for (i = 0; i < ARRAY_SIZE(call->rtt_serial); i++) { + if (!test_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &avail)) continue; - goto found; - } - return; + sent_at = call->rtt_sent_at[i]; + orig_serial = call->rtt_serial[i]; + + if (orig_serial == acked_serial) { + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_mb(); /* Read data before setting avail bit */ + set_bit(i, &call->rtt_avail); + if (type != rxrpc_rtt_rx_cancel) + rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial, + sent_at, resp_time); + else + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i, + orig_serial, acked_serial, 0, 0); + matched = true; + } + + /* If a later serial is being acked, then mark this slot as + * being available. + */ + if (after(acked_serial, orig_serial)) { + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_obsolete, i, + orig_serial, acked_serial, 0, 0); + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_wmb(); + set_bit(i, &call->rtt_avail); + } + } -found: - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_requested_ack, - orig_serial, ack_serial, sent_at, resp_time); + if (!matched) + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0); } /* @@ -682,27 +703,11 @@ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) */ static void rxrpc_input_ping_response(struct rxrpc_call *call, ktime_t resp_time, - rxrpc_serial_t orig_serial, + rxrpc_serial_t acked_serial, rxrpc_serial_t ack_serial) { - rxrpc_serial_t ping_serial; - ktime_t ping_time; - - ping_time = call->ping_time; - smp_rmb(); - ping_serial = READ_ONCE(call->ping_serial); - - if (orig_serial == call->acks_lost_ping) + if (acked_serial == call->acks_lost_ping) rxrpc_input_check_for_lost_ack(call); - - if (before(orig_serial, ping_serial) || - !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags)) - return; - if (after(orig_serial, ping_serial)) - return; - - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_ping_response, - orig_serial, ack_serial, ping_time, resp_time); } /* @@ -843,7 +848,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ackinfo info; u8 acks[RXRPC_MAXACKS]; } buf; - rxrpc_serial_t acked_serial; + rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -856,6 +861,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } offset += sizeof(buf.ack); + ack_serial = sp->hdr.serial; acked_serial = ntohl(buf.ack.serial); first_soft_ack = ntohl(buf.ack.firstPacket); prev_pkt = ntohl(buf.ack.previousPacket); @@ -864,31 +870,42 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? buf.ack.reason : RXRPC_ACK__INVALID); - trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial, + trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); - if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE) + switch (buf.ack.reason) { + case RXRPC_ACK_PING_RESPONSE: rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - sp->hdr.serial); - if (buf.ack.reason == RXRPC_ACK_REQUESTED) - rxrpc_input_requested_ack(call, skb->tstamp, acked_serial, - sp->hdr.serial); + ack_serial); + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_ping_response); + break; + case RXRPC_ACK_REQUESTED: + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_requested_ack); + break; + default: + if (acked_serial != 0) + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_cancel); + break; + } if (buf.ack.reason == RXRPC_ACK_PING) { - _proto("Rx ACK %%%u PING Request", sp->hdr.serial); + _proto("Rx ACK %%%u PING Request", ack_serial); rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - sp->hdr.serial, true, true, + ack_serial, true, true, rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - sp->hdr.serial, true, true, + ack_serial, true, true, rxrpc_propose_ack_respond_to_ack); } /* Discard any out-of-order or duplicate ACKs (outside lock). */ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->ackr_first_seq, prev_pkt, call->ackr_prev_seq); return; @@ -904,7 +921,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) /* Discard any out-of-order or duplicate ACKs (inside lock). */ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->ackr_first_seq, prev_pkt, call->ackr_prev_seq); goto out; @@ -964,7 +981,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial, false, true, rxrpc_propose_ack_ping_for_lost_reply); @@ -1084,7 +1101,7 @@ static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx, switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); - /* Fall through */ + fallthrough; case RXRPC_CALL_COMPLETE: break; default: @@ -1243,12 +1260,12 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) case RXRPC_PACKET_TYPE_BUSY: if (rxrpc_to_server(sp)) goto discard; - /* Fall through */ + fallthrough; case RXRPC_PACKET_TYPE_ACK: case RXRPC_PACKET_TYPE_ACKALL: if (sp->hdr.callNumber == 0) goto bad_message; - /* Fall through */ + fallthrough; case RXRPC_PACKET_TYPE_ABORT: break; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index c8b2097f499c..8c2881054266 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -86,8 +86,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->reject_queue); skb_queue_head_init(&local->event_queue); - local->client_conns = RB_ROOT; - spin_lock_init(&local->client_conns_lock); + local->client_bundles = RB_ROOT; + spin_lock_init(&local->client_bundles_lock); spin_lock_init(&local->lock); rwlock_init(&local->services_lock); local->debug_id = atomic_inc_return(&rxrpc_debug_id); @@ -162,7 +162,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) /* Fall through and set IPv4 options too otherwise we don't get * errors from IPv4 packets sent through the IPv6 socket. */ - /* Fall through */ + fallthrough; case AF_INET: /* we want to receive ICMP errors */ ip_sock_set_recverr(local->socket->sk); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index b312aab80fed..25bbc4cc8b13 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -62,13 +62,10 @@ static __net_init int rxrpc_init_net(struct net *net) timer_setup(&rxnet->service_conn_reap_timer, rxrpc_service_conn_reap_timeout, 0); - rxnet->nr_client_conns = 0; - rxnet->nr_active_client_conns = 0; + atomic_set(&rxnet->nr_client_conns, 0); rxnet->kill_all_client_conns = false; spin_lock_init(&rxnet->client_conn_cache_lock); spin_lock_init(&rxnet->client_conn_discard_lock); - INIT_LIST_HEAD(&rxnet->waiting_client_conns); - INIT_LIST_HEAD(&rxnet->active_client_conns); INIT_LIST_HEAD(&rxnet->idle_client_conns); INIT_WORK(&rxnet->client_conn_reaper, rxrpc_discard_expired_client_conns); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 1ba43c3df4ad..10f2bf2e9068 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -124,6 +124,49 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, } /* + * Record the beginning of an RTT probe. + */ +static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, + enum rxrpc_rtt_tx_trace why) +{ + unsigned long avail = call->rtt_avail; + int rtt_slot = 9; + + if (!(avail & RXRPC_CALL_RTT_AVAIL_MASK)) + goto no_slot; + + rtt_slot = __ffs(avail & RXRPC_CALL_RTT_AVAIL_MASK); + if (!test_and_clear_bit(rtt_slot, &call->rtt_avail)) + goto no_slot; + + call->rtt_serial[rtt_slot] = serial; + call->rtt_sent_at[rtt_slot] = ktime_get_real(); + smp_wmb(); /* Write data before avail bit */ + set_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + + trace_rxrpc_rtt_tx(call, why, rtt_slot, serial); + return rtt_slot; + +no_slot: + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_no_slot, rtt_slot, serial); + return -1; +} + +/* + * Cancel an RTT probe. + */ +static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, + rxrpc_serial_t serial, int rtt_slot) +{ + if (rtt_slot != -1) { + clear_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_wmb(); /* Clear pending bit before setting slot */ + set_bit(rtt_slot, &call->rtt_avail); + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_cancel, rtt_slot, serial); + } +} + +/* * Send an ACK call packet. */ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, @@ -136,7 +179,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; size_t len, n; - int ret; + int ret, rtt_slot = -1; u8 reason; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -196,18 +239,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (_serial) *_serial = serial; - if (ping) { - call->ping_serial = serial; - smp_wmb(); - /* We need to stick a time in before we send the packet in case - * the reply gets back before kernel_sendmsg() completes - but - * asking UDP to send the packet can take a relatively long - * time. - */ - call->ping_time = ktime_get_real(); - set_bit(RXRPC_CALL_PINGING, &call->flags); - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial); - } + if (ping) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); conn->params.peer->last_tx_at = ktime_get_seconds(); @@ -221,8 +254,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { - if (ping) - clear_bit(RXRPC_CALL_PINGING, &call->flags); + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); rxrpc_propose_ACK(call, pkt->ack.reason, ntohl(pkt->ack.serial), false, true, @@ -321,10 +353,16 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, struct kvec iov[2]; rxrpc_serial_t serial; size_t len; - int ret; + int ret, rtt_slot = -1; _enter(",{%d}", skb->len); + if (hlist_unhashed(&call->error_link)) { + spin_lock_bh(&call->peer->lock); + hlist_add_head_rcu(&call->error_link, &call->peer->error_targets); + spin_unlock_bh(&call->peer->lock); + } + /* Each transmission of a Tx packet needs a new serial number */ serial = atomic_inc_return(&conn->serial); @@ -397,6 +435,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, sp->hdr.serial = serial; smp_wmb(); /* Set serial before timestamp */ skb->tstamp = ktime_get_real(); + if (whdr.flags & RXRPC_REQUEST_ACK) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet @@ -408,12 +448,15 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, conn->params.peer->last_tx_at = ktime_get_seconds(); up_read(&conn->params.local->defrag_sem); - if (ret < 0) + if (ret < 0) { + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); - else + } else { trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_nofrag); + } + rxrpc_tx_backoff(call, ret); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -422,7 +465,6 @@ done: if (ret >= 0) { if (whdr.flags & RXRPC_REQUEST_ACK) { call->peer->rtt_last_req = skb->tstamp; - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial); if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -469,6 +511,8 @@ send_fragmentable: sp->hdr.serial = serial; smp_wmb(); /* Set serial before timestamp */ skb->tstamp = ktime_get_real(); + if (whdr.flags & RXRPC_REQUEST_ACK) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); switch (conn->params.local->srx.transport.family) { case AF_INET6: @@ -487,12 +531,14 @@ send_fragmentable: BUG(); } - if (ret < 0) + if (ret < 0) { + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); - else + } else { trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_frag); + } rxrpc_tx_backoff(call, ret); up_write(&conn->params.local->defrag_sem); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index a852f46d5234..be032850ae8c 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -273,7 +273,7 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, case SO_EE_ORIGIN_ICMP6: if (err == EACCES) err = EHOSTUNREACH; - /* Fall through */ + fallthrough; default: _proto("Rx Received error report { orig=%u }", ee->ee_origin); break; diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index ca29976bb193..68396d052052 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -502,11 +502,21 @@ EXPORT_SYMBOL(rxrpc_kernel_get_peer); * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT * @sock: The socket on which the call is in progress. * @call: The call to query + * @_srtt: Where to store the SRTT value. * - * Get the call's peer smoothed RTT. + * Get the call's peer smoothed RTT in uS. */ -u32 rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call) +bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call, + u32 *_srtt) { - return call->peer->srtt_us >> 3; + struct rxrpc_peer *peer = call->peer; + + if (peer->rtt_count == 0) { + *_srtt = 1000000; /* 1S */ + return false; + } + + *_srtt = call->peer->srtt_us >> 3; + return true; } EXPORT_SYMBOL(rxrpc_kernel_get_srtt); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 543afd9bd664..e2f990754f88 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -165,7 +165,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) "Proto Local " " Remote " " SvID ConnID End Use State Key " - " Serial ISerial\n" + " Serial ISerial CallId0 CallId1 CallId2 CallId3\n" ); return 0; } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index efecc5a8f67d..c4684dde1f16 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -776,7 +776,7 @@ out: case RXRPC_ACK_DELAY: if (ret != -EAGAIN) break; - /* Fall through */ + fallthrough; default: rxrpc_send_ack_packet(call, false, NULL); } diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c index 928d8b34a3ee..4e565eeab426 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -14,7 +14,6 @@ #define RXRPC_RTO_MAX ((unsigned)(120 * HZ)) #define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ -#define rxrpc_min_rtt_wlen 300 /* As sysctl_tcp_min_rtt_wlen */ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) { @@ -146,6 +145,7 @@ static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) * exclusive access to the peer RTT data. */ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time) { @@ -162,7 +162,7 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, peer->rtt_count++; spin_unlock(&peer->rtt_input_lock); - trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, + trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, peer->srtt_us >> 3, peer->rto_j); } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 52a24d4ef5d8..f114dc2af5cf 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -1137,7 +1137,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, ret = -ENOMEM; ticket = kmalloc(ticket_len, GFP_NOFS); if (!ticket) - goto temporary_error; + goto temporary_error_free_resp; eproto = tracepoint_string("rxkad_tkt_short"); abort_code = RXKADPACKETSHORT; @@ -1169,7 +1169,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, if (response->encrypted.checksum != csum) goto protocol_error_free; - spin_lock(&conn->channel_lock); + spin_lock(&conn->bundle->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { struct rxrpc_call *call; u32 call_id = ntohl(response->encrypted.call_id[i]); @@ -1186,13 +1186,13 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, if (call_id > conn->channels[i].call_counter) { call = rcu_dereference_protected( conn->channels[i].call, - lockdep_is_held(&conn->channel_lock)); + lockdep_is_held(&conn->bundle->channel_lock)); if (call && call->state < RXRPC_CALL_COMPLETE) goto protocol_error_unlock; conn->channels[i].call_counter = call_id; } } - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); eproto = tracepoint_string("rxkad_rsp_seq"); abort_code = RXKADOUTOFSEQUENCE; @@ -1219,7 +1219,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, return 0; protocol_error_unlock: - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); protocol_error_free: kfree(ticket); protocol_error: @@ -1230,6 +1230,7 @@ protocol_error: temporary_error_free_ticket: kfree(ticket); +temporary_error_free_resp: kfree(response); temporary_error: /* Ignore the response packet if we got a temporary error such as diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index f3f6da6e4ad2..0824e103d037 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -241,7 +241,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); if (!last) break; - /* Fall through */ + fallthrough; case RXRPC_CALL_SERVER_SEND_REPLY: call->state = RXRPC_CALL_SERVER_AWAIT_ACK; rxrpc_notify_end_tx(rx, call, notify_end_tx); @@ -721,13 +721,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (p.call.timeouts.normal > 0 && j == 0) j = 1; WRITE_ONCE(call->next_rx_timo, j); - /* Fall through */ + fallthrough; case 2: j = msecs_to_jiffies(p.call.timeouts.idle); if (p.call.timeouts.idle > 0 && j == 0) j = 1; WRITE_ONCE(call->next_req_timo, j); - /* Fall through */ + fallthrough; case 1: if (p.call.timeouts.hard > 0) { j = msecs_to_jiffies(p.call.timeouts.hard); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index e91acc95ff28..540351d6a5f4 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -74,21 +74,13 @@ static struct ctl_table rxrpc_sysctl_table[] = { /* Non-time values */ { - .procname = "max_client_conns", - .data = &rxrpc_max_client_connections, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = (void *)&rxrpc_reap_client_connections, - }, - { .procname = "reap_client_conns", .data = &rxrpc_reap_client_connections, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)SYSCTL_ONE, - .extra2 = (void *)&rxrpc_max_client_connections, + .extra2 = (void *)&n_65535, }, { .procname = "max_backlog", diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 063d8aaf2900..f64af9d9dfee 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -976,7 +976,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, #endif NL_SET_ERR_MSG(extack, "Failed to load TC action module"); err = -ENOENT; - goto err_out; + goto err_free; } /* backward compatibility for policer */ @@ -1013,11 +1013,12 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, err_mod: module_put(a_o->owner); -err_out: +err_free: if (cookie) { kfree(cookie->data); kfree(cookie); } +err_out: return ERR_PTR(err); } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index e6ad42b11835..47f9128ecb8f 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -704,7 +704,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, err = ip_defrag(net, skb, user); local_bh_enable(); if (err && err != -EINPROGRESS) - goto out_free; + return err; if (!err) { *defrag = true; @@ -1039,7 +1039,7 @@ drop: static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { [TCA_CT_ACTION] = { .type = NLA_U16 }, - [TCA_CT_PARMS] = { .type = NLA_EXACT_LEN, .len = sizeof(struct tc_ct) }, + [TCA_CT_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ct)), [TCA_CT_ZONE] = { .type = NLA_U16 }, [TCA_CT_MARK] = { .type = NLA_U32 }, [TCA_CT_MARK_MASK] = { .type = NLA_U32 }, @@ -1049,10 +1049,8 @@ static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { .len = 128 / BITS_PER_BYTE }, [TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 }, [TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 }, - [TCA_CT_NAT_IPV6_MIN] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct in6_addr) }, - [TCA_CT_NAT_IPV6_MAX] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct in6_addr) }, + [TCA_CT_NAT_IPV6_MIN] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + [TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 }, [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 }, }; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index b5042f3ea079..e88fa19ea8a9 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -144,9 +144,8 @@ out: } static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = { - [TCA_CTINFO_ACT] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct - tc_ctinfo) }, + [TCA_CTINFO_ACT] = + NLA_POLICY_EXACT_LEN(sizeof(struct tc_ctinfo)), [TCA_CTINFO_ZONE] = { .type = NLA_U16 }, [TCA_CTINFO_PARMS_DSCP_MASK] = { .type = NLA_U32 }, [TCA_CTINFO_PARMS_DSCP_STATEMASK] = { .type = NLA_U32 }, diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 1fb8d428d2c1..f5dd4d1d274e 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -159,8 +159,8 @@ static const struct nla_policy entry_policy[TCA_GATE_ENTRY_MAX + 1] = { }; static const struct nla_policy gate_policy[TCA_GATE_MAX + 1] = { - [TCA_GATE_PARMS] = { .len = sizeof(struct tc_gate), - .type = NLA_EXACT_LEN }, + [TCA_GATE_PARMS] = + NLA_POLICY_EXACT_LEN(sizeof(struct tc_gate)), [TCA_GATE_PRIORITY] = { .type = NLA_S32 }, [TCA_GATE_ENTRY_LIST] = { .type = NLA_NESTED }, [TCA_GATE_BASE_TIME] = { .type = NLA_U64 }, diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 0618b63f87c4..7d37638ee1c7 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1670,7 +1670,7 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return 0; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index deac82f3ad7b..e89fab6ccb34 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -353,23 +353,11 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt, FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP, tb[TCA_RED_EARLY_DROP_BLOCK], extack); if (err) - goto err_early_drop_init; - - err = tcf_qevent_init(&q->qe_mark, sch, - FLOW_BLOCK_BINDER_TYPE_RED_MARK, - tb[TCA_RED_MARK_BLOCK], extack); - if (err) - goto err_mark_init; - - return 0; + return err; -err_mark_init: - tcf_qevent_destroy(&q->qe_early_drop, sch); -err_early_drop_init: - del_timer_sync(&q->adapt_timer); - red_offload(sch, false); - qdisc_put(q->qdisc); - return err; + return tcf_qevent_init(&q->qe_mark, sch, + FLOW_BLOCK_BINDER_TYPE_RED_MARK, + tb[TCA_RED_MARK_BLOCK], extack); } static int red_change(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index e981992634dd..fe53c1e38c7d 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1176,9 +1176,27 @@ static void taprio_offload_config_changed(struct taprio_sched *q) spin_unlock(&q->current_entry_lock); } -static void taprio_sched_to_offload(struct taprio_sched *q, +static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) +{ + u32 i, queue_mask = 0; + + for (i = 0; i < dev->num_tc; i++) { + u32 offset, count; + + if (!(tc_mask & BIT(i))) + continue; + + offset = dev->tc_to_txq[i].offset; + count = dev->tc_to_txq[i].count; + + queue_mask |= GENMASK(offset + count - 1, offset); + } + + return queue_mask; +} + +static void taprio_sched_to_offload(struct net_device *dev, struct sched_gate_list *sched, - const struct tc_mqprio_qopt *mqprio, struct tc_taprio_qopt_offload *offload) { struct sched_entry *entry; @@ -1193,7 +1211,8 @@ static void taprio_sched_to_offload(struct taprio_sched *q, e->command = entry->command; e->interval = entry->interval; - e->gate_mask = entry->gate_mask; + e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask); + i++; } @@ -1201,7 +1220,6 @@ static void taprio_sched_to_offload(struct taprio_sched *q, } static int taprio_enable_offload(struct net_device *dev, - struct tc_mqprio_qopt *mqprio, struct taprio_sched *q, struct sched_gate_list *sched, struct netlink_ext_ack *extack) @@ -1223,7 +1241,7 @@ static int taprio_enable_offload(struct net_device *dev, return -ENOMEM; } offload->enable = 1; - taprio_sched_to_offload(q, sched, mqprio, offload); + taprio_sched_to_offload(dev, sched, offload); err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err < 0) { @@ -1485,7 +1503,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, } if (FULL_OFFLOAD_IS_ENABLED(q->flags)) - err = taprio_enable_offload(dev, mqprio, q, new_admin, extack); + err = taprio_enable_offload(dev, q, new_admin, extack); else err = taprio_disable_offload(dev, q, extack); if (err) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 8d735461fa19..fdb69d46276d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1351,7 +1351,7 @@ static void sctp_select_active_and_retran_path(struct sctp_association *asoc) } /* We did not find anything useful for a possible retransmission - * path; either primary path that we found is the the same as + * path; either primary path that we found is the same as * the current one, or we didn't generally find an active one. */ if (trans_sec == NULL) @@ -1537,7 +1537,7 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) /* If we've reached or overflowed our receive buffer, announce * a 0 rwnd if rwnd would still be positive. Store the - * the potential pressure overflow so that the window can be restored + * potential pressure overflow so that the window can be restored * back to original value. */ if (rx_count >= asoc->base.sk->sk_rcvbuf) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 9e289c770574..589868d96e3f 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -445,7 +445,7 @@ struct sctp_shared_key *sctp_auth_get_shkey( } /* - * Initialize all the possible digest transforms that we can use. Right now + * Initialize all the possible digest transforms that we can use. Right * now, the supported digests are SHA1 and SHA256. We do this here once * because of the restrictiong that transforms may only be allocated in * user context. This forces us to pre-allocated all possible transforms @@ -810,7 +810,7 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, } /* Set a new shared key on either endpoint or association. If the - * the key with a same ID already exists, replace the key (remove the + * key with a same ID already exists, replace the key (remove the * old key and add a new one). */ int sctp_auth_set_key(struct sctp_endpoint *ep, diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 701c5a4e441d..53e5ed79f63f 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -505,7 +505,7 @@ int sctp_in_scope(struct net *net, const union sctp_addr *addr, return 0; /* * For INIT and INIT-ACK address list, let L be the level of - * of requested destination address, sender and receiver + * requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. * diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index ab6a997e222f..fd4f8243cc35 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -179,7 +179,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, __func__, asoc, max_data); } - /* If the the peer requested that we authenticate DATA chunks + /* If the peer requested that we authenticate DATA chunks * we need to account for bundling of the AUTH chunks along with * DATA. */ diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index aea2a982984d..8a58f42d6d19 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -875,7 +875,7 @@ static int sctp_inet6_af_supported(sa_family_t family, struct sctp_sock *sp) case AF_INET: if (!__ipv6_only_sock(sctp_opt2sk(sp))) return 1; - /* fallthru */ + fallthrough; default: return 0; } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 577e3bc4ee6f..3fd06a27105d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -912,7 +912,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) case SCTP_CID_ABORT: if (sctp_test_T_bit(chunk)) ctx->packet->vtag = ctx->asoc->c.my_vtag; - /* fallthru */ + fallthrough; /* The following chunks are "response" chunks, i.e. * they are generated in response to something we @@ -927,7 +927,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) case SCTP_CID_ECN_CWR: case SCTP_CID_ASCONF_ACK: one_packet = 1; - /* Fall through */ + fallthrough; case SCTP_CID_SACK: case SCTP_CID_HEARTBEAT: @@ -1030,7 +1030,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, if (!ctx->packet || !ctx->packet->has_cookie_echo) return; - /* fall through */ + fallthrough; case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d19db22262fd..25833238fe93 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -372,7 +372,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) * Level 3 - private addresses. * Level 4 - global addresses * For INIT and INIT-ACK address list, let L be the level of - * of requested destination address, sender and receiver + * requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. * @@ -1483,10 +1483,10 @@ static __init int sctp_init(void) num_entries = (1UL << order) * PAGE_SIZE / sizeof(struct sctp_bind_hashbucket); - /* And finish by rounding it down to the nearest power of two - * this wastes some memory of course, but its needed because + /* And finish by rounding it down to the nearest power of two. + * This wastes some memory of course, but it's needed because * the hash function operates based on the assumption that - * that the number of entries is a power of two + * the number of entries is a power of two. */ sctp_port_hashsize = rounddown_pow_of_two(num_entries); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 47910470e532..9a56ae2f3651 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1235,7 +1235,7 @@ nodata: /* Create an Operation Error chunk of a fixed size, specifically, * min(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - overheads. - * This is a helper function to allocate an error chunk for for those + * This is a helper function to allocate an error chunk for those * invalid parameter codes in which we may not want to report all the * errors, if the incoming chunk is large. If it can't fit in a single * packet, we ignore it. @@ -1780,7 +1780,7 @@ no_hmac: * for init collision case of lost COOKIE ACK. * If skb has been timestamped, then use the stamp, otherwise * use current time. This introduces a small possibility that - * that a cookie may be considered expired, but his would only slow + * a cookie may be considered expired, but this would only slow * down the new association establishment instead of every packet. */ if (sock_flag(ep->base.sk, SOCK_TIMESTAMP)) @@ -2077,7 +2077,7 @@ static enum sctp_ierror sctp_process_unk_param( break; case SCTP_PARAM_ACTION_DISCARD_ERR: retval = SCTP_IERROR_ERROR; - /* Fall through */ + fallthrough; case SCTP_PARAM_ACTION_SKIP_ERR: /* Make an ERROR chunk, preparing enough room for * returning multiple unknown parameters. @@ -2319,7 +2319,7 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, /* This implementation defaults to making the first transport * added as the primary transport. The source address seems to - * be a a better choice than any of the embedded addresses. + * be a better choice than any of the embedded addresses. */ if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE)) goto nomem; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 9f36fe911d08..aa821e71f05e 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1516,7 +1516,7 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, if (timer_pending(timer)) break; - /* fall through */ + fallthrough; case SCTP_CMD_TIMER_START: timer = &asoc->timers[cmd->obj.to]; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index e86620fbd90f..c669f8bd1eab 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4315,7 +4315,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); } - /* Fall Through */ + fallthrough; case SCTP_IERROR_AUTH_BAD_KEYID: case SCTP_IERROR_BAD_SIG: return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ec1fba1fbe71..836615f71a7d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8060,8 +8060,6 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) pr_debug("%s: begins, snum:%d\n", __func__, snum); - local_bh_disable(); - if (snum == 0) { /* Search for an available port. */ int low, high, remaining, index; @@ -8079,20 +8077,21 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) continue; index = sctp_phashfn(net, rover); head = &sctp_port_hashtable[index]; - spin_lock(&head->lock); + spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) if ((pp->port == rover) && net_eq(net, pp->net)) goto next; break; next: - spin_unlock(&head->lock); + spin_unlock_bh(&head->lock); + cond_resched(); } while (--remaining > 0); /* Exhausted local port range during search? */ ret = 1; if (remaining <= 0) - goto fail; + return ret; /* OK, here is the one we will use. HEAD (the port * hash table list entry) is non-NULL and we hold it's @@ -8107,7 +8106,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) * port iterator, pp being NULL. */ head = &sctp_port_hashtable[sctp_phashfn(net, snum)]; - spin_lock(&head->lock); + spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) { if ((pp->port == snum) && net_eq(pp->net, net)) goto pp_found; @@ -8207,10 +8206,7 @@ success: ret = 0; fail_unlock: - spin_unlock(&head->lock); - -fail: - local_bh_enable(); + spin_unlock_bh(&head->lock); return ret; } diff --git a/net/sctp/stream.c b/net/sctp/stream.c index bda2536dd740..6dc95dcc0ff4 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -88,12 +88,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, int ret; if (outcnt <= stream->outcnt) - return 0; + goto out; ret = genradix_prealloc(&stream->out, outcnt, gfp); if (ret) return ret; +out: stream->outcnt = outcnt; return 0; } @@ -104,12 +105,13 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, int ret; if (incnt <= stream->incnt) - return 0; + goto out; ret = genradix_prealloc(&stream->in, incnt, gfp); if (ret) return ret; +out: stream->incnt = incnt; return 0; } diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 1c6c640607c5..407fed46931b 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -740,7 +740,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq) /* Helper function to gather skbs that have possibly become - * ordered by an an incoming chunk. + * ordered by an incoming chunk. */ static void sctp_ulpq_retrieve_ordered(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e7649bbc2b87..f5bececfedaa 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -55,6 +55,9 @@ static DEFINE_MUTEX(smc_client_lgr_pending); /* serialize link group * creation on client */ +struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ +struct workqueue_struct *smc_close_wq; /* wq for close work */ + static void smc_tcp_listen_work(struct work_struct *); static void smc_connect_work(struct work_struct *); @@ -436,10 +439,10 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc) static void smcr_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { - int bufsize = smc_uncompress_bufsize(clc->rmbe_size); + int bufsize = smc_uncompress_bufsize(clc->r0.rmbe_size); - smc->conn.peer_rmbe_idx = clc->rmbe_idx; - smc->conn.local_tx_ctrl.token = ntohl(clc->rmbe_alert_token); + smc->conn.peer_rmbe_idx = clc->r0.rmbe_idx; + smc->conn.local_tx_ctrl.token = ntohl(clc->r0.rmbe_alert_token); smc->conn.peer_rmbe_size = bufsize; atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1); @@ -448,10 +451,10 @@ static void smcr_conn_save_peer_info(struct smc_sock *smc, static void smcd_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { - int bufsize = smc_uncompress_bufsize(clc->dmbe_size); + int bufsize = smc_uncompress_bufsize(clc->d0.dmbe_size); - smc->conn.peer_rmbe_idx = clc->dmbe_idx; - smc->conn.peer_token = clc->token; + smc->conn.peer_rmbe_idx = clc->d0.dmbe_idx; + smc->conn.peer_token = clc->d0.token; /* msg header takes up space in the buffer */ smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg); atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); @@ -470,11 +473,11 @@ static void smc_conn_save_peer_info(struct smc_sock *smc, static void smc_link_save_peer_info(struct smc_link *link, struct smc_clc_msg_accept_confirm *clc) { - link->peer_qpn = ntoh24(clc->qpn); - memcpy(link->peer_gid, clc->lcl.gid, SMC_GID_SIZE); - memcpy(link->peer_mac, clc->lcl.mac, sizeof(link->peer_mac)); - link->peer_psn = ntoh24(clc->psn); - link->peer_mtu = clc->qp_mtu; + link->peer_qpn = ntoh24(clc->r0.qpn); + memcpy(link->peer_gid, clc->r0.lcl.gid, SMC_GID_SIZE); + memcpy(link->peer_mac, clc->r0.lcl.mac, sizeof(link->peer_mac)); + link->peer_psn = ntoh24(clc->r0.psn); + link->peer_mtu = clc->r0.qp_mtu; } static void smc_switch_to_fallback(struct smc_sock *smc) @@ -523,11 +526,11 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) /* abort connecting */ static int smc_connect_abort(struct smc_sock *smc, int reason_code, - int local_contact) + int local_first) { bool is_smcd = smc->conn.lgr->is_smcd; - if (local_contact == SMC_FIRST_CONTACT) + if (local_first) smc_lgr_cleanup_early(&smc->conn); else smc_conn_free(&smc->conn); @@ -613,9 +616,9 @@ static int smc_connect_rdma(struct smc_sock *smc, struct smc_link *link; ini->is_smcd = false; - ini->ib_lcl = &aclc->lcl; - ini->ib_clcqpn = ntoh24(aclc->qpn); - ini->srv_first_contact = aclc->hdr.flag; + ini->ib_lcl = &aclc->r0.lcl; + ini->ib_clcqpn = ntoh24(aclc->r0.qpn); + ini->first_contact_peer = aclc->hdr.flag; mutex_lock(&smc_client_lgr_pending); reason_code = smc_conn_create(smc, ini); @@ -626,7 +629,7 @@ static int smc_connect_rdma(struct smc_sock *smc, smc_conn_save_peer_info(smc, aclc); - if (ini->cln_first_contact == SMC_FIRST_CONTACT) { + if (ini->first_contact_local) { link = smc->conn.lnk; } else { /* set link that was assigned by server */ @@ -634,60 +637,62 @@ static int smc_connect_rdma(struct smc_sock *smc, for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *l = &smc->conn.lgr->lnk[i]; - if (l->peer_qpn == ntoh24(aclc->qpn) && - !memcmp(l->peer_gid, &aclc->lcl.gid, SMC_GID_SIZE) && - !memcmp(l->peer_mac, &aclc->lcl.mac, sizeof(l->peer_mac))) { + if (l->peer_qpn == ntoh24(aclc->r0.qpn) && + !memcmp(l->peer_gid, &aclc->r0.lcl.gid, + SMC_GID_SIZE) && + !memcmp(l->peer_mac, &aclc->r0.lcl.mac, + sizeof(l->peer_mac))) { link = l; break; } } if (!link) return smc_connect_abort(smc, SMC_CLC_DECL_NOSRVLINK, - ini->cln_first_contact); + ini->first_contact_local); smc->conn.lnk = link; } /* create send buffer and rmb */ if (smc_buf_create(smc, false)) return smc_connect_abort(smc, SMC_CLC_DECL_MEM, - ini->cln_first_contact); + ini->first_contact_local); - if (ini->cln_first_contact == SMC_FIRST_CONTACT) + if (ini->first_contact_local) smc_link_save_peer_info(link, aclc); if (smc_rmb_rtoken_handling(&smc->conn, link, aclc)) return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK, - ini->cln_first_contact); + ini->first_contact_local); smc_close_init(smc); smc_rx_init(smc); - if (ini->cln_first_contact == SMC_FIRST_CONTACT) { + if (ini->first_contact_local) { if (smc_ib_ready_link(link)) return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK, - ini->cln_first_contact); + ini->first_contact_local); } else { if (smcr_lgr_reg_rmbs(link, smc->conn.rmb_desc)) return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB, - ini->cln_first_contact); + ini->first_contact_local); } smc_rmb_sync_sg_for_device(&smc->conn); reason_code = smc_clc_send_confirm(smc); if (reason_code) return smc_connect_abort(smc, reason_code, - ini->cln_first_contact); + ini->first_contact_local); smc_tx_init(smc); - if (ini->cln_first_contact == SMC_FIRST_CONTACT) { + if (ini->first_contact_local) { /* QP confirmation over RoCE fabric */ smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK); reason_code = smcr_clnt_conf_first_link(smc); smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl); if (reason_code) return smc_connect_abort(smc, reason_code, - ini->cln_first_contact); + ini->first_contact_local); } mutex_unlock(&smc_client_lgr_pending); @@ -707,8 +712,8 @@ static int smc_connect_ism(struct smc_sock *smc, int rc = 0; ini->is_smcd = true; - ini->ism_gid = aclc->gid; - ini->srv_first_contact = aclc->hdr.flag; + ini->ism_peer_gid = aclc->d0.gid; + ini->first_contact_peer = aclc->hdr.flag; /* there is only one lgr role for SMC-D; use server lock */ mutex_lock(&smc_server_lgr_pending); @@ -724,7 +729,7 @@ static int smc_connect_ism(struct smc_sock *smc, return smc_connect_abort(smc, (rc == -ENOSPC) ? SMC_CLC_DECL_MAX_DMB : SMC_CLC_DECL_MEM, - ini->cln_first_contact); + ini->first_contact_local); smc_conn_save_peer_info(smc, aclc); smc_close_init(smc); @@ -733,7 +738,7 @@ static int smc_connect_ism(struct smc_sock *smc, rc = smc_clc_send_confirm(smc); if (rc) - return smc_connect_abort(smc, rc, ini->cln_first_contact); + return smc_connect_abort(smc, rc, ini->first_contact_local); mutex_unlock(&smc_server_lgr_pending); smc_copy_sock_settings_to_clc(smc); @@ -903,7 +908,7 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, if (smc->use_fallback) goto out; if (flags & O_NONBLOCK) { - if (schedule_work(&smc->connect_work)) + if (queue_work(smc_hs_wq, &smc->connect_work)) smc->connect_nonblock = 1; rc = -EINPROGRESS; } else { @@ -940,10 +945,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) mutex_lock(&lsmc->clcsock_release_lock); if (lsmc->clcsock) - rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + rc = kernel_accept(lsmc->clcsock, &new_clcsock, SOCK_NONBLOCK); mutex_unlock(&lsmc->clcsock_release_lock); lock_sock(lsk); - if (rc < 0) + if (rc < 0 && rc != -EAGAIN) lsk->sk_err = -rc; if (rc < 0 || lsk->sk_state == SMC_CLOSED) { new_sk->sk_prot->unhash(new_sk); @@ -956,6 +961,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) goto out; } + /* new clcsock has inherited the smc listen-specific sk_data_ready + * function; switch it back to the original sk_data_ready function + */ + new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready; (*new_smc)->clcsock = new_clcsock; out: return rc; @@ -1123,10 +1132,10 @@ static void smc_listen_out_err(struct smc_sock *new_smc) /* listen worker: decline and fall back if possible */ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, - int local_contact) + bool local_first) { /* RDMA setup failed, switch back to TCP */ - if (local_contact == SMC_FIRST_CONTACT) + if (local_first) smc_lgr_cleanup_early(&new_smc->conn); else smc_conn_free(&new_smc->conn); @@ -1182,30 +1191,16 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { - struct smc_clc_msg_smcd *pclc_smcd; int rc; - pclc_smcd = smc_get_clc_msg_smcd(pclc); - ini->ism_gid = pclc_smcd->gid; rc = smc_conn_create(new_smc, ini); if (rc) return rc; - /* Check if peer can be reached via ISM device */ - if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid, - new_smc->conn.lgr->vlan_id, - new_smc->conn.lgr->smcd)) { - if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_cleanup_early(&new_smc->conn); - else - smc_conn_free(&new_smc->conn); - return SMC_CLC_DECL_SMCDNOTALK; - } - /* Create send and receive buffers */ rc = smc_buf_create(new_smc, true); if (rc) { - if (ini->cln_first_contact == SMC_FIRST_CONTACT) + if (ini->first_contact_local) smc_lgr_cleanup_early(&new_smc->conn); else smc_conn_free(&new_smc->conn); @@ -1217,11 +1212,11 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, } /* listen worker: register buffers */ -static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) +static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first) { struct smc_connection *conn = &new_smc->conn; - if (local_contact != SMC_FIRST_CONTACT) { + if (!local_first) { if (smcr_lgr_reg_rmbs(conn->lnk, conn->rmb_desc)) return SMC_CLC_DECL_ERR_REGRMB; } @@ -1233,35 +1228,25 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) /* listen worker: finish RDMA setup */ static int smc_listen_rdma_finish(struct smc_sock *new_smc, struct smc_clc_msg_accept_confirm *cclc, - int local_contact) + bool local_first) { struct smc_link *link = new_smc->conn.lnk; int reason_code = 0; - if (local_contact == SMC_FIRST_CONTACT) + if (local_first) smc_link_save_peer_info(link, cclc); - if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc)) { - reason_code = SMC_CLC_DECL_ERR_RTOK; - goto decline; - } + if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc)) + return SMC_CLC_DECL_ERR_RTOK; - if (local_contact == SMC_FIRST_CONTACT) { - if (smc_ib_ready_link(link)) { - reason_code = SMC_CLC_DECL_ERR_RDYLNK; - goto decline; - } + if (local_first) { + if (smc_ib_ready_link(link)) + return SMC_CLC_DECL_ERR_RDYLNK; /* QP confirmation over RoCE fabric */ smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK); reason_code = smcr_serv_conf_first_link(new_smc); smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl); - if (reason_code) - goto decline; } - return 0; - -decline: - smc_listen_decline(new_smc, reason_code, local_contact); return reason_code; } @@ -1272,10 +1257,10 @@ static void smc_listen_work(struct work_struct *work) smc_listen_work); struct socket *newclcsock = new_smc->clcsock; struct smc_clc_msg_accept_confirm cclc; + struct smc_clc_msg_proposal_area *buf; struct smc_clc_msg_proposal *pclc; struct smc_init_info ini = {0}; bool ism_supported = false; - u8 buf[SMC_CLC_MAX_LEN]; int rc = 0; if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN) @@ -1297,8 +1282,13 @@ static void smc_listen_work(struct work_struct *work) /* do inband token exchange - * wait for and receive SMC Proposal CLC message */ - pclc = (struct smc_clc_msg_proposal *)&buf; - rc = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN, + buf = kzalloc(sizeof(*buf), GFP_KERNEL); + if (!buf) { + rc = SMC_CLC_DECL_MEM; + goto out_decl; + } + pclc = (struct smc_clc_msg_proposal *)buf; + rc = smc_clc_wait_msg(new_smc, pclc, sizeof(*buf), SMC_CLC_PROPOSAL, CLC_WAIT_TIME); if (rc) goto out_decl; @@ -1327,7 +1317,10 @@ static void smc_listen_work(struct work_struct *work) /* check if ISM is available */ if (pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) { + struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc); + ini.is_smcd = true; /* prepare ISM check */ + ini.ism_peer_gid = pclc_smcd->gid; rc = smc_find_ism_device(new_smc, &ini); if (!rc) rc = smc_listen_ism_init(new_smc, pclc, &ini); @@ -1354,13 +1347,13 @@ static void smc_listen_work(struct work_struct *work) rc = smc_listen_rdma_init(new_smc, &ini); if (rc) goto out_unlock; - rc = smc_listen_rdma_reg(new_smc, ini.cln_first_contact); + rc = smc_listen_rdma_reg(new_smc, ini.first_contact_local); if (rc) goto out_unlock; } /* send SMC Accept CLC message */ - rc = smc_clc_send_accept(new_smc, ini.cln_first_contact); + rc = smc_clc_send_accept(new_smc, ini.first_contact_local); if (rc) goto out_unlock; @@ -1378,12 +1371,13 @@ static void smc_listen_work(struct work_struct *work) } /* finish worker */ + kfree(buf); if (!ism_supported) { rc = smc_listen_rdma_finish(new_smc, &cclc, - ini.cln_first_contact); - mutex_unlock(&smc_server_lgr_pending); + ini.first_contact_local); if (rc) - return; + goto out_unlock; + mutex_unlock(&smc_server_lgr_pending); } smc_conn_save_peer_info(new_smc, &cclc); smc_listen_out_connected(new_smc); @@ -1392,7 +1386,8 @@ static void smc_listen_work(struct work_struct *work) out_unlock: mutex_unlock(&smc_server_lgr_pending); out_decl: - smc_listen_decline(new_smc, rc, ini.cln_first_contact); + smc_listen_decline(new_smc, rc, ini.first_contact_local); + kfree(buf); } static void smc_tcp_listen_work(struct work_struct *work) @@ -1406,7 +1401,7 @@ static void smc_tcp_listen_work(struct work_struct *work) lock_sock(lsk); while (lsk->sk_state == SMC_LISTEN) { rc = smc_clcsock_accept(lsmc, &new_smc); - if (rc) + if (rc) /* clcsock accept queue empty or error */ goto out; if (!new_smc) continue; @@ -1420,13 +1415,29 @@ static void smc_tcp_listen_work(struct work_struct *work) new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ - if (!schedule_work(&new_smc->smc_listen_work)) + if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work)) sock_put(&new_smc->sk); } out: release_sock(lsk); - sock_put(&lsmc->sk); /* sock_hold in smc_listen */ + sock_put(&lsmc->sk); /* sock_hold in smc_clcsock_data_ready() */ +} + +static void smc_clcsock_data_ready(struct sock *listen_clcsock) +{ + struct smc_sock *lsmc; + + lsmc = (struct smc_sock *) + ((uintptr_t)listen_clcsock->sk_user_data & ~SK_USER_DATA_NOCOPY); + if (!lsmc) + return; + lsmc->clcsk_data_ready(listen_clcsock); + if (lsmc->sk.sk_state == SMC_LISTEN) { + sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ + if (!queue_work(smc_hs_wq, &lsmc->tcp_listen_work)) + sock_put(&lsmc->sk); + } } static int smc_listen(struct socket *sock, int backlog) @@ -1455,15 +1466,19 @@ static int smc_listen(struct socket *sock, int backlog) if (!smc->use_fallback) tcp_sk(smc->clcsock->sk)->syn_smc = 1; + /* save original sk_data_ready function and establish + * smc-specific sk_data_ready function + */ + smc->clcsk_data_ready = smc->clcsock->sk->sk_data_ready; + smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready; + smc->clcsock->sk->sk_user_data = + (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); rc = kernel_listen(smc->clcsock, backlog); if (rc) goto out; sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = SMC_LISTEN; - sock_hold(sk); /* sock_hold in tcp_listen_worker */ - if (!schedule_work(&smc->tcp_listen_work)) - sock_put(sk); out: release_sock(sk); @@ -1788,8 +1803,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { if (val) - mod_delayed_work(system_wq, &smc->conn.tx_work, - 0); + mod_delayed_work(smc->conn.lgr->tx_wq, + &smc->conn.tx_work, 0); } break; case TCP_CORK: @@ -1797,8 +1812,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { if (!val) - mod_delayed_work(system_wq, &smc->conn.tx_work, - 0); + mod_delayed_work(smc->conn.lgr->tx_wq, + &smc->conn.tx_work, 0); } break; case TCP_DEFER_ACCEPT: @@ -2081,10 +2096,19 @@ static int __init smc_init(void) if (rc) goto out_pernet_subsys; + rc = -ENOMEM; + smc_hs_wq = alloc_workqueue("smc_hs_wq", 0, 0); + if (!smc_hs_wq) + goto out_pnet; + + smc_close_wq = alloc_workqueue("smc_close_wq", 0, 0); + if (!smc_close_wq) + goto out_alloc_hs_wq; + rc = smc_core_init(); if (rc) { pr_err("%s: smc_core_init fails with %d\n", __func__, rc); - goto out_pnet; + goto out_alloc_wqs; } rc = smc_llc_init(); @@ -2136,6 +2160,10 @@ out_proto: proto_unregister(&smc_proto); out_core: smc_core_exit(); +out_alloc_wqs: + destroy_workqueue(smc_close_wq); +out_alloc_hs_wq: + destroy_workqueue(smc_hs_wq); out_pnet: smc_pnet_exit(); out_pernet_subsys: @@ -2150,6 +2178,8 @@ static void __exit smc_exit(void) sock_unregister(PF_SMC); smc_core_exit(); smc_ib_unregister_client(); + destroy_workqueue(smc_close_wq); + destroy_workqueue(smc_hs_wq); proto_unregister(&smc_proto6); proto_unregister(&smc_proto); smc_pnet_exit(); diff --git a/net/smc/smc.h b/net/smc/smc.h index 6f1c42da7a4c..2bd57e57b7e7 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -18,6 +18,8 @@ #include "smc_ib.h" +#define SMC_V1 1 /* SMC version V1 */ + #define SMCPROTO_SMC 0 /* SMC protocol, IPv4 */ #define SMCPROTO_SMC6 1 /* SMC protocol, IPv6 */ @@ -201,6 +203,8 @@ struct smc_connection { struct smc_sock { /* smc sock container */ struct sock sk; struct socket *clcsock; /* internal tcp socket */ + void (*clcsk_data_ready)(struct sock *sk); + /* original data_ready fct. **/ struct smc_connection conn; /* smc connection */ struct smc_sock *listen_smc; /* listen parent */ struct work_struct connect_work; /* handle non-blocking connect*/ @@ -235,6 +239,9 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } +extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ +extern struct workqueue_struct *smc_close_wq; /* wq for close work */ + #define SMC_SYSTEMID_LEN 8 extern u8 local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */ diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index ce468ff62a19..b1ce6ccbfaec 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -299,7 +299,7 @@ static void smc_cdc_msg_validate(struct smc_sock *smc, struct smc_cdc_msg *cdc, conn->lnk = link; spin_unlock_bh(&conn->send_lock); sock_hold(&smc->sk); /* sock_put in abort_work */ - if (!schedule_work(&conn->abort_work)) + if (!queue_work(smc_close_wq, &conn->abort_work)) sock_put(&smc->sk); } } @@ -368,7 +368,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN; sock_set_flag(&smc->sk, SOCK_DONE); sock_hold(&smc->sk); /* sock_put in close_work */ - if (!schedule_work(&conn->close_work)) + if (!queue_work(smc_close_wq, &conn->close_work)) sock_put(&smc->sk); } } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 779f4142a11d..bd116e1949b9 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -153,7 +153,6 @@ static int smc_clc_prfx_set(struct socket *clcsock, struct sockaddr_in *addr; int rc = -ENOENT; - memset(prop, 0, sizeof(*prop)); if (!dst) { rc = -ENOTCONN; goto out; @@ -320,7 +319,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, } datlen = ntohs(clcm->length); if ((len < sizeof(struct smc_clc_msg_hdr)) || - (clcm->version < SMC_CLC_V1) || + (clcm->version < SMC_V1) || ((clcm->type != SMC_CLC_DECLINE) && (clcm->type != expected_type))) { smc->sk.sk_err = EPROTO; @@ -389,7 +388,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) memcpy(dclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); dclc.hdr.type = SMC_CLC_DECLINE; dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); - dclc.hdr.version = SMC_CLC_V1; + dclc.hdr.version = SMC_V1; dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0; if ((!smc->conn.lgr || !smc->conn.lgr->is_smcd) && smc_ib_is_valid_local_systemid()) @@ -412,138 +411,171 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, struct smc_init_info *ini) { - struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX]; - struct smc_clc_msg_proposal_prefix pclc_prfx; - struct smc_clc_msg_smcd pclc_smcd; - struct smc_clc_msg_proposal pclc; - struct smc_clc_msg_trail trl; + struct smc_clc_msg_proposal_prefix *pclc_prfx; + struct smc_clc_msg_proposal *pclc_base; + struct smc_clc_msg_proposal_area *pclc; + struct smc_clc_ipv6_prefix *ipv6_prfx; + struct smc_clc_msg_smcd *pclc_smcd; + struct smc_clc_msg_trail *trl; int len, i, plen, rc; int reason_code = 0; struct kvec vec[5]; struct msghdr msg; + pclc = kzalloc(sizeof(*pclc), GFP_KERNEL); + if (!pclc) + return -ENOMEM; + + pclc_base = &pclc->pclc_base; + pclc_smcd = &pclc->pclc_smcd; + pclc_prfx = &pclc->pclc_prfx; + ipv6_prfx = pclc->pclc_prfx_ipv6; + trl = &pclc->pclc_trl; + /* retrieve ip prefixes for CLC proposal msg */ - rc = smc_clc_prfx_set(smc->clcsock, &pclc_prfx, ipv6_prfx); - if (rc) + rc = smc_clc_prfx_set(smc->clcsock, pclc_prfx, ipv6_prfx); + if (rc) { + kfree(pclc); return SMC_CLC_DECL_CNFERR; /* configuration error */ + } /* send SMC Proposal CLC message */ - plen = sizeof(pclc) + sizeof(pclc_prfx) + - (pclc_prfx.ipv6_prefixes_cnt * sizeof(ipv6_prfx[0])) + - sizeof(trl); - memset(&pclc, 0, sizeof(pclc)); - memcpy(pclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); - pclc.hdr.type = SMC_CLC_PROPOSAL; - pclc.hdr.version = SMC_CLC_V1; /* SMC version */ - pclc.hdr.path = smc_type; + plen = sizeof(*pclc_base) + sizeof(*pclc_prfx) + + (pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0])) + + sizeof(*trl); + memcpy(pclc_base->hdr.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + pclc_base->hdr.type = SMC_CLC_PROPOSAL; + pclc_base->hdr.version = SMC_V1; /* SMC version */ + pclc_base->hdr.path = smc_type; if (smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B) { /* add SMC-R specifics */ - memcpy(pclc.lcl.id_for_peer, local_systemid, + memcpy(pclc_base->lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&pclc.lcl.gid, ini->ib_gid, SMC_GID_SIZE); - memcpy(&pclc.lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1], + memcpy(pclc_base->lcl.gid, ini->ib_gid, SMC_GID_SIZE); + memcpy(pclc_base->lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1], ETH_ALEN); - pclc.iparea_offset = htons(0); + pclc_base->iparea_offset = htons(0); } if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) { /* add SMC-D specifics */ - memset(&pclc_smcd, 0, sizeof(pclc_smcd)); - plen += sizeof(pclc_smcd); - pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET); - pclc_smcd.gid = ini->ism_dev->local_gid; + plen += sizeof(*pclc_smcd); + pclc_base->iparea_offset = htons(sizeof(*pclc_smcd)); + pclc_smcd->gid = ini->ism_dev->local_gid; } - pclc.hdr.length = htons(plen); + pclc_base->hdr.length = htons(plen); - memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); + memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); memset(&msg, 0, sizeof(msg)); i = 0; - vec[i].iov_base = &pclc; - vec[i++].iov_len = sizeof(pclc); + vec[i].iov_base = pclc_base; + vec[i++].iov_len = sizeof(*pclc_base); if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) { - vec[i].iov_base = &pclc_smcd; - vec[i++].iov_len = sizeof(pclc_smcd); + vec[i].iov_base = pclc_smcd; + vec[i++].iov_len = sizeof(*pclc_smcd); } - vec[i].iov_base = &pclc_prfx; - vec[i++].iov_len = sizeof(pclc_prfx); - if (pclc_prfx.ipv6_prefixes_cnt > 0) { - vec[i].iov_base = &ipv6_prfx[0]; - vec[i++].iov_len = pclc_prfx.ipv6_prefixes_cnt * + vec[i].iov_base = pclc_prfx; + vec[i++].iov_len = sizeof(*pclc_prfx); + if (pclc_prfx->ipv6_prefixes_cnt > 0) { + vec[i].iov_base = ipv6_prfx; + vec[i++].iov_len = pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0]); } - vec[i].iov_base = &trl; - vec[i++].iov_len = sizeof(trl); + vec[i].iov_base = trl; + vec[i++].iov_len = sizeof(*trl); /* due to the few bytes needed for clc-handshake this cannot block */ len = kernel_sendmsg(smc->clcsock, &msg, vec, i, plen); if (len < 0) { smc->sk.sk_err = smc->clcsock->sk->sk_err; reason_code = -smc->sk.sk_err; - } else if (len < (int)sizeof(pclc)) { + } else if (len < ntohs(pclc_base->hdr.length)) { reason_code = -ENETUNREACH; smc->sk.sk_err = -reason_code; } + kfree(pclc); return reason_code; } -/* send CLC CONFIRM message across internal TCP socket */ -int smc_clc_send_confirm(struct smc_sock *smc) +/* build and send CLC CONFIRM / ACCEPT message */ +static int smc_clc_send_confirm_accept(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *clc, + int first_contact) { struct smc_connection *conn = &smc->conn; - struct smc_clc_msg_accept_confirm cclc; - struct smc_link *link; - int reason_code = 0; struct msghdr msg; struct kvec vec; - int len; /* send SMC Confirm CLC msg */ - memset(&cclc, 0, sizeof(cclc)); - cclc.hdr.type = SMC_CLC_CONFIRM; - cclc.hdr.version = SMC_CLC_V1; /* SMC version */ - if (smc->conn.lgr->is_smcd) { + clc->hdr.version = SMC_V1; /* SMC version */ + if (first_contact) + clc->hdr.flag = 1; + if (conn->lgr->is_smcd) { /* SMC-D specific settings */ - memcpy(cclc.hdr.eyecatcher, SMCD_EYECATCHER, + memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)); - cclc.hdr.path = SMC_TYPE_D; - cclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); - cclc.gid = conn->lgr->smcd->local_gid; - cclc.token = conn->rmb_desc->token; - cclc.dmbe_size = conn->rmbe_size_short; - cclc.dmbe_idx = 0; - memcpy(&cclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); - memcpy(cclc.smcd_trl.eyecatcher, SMCD_EYECATCHER, + clc->hdr.path = SMC_TYPE_D; + clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); + clc->d0.gid = conn->lgr->smcd->local_gid; + clc->d0.token = conn->rmb_desc->token; + clc->d0.dmbe_size = conn->rmbe_size_short; + clc->d0.dmbe_idx = 0; + memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); + memcpy(clc->d0.smcd_trl.eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)); } else { + struct smc_link *link = conn->lnk; + /* SMC-R specific settings */ link = conn->lnk; - memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER, + memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); - cclc.hdr.path = SMC_TYPE_R; - cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); - memcpy(cclc.lcl.id_for_peer, local_systemid, + clc->hdr.path = SMC_TYPE_R; + clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); + memcpy(clc->r0.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&cclc.lcl.gid, link->gid, SMC_GID_SIZE); - memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], + memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE); + memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN); - hton24(cclc.qpn, link->roce_qp->qp_num); - cclc.rmb_rkey = + hton24(clc->r0.qpn, link->roce_qp->qp_num); + clc->r0.rmb_rkey = htonl(conn->rmb_desc->mr_rx[link->link_idx]->rkey); - cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ - cclc.rmbe_alert_token = htonl(conn->alert_token_local); - cclc.qp_mtu = min(link->path_mtu, link->peer_mtu); - cclc.rmbe_size = conn->rmbe_size_short; - cclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address + clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ + clc->r0.rmbe_alert_token = htonl(conn->alert_token_local); + switch (clc->hdr.type) { + case SMC_CLC_ACCEPT: + clc->r0.qp_mtu = link->path_mtu; + break; + case SMC_CLC_CONFIRM: + clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); + break; + } + clc->r0.rmbe_size = conn->rmbe_size_short; + clc->r0.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address (conn->rmb_desc->sgt[link->link_idx].sgl)); - hton24(cclc.psn, link->psn_initial); - memcpy(cclc.smcr_trl.eyecatcher, SMC_EYECATCHER, + hton24(clc->r0.psn, link->psn_initial); + memcpy(clc->r0.smcr_trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); } memset(&msg, 0, sizeof(msg)); - vec.iov_base = &cclc; - vec.iov_len = ntohs(cclc.hdr.length); - len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, - ntohs(cclc.hdr.length)); + vec.iov_base = clc; + vec.iov_len = ntohs(clc->hdr.length); + return kernel_sendmsg(smc->clcsock, &msg, &vec, 1, + ntohs(clc->hdr.length)); +} + +/* send CLC CONFIRM message across internal TCP socket */ +int smc_clc_send_confirm(struct smc_sock *smc) +{ + struct smc_clc_msg_accept_confirm cclc; + int reason_code = 0; + int len; + + /* send SMC Confirm CLC msg */ + memset(&cclc, 0, sizeof(cclc)); + cclc.hdr.type = SMC_CLC_CONFIRM; + len = smc_clc_send_confirm_accept(smc, &cclc, 0); if (len < ntohs(cclc.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; @@ -557,65 +589,14 @@ int smc_clc_send_confirm(struct smc_sock *smc) } /* send CLC ACCEPT message across internal TCP socket */ -int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact) +int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact) { - struct smc_connection *conn = &new_smc->conn; struct smc_clc_msg_accept_confirm aclc; - struct smc_link *link; - struct msghdr msg; - struct kvec vec; int len; memset(&aclc, 0, sizeof(aclc)); aclc.hdr.type = SMC_CLC_ACCEPT; - aclc.hdr.version = SMC_CLC_V1; /* SMC version */ - if (srv_first_contact) - aclc.hdr.flag = 1; - - if (new_smc->conn.lgr->is_smcd) { - /* SMC-D specific settings */ - aclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); - memcpy(aclc.hdr.eyecatcher, SMCD_EYECATCHER, - sizeof(SMCD_EYECATCHER)); - aclc.hdr.path = SMC_TYPE_D; - aclc.gid = conn->lgr->smcd->local_gid; - aclc.token = conn->rmb_desc->token; - aclc.dmbe_size = conn->rmbe_size_short; - aclc.dmbe_idx = 0; - memcpy(&aclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); - memcpy(aclc.smcd_trl.eyecatcher, SMCD_EYECATCHER, - sizeof(SMCD_EYECATCHER)); - } else { - /* SMC-R specific settings */ - aclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); - memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER, - sizeof(SMC_EYECATCHER)); - aclc.hdr.path = SMC_TYPE_R; - link = conn->lnk; - memcpy(aclc.lcl.id_for_peer, local_systemid, - sizeof(local_systemid)); - memcpy(&aclc.lcl.gid, link->gid, SMC_GID_SIZE); - memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], - ETH_ALEN); - hton24(aclc.qpn, link->roce_qp->qp_num); - aclc.rmb_rkey = - htonl(conn->rmb_desc->mr_rx[link->link_idx]->rkey); - aclc.rmbe_idx = 1; /* as long as 1 RMB = 1 RMBE */ - aclc.rmbe_alert_token = htonl(conn->alert_token_local); - aclc.qp_mtu = link->path_mtu; - aclc.rmbe_size = conn->rmbe_size_short, - aclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address - (conn->rmb_desc->sgt[link->link_idx].sgl)); - hton24(aclc.psn, link->psn_initial); - memcpy(aclc.smcr_trl.eyecatcher, SMC_EYECATCHER, - sizeof(SMC_EYECATCHER)); - } - - memset(&msg, 0, sizeof(msg)); - vec.iov_base = &aclc; - vec.iov_len = ntohs(aclc.hdr.length); - len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1, - ntohs(aclc.hdr.length)); + len = smc_clc_send_confirm_accept(new_smc, &aclc, srv_first_contact); if (len < ntohs(aclc.hdr.length)) len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index cf7b45306f4e..fcd8521c7737 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -22,7 +22,6 @@ #define SMC_CLC_CONFIRM 0x03 #define SMC_CLC_DECLINE 0x04 -#define SMC_CLC_V1 0x1 /* SMC version */ #define SMC_TYPE_R 0 /* SMC-R only */ #define SMC_TYPE_D 1 /* SMC-D only */ #define SMC_TYPE_N 2 /* neither SMC-R nor SMC-D */ @@ -38,7 +37,6 @@ #define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found (R or D) */ #define SMC_CLC_DECL_NOSMCDDEV 0x03030001 /* no SMC-D device found */ #define SMC_CLC_DECL_NOSMCRDEV 0x03030002 /* no SMC-R device found */ -#define SMC_CLC_DECL_SMCDNOTALK 0x03030003 /* SMC-D dev can't talk to peer */ #define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/ #define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */ #define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */ @@ -111,55 +109,58 @@ struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ __be16 iparea_offset; /* offset to IP address information area */ } __aligned(4); -#define SMC_CLC_PROPOSAL_MAX_OFFSET 0x28 -#define SMC_CLC_PROPOSAL_MAX_PREFIX (SMC_CLC_MAX_V6_PREFIX * \ - sizeof(struct smc_clc_ipv6_prefix)) -#define SMC_CLC_MAX_LEN (sizeof(struct smc_clc_msg_proposal) + \ - SMC_CLC_PROPOSAL_MAX_OFFSET + \ - sizeof(struct smc_clc_msg_proposal_prefix) + \ - SMC_CLC_PROPOSAL_MAX_PREFIX + \ - sizeof(struct smc_clc_msg_trail)) +struct smc_clc_msg_proposal_area { + struct smc_clc_msg_proposal pclc_base; + struct smc_clc_msg_smcd pclc_smcd; + struct smc_clc_msg_proposal_prefix pclc_prfx; + struct smc_clc_ipv6_prefix pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX]; + struct smc_clc_msg_trail pclc_trl; +}; -struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ - struct smc_clc_msg_hdr hdr; - union { - struct { /* SMC-R */ - struct smc_clc_msg_local lcl; - u8 qpn[3]; /* QP number */ - __be32 rmb_rkey; /* RMB rkey */ - u8 rmbe_idx; /* Index of RMBE in RMB */ - __be32 rmbe_alert_token;/* unique connection id */ -#if defined(__BIG_ENDIAN_BITFIELD) - u8 rmbe_size : 4, /* buf size (compressed) */ - qp_mtu : 4; /* QP mtu */ +struct smcr_clc_msg_accept_confirm { /* SMCR accept/confirm */ + struct smc_clc_msg_local lcl; + u8 qpn[3]; /* QP number */ + __be32 rmb_rkey; /* RMB rkey */ + u8 rmbe_idx; /* Index of RMBE in RMB */ + __be32 rmbe_alert_token; /* unique connection id */ + #if defined(__BIG_ENDIAN_BITFIELD) + u8 rmbe_size : 4, /* buf size (compressed) */ + qp_mtu : 4; /* QP mtu */ #elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 qp_mtu : 4, - rmbe_size : 4; + u8 qp_mtu : 4, + rmbe_size : 4; #endif - u8 reserved; - __be64 rmb_dma_addr; /* RMB virtual address */ - u8 reserved2; - u8 psn[3]; /* packet sequence number */ - struct smc_clc_msg_trail smcr_trl; - /* eye catcher "SMCR" EBCDIC */ - } __packed; - struct { /* SMC-D */ - u64 gid; /* Sender GID */ - u64 token; /* DMB token */ - u8 dmbe_idx; /* DMBE index */ + u8 reserved; + __be64 rmb_dma_addr; /* RMB virtual address */ + u8 reserved2; + u8 psn[3]; /* packet sequence number */ + struct smc_clc_msg_trail smcr_trl; + /* eye catcher "SMCR" EBCDIC */ +} __packed; + +struct smcd_clc_msg_accept_confirm { /* SMCD accept/confirm */ + u64 gid; /* Sender GID */ + u64 token; /* DMB token */ + u8 dmbe_idx; /* DMBE index */ #if defined(__BIG_ENDIAN_BITFIELD) - u8 dmbe_size : 4, /* buf size (compressed) */ - reserved3 : 4; + u8 dmbe_size : 4, /* buf size (compressed) */ + reserved3 : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 reserved3 : 4, - dmbe_size : 4; + u8 reserved3 : 4, + dmbe_size : 4; #endif - u16 reserved4; - u32 linkid; /* Link identifier */ - u32 reserved5[3]; - struct smc_clc_msg_trail smcd_trl; - /* eye catcher "SMCD" EBCDIC */ - } __packed; + u16 reserved4; + u32 linkid; /* Link identifier */ + u32 reserved5[3]; + struct smc_clc_msg_trail smcd_trl; + /* eye catcher "SMCD" EBCDIC */ +} __packed; + +struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ + struct smc_clc_msg_hdr hdr; + union { + struct smcr_clc_msg_accept_confirm r0; /* SMC-R */ + struct smcd_clc_msg_accept_confirm d0; /* SMC-D */ }; } __packed; /* format defined in RFC7609 */ @@ -200,6 +201,6 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info); int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, struct smc_init_info *ini); int smc_clc_send_confirm(struct smc_sock *smc); -int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact); +int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact); #endif diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 290270c821ca..10d05a6d34fc 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -116,7 +116,6 @@ static void smc_close_cancel_work(struct smc_sock *smc) cancel_work_sync(&smc->conn.close_work); cancel_delayed_work_sync(&smc->conn.tx_work); lock_sock(sk); - sk->sk_state = SMC_CLOSED; } /* terminate smc socket abnormally - active abort @@ -134,22 +133,22 @@ void smc_close_active_abort(struct smc_sock *smc) } switch (sk->sk_state) { case SMC_ACTIVE: - sk->sk_state = SMC_PEERABORTWAIT; - smc_close_cancel_work(smc); - sk->sk_state = SMC_CLOSED; - sock_put(sk); /* passive closing */ - break; case SMC_APPCLOSEWAIT1: case SMC_APPCLOSEWAIT2: + sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); + if (sk->sk_state != SMC_PEERABORTWAIT) + break; sk->sk_state = SMC_CLOSED; - sock_put(sk); /* postponed passive closing */ + sock_put(sk); /* (postponed) passive closing */ break; case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); + if (sk->sk_state != SMC_PEERABORTWAIT) + break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; @@ -159,6 +158,8 @@ void smc_close_active_abort(struct smc_sock *smc) case SMC_APPFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); + if (sk->sk_state != SMC_PEERABORTWAIT) + break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; @@ -207,12 +208,11 @@ again: break; case SMC_LISTEN: sk->sk_state = SMC_CLOSED; + smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + smc->clcsock->sk->sk_user_data = NULL; sk->sk_state_change(sk); /* wake up accept */ - if (smc->clcsock && smc->clcsock->sk) { + if (smc->clcsock && smc->clcsock->sk) rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); - /* wake up kernel_accept of smc_tcp_listen_worker */ - smc->clcsock->sk->sk_data_ready(smc->clcsock->sk); - } smc_close_cleanup_listen(sk); release_sock(sk); flush_work(&smc->tcp_listen_work); @@ -372,7 +372,7 @@ static void smc_close_passive_work(struct work_struct *work) case SMC_PEERCLOSEWAIT1: if (rxflags->peer_done_writing) sk->sk_state = SMC_PEERCLOSEWAIT2; - /* fall through */ + fallthrough; /* to check for closing */ case SMC_PEERCLOSEWAIT2: if (!smc_cdc_rxed_any_close(conn)) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index b42fa3b00d00..c811ae1a8add 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -34,7 +34,6 @@ #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) #define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ) -#define SMC_LGR_FREE_DELAY_FAST (8 * HZ) static struct smc_lgr_list smc_lgr_list = { /* established link groups */ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), @@ -70,7 +69,7 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) * creation. For client use a somewhat higher removal delay time, * otherwise there is a risk of out-of-sync link groups. */ - if (!lgr->freeing && !lgr->freefast) { + if (!lgr->freeing) { mod_delayed_work(system_wq, &lgr->free_work, (!lgr->is_smcd && lgr->role == SMC_CLNT) ? SMC_LGR_FREE_DELAY_CLNT : @@ -78,15 +77,6 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) } } -void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr) -{ - if (!lgr->freeing && !lgr->freefast) { - lgr->freefast = 1; - mod_delayed_work(system_wq, &lgr->free_work, - SMC_LGR_FREE_DELAY_FAST); - } -} - /* Register connection's alert token in our lookup structure. * To use rbtrees we have to implement our own insert core. * Requires @conns_lock @@ -227,7 +217,7 @@ void smc_lgr_cleanup_early(struct smc_connection *conn) if (!list_empty(lgr_list)) list_del_init(lgr_list); spin_unlock_bh(lgr_lock); - smc_lgr_schedule_free_work_fast(lgr); + __smc_lgr_terminate(lgr, true); } static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr) @@ -396,10 +386,15 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) rc = SMC_CLC_DECL_MEM; goto ism_put_vlan; } + lgr->tx_wq = alloc_workqueue("smc_tx_wq-%*phN", 0, 0, + SMC_LGR_ID_SIZE, &lgr->id); + if (!lgr->tx_wq) { + rc = -ENOMEM; + goto free_lgr; + } lgr->is_smcd = ini->is_smcd; lgr->sync_err = 0; lgr->terminating = 0; - lgr->freefast = 0; lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; mutex_init(&lgr->sndbufs_lock); @@ -418,7 +413,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) if (ini->is_smcd) { /* SMC-D specific settings */ get_device(&ini->ism_dev->dev); - lgr->peer_gid = ini->ism_gid; + lgr->peer_gid = ini->ism_peer_gid; lgr->smcd = ini->ism_dev; lgr_list = &ini->ism_dev->lgr_list; lgr_lock = &lgr->smcd->lgr_lock; @@ -437,7 +432,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lnk = &lgr->lnk[link_idx]; rc = smcr_link_init(lgr, lnk, link_idx, ini); if (rc) - goto free_lgr; + goto free_wq; lgr_list = &smc_lgr_list.list; lgr_lock = &smc_lgr_list.lock; atomic_inc(&lgr_cnt); @@ -448,6 +443,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) spin_unlock_bh(lgr_lock); return 0; +free_wq: + destroy_workqueue(lgr->tx_wq); free_lgr: kfree(lgr); ism_put_vlan: @@ -517,7 +514,7 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, smc->sk.sk_state != SMC_CLOSED) { rc = smcr_cdc_msg_send_validation(conn, pend, wr_buf); if (!rc) { - schedule_delayed_work(&conn->tx_work, 0); + queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, 0); smc->sk.sk_data_ready(&smc->sk); } } else { @@ -824,11 +821,10 @@ static void smc_lgr_free(struct smc_link_group *lgr) } smc_lgr_free_bufs(lgr); + destroy_workqueue(lgr->tx_wq); if (lgr->is_smcd) { - if (!lgr->terminating) { - smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); - put_device(&lgr->smcd->dev); - } + smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); + put_device(&lgr->smcd->dev); if (!atomic_dec_return(&lgr->smcd->lgr_cnt)) wake_up(&lgr->smcd->lgrs_deleted); } else { @@ -889,8 +885,6 @@ static void smc_lgr_cleanup(struct smc_link_group *lgr) if (lgr->is_smcd) { smc_ism_signal_shutdown(lgr); smcd_unregister_all_dmbs(lgr); - smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); - put_device(&lgr->smcd->dev); } else { u32 rsn = lgr->llc_termination_rsn; @@ -1296,9 +1290,9 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) lgr_list = ini->is_smcd ? &ini->ism_dev->lgr_list : &smc_lgr_list.list; lgr_lock = ini->is_smcd ? &ini->ism_dev->lgr_lock : &smc_lgr_list.lock; - ini->cln_first_contact = SMC_FIRST_CONTACT; + ini->first_contact_local = 1; role = smc->listen_smc ? SMC_SERV : SMC_CLNT; - if (role == SMC_CLNT && ini->srv_first_contact) + if (role == SMC_CLNT && ini->first_contact_peer) /* create new link group as well */ goto create; @@ -1307,14 +1301,14 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) list_for_each_entry(lgr, lgr_list, list) { write_lock_bh(&lgr->conns_lock); if ((ini->is_smcd ? - smcd_lgr_match(lgr, ini->ism_dev, ini->ism_gid) : + smcd_lgr_match(lgr, ini->ism_dev, ini->ism_peer_gid) : smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) && !lgr->sync_err && lgr->vlan_id == ini->vlan_id && (role == SMC_CLNT || ini->is_smcd || lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { /* link group found */ - ini->cln_first_contact = SMC_REUSE_CONTACT; + ini->first_contact_local = 0; conn->lgr = lgr; rc = smc_lgr_register_conn(conn, false); write_unlock_bh(&lgr->conns_lock); @@ -1328,8 +1322,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) if (rc) return rc; - if (role == SMC_CLNT && !ini->srv_first_contact && - ini->cln_first_contact == SMC_FIRST_CONTACT) { + if (role == SMC_CLNT && !ini->first_contact_peer && + ini->first_contact_local) { /* Server reuses a link group, but Client wants to start * a new one * send out_of_sync decline, reason synchr. error @@ -1338,7 +1332,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) } create: - if (ini->cln_first_contact == SMC_FIRST_CONTACT) { + if (ini->first_contact_local) { rc = smc_lgr_create(smc, ini); if (rc) goto out; @@ -1356,6 +1350,8 @@ create: if (ini->is_smcd) { conn->rx_off = sizeof(struct smcd_cdc_msg); smcd_cdc_rx_init(conn); /* init tasklet for this conn */ + } else { + conn->rx_off = 0; } #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); @@ -1777,6 +1773,7 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) list_del(&smc->conn.sndbuf_desc->list); mutex_unlock(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); + smc->conn.sndbuf_desc = NULL; } return rc; } @@ -1889,8 +1886,8 @@ int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *lnk, struct smc_clc_msg_accept_confirm *clc) { - conn->rtoken_idx = smc_rtoken_add(lnk, clc->rmb_dma_addr, - clc->rmb_rkey); + conn->rtoken_idx = smc_rtoken_add(lnk, clc->r0.rmb_dma_addr, + clc->r0.rmb_rkey); if (conn->rtoken_idx < 0) return conn->rtoken_idx; return 0; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 1c4d5439d0ff..37a5903789b0 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -137,9 +137,6 @@ struct smc_link { #define SMC_LINKS_PER_LGR_MAX 3 #define SMC_SINGLE_LINK 0 -#define SMC_FIRST_CONTACT 1 /* first contact to a peer */ -#define SMC_REUSE_CONTACT 0 /* follow-on contact to a peer*/ - /* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */ struct smc_buf_desc { struct list_head list; @@ -228,9 +225,9 @@ struct smc_link_group { u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ struct work_struct terminate_work; /* abnormal lgr termination */ + struct workqueue_struct *tx_wq; /* wq for conn. tx workers */ u8 sync_err : 1; /* lgr no longer fits to peer */ u8 terminating : 1;/* lgr is terminating */ - u8 freefast : 1; /* free worker scheduled fast */ u8 freeing : 1; /* lgr is being freed */ bool is_smcd; /* SMC-R or SMC-D */ @@ -294,9 +291,9 @@ struct smc_clc_msg_local; struct smc_init_info { u8 is_smcd; + u8 first_contact_peer; + u8 first_contact_local; unsigned short vlan_id; - int srv_first_contact; - int cln_first_contact; /* SMC-R */ struct smc_clc_msg_local *ib_lcl; struct smc_ib_device *ib_dev; @@ -304,7 +301,7 @@ struct smc_init_info { u8 ib_port; u32 ib_clcqpn; /* SMC-D */ - u64 ism_gid; + u64 ism_peer_gid; struct smcd_dev *ism_dev; }; diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index e1f64f4ba236..f15fca59b4b2 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -22,6 +22,15 @@ #include "smc.h" #include "smc_core.h" +struct smc_diag_dump_ctx { + int pos[2]; +}; + +static struct smc_diag_dump_ctx *smc_dump_context(struct netlink_callback *cb) +{ + return (struct smc_diag_dump_ctx *)cb->ctx; +} + static void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) { sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", @@ -170,13 +179,15 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { struct smc_connection *conn = &smc->conn; - struct smcd_diag_dmbinfo dinfo = { - .linkid = *((u32 *)conn->lgr->id), - .peer_gid = conn->lgr->peer_gid, - .my_gid = conn->lgr->smcd->local_gid, - .token = conn->rmb_desc->token, - .peer_token = conn->peer_token - }; + struct smcd_diag_dmbinfo dinfo; + + memset(&dinfo, 0, sizeof(dinfo)); + + dinfo.linkid = *((u32 *)conn->lgr->id); + dinfo.peer_gid = conn->lgr->peer_gid; + dinfo.my_gid = conn->lgr->smcd->local_gid; + dinfo.token = conn->rmb_desc->token; + dinfo.peer_token = conn->peer_token; if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0) goto errout; @@ -191,13 +202,15 @@ errout: } static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb, int p_type) { + struct smc_diag_dump_ctx *cb_ctx = smc_dump_context(cb); struct net *net = sock_net(skb->sk); + int snum = cb_ctx->pos[p_type]; struct nlattr *bc = NULL; struct hlist_head *head; + int rc = 0, num = 0; struct sock *sk; - int rc = 0; read_lock(&prot->h.smc_hash->lock); head = &prot->h.smc_hash->ht; @@ -207,13 +220,18 @@ static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb, sk_for_each(sk, head) { if (!net_eq(sock_net(sk), net)) continue; + if (num < snum) + goto next; rc = __smc_diag_dump(sk, skb, cb, nlmsg_data(cb->nlh), bc); - if (rc) - break; + if (rc < 0) + goto out; +next: + num++; } out: read_unlock(&prot->h.smc_hash->lock); + cb_ctx->pos[p_type] = num; return rc; } @@ -221,10 +239,10 @@ static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { int rc = 0; - rc = smc_diag_dump_proto(&smc_proto, skb, cb); + rc = smc_diag_dump_proto(&smc_proto, skb, cb, SMCPROTO_SMC); if (!rc) - rc = smc_diag_dump_proto(&smc_proto6, skb, cb); - return rc; + smc_diag_dump_proto(&smc_proto6, skb, cb, SMCPROTO_SMC6); + return skb->len; } static int smc_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index df5b0a6ea848..2db967f2fb50 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -841,6 +841,9 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) struct smc_init_info ini; int lnk_idx, rc = 0; + if (!llc->qp_mtu) + goto out_reject; + ini.vlan_id = lgr->vlan_id; smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); if (!memcmp(llc->sender_gid, link->peer_gid, SMC_GID_SIZE) && @@ -917,10 +920,20 @@ out: kfree(qentry); } +static bool smc_llc_is_empty_llc_message(union smc_llc_msg *llc) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(llc->raw.data); i++) + if (llc->raw.data[i]) + return false; + return true; +} + static bool smc_llc_is_local_add_link(union smc_llc_msg *llc) { if (llc->raw.hdr.common.type == SMC_LLC_ADD_LINK && - !llc->add_link.qp_mtu && !llc->add_link.link_num) + smc_llc_is_empty_llc_message(llc)) return true; return false; } @@ -1678,7 +1691,7 @@ static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc) spin_lock_irqsave(&lgr->llc_event_q_lock, flags); list_add_tail(&qentry->list, &lgr->llc_event_q); spin_unlock_irqrestore(&lgr->llc_event_q_lock, flags); - schedule_work(&lgr->llc_event_work); + queue_work(system_highpri_wq, &lgr->llc_event_work); } /* copy received msg and add it to the event queue */ diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 30e5fac7034e..70684c49510e 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -928,7 +928,10 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && - !ismdev->going_away) { + !ismdev->going_away && + (!ini->ism_peer_gid || + !smc_ism_cantalk(ini->ism_peer_gid, ini->vlan_id, + ismdev))) { ini->ism_dev = ismdev; break; } diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 54ba0443847e..4532c16bf85e 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -228,8 +228,8 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) /* for a corked socket defer the RDMA writes if there * is still sufficient sndbuf_space available */ - schedule_delayed_work(&conn->tx_work, - SMC_TX_CORK_DELAY); + queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, + SMC_TX_CORK_DELAY); else smc_tx_sndbuf_nonempty(conn); } /* while (msg_data_left(msg)) */ @@ -499,7 +499,7 @@ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) if (conn->killed) return -EPIPE; rc = 0; - mod_delayed_work(system_wq, &conn->tx_work, + mod_delayed_work(conn->lgr->tx_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } return rc; @@ -623,8 +623,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) return; if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && !conn->killed) { - schedule_delayed_work(&conn->tx_work, - SMC_TX_WORK_DELAY); + queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, + SMC_TX_WORK_DELAY); return; } } diff --git a/net/socket.c b/net/socket.c index dbbe8ea7d395..82262e1922f9 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2628,9 +2628,11 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { - /* disallow ancillary data requests from this path */ - if (msg->msg_control || msg->msg_controllen) - return -EINVAL; + if (msg->msg_control || msg->msg_controllen) { + /* disallow ancillary data reqs unless cmsg is plain data */ + if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY)) + return -EINVAL; + } return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } @@ -3610,7 +3612,7 @@ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) EXPORT_SYMBOL(kernel_getsockname); /** - * kernel_peername - get the address which the socket is connected (kernel space) + * kernel_getpeername - get the address which the socket is connected (kernel space) * @sock: socket * @addr: address holder * @@ -3671,7 +3673,7 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, EXPORT_SYMBOL(kernel_sendpage_locked); /** - * kernel_shutdown - shut down part of a full-duplex connection (kernel space) + * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket * @how: connection part * diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 90b8329fef82..8b300b74a722 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -137,7 +137,7 @@ gss_krb5_make_confounder(char *p, u32 conflen) switch (conflen) { case 16: *q++ = i++; - /* fall through */ + fallthrough; case 8: *q++ = i++; break; diff --git a/net/sunrpc/auth_gss/trace.c b/net/sunrpc/auth_gss/trace.c index d26036a57443..76685abba60f 100644 --- a/net/sunrpc/auth_gss/trace.c +++ b/net/sunrpc/auth_gss/trace.c @@ -9,7 +9,6 @@ #include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/auth_gss.h> #include <linux/sunrpc/gss_err.h> -#include <linux/sunrpc/auth_gss.h> #define CREATE_TRACE_POINTS #include <trace/events/rpcgss.h> diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index a91d1cdad9d7..62e0b6c1e8cf 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1702,7 +1702,7 @@ call_reserveresult(struct rpc_task *task) switch (status) { case -ENOMEM: rpc_delay(task, HZ >> 2); - /* fall through */ + fallthrough; case -EAGAIN: /* woken up; retry */ task->tk_action = call_retry_reserve; return; @@ -1759,13 +1759,13 @@ call_refreshresult(struct rpc_task *task) /* Use rate-limiting and a max number of retries if refresh * had status 0 but failed to update the cred. */ - /* fall through */ + fallthrough; case -ETIMEDOUT: rpc_delay(task, 3*HZ); - /* fall through */ + fallthrough; case -EAGAIN: status = -EACCES; - /* fall through */ + fallthrough; case -EKEYEXPIRED: if (!task->tk_cred_retry) break; @@ -2132,7 +2132,7 @@ call_connect_status(struct rpc_task *task) rpc_force_rebind(clnt); goto out_retry; } - /* fall through */ + fallthrough; case -ECONNRESET: case -ECONNABORTED: case -ENETDOWN: @@ -2146,7 +2146,7 @@ call_connect_status(struct rpc_task *task) break; /* retry with existing socket, after a delay */ rpc_delay(task, 3*HZ); - /* fall through */ + fallthrough; case -EADDRINUSE: case -ENOTCONN: case -EAGAIN: @@ -2228,7 +2228,7 @@ call_transmit_status(struct rpc_task *task) */ case -ENOBUFS: rpc_delay(task, HZ>>2); - /* fall through */ + fallthrough; case -EBADSLT: case -EAGAIN: task->tk_action = call_transmit; @@ -2247,7 +2247,7 @@ call_transmit_status(struct rpc_task *task) rpc_call_rpcerror(task, task->tk_status); return; } - /* fall through */ + fallthrough; case -ECONNRESET: case -ECONNABORTED: case -EADDRINUSE: @@ -2313,7 +2313,7 @@ call_bc_transmit_status(struct rpc_task *task) break; case -ENOBUFS: rpc_delay(task, HZ>>2); - /* fall through */ + fallthrough; case -EBADSLT: case -EAGAIN: task->tk_status = 0; @@ -2380,7 +2380,7 @@ call_status(struct rpc_task *task) * were a timeout. */ rpc_delay(task, 3*HZ); - /* fall through */ + fallthrough; case -ETIMEDOUT: break; case -ECONNREFUSED: @@ -2391,7 +2391,7 @@ call_status(struct rpc_task *task) break; case -EADDRINUSE: rpc_delay(task, 3*HZ); - /* fall through */ + fallthrough; case -EPIPE: case -EAGAIN: break; diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 999eee1ed61c..6c86e2a7d942 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -108,8 +108,10 @@ proc_dodebug(struct ctl_table *table, int write, void *buffer, size_t *lenp, left -= (s - tmpbuf); if (left && !isspace(*s)) return -EINVAL; - while (left && isspace(*s)) - left--, s++; + while (left && isspace(*s)) { + left--; + s++; + } } else left = 0; *(unsigned int *) table->data = value; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 6ba9d5842629..5a8e47bbfb9f 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1623,7 +1623,7 @@ void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) case -EAGAIN: xprt_add_backlog(xprt, task); dprintk("RPC: waiting for request slot\n"); - /* fall through */ + fallthrough; default: task->tk_status = -EAGAIN; } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 75c646743df3..3f86d039875c 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -268,7 +268,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DEVICE_REMOVAL: pr_info("rpcrdma: removing device %s for %pISpc\n", ep->re_id->device->name, sap); - /* fall through */ + fallthrough; case RDMA_CM_EVENT_ADDR_CHANGE: ep->re_connect_status = -ENODEV; goto disconnected; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c57aef829403..554e1bb4c1c7 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -885,7 +885,7 @@ static int xs_local_send_request(struct rpc_rqst *req) default: dprintk("RPC: sendmsg returned unrecognized error %d\n", -status); - /* fall through */ + fallthrough; case -EPIPE: xs_close(xprt); status = -ENOTCONN; @@ -1436,7 +1436,7 @@ static void xs_tcp_state_change(struct sock *sk) xprt->connect_cookie++; clear_bit(XPRT_CONNECTED, &xprt->state); xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT); - /* fall through */ + fallthrough; case TCP_CLOSING: /* * If the server closed down the connection, make sure that @@ -2202,7 +2202,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) switch (ret) { case 0: xs_set_srcport(transport, sock); - /* fall through */ + fallthrough; case -EINPROGRESS: /* SYN_SENT! */ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) @@ -2255,7 +2255,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) default: printk("%s: connect returned unhandled error %d\n", __func__, status); - /* fall through */ + fallthrough; case -EADDRNOTAVAIL: /* We're probably in TIME_WAIT. Get rid of existing socket, * and retry diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index 9dd780215eef..be1c4003d67d 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -6,6 +6,7 @@ menuconfig TIPC tristate "The TIPC Protocol" depends on INET + depends on IPV6 || IPV6=n help The Transparent Inter Process Communication (TIPC) protocol is specially designed for intra cluster communication. This protocol diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 808b147df7d5..650414110452 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -652,7 +652,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, test_and_set_bit_lock(0, &b->up); break; } - /* fall through */ + fallthrough; case NETDEV_GOING_DOWN: clear_bit_unlock(0, &b->up); tipc_reset_bearer(net, b); diff --git a/net/tipc/core.c b/net/tipc/core.c index 4f6dc74adf45..c2ff42900b53 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -60,6 +60,7 @@ static int __net_init tipc_init_net(struct net *net) tn->trial_addr = 0; tn->addr_trial_end = 0; tn->capabilities = TIPC_NODE_CAPABILITIES; + INIT_WORK(&tn->final_work.work, tipc_net_finalize_work); memset(tn->node_id, 0, sizeof(tn->node_id)); memset(tn->node_id_string, 0, sizeof(tn->node_id_string)); tn->mon_threshold = TIPC_DEF_MON_THRESHOLD; @@ -107,8 +108,13 @@ out_crypto: static void __net_exit tipc_exit_net(struct net *net) { + struct tipc_net *tn = tipc_net(net); + tipc_detach_loopback(net); + /* Make sure the tipc_net_finalize_work() finished */ + cancel_work_sync(&tn->final_work.work); tipc_net_stop(net); + tipc_bcast_stop(net); tipc_nametbl_stop(net); tipc_sk_rht_destroy(net); diff --git a/net/tipc/core.h b/net/tipc/core.h index 631d83c9705f..1d57a4d3b05e 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -90,6 +90,12 @@ extern unsigned int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; +struct tipc_net_work { + struct work_struct work; + struct net *net; + u32 addr; +}; + struct tipc_net { u8 node_id[NODE_ID_LEN]; u32 node_addr; @@ -143,6 +149,8 @@ struct tipc_net { /* TX crypto handler */ struct tipc_crypto *crypto_tx; #endif + /* Work item for net finalize */ + struct tipc_net_work final_work; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 001bcb0f2480..7c523dc81575 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -326,7 +326,8 @@ static void tipc_aead_free(struct rcu_head *rp) if (aead->cloned) { tipc_aead_put(aead->cloned); } else { - head = *this_cpu_ptr(aead->tfm_entry); + head = *get_cpu_ptr(aead->tfm_entry); + put_cpu_ptr(aead->tfm_entry); list_for_each_entry_safe(tfm_entry, tmp, &head->list, list) { crypto_free_aead(tfm_entry->tfm); list_del(&tfm_entry->list); @@ -399,10 +400,15 @@ static void tipc_aead_users_set(struct tipc_aead __rcu *aead, int val) */ static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead) { - struct tipc_tfm **tfm_entry = this_cpu_ptr(aead->tfm_entry); + struct tipc_tfm **tfm_entry; + struct crypto_aead *tfm; + tfm_entry = get_cpu_ptr(aead->tfm_entry); *tfm_entry = list_next_entry(*tfm_entry, list); - return (*tfm_entry)->tfm; + tfm = (*tfm_entry)->tfm; + put_cpu_ptr(tfm_entry); + + return tfm; } /** @@ -757,10 +763,12 @@ static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err) switch (err) { case 0: this_cpu_inc(tx->stats->stat[STAT_ASYNC_OK]); + rcu_read_lock(); if (likely(test_bit(0, &b->up))) b->media->send_msg(net, skb, b, &tx_ctx->dst); else kfree_skb(skb); + rcu_read_unlock(); break; case -EINPROGRESS: return; diff --git a/net/tipc/group.c b/net/tipc/group.c index 89257e2a980d..588c2d2b0c69 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -536,7 +536,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, update = true; deliver = false; } - /* Fall thru */ + fallthrough; case TIPC_GRP_BCAST_MSG: m->bc_rcv_nxt++; ack = msg_grp_bc_ack_req(hdr); diff --git a/net/tipc/link.c b/net/tipc/link.c index 107578122973..a2989f22ebb6 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -216,11 +216,6 @@ enum { #define TIPC_BC_RETR_LIM (jiffies + msecs_to_jiffies(10)) #define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1)) -/* - * Interval between NACKs when packets arrive out of order - */ -#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2) - /* Link FSM states: */ enum { @@ -1239,7 +1234,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, skb_queue_tail(mc_inputq, skb); return true; } - /* fall through */ + fallthrough; case CONN_MANAGER: skb_queue_tail(inputq, skb); return true; diff --git a/net/tipc/net.c b/net/tipc/net.c index 85400e4242de..0bb2323201da 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -105,12 +105,6 @@ * - A local spin_lock protecting the queue of subscriber events. */ -struct tipc_net_work { - struct work_struct work; - struct net *net; - u32 addr; -}; - static void tipc_net_finalize(struct net *net, u32 addr); int tipc_net_init(struct net *net, u8 *node_id, u32 addr) @@ -142,25 +136,21 @@ static void tipc_net_finalize(struct net *net, u32 addr) TIPC_CLUSTER_SCOPE, 0, addr); } -static void tipc_net_finalize_work(struct work_struct *work) +void tipc_net_finalize_work(struct work_struct *work) { struct tipc_net_work *fwork; fwork = container_of(work, struct tipc_net_work, work); tipc_net_finalize(fwork->net, fwork->addr); - kfree(fwork); } void tipc_sched_net_finalize(struct net *net, u32 addr) { - struct tipc_net_work *fwork = kzalloc(sizeof(*fwork), GFP_ATOMIC); + struct tipc_net *tn = tipc_net(net); - if (!fwork) - return; - INIT_WORK(&fwork->work, tipc_net_finalize_work); - fwork->net = net; - fwork->addr = addr; - schedule_work(&fwork->work); + tn->final_work.net = net; + tn->final_work.addr = addr; + schedule_work(&tn->final_work.work); } void tipc_net_stop(struct net *net) diff --git a/net/tipc/net.h b/net/tipc/net.h index 6740d97c706e..d0c91d2df20a 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -42,6 +42,7 @@ extern const struct nla_policy tipc_nl_net_policy[]; int tipc_net_init(struct net *net, u8 *node_id, u32 addr); +void tipc_net_finalize_work(struct work_struct *work); void tipc_sched_net_finalize(struct net *net, u32 addr); void tipc_net_stop(struct net *net); int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 217516357ef2..90e3c70a91ad 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -275,8 +275,9 @@ err_out: static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg) { - int err; + struct nlmsghdr *nlh; struct sk_buff *arg; + int err; if (msg->req_type && (!msg->req_size || !TLV_CHECK_TYPE(msg->req, msg->req_type))) @@ -305,6 +306,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; } + nlh = nlmsg_put(arg, 0, 0, tipc_genl_family.id, 0, NLM_F_MULTI); + if (!nlh) { + kfree_skb(arg); + kfree_skb(msg->rep); + msg->rep = NULL; + return -EMSGSIZE; + } + nlmsg_end(arg, nlh); + err = __tipc_nl_compat_dumpit(cmd, msg, arg); if (err) { kfree_skb(msg->rep); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 07419f36116a..dd93e8ecb2f4 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -52,7 +52,6 @@ #define NAGLE_START_MAX 1024 #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ #define CONN_PROBING_INTV msecs_to_jiffies(3600000) /* [ms] => 1 h */ -#define TIPC_FWD_MSG 1 #define TIPC_MAX_PORT 0xffffffff #define TIPC_MIN_PORT 1 #define TIPC_ACK_RATE 4 /* ACK at 1/4 of of rcv window size */ @@ -783,7 +782,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, case TIPC_ESTABLISHED: if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk)) revents |= EPOLLOUT; - /* fall through */ + fallthrough; case TIPC_LISTEN: case TIPC_CONNECTING: if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) @@ -2597,7 +2596,7 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, * case is EINPROGRESS, rather than EALREADY. */ res = -EINPROGRESS; - /* fall through */ + fallthrough; case TIPC_CONNECTING: if (!timeout) { if (previous == TIPC_CONNECTING) @@ -2771,18 +2770,21 @@ static int tipc_shutdown(struct socket *sock, int how) trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " "); __tipc_shutdown(sock, TIPC_CONN_SHUTDOWN); - sk->sk_shutdown = SEND_SHUTDOWN; + if (tipc_sk_type_connectionless(sk)) + sk->sk_shutdown = SHUTDOWN_MASK; + else + sk->sk_shutdown = SEND_SHUTDOWN; if (sk->sk_state == TIPC_DISCONNECTING) { /* Discard any unreceived messages */ __skb_queue_purge(&sk->sk_receive_queue); - /* Wake up anyone sleeping in poll */ - sk->sk_state_change(sk); res = 0; } else { res = -ENOTCONN; } + /* Wake up anyone sleeping in poll. */ + sk->sk_state_change(sk); release_sock(sk); return res; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 53f0de0676b7..911d13cd2e67 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -660,6 +660,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, struct udp_tunnel_sock_cfg tuncfg = {NULL}; struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; u8 node_id[NODE_ID_LEN] = {0,}; + struct net_device *dev; int rmcast = 0; ub = kzalloc(sizeof(*ub), GFP_ATOMIC); @@ -714,8 +715,6 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, rcu_assign_pointer(ub->bearer, b); tipc_udp_media_addr_set(&b->addr, &local); if (local.proto == htons(ETH_P_IP)) { - struct net_device *dev; - dev = __ip_dev_find(net, local.ipv4.s_addr, false); if (!dev) { err = -ENODEV; @@ -738,9 +737,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, b->mtu = b->media->mtu; #if IS_ENABLED(CONFIG_IPV6) } else if (local.proto == htons(ETH_P_IPV6)) { - struct net_device *dev; - - dev = ipv6_dev_find(net, &local.ipv6); + dev = ub->ifindex ? __dev_get_by_index(net, ub->ifindex) : NULL; + dev = ipv6_dev_find(net, &local.ipv6, dev); if (!dev) { err = -ENODEV; goto err; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index bbc52b088d29..002b0859fed5 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -330,12 +330,13 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) tls_ctx_free(sk, ctx); } -static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, - int __user *optlen) +static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, + int __user *optlen, int tx) { int rc = 0; struct tls_context *ctx = tls_get_ctx(sk); struct tls_crypto_info *crypto_info; + struct cipher_context *cctx; int len; if (get_user(len, optlen)) @@ -352,7 +353,13 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } /* get user crypto info */ - crypto_info = &ctx->crypto_send.info; + if (tx) { + crypto_info = &ctx->crypto_send.info; + cctx = &ctx->tx; + } else { + crypto_info = &ctx->crypto_recv.info; + cctx = &ctx->rx; + } if (!TLS_CRYPTO_INFO_READY(crypto_info)) { rc = -EBUSY; @@ -379,9 +386,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } lock_sock(sk); memcpy(crypto_info_aes_gcm_128->iv, - ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); - memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->tx.rec_seq, + memcpy(crypto_info_aes_gcm_128->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE); release_sock(sk); if (copy_to_user(optval, @@ -403,9 +410,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } lock_sock(sk); memcpy(crypto_info_aes_gcm_256->iv, - ctx->tx.iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, + cctx->iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, TLS_CIPHER_AES_GCM_256_IV_SIZE); - memcpy(crypto_info_aes_gcm_256->rec_seq, ctx->tx.rec_seq, + memcpy(crypto_info_aes_gcm_256->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE); release_sock(sk); if (copy_to_user(optval, @@ -429,7 +436,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname, switch (optname) { case TLS_TX: - rc = do_tls_getsockopt_tx(sk, optval, optlen); + case TLS_RX: + rc = do_tls_getsockopt_conf(sk, optval, optlen, + optname == TLS_TX); break; default: rc = -ENOPROTOOPT; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 181ea6fb56a6..92784e51ee7d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -837,7 +837,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol, */ case SOCK_RAW: sock->type = SOCK_DGRAM; - /* fall through */ + fallthrough; case SOCK_DGRAM: sock->ops = &unix_dgram_ops; break; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 90f0f82cd9ca..6a6f2f214c10 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -10,6 +10,7 @@ */ #include <linux/export.h> +#include <linux/bitfield.h> #include <net/cfg80211.h> #include "core.h" #include "rdev-ops.h" @@ -912,6 +913,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, struct ieee80211_sta_vht_cap *vht_cap; struct ieee80211_edmg *edmg_cap; u32 width, control_freq, cap; + bool support_80_80 = false; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -957,7 +959,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, if (!ht_cap->ht_supported && chandef->chan->band != NL80211_BAND_6GHZ) return false; - /* fall through */ + fallthrough; case NL80211_CHAN_WIDTH_20_NOHT: prohibited_flags |= IEEE80211_CHAN_NO_20MHZ; width = 20; @@ -979,11 +981,15 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; break; case NL80211_CHAN_WIDTH_80P80: - cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; - if (chandef->chan->band != NL80211_BAND_6GHZ && - cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + cap = vht_cap->cap; + support_80_80 = + (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || + (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || + u32_get_bits(cap, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) > 1; + if (chandef->chan->band != NL80211_BAND_6GHZ && !support_80_80) return false; - /* fall through */ + fallthrough; case NL80211_CHAN_WIDTH_80: prohibited_flags |= IEEE80211_CHAN_NO_80MHZ; width = 80; @@ -1001,7 +1007,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && - cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ && + !(vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)) return false; break; default: diff --git a/net/wireless/core.h b/net/wireless/core.h index 67b0389fca4d..2ebc2a66680d 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -466,8 +466,8 @@ extern struct work_struct cfg80211_disconnect_work; * * Checks if chandef is usable and we can/need start CAC on such channel. * - * Return: Return true if all channels available and at least - * one channel require CAC (NL80211_DFS_USABLE) + * Return: true if all channels available and at least + * one channel requires CAC (NL80211_DFS_USABLE) */ bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index a6c61a2e6569..db7333e20dd7 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -941,7 +941,7 @@ void cfg80211_cac_event(struct net_device *netdev, sizeof(struct cfg80211_chan_def)); queue_work(cfg80211_wq, &rdev->propagate_cac_done_wk); cfg80211_sched_dfs_chan_update(rdev); - /* fall through */ + fallthrough; case NL80211_RADAR_CAC_ABORTED: wdev->cac_started = false; break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c04fc6cf6583..52a35e788547 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -336,6 +336,13 @@ static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = { .len = NL80211_MAX_SUPP_HT_RATES }, [NL80211_TXRATE_VHT] = NLA_POLICY_EXACT_LEN_WARN(sizeof(struct nl80211_txrate_vht)), [NL80211_TXRATE_GI] = { .type = NLA_U8 }, + [NL80211_TXRATE_HE] = NLA_POLICY_EXACT_LEN(sizeof(struct nl80211_txrate_he)), + [NL80211_TXRATE_HE_GI] = NLA_POLICY_RANGE(NLA_U8, + NL80211_RATE_INFO_HE_GI_0_8, + NL80211_RATE_INFO_HE_GI_3_2), + [NL80211_TXRATE_HE_LTF] = NLA_POLICY_RANGE(NLA_U8, + NL80211_RATE_INFO_HE_1XLTF, + NL80211_RATE_INFO_HE_4XLTF), }; static const struct nla_policy @@ -539,7 +546,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 }, [NL80211_ATTR_WDEV] = { .type = NLA_U64 }, [NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 }, - [NL80211_ATTR_AUTH_DATA] = { .type = NLA_BINARY, }, + + /* need to include at least Auth Transaction and Status Code */ + [NL80211_ATTR_AUTH_DATA] = NLA_POLICY_MIN_LEN(4), + [NL80211_ATTR_VHT_CAPABILITY] = NLA_POLICY_EXACT_LEN_WARN(NL80211_VHT_CAPABILITY_LEN), [NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 }, [NL80211_ATTR_P2P_CTWINDOW] = NLA_POLICY_MAX(NLA_U8, 127), @@ -561,23 +571,30 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY, .len = IEEE80211_MAX_DATA_LEN }, [NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 }, - [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 }, + [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = + NLA_POLICY_MAX(NLA_U16, NL80211_CRIT_PROTO_MAX_DURATION), [NL80211_ATTR_PEER_AID] = NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID), [NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 }, [NL80211_ATTR_CH_SWITCH_BLOCK_TX] = { .type = NLA_FLAG }, [NL80211_ATTR_CSA_IES] = { .type = NLA_NESTED }, - [NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_BINARY }, - [NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_BINARY }, - [NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY }, - [NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY }, + [NL80211_ATTR_CNTDWN_OFFS_BEACON] = { .type = NLA_BINARY }, + [NL80211_ATTR_CNTDWN_OFFS_PRESP] = { .type = NLA_BINARY }, + [NL80211_ATTR_STA_SUPPORTED_CHANNELS] = NLA_POLICY_MIN_LEN(2), + /* + * The value of the Length field of the Supported Operating + * Classes element is between 2 and 253. + */ + [NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = + NLA_POLICY_RANGE(NLA_BINARY, 2, 253), [NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG }, [NL80211_ATTR_OPMODE_NOTIF] = { .type = NLA_U8 }, [NL80211_ATTR_VENDOR_ID] = { .type = NLA_U32 }, [NL80211_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, - [NL80211_ATTR_QOS_MAP] = { .type = NLA_BINARY, - .len = IEEE80211_QOS_MAP_LEN_MAX }, + [NL80211_ATTR_QOS_MAP] = NLA_POLICY_RANGE(NLA_BINARY, + IEEE80211_QOS_MAP_LEN_MIN, + IEEE80211_QOS_MAP_LEN_MAX), [NL80211_ATTR_MAC_HINT] = NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN), [NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 }, [NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 }, @@ -625,15 +642,17 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { .len = FILS_ERP_MAX_RRK_LEN }, [NL80211_ATTR_FILS_CACHE_ID] = NLA_POLICY_EXACT_LEN_WARN(2), [NL80211_ATTR_PMK] = { .type = NLA_BINARY, .len = PMK_MAX_LEN }, + [NL80211_ATTR_PMKR0_NAME] = NLA_POLICY_EXACT_LEN(WLAN_PMK_NAME_LEN), [NL80211_ATTR_SCHED_SCAN_MULTI] = { .type = NLA_FLAG }, [NL80211_ATTR_EXTERNAL_AUTH_SUPPORT] = { .type = NLA_FLAG }, [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, - [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY, - .len = NL80211_HE_MAX_CAPABILITY_LEN }, - + [NL80211_ATTR_HE_CAPABILITY] = + NLA_POLICY_RANGE(NLA_BINARY, + NL80211_HE_MIN_CAPABILITY_LEN, + NL80211_HE_MAX_CAPABILITY_LEN), [NL80211_ATTR_FTM_RESPONDER] = NLA_POLICY_NESTED(nl80211_ftm_responder_policy), [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), @@ -654,10 +673,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_RECEIVE_MULTICAST] = { .type = NLA_FLAG }, [NL80211_ATTR_WIPHY_FREQ_OFFSET] = NLA_POLICY_RANGE(NLA_U32, 0, 999), [NL80211_ATTR_SCAN_FREQ_KHZ] = { .type = NLA_NESTED }, - [NL80211_ATTR_HE_6GHZ_CAPABILITY] = { - .type = NLA_EXACT_LEN, - .len = sizeof(struct ieee80211_he_6ghz_capa), - }, + [NL80211_ATTR_HE_6GHZ_CAPABILITY] = + NLA_POLICY_EXACT_LEN(sizeof(struct ieee80211_he_6ghz_capa)), }; /* policy for the key attributes */ @@ -703,7 +720,7 @@ nl80211_wowlan_tcp_policy[NUM_NL80211_WOWLAN_TCP] = { [NL80211_WOWLAN_TCP_DST_MAC] = NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN), [NL80211_WOWLAN_TCP_SRC_PORT] = { .type = NLA_U16 }, [NL80211_WOWLAN_TCP_DST_PORT] = { .type = NLA_U16 }, - [NL80211_WOWLAN_TCP_DATA_PAYLOAD] = { .type = NLA_MIN_LEN, .len = 1 }, + [NL80211_WOWLAN_TCP_DATA_PAYLOAD] = NLA_POLICY_MIN_LEN(1), [NL80211_WOWLAN_TCP_DATA_PAYLOAD_SEQ] = { .len = sizeof(struct nl80211_wowlan_tcp_data_seq) }, @@ -711,8 +728,8 @@ nl80211_wowlan_tcp_policy[NUM_NL80211_WOWLAN_TCP] = { .len = sizeof(struct nl80211_wowlan_tcp_data_token) }, [NL80211_WOWLAN_TCP_DATA_INTERVAL] = { .type = NLA_U32 }, - [NL80211_WOWLAN_TCP_WAKE_PAYLOAD] = { .type = NLA_MIN_LEN, .len = 1 }, - [NL80211_WOWLAN_TCP_WAKE_MASK] = { .type = NLA_MIN_LEN, .len = 1 }, + [NL80211_WOWLAN_TCP_WAKE_PAYLOAD] = NLA_POLICY_MIN_LEN(1), + [NL80211_WOWLAN_TCP_WAKE_MASK] = NLA_POLICY_MIN_LEN(1), }; #endif /* CONFIG_PM */ @@ -738,7 +755,7 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { .type = NLA_BINARY, .len = NL80211_KCK_EXT_LEN }, - [NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN_WARN(NL80211_REPLAY_CTR_LEN), + [NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN(NL80211_REPLAY_CTR_LEN), [NL80211_REKEY_DATA_AKM] = { .type = NLA_U32 }, }; @@ -778,7 +795,8 @@ nl80211_bss_select_policy[NL80211_BSS_SELECT_ATTR_MAX + 1] = { /* policy for NAN function attributes */ static const struct nla_policy nl80211_nan_func_policy[NL80211_NAN_FUNC_ATTR_MAX + 1] = { - [NL80211_NAN_FUNC_TYPE] = { .type = NLA_U8 }, + [NL80211_NAN_FUNC_TYPE] = + NLA_POLICY_MAX(NLA_U8, NL80211_NAN_FUNC_MAX_TYPE), [NL80211_NAN_FUNC_SERVICE_ID] = { .len = NL80211_NAN_FUNC_SERVICE_ID_LEN }, [NL80211_NAN_FUNC_PUBLISH_TYPE] = { .type = NLA_U8 }, @@ -2107,7 +2125,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 1: if (nla_put(msg, NL80211_ATTR_CIPHER_SUITES, sizeof(u32) * rdev->wiphy.n_cipher_suites, @@ -2154,7 +2172,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 2: if (nl80211_put_iftypes(msg, NL80211_ATTR_SUPPORTED_IFTYPES, rdev->wiphy.interface_modes)) @@ -2162,7 +2180,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 3: nl_bands = nla_nest_start_noflag(msg, NL80211_ATTR_WIPHY_BANDS); @@ -2189,7 +2207,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->chan_start++; if (state->split) break; - /* fall through */ + fallthrough; default: /* add frequencies */ nl_freqs = nla_nest_start_noflag(msg, @@ -2244,7 +2262,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 4: nl_cmds = nla_nest_start_noflag(msg, NL80211_ATTR_SUPPORTED_COMMANDS); @@ -2273,7 +2291,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 5: if (rdev->ops->remain_on_channel && (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) && @@ -2291,7 +2309,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 6: #ifdef CONFIG_PM if (nl80211_send_wowlan(msg, rdev, state->split)) @@ -2302,7 +2320,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, #else state->split_start++; #endif - /* fall through */ + fallthrough; case 7: if (nl80211_put_iftypes(msg, NL80211_ATTR_SOFTWARE_IFTYPES, rdev->wiphy.software_iftypes)) @@ -2315,7 +2333,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 8: if ((rdev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) && nla_put_u32(msg, NL80211_ATTR_DEVICE_AP_SME, @@ -4419,21 +4437,106 @@ static bool vht_set_mcs_mask(struct ieee80211_supported_band *sband, return true; } +static u16 he_mcs_map_to_mcs_mask(u8 he_mcs_map) +{ + switch (he_mcs_map) { + case IEEE80211_HE_MCS_NOT_SUPPORTED: + return 0; + case IEEE80211_HE_MCS_SUPPORT_0_7: + return 0x00FF; + case IEEE80211_HE_MCS_SUPPORT_0_9: + return 0x03FF; + case IEEE80211_HE_MCS_SUPPORT_0_11: + return 0xFFF; + default: + break; + } + return 0; +} + +static void he_build_mcs_mask(u16 he_mcs_map, + u16 he_mcs_mask[NL80211_HE_NSS_MAX]) +{ + u8 nss; + + for (nss = 0; nss < NL80211_HE_NSS_MAX; nss++) { + he_mcs_mask[nss] = he_mcs_map_to_mcs_mask(he_mcs_map & 0x03); + he_mcs_map >>= 2; + } +} + +static u16 he_get_txmcsmap(struct genl_info *info, + const struct ieee80211_sta_he_cap *he_cap) +{ + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + __le16 tx_mcs; + + switch (wdev->chandef.width) { + case NL80211_CHAN_WIDTH_80P80: + tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80p80; + break; + case NL80211_CHAN_WIDTH_160: + tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_160; + break; + default: + tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80; + break; + } + return le16_to_cpu(tx_mcs); +} + +static bool he_set_mcs_mask(struct genl_info *info, + struct wireless_dev *wdev, + struct ieee80211_supported_band *sband, + struct nl80211_txrate_he *txrate, + u16 mcs[NL80211_HE_NSS_MAX]) +{ + const struct ieee80211_sta_he_cap *he_cap; + u16 tx_mcs_mask[NL80211_HE_NSS_MAX] = {}; + u16 tx_mcs_map = 0; + u8 i; + + he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype); + if (!he_cap) + return false; + + memset(mcs, 0, sizeof(u16) * NL80211_HE_NSS_MAX); + + tx_mcs_map = he_get_txmcsmap(info, he_cap); + + /* Build he_mcs_mask from HE capabilities */ + he_build_mcs_mask(tx_mcs_map, tx_mcs_mask); + + for (i = 0; i < NL80211_HE_NSS_MAX; i++) { + if ((tx_mcs_mask[i] & txrate->mcs[i]) == txrate->mcs[i]) + mcs[i] = txrate->mcs[i]; + else + return false; + } + + return true; +} + static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, struct nlattr *attrs[], enum nl80211_attrs attr, - struct cfg80211_bitrate_mask *mask) + struct cfg80211_bitrate_mask *mask, + struct net_device *dev) { struct nlattr *tb[NL80211_TXRATE_MAX + 1]; struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = dev->ieee80211_ptr; int rem, i; struct nlattr *tx_rates; struct ieee80211_supported_band *sband; - u16 vht_tx_mcs_map; + u16 vht_tx_mcs_map, he_tx_mcs_map; memset(mask, 0, sizeof(*mask)); /* Default to all rates enabled */ for (i = 0; i < NUM_NL80211_BANDS; i++) { + const struct ieee80211_sta_he_cap *he_cap; + sband = rdev->wiphy.bands[i]; if (!sband) @@ -4449,6 +4552,16 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); vht_build_mcs_mask(vht_tx_mcs_map, mask->control[i].vht_mcs); + + he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype); + if (!he_cap) + continue; + + he_tx_mcs_map = he_get_txmcsmap(info, he_cap); + he_build_mcs_mask(he_tx_mcs_map, mask->control[i].he_mcs); + + mask->control[i].he_gi = 0xFF; + mask->control[i].he_ltf = 0xFF; } /* if no rates are given set it back to the defaults */ @@ -4504,13 +4617,25 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, if (mask->control[band].gi > NL80211_TXRATE_FORCE_LGI) return -EINVAL; } + if (tb[NL80211_TXRATE_HE] && + !he_set_mcs_mask(info, wdev, sband, + nla_data(tb[NL80211_TXRATE_HE]), + mask->control[band].he_mcs)) + return -EINVAL; + if (tb[NL80211_TXRATE_HE_GI]) + mask->control[band].he_gi = + nla_get_u8(tb[NL80211_TXRATE_HE_GI]); + if (tb[NL80211_TXRATE_HE_LTF]) + mask->control[band].he_ltf = + nla_get_u8(tb[NL80211_TXRATE_HE_LTF]); if (mask->control[band].legacy == 0) { - /* don't allow empty legacy rates if HT or VHT + /* don't allow empty legacy rates if HT, VHT or HE * are not even supported. */ if (!(rdev->wiphy.bands[band]->ht_cap.ht_supported || - rdev->wiphy.bands[band]->vht_cap.vht_supported)) + rdev->wiphy.bands[band]->vht_cap.vht_supported || + ieee80211_get_he_iftype_cap(sband, wdev->iftype))) return -EINVAL; for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) @@ -4521,6 +4646,10 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, if (mask->control[band].vht_mcs[i]) goto out; + for (i = 0; i < NL80211_HE_NSS_MAX; i++) + if (mask->control[band].he_mcs[i]) + goto out; + /* legacy and mcs rates may not be both empty */ return -EINVAL; } @@ -4831,8 +4960,9 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev, return false; return true; case NL80211_CMD_START_AP: - /* SAE not supported yet */ - if (auth_type == NL80211_AUTHTYPE_SAE) + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP) && + auth_type == NL80211_AUTHTYPE_SAE) return false; /* FILS not supported yet */ if (auth_type == NL80211_AUTHTYPE_FILS_SK || @@ -4896,8 +5026,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) params.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); params.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid_len == 0 || - params.ssid_len > IEEE80211_MAX_SSID_LEN) + if (params.ssid_len == 0) return -EINVAL; } @@ -4966,7 +5095,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TX_RATES]) { err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, - ¶ms.beacon_rate); + ¶ms.beacon_rate, + dev); if (err) return err; @@ -5207,7 +5337,7 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr) break; default: WARN_ON(1); - /* fall through */ + fallthrough; case RATE_INFO_BW_20: rate_flg = 0; break; @@ -5837,11 +5967,9 @@ static int nl80211_parse_sta_channel_info(struct genl_info *info, nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_CHANNELS]); /* * Need to include at least one (first channel, number of - * channels) tuple for each subband, and must have proper - * tuples for the rest of the data as well. + * channels) tuple for each subband (checked in policy), + * and must have proper tuples for the rest of the data as well. */ - if (params->supported_channels_len < 2) - return -EINVAL; if (params->supported_channels_len % 2) return -EINVAL; } @@ -5851,13 +5979,6 @@ static int nl80211_parse_sta_channel_info(struct genl_info *info, nla_data(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]); params->supported_oper_classes_len = nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]); - /* - * The value of the Length field of the Supported Operating - * Classes element is between 2 and 253. - */ - if (params->supported_oper_classes_len < 2 || - params->supported_oper_classes_len > 253) - return -EINVAL; } return 0; } @@ -5880,9 +6001,6 @@ static int nl80211_set_station_tdls(struct genl_info *info, nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); params->he_capa_len = nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); - - if (params->he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) - return -EINVAL; } err = nl80211_parse_sta_channel_info(info, params); @@ -6011,7 +6129,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) params.he_6ghz_capa = - nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + nla_data(info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]); if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) params.airtime_weight = @@ -6141,10 +6259,6 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); params.he_capa_len = nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); - - /* max len is validated in nla policy */ - if (params.he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) - return -EINVAL; } if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) @@ -8416,23 +8530,14 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, } if (ssid) { - if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) { - err = -EINVAL; - goto out_free; - } memcpy(request->match_sets[i].ssid.ssid, nla_data(ssid), nla_len(ssid)); request->match_sets[i].ssid.ssid_len = nla_len(ssid); } - if (bssid) { - if (nla_len(bssid) != ETH_ALEN) { - err = -EINVAL; - goto out_free; - } + if (bssid) memcpy(request->match_sets[i].bssid, nla_data(bssid), ETH_ALEN); - } /* special attribute - old implementation w/a */ request->match_sets[i].rssi_thold = default_match_rssi; @@ -8787,10 +8892,10 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) if (err) return err; - if (!csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]) + if (!csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]) return -EINVAL; - len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]); + len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); if (!len || (len % sizeof(u16))) return -EINVAL; @@ -8801,7 +8906,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) return -EINVAL; params.counter_offsets_beacon = - nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]); + nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); /* sanity checks - counters should fit and be the same */ for (i = 0; i < params.n_counter_offsets_beacon; i++) { @@ -8814,8 +8919,8 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - if (csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]) { - len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]); + if (csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]) { + len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); if (!len || (len % sizeof(u16))) return -EINVAL; @@ -8826,7 +8931,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) return -EINVAL; params.counter_offsets_presp = - nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]); + nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); /* sanity checks - counters should fit and be the same */ for (i = 0; i < params.n_counter_offsets_presp; i++) { @@ -9309,9 +9414,6 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) return -EINVAL; auth_data = nla_data(info->attrs[NL80211_ATTR_AUTH_DATA]); auth_data_len = nla_len(info->attrs[NL80211_ATTR_AUTH_DATA]); - /* need to include at least Auth Transaction and Status Code */ - if (auth_data_len < 4) - return -EINVAL; } local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; @@ -9451,7 +9553,9 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, if (info->attrs[NL80211_ATTR_SAE_PASSWORD]) { if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_SAE_OFFLOAD)) + NL80211_EXT_FEATURE_SAE_OFFLOAD) && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP)) return -EINVAL; settings->sae_pwd = nla_data(info->attrs[NL80211_ATTR_SAE_PASSWORD]); @@ -10798,7 +10902,8 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, return -EOPNOTSUPP; err = nl80211_parse_tx_bitrate_mask(info, info->attrs, - NL80211_ATTR_TX_RATES, &mask); + NL80211_ATTR_TX_RATES, &mask, + dev); if (err) return err; @@ -11406,7 +11511,8 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TX_RATES]) { err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, - &setup.beacon_rate); + &setup.beacon_rate, + dev); if (err) return err; @@ -12358,8 +12464,6 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] || !tb[NL80211_REKEY_DATA_KCK]) return -EINVAL; - if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN) - return -ERANGE; if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN && !(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK && nla_len(tb[NL80211_REKEY_DATA_KEK]) == NL80211_KEK_EXT_LEN)) @@ -12684,8 +12788,7 @@ static int nl80211_nan_add_func(struct sk_buff *skb, func->cookie = cfg80211_assign_cookie(rdev); - if (!tb[NL80211_NAN_FUNC_TYPE] || - nla_get_u8(tb[NL80211_NAN_FUNC_TYPE]) > NL80211_NAN_FUNC_MAX_TYPE) { + if (!tb[NL80211_NAN_FUNC_TYPE]) { err = -EINVAL; goto out; } @@ -13175,9 +13278,6 @@ static int nl80211_crit_protocol_start(struct sk_buff *skb, duration = nla_get_u16(info->attrs[NL80211_ATTR_MAX_CRIT_PROT_DURATION]); - if (duration > NL80211_CRIT_PROTO_MAX_DURATION) - return -ERANGE; - ret = rdev_crit_proto_start(rdev, wdev, proto, duration); if (!ret) rdev->crit_proto_nlportid = info->snd_portid; @@ -13562,8 +13662,7 @@ static int nl80211_set_qos_map(struct sk_buff *skb, pos = nla_data(info->attrs[NL80211_ATTR_QOS_MAP]); len = nla_len(info->attrs[NL80211_ATTR_QOS_MAP]); - if (len % 2 || len < IEEE80211_QOS_MAP_LEN_MIN || - len > IEEE80211_QOS_MAP_LEN_MAX) + if (len % 2) return -EINVAL; qos_map = kzalloc(sizeof(struct cfg80211_qos_map), GFP_KERNEL); @@ -13831,17 +13930,9 @@ static int nl80211_set_pmk(struct sk_buff *skb, struct genl_info *info) goto out; } - if (info->attrs[NL80211_ATTR_PMKR0_NAME]) { - int r0_name_len = nla_len(info->attrs[NL80211_ATTR_PMKR0_NAME]); - - if (r0_name_len != WLAN_PMK_NAME_LEN) { - ret = -EINVAL; - goto out; - } - + if (info->attrs[NL80211_ATTR_PMKR0_NAME]) pmk_conf.pmk_r0_name = nla_data(info->attrs[NL80211_ATTR_PMKR0_NAME]); - } ret = rdev_set_pmk(rdev, dev, &pmk_conf); out: @@ -13900,8 +13991,7 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_SSID]) { params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid.ssid_len == 0 || - params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) + if (params.ssid.ssid_len == 0) return -EINVAL; memcpy(params.ssid.ssid, nla_data(info->attrs[NL80211_ATTR_SSID]), @@ -14202,7 +14292,7 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev, if (tid_conf->txrate_type != NL80211_TX_RATE_AUTOMATIC) { attr = NL80211_TID_CONFIG_ATTR_TX_RATE; err = nl80211_parse_tx_bitrate_mask(info, attrs, attr, - &tid_conf->txrate_mask); + &tid_conf->txrate_mask, dev); if (err) return err; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 35b8847a2f6d..0ab7808fcec8 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1594,7 +1594,7 @@ freq_reg_info_regd(u32 center_freq, /* * We only need to know if one frequency rule was - * was in center_freq's band, that's enough, so lets + * in center_freq's band, that's enough, so let's * not overwrite it once found */ if (!band_rule_found) @@ -1691,57 +1691,18 @@ static uint32_t reg_rule_to_chan_bw_flags(const struct ieee80211_regdomain *regd return bw_flags; } -/* - * Note that right now we assume the desired channel bandwidth - * is always 20 MHz for each individual channel (HT40 uses 20 MHz - * per channel, the primary and the extension channel). - */ -static void handle_channel(struct wiphy *wiphy, - enum nl80211_reg_initiator initiator, - struct ieee80211_channel *chan) +static void handle_channel_single_rule(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator, + struct ieee80211_channel *chan, + u32 flags, + struct regulatory_request *lr, + struct wiphy *request_wiphy, + const struct ieee80211_reg_rule *reg_rule) { - u32 flags, bw_flags = 0; - const struct ieee80211_reg_rule *reg_rule = NULL; + u32 bw_flags = 0; const struct ieee80211_power_rule *power_rule = NULL; - struct wiphy *request_wiphy = NULL; - struct regulatory_request *lr = get_last_request(); const struct ieee80211_regdomain *regd; - request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); - - flags = chan->orig_flags; - - reg_rule = freq_reg_info(wiphy, ieee80211_channel_to_khz(chan)); - if (IS_ERR(reg_rule)) { - /* - * We will disable all channels that do not match our - * received regulatory rule unless the hint is coming - * from a Country IE and the Country IE had no information - * about a band. The IEEE 802.11 spec allows for an AP - * to send only a subset of the regulatory rules allowed, - * so an AP in the US that only supports 2.4 GHz may only send - * a country IE with information for the 2.4 GHz band - * while 5 GHz is still supported. - */ - if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && - PTR_ERR(reg_rule) == -ERANGE) - return; - - if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && - request_wiphy && request_wiphy == wiphy && - request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { - pr_debug("Disabling freq %d.%03d MHz for good\n", - chan->center_freq, chan->freq_offset); - chan->orig_flags |= IEEE80211_CHAN_DISABLED; - chan->flags = chan->orig_flags; - } else { - pr_debug("Disabling freq %d.%03d MHz\n", - chan->center_freq, chan->freq_offset); - chan->flags |= IEEE80211_CHAN_DISABLED; - } - return; - } - regd = reg_get_regdomain(wiphy); power_rule = ®_rule->power_rule; @@ -1803,6 +1764,204 @@ static void handle_channel(struct wiphy *wiphy, chan->max_power = chan->max_reg_power; } +static void handle_channel_adjacent_rules(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator, + struct ieee80211_channel *chan, + u32 flags, + struct regulatory_request *lr, + struct wiphy *request_wiphy, + const struct ieee80211_reg_rule *rrule1, + const struct ieee80211_reg_rule *rrule2, + struct ieee80211_freq_range *comb_range) +{ + u32 bw_flags1 = 0; + u32 bw_flags2 = 0; + const struct ieee80211_power_rule *power_rule1 = NULL; + const struct ieee80211_power_rule *power_rule2 = NULL; + const struct ieee80211_regdomain *regd; + + regd = reg_get_regdomain(wiphy); + + power_rule1 = &rrule1->power_rule; + power_rule2 = &rrule2->power_rule; + bw_flags1 = reg_rule_to_chan_bw_flags(regd, rrule1, chan); + bw_flags2 = reg_rule_to_chan_bw_flags(regd, rrule2, chan); + + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && + request_wiphy && request_wiphy == wiphy && + request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { + /* This guarantees the driver's requested regulatory domain + * will always be used as a base for further regulatory + * settings + */ + chan->flags = + map_regdom_flags(rrule1->flags) | + map_regdom_flags(rrule2->flags) | + bw_flags1 | + bw_flags2; + chan->orig_flags = chan->flags; + chan->max_antenna_gain = + min_t(int, MBI_TO_DBI(power_rule1->max_antenna_gain), + MBI_TO_DBI(power_rule2->max_antenna_gain)); + chan->orig_mag = chan->max_antenna_gain; + chan->max_reg_power = + min_t(int, MBM_TO_DBM(power_rule1->max_eirp), + MBM_TO_DBM(power_rule2->max_eirp)); + chan->max_power = chan->max_reg_power; + chan->orig_mpwr = chan->max_reg_power; + + if (chan->flags & IEEE80211_CHAN_RADAR) { + chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; + if (rrule1->dfs_cac_ms || rrule2->dfs_cac_ms) + chan->dfs_cac_ms = max_t(unsigned int, + rrule1->dfs_cac_ms, + rrule2->dfs_cac_ms); + } + + return; + } + + chan->dfs_state = NL80211_DFS_USABLE; + chan->dfs_state_entered = jiffies; + + chan->beacon_found = false; + chan->flags = flags | bw_flags1 | bw_flags2 | + map_regdom_flags(rrule1->flags) | + map_regdom_flags(rrule2->flags); + + /* reg_rule_to_chan_bw_flags may forbids 10 and forbids 20 MHz + * (otherwise no adj. rule case), recheck therefore + */ + if (cfg80211_does_bw_fit_range(comb_range, + ieee80211_channel_to_khz(chan), + MHZ_TO_KHZ(10))) + chan->flags &= ~IEEE80211_CHAN_NO_10MHZ; + if (cfg80211_does_bw_fit_range(comb_range, + ieee80211_channel_to_khz(chan), + MHZ_TO_KHZ(20))) + chan->flags &= ~IEEE80211_CHAN_NO_20MHZ; + + chan->max_antenna_gain = + min_t(int, chan->orig_mag, + min_t(int, + MBI_TO_DBI(power_rule1->max_antenna_gain), + MBI_TO_DBI(power_rule2->max_antenna_gain))); + chan->max_reg_power = min_t(int, + MBM_TO_DBM(power_rule1->max_eirp), + MBM_TO_DBM(power_rule2->max_eirp)); + + if (chan->flags & IEEE80211_CHAN_RADAR) { + if (rrule1->dfs_cac_ms || rrule2->dfs_cac_ms) + chan->dfs_cac_ms = max_t(unsigned int, + rrule1->dfs_cac_ms, + rrule2->dfs_cac_ms); + else + chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; + } + + if (chan->orig_mpwr) { + /* Devices that use REGULATORY_COUNTRY_IE_FOLLOW_POWER + * will always follow the passed country IE power settings. + */ + if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && + wiphy->regulatory_flags & REGULATORY_COUNTRY_IE_FOLLOW_POWER) + chan->max_power = chan->max_reg_power; + else + chan->max_power = min(chan->orig_mpwr, + chan->max_reg_power); + } else { + chan->max_power = chan->max_reg_power; + } +} + +/* Note that right now we assume the desired channel bandwidth + * is always 20 MHz for each individual channel (HT40 uses 20 MHz + * per channel, the primary and the extension channel). + */ +static void handle_channel(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator, + struct ieee80211_channel *chan) +{ + const u32 orig_chan_freq = ieee80211_channel_to_khz(chan); + struct regulatory_request *lr = get_last_request(); + struct wiphy *request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); + const struct ieee80211_reg_rule *rrule = NULL; + const struct ieee80211_reg_rule *rrule1 = NULL; + const struct ieee80211_reg_rule *rrule2 = NULL; + + u32 flags = chan->orig_flags; + + rrule = freq_reg_info(wiphy, orig_chan_freq); + if (IS_ERR(rrule)) { + /* check for adjacent match, therefore get rules for + * chan - 20 MHz and chan + 20 MHz and test + * if reg rules are adjacent + */ + rrule1 = freq_reg_info(wiphy, + orig_chan_freq - MHZ_TO_KHZ(20)); + rrule2 = freq_reg_info(wiphy, + orig_chan_freq + MHZ_TO_KHZ(20)); + if (!IS_ERR(rrule1) && !IS_ERR(rrule2)) { + struct ieee80211_freq_range comb_range; + + if (rrule1->freq_range.end_freq_khz != + rrule2->freq_range.start_freq_khz) + goto disable_chan; + + comb_range.start_freq_khz = + rrule1->freq_range.start_freq_khz; + comb_range.end_freq_khz = + rrule2->freq_range.end_freq_khz; + comb_range.max_bandwidth_khz = + min_t(u32, + rrule1->freq_range.max_bandwidth_khz, + rrule2->freq_range.max_bandwidth_khz); + + if (!cfg80211_does_bw_fit_range(&comb_range, + orig_chan_freq, + MHZ_TO_KHZ(20))) + goto disable_chan; + + handle_channel_adjacent_rules(wiphy, initiator, chan, + flags, lr, request_wiphy, + rrule1, rrule2, + &comb_range); + return; + } + +disable_chan: + /* We will disable all channels that do not match our + * received regulatory rule unless the hint is coming + * from a Country IE and the Country IE had no information + * about a band. The IEEE 802.11 spec allows for an AP + * to send only a subset of the regulatory rules allowed, + * so an AP in the US that only supports 2.4 GHz may only send + * a country IE with information for the 2.4 GHz band + * while 5 GHz is still supported. + */ + if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && + PTR_ERR(rrule) == -ERANGE) + return; + + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && + request_wiphy && request_wiphy == wiphy && + request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { + pr_debug("Disabling freq %d.%03d MHz for good\n", + chan->center_freq, chan->freq_offset); + chan->orig_flags |= IEEE80211_CHAN_DISABLED; + chan->flags = chan->orig_flags; + } else { + pr_debug("Disabling freq %d.%03d MHz\n", + chan->center_freq, chan->freq_offset); + chan->flags |= IEEE80211_CHAN_DISABLED; + } + return; + } + + handle_channel_single_rule(wiphy, initiator, chan, flags, lr, + request_wiphy, rrule); +} + static void handle_band(struct wiphy *wiphy, enum nl80211_reg_initiator initiator, struct ieee80211_supported_band *sband) @@ -2946,6 +3105,9 @@ int regulatory_hint_user(const char *alpha2, if (WARN_ON(!alpha2)) return -EINVAL; + if (!is_world_regdom(alpha2) && !is_an_alpha2(alpha2)) + return -EINVAL; + request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; @@ -3167,7 +3329,7 @@ static void restore_custom_reg_settings(struct wiphy *wiphy) * - send a user regulatory hint if applicable * * Device drivers that send a regulatory hint for a specific country - * keep their own regulatory domain on wiphy->regd so that does does + * keep their own regulatory domain on wiphy->regd so that does * not need to be remembered. */ static void restore_regulatory_settings(bool reset_user, bool cached) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index e67a74488bbe..84fc8ab16dd2 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -55,7 +55,7 @@ * * Also note that the hidden_beacon_bss pointer is only relevant * if the driver uses something other than the IEs, e.g. private - * data stored stored in the BSS struct, since the beacon IEs are + * data stored in the BSS struct, since the beacon IEs are * also linked into the probe response struct. */ @@ -1433,7 +1433,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, switch (ftype) { case CFG80211_BSS_FTYPE_BEACON: ies->from_beacon = true; - /* fall through */ + fallthrough; case CFG80211_BSS_FTYPE_UNKNOWN: rcu_assign_pointer(tmp.pub.beacon_ies, ies); break; @@ -1488,7 +1488,7 @@ static const struct element ielen - (mbssid_end - ie)); /* - * If is is not the last subelement in current MBSSID IE or there isn't + * If it is not the last subelement in current MBSSID IE or there isn't * a next MBSSID IE - profile is complete. */ if ((sub_elem->data + sub_elem->datalen < mbssid_end - 1) || diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 985f3c23f054..38df713f2e2e 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -24,7 +24,7 @@ /* * Software SME in cfg80211, using auth/assoc/deauth calls to the - * driver. This is is for implementing nl80211's connect/disconnect + * driver. This is for implementing nl80211's connect/disconnect * and wireless extensions (if configured.) */ @@ -205,7 +205,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev, return err; case CFG80211_CONN_ASSOC_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_ASSOC; - /* fall through */ + fallthrough; case CFG80211_CONN_ASSOC_FAILED: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, @@ -215,7 +215,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev, cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); - /* fall through */ + fallthrough; case CFG80211_CONN_ABANDON: /* free directly, disconnected event already sent */ cfg80211_sme_free(wdev); diff --git a/net/wireless/util.c b/net/wireless/util.c index dfad1c0f57ad..4a9ff9ef513f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -123,11 +123,13 @@ int ieee80211_freq_khz_to_channel(u32 freq) return (freq - 2407) / 5; else if (freq >= 4910 && freq <= 4980) return (freq - 4000) / 5; - else if (freq < 5945) + else if (freq < 5925) return (freq - 5000) / 5; + else if (freq == 5935) + return 2; else if (freq <= 45000) /* DMG band lower limit */ - /* see 802.11ax D4.1 27.3.22.2 */ - return (freq - 5940) / 5; + /* see 802.11ax D6.1 27.3.22.2 */ + return (freq - 5950) / 5; else if (freq >= 58320 && freq <= 70200) return (freq - 56160) / 2160; else @@ -198,7 +200,7 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_G; want--; - /* fall through */ + fallthrough; default: sband->bitrates[i].flags |= IEEE80211_RATE_ERP_G; @@ -1008,7 +1010,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_STATION: if (dev->ieee80211_ptr->use_4addr) break; - /* fall through */ + fallthrough; case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_ADHOC: diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index aa918d7ff6bd..78f2927ead7f 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -497,7 +497,7 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, /* * We only need to store WEP keys, since they're the only keys that - * can be be set before a connection is established and persist after + * can be set before a connection is established and persist after * disconnecting. */ if (!addr && (params->cipher == WLAN_CIPHER_SUITE_WEP40 || @@ -1334,7 +1334,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) wstats.qual.qual = sig + 110; break; } - /* fall through */ + fallthrough; case CFG80211_SIGNAL_TYPE_UNSPEC: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; @@ -1343,7 +1343,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) wstats.qual.qual = sinfo.signal; break; } - /* fall through */ + fallthrough; default: wstats.qual.updated |= IW_QUAL_LEVEL_INVALID; wstats.qual.updated |= IW_QUAL_QUAL_INVALID; diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 7fb327632272..8e1a49b0c0dc 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -98,7 +98,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, *vc_fac_mask |= X25_MASK_REVERSE; break; } - /*fall through */ + fallthrough; case X25_FAC_THROUGHPUT: facilities->throughput = p[1]; *vc_fac_mask |= X25_MASK_THROUGHPUT; diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 4d3bb46aaae0..e1c4197af468 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -349,7 +349,7 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp case X25_RESET_REQUEST: x25_write_internal(sk, X25_RESET_CONFIRMATION); - /* fall through */ + fallthrough; case X25_RESET_CONFIRMATION: { x25_stop_timer(sk); x25->condition = 0x00; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index e97db37354e4..a7227b447228 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -23,162 +23,6 @@ static DEFINE_IDA(umem_ida); -void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) -{ - unsigned long flags; - - if (!xs->tx) - return; - - spin_lock_irqsave(&umem->xsk_tx_list_lock, flags); - list_add_rcu(&xs->list, &umem->xsk_tx_list); - spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags); -} - -void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) -{ - unsigned long flags; - - if (!xs->tx) - return; - - spin_lock_irqsave(&umem->xsk_tx_list_lock, flags); - list_del_rcu(&xs->list); - spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags); -} - -/* The umem is stored both in the _rx struct and the _tx struct as we do - * not know if the device has more tx queues than rx, or the opposite. - * This might also change during run time. - */ -static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem, - u16 queue_id) -{ - if (queue_id >= max_t(unsigned int, - dev->real_num_rx_queues, - dev->real_num_tx_queues)) - return -EINVAL; - - if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].umem = umem; - if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].umem = umem; - - return 0; -} - -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) -{ - if (queue_id < dev->real_num_rx_queues) - return dev->_rx[queue_id].umem; - if (queue_id < dev->real_num_tx_queues) - return dev->_tx[queue_id].umem; - - return NULL; -} -EXPORT_SYMBOL(xdp_get_umem_from_qid); - -static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id) -{ - if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].umem = NULL; - if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].umem = NULL; -} - -int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, - u16 queue_id, u16 flags) -{ - bool force_zc, force_copy; - struct netdev_bpf bpf; - int err = 0; - - ASSERT_RTNL(); - - force_zc = flags & XDP_ZEROCOPY; - force_copy = flags & XDP_COPY; - - if (force_zc && force_copy) - return -EINVAL; - - if (xdp_get_umem_from_qid(dev, queue_id)) - return -EBUSY; - - err = xdp_reg_umem_at_qid(dev, umem, queue_id); - if (err) - return err; - - umem->dev = dev; - umem->queue_id = queue_id; - - if (flags & XDP_USE_NEED_WAKEUP) { - umem->flags |= XDP_UMEM_USES_NEED_WAKEUP; - /* Tx needs to be explicitly woken up the first time. - * Also for supporting drivers that do not implement this - * feature. They will always have to call sendto(). - */ - xsk_set_tx_need_wakeup(umem); - } - - dev_hold(dev); - - if (force_copy) - /* For copy-mode, we are done. */ - return 0; - - if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) { - err = -EOPNOTSUPP; - goto err_unreg_umem; - } - - bpf.command = XDP_SETUP_XSK_UMEM; - bpf.xsk.umem = umem; - bpf.xsk.queue_id = queue_id; - - err = dev->netdev_ops->ndo_bpf(dev, &bpf); - if (err) - goto err_unreg_umem; - - umem->zc = true; - return 0; - -err_unreg_umem: - if (!force_zc) - err = 0; /* fallback to copy mode */ - if (err) - xdp_clear_umem_at_qid(dev, queue_id); - return err; -} - -void xdp_umem_clear_dev(struct xdp_umem *umem) -{ - struct netdev_bpf bpf; - int err; - - ASSERT_RTNL(); - - if (!umem->dev) - return; - - if (umem->zc) { - bpf.command = XDP_SETUP_XSK_UMEM; - bpf.xsk.umem = NULL; - bpf.xsk.queue_id = umem->queue_id; - - err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf); - - if (err) - WARN(1, "failed to disable umem!\n"); - } - - xdp_clear_umem_at_qid(umem->dev, umem->queue_id); - - dev_put(umem->dev); - umem->dev = NULL; - umem->zc = false; -} - static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); @@ -195,38 +39,33 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem) } } -static void xdp_umem_release(struct xdp_umem *umem) +static void xdp_umem_addr_unmap(struct xdp_umem *umem) { - rtnl_lock(); - xdp_umem_clear_dev(umem); - rtnl_unlock(); - - ida_simple_remove(&umem_ida, umem->id); + vunmap(umem->addrs); + umem->addrs = NULL; +} - if (umem->fq) { - xskq_destroy(umem->fq); - umem->fq = NULL; - } +static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages, + u32 nr_pages) +{ + umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); + if (!umem->addrs) + return -ENOMEM; + return 0; +} - if (umem->cq) { - xskq_destroy(umem->cq); - umem->cq = NULL; - } +static void xdp_umem_release(struct xdp_umem *umem) +{ + umem->zc = false; + ida_simple_remove(&umem_ida, umem->id); - xp_destroy(umem->pool); + xdp_umem_addr_unmap(umem); xdp_umem_unpin_pages(umem); xdp_umem_unaccount_pages(umem); kfree(umem); } -static void xdp_umem_release_deferred(struct work_struct *work) -{ - struct xdp_umem *umem = container_of(work, struct xdp_umem, work); - - xdp_umem_release(umem); -} - void xdp_get_umem(struct xdp_umem *umem) { refcount_inc(&umem->users); @@ -237,10 +76,8 @@ void xdp_put_umem(struct xdp_umem *umem) if (!umem) return; - if (refcount_dec_and_test(&umem->users)) { - INIT_WORK(&umem->work, xdp_umem_release_deferred); - schedule_work(&umem->work); - } + if (refcount_dec_and_test(&umem->users)) + xdp_umem_release(umem); } static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) @@ -319,8 +156,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - if (mr->flags & ~(XDP_UMEM_UNALIGNED_CHUNK_FLAG | - XDP_UMEM_USES_NEED_WAKEUP)) + if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG) return -EINVAL; if (!unaligned_chunks && !is_power_of_2(chunk_size)) @@ -356,13 +192,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->size = size; umem->headroom = headroom; umem->chunk_size = chunk_size; + umem->chunks = chunks; umem->npgs = (u32)npgs; umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; - INIT_LIST_HEAD(&umem->xsk_tx_list); - spin_lock_init(&umem->xsk_tx_list_lock); + INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); err = xdp_umem_account_pages(umem); @@ -373,15 +209,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (err) goto out_account; - umem->pool = xp_create(umem->pgs, umem->npgs, chunks, chunk_size, - headroom, size, unaligned_chunks); - if (!umem->pool) { - err = -ENOMEM; - goto out_pin; - } + err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs); + if (err) + goto out_unpin; + return 0; -out_pin: +out_unpin: xdp_umem_unpin_pages(umem); out_account: xdp_umem_unaccount_pages(umem); @@ -413,8 +247,3 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) return umem; } - -bool xdp_umem_validate_queues(struct xdp_umem *umem) -{ - return umem->fq && umem->cq; -} diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index 32067fe98f65..181fdda2f2a8 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -8,14 +8,8 @@ #include <net/xdp_sock_drv.h> -int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, - u16 queue_id, u16 flags); -void xdp_umem_clear_dev(struct xdp_umem *umem); -bool xdp_umem_validate_queues(struct xdp_umem *umem); void xdp_get_umem(struct xdp_umem *umem); void xdp_put_umem(struct xdp_umem *umem); -void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs); -void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs); struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr); #endif /* XDP_UMEM_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index c3231620d210..5eb6662f562a 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -36,68 +36,108 @@ static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return READ_ONCE(xs->rx) && READ_ONCE(xs->umem) && - READ_ONCE(xs->umem->fq); + (xs->pool->fq || READ_ONCE(xs->fq_tmp)); } -void xsk_set_rx_need_wakeup(struct xdp_umem *umem) +void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { - if (umem->need_wakeup & XDP_WAKEUP_RX) + if (pool->cached_need_wakeup & XDP_WAKEUP_RX) return; - umem->fq->ring->flags |= XDP_RING_NEED_WAKEUP; - umem->need_wakeup |= XDP_WAKEUP_RX; + pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP; + pool->cached_need_wakeup |= XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_set_rx_need_wakeup); -void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { struct xdp_sock *xs; - if (umem->need_wakeup & XDP_WAKEUP_TX) + if (pool->cached_need_wakeup & XDP_WAKEUP_TX) return; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); - umem->need_wakeup |= XDP_WAKEUP_TX; + pool->cached_need_wakeup |= XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_set_tx_need_wakeup); -void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { - if (!(umem->need_wakeup & XDP_WAKEUP_RX)) + if (!(pool->cached_need_wakeup & XDP_WAKEUP_RX)) return; - umem->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; - umem->need_wakeup &= ~XDP_WAKEUP_RX; + pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; + pool->cached_need_wakeup &= ~XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_clear_rx_need_wakeup); -void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { struct xdp_sock *xs; - if (!(umem->need_wakeup & XDP_WAKEUP_TX)) + if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX)) return; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); - umem->need_wakeup &= ~XDP_WAKEUP_TX; + pool->cached_need_wakeup &= ~XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_clear_tx_need_wakeup); -bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { - return umem->flags & XDP_UMEM_USES_NEED_WAKEUP; + return pool->uses_need_wakeup; +} +EXPORT_SYMBOL(xsk_uses_need_wakeup); + +struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, + u16 queue_id) +{ + if (queue_id < dev->real_num_rx_queues) + return dev->_rx[queue_id].pool; + if (queue_id < dev->real_num_tx_queues) + return dev->_tx[queue_id].pool; + + return NULL; +} +EXPORT_SYMBOL(xsk_get_pool_from_qid); + +void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) +{ + if (queue_id < dev->real_num_rx_queues) + dev->_rx[queue_id].pool = NULL; + if (queue_id < dev->real_num_tx_queues) + dev->_tx[queue_id].pool = NULL; +} + +/* The buffer pool is stored both in the _rx struct and the _tx struct as we do + * not know if the device has more tx queues than rx, or the opposite. + * This might also change during run time. + */ +int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, + u16 queue_id) +{ + if (queue_id >= max_t(unsigned int, + dev->real_num_rx_queues, + dev->real_num_tx_queues)) + return -EINVAL; + + if (queue_id < dev->real_num_rx_queues) + dev->_rx[queue_id].pool = pool; + if (queue_id < dev->real_num_tx_queues) + dev->_tx[queue_id].pool = pool; + + return 0; } -EXPORT_SYMBOL(xsk_umem_uses_need_wakeup); void xp_release(struct xdp_buff_xsk *xskb) { @@ -155,12 +195,12 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, struct xdp_buff *xsk_xdp; int err; - if (len > xsk_umem_get_rx_frame_size(xs->umem)) { + if (len > xsk_pool_get_rx_frame_size(xs->pool)) { xs->rx_dropped++; return -ENOSPC; } - xsk_xdp = xsk_buff_alloc(xs->umem); + xsk_xdp = xsk_buff_alloc(xs->pool); if (!xsk_xdp) { xs->rx_dropped++; return -ENOSPC; @@ -208,7 +248,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, static void xsk_flush(struct xdp_sock *xs) { xskq_prod_submit(xs->rx); - __xskq_cons_release(xs->umem->fq); + __xskq_cons_release(xs->pool->fq); sock_def_readable(&xs->sk); } @@ -249,32 +289,32 @@ void __xsk_map_flush(void) } } -void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { - xskq_prod_submit_n(umem->cq, nb_entries); + xskq_prod_submit_n(pool->cq, nb_entries); } -EXPORT_SYMBOL(xsk_umem_complete_tx); +EXPORT_SYMBOL(xsk_tx_completed); -void xsk_umem_consume_tx_done(struct xdp_umem *umem) +void xsk_tx_release(struct xsk_buff_pool *pool) { struct xdp_sock *xs; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); } -EXPORT_SYMBOL(xsk_umem_consume_tx_done); +EXPORT_SYMBOL(xsk_tx_release); -bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) +bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { struct xdp_sock *xs; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { - if (!xskq_cons_peek_desc(xs->tx, desc, umem)) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { + if (!xskq_cons_peek_desc(xs->tx, desc, pool)) { xs->tx->queue_empty_descs++; continue; } @@ -284,7 +324,7 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - if (xskq_prod_reserve_addr(umem->cq, desc->addr)) + if (xskq_prod_reserve_addr(pool->cq, desc->addr)) goto out; xskq_cons_release(xs->tx); @@ -296,7 +336,7 @@ out: rcu_read_unlock(); return false; } -EXPORT_SYMBOL(xsk_umem_consume_tx); +EXPORT_SYMBOL(xsk_tx_peek_desc); static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { @@ -322,7 +362,7 @@ static void xsk_destruct_skb(struct sk_buff *skb) unsigned long flags; spin_lock_irqsave(&xs->tx_completion_lock, flags); - xskq_prod_submit_addr(xs->umem->cq, addr); + xskq_prod_submit_addr(xs->pool->cq, addr); spin_unlock_irqrestore(&xs->tx_completion_lock, flags); sock_wfree(skb); @@ -342,7 +382,7 @@ static int xsk_generic_xmit(struct sock *sk) if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; - while (xskq_cons_peek_desc(xs->tx, &desc, xs->umem)) { + while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) { char *buffer; u64 addr; u32 len; @@ -359,14 +399,14 @@ static int xsk_generic_xmit(struct sock *sk) skb_put(skb, len); addr = desc.addr; - buffer = xsk_buff_raw_get_data(xs->umem, addr); + buffer = xsk_buff_raw_get_data(xs->pool, addr); err = skb_store_bits(skb, 0, buffer, len); /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - if (unlikely(err) || xskq_prod_reserve(xs->umem->cq)) { + if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) { kfree_skb(skb); goto out; } @@ -431,16 +471,16 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); - struct xdp_umem *umem; + struct xsk_buff_pool *pool; if (unlikely(!xsk_is_bound(xs))) return mask; - umem = xs->umem; + pool = xs->pool; - if (umem->need_wakeup) { + if (pool->cached_need_wakeup) { if (xs->zc) - xsk_wakeup(xs, umem->need_wakeup); + xsk_wakeup(xs, pool->cached_need_wakeup); else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); @@ -481,7 +521,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs) WRITE_ONCE(xs->state, XSK_UNBOUND); /* Wait for driver to stop using the xdp socket. */ - xdp_del_sk_umem(xs->umem, xs); + xp_del_xsk(xs->pool, xs); xs->dev = NULL; synchronize_net(); dev_put(dev); @@ -559,6 +599,8 @@ static int xsk_release(struct socket *sock) xskq_destroy(xs->rx); xskq_destroy(xs->tx); + xskq_destroy(xs->fq_tmp); + xskq_destroy(xs->cq_tmp); sock_orphan(sk); sock->sk = NULL; @@ -586,6 +628,11 @@ static struct socket *xsk_lookup_xsk_from_fd(int fd) return sock; } +static bool xsk_validate_queues(struct xdp_sock *xs) +{ + return xs->fq_tmp && xs->cq_tmp; +} + static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr; @@ -654,29 +701,64 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) sockfd_put(sock); goto out_unlock; } - if (umem_xs->dev != dev || umem_xs->queue_id != qid) { - err = -EINVAL; - sockfd_put(sock); - goto out_unlock; + + if (umem_xs->queue_id != qid || umem_xs->dev != dev) { + /* Share the umem with another socket on another qid + * and/or device. + */ + xs->pool = xp_create_and_assign_umem(xs, + umem_xs->umem); + if (!xs->pool) { + sockfd_put(sock); + goto out_unlock; + } + + err = xp_assign_dev_shared(xs->pool, umem_xs->umem, + dev, qid); + if (err) { + xp_destroy(xs->pool); + sockfd_put(sock); + goto out_unlock; + } + } else { + /* Share the buffer pool with the other socket. */ + if (xs->fq_tmp || xs->cq_tmp) { + /* Do not allow setting your own fq or cq. */ + err = -EINVAL; + sockfd_put(sock); + goto out_unlock; + } + + xp_get_pool(umem_xs->pool); + xs->pool = umem_xs->pool; } xdp_get_umem(umem_xs->umem); WRITE_ONCE(xs->umem, umem_xs->umem); sockfd_put(sock); - } else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) { + } else if (!xs->umem || !xsk_validate_queues(xs)) { err = -EINVAL; goto out_unlock; } else { /* This xsk has its own umem. */ - err = xdp_umem_assign_dev(xs->umem, dev, qid, flags); - if (err) + xs->pool = xp_create_and_assign_umem(xs, xs->umem); + if (!xs->pool) { + err = -ENOMEM; + goto out_unlock; + } + + err = xp_assign_dev(xs->pool, dev, qid, flags); + if (err) { + xp_destroy(xs->pool); + xs->pool = NULL; goto out_unlock; + } } xs->dev = dev; xs->zc = xs->umem->zc; xs->queue_id = qid; - xdp_add_sk_umem(xs->umem, xs); + xp_add_xsk(xs->pool, xs); out_unlock: if (err) { @@ -782,16 +864,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, mutex_unlock(&xs->mutex); return -EBUSY; } - if (!xs->umem) { - mutex_unlock(&xs->mutex); - return -EINVAL; - } - q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq : - &xs->umem->cq; + q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp : + &xs->cq_tmp; err = xsk_init_queue(entries, q, true); - if (optname == XDP_UMEM_FILL_RING) - xp_set_fq(xs->umem->pool, *q); mutex_unlock(&xs->mutex); return err; } @@ -858,7 +934,7 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname, if (extra_stats) { stats.rx_ring_full = xs->rx_queue_full; stats.rx_fill_ring_empty_descs = - xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0; + xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx); } else { stats.rx_dropped += xs->rx_queue_full; @@ -960,7 +1036,6 @@ static int xsk_mmap(struct file *file, struct socket *sock, unsigned long size = vma->vm_end - vma->vm_start; struct xdp_sock *xs = xdp_sk(sock->sk); struct xsk_queue *q = NULL; - struct xdp_umem *umem; unsigned long pfn; struct page *qpg; @@ -972,16 +1047,12 @@ static int xsk_mmap(struct file *file, struct socket *sock, } else if (offset == XDP_PGOFF_TX_RING) { q = READ_ONCE(xs->tx); } else { - umem = READ_ONCE(xs->umem); - if (!umem) - return -EINVAL; - /* Matches the smp_wmb() in XDP_UMEM_REG */ smp_rmb(); if (offset == XDP_UMEM_PGOFF_FILL_RING) - q = READ_ONCE(umem->fq); + q = READ_ONCE(xs->fq_tmp); else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) - q = READ_ONCE(umem->cq); + q = READ_ONCE(xs->cq_tmp); } if (!q) @@ -1019,8 +1090,8 @@ static int xsk_notifier(struct notifier_block *this, xsk_unbind_dev(xs); - /* Clear device references in umem. */ - xdp_umem_clear_dev(xs->umem); + /* Clear device references. */ + xp_clear_dev(xs->pool); } mutex_unlock(&xs->mutex); } @@ -1064,7 +1135,7 @@ static void xsk_destruct(struct sock *sk) if (!sock_flag(sk, SOCK_DEAD)) return; - xdp_put_umem(xs->umem); + xp_put_pool(xs->pool); sk_refcnt_debug_dec(sk); } @@ -1072,8 +1143,8 @@ static void xsk_destruct(struct sock *sk) static int xsk_create(struct net *net, struct socket *sock, int protocol, int kern) { - struct sock *sk; struct xdp_sock *xs; + struct sock *sk; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index 455ddd480f3d..da1f73e43924 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -11,13 +11,6 @@ #define XSK_NEXT_PG_CONTIG_SHIFT 0 #define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT) -/* Flags for the umem flags field. - * - * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public - * flags. See inlude/uapi/include/linux/if_xdp.h. - */ -#define XDP_UMEM_USES_NEED_WAKEUP BIT(1) - struct xdp_ring_offset_v1 { __u64 producer; __u64 consumer; @@ -51,5 +44,8 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, struct xdp_sock **map_entry); int xsk_map_inc(struct xsk_map *map); void xsk_map_put(struct xsk_map *map); +void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id); +int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, + u16 queue_id); #endif /* XSK_H_ */ diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index a2044c245215..795d7c81c0ca 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -2,21 +2,37 @@ #include <net/xsk_buff_pool.h> #include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> +#include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> +#include <linux/swiotlb.h> #include "xsk_queue.h" +#include "xdp_umem.h" +#include "xsk.h" -static void xp_addr_unmap(struct xsk_buff_pool *pool) +void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) { - vunmap(pool->addrs); + unsigned long flags; + + if (!xs->tx) + return; + + spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); + list_add_rcu(&xs->tx_list, &pool->xsk_tx_list); + spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); } -static int xp_addr_map(struct xsk_buff_pool *pool, - struct page **pages, u32 nr_pages) +void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) { - pool->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - if (!pool->addrs) - return -ENOMEM; - return 0; + unsigned long flags; + + if (!xs->tx) + return; + + spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); + list_del_rcu(&xs->tx_list); + spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); } void xp_destroy(struct xsk_buff_pool *pool) @@ -24,59 +40,61 @@ void xp_destroy(struct xsk_buff_pool *pool) if (!pool) return; - xp_addr_unmap(pool); kvfree(pool->heads); kvfree(pool); } -struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, - u32 chunk_size, u32 headroom, u64 size, - bool unaligned) +struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, + struct xdp_umem *umem) { struct xsk_buff_pool *pool; struct xdp_buff_xsk *xskb; - int err; u32 i; - pool = kvzalloc(struct_size(pool, free_heads, chunks), GFP_KERNEL); + pool = kvzalloc(struct_size(pool, free_heads, umem->chunks), + GFP_KERNEL); if (!pool) goto out; - pool->heads = kvcalloc(chunks, sizeof(*pool->heads), GFP_KERNEL); + pool->heads = kvcalloc(umem->chunks, sizeof(*pool->heads), GFP_KERNEL); if (!pool->heads) goto out; - pool->chunk_mask = ~((u64)chunk_size - 1); - pool->addrs_cnt = size; - pool->heads_cnt = chunks; - pool->free_heads_cnt = chunks; - pool->headroom = headroom; - pool->chunk_size = chunk_size; - pool->unaligned = unaligned; - pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM; + pool->chunk_mask = ~((u64)umem->chunk_size - 1); + pool->addrs_cnt = umem->size; + pool->heads_cnt = umem->chunks; + pool->free_heads_cnt = umem->chunks; + pool->headroom = umem->headroom; + pool->chunk_size = umem->chunk_size; + pool->unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; + pool->frame_len = umem->chunk_size - umem->headroom - + XDP_PACKET_HEADROOM; + pool->umem = umem; + pool->addrs = umem->addrs; INIT_LIST_HEAD(&pool->free_list); + INIT_LIST_HEAD(&pool->xsk_tx_list); + spin_lock_init(&pool->xsk_tx_list_lock); + refcount_set(&pool->users, 1); + + pool->fq = xs->fq_tmp; + pool->cq = xs->cq_tmp; + xs->fq_tmp = NULL; + xs->cq_tmp = NULL; for (i = 0; i < pool->free_heads_cnt; i++) { xskb = &pool->heads[i]; xskb->pool = pool; - xskb->xdp.frame_sz = chunk_size - headroom; + xskb->xdp.frame_sz = umem->chunk_size - umem->headroom; pool->free_heads[i] = xskb; } - err = xp_addr_map(pool, pages, nr_pages); - if (!err) - return pool; + return pool; out: xp_destroy(pool); return NULL; } -void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq) -{ - pool->fq = fq; -} - void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { u32 i; @@ -86,70 +104,320 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) } EXPORT_SYMBOL(xp_set_rxq_info); -void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) +static void xp_disable_drv_zc(struct xsk_buff_pool *pool) { - dma_addr_t *dma; - u32 i; + struct netdev_bpf bpf; + int err; - if (pool->dma_pages_cnt == 0) + ASSERT_RTNL(); + + if (pool->umem->zc) { + bpf.command = XDP_SETUP_XSK_POOL; + bpf.xsk.pool = NULL; + bpf.xsk.queue_id = pool->queue_id; + + err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf); + + if (err) + WARN(1, "Failed to disable zero-copy!\n"); + } +} + +static int __xp_assign_dev(struct xsk_buff_pool *pool, + struct net_device *netdev, u16 queue_id, u16 flags) +{ + bool force_zc, force_copy; + struct netdev_bpf bpf; + int err = 0; + + ASSERT_RTNL(); + + force_zc = flags & XDP_ZEROCOPY; + force_copy = flags & XDP_COPY; + + if (force_zc && force_copy) + return -EINVAL; + + if (xsk_get_pool_from_qid(netdev, queue_id)) + return -EBUSY; + + pool->netdev = netdev; + pool->queue_id = queue_id; + err = xsk_reg_pool_at_qid(netdev, pool, queue_id); + if (err) + return err; + + if (flags & XDP_USE_NEED_WAKEUP) { + pool->uses_need_wakeup = true; + /* Tx needs to be explicitly woken up the first time. + * Also for supporting drivers that do not implement this + * feature. They will always have to call sendto(). + */ + pool->cached_need_wakeup = XDP_WAKEUP_TX; + } + + dev_hold(netdev); + + if (force_copy) + /* For copy-mode, we are done. */ + return 0; + + if (!netdev->netdev_ops->ndo_bpf || + !netdev->netdev_ops->ndo_xsk_wakeup) { + err = -EOPNOTSUPP; + goto err_unreg_pool; + } + + bpf.command = XDP_SETUP_XSK_POOL; + bpf.xsk.pool = pool; + bpf.xsk.queue_id = queue_id; + + err = netdev->netdev_ops->ndo_bpf(netdev, &bpf); + if (err) + goto err_unreg_pool; + + if (!pool->dma_pages) { + WARN(1, "Driver did not DMA map zero-copy buffers"); + goto err_unreg_xsk; + } + pool->umem->zc = true; + return 0; + +err_unreg_xsk: + xp_disable_drv_zc(pool); +err_unreg_pool: + if (!force_zc) + err = 0; /* fallback to copy mode */ + if (err) + xsk_clear_pool_at_qid(netdev, queue_id); + return err; +} + +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, + u16 queue_id, u16 flags) +{ + return __xp_assign_dev(pool, dev, queue_id, flags); +} + +int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, + struct net_device *dev, u16 queue_id) +{ + u16 flags; + + /* One fill and completion ring required for each queue id. */ + if (!pool->fq || !pool->cq) + return -EINVAL; + + flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY; + if (pool->uses_need_wakeup) + flags |= XDP_USE_NEED_WAKEUP; + + return __xp_assign_dev(pool, dev, queue_id, flags); +} + +void xp_clear_dev(struct xsk_buff_pool *pool) +{ + if (!pool->netdev) return; - for (i = 0; i < pool->dma_pages_cnt; i++) { - dma = &pool->dma_pages[i]; + xp_disable_drv_zc(pool); + xsk_clear_pool_at_qid(pool->netdev, pool->queue_id); + dev_put(pool->netdev); + pool->netdev = NULL; +} + +static void xp_release_deferred(struct work_struct *work) +{ + struct xsk_buff_pool *pool = container_of(work, struct xsk_buff_pool, + work); + + rtnl_lock(); + xp_clear_dev(pool); + rtnl_unlock(); + + if (pool->fq) { + xskq_destroy(pool->fq); + pool->fq = NULL; + } + + if (pool->cq) { + xskq_destroy(pool->cq); + pool->cq = NULL; + } + + xdp_put_umem(pool->umem); + xp_destroy(pool); +} + +void xp_get_pool(struct xsk_buff_pool *pool) +{ + refcount_inc(&pool->users); +} + +void xp_put_pool(struct xsk_buff_pool *pool) +{ + if (!pool) + return; + + if (refcount_dec_and_test(&pool->users)) { + INIT_WORK(&pool->work, xp_release_deferred); + schedule_work(&pool->work); + } +} + +static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool) +{ + struct xsk_dma_map *dma_map; + + list_for_each_entry(dma_map, &pool->umem->xsk_dma_list, list) { + if (dma_map->netdev == pool->netdev) + return dma_map; + } + + return NULL; +} + +static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_device *netdev, + u32 nr_pages, struct xdp_umem *umem) +{ + struct xsk_dma_map *dma_map; + + dma_map = kzalloc(sizeof(*dma_map), GFP_KERNEL); + if (!dma_map) + return NULL; + + dma_map->dma_pages = kvcalloc(nr_pages, sizeof(*dma_map->dma_pages), GFP_KERNEL); + if (!dma_map) { + kfree(dma_map); + return NULL; + } + + dma_map->netdev = netdev; + dma_map->dev = dev; + dma_map->dma_need_sync = false; + dma_map->dma_pages_cnt = nr_pages; + refcount_set(&dma_map->users, 0); + list_add(&dma_map->list, &umem->xsk_dma_list); + return dma_map; +} + +static void xp_destroy_dma_map(struct xsk_dma_map *dma_map) +{ + list_del(&dma_map->list); + kvfree(dma_map->dma_pages); + kfree(dma_map); +} + +static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs) +{ + dma_addr_t *dma; + u32 i; + + for (i = 0; i < dma_map->dma_pages_cnt; i++) { + dma = &dma_map->dma_pages[i]; if (*dma) { - dma_unmap_page_attrs(pool->dev, *dma, PAGE_SIZE, + dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE, DMA_BIDIRECTIONAL, attrs); *dma = 0; } } + xp_destroy_dma_map(dma_map); +} + +void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) +{ + struct xsk_dma_map *dma_map; + + if (pool->dma_pages_cnt == 0) + return; + + dma_map = xp_find_dma_map(pool); + if (!dma_map) { + WARN(1, "Could not find dma_map for device"); + return; + } + + if (!refcount_dec_and_test(&dma_map->users)) + return; + + __xp_dma_unmap(dma_map, attrs); kvfree(pool->dma_pages); pool->dma_pages_cnt = 0; pool->dev = NULL; } EXPORT_SYMBOL(xp_dma_unmap); -static void xp_check_dma_contiguity(struct xsk_buff_pool *pool) +static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map) { u32 i; - for (i = 0; i < pool->dma_pages_cnt - 1; i++) { - if (pool->dma_pages[i] + PAGE_SIZE == pool->dma_pages[i + 1]) - pool->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK; + for (i = 0; i < dma_map->dma_pages_cnt - 1; i++) { + if (dma_map->dma_pages[i] + PAGE_SIZE == dma_map->dma_pages[i + 1]) + dma_map->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK; else - pool->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK; + dma_map->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK; } } +static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map) +{ + pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL); + if (!pool->dma_pages) + return -ENOMEM; + + pool->dev = dma_map->dev; + pool->dma_pages_cnt = dma_map->dma_pages_cnt; + pool->dma_need_sync = dma_map->dma_need_sync; + refcount_inc(&dma_map->users); + memcpy(pool->dma_pages, dma_map->dma_pages, + pool->dma_pages_cnt * sizeof(*pool->dma_pages)); + + return 0; +} + int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages) { + struct xsk_dma_map *dma_map; dma_addr_t dma; + int err; u32 i; - pool->dma_pages = kvcalloc(nr_pages, sizeof(*pool->dma_pages), - GFP_KERNEL); - if (!pool->dma_pages) - return -ENOMEM; + dma_map = xp_find_dma_map(pool); + if (dma_map) { + err = xp_init_dma_info(pool, dma_map); + if (err) + return err; + + return 0; + } - pool->dev = dev; - pool->dma_pages_cnt = nr_pages; - pool->dma_need_sync = false; + dma_map = xp_create_dma_map(dev, pool->netdev, nr_pages, pool->umem); + if (!dma_map) + return -ENOMEM; - for (i = 0; i < pool->dma_pages_cnt; i++) { + for (i = 0; i < dma_map->dma_pages_cnt; i++) { dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE, DMA_BIDIRECTIONAL, attrs); if (dma_mapping_error(dev, dma)) { - xp_dma_unmap(pool, attrs); + __xp_dma_unmap(dma_map, attrs); return -ENOMEM; } if (dma_need_sync(dev, dma)) - pool->dma_need_sync = true; - pool->dma_pages[i] = dma; + dma_map->dma_need_sync = true; + dma_map->dma_pages[i] = dma; } if (pool->unaligned) - xp_check_dma_contiguity(pool); + xp_check_dma_contiguity(dma_map); + + err = xp_init_dma_info(pool, dma_map); + if (err) { + __xp_dma_unmap(dma_map, attrs); + return err; + } + return 0; } EXPORT_SYMBOL(xp_dma_map); diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c index 21e9c2d123ee..5bd8ea9d206a 100644 --- a/net/xdp/xsk_diag.c +++ b/net/xdp/xsk_diag.c @@ -46,6 +46,7 @@ static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs, static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) { + struct xsk_buff_pool *pool = xs->pool; struct xdp_umem *umem = xs->umem; struct xdp_diag_umem du = {}; int err; @@ -58,8 +59,8 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) du.num_pages = umem->npgs; du.chunk_size = umem->chunk_size; du.headroom = umem->headroom; - du.ifindex = umem->dev ? umem->dev->ifindex : 0; - du.queue_id = umem->queue_id; + du.ifindex = pool->netdev ? pool->netdev->ifindex : 0; + du.queue_id = pool->queue_id; du.flags = 0; if (umem->zc) du.flags |= XDP_DU_F_ZEROCOPY; @@ -67,10 +68,11 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du); - if (!err && umem->fq) - err = xsk_diag_put_ring(umem->fq, XDP_DIAG_UMEM_FILL_RING, nlskb); - if (!err && umem->cq) { - err = xsk_diag_put_ring(umem->cq, XDP_DIAG_UMEM_COMPLETION_RING, + if (!err && pool->fq) + err = xsk_diag_put_ring(pool->fq, + XDP_DIAG_UMEM_FILL_RING, nlskb); + if (!err && pool->cq) { + err = xsk_diag_put_ring(pool->cq, XDP_DIAG_UMEM_COMPLETION_RING, nlskb); } return err; @@ -83,7 +85,7 @@ static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb) du.n_rx_dropped = xs->rx_dropped; du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx); du.n_rx_full = xs->rx_queue_full; - du.n_fill_ring_empty = xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0; + du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx); du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx); return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index bf42cfd74b89..2d883f631c85 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -166,9 +166,9 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool, static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d, - struct xdp_umem *umem) + struct xsk_buff_pool *pool) { - if (!xp_validate_desc(umem->pool, d)) { + if (!xp_validate_desc(pool, d)) { q->invalid_descs++; return false; } @@ -177,14 +177,14 @@ static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, static inline bool xskq_cons_read_desc(struct xsk_queue *q, struct xdp_desc *desc, - struct xdp_umem *umem) + struct xsk_buff_pool *pool) { while (q->cached_cons != q->cached_prod) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx = q->cached_cons & q->ring_mask; *desc = ring->desc[idx]; - if (xskq_cons_is_valid_desc(q, desc, umem)) + if (xskq_cons_is_valid_desc(q, desc, pool)) return true; q->cached_cons++; @@ -236,11 +236,11 @@ static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xskq_cons_peek_desc(struct xsk_queue *q, struct xdp_desc *desc, - struct xdp_umem *umem) + struct xsk_buff_pool *pool) { if (q->cached_prod == q->cached_cons) xskq_cons_get_entries(q); - return xskq_cons_read_desc(q, desc, umem); + return xskq_cons_read_desc(q, desc, pool); } static inline void xskq_cons_release(struct xsk_queue *q) diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 8367adbbe9df..2a4fd6677155 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -254,8 +254,16 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, spin_unlock_bh(&map->lock); } +static bool xsk_map_meta_equal(const struct bpf_map *meta0, + const struct bpf_map *meta1) +{ + return meta0->max_entries == meta1->max_entries && + bpf_map_meta_equal(meta0, meta1); +} + static int xsk_map_btf_id; const struct bpf_map_ops xsk_map_ops = { + .map_meta_equal = xsk_map_meta_equal, .map_alloc = xsk_map_alloc, .map_free = xsk_map_free, .map_get_next_key = xsk_map_get_next_key, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d5280fd6f9c1..d622c2548d22 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3410,7 +3410,7 @@ decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse) switch (nexthdr) { case NEXTHDR_FRAGMENT: onlyproto = 1; - /* fall through */ + fallthrough; case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index f87ee02073ba..4f1ed0e3cf9f 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -48,6 +48,7 @@ tprogs-y += syscall_tp tprogs-y += cpustat tprogs-y += xdp_adjust_tail tprogs-y += xdpsock +tprogs-y += xsk_fwd tprogs-y += xdp_fwd tprogs-y += task_fd_query tprogs-y += xdp_sample_pkts @@ -71,12 +72,12 @@ tracex4-objs := tracex4_user.o tracex5-objs := tracex5_user.o $(TRACE_HELPERS) tracex6-objs := tracex6_user.o tracex7-objs := tracex7_user.o -test_probe_write_user-objs := bpf_load.o test_probe_write_user_user.o -trace_output-objs := bpf_load.o trace_output_user.o $(TRACE_HELPERS) -lathist-objs := bpf_load.o lathist_user.o -offwaketime-objs := bpf_load.o offwaketime_user.o $(TRACE_HELPERS) -spintest-objs := bpf_load.o spintest_user.o $(TRACE_HELPERS) -map_perf_test-objs := bpf_load.o map_perf_test_user.o +test_probe_write_user-objs := test_probe_write_user_user.o +trace_output-objs := trace_output_user.o $(TRACE_HELPERS) +lathist-objs := lathist_user.o +offwaketime-objs := offwaketime_user.o $(TRACE_HELPERS) +spintest-objs := spintest_user.o $(TRACE_HELPERS) +map_perf_test-objs := map_perf_test_user.o test_overhead-objs := bpf_load.o test_overhead_user.o test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o test_cgrp2_attach-objs := test_cgrp2_attach.o @@ -86,7 +87,7 @@ xdp1-objs := xdp1_user.o # reuse xdp1 source intentionally xdp2-objs := xdp1_user.o xdp_router_ipv4-objs := xdp_router_ipv4_user.o -test_current_task_under_cgroup-objs := bpf_load.o $(CGROUP_HELPERS) \ +test_current_task_under_cgroup-objs := $(CGROUP_HELPERS) \ test_current_task_under_cgroup_user.o trace_event-objs := trace_event_user.o $(TRACE_HELPERS) sampleip-objs := sampleip_user.o $(TRACE_HELPERS) @@ -100,10 +101,11 @@ xdp_redirect_map-objs := xdp_redirect_map_user.o xdp_redirect_cpu-objs := bpf_load.o xdp_redirect_cpu_user.o xdp_monitor-objs := bpf_load.o xdp_monitor_user.o xdp_rxq_info-objs := xdp_rxq_info_user.o -syscall_tp-objs := bpf_load.o syscall_tp_user.o -cpustat-objs := bpf_load.o cpustat_user.o +syscall_tp-objs := syscall_tp_user.o +cpustat-objs := cpustat_user.o xdp_adjust_tail-objs := xdp_adjust_tail_user.o xdpsock-objs := xdpsock_user.o +xsk_fwd-objs := xsk_fwd.o xdp_fwd-objs := xdp_fwd_user.o task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS) xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS) @@ -203,6 +205,7 @@ TPROGLDLIBS_trace_output += -lrt TPROGLDLIBS_map_perf_test += -lrt TPROGLDLIBS_test_overhead += -lrt TPROGLDLIBS_xdpsock += -pthread +TPROGLDLIBS_xsk_fwd += -pthread # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # make M=samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c index a86a19d5f033..5aefd19cdfa1 100644 --- a/samples/bpf/cpustat_kern.c +++ b/samples/bpf/cpustat_kern.c @@ -51,28 +51,28 @@ static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 }; #define MAP_OFF_PSTATE_IDX 3 #define MAP_OFF_NUM 4 -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = MAX_CPU * MAP_OFF_NUM, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAP_OFF_NUM); +} my_map SEC(".maps"); /* cstate_duration records duration time for every idle state per CPU */ -struct bpf_map_def SEC("maps") cstate_duration = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = MAX_CPU * MAX_CSTATE_ENTRIES, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAX_CSTATE_ENTRIES); +} cstate_duration SEC(".maps"); /* pstate_duration records duration time for every operating point per CPU */ -struct bpf_map_def SEC("maps") pstate_duration = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = MAX_CPU * MAX_PSTATE_ENTRIES, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAX_PSTATE_ENTRIES); +} pstate_duration SEC(".maps"); /* * The trace events for cpu_idle and cpu_frequency are taken from: diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c index 869a99406dbf..96675985e9e0 100644 --- a/samples/bpf/cpustat_user.c +++ b/samples/bpf/cpustat_user.c @@ -9,7 +9,6 @@ #include <string.h> #include <unistd.h> #include <fcntl.h> -#include <linux/bpf.h> #include <locale.h> #include <sys/types.h> #include <sys/stat.h> @@ -18,7 +17,9 @@ #include <sys/wait.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include <bpf/libbpf.h> + +static int cstate_map_fd, pstate_map_fd; #define MAX_CPU 8 #define MAX_PSTATE_ENTRIES 5 @@ -181,21 +182,50 @@ static void int_exit(int sig) { cpu_stat_inject_cpu_idle_event(); cpu_stat_inject_cpu_frequency_event(); - cpu_stat_update(map_fd[1], map_fd[2]); + cpu_stat_update(cstate_map_fd, pstate_map_fd); cpu_stat_print(); exit(0); } int main(int argc, char **argv) { + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; char filename[256]; int ret; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + cstate_map_fd = bpf_object__find_map_fd_by_name(obj, "cstate_duration"); + pstate_map_fd = bpf_object__find_map_fd_by_name(obj, "pstate_duration"); + if (cstate_map_fd < 0 || pstate_map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } ret = cpu_stat_inject_cpu_idle_event(); @@ -210,10 +240,13 @@ int main(int argc, char **argv) signal(SIGTERM, int_exit); while (1) { - cpu_stat_update(map_fd[1], map_fd[2]); + cpu_stat_update(cstate_map_fd, pstate_map_fd); cpu_stat_print(); sleep(5); } +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index 7d7153777678..4b22ace52f80 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -483,7 +483,7 @@ int main(int argc, char **argv) "Option -%c requires an argument.\n\n", optopt); case 'h': - // fallthrough + fallthrough; default: Usage(); return 0; diff --git a/samples/bpf/lathist_kern.c b/samples/bpf/lathist_kern.c index ca9c2e4e69aa..4adfcbbe6ef4 100644 --- a/samples/bpf/lathist_kern.c +++ b/samples/bpf/lathist_kern.c @@ -18,12 +18,12 @@ * trace_preempt_[on|off] tracepoints hooks is not supported. */ -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(u64), - .max_entries = MAX_CPU, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, u64); + __uint(max_entries, MAX_CPU); +} my_map SEC(".maps"); SEC("kprobe/trace_preempt_off") int bpf_prog1(struct pt_regs *ctx) @@ -61,12 +61,12 @@ static unsigned int log2l(unsigned long v) return log2(v); } -struct bpf_map_def SEC("maps") my_lat = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(long), - .max_entries = MAX_CPU * MAX_ENTRIES, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, long); + __uint(max_entries, MAX_CPU * MAX_ENTRIES); +} my_lat SEC(".maps"); SEC("kprobe/trace_preempt_on") int bpf_prog2(struct pt_regs *ctx) diff --git a/samples/bpf/lathist_user.c b/samples/bpf/lathist_user.c index 2ff2839a52d5..7d8ff2418303 100644 --- a/samples/bpf/lathist_user.c +++ b/samples/bpf/lathist_user.c @@ -6,9 +6,8 @@ #include <unistd.h> #include <stdlib.h> #include <signal.h> -#include <linux/bpf.h> +#include <bpf/libbpf.h> #include <bpf/bpf.h> -#include "bpf_load.h" #define MAX_ENTRIES 20 #define MAX_CPU 4 @@ -81,20 +80,51 @@ static void get_data(int fd) int main(int argc, char **argv) { + struct bpf_link *links[2]; + struct bpf_program *prog; + struct bpf_object *obj; char filename[256]; + int map_fd, i = 0; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + map_fd = bpf_object__find_map_fd_by_name(obj, "my_lat"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + links[i] = bpf_program__attach(prog); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; } while (1) { - get_data(map_fd[1]); + get_data(map_fd); print_hist(); sleep(5); } +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c index e74ee1cd4b9c..14b792915a9c 100644 --- a/samples/bpf/offwaketime_kern.c +++ b/samples/bpf/offwaketime_kern.c @@ -28,38 +28,38 @@ struct key_t { u32 tret; }; -struct bpf_map_def SEC("maps") counts = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct key_t), - .value_size = sizeof(u64), - .max_entries = 10000, -}; - -struct bpf_map_def SEC("maps") start = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = 10000, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct key_t); + __type(value, u64); + __uint(max_entries, 10000); +} counts SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, u64); + __uint(max_entries, 10000); +} start SEC(".maps"); struct wokeby_t { char name[TASK_COMM_LEN]; u32 ret; }; -struct bpf_map_def SEC("maps") wokeby = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(u32), - .value_size = sizeof(struct wokeby_t), - .max_entries = 10000, -}; - -struct bpf_map_def SEC("maps") stackmap = { - .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(u32), - .value_size = PERF_MAX_STACK_DEPTH * sizeof(u64), - .max_entries = 10000, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, struct wokeby_t); + __uint(max_entries, 10000); +} wokeby SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(key_size, sizeof(u32)); + __uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64)); + __uint(max_entries, 10000); +} stackmap SEC(".maps"); #define STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP) diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index 51c7da5341cc..5734cfdaaacb 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -5,19 +5,19 @@ #include <unistd.h> #include <stdlib.h> #include <signal.h> -#include <linux/bpf.h> -#include <string.h> #include <linux/perf_event.h> #include <errno.h> -#include <assert.h> #include <stdbool.h> #include <sys/resource.h> #include <bpf/libbpf.h> -#include "bpf_load.h" +#include <bpf/bpf.h> #include "trace_helpers.h" #define PRINT_RAW_ADDR 0 +/* counts, stackmap */ +static int map_fd[2]; + static void print_ksym(__u64 addr) { struct ksym *sym; @@ -52,14 +52,14 @@ static void print_stack(struct key_t *key, __u64 count) int i; printf("%s;", key->target); - if (bpf_map_lookup_elem(map_fd[3], &key->tret, ip) != 0) { + if (bpf_map_lookup_elem(map_fd[1], &key->tret, ip) != 0) { printf("---;"); } else { for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--) print_ksym(ip[i]); } printf("-;"); - if (bpf_map_lookup_elem(map_fd[3], &key->wret, ip) != 0) { + if (bpf_map_lookup_elem(map_fd[1], &key->wret, ip) != 0) { printf("---;"); } else { for (i = 0; i < PERF_MAX_STACK_DEPTH; i++) @@ -96,23 +96,54 @@ static void int_exit(int sig) int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_object *obj = NULL; + struct bpf_link *links[2]; + struct bpf_program *prog; + int delay = 1, i = 0; char filename[256]; - int delay = 1; - - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); - signal(SIGINT, int_exit); - signal(SIGTERM, int_exit); + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); return 2; } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counts"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "stackmap"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + bpf_object__for_each_program(prog, obj) { + links[i] = bpf_program__attach(prog); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; } if (argc > 1) @@ -120,5 +151,10 @@ int main(int argc, char **argv) sleep(delay); print_stacks(map_fd[0]); +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c index f508af357251..455da77319d9 100644 --- a/samples/bpf/spintest_kern.c +++ b/samples/bpf/spintest_kern.c @@ -12,25 +12,25 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(long), - .value_size = sizeof(long), - .max_entries = 1024, -}; -struct bpf_map_def SEC("maps") my_map2 = { - .type = BPF_MAP_TYPE_PERCPU_HASH, - .key_size = sizeof(long), - .value_size = sizeof(long), - .max_entries = 1024, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, long); + __type(value, long); + __uint(max_entries, 1024); +} my_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(key_size, sizeof(long)); + __uint(value_size, sizeof(long)); + __uint(max_entries, 1024); +} my_map2 SEC(".maps"); -struct bpf_map_def SEC("maps") stackmap = { - .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(u32), - .value_size = PERF_MAX_STACK_DEPTH * sizeof(u64), - .max_entries = 10000, -}; +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(key_size, sizeof(u32)); + __uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64)); + __uint(max_entries, 10000); +} stackmap SEC(".maps"); #define PROG(foo) \ int foo(struct pt_regs *ctx) \ diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c index fb430ea2ef51..847da9284fa8 100644 --- a/samples/bpf/spintest_user.c +++ b/samples/bpf/spintest_user.c @@ -1,40 +1,77 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include <unistd.h> -#include <linux/bpf.h> #include <string.h> #include <assert.h> #include <sys/resource.h> #include <bpf/libbpf.h> -#include "bpf_load.h" +#include <bpf/bpf.h> #include "trace_helpers.h" int main(int ac, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char filename[256], symbol[256]; + struct bpf_object *obj = NULL; + struct bpf_link *links[20]; long key, next_key, value; - char filename[256]; + struct bpf_program *prog; + int map_fd, i, j = 0; + const char *title; struct ksym *sym; - int i; - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); return 2; } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + title = bpf_program__title(prog, false); + if (sscanf(title, "kprobe/%s", symbol) != 1) + continue; + + /* Attach prog only when symbol exists */ + if (ksym_get_addr(symbol)) { + links[j] = bpf_program__attach(prog); + if (libbpf_get_error(links[j])) { + fprintf(stderr, "bpf_program__attach failed\n"); + links[j] = NULL; + goto cleanup; + } + j++; + } } for (i = 0; i < 5; i++) { key = 0; printf("kprobing funcs:"); - while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) { - bpf_map_lookup_elem(map_fd[0], &next_key, &value); + while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(map_fd, &next_key, &value); assert(next_key == value); sym = ksym_search(value); key = next_key; @@ -48,10 +85,15 @@ int main(int ac, char **argv) if (key) printf("\n"); key = 0; - while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) - bpf_map_delete_elem(map_fd[0], &next_key); + while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) + bpf_map_delete_elem(map_fd, &next_key); sleep(1); } +cleanup: + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c index 5a62b03b1f88..50231c2eff9c 100644 --- a/samples/bpf/syscall_tp_kern.c +++ b/samples/bpf/syscall_tp_kern.c @@ -18,19 +18,19 @@ struct syscalls_exit_open_args { long ret; }; -struct bpf_map_def SEC("maps") enter_open_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 1); +} enter_open_map SEC(".maps"); -struct bpf_map_def SEC("maps") exit_open_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 1); +} exit_open_map SEC(".maps"); static __always_inline void count(void *map) { diff --git a/samples/bpf/syscall_tp_user.c b/samples/bpf/syscall_tp_user.c index 57014bab7cbe..76a1d00128fb 100644 --- a/samples/bpf/syscall_tp_user.c +++ b/samples/bpf/syscall_tp_user.c @@ -5,16 +5,12 @@ #include <unistd.h> #include <fcntl.h> #include <stdlib.h> -#include <signal.h> -#include <linux/bpf.h> #include <string.h> #include <linux/perf_event.h> #include <errno.h> -#include <assert.h> -#include <stdbool.h> #include <sys/resource.h> +#include <bpf/libbpf.h> #include <bpf/bpf.h> -#include "bpf_load.h" /* This program verifies bpf attachment to tracepoint sys_enter_* and sys_exit_*. * This requires kernel CONFIG_FTRACE_SYSCALLS to be set. @@ -49,16 +45,44 @@ static void verify_map(int map_id) static int test(char *filename, int num_progs) { - int i, fd, map0_fds[num_progs], map1_fds[num_progs]; + int map0_fds[num_progs], map1_fds[num_progs], fd, i, j = 0; + struct bpf_link *links[num_progs * 4]; + struct bpf_object *objs[num_progs]; + struct bpf_program *prog; for (i = 0; i < num_progs; i++) { - if (load_bpf_file(filename)) { - fprintf(stderr, "%s", bpf_log_buf); - return 1; + objs[i] = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(objs[i])) { + fprintf(stderr, "opening BPF object file failed\n"); + objs[i] = NULL; + goto cleanup; } - printf("prog #%d: map ids %d %d\n", i, map_fd[0], map_fd[1]); - map0_fds[i] = map_fd[0]; - map1_fds[i] = map_fd[1]; + + /* load BPF program */ + if (bpf_object__load(objs[i])) { + fprintf(stderr, "loading BPF object file failed\n"); + goto cleanup; + } + + map0_fds[i] = bpf_object__find_map_fd_by_name(objs[i], + "enter_open_map"); + map1_fds[i] = bpf_object__find_map_fd_by_name(objs[i], + "exit_open_map"); + if (map0_fds[i] < 0 || map1_fds[i] < 0) { + fprintf(stderr, "finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, objs[i]) { + links[j] = bpf_program__attach(prog); + if (libbpf_get_error(links[j])) { + fprintf(stderr, "bpf_program__attach failed\n"); + links[j] = NULL; + goto cleanup; + } + j++; + } + printf("prog #%d: map ids %d %d\n", i, map0_fds[i], map1_fds[i]); } /* current load_bpf_file has perf_event_open default pid = -1 @@ -80,6 +104,12 @@ static int test(char *filename, int num_progs) verify_map(map1_fds[i]); } +cleanup: + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + for (i--; i >= 0; i--) + bpf_object__close(objs[i]); return 0; } diff --git a/samples/bpf/task_fd_query_kern.c b/samples/bpf/task_fd_query_kern.c index 278ade5427c8..c821294e1774 100644 --- a/samples/bpf/task_fd_query_kern.c +++ b/samples/bpf/task_fd_query_kern.c @@ -10,7 +10,7 @@ int bpf_prog1(struct pt_regs *ctx) return 0; } -SEC("kretprobe/blk_account_io_completion") +SEC("kretprobe/blk_account_io_done") int bpf_prog2(struct pt_regs *ctx) { return 0; diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index ff2e9c1c7266..4a74531dc403 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -314,7 +314,7 @@ int main(int argc, char **argv) /* test two functions in the corresponding *_kern.c file */ CHECK_AND_RET(test_debug_fs_kprobe(0, "blk_mq_start_request", BPF_FD_TYPE_KPROBE)); - CHECK_AND_RET(test_debug_fs_kprobe(1, "blk_account_io_completion", + CHECK_AND_RET(test_debug_fs_kprobe(1, "blk_account_io_done", BPF_FD_TYPE_KRETPROBE)); /* test nondebug fs kprobe */ diff --git a/samples/bpf/test_current_task_under_cgroup_kern.c b/samples/bpf/test_current_task_under_cgroup_kern.c index 6dc4f41bb6cb..fbd43e2bb4d3 100644 --- a/samples/bpf/test_current_task_under_cgroup_kern.c +++ b/samples/bpf/test_current_task_under_cgroup_kern.c @@ -10,23 +10,24 @@ #include <linux/version.h> #include <bpf/bpf_helpers.h> #include <uapi/linux/utsname.h> +#include "trace_common.h" -struct bpf_map_def SEC("maps") cgroup_map = { - .type = BPF_MAP_TYPE_CGROUP_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u32)); + __uint(max_entries, 1); +} cgroup_map SEC(".maps"); -struct bpf_map_def SEC("maps") perf_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, 1); +} perf_map SEC(".maps"); /* Writes the last PID that called sync to a map at index 0 */ -SEC("kprobe/sys_sync") +SEC("kprobe/" SYSCALL(sys_sync)) int bpf_prog1(struct pt_regs *ctx) { u64 pid = bpf_get_current_pid_tgid(); diff --git a/samples/bpf/test_current_task_under_cgroup_user.c b/samples/bpf/test_current_task_under_cgroup_user.c index 06e9f8ce42e2..ac251a417f45 100644 --- a/samples/bpf/test_current_task_under_cgroup_user.c +++ b/samples/bpf/test_current_task_under_cgroup_user.c @@ -4,10 +4,9 @@ #define _GNU_SOURCE #include <stdio.h> -#include <linux/bpf.h> #include <unistd.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include <bpf/libbpf.h> #include "cgroup_helpers.h" #define CGROUP_PATH "/my-cgroup" @@ -15,13 +14,44 @@ int main(int argc, char **argv) { pid_t remote_pid, local_pid = getpid(); - int cg2, idx = 0, rc = 0; + struct bpf_link *link = NULL; + struct bpf_program *prog; + int cg2, idx = 0, rc = 1; + struct bpf_object *obj; char filename[256]; + int map_fd[2]; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "cgroup_map"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "perf_map"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } if (setup_cgroup_environment()) @@ -70,12 +100,14 @@ int main(int argc, char **argv) goto err; } - goto out; -err: - rc = 1; + rc = 0; -out: +err: close(cg2); cleanup_cgroup_environment(); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); return rc; } diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user_kern.c index fd651a65281e..220a96438d75 100644 --- a/samples/bpf/test_probe_write_user_kern.c +++ b/samples/bpf/test_probe_write_user_kern.c @@ -13,12 +13,12 @@ #include <bpf/bpf_core_read.h> #include "trace_common.h" -struct bpf_map_def SEC("maps") dnat_map = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct sockaddr_in), - .value_size = sizeof(struct sockaddr_in), - .max_entries = 256, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct sockaddr_in); + __type(value, struct sockaddr_in); + __uint(max_entries, 256); +} dnat_map SEC(".maps"); /* kprobe is NOT a stable ABI * kernel functions can be removed, renamed or completely change semantics. diff --git a/samples/bpf/test_probe_write_user_user.c b/samples/bpf/test_probe_write_user_user.c index 045eb5e30f54..00ccfb834e45 100644 --- a/samples/bpf/test_probe_write_user_user.c +++ b/samples/bpf/test_probe_write_user_user.c @@ -1,21 +1,22 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include <assert.h> -#include <linux/bpf.h> #include <unistd.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include <bpf/libbpf.h> #include <sys/socket.h> -#include <string.h> #include <netinet/in.h> #include <arpa/inet.h> int main(int ac, char **argv) { - int serverfd, serverconnfd, clientfd; - socklen_t sockaddr_len; - struct sockaddr serv_addr, mapped_addr, tmp_addr; struct sockaddr_in *serv_addr_in, *mapped_addr_in, *tmp_addr_in; + struct sockaddr serv_addr, mapped_addr, tmp_addr; + int serverfd, serverconnfd, clientfd, map_fd; + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; + socklen_t sockaddr_len; char filename[256]; char *ip; @@ -24,10 +25,35 @@ int main(int ac, char **argv) tmp_addr_in = (struct sockaddr_in *)&tmp_addr; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (libbpf_get_error(prog)) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "dnat_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } assert((serverfd = socket(AF_INET, SOCK_STREAM, 0)) > 0); @@ -51,7 +77,7 @@ int main(int ac, char **argv) mapped_addr_in->sin_port = htons(5555); mapped_addr_in->sin_addr.s_addr = inet_addr("255.255.255.255"); - assert(!bpf_map_update_elem(map_fd[0], &mapped_addr, &serv_addr, BPF_ANY)); + assert(!bpf_map_update_elem(map_fd, &mapped_addr, &serv_addr, BPF_ANY)); assert(listen(serverfd, 5) == 0); @@ -75,5 +101,8 @@ int main(int ac, char **argv) /* Is the server's getsockname = the socket getpeername */ assert(memcmp(&serv_addr, &tmp_addr, sizeof(struct sockaddr_in)) == 0); +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c index 1d7d422cae6f..b64815af0943 100644 --- a/samples/bpf/trace_output_kern.c +++ b/samples/bpf/trace_output_kern.c @@ -2,15 +2,16 @@ #include <linux/version.h> #include <uapi/linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "trace_common.h" -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(u32), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(u32)); + __uint(max_entries, 2); +} my_map SEC(".maps"); -SEC("kprobe/sys_write") +SEC("kprobe/" SYSCALL(sys_write)) int bpf_prog1(struct pt_regs *ctx) { struct S { diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c index 60a17dd05345..364b98764d54 100644 --- a/samples/bpf/trace_output_user.c +++ b/samples/bpf/trace_output_user.c @@ -1,23 +1,10 @@ // SPDX-License-Identifier: GPL-2.0-only #include <stdio.h> -#include <unistd.h> -#include <stdlib.h> -#include <stdbool.h> -#include <string.h> #include <fcntl.h> #include <poll.h> -#include <linux/perf_event.h> -#include <linux/bpf.h> -#include <errno.h> -#include <assert.h> -#include <sys/syscall.h> -#include <sys/ioctl.h> -#include <sys/mman.h> #include <time.h> #include <signal.h> #include <bpf/libbpf.h> -#include "bpf_load.h" -#include "perf-sys.h" static __u64 time_get_ns(void) { @@ -57,20 +44,48 @@ static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) int main(int argc, char **argv) { struct perf_buffer_opts pb_opts = {}; + struct bpf_link *link = NULL; + struct bpf_program *prog; struct perf_buffer *pb; + struct bpf_object *obj; + int map_fd, ret = 0; char filename[256]; FILE *f; - int ret; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (libbpf_get_error(prog)) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } pb_opts.sample_cb = print_bpf_output; - pb = perf_buffer__new(map_fd[0], 8, &pb_opts); + pb = perf_buffer__new(map_fd, 8, &pb_opts); ret = libbpf_get_error(pb); if (ret) { printf("failed to setup perf_buffer: %d\n", ret); @@ -84,5 +99,9 @@ int main(int argc, char **argv) while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) { } kill(0, SIGINT); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); return ret; } diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c index 659613c19a82..710a4410b2fb 100644 --- a/samples/bpf/tracex3_kern.c +++ b/samples/bpf/tracex3_kern.c @@ -49,7 +49,7 @@ struct { __uint(max_entries, SLOTS); } lat_map SEC(".maps"); -SEC("kprobe/blk_account_io_completion") +SEC("kprobe/blk_account_io_done") int bpf_prog2(struct pt_regs *ctx) { long rq = PT_REGS_PARM1(ctx); diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 19c679456a0e..4cead341ae57 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -613,7 +613,16 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) { struct xsk_umem_info *umem; struct xsk_umem_config cfg = { - .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + /* We recommend that you set the fill ring size >= HW RX ring size + + * AF_XDP RX ring size. Make sure you fill up the fill ring + * with buffers at regular intervals, and you will with this setting + * avoid allocation failures in the driver. These are usually quite + * expensive since drivers have not been written to assume that + * allocation failures are common. For regular sockets, kernel + * allocated memory is used that only runs out in OOM situations + * that should be rare. + */ + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, .frame_size = opt_xsk_frame_size, .frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM, @@ -640,13 +649,13 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem) u32 idx; ret = xsk_ring_prod__reserve(&umem->fq, - XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx); - if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) + XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, &idx); + if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS * 2) exit_with_error(-ret); - for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) + for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS * 2; i++) *xsk_ring_prod__fill_addr(&umem->fq, idx++) = i * opt_xsk_frame_size; - xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS); + xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS * 2); } static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, @@ -888,9 +897,6 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, if (!xsk->outstanding_tx) return; - if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) - kick_tx(xsk); - ndescs = (xsk->outstanding_tx > opt_batch_size) ? opt_batch_size : xsk->outstanding_tx; @@ -1004,7 +1010,7 @@ static void rx_drop_all(void) } } -static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size) +static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) { u32 idx; unsigned int i; @@ -1017,14 +1023,14 @@ static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size) for (i = 0; i < batch_size; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - tx_desc->addr = (frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT; + tx_desc->addr = (*frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT; tx_desc->len = PKT_SIZE; } xsk_ring_prod__submit(&xsk->tx, batch_size); xsk->outstanding_tx += batch_size; - frame_nb += batch_size; - frame_nb %= NUM_FRAMES; + *frame_nb += batch_size; + *frame_nb %= NUM_FRAMES; complete_tx_only(xsk, batch_size); } @@ -1080,7 +1086,7 @@ static void tx_only_all(void) } for (i = 0; i < num_socks; i++) - tx_only(xsks[i], frame_nb[i], batch_size); + tx_only(xsks[i], &frame_nb[i], batch_size); pkt_cnt += batch_size; diff --git a/samples/bpf/xsk_fwd.c b/samples/bpf/xsk_fwd.c new file mode 100644 index 000000000000..1cd97c84c337 --- /dev/null +++ b/samples/bpf/xsk_fwd.c @@ -0,0 +1,1085 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2020 Intel Corporation. */ + +#define _GNU_SOURCE +#include <poll.h> +#include <pthread.h> +#include <signal.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/resource.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <time.h> +#include <unistd.h> +#include <getopt.h> +#include <netinet/ether.h> +#include <net/if.h> + +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <linux/if_xdp.h> + +#include <bpf/libbpf.h> +#include <bpf/xsk.h> +#include <bpf/bpf.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef __u64 u64; +typedef __u32 u32; +typedef __u16 u16; +typedef __u8 u8; + +/* This program illustrates the packet forwarding between multiple AF_XDP + * sockets in multi-threaded environment. All threads are sharing a common + * buffer pool, with each socket having its own private buffer cache. + * + * Example 1: Single thread handling two sockets. The packets received by socket + * A (interface IFA, queue QA) are forwarded to socket B (interface IFB, queue + * QB), while the packets received by socket B are forwarded to socket A. The + * thread is running on CPU core X: + * + * ./xsk_fwd -i IFA -q QA -i IFB -q QB -c X + * + * Example 2: Two threads, each handling two sockets. The thread running on CPU + * core X forwards all the packets received by socket A to socket B, and all the + * packets received by socket B to socket A. The thread running on CPU core Y is + * performing the same packet forwarding between sockets C and D: + * + * ./xsk_fwd -i IFA -q QA -i IFB -q QB -i IFC -q QC -i IFD -q QD + * -c CX -c CY + */ + +/* + * Buffer pool and buffer cache + * + * For packet forwarding, the packet buffers are typically allocated from the + * pool for packet reception and freed back to the pool for further reuse once + * the packet transmission is completed. + * + * The buffer pool is shared between multiple threads. In order to minimize the + * access latency to the shared buffer pool, each thread creates one (or + * several) buffer caches, which, unlike the buffer pool, are private to the + * thread that creates them and therefore cannot be shared with other threads. + * The access to the shared pool is only needed either (A) when the cache gets + * empty due to repeated buffer allocations and it needs to be replenished from + * the pool, or (B) when the cache gets full due to repeated buffer free and it + * needs to be flushed back to the pull. + * + * In a packet forwarding system, a packet received on any input port can + * potentially be transmitted on any output port, depending on the forwarding + * configuration. For AF_XDP sockets, for this to work with zero-copy of the + * packet buffers when, it is required that the buffer pool memory fits into the + * UMEM area shared by all the sockets. + */ + +struct bpool_params { + u32 n_buffers; + u32 buffer_size; + int mmap_flags; + + u32 n_users_max; + u32 n_buffers_per_slab; +}; + +/* This buffer pool implementation organizes the buffers into equally sized + * slabs of *n_buffers_per_slab*. Initially, there are *n_slabs* slabs in the + * pool that are completely filled with buffer pointers (full slabs). + * + * Each buffer cache has a slab for buffer allocation and a slab for buffer + * free, with both of these slabs initially empty. When the cache's allocation + * slab goes empty, it is swapped with one of the available full slabs from the + * pool, if any is available. When the cache's free slab goes full, it is + * swapped for one of the empty slabs from the pool, which is guaranteed to + * succeed. + * + * Partially filled slabs never get traded between the cache and the pool + * (except when the cache itself is destroyed), which enables fast operation + * through pointer swapping. + */ +struct bpool { + struct bpool_params params; + pthread_mutex_t lock; + void *addr; + + u64 **slabs; + u64 **slabs_reserved; + u64 *buffers; + u64 *buffers_reserved; + + u64 n_slabs; + u64 n_slabs_reserved; + u64 n_buffers; + + u64 n_slabs_available; + u64 n_slabs_reserved_available; + + struct xsk_umem_config umem_cfg; + struct xsk_ring_prod umem_fq; + struct xsk_ring_cons umem_cq; + struct xsk_umem *umem; +}; + +static struct bpool * +bpool_init(struct bpool_params *params, + struct xsk_umem_config *umem_cfg) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + u64 n_slabs, n_slabs_reserved, n_buffers, n_buffers_reserved; + u64 slabs_size, slabs_reserved_size; + u64 buffers_size, buffers_reserved_size; + u64 total_size, i; + struct bpool *bp; + u8 *p; + int status; + + /* mmap prep. */ + if (setrlimit(RLIMIT_MEMLOCK, &r)) + return NULL; + + /* bpool internals dimensioning. */ + n_slabs = (params->n_buffers + params->n_buffers_per_slab - 1) / + params->n_buffers_per_slab; + n_slabs_reserved = params->n_users_max * 2; + n_buffers = n_slabs * params->n_buffers_per_slab; + n_buffers_reserved = n_slabs_reserved * params->n_buffers_per_slab; + + slabs_size = n_slabs * sizeof(u64 *); + slabs_reserved_size = n_slabs_reserved * sizeof(u64 *); + buffers_size = n_buffers * sizeof(u64); + buffers_reserved_size = n_buffers_reserved * sizeof(u64); + + total_size = sizeof(struct bpool) + + slabs_size + slabs_reserved_size + + buffers_size + buffers_reserved_size; + + /* bpool memory allocation. */ + p = calloc(total_size, sizeof(u8)); + if (!p) + return NULL; + + /* bpool memory initialization. */ + bp = (struct bpool *)p; + memcpy(&bp->params, params, sizeof(*params)); + bp->params.n_buffers = n_buffers; + + bp->slabs = (u64 **)&p[sizeof(struct bpool)]; + bp->slabs_reserved = (u64 **)&p[sizeof(struct bpool) + + slabs_size]; + bp->buffers = (u64 *)&p[sizeof(struct bpool) + + slabs_size + slabs_reserved_size]; + bp->buffers_reserved = (u64 *)&p[sizeof(struct bpool) + + slabs_size + slabs_reserved_size + buffers_size]; + + bp->n_slabs = n_slabs; + bp->n_slabs_reserved = n_slabs_reserved; + bp->n_buffers = n_buffers; + + for (i = 0; i < n_slabs; i++) + bp->slabs[i] = &bp->buffers[i * params->n_buffers_per_slab]; + bp->n_slabs_available = n_slabs; + + for (i = 0; i < n_slabs_reserved; i++) + bp->slabs_reserved[i] = &bp->buffers_reserved[i * + params->n_buffers_per_slab]; + bp->n_slabs_reserved_available = n_slabs_reserved; + + for (i = 0; i < n_buffers; i++) + bp->buffers[i] = i * params->buffer_size; + + /* lock. */ + status = pthread_mutex_init(&bp->lock, NULL); + if (status) { + free(p); + return NULL; + } + + /* mmap. */ + bp->addr = mmap(NULL, + n_buffers * params->buffer_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | params->mmap_flags, + -1, + 0); + if (bp->addr == MAP_FAILED) { + pthread_mutex_destroy(&bp->lock); + free(p); + return NULL; + } + + /* umem. */ + status = xsk_umem__create(&bp->umem, + bp->addr, + bp->params.n_buffers * bp->params.buffer_size, + &bp->umem_fq, + &bp->umem_cq, + umem_cfg); + if (status) { + munmap(bp->addr, bp->params.n_buffers * bp->params.buffer_size); + pthread_mutex_destroy(&bp->lock); + free(p); + return NULL; + } + memcpy(&bp->umem_cfg, umem_cfg, sizeof(*umem_cfg)); + + return bp; +} + +static void +bpool_free(struct bpool *bp) +{ + if (!bp) + return; + + xsk_umem__delete(bp->umem); + munmap(bp->addr, bp->params.n_buffers * bp->params.buffer_size); + pthread_mutex_destroy(&bp->lock); + free(bp); +} + +struct bcache { + struct bpool *bp; + + u64 *slab_cons; + u64 *slab_prod; + + u64 n_buffers_cons; + u64 n_buffers_prod; +}; + +static u32 +bcache_slab_size(struct bcache *bc) +{ + struct bpool *bp = bc->bp; + + return bp->params.n_buffers_per_slab; +} + +static struct bcache * +bcache_init(struct bpool *bp) +{ + struct bcache *bc; + + bc = calloc(1, sizeof(struct bcache)); + if (!bc) + return NULL; + + bc->bp = bp; + bc->n_buffers_cons = 0; + bc->n_buffers_prod = 0; + + pthread_mutex_lock(&bp->lock); + if (bp->n_slabs_reserved_available == 0) { + pthread_mutex_unlock(&bp->lock); + free(bc); + return NULL; + } + + bc->slab_cons = bp->slabs_reserved[bp->n_slabs_reserved_available - 1]; + bc->slab_prod = bp->slabs_reserved[bp->n_slabs_reserved_available - 2]; + bp->n_slabs_reserved_available -= 2; + pthread_mutex_unlock(&bp->lock); + + return bc; +} + +static void +bcache_free(struct bcache *bc) +{ + struct bpool *bp; + + if (!bc) + return; + + /* In order to keep this example simple, the case of freeing any + * existing buffers from the cache back to the pool is ignored. + */ + + bp = bc->bp; + pthread_mutex_lock(&bp->lock); + bp->slabs_reserved[bp->n_slabs_reserved_available] = bc->slab_prod; + bp->slabs_reserved[bp->n_slabs_reserved_available + 1] = bc->slab_cons; + bp->n_slabs_reserved_available += 2; + pthread_mutex_unlock(&bp->lock); + + free(bc); +} + +/* To work correctly, the implementation requires that the *n_buffers* input + * argument is never greater than the buffer pool's *n_buffers_per_slab*. This + * is typically the case, with one exception taking place when large number of + * buffers are allocated at init time (e.g. for the UMEM fill queue setup). + */ +static inline u32 +bcache_cons_check(struct bcache *bc, u32 n_buffers) +{ + struct bpool *bp = bc->bp; + u64 n_buffers_per_slab = bp->params.n_buffers_per_slab; + u64 n_buffers_cons = bc->n_buffers_cons; + u64 n_slabs_available; + u64 *slab_full; + + /* + * Consumer slab is not empty: Use what's available locally. Do not + * look for more buffers from the pool when the ask can only be + * partially satisfied. + */ + if (n_buffers_cons) + return (n_buffers_cons < n_buffers) ? + n_buffers_cons : + n_buffers; + + /* + * Consumer slab is empty: look to trade the current consumer slab + * (full) for a full slab from the pool, if any is available. + */ + pthread_mutex_lock(&bp->lock); + n_slabs_available = bp->n_slabs_available; + if (!n_slabs_available) { + pthread_mutex_unlock(&bp->lock); + return 0; + } + + n_slabs_available--; + slab_full = bp->slabs[n_slabs_available]; + bp->slabs[n_slabs_available] = bc->slab_cons; + bp->n_slabs_available = n_slabs_available; + pthread_mutex_unlock(&bp->lock); + + bc->slab_cons = slab_full; + bc->n_buffers_cons = n_buffers_per_slab; + return n_buffers; +} + +static inline u64 +bcache_cons(struct bcache *bc) +{ + u64 n_buffers_cons = bc->n_buffers_cons - 1; + u64 buffer; + + buffer = bc->slab_cons[n_buffers_cons]; + bc->n_buffers_cons = n_buffers_cons; + return buffer; +} + +static inline void +bcache_prod(struct bcache *bc, u64 buffer) +{ + struct bpool *bp = bc->bp; + u64 n_buffers_per_slab = bp->params.n_buffers_per_slab; + u64 n_buffers_prod = bc->n_buffers_prod; + u64 n_slabs_available; + u64 *slab_empty; + + /* + * Producer slab is not yet full: store the current buffer to it. + */ + if (n_buffers_prod < n_buffers_per_slab) { + bc->slab_prod[n_buffers_prod] = buffer; + bc->n_buffers_prod = n_buffers_prod + 1; + return; + } + + /* + * Producer slab is full: trade the cache's current producer slab + * (full) for an empty slab from the pool, then store the current + * buffer to the new producer slab. As one full slab exists in the + * cache, it is guaranteed that there is at least one empty slab + * available in the pool. + */ + pthread_mutex_lock(&bp->lock); + n_slabs_available = bp->n_slabs_available; + slab_empty = bp->slabs[n_slabs_available]; + bp->slabs[n_slabs_available] = bc->slab_prod; + bp->n_slabs_available = n_slabs_available + 1; + pthread_mutex_unlock(&bp->lock); + + slab_empty[0] = buffer; + bc->slab_prod = slab_empty; + bc->n_buffers_prod = 1; +} + +/* + * Port + * + * Each of the forwarding ports sits on top of an AF_XDP socket. In order for + * packet forwarding to happen with no packet buffer copy, all the sockets need + * to share the same UMEM area, which is used as the buffer pool memory. + */ +#ifndef MAX_BURST_RX +#define MAX_BURST_RX 64 +#endif + +#ifndef MAX_BURST_TX +#define MAX_BURST_TX 64 +#endif + +struct burst_rx { + u64 addr[MAX_BURST_RX]; + u32 len[MAX_BURST_RX]; +}; + +struct burst_tx { + u64 addr[MAX_BURST_TX]; + u32 len[MAX_BURST_TX]; + u32 n_pkts; +}; + +struct port_params { + struct xsk_socket_config xsk_cfg; + struct bpool *bp; + const char *iface; + u32 iface_queue; +}; + +struct port { + struct port_params params; + + struct bcache *bc; + + struct xsk_ring_cons rxq; + struct xsk_ring_prod txq; + struct xsk_ring_prod umem_fq; + struct xsk_ring_cons umem_cq; + struct xsk_socket *xsk; + int umem_fq_initialized; + + u64 n_pkts_rx; + u64 n_pkts_tx; +}; + +static void +port_free(struct port *p) +{ + if (!p) + return; + + /* To keep this example simple, the code to free the buffers from the + * socket's receive and transmit queues, as well as from the UMEM fill + * and completion queues, is not included. + */ + + if (p->xsk) + xsk_socket__delete(p->xsk); + + bcache_free(p->bc); + + free(p); +} + +static struct port * +port_init(struct port_params *params) +{ + struct port *p; + u32 umem_fq_size, pos = 0; + int status, i; + + /* Memory allocation and initialization. */ + p = calloc(sizeof(struct port), 1); + if (!p) + return NULL; + + memcpy(&p->params, params, sizeof(p->params)); + umem_fq_size = params->bp->umem_cfg.fill_size; + + /* bcache. */ + p->bc = bcache_init(params->bp); + if (!p->bc || + (bcache_slab_size(p->bc) < umem_fq_size) || + (bcache_cons_check(p->bc, umem_fq_size) < umem_fq_size)) { + port_free(p); + return NULL; + } + + /* xsk socket. */ + status = xsk_socket__create_shared(&p->xsk, + params->iface, + params->iface_queue, + params->bp->umem, + &p->rxq, + &p->txq, + &p->umem_fq, + &p->umem_cq, + ¶ms->xsk_cfg); + if (status) { + port_free(p); + return NULL; + } + + /* umem fq. */ + xsk_ring_prod__reserve(&p->umem_fq, umem_fq_size, &pos); + + for (i = 0; i < umem_fq_size; i++) + *xsk_ring_prod__fill_addr(&p->umem_fq, pos + i) = + bcache_cons(p->bc); + + xsk_ring_prod__submit(&p->umem_fq, umem_fq_size); + p->umem_fq_initialized = 1; + + return p; +} + +static inline u32 +port_rx_burst(struct port *p, struct burst_rx *b) +{ + u32 n_pkts, pos, i; + + /* Free buffers for FQ replenish. */ + n_pkts = ARRAY_SIZE(b->addr); + + n_pkts = bcache_cons_check(p->bc, n_pkts); + if (!n_pkts) + return 0; + + /* RXQ. */ + n_pkts = xsk_ring_cons__peek(&p->rxq, n_pkts, &pos); + if (!n_pkts) { + if (xsk_ring_prod__needs_wakeup(&p->umem_fq)) { + struct pollfd pollfd = { + .fd = xsk_socket__fd(p->xsk), + .events = POLLIN, + }; + + poll(&pollfd, 1, 0); + } + return 0; + } + + for (i = 0; i < n_pkts; i++) { + b->addr[i] = xsk_ring_cons__rx_desc(&p->rxq, pos + i)->addr; + b->len[i] = xsk_ring_cons__rx_desc(&p->rxq, pos + i)->len; + } + + xsk_ring_cons__release(&p->rxq, n_pkts); + p->n_pkts_rx += n_pkts; + + /* UMEM FQ. */ + for ( ; ; ) { + int status; + + status = xsk_ring_prod__reserve(&p->umem_fq, n_pkts, &pos); + if (status == n_pkts) + break; + + if (xsk_ring_prod__needs_wakeup(&p->umem_fq)) { + struct pollfd pollfd = { + .fd = xsk_socket__fd(p->xsk), + .events = POLLIN, + }; + + poll(&pollfd, 1, 0); + } + } + + for (i = 0; i < n_pkts; i++) + *xsk_ring_prod__fill_addr(&p->umem_fq, pos + i) = + bcache_cons(p->bc); + + xsk_ring_prod__submit(&p->umem_fq, n_pkts); + + return n_pkts; +} + +static inline void +port_tx_burst(struct port *p, struct burst_tx *b) +{ + u32 n_pkts, pos, i; + int status; + + /* UMEM CQ. */ + n_pkts = p->params.bp->umem_cfg.comp_size; + + n_pkts = xsk_ring_cons__peek(&p->umem_cq, n_pkts, &pos); + + for (i = 0; i < n_pkts; i++) { + u64 addr = *xsk_ring_cons__comp_addr(&p->umem_cq, pos + i); + + bcache_prod(p->bc, addr); + } + + xsk_ring_cons__release(&p->umem_cq, n_pkts); + + /* TXQ. */ + n_pkts = b->n_pkts; + + for ( ; ; ) { + status = xsk_ring_prod__reserve(&p->txq, n_pkts, &pos); + if (status == n_pkts) + break; + + if (xsk_ring_prod__needs_wakeup(&p->txq)) + sendto(xsk_socket__fd(p->xsk), NULL, 0, MSG_DONTWAIT, + NULL, 0); + } + + for (i = 0; i < n_pkts; i++) { + xsk_ring_prod__tx_desc(&p->txq, pos + i)->addr = b->addr[i]; + xsk_ring_prod__tx_desc(&p->txq, pos + i)->len = b->len[i]; + } + + xsk_ring_prod__submit(&p->txq, n_pkts); + if (xsk_ring_prod__needs_wakeup(&p->txq)) + sendto(xsk_socket__fd(p->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + p->n_pkts_tx += n_pkts; +} + +/* + * Thread + * + * Packet forwarding threads. + */ +#ifndef MAX_PORTS_PER_THREAD +#define MAX_PORTS_PER_THREAD 16 +#endif + +struct thread_data { + struct port *ports_rx[MAX_PORTS_PER_THREAD]; + struct port *ports_tx[MAX_PORTS_PER_THREAD]; + u32 n_ports_rx; + struct burst_rx burst_rx; + struct burst_tx burst_tx[MAX_PORTS_PER_THREAD]; + u32 cpu_core_id; + int quit; +}; + +static void swap_mac_addresses(void *data) +{ + struct ether_header *eth = (struct ether_header *)data; + struct ether_addr *src_addr = (struct ether_addr *)ð->ether_shost; + struct ether_addr *dst_addr = (struct ether_addr *)ð->ether_dhost; + struct ether_addr tmp; + + tmp = *src_addr; + *src_addr = *dst_addr; + *dst_addr = tmp; +} + +static void * +thread_func(void *arg) +{ + struct thread_data *t = arg; + cpu_set_t cpu_cores; + u32 i; + + CPU_ZERO(&cpu_cores); + CPU_SET(t->cpu_core_id, &cpu_cores); + pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpu_cores); + + for (i = 0; !t->quit; i = (i + 1) & (t->n_ports_rx - 1)) { + struct port *port_rx = t->ports_rx[i]; + struct port *port_tx = t->ports_tx[i]; + struct burst_rx *brx = &t->burst_rx; + struct burst_tx *btx = &t->burst_tx[i]; + u32 n_pkts, j; + + /* RX. */ + n_pkts = port_rx_burst(port_rx, brx); + if (!n_pkts) + continue; + + /* Process & TX. */ + for (j = 0; j < n_pkts; j++) { + u64 addr = xsk_umem__add_offset_to_addr(brx->addr[j]); + u8 *pkt = xsk_umem__get_data(port_rx->params.bp->addr, + addr); + + swap_mac_addresses(pkt); + + btx->addr[btx->n_pkts] = brx->addr[j]; + btx->len[btx->n_pkts] = brx->len[j]; + btx->n_pkts++; + + if (btx->n_pkts == MAX_BURST_TX) { + port_tx_burst(port_tx, btx); + btx->n_pkts = 0; + } + } + } + + return NULL; +} + +/* + * Process + */ +static const struct bpool_params bpool_params_default = { + .n_buffers = 64 * 1024, + .buffer_size = XSK_UMEM__DEFAULT_FRAME_SIZE, + .mmap_flags = 0, + + .n_users_max = 16, + .n_buffers_per_slab = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, +}; + +static const struct xsk_umem_config umem_cfg_default = { + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, + .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, + .frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM, + .flags = 0, +}; + +static const struct port_params port_params_default = { + .xsk_cfg = { + .rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .libbpf_flags = 0, + .xdp_flags = XDP_FLAGS_DRV_MODE, + .bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY, + }, + + .bp = NULL, + .iface = NULL, + .iface_queue = 0, +}; + +#ifndef MAX_PORTS +#define MAX_PORTS 64 +#endif + +#ifndef MAX_THREADS +#define MAX_THREADS 64 +#endif + +static struct bpool_params bpool_params; +static struct xsk_umem_config umem_cfg; +static struct bpool *bp; + +static struct port_params port_params[MAX_PORTS]; +static struct port *ports[MAX_PORTS]; +static u64 n_pkts_rx[MAX_PORTS]; +static u64 n_pkts_tx[MAX_PORTS]; +static int n_ports; + +static pthread_t threads[MAX_THREADS]; +static struct thread_data thread_data[MAX_THREADS]; +static int n_threads; + +static void +print_usage(char *prog_name) +{ + const char *usage = + "Usage:\n" + "\t%s [ -b SIZE ] -c CORE -i INTERFACE [ -q QUEUE ]\n" + "\n" + "-c CORE CPU core to run a packet forwarding thread\n" + " on. May be invoked multiple times.\n" + "\n" + "-b SIZE Number of buffers in the buffer pool shared\n" + " by all the forwarding threads. Default: %u.\n" + "\n" + "-i INTERFACE Network interface. Each (INTERFACE, QUEUE)\n" + " pair specifies one forwarding port. May be\n" + " invoked multiple times.\n" + "\n" + "-q QUEUE Network interface queue for RX and TX. Each\n" + " (INTERFACE, QUEUE) pair specified one\n" + " forwarding port. Default: %u. May be invoked\n" + " multiple times.\n" + "\n"; + printf(usage, + prog_name, + bpool_params_default.n_buffers, + port_params_default.iface_queue); +} + +static int +parse_args(int argc, char **argv) +{ + struct option lgopts[] = { + { NULL, 0, 0, 0 } + }; + int opt, option_index; + + /* Parse the input arguments. */ + for ( ; ;) { + opt = getopt_long(argc, argv, "c:i:q:", lgopts, &option_index); + if (opt == EOF) + break; + + switch (opt) { + case 'b': + bpool_params.n_buffers = atoi(optarg); + break; + + case 'c': + if (n_threads == MAX_THREADS) { + printf("Max number of threads (%d) reached.\n", + MAX_THREADS); + return -1; + } + + thread_data[n_threads].cpu_core_id = atoi(optarg); + n_threads++; + break; + + case 'i': + if (n_ports == MAX_PORTS) { + printf("Max number of ports (%d) reached.\n", + MAX_PORTS); + return -1; + } + + port_params[n_ports].iface = optarg; + port_params[n_ports].iface_queue = 0; + n_ports++; + break; + + case 'q': + if (n_ports == 0) { + printf("No port specified for queue.\n"); + return -1; + } + port_params[n_ports - 1].iface_queue = atoi(optarg); + break; + + default: + printf("Illegal argument.\n"); + return -1; + } + } + + optind = 1; /* reset getopt lib */ + + /* Check the input arguments. */ + if (!n_ports) { + printf("No ports specified.\n"); + return -1; + } + + if (!n_threads) { + printf("No threads specified.\n"); + return -1; + } + + if (n_ports % n_threads) { + printf("Ports cannot be evenly distributed to threads.\n"); + return -1; + } + + return 0; +} + +static void +print_port(u32 port_id) +{ + struct port *port = ports[port_id]; + + printf("Port %u: interface = %s, queue = %u\n", + port_id, port->params.iface, port->params.iface_queue); +} + +static void +print_thread(u32 thread_id) +{ + struct thread_data *t = &thread_data[thread_id]; + u32 i; + + printf("Thread %u (CPU core %u): ", + thread_id, t->cpu_core_id); + + for (i = 0; i < t->n_ports_rx; i++) { + struct port *port_rx = t->ports_rx[i]; + struct port *port_tx = t->ports_tx[i]; + + printf("(%s, %u) -> (%s, %u), ", + port_rx->params.iface, + port_rx->params.iface_queue, + port_tx->params.iface, + port_tx->params.iface_queue); + } + + printf("\n"); +} + +static void +print_port_stats_separator(void) +{ + printf("+-%4s-+-%12s-+-%13s-+-%12s-+-%13s-+\n", + "----", + "------------", + "-------------", + "------------", + "-------------"); +} + +static void +print_port_stats_header(void) +{ + print_port_stats_separator(); + printf("| %4s | %12s | %13s | %12s | %13s |\n", + "Port", + "RX packets", + "RX rate (pps)", + "TX packets", + "TX_rate (pps)"); + print_port_stats_separator(); +} + +static void +print_port_stats_trailer(void) +{ + print_port_stats_separator(); + printf("\n"); +} + +static void +print_port_stats(int port_id, u64 ns_diff) +{ + struct port *p = ports[port_id]; + double rx_pps, tx_pps; + + rx_pps = (p->n_pkts_rx - n_pkts_rx[port_id]) * 1000000000. / ns_diff; + tx_pps = (p->n_pkts_tx - n_pkts_tx[port_id]) * 1000000000. / ns_diff; + + printf("| %4d | %12llu | %13.0f | %12llu | %13.0f |\n", + port_id, + p->n_pkts_rx, + rx_pps, + p->n_pkts_tx, + tx_pps); + + n_pkts_rx[port_id] = p->n_pkts_rx; + n_pkts_tx[port_id] = p->n_pkts_tx; +} + +static void +print_port_stats_all(u64 ns_diff) +{ + int i; + + print_port_stats_header(); + for (i = 0; i < n_ports; i++) + print_port_stats(i, ns_diff); + print_port_stats_trailer(); +} + +static int quit; + +static void +signal_handler(int sig) +{ + quit = 1; +} + +static void remove_xdp_program(void) +{ + int i; + + for (i = 0 ; i < n_ports; i++) + bpf_set_link_xdp_fd(if_nametoindex(port_params[i].iface), -1, + port_params[i].xsk_cfg.xdp_flags); +} + +int main(int argc, char **argv) +{ + struct timespec time; + u64 ns0; + int i; + + /* Parse args. */ + memcpy(&bpool_params, &bpool_params_default, + sizeof(struct bpool_params)); + memcpy(&umem_cfg, &umem_cfg_default, + sizeof(struct xsk_umem_config)); + for (i = 0; i < MAX_PORTS; i++) + memcpy(&port_params[i], &port_params_default, + sizeof(struct port_params)); + + if (parse_args(argc, argv)) { + print_usage(argv[0]); + return -1; + } + + /* Buffer pool initialization. */ + bp = bpool_init(&bpool_params, &umem_cfg); + if (!bp) { + printf("Buffer pool initialization failed.\n"); + return -1; + } + printf("Buffer pool created successfully.\n"); + + /* Ports initialization. */ + for (i = 0; i < MAX_PORTS; i++) + port_params[i].bp = bp; + + for (i = 0; i < n_ports; i++) { + ports[i] = port_init(&port_params[i]); + if (!ports[i]) { + printf("Port %d initialization failed.\n", i); + return -1; + } + print_port(i); + } + printf("All ports created successfully.\n"); + + /* Threads. */ + for (i = 0; i < n_threads; i++) { + struct thread_data *t = &thread_data[i]; + u32 n_ports_per_thread = n_ports / n_threads, j; + + for (j = 0; j < n_ports_per_thread; j++) { + t->ports_rx[j] = ports[i * n_ports_per_thread + j]; + t->ports_tx[j] = ports[i * n_ports_per_thread + + (j + 1) % n_ports_per_thread]; + } + + t->n_ports_rx = n_ports_per_thread; + + print_thread(i); + } + + for (i = 0; i < n_threads; i++) { + int status; + + status = pthread_create(&threads[i], + NULL, + thread_func, + &thread_data[i]); + if (status) { + printf("Thread %d creation failed.\n", i); + return -1; + } + } + printf("All threads created successfully.\n"); + + /* Print statistics. */ + signal(SIGINT, signal_handler); + signal(SIGTERM, signal_handler); + signal(SIGABRT, signal_handler); + + clock_gettime(CLOCK_MONOTONIC, &time); + ns0 = time.tv_sec * 1000000000UL + time.tv_nsec; + for ( ; !quit; ) { + u64 ns1, ns_diff; + + sleep(1); + clock_gettime(CLOCK_MONOTONIC, &time); + ns1 = time.tv_sec * 1000000000UL + time.tv_nsec; + ns_diff = ns1 - ns0; + ns0 = ns1; + + print_port_stats_all(ns_diff); + } + + /* Threads completion. */ + printf("Quit.\n"); + for (i = 0; i < n_threads; i++) + thread_data[i].quit = 1; + + for (i = 0; i < n_threads; i++) + pthread_join(threads[i], NULL); + + for (i = 0; i < n_ports; i++) + port_free(ports[i]); + + bpool_free(bp); + + remove_xdp_program(); + + return 0; +} diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 62c275685b75..95e4cdb94fe9 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -66,7 +66,6 @@ KBUILD_CFLAGS += -Wnested-externs KBUILD_CFLAGS += -Wshadow KBUILD_CFLAGS += $(call cc-option, -Wlogical-op) KBUILD_CFLAGS += -Wmissing-field-initializers -KBUILD_CFLAGS += -Wsign-compare KBUILD_CFLAGS += -Wtype-limits KBUILD_CFLAGS += $(call cc-option, -Wmaybe-uninitialized) KBUILD_CFLAGS += $(call cc-option, -Wunused-macros) @@ -87,6 +86,7 @@ KBUILD_CFLAGS += -Wpacked KBUILD_CFLAGS += -Wpadded KBUILD_CFLAGS += -Wpointer-arith KBUILD_CFLAGS += -Wredundant-decls +KBUILD_CFLAGS += -Wsign-compare KBUILD_CFLAGS += -Wswitch-default KBUILD_CFLAGS += $(call cc-option, -Wpacked-bitfield-compat) diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 5bfa448b4704..08388173973f 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -432,6 +432,7 @@ class PrinterHelpers(Printer): 'struct __sk_buff', 'struct sk_msg_md', 'struct xdp_md', + 'struct path', ] known_types = { '...', @@ -472,6 +473,7 @@ class PrinterHelpers(Printer): 'struct tcp_request_sock', 'struct udp6_sock', 'struct task_struct', + 'struct path', } mapped_types = { 'u8': '__u8', diff --git a/scripts/extract-cert.c b/scripts/extract-cert.c index b071bf476fea..3bc48c726c41 100644 --- a/scripts/extract-cert.c +++ b/scripts/extract-cert.c @@ -71,7 +71,7 @@ static void drain_openssl_errors(void) static const char *key_pass; static BIO *wb; static char *cert_dst; -int kbuild_verbose; +static int kbuild_verbose; static void write_cert(X509 *x509) { diff --git a/scripts/genksyms/keywords.c b/scripts/genksyms/keywords.c index 7a85c4e21175..057c6cabad1d 100644 --- a/scripts/genksyms/keywords.c +++ b/scripts/genksyms/keywords.c @@ -25,9 +25,9 @@ static struct resword { { "__int128_t", BUILTIN_INT_KEYW }, { "__uint128_t", BUILTIN_INT_KEYW }, - // According to rth, c99 defines "_Bool", __restrict", __restrict__", "restrict". KAO + // According to rth, c99 defines "_Bool", "__restrict", "__restrict__", "restrict". KAO { "_Bool", BOOL_KEYW }, - { "_restrict", RESTRICT_KEYW }, + { "__restrict", RESTRICT_KEYW }, { "__restrict__", RESTRICT_KEYW }, { "restrict", RESTRICT_KEYW }, { "asm", ASM_KEYW }, diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c index daf1c1506ec4..e0f965529166 100644 --- a/scripts/kconfig/nconf.c +++ b/scripts/kconfig/nconf.c @@ -755,7 +755,6 @@ static void build_conf(struct menu *menu) switch (ptype) { case P_MENU: child_count++; - prompt = prompt; if (single_menu_mode) { item_make(menu, 'm', "%s%*c%s", diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index bc390df49f1f..8638785328a7 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -885,7 +885,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) connect(action, SIGNAL(toggled(bool)), parent(), SLOT(setShowName(bool))); connect(parent(), SIGNAL(showNameChanged(bool)), - action, SLOT(setOn(bool))); + action, SLOT(setChecked(bool))); action->setChecked(showName); headerPopup->addAction(action); @@ -894,7 +894,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) connect(action, SIGNAL(toggled(bool)), parent(), SLOT(setShowRange(bool))); connect(parent(), SIGNAL(showRangeChanged(bool)), - action, SLOT(setOn(bool))); + action, SLOT(setChecked(bool))); action->setChecked(showRange); headerPopup->addAction(action); @@ -903,7 +903,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) connect(action, SIGNAL(toggled(bool)), parent(), SLOT(setShowData(bool))); connect(parent(), SIGNAL(showDataChanged(bool)), - action, SLOT(setOn(bool))); + action, SLOT(setChecked(bool))); action->setChecked(showData); headerPopup->addAction(action); } @@ -1012,6 +1012,16 @@ ConfigInfoView::ConfigInfoView(QWidget* parent, const char *name) configSettings->endGroup(); connect(configApp, SIGNAL(aboutToQuit()), SLOT(saveSettings())); } + + contextMenu = createStandardContextMenu(); + QAction *action = new QAction("Show Debug Info", contextMenu); + + action->setCheckable(true); + connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool))); + connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setChecked(bool))); + action->setChecked(showDebug()); + contextMenu->addSeparator(); + contextMenu->addAction(action); } void ConfigInfoView::saveSettings(void) @@ -1066,80 +1076,80 @@ void ConfigInfoView::symbolInfo(void) void ConfigInfoView::menuInfo(void) { struct symbol* sym; - QString head, debug, help; + QString info; + QTextStream stream(&info); sym = _menu->sym; if (sym) { if (_menu->prompt) { - head += "<big><b>"; - head += print_filter(_menu->prompt->text); - head += "</b></big>"; + stream << "<big><b>"; + stream << print_filter(_menu->prompt->text); + stream << "</b></big>"; if (sym->name) { - head += " ("; + stream << " ("; if (showDebug()) - head += QString().sprintf("<a href=\"s%s\">", sym->name); - head += print_filter(sym->name); + stream << "<a href=\"s" << sym->name << "\">"; + stream << print_filter(sym->name); if (showDebug()) - head += "</a>"; - head += ")"; + stream << "</a>"; + stream << ")"; } } else if (sym->name) { - head += "<big><b>"; + stream << "<big><b>"; if (showDebug()) - head += QString().sprintf("<a href=\"s%s\">", sym->name); - head += print_filter(sym->name); + stream << "<a href=\"s" << sym->name << "\">"; + stream << print_filter(sym->name); if (showDebug()) - head += "</a>"; - head += "</b></big>"; + stream << "</a>"; + stream << "</b></big>"; } - head += "<br><br>"; + stream << "<br><br>"; if (showDebug()) - debug = debug_info(sym); + stream << debug_info(sym); - struct gstr help_gstr = str_new(); - menu_get_ext_help(_menu, &help_gstr); - help = print_filter(str_get(&help_gstr)); - str_free(&help_gstr); } else if (_menu->prompt) { - head += "<big><b>"; - head += print_filter(_menu->prompt->text); - head += "</b></big><br><br>"; + stream << "<big><b>"; + stream << print_filter(_menu->prompt->text); + stream << "</b></big><br><br>"; if (showDebug()) { if (_menu->prompt->visible.expr) { - debug += " dep: "; - expr_print(_menu->prompt->visible.expr, expr_print_help, &debug, E_NONE); - debug += "<br><br>"; + stream << " dep: "; + expr_print(_menu->prompt->visible.expr, + expr_print_help, &stream, E_NONE); + stream << "<br><br>"; } } } if (showDebug()) - debug += QString().sprintf("defined at %s:%d<br><br>", _menu->file->name, _menu->lineno); + stream << "defined at " << _menu->file->name << ":" + << _menu->lineno << "<br><br>"; - setText(head + debug + help); + setText(info); } QString ConfigInfoView::debug_info(struct symbol *sym) { QString debug; + QTextStream stream(&debug); - debug += "type: "; - debug += print_filter(sym_type_name(sym->type)); + stream << "type: "; + stream << print_filter(sym_type_name(sym->type)); if (sym_is_choice(sym)) - debug += " (choice)"; + stream << " (choice)"; debug += "<br>"; if (sym->rev_dep.expr) { - debug += "reverse dep: "; - expr_print(sym->rev_dep.expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << "reverse dep: "; + expr_print(sym->rev_dep.expr, expr_print_help, &stream, E_NONE); + stream << "<br>"; } for (struct property *prop = sym->prop; prop; prop = prop->next) { switch (prop->type) { case P_PROMPT: case P_MENU: - debug += QString().sprintf("prompt: <a href=\"m%s\">", sym->name); - debug += print_filter(prop->text); - debug += "</a><br>"; + stream << "prompt: <a href=\"m" << sym->name << "\">"; + stream << print_filter(prop->text); + stream << "</a><br>"; break; case P_DEFAULT: case P_SELECT: @@ -1147,30 +1157,33 @@ QString ConfigInfoView::debug_info(struct symbol *sym) case P_COMMENT: case P_IMPLY: case P_SYMBOL: - debug += prop_get_type_name(prop->type); - debug += ": "; - expr_print(prop->expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << prop_get_type_name(prop->type); + stream << ": "; + expr_print(prop->expr, expr_print_help, + &stream, E_NONE); + stream << "<br>"; break; case P_CHOICE: if (sym_is_choice(sym)) { - debug += "choice: "; - expr_print(prop->expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << "choice: "; + expr_print(prop->expr, expr_print_help, + &stream, E_NONE); + stream << "<br>"; } break; default: - debug += "unknown property: "; - debug += prop_get_type_name(prop->type); - debug += "<br>"; + stream << "unknown property: "; + stream << prop_get_type_name(prop->type); + stream << "<br>"; } if (prop->visible.expr) { - debug += " dep: "; - expr_print(prop->visible.expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << " dep: "; + expr_print(prop->visible.expr, expr_print_help, + &stream, E_NONE); + stream << "<br>"; } } - debug += "<br>"; + stream << "<br>"; return debug; } @@ -1208,15 +1221,15 @@ QString ConfigInfoView::print_filter(const QString &str) void ConfigInfoView::expr_print_help(void *data, struct symbol *sym, const char *str) { - QString* text = reinterpret_cast<QString*>(data); - QString str2 = print_filter(str); + QTextStream *stream = reinterpret_cast<QTextStream *>(data); if (sym && sym->name && !(sym->flags & SYMBOL_CONST)) { - *text += QString().sprintf("<a href=\"s%s\">", sym->name); - *text += str2; - *text += "</a>"; - } else - *text += str2; + *stream << "<a href=\"s" << sym->name << "\">"; + *stream << print_filter(str); + *stream << "</a>"; + } else { + *stream << print_filter(str); + } } void ConfigInfoView::clicked(const QUrl &url) @@ -1228,7 +1241,6 @@ void ConfigInfoView::clicked(const QUrl &url) struct menu *m = NULL; if (count < 1) { - qInfo() << "Clicked link is empty"; delete[] data; return; } @@ -1241,7 +1253,6 @@ void ConfigInfoView::clicked(const QUrl &url) strcat(data, "$"); result = sym_re_search(data); if (!result) { - qInfo() << "Clicked symbol is invalid:" << data; delete[] data; return; } @@ -1268,23 +1279,10 @@ void ConfigInfoView::clicked(const QUrl &url) delete data; } -QMenu* ConfigInfoView::createStandardContextMenu(const QPoint & pos) -{ - QMenu* popup = Parent::createStandardContextMenu(pos); - QAction* action = new QAction("Show Debug Info", popup); - - action->setCheckable(true); - connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool))); - connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setOn(bool))); - action->setChecked(showDebug()); - popup->addSeparator(); - popup->addAction(action); - return popup; -} - -void ConfigInfoView::contextMenuEvent(QContextMenuEvent *e) +void ConfigInfoView::contextMenuEvent(QContextMenuEvent *event) { - Parent::contextMenuEvent(e); + contextMenu->popup(event->globalPos()); + event->accept(); } ConfigSearchWindow::ConfigSearchWindow(ConfigMainWindow *parent) diff --git a/scripts/kconfig/qconf.h b/scripts/kconfig/qconf.h index 461df6419f15..f97376a8123f 100644 --- a/scripts/kconfig/qconf.h +++ b/scripts/kconfig/qconf.h @@ -30,7 +30,7 @@ public: }; enum colIdx { - promptColIdx, nameColIdx, noColIdx, modColIdx, yesColIdx, dataColIdx, colNr + promptColIdx, nameColIdx, noColIdx, modColIdx, yesColIdx, dataColIdx }; enum listMode { singleMode, menuMode, symbolMode, fullMode, listMode @@ -215,6 +215,7 @@ public: class ConfigInfoView : public QTextBrowser { Q_OBJECT typedef class QTextBrowser Parent; + QMenu *contextMenu; public: ConfigInfoView(QWidget* parent, const char *name = 0); bool showDebug(void) const { return _showDebug; } @@ -235,8 +236,7 @@ protected: QString debug_info(struct symbol *sym); static QString print_filter(const QString &str); static void expr_print_help(void *data, struct symbol *sym, const char *str); - QMenu *createStandardContextMenu(const QPoint & pos); - void contextMenuEvent(QContextMenuEvent *e); + void contextMenuEvent(QContextMenuEvent *event); struct symbol *sym; struct menu *_menu; diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl index 19857d18d814..1c78ba49ca99 100755 --- a/scripts/kconfig/streamline_config.pl +++ b/scripts/kconfig/streamline_config.pl @@ -593,7 +593,10 @@ while ($repeat) { } my %setconfigs; -my @preserved_kconfigs = split(/:/,$ENV{LMC_KEEP}); +my @preserved_kconfigs; +if (defined($ENV{'LMC_KEEP'})) { + @preserved_kconfigs = split(/:/,$ENV{LMC_KEEP}); +} sub in_preserved_kconfigs { my $kconfig = $config2kfile{$_[0]}; diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 7b0e13ce7dc7..f919ebd042fd 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -577,7 +577,7 @@ static struct aa_label *x_to_label(struct aa_profile *profile, stack = NULL; break; } - /* fall through - to X_NAME */ + fallthrough; /* to X_NAME */ case AA_X_NAME: if (xindex & AA_X_CHILD) /* released by caller */ diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c index 30c246a9d440..fa49b81eb54c 100644 --- a/security/apparmor/lib.c +++ b/security/apparmor/lib.c @@ -292,13 +292,13 @@ void aa_apply_modes_to_perms(struct aa_profile *profile, struct aa_perms *perms) switch (AUDIT_MODE(profile)) { case AUDIT_ALL: perms->audit = ALL_PERMS_MASK; - /* fall through */ + fallthrough; case AUDIT_NOQUIET: perms->quiet = 0; break; case AUDIT_QUIET: perms->audit = 0; - /* fall through */ + fallthrough; case AUDIT_QUIET_DENIED: perms->quiet = ALL_PERMS_MASK; break; diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c index 32d32d485451..788667d582ae 100644 --- a/security/bpf/hooks.c +++ b/security/bpf/hooks.c @@ -11,6 +11,7 @@ static struct security_hook_list bpf_lsm_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(NAME, bpf_lsm_##NAME), #include <linux/lsm_hook_defs.h> #undef LSM_HOOK + LSM_HOOK_INIT(inode_free_security, bpf_inode_storage_free), }; static int __init bpf_lsm_init(void) @@ -20,7 +21,12 @@ static int __init bpf_lsm_init(void) return 0; } +struct lsm_blob_sizes bpf_lsm_blob_sizes __lsm_ro_after_init = { + .lbs_inode = sizeof(struct bpf_storage_blob), +}; + DEFINE_LSM(bpf) = { .name = "bpf", .init = bpf_lsm_init, + .blobs = &bpf_lsm_blob_sizes }; diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 372d16382960..b8848f53c8cc 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -223,7 +223,7 @@ static int xattr_verify(enum ima_hooks func, struct integrity_iint_cache *iint, case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ hash_start = 1; - /* fall through */ + fallthrough; case IMA_XATTR_DIGEST: if (iint->flags & IMA_DIGSIG_REQUIRED) { *cause = "IMA-signature-required"; @@ -395,7 +395,7 @@ int ima_appraise_measurement(enum ima_hooks func, /* It's fine not to have xattrs when using a modsig. */ if (try_modsig) break; - /* fall through */ + fallthrough; case INTEGRITY_NOLABEL: /* No security.evm xattr. */ cause = "missing-HMAC"; goto out; diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 07f033634b27..b4de33074b37 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -1279,12 +1279,12 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) case Opt_uid_gt: case Opt_euid_gt: entry->uid_op = &uid_gt; - /* fall through */ + fallthrough; case Opt_uid_lt: case Opt_euid_lt: if ((token == Opt_uid_lt) || (token == Opt_euid_lt)) entry->uid_op = &uid_lt; - /* fall through */ + fallthrough; case Opt_uid_eq: case Opt_euid_eq: uid_token = (token == Opt_uid_eq) || @@ -1313,11 +1313,11 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) break; case Opt_fowner_gt: entry->fowner_op = &uid_gt; - /* fall through */ + fallthrough; case Opt_fowner_lt: if (token == Opt_fowner_lt) entry->fowner_op = &uid_lt; - /* fall through */ + fallthrough; case Opt_fowner_eq: ima_log_string_op(ab, "fowner", args[0].from, entry->fowner_op); diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index 41a5f435b793..c022ee9e2a4e 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -77,7 +77,7 @@ static void ima_show_template_data_ascii(struct seq_file *m, /* skip ':' and '\0' */ buf_ptr += 2; buflen -= buf_ptr - field_data->data; - /* fall through */ + fallthrough; case DATA_FMT_DIGEST: case DATA_FMT_HEX: if (!buflen) diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 7e0232db1707..1fe8b934f656 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -465,7 +465,7 @@ key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx) case -EAGAIN: /* no key */ if (ret) break; - /* fall through */ + fallthrough; case -ENOKEY: /* negative key */ ret = key_ref; break; @@ -487,7 +487,7 @@ key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx) case -EAGAIN: /* no key */ if (ret) break; - /* fall through */ + fallthrough; case -ENOKEY: /* negative key */ ret = key_ref; break; @@ -509,7 +509,7 @@ key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx) case -EAGAIN: /* no key */ if (ret) break; - /* fall through */ + fallthrough; case -ENOKEY: /* negative key */ ret = key_ref; break; diff --git a/security/keys/request_key.c b/security/keys/request_key.c index e1b9f1a80676..2da4404276f0 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -295,26 +295,26 @@ static int construct_get_dest_keyring(struct key **_dest_keyring) } } - /* fall through */ + fallthrough; case KEY_REQKEY_DEFL_THREAD_KEYRING: dest_keyring = key_get(cred->thread_keyring); if (dest_keyring) break; - /* fall through */ + fallthrough; case KEY_REQKEY_DEFL_PROCESS_KEYRING: dest_keyring = key_get(cred->process_keyring); if (dest_keyring) break; - /* fall through */ + fallthrough; case KEY_REQKEY_DEFL_SESSION_KEYRING: dest_keyring = key_get(cred->session_keyring); if (dest_keyring) break; - /* fall through */ + fallthrough; case KEY_REQKEY_DEFL_USER_SESSION_KEYRING: ret = look_up_user_keyrings(NULL, &dest_keyring); if (ret < 0) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index ca901025802a..a340986aa92e 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3606,26 +3606,20 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case FIONREAD: - /* fall through */ case FIBMAP: - /* fall through */ case FIGETBSZ: - /* fall through */ case FS_IOC_GETFLAGS: - /* fall through */ case FS_IOC_GETVERSION: error = file_has_perm(cred, file, FILE__GETATTR); break; case FS_IOC_SETFLAGS: - /* fall through */ case FS_IOC_SETVERSION: error = file_has_perm(cred, file, FILE__SETATTR); break; /* sys_ioctl() checks */ case FIONBIO: - /* fall through */ case FIOASYNC: error = file_has_perm(cred, file, 0); break; @@ -3783,7 +3777,7 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd, err = file_has_perm(cred, file, FILE__WRITE); break; } - /* fall through */ + fallthrough; case F_SETOWN: case F_SETSIG: case F_GETFL: diff --git a/security/selinux/ss/mls.c b/security/selinux/ss/mls.c index 408d306895f8..d338962fb0c4 100644 --- a/security/selinux/ss/mls.c +++ b/security/selinux/ss/mls.c @@ -535,7 +535,7 @@ int mls_compute_sid(struct policydb *p, scontext, tcontext); } - /* Fallthrough */ + fallthrough; case AVTAB_CHANGE: if ((tclass == p->process_class) || sock) /* Use the process MLS attributes. */ @@ -546,8 +546,6 @@ int mls_compute_sid(struct policydb *p, case AVTAB_MEMBER: /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); - - /* fall through */ } return -EINVAL; } diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 8ffbf951b7ed..8c0893eb5aa8 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -3365,7 +3365,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode) * to set mount options simulate setting the * superblock default. */ - /* Fall through */ + fallthrough; default: /* * This isn't an understood special case. diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index c16b8c1b03e7..4bee32bfe16d 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -1240,7 +1240,7 @@ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head, tomoyo_set_space(head); tomoyo_set_string(head, cond->transit->name); } - /* fall through */ + fallthrough; case 1: { const u16 condc = cond->condc; @@ -1345,12 +1345,12 @@ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head, } } head->r.cond_step++; - /* fall through */ + fallthrough; case 2: if (!tomoyo_flush(head)) break; head->r.cond_step++; - /* fall through */ + fallthrough; case 3: if (cond->grant_log != TOMOYO_GRANTLOG_AUTO) tomoyo_io_printf(head, " grant_log=%s", @@ -1639,7 +1639,7 @@ static void tomoyo_read_domain(struct tomoyo_io_buffer *head) tomoyo_set_string(head, tomoyo_dif[i]); head->r.index = 0; head->r.step++; - /* fall through */ + fallthrough; case 1: while (head->r.index < TOMOYO_MAX_ACL_GROUPS) { i = head->r.index++; @@ -1652,14 +1652,14 @@ static void tomoyo_read_domain(struct tomoyo_io_buffer *head) head->r.index = 0; head->r.step++; tomoyo_set_lf(head); - /* fall through */ + fallthrough; case 2: if (!tomoyo_read_domain2(head, &domain->acl_info_list)) return; head->r.step++; if (!tomoyo_set_lf(head)) return; - /* fall through */ + fallthrough; case 3: head->r.step = 0; if (head->r.print_this_domain_only) @@ -2088,7 +2088,7 @@ int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) /* Check max_learning_entry parameter. */ if (tomoyo_domain_quota_is_ok(r)) break; - /* fall through */ + fallthrough; default: return 0; } @@ -2710,13 +2710,13 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, case TOMOYO_DOMAINPOLICY: if (tomoyo_select_domain(head, cp0)) continue; - /* fall through */ + fallthrough; case TOMOYO_EXCEPTIONPOLICY: if (!strcmp(cp0, "select transition_only")) { head->r.print_transition_related_only = true; continue; } - /* fall through */ + fallthrough; default: if (!tomoyo_manager()) { error = -EPERM; diff --git a/security/tomoyo/file.c b/security/tomoyo/file.c index 86f7d1b90212..051f7297877c 100644 --- a/security/tomoyo/file.c +++ b/security/tomoyo/file.c @@ -927,7 +927,7 @@ int tomoyo_path2_perm(const u8 operation, const struct path *path1, case TOMOYO_TYPE_LINK: if (!d_is_dir(path1->dentry)) break; - /* fall through */ + fallthrough; case TOMOYO_TYPE_PIVOT_ROOT: tomoyo_add_slash(&buf1); tomoyo_add_slash(&buf2); diff --git a/sound/core/oss/mulaw.c b/sound/core/oss/mulaw.c index 3788906421a7..fe27034f2846 100644 --- a/sound/core/oss/mulaw.c +++ b/sound/core/oss/mulaw.c @@ -329,8 +329,8 @@ int snd_pcm_plugin_build_mulaw(struct snd_pcm_substream *plug, snd_BUG(); return -EINVAL; } - if (snd_BUG_ON(!snd_pcm_format_linear(format->format))) - return -ENXIO; + if (!snd_pcm_format_linear(format->format)) + return -EINVAL; err = snd_pcm_plugin_build(plug, "Mu-Law<->linear conversion", src_format, dst_format, diff --git a/sound/core/timer.c b/sound/core/timer.c index d9f85f2d66a3..6e27d87b18ed 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -816,9 +816,9 @@ static void snd_timer_clear_callbacks(struct snd_timer *timer, * timer tasklet * */ -static void snd_timer_tasklet(unsigned long arg) +static void snd_timer_tasklet(struct tasklet_struct *t) { - struct snd_timer *timer = (struct snd_timer *) arg; + struct snd_timer *timer = from_tasklet(timer, t, task_queue); unsigned long flags; if (timer->card && timer->card->shutdown) { @@ -967,8 +967,7 @@ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid, INIT_LIST_HEAD(&timer->ack_list_head); INIT_LIST_HEAD(&timer->sack_list_head); spin_lock_init(&timer->lock); - tasklet_init(&timer->task_queue, snd_timer_tasklet, - (unsigned long)timer); + tasklet_setup(&timer->task_queue, snd_timer_tasklet); timer->max_instances = 1000; /* default limit per timer */ if (card != NULL) { timer->module = card->module; diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index f8586f75441d..ee1c428b1fd3 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -64,7 +64,7 @@ #define IT_PKT_HEADER_SIZE_CIP 8 // For 2 CIP header. #define IT_PKT_HEADER_SIZE_NO_CIP 0 // Nothing. -static void pcm_period_tasklet(unsigned long data); +static void pcm_period_tasklet(struct tasklet_struct *t); /** * amdtp_stream_init - initialize an AMDTP stream structure @@ -94,7 +94,7 @@ int amdtp_stream_init(struct amdtp_stream *s, struct fw_unit *unit, s->flags = flags; s->context = ERR_PTR(-1); mutex_init(&s->mutex); - tasklet_init(&s->period_tasklet, pcm_period_tasklet, (unsigned long)s); + tasklet_setup(&s->period_tasklet, pcm_period_tasklet); s->packet_index = 0; init_waitqueue_head(&s->callback_wait); @@ -441,9 +441,9 @@ static void update_pcm_pointers(struct amdtp_stream *s, } } -static void pcm_period_tasklet(unsigned long data) +static void pcm_period_tasklet(struct tasklet_struct *t) { - struct amdtp_stream *s = (void *)data; + struct amdtp_stream *s = from_tasklet(s, t, period_tasklet); struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); if (pcm) diff --git a/sound/firewire/digi00x/digi00x.c b/sound/firewire/digi00x/digi00x.c index c84b913a9fe0..ab8408966ec3 100644 --- a/sound/firewire/digi00x/digi00x.c +++ b/sound/firewire/digi00x/digi00x.c @@ -14,6 +14,7 @@ MODULE_LICENSE("GPL v2"); #define VENDOR_DIGIDESIGN 0x00a07e #define MODEL_CONSOLE 0x000001 #define MODEL_RACK 0x000002 +#define SPEC_VERSION 0x000001 static int name_card(struct snd_dg00x *dg00x) { @@ -175,14 +176,18 @@ static const struct ieee1394_device_id snd_dg00x_id_table[] = { /* Both of 002/003 use the same ID. */ { .match_flags = IEEE1394_MATCH_VENDOR_ID | + IEEE1394_MATCH_VERSION | IEEE1394_MATCH_MODEL_ID, .vendor_id = VENDOR_DIGIDESIGN, + .version = SPEC_VERSION, .model_id = MODEL_CONSOLE, }, { .match_flags = IEEE1394_MATCH_VENDOR_ID | + IEEE1394_MATCH_VERSION | IEEE1394_MATCH_MODEL_ID, .vendor_id = VENDOR_DIGIDESIGN, + .version = SPEC_VERSION, .model_id = MODEL_RACK, }, {} diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c index 5dac0d9fc58e..75f2edd8e78f 100644 --- a/sound/firewire/tascam/tascam.c +++ b/sound/firewire/tascam/tascam.c @@ -39,9 +39,6 @@ static const struct snd_tscm_spec model_specs[] = { .midi_capture_ports = 2, .midi_playback_ports = 4, }, - // This kernel module doesn't support FE-8 because the most of features - // can be implemented in userspace without any specific support of this - // module. }; static int identify_model(struct snd_tscm *tscm) @@ -211,11 +208,39 @@ static void snd_tscm_remove(struct fw_unit *unit) } static const struct ieee1394_device_id snd_tscm_id_table[] = { + // Tascam, FW-1884. + { + .match_flags = IEEE1394_MATCH_VENDOR_ID | + IEEE1394_MATCH_SPECIFIER_ID | + IEEE1394_MATCH_VERSION, + .vendor_id = 0x00022e, + .specifier_id = 0x00022e, + .version = 0x800000, + }, + // Tascam, FE-8 (.version = 0x800001) + // This kernel module doesn't support FE-8 because the most of features + // can be implemented in userspace without any specific support of this + // module. + // + // .version = 0x800002 is unknown. + // + // Tascam, FW-1082. + { + .match_flags = IEEE1394_MATCH_VENDOR_ID | + IEEE1394_MATCH_SPECIFIER_ID | + IEEE1394_MATCH_VERSION, + .vendor_id = 0x00022e, + .specifier_id = 0x00022e, + .version = 0x800003, + }, + // Tascam, FW-1804. { .match_flags = IEEE1394_MATCH_VENDOR_ID | - IEEE1394_MATCH_SPECIFIER_ID, + IEEE1394_MATCH_SPECIFIER_ID | + IEEE1394_MATCH_VERSION, .vendor_id = 0x00022e, .specifier_id = 0x00022e, + .version = 0x800004, }, {} }; diff --git a/sound/hda/hdac_bus.c b/sound/hda/hdac_bus.c index 09ddab5f5cae..9766f6af8743 100644 --- a/sound/hda/hdac_bus.c +++ b/sound/hda/hdac_bus.c @@ -46,6 +46,18 @@ int snd_hdac_bus_init(struct hdac_bus *bus, struct device *dev, INIT_LIST_HEAD(&bus->hlink_list); init_waitqueue_head(&bus->rirb_wq); bus->irq = -1; + + /* + * Default value of '8' is as per the HD audio specification (Rev 1.0a). + * Following relation is used to derive STRIPE control value. + * For sample rate <= 48K: + * { ((num_channels * bits_per_sample) / number of SDOs) >= 8 } + * For sample rate > 48K: + * { ((num_channels * bits_per_sample * rate/48000) / + * number of SDOs) >= 8 } + */ + bus->sdo_limit = 8; + return 0; } EXPORT_SYMBOL_GPL(snd_hdac_bus_init); diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index 011b17cc1efa..b98449fd92f3 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -529,17 +529,6 @@ bool snd_hdac_bus_init_chip(struct hdac_bus *bus, bool full_reset) bus->chip_init = true; - /* - * Default value of '8' is as per the HD audio specification (Rev 1.0a). - * Following relation is used to derive STRIPE control value. - * For sample rate <= 48K: - * { ((num_channels * bits_per_sample) / number of SDOs) >= 8 } - * For sample rate > 48K: - * { ((num_channels * bits_per_sample * rate/48000) / - * number of SDOs) >= 8 } - */ - bus->sdo_limit = 8; - return true; } EXPORT_SYMBOL_GPL(snd_hdac_bus_init_chip); diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c index 333220f0f8af..3e9e9ac804f6 100644 --- a/sound/hda/hdac_device.c +++ b/sound/hda/hdac_device.c @@ -127,6 +127,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_device_init); void snd_hdac_device_exit(struct hdac_device *codec) { pm_runtime_put_noidle(&codec->dev); + /* keep balance of runtime PM child_count in parent device */ + pm_runtime_set_suspended(&codec->dev); snd_hdac_bus_remove_device(codec->bus, codec); kfree(codec->vendor_name); kfree(codec->chip_name); diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 99aec7349167..1c5114dedda9 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -54,7 +54,7 @@ static const struct config_entry config_table[] = { #endif /* * Apollolake (Broxton-P) - * the legacy HDaudio driver is used except on Up Squared (SOF) and + * the legacy HDAudio driver is used except on Up Squared (SOF) and * Chromebooks (SST) */ #if IS_ENABLED(CONFIG_SND_SOC_SOF_APOLLOLAKE) @@ -89,7 +89,7 @@ static const struct config_entry config_table[] = { }, #endif /* - * Skylake and Kabylake use legacy HDaudio driver except for Google + * Skylake and Kabylake use legacy HDAudio driver except for Google * Chromebooks (SST) */ @@ -135,7 +135,7 @@ static const struct config_entry config_table[] = { #endif /* - * Geminilake uses legacy HDaudio driver except for Google + * Geminilake uses legacy HDAudio driver except for Google * Chromebooks */ /* Geminilake */ @@ -157,7 +157,7 @@ static const struct config_entry config_table[] = { /* * CoffeeLake, CannonLake, CometLake, IceLake, TigerLake use legacy - * HDaudio driver except for Google Chromebooks and when DMICs are + * HDAudio driver except for Google Chromebooks and when DMICs are * present. Two cases are required since Coreboot does not expose NHLT * tables. * @@ -391,7 +391,7 @@ int snd_intel_dsp_driver_probe(struct pci_dev *pci) if (pci->class == 0x040300) return SND_INTEL_DSP_DRIVER_LEGACY; if (pci->class != 0x040100 && pci->class != 0x040380) { - dev_err(&pci->dev, "Unknown PCI class/subclass/prog-if information (0x%06x) found, selecting HDA legacy driver\n", pci->class); + dev_err(&pci->dev, "Unknown PCI class/subclass/prog-if information (0x%06x) found, selecting HDAudio legacy driver\n", pci->class); return SND_INTEL_DSP_DRIVER_LEGACY; } diff --git a/sound/isa/sscape.c b/sound/isa/sscape.c index 5363d88cc4b9..2e5a5c5279e8 100644 --- a/sound/isa/sscape.c +++ b/sound/isa/sscape.c @@ -308,7 +308,7 @@ static inline int verify_mpu401(const struct snd_mpu401 *mpu) } /* - * This is apparently the standard way to initailise an MPU-401 + * This is apparently the standard way to initialise an MPU-401 */ static inline void initialise_mpu401(const struct snd_mpu401 *mpu) { @@ -339,7 +339,7 @@ static void soundscape_free(struct snd_card *c) } /* - * Tell the SoundScape to begin a DMA tranfer using the given channel. + * Tell the SoundScape to begin a DMA transfer using the given channel. * All locking issues are left to the caller. */ static void sscape_start_dma_unsafe(unsigned io_base, enum GA_REG reg) @@ -803,7 +803,7 @@ static int mpu401_open(struct snd_mpu401 *mpu) } /* - * Initialse an MPU-401 subdevice for MIDI support on the SoundScape. + * Initialise an MPU-401 subdevice for MIDI support on the SoundScape. */ static int create_mpu401(struct snd_card *card, int devnum, unsigned long port, int irq) diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c index 023c35a2a951..35e76480306e 100644 --- a/sound/pci/asihpi/asihpi.c +++ b/sound/pci/asihpi/asihpi.c @@ -921,10 +921,10 @@ static void snd_card_asihpi_timer_function(struct timer_list *t) add_timer(&dpcm->timer); } -static void snd_card_asihpi_int_task(unsigned long data) +static void snd_card_asihpi_int_task(struct tasklet_struct *t) { - struct hpi_adapter *a = (struct hpi_adapter *)data; - struct snd_card_asihpi *asihpi; + struct snd_card_asihpi *asihpi = from_tasklet(asihpi, t, t); + struct hpi_adapter *a = asihpi->hpi; WARN_ON(!a || !a->snd_card || !a->snd_card->private_data); asihpi = (struct snd_card_asihpi *)a->snd_card->private_data; @@ -2871,8 +2871,7 @@ static int snd_asihpi_probe(struct pci_dev *pci_dev, if (hpi->interrupt_mode) { asihpi->pcm_start = snd_card_asihpi_pcm_int_start; asihpi->pcm_stop = snd_card_asihpi_pcm_int_stop; - tasklet_init(&asihpi->t, snd_card_asihpi_int_task, - (unsigned long)hpi); + tasklet_setup(&asihpi->t, snd_card_asihpi_int_task); hpi->interrupt_callback = snd_card_asihpi_isr; } else { asihpi->pcm_start = snd_card_asihpi_pcm_timer_start; diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c index 70d775ff967e..c189f70c82cb 100644 --- a/sound/pci/ca0106/ca0106_main.c +++ b/sound/pci/ca0106/ca0106_main.c @@ -537,7 +537,8 @@ static int snd_ca0106_pcm_power_dac(struct snd_ca0106 *chip, int channel_id, else /* Power down */ chip->spi_dac_reg[reg] |= bit; - return snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]); + if (snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]) != 0) + return -ENXIO; } return 0; } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e34a4d5d047c..36a9dbc33aa0 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2127,9 +2127,10 @@ static int azx_probe(struct pci_dev *pci, */ if (dmic_detect) { err = snd_intel_dsp_driver_probe(pci); - if (err != SND_INTEL_DSP_DRIVER_ANY && - err != SND_INTEL_DSP_DRIVER_LEGACY) + if (err != SND_INTEL_DSP_DRIVER_ANY && err != SND_INTEL_DSP_DRIVER_LEGACY) { + dev_dbg(&pci->dev, "HDAudio driver not selected, aborting probe\n"); return -ENODEV; + } } else { dev_warn(&pci->dev, "dmic_detect option is deprecated, pass snd-intel-dspcfg.dsp_driver=1 option instead\n"); } @@ -2745,8 +2746,6 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_HDMI }, /* Zhaoxin */ { PCI_DEVICE(0x1d17, 0x3288), .driver_data = AZX_DRIVER_ZHAOXIN }, - /* Loongson */ - { PCI_DEVICE(0x0014, 0x7a07), .driver_data = AZX_DRIVER_GENERIC }, { 0, } }; MODULE_DEVICE_TABLE(pci, azx_ids); diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c index c94553bcca88..70164d1428d4 100644 --- a/sound/pci/hda/hda_tegra.c +++ b/sound/pci/hda/hda_tegra.c @@ -179,6 +179,10 @@ static int __maybe_unused hda_tegra_runtime_suspend(struct device *dev) struct hda_tegra *hda = container_of(chip, struct hda_tegra, chip); if (chip && chip->running) { + /* enable controller wake up event */ + azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | + STATESTS_INT_MASK); + azx_stop_chip(chip); azx_enter_link_reset(chip); } @@ -200,6 +204,9 @@ static int __maybe_unused hda_tegra_runtime_resume(struct device *dev) if (chip && chip->running) { hda_tegra_init(hda); azx_init_chip(chip, 1); + /* disable controller wake up event*/ + azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & + ~STATESTS_INT_MASK); } return 0; diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index b8c8490e568b..402050088090 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2794,6 +2794,7 @@ static void i915_pin_cvt_fixup(struct hda_codec *codec, hda_nid_t cvt_nid) { if (per_pin) { + haswell_verify_D0(codec, per_pin->cvt_nid, per_pin->pin_nid); snd_hda_set_dev_select(codec, per_pin->pin_nid, per_pin->dev_id); intel_verify_pin_cvt_connect(codec, per_pin); @@ -3734,6 +3735,7 @@ static int tegra_hdmi_build_pcms(struct hda_codec *codec) static int patch_tegra_hdmi(struct hda_codec *codec) { + struct hdmi_spec *spec; int err; err = patch_generic_hdmi(codec); @@ -3741,6 +3743,10 @@ static int patch_tegra_hdmi(struct hda_codec *codec) return err; codec->patch_ops.build_pcms = tegra_hdmi_build_pcms; + spec = codec->spec; + spec->chmap.ops.chmap_cea_alloc_validate_get_type = + nvhdmi_chmap_cea_alloc_validate_get_type; + spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate; return 0; } @@ -4263,6 +4269,7 @@ HDA_CODEC_ENTRY(0x8086280c, "Cannonlake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi), +HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7f9d35273734..c521a1f17096 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2475,6 +2475,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), + SND_PCI_QUIRK(0x1462, 0x9c37, "MSI X570-A PRO", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), @@ -5867,6 +5868,39 @@ static void alc275_fixup_gpio4_off(struct hda_codec *codec, } } +/* Quirk for Thinkpad X1 7th and 8th Gen + * The following fixed routing needed + * DAC1 (NID 0x02) -> Speaker (NID 0x14); some eq applied secretly + * DAC2 (NID 0x03) -> Bass (NID 0x17) & Headphone (NID 0x21); sharing a DAC + * DAC3 (NID 0x06) -> Unused, due to the lack of volume amp + */ +static void alc285_fixup_thinkpad_x1_gen7(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + static const hda_nid_t conn[] = { 0x02, 0x03 }; /* exclude 0x06 */ + static const hda_nid_t preferred_pairs[] = { + 0x14, 0x02, 0x17, 0x03, 0x21, 0x03, 0 + }; + struct alc_spec *spec = codec->spec; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn); + spec->gen.preferred_dacs = preferred_pairs; + break; + case HDA_FIXUP_ACT_BUILD: + /* The generic parser creates somewhat unintuitive volume ctls + * with the fixed routing above, and the shared DAC2 may be + * confusing for PA. + * Rename those to unique names so that PA doesn't touch them + * and use only Master volume. + */ + rename_ctl(codec, "Front Playback Volume", "DAC1 Playback Volume"); + rename_ctl(codec, "Bass Speaker Playback Volume", "DAC2 Playback Volume"); + break; + } +} + static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -6135,6 +6169,7 @@ enum { ALC289_FIXUP_DUAL_SPK, ALC294_FIXUP_SPK2_TO_DAC1, ALC294_FIXUP_ASUS_DUAL_SPK, + ALC285_FIXUP_THINKPAD_X1_GEN7, ALC285_FIXUP_THINKPAD_HEADSET_JACK, ALC294_FIXUP_ASUS_HPE, ALC294_FIXUP_ASUS_COEF_1B, @@ -7280,11 +7315,17 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_SPK2_TO_DAC1 }, + [ALC285_FIXUP_THINKPAD_X1_GEN7] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_thinkpad_x1_gen7, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI + }, [ALC285_FIXUP_THINKPAD_HEADSET_JACK] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_headset_jack, .chained = true, - .chain_id = ALC285_FIXUP_SPEAKER2_TO_DAC1 + .chain_id = ALC285_FIXUP_THINKPAD_X1_GEN7 }, [ALC294_FIXUP_ASUS_HPE] = { .type = HDA_FIXUP_VERBS, @@ -7694,6 +7735,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), @@ -7955,6 +7999,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC299_FIXUP_PREDATOR_SPK, .name = "predator-spk"}, {.id = ALC298_FIXUP_HUAWEI_MBX_STEREO, .name = "huawei-mbx-stereo"}, {.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"}, + {.id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc298-samsung-headphone"}, {} }; #define ALC225_STANDARD_PINS \ diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c index b4f300281822..098c69b3b7aa 100644 --- a/sound/pci/riptide/riptide.c +++ b/sound/pci/riptide/riptide.c @@ -1070,9 +1070,9 @@ getmixer(struct cmdif *cif, short num, unsigned short *rval, return 0; } -static void riptide_handleirq(unsigned long dev_id) +static void riptide_handleirq(struct tasklet_struct *t) { - struct snd_riptide *chip = (void *)dev_id; + struct snd_riptide *chip = from_tasklet(chip, t, riptide_tq); struct cmdif *cif = chip->cif; struct snd_pcm_substream *substream[PLAYBACK_SUBSTREAMS + 1]; struct snd_pcm_runtime *runtime; @@ -1843,7 +1843,7 @@ snd_riptide_create(struct snd_card *card, struct pci_dev *pci, chip->received_irqs = 0; chip->handled_irqs = 0; chip->cif = NULL; - tasklet_init(&chip->riptide_tq, riptide_handleirq, (unsigned long)chip); + tasklet_setup(&chip->riptide_tq, riptide_handleirq); if ((chip->res_port = request_region(chip->port, 64, "RIPTIDE")) == NULL) { diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 227aece17e39..dda56ecfd33b 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -3791,9 +3791,9 @@ static int snd_hdsp_set_defaults(struct hdsp *hdsp) return 0; } -static void hdsp_midi_tasklet(unsigned long arg) +static void hdsp_midi_tasklet(struct tasklet_struct *t) { - struct hdsp *hdsp = (struct hdsp *)arg; + struct hdsp *hdsp = from_tasklet(hdsp, t, midi_tasklet); if (hdsp->midi[0].pending) snd_hdsp_midi_input_read (&hdsp->midi[0]); @@ -5182,7 +5182,7 @@ static int snd_hdsp_create(struct snd_card *card, spin_lock_init(&hdsp->lock); - tasklet_init(&hdsp->midi_tasklet, hdsp_midi_tasklet, (unsigned long)hdsp); + tasklet_setup(&hdsp->midi_tasklet, hdsp_midi_tasklet); pci_read_config_word(hdsp->pci, PCI_CLASS_REVISION, &hdsp->firmware_rev); hdsp->firmware_rev &= 0xff; diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index 0fa49f4d15cf..572350aaf18d 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -2169,9 +2169,9 @@ static int snd_hdspm_create_midi(struct snd_card *card, } -static void hdspm_midi_tasklet(unsigned long arg) +static void hdspm_midi_tasklet(struct tasklet_struct *t) { - struct hdspm *hdspm = (struct hdspm *)arg; + struct hdspm *hdspm = from_tasklet(hdspm, t, midi_tasklet); int i = 0; while (i < hdspm->midiPorts) { @@ -6836,8 +6836,7 @@ static int snd_hdspm_create(struct snd_card *card, } - tasklet_init(&hdspm->midi_tasklet, - hdspm_midi_tasklet, (unsigned long) hdspm); + tasklet_setup(&hdspm->midi_tasklet, hdspm_midi_tasklet); if (hdspm->io_type != MADIface) { diff --git a/sound/ppc/snd_ps3.c b/sound/ppc/snd_ps3.c index b8161a08f2ca..58bb49fff184 100644 --- a/sound/ppc/snd_ps3.c +++ b/sound/ppc/snd_ps3.c @@ -227,14 +227,14 @@ static int snd_ps3_program_dma(struct snd_ps3_card_info *card, switch (filltype) { case SND_PS3_DMA_FILLTYPE_SILENT_FIRSTFILL: silent = 1; - /* intentionally fall thru */ + fallthrough; case SND_PS3_DMA_FILLTYPE_FIRSTFILL: ch0_kick_event = PS3_AUDIO_KICK_EVENT_ALWAYS; break; case SND_PS3_DMA_FILLTYPE_SILENT_RUNNING: silent = 1; - /* intentionally fall thru */ + fallthrough; case SND_PS3_DMA_FILLTYPE_RUNNING: ch0_kick_event = PS3_AUDIO_KICK_EVENT_SERIALOUT0_EMPTY; break; diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c index 55815fdaa1aa..406526e79af3 100644 --- a/sound/soc/amd/acp3x-rt5682-max9836.c +++ b/sound/soc/amd/acp3x-rt5682-max9836.c @@ -138,7 +138,7 @@ static int acp3x_1015_hw_params(struct snd_pcm_substream *substream, srate = params_rate(params); for_each_rtd_codec_dais(rtd, i, codec_dai) { - if (strcmp(codec_dai->component->name, "rt1015-aif")) + if (strcmp(codec_dai->name, "rt1015-aif")) continue; ret = snd_soc_dai_set_bclk_ratio(codec_dai, 64); if (ret < 0) diff --git a/sound/soc/amd/renoir/acp3x-pdm-dma.c b/sound/soc/amd/renoir/acp3x-pdm-dma.c index 623dfd3ea705..7b14d9a81b97 100644 --- a/sound/soc/amd/renoir/acp3x-pdm-dma.c +++ b/sound/soc/amd/renoir/acp3x-pdm-dma.c @@ -314,40 +314,30 @@ static int acp_pdm_dma_close(struct snd_soc_component *component, return 0; } -static int acp_pdm_dai_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params, - struct snd_soc_dai *dai) +static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream, + int cmd, struct snd_soc_dai *dai) { struct pdm_stream_instance *rtd; + int ret; + bool pdm_status; unsigned int ch_mask; rtd = substream->runtime->private_data; - switch (params_channels(params)) { + ret = 0; + switch (substream->runtime->channels) { case TWO_CH: ch_mask = 0x00; break; default: return -EINVAL; } - rn_writel(ch_mask, rtd->acp_base + ACP_WOV_PDM_NO_OF_CHANNELS); - rn_writel(PDM_DECIMATION_FACTOR, rtd->acp_base + - ACP_WOV_PDM_DECIMATION_FACTOR); - return 0; -} - -static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream, - int cmd, struct snd_soc_dai *dai) -{ - struct pdm_stream_instance *rtd; - int ret; - bool pdm_status; - - rtd = substream->runtime->private_data; - ret = 0; switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + rn_writel(ch_mask, rtd->acp_base + ACP_WOV_PDM_NO_OF_CHANNELS); + rn_writel(PDM_DECIMATION_FACTOR, rtd->acp_base + + ACP_WOV_PDM_DECIMATION_FACTOR); rtd->bytescount = acp_pdm_get_byte_count(rtd, substream->stream); pdm_status = check_pdm_dma_status(rtd->acp_base); @@ -369,7 +359,6 @@ static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream, } static struct snd_soc_dai_ops acp_pdm_dai_ops = { - .hw_params = acp_pdm_dai_hw_params, .trigger = acp_pdm_dai_trigger, }; diff --git a/sound/soc/atmel/mchp-i2s-mcc.c b/sound/soc/atmel/mchp-i2s-mcc.c index 3cb63886195f..04acc18f2d72 100644 --- a/sound/soc/atmel/mchp-i2s-mcc.c +++ b/sound/soc/atmel/mchp-i2s-mcc.c @@ -536,7 +536,7 @@ static int mchp_i2s_mcc_hw_params(struct snd_pcm_substream *substream, /* cpu is BCLK master */ mrb |= MCHP_I2SMCC_MRB_CLKSEL_INT; set_divs = 1; - /* fall through */ + fallthrough; case SND_SOC_DAIFMT_CBM_CFM: /* cpu is slave */ mra |= MCHP_I2SMCC_MRA_MODE_SLAVE; diff --git a/sound/soc/codecs/jz4770.c b/sound/soc/codecs/jz4770.c index c0a28f06b09a..298689a07168 100644 --- a/sound/soc/codecs/jz4770.c +++ b/sound/soc/codecs/jz4770.c @@ -202,7 +202,7 @@ static int jz4770_codec_set_bias_level(struct snd_soc_component *codec, REG_CR_VIC_SB_SLEEP, REG_CR_VIC_SB_SLEEP); regmap_update_bits(regmap, JZ4770_CODEC_REG_CR_VIC, REG_CR_VIC_SB, REG_CR_VIC_SB); - /* fall-through */ + fallthrough; default: break; } diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c index 4428c62e25cf..3ddd822240e3 100644 --- a/sound/soc/codecs/msm8916-wcd-analog.c +++ b/sound/soc/codecs/msm8916-wcd-analog.c @@ -19,8 +19,8 @@ #define CDC_D_REVISION1 (0xf000) #define CDC_D_PERPH_SUBTYPE (0xf005) -#define CDC_D_INT_EN_SET (0x015) -#define CDC_D_INT_EN_CLR (0x016) +#define CDC_D_INT_EN_SET (0xf015) +#define CDC_D_INT_EN_CLR (0xf016) #define MBHC_SWITCH_INT BIT(7) #define MBHC_MIC_ELECTRICAL_INS_REM_DET BIT(6) #define MBHC_BUTTON_PRESS_DET BIT(5) diff --git a/sound/soc/codecs/pcm186x.c b/sound/soc/codecs/pcm186x.c index f0da55901dcb..b8845f45549e 100644 --- a/sound/soc/codecs/pcm186x.c +++ b/sound/soc/codecs/pcm186x.c @@ -401,7 +401,7 @@ static int pcm186x_set_fmt(struct snd_soc_dai *dai, unsigned int format) break; case SND_SOC_DAIFMT_DSP_A: priv->tdm_offset += 1; - /* fall through */ + fallthrough; /* DSP_A uses the same basic config as DSP_B * except we need to shift the TDM output by one BCK cycle */ diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index 68a3b48e6b31..3bce9a14f0f3 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -412,8 +412,12 @@ int wm8958_aif_ev(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct wm8994 *control = dev_get_drvdata(component->dev->parent); int i; + if (control->type != WM8958) + return 0; + switch (event) { case SND_SOC_DAPM_POST_PMU: case SND_SOC_DAPM_PRE_PMU: diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 317916cb4e27..0623a2251084 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -151,7 +151,6 @@ static const struct reg_default wm8962_reg[] = { { 40, 0x0000 }, /* R40 - SPKOUTL volume */ { 41, 0x0000 }, /* R41 - SPKOUTR volume */ - { 48, 0x0000 }, /* R48 - Additional control(4) */ { 49, 0x0010 }, /* R49 - Class D Control 1 */ { 51, 0x0003 }, /* R51 - Class D Control 2 */ @@ -842,6 +841,7 @@ static bool wm8962_readable_register(struct device *dev, unsigned int reg) case WM8962_SPKOUTL_VOLUME: case WM8962_SPKOUTR_VOLUME: case WM8962_THERMAL_SHUTDOWN_STATUS: + case WM8962_ADDITIONAL_CONTROL_4: case WM8962_CLASS_D_CONTROL_1: case WM8962_CLASS_D_CONTROL_2: case WM8962_CLOCKING_4: diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index a84ae879d37e..038be667c1a6 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -43,10 +43,12 @@ #define WM8994_NUM_DRC 3 #define WM8994_NUM_EQ 3 -static struct { +struct wm8994_reg_mask { unsigned int reg; unsigned int mask; -} wm8994_vu_bits[] = { +}; + +static struct wm8994_reg_mask wm8994_vu_bits[] = { { WM8994_LEFT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU }, { WM8994_RIGHT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU }, { WM8994_LEFT_LINE_INPUT_3_4_VOLUME, WM8994_IN2_VU }, @@ -60,14 +62,10 @@ static struct { { WM8994_AIF1_DAC1_LEFT_VOLUME, WM8994_AIF1DAC1_VU }, { WM8994_AIF1_DAC1_RIGHT_VOLUME, WM8994_AIF1DAC1_VU }, - { WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU }, - { WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU }, { WM8994_AIF2_DAC_LEFT_VOLUME, WM8994_AIF2DAC_VU }, { WM8994_AIF2_DAC_RIGHT_VOLUME, WM8994_AIF2DAC_VU }, { WM8994_AIF1_ADC1_LEFT_VOLUME, WM8994_AIF1ADC1_VU }, { WM8994_AIF1_ADC1_RIGHT_VOLUME, WM8994_AIF1ADC1_VU }, - { WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU }, - { WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU }, { WM8994_AIF2_ADC_LEFT_VOLUME, WM8994_AIF2ADC_VU }, { WM8994_AIF2_ADC_RIGHT_VOLUME, WM8994_AIF1ADC2_VU }, { WM8994_DAC1_LEFT_VOLUME, WM8994_DAC1_VU }, @@ -76,6 +74,14 @@ static struct { { WM8994_DAC2_RIGHT_VOLUME, WM8994_DAC2_VU }, }; +/* VU bitfields for ADC2, DAC2 not available on WM1811 */ +static struct wm8994_reg_mask wm8994_adc2_dac2_vu_bits[] = { + { WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU }, + { WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU }, + { WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU }, + { WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU }, +}; + static int wm8994_drc_base[] = { WM8994_AIF1_DRC1_1, WM8994_AIF1_DRC2_1, @@ -1030,6 +1036,26 @@ static bool wm8994_check_class_w_digital(struct snd_soc_component *component) return true; } +static void wm8994_update_vu_bits(struct snd_soc_component *component) +{ + struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component); + struct wm8994 *control = wm8994->wm8994; + int i; + + for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++) + snd_soc_component_write(component, wm8994_vu_bits[i].reg, + snd_soc_component_read(component, + wm8994_vu_bits[i].reg)); + if (control->type == WM1811) + return; + + for (i = 0; i < ARRAY_SIZE(wm8994_adc2_dac2_vu_bits); i++) + snd_soc_component_write(component, + wm8994_adc2_dac2_vu_bits[i].reg, + snd_soc_component_read(component, + wm8994_adc2_dac2_vu_bits[i].reg)); +} + static int aif_mclk_set(struct snd_soc_component *component, int aif, bool enable) { struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component); @@ -1076,7 +1102,7 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w, struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component); struct wm8994 *control = wm8994->wm8994; int mask = WM8994_AIF1DAC1L_ENA | WM8994_AIF1DAC1R_ENA; - int ret, i; + int ret; int dac; int adc; int val; @@ -1144,10 +1170,7 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w, break; case SND_SOC_DAPM_POST_PMU: - for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++) - snd_soc_component_write(component, wm8994_vu_bits[i].reg, - snd_soc_component_read(component, - wm8994_vu_bits[i].reg)); + wm8994_update_vu_bits(component); break; case SND_SOC_DAPM_PRE_PMD: @@ -1181,7 +1204,7 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); - int ret, i; + int ret; int dac; int adc; int val; @@ -1237,10 +1260,7 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w, break; case SND_SOC_DAPM_POST_PMU: - for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++) - snd_soc_component_write(component, wm8994_vu_bits[i].reg, - snd_soc_component_read(component, - wm8994_vu_bits[i].reg)); + wm8994_update_vu_bits(component); break; case SND_SOC_DAPM_PRE_PMD: @@ -4346,6 +4366,14 @@ static int wm8994_component_probe(struct snd_soc_component *component) wm8994_vu_bits[i].mask, wm8994_vu_bits[i].mask); + if (control->type != WM1811) { + for (i = 0; i < ARRAY_SIZE(wm8994_adc2_dac2_vu_bits); i++) + snd_soc_component_update_bits(component, + wm8994_adc2_dac2_vu_bits[i].reg, + wm8994_adc2_dac2_vu_bits[i].mask, + wm8994_adc2_dac2_vu_bits[i].mask); + } + /* Set the low bit of the 3D stereo depth so TLV matches */ snd_soc_component_update_bits(component, WM8994_AIF1_DAC1_FILTERS_2, 1 << WM8994_AIF1DAC1_3D_GAIN_SHIFT, diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index de136c0a497d..52adedc03245 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -73,6 +73,7 @@ struct cpu_priv { * @codec_priv: CODEC private data * @cpu_priv: CPU private data * @card: ASoC card structure + * @streams: Mask of current active streams * @sample_rate: Current sample rate * @sample_format: Current sample format * @asrc_rate: ASRC sample rate used by Back-Ends @@ -89,6 +90,7 @@ struct fsl_asoc_card_priv { struct codec_priv codec_priv; struct cpu_priv cpu_priv; struct snd_soc_card card; + u8 streams; u32 sample_rate; snd_pcm_format_t sample_format; u32 asrc_rate; @@ -151,21 +153,17 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream); struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card); bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; + struct codec_priv *codec_priv = &priv->codec_priv; struct cpu_priv *cpu_priv = &priv->cpu_priv; struct device *dev = rtd->card->dev; + unsigned int pll_out; int ret; priv->sample_rate = params_rate(params); priv->sample_format = params_format(params); + priv->streams |= BIT(substream->stream); - /* - * If codec-dai is DAI Master and all configurations are already in the - * set_bias_level(), bypass the remaining settings in hw_params(). - * Note: (dai_fmt & CBM_CFM) includes CBM_CFM and CBM_CFS. - */ - if ((priv->card.set_bias_level && - priv->dai_fmt & SND_SOC_DAIFMT_CBM_CFM) || - fsl_asoc_card_is_ac97(priv)) + if (fsl_asoc_card_is_ac97(priv)) return 0; /* Specific configurations of DAIs starts from here */ @@ -174,7 +172,7 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, cpu_priv->sysclk_dir[tx]); if (ret && ret != -ENOTSUPP) { dev_err(dev, "failed to set sysclk for cpu dai\n"); - return ret; + goto fail; } if (cpu_priv->slot_width) { @@ -182,6 +180,68 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, cpu_priv->slot_width); if (ret && ret != -ENOTSUPP) { dev_err(dev, "failed to set TDM slot for cpu dai\n"); + goto fail; + } + } + + /* Specific configuration for PLL */ + if (codec_priv->pll_id && codec_priv->fll_id) { + if (priv->sample_format == SNDRV_PCM_FORMAT_S24_LE) + pll_out = priv->sample_rate * 384; + else + pll_out = priv->sample_rate * 256; + + ret = snd_soc_dai_set_pll(asoc_rtd_to_codec(rtd, 0), + codec_priv->pll_id, + codec_priv->mclk_id, + codec_priv->mclk_freq, pll_out); + if (ret) { + dev_err(dev, "failed to start FLL: %d\n", ret); + goto fail; + } + + ret = snd_soc_dai_set_sysclk(asoc_rtd_to_codec(rtd, 0), + codec_priv->fll_id, + pll_out, SND_SOC_CLOCK_IN); + + if (ret && ret != -ENOTSUPP) { + dev_err(dev, "failed to set SYSCLK: %d\n", ret); + goto fail; + } + } + + return 0; + +fail: + priv->streams &= ~BIT(substream->stream); + return ret; +} + +static int fsl_asoc_card_hw_free(struct snd_pcm_substream *substream) +{ + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card); + struct codec_priv *codec_priv = &priv->codec_priv; + struct device *dev = rtd->card->dev; + int ret; + + priv->streams &= ~BIT(substream->stream); + + if (!priv->streams && codec_priv->pll_id && codec_priv->fll_id) { + /* Force freq to be 0 to avoid error message in codec */ + ret = snd_soc_dai_set_sysclk(asoc_rtd_to_codec(rtd, 0), + codec_priv->mclk_id, + 0, + SND_SOC_CLOCK_IN); + if (ret) { + dev_err(dev, "failed to switch away from FLL: %d\n", ret); + return ret; + } + + ret = snd_soc_dai_set_pll(asoc_rtd_to_codec(rtd, 0), + codec_priv->pll_id, 0, 0, 0); + if (ret && ret != -ENOTSUPP) { + dev_err(dev, "failed to stop FLL: %d\n", ret); return ret; } } @@ -191,6 +251,7 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, static const struct snd_soc_ops fsl_asoc_card_ops = { .hw_params = fsl_asoc_card_hw_params, + .hw_free = fsl_asoc_card_hw_free, }; static int be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, @@ -254,75 +315,6 @@ static struct snd_soc_dai_link fsl_asoc_card_dai[] = { }, }; -static int fsl_asoc_card_set_bias_level(struct snd_soc_card *card, - struct snd_soc_dapm_context *dapm, - enum snd_soc_bias_level level) -{ - struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(card); - struct snd_soc_pcm_runtime *rtd; - struct snd_soc_dai *codec_dai; - struct codec_priv *codec_priv = &priv->codec_priv; - struct device *dev = card->dev; - unsigned int pll_out; - int ret; - - rtd = snd_soc_get_pcm_runtime(card, &card->dai_link[0]); - codec_dai = asoc_rtd_to_codec(rtd, 0); - if (dapm->dev != codec_dai->dev) - return 0; - - switch (level) { - case SND_SOC_BIAS_PREPARE: - if (dapm->bias_level != SND_SOC_BIAS_STANDBY) - break; - - if (priv->sample_format == SNDRV_PCM_FORMAT_S24_LE) - pll_out = priv->sample_rate * 384; - else - pll_out = priv->sample_rate * 256; - - ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id, - codec_priv->mclk_id, - codec_priv->mclk_freq, pll_out); - if (ret) { - dev_err(dev, "failed to start FLL: %d\n", ret); - return ret; - } - - ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->fll_id, - pll_out, SND_SOC_CLOCK_IN); - if (ret && ret != -ENOTSUPP) { - dev_err(dev, "failed to set SYSCLK: %d\n", ret); - return ret; - } - break; - - case SND_SOC_BIAS_STANDBY: - if (dapm->bias_level != SND_SOC_BIAS_PREPARE) - break; - - ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->mclk_id, - codec_priv->mclk_freq, - SND_SOC_CLOCK_IN); - if (ret && ret != -ENOTSUPP) { - dev_err(dev, "failed to switch away from FLL: %d\n", ret); - return ret; - } - - ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id, 0, 0, 0); - if (ret) { - dev_err(dev, "failed to stop FLL: %d\n", ret); - return ret; - } - break; - - default: - break; - } - - return 0; -} - static int fsl_asoc_card_audmux_init(struct device_node *np, struct fsl_asoc_card_priv *priv) { @@ -611,7 +603,6 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) /* Diversify the card configurations */ if (of_device_is_compatible(np, "fsl,imx-audio-cs42888")) { codec_dai_name = "cs42888"; - priv->card.set_bias_level = NULL; priv->cpu_priv.sysclk_freq[TX] = priv->codec_priv.mclk_freq; priv->cpu_priv.sysclk_freq[RX] = priv->codec_priv.mclk_freq; priv->cpu_priv.sysclk_dir[TX] = SND_SOC_CLOCK_OUT; @@ -628,26 +619,22 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM; } else if (of_device_is_compatible(np, "fsl,imx-audio-wm8962")) { codec_dai_name = "wm8962"; - priv->card.set_bias_level = fsl_asoc_card_set_bias_level; priv->codec_priv.mclk_id = WM8962_SYSCLK_MCLK; priv->codec_priv.fll_id = WM8962_SYSCLK_FLL; priv->codec_priv.pll_id = WM8962_FLL; priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM; } else if (of_device_is_compatible(np, "fsl,imx-audio-wm8960")) { codec_dai_name = "wm8960-hifi"; - priv->card.set_bias_level = fsl_asoc_card_set_bias_level; priv->codec_priv.fll_id = WM8960_SYSCLK_AUTO; priv->codec_priv.pll_id = WM8960_SYSCLK_AUTO; priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM; } else if (of_device_is_compatible(np, "fsl,imx-audio-ac97")) { codec_dai_name = "ac97-hifi"; - priv->card.set_bias_level = NULL; priv->dai_fmt = SND_SOC_DAIFMT_AC97; priv->card.dapm_routes = audio_map_ac97; priv->card.num_dapm_routes = ARRAY_SIZE(audio_map_ac97); } else if (of_device_is_compatible(np, "fsl,imx-audio-mqs")) { codec_dai_name = "fsl-mqs-dai"; - priv->card.set_bias_level = NULL; priv->dai_fmt = SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS | SND_SOC_DAIFMT_NB_NF; @@ -657,7 +644,6 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) priv->card.num_dapm_routes = ARRAY_SIZE(audio_map_tx); } else if (of_device_is_compatible(np, "fsl,imx-audio-wm8524")) { codec_dai_name = "wm8524-hifi"; - priv->card.set_bias_level = NULL; priv->dai_fmt |= SND_SOC_DAIFMT_CBS_CFS; priv->dai_link[1].dpcm_capture = 0; priv->dai_link[2].dpcm_capture = 0; diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c index 4ae36099ae82..79b861afd986 100644 --- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -708,9 +708,9 @@ static void fsl_esai_trigger_stop(struct fsl_esai *esai_priv, bool tx) ESAI_xFCR_xFR, 0); } -static void fsl_esai_hw_reset(unsigned long arg) +static void fsl_esai_hw_reset(struct tasklet_struct *t) { - struct fsl_esai *esai_priv = (struct fsl_esai *)arg; + struct fsl_esai *esai_priv = from_tasklet(esai_priv, t, task); bool tx = true, rx = false, enabled[2]; unsigned long lock_flags; u32 tfcr, rfcr; @@ -1070,8 +1070,7 @@ static int fsl_esai_probe(struct platform_device *pdev) return ret; } - tasklet_init(&esai_priv->task, fsl_esai_hw_reset, - (unsigned long)esai_priv); + tasklet_setup(&esai_priv->task, fsl_esai_hw_reset); pm_runtime_enable(&pdev->dev); diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index d8b9c6547142..404be27c15fe 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -898,7 +898,7 @@ static int _fsl_ssi_set_dai_fmt(struct fsl_ssi *ssi, unsigned int fmt) "missing baudclk for master mode\n"); return -EINVAL; } - /* fall through */ + fallthrough; case SND_SOC_DAIFMT_CBM_CFS: ssi->i2s_net |= SSI_SCR_I2S_MODE_MASTER; break; diff --git a/sound/soc/fsl/mpc5200_dma.c b/sound/soc/fsl/mpc5200_dma.c index 9e4f66b6b92b..231984882176 100644 --- a/sound/soc/fsl/mpc5200_dma.c +++ b/sound/soc/fsl/mpc5200_dma.c @@ -339,7 +339,6 @@ static int psc_dma_new(struct snd_soc_component *component, static void psc_dma_free(struct snd_soc_component *component, struct snd_pcm *pcm) { - struct snd_soc_pcm_runtime *rtd = pcm->private_data; struct snd_pcm_substream *substream; int stream; diff --git a/sound/soc/hisilicon/hi6210-i2s.c b/sound/soc/hisilicon/hi6210-i2s.c index fd5dcd6b9f85..907f5f1f7b44 100644 --- a/sound/soc/hisilicon/hi6210-i2s.c +++ b/sound/soc/hisilicon/hi6210-i2s.c @@ -261,13 +261,13 @@ static int hi6210_i2s_hw_params(struct snd_pcm_substream *substream, switch (params_format(params)) { case SNDRV_PCM_FORMAT_U16_LE: signed_data = HII2S_I2S_CFG__S2_CODEC_DATA_FORMAT; - /* fall through */ + fallthrough; case SNDRV_PCM_FORMAT_S16_LE: bits = HII2S_BITS_16; break; case SNDRV_PCM_FORMAT_U24_LE: signed_data = HII2S_I2S_CFG__S2_CODEC_DATA_FORMAT; - /* fall through */ + fallthrough; case SNDRV_PCM_FORMAT_S24_LE: bits = HII2S_BITS_24; break; diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c index 49b9f18472bc..b1cac7abdc0a 100644 --- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c +++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c @@ -331,7 +331,7 @@ static int sst_media_open(struct snd_pcm_substream *substream, ret_val = power_up_sst(stream); if (ret_val < 0) - return ret_val; + goto out_power_up; /* Make sure, that the period size is always even */ snd_pcm_hw_constraint_step(substream->runtime, 0, @@ -340,8 +340,9 @@ static int sst_media_open(struct snd_pcm_substream *substream, return snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); out_ops: - kfree(stream); mutex_unlock(&sst_lock); +out_power_up: + kfree(stream); return ret_val; } diff --git a/sound/soc/intel/baytrail/sst-baytrail-pcm.c b/sound/soc/intel/baytrail/sst-baytrail-pcm.c index 54a66cc6db89..d2cda33b65d5 100644 --- a/sound/soc/intel/baytrail/sst-baytrail-pcm.c +++ b/sound/soc/intel/baytrail/sst-baytrail-pcm.c @@ -181,7 +181,7 @@ static int sst_byt_pcm_trigger(struct snd_soc_component *component, break; case SNDRV_PCM_TRIGGER_SUSPEND: pdata->restore_stream = false; - /* fallthrough */ + fallthrough; case SNDRV_PCM_TRIGGER_PAUSE_PUSH: sst_byt_stream_pause(byt, pcm_data->stream); break; diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c index 414ae4bb5224..7ae34b49815c 100644 --- a/sound/soc/intel/boards/bytcht_es8316.c +++ b/sound/soc/intel/boards/bytcht_es8316.c @@ -573,7 +573,7 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) break; default: dev_err(dev, "get speaker GPIO failed: %d\n", ret); - /* fall through */ + fallthrough; case -EPROBE_DEFER: return ret; } diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c index 4e2897596cea..688b5e0a49e3 100644 --- a/sound/soc/intel/boards/bytcr_rt5651.c +++ b/sound/soc/intel/boards/bytcr_rt5651.c @@ -1009,7 +1009,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Failed to get ext-amp-enable GPIO: %d\n", ret_val); - /* fall through */ + fallthrough; case -EPROBE_DEFER: put_device(codec_dev); return ret_val; @@ -1029,7 +1029,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Failed to get hp-detect GPIO: %d\n", ret_val); - /* fall through */ + fallthrough; case -EPROBE_DEFER: put_device(codec_dev); return ret_val; diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c index 5dee55e9546b..bbe8d782e0af 100644 --- a/sound/soc/intel/skylake/skl-pcm.c +++ b/sound/soc/intel/skylake/skl-pcm.c @@ -488,7 +488,7 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd, stream->lpib); snd_hdac_ext_stream_set_lpib(stream, stream->lpib); } - /* fall through */ + fallthrough; case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c index 36df30915378..c8664ab80d45 100644 --- a/sound/soc/meson/axg-tdm-interface.c +++ b/sound/soc/meson/axg-tdm-interface.c @@ -58,17 +58,17 @@ int axg_tdm_set_tdm_slots(struct snd_soc_dai *dai, u32 *tx_mask, switch (slot_width) { case 0: slot_width = 32; - /* Fall-through */ + fallthrough; case 32: fmt |= SNDRV_PCM_FMTBIT_S32_LE; - /* Fall-through */ + fallthrough; case 24: fmt |= SNDRV_PCM_FMTBIT_S24_LE; fmt |= SNDRV_PCM_FMTBIT_S20_LE; - /* Fall-through */ + fallthrough; case 16: fmt |= SNDRV_PCM_FMTBIT_S16_LE; - /* Fall-through */ + fallthrough; case 8: fmt |= SNDRV_PCM_FMTBIT_S8; break; @@ -133,7 +133,7 @@ static int axg_tdm_iface_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) case SND_SOC_DAIFMT_CBS_CFM: case SND_SOC_DAIFMT_CBM_CFS: dev_err(dai->dev, "only CBS_CFS and CBM_CFM are supported\n"); - /* Fall-through */ + fallthrough; default: return -EINVAL; } diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c index d1e09ade0190..c4e7307a4437 100644 --- a/sound/soc/pxa/pxa-ssp.c +++ b/sound/soc/pxa/pxa-ssp.c @@ -488,7 +488,7 @@ static int pxa_ssp_configure_dai_fmt(struct ssp_priv *priv) case SND_SOC_DAIFMT_DSP_A: sspsp |= SSPSP_FSRT; - /* fall through */ + fallthrough; case SND_SOC_DAIFMT_DSP_B: sscr0 |= SSCR0_MOD | SSCR0_PSP; sscr1 |= SSCR1_TRAIL | SSCR1_RWOT; diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c index 2a5302f1db98..0168af849272 100644 --- a/sound/soc/qcom/qdsp6/q6afe-dai.c +++ b/sound/soc/qcom/qdsp6/q6afe-dai.c @@ -1150,206 +1150,206 @@ static int q6afe_of_xlate_dai_name(struct snd_soc_component *component, } static const struct snd_soc_dapm_widget q6afe_dai_widgets[] = { - SND_SOC_DAPM_AIF_IN("HDMI_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_0_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_1_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_2_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_3_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_4_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_5_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_6_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("HDMI_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_0_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_1_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_2_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_3_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_4_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_5_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_6_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_TX", NULL, 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX_SD1", "Secondary MI2S Playback SD1", - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRI_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRI_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_7", NULL, - 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("DISPLAY_PORT_RX", "NULL", 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("DISPLAY_PORT_RX", "NULL", 0, SND_SOC_NOPM, 0, 0), }; static const struct snd_soc_component_driver q6afe_dai_component = { diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c index eaa95b5a7b66..25d23e0266c7 100644 --- a/sound/soc/qcom/qdsp6/q6routing.c +++ b/sound/soc/qcom/qdsp6/q6routing.c @@ -973,6 +973,20 @@ static int msm_routing_probe(struct snd_soc_component *c) return 0; } +static unsigned int q6routing_reg_read(struct snd_soc_component *component, + unsigned int reg) +{ + /* default value */ + return 0; +} + +static int q6routing_reg_write(struct snd_soc_component *component, + unsigned int reg, unsigned int val) +{ + /* dummy */ + return 0; +} + static const struct snd_soc_component_driver msm_soc_routing_component = { .probe = msm_routing_probe, .name = DRV_NAME, @@ -981,6 +995,8 @@ static const struct snd_soc_component_driver msm_soc_routing_component = { .num_dapm_widgets = ARRAY_SIZE(msm_qdsp6_widgets), .dapm_routes = intercon, .num_dapm_routes = ARRAY_SIZE(intercon), + .read = q6routing_reg_read, + .write = q6routing_reg_write, }; static int q6pcm_routing_probe(struct platform_device *pdev) diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c index 1707414cfa92..5adb293d0435 100644 --- a/sound/soc/rockchip/rockchip_pdm.c +++ b/sound/soc/rockchip/rockchip_pdm.c @@ -229,13 +229,13 @@ static int rockchip_pdm_hw_params(struct snd_pcm_substream *substream, switch (params_channels(params)) { case 8: val |= PDM_PATH3_EN; - /* fallthrough */ + fallthrough; case 6: val |= PDM_PATH2_EN; - /* fallthrough */ + fallthrough; case 4: val |= PDM_PATH1_EN; - /* fallthrough */ + fallthrough; case 2: val |= PDM_PATH0_EN; break; diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index 80ecb5c7fed0..df53d4ea808f 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -733,7 +733,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, switch (params_channels(params)) { case 6: val |= MOD_DC2_EN; - /* Fall through */ + fallthrough; case 4: val |= MOD_DC1_EN; break; diff --git a/sound/soc/sh/siu_pcm.c b/sound/soc/sh/siu_pcm.c index bd9de77c35f3..50fc7810723e 100644 --- a/sound/soc/sh/siu_pcm.c +++ b/sound/soc/sh/siu_pcm.c @@ -198,9 +198,9 @@ static int siu_pcm_rd_set(struct siu_port *port_info, return 0; } -static void siu_io_tasklet(unsigned long data) +static void siu_io_tasklet(struct tasklet_struct *t) { - struct siu_stream *siu_stream = (struct siu_stream *)data; + struct siu_stream *siu_stream = from_tasklet(siu_stream, t, tasklet); struct snd_pcm_substream *substream = siu_stream->substream; struct device *dev = substream->pcm->card->dev; struct snd_pcm_runtime *rt = substream->runtime; @@ -520,10 +520,8 @@ static int siu_pcm_new(struct snd_soc_component *component, (*port_info)->pcm = pcm; /* IO tasklets */ - tasklet_init(&(*port_info)->playback.tasklet, siu_io_tasklet, - (unsigned long)&(*port_info)->playback); - tasklet_init(&(*port_info)->capture.tasklet, siu_io_tasklet, - (unsigned long)&(*port_info)->capture); + tasklet_setup(&(*port_info)->playback.tasklet, siu_io_tasklet); + tasklet_setup(&(*port_info)->capture.tasklet, siu_io_tasklet); } dev_info(card->dev, "SuperH SIU driver initialized.\n"); diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c index f0b4f4bc44a4..5504b92946e3 100644 --- a/sound/soc/soc-component.c +++ b/sound/soc/soc-component.c @@ -406,7 +406,7 @@ static unsigned int soc_component_read_no_lock( ret = -EIO; if (ret < 0) - soc_component_ret(component, ret); + return soc_component_ret(component, ret); return val; } diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 2fe1b2ec7c8f..663e3839f251 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -618,7 +618,7 @@ int snd_soc_suspend(struct device *dev) "ASoC: idle_bias_off CODEC on over suspend\n"); break; } - /* fall through */ + fallthrough; case SND_SOC_BIAS_OFF: snd_soc_component_suspend(component); diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index cee998671318..5b60379237bf 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1057,7 +1057,7 @@ static int soc_tplg_denum_create(struct soc_tplg *tplg, unsigned int count, ec->hdr.name); goto err_denum; } - /* fall through */ + fallthrough; case SND_SOC_TPLG_CTL_ENUM: case SND_SOC_TPLG_DAPM_CTL_ENUM_DOUBLE: case SND_SOC_TPLG_DAPM_CTL_ENUM_VIRT: @@ -1445,7 +1445,7 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_denum_create( ec->hdr.name); goto err_se; } - /* fall through */ + fallthrough; case SND_SOC_TPLG_CTL_ENUM: case SND_SOC_TPLG_DAPM_CTL_ENUM_DOUBLE: case SND_SOC_TPLG_DAPM_CTL_ENUM_VIRT: diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index df1c6997cb4e..c6cb8c212eca 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -310,7 +310,7 @@ static int hda_link_pcm_trigger(struct snd_pcm_substream *substream, return ret; } - /* fallthrough */ + fallthrough; case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: snd_hdac_ext_link_stream_start(link_dev); @@ -333,7 +333,7 @@ static int hda_link_pcm_trigger(struct snd_pcm_substream *substream, link_dev->link_prepared = 0; - /* fallthrough */ + fallthrough; case SNDRV_PCM_TRIGGER_PAUSE_PUSH: snd_hdac_ext_link_stream_clear(link_dev); break; diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index d730e437e4ba..71c3f29057a7 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -361,7 +361,7 @@ static int sof_pcm_trigger(struct snd_soc_component *component, return ret; } - /* fallthrough */ + fallthrough; case SNDRV_PCM_TRIGGER_START: if (spcm->stream[substream->stream].suspend_ignored) { /* @@ -386,7 +386,7 @@ static int sof_pcm_trigger(struct snd_soc_component *component, spcm->stream[substream->stream].suspend_ignored = true; return 0; } - /* fallthrough */ + fallthrough; case SNDRV_PCM_TRIGGER_STOP: stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_STOP; ipc_first = true; diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c index fe7117171a0e..0cbe31e2c7e9 100644 --- a/sound/soc/tegra/tegra186_dspk.c +++ b/sound/soc/tegra/tegra186_dspk.c @@ -71,7 +71,7 @@ static int tegra186_dspk_put_control(struct snd_kcontrol *kcontrol, return 0; } -static int tegra186_dspk_runtime_suspend(struct device *dev) +static int __maybe_unused tegra186_dspk_runtime_suspend(struct device *dev) { struct tegra186_dspk *dspk = dev_get_drvdata(dev); @@ -83,7 +83,7 @@ static int tegra186_dspk_runtime_suspend(struct device *dev) return 0; } -static int tegra186_dspk_runtime_resume(struct device *dev) +static int __maybe_unused tegra186_dspk_runtime_resume(struct device *dev) { struct tegra186_dspk *dspk = dev_get_drvdata(dev); int err; diff --git a/sound/soc/tegra/tegra210_admaif.c b/sound/soc/tegra/tegra210_admaif.c index 4894e8e6ee7f..1268046b345d 100644 --- a/sound/soc/tegra/tegra210_admaif.c +++ b/sound/soc/tegra/tegra210_admaif.c @@ -219,7 +219,7 @@ static const struct regmap_config tegra186_admaif_regmap_config = { .cache_type = REGCACHE_FLAT, }; -static int tegra_admaif_runtime_suspend(struct device *dev) +static int __maybe_unused tegra_admaif_runtime_suspend(struct device *dev) { struct tegra_admaif *admaif = dev_get_drvdata(dev); @@ -229,7 +229,7 @@ static int tegra_admaif_runtime_suspend(struct device *dev) return 0; } -static int tegra_admaif_runtime_resume(struct device *dev) +static int __maybe_unused tegra_admaif_runtime_resume(struct device *dev) { struct tegra_admaif *admaif = dev_get_drvdata(dev); diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c index 5123a96fdde8..66287a7c9865 100644 --- a/sound/soc/tegra/tegra210_ahub.c +++ b/sound/soc/tegra/tegra210_ahub.c @@ -564,7 +564,7 @@ static const struct of_device_id tegra_ahub_of_match[] = { }; MODULE_DEVICE_TABLE(of, tegra_ahub_of_match); -static int tegra_ahub_runtime_suspend(struct device *dev) +static int __maybe_unused tegra_ahub_runtime_suspend(struct device *dev) { struct tegra_ahub *ahub = dev_get_drvdata(dev); @@ -576,7 +576,7 @@ static int tegra_ahub_runtime_suspend(struct device *dev) return 0; } -static int tegra_ahub_runtime_resume(struct device *dev) +static int __maybe_unused tegra_ahub_runtime_resume(struct device *dev) { struct tegra_ahub *ahub = dev_get_drvdata(dev); int err; diff --git a/sound/soc/tegra/tegra210_dmic.c b/sound/soc/tegra/tegra210_dmic.c index d682414ad90d..a661f40bc41c 100644 --- a/sound/soc/tegra/tegra210_dmic.c +++ b/sound/soc/tegra/tegra210_dmic.c @@ -40,7 +40,7 @@ static const struct reg_default tegra210_dmic_reg_defaults[] = { { TEGRA210_DMIC_LP_BIQUAD_1_COEF_4, 0x0 }, }; -static int tegra210_dmic_runtime_suspend(struct device *dev) +static int __maybe_unused tegra210_dmic_runtime_suspend(struct device *dev) { struct tegra210_dmic *dmic = dev_get_drvdata(dev); @@ -52,7 +52,7 @@ static int tegra210_dmic_runtime_suspend(struct device *dev) return 0; } -static int tegra210_dmic_runtime_resume(struct device *dev) +static int __maybe_unused tegra210_dmic_runtime_resume(struct device *dev) { struct tegra210_dmic *dmic = dev_get_drvdata(dev); int err; diff --git a/sound/soc/tegra/tegra210_i2s.c b/sound/soc/tegra/tegra210_i2s.c index 722092181583..a383bd5c51cd 100644 --- a/sound/soc/tegra/tegra210_i2s.c +++ b/sound/soc/tegra/tegra210_i2s.c @@ -164,7 +164,7 @@ static int tegra210_i2s_init(struct snd_soc_dapm_widget *w, return tegra210_i2s_sw_reset(compnt, is_playback); } -static int tegra210_i2s_runtime_suspend(struct device *dev) +static int __maybe_unused tegra210_i2s_runtime_suspend(struct device *dev) { struct tegra210_i2s *i2s = dev_get_drvdata(dev); @@ -176,7 +176,7 @@ static int tegra210_i2s_runtime_suspend(struct device *dev) return 0; } -static int tegra210_i2s_runtime_resume(struct device *dev) +static int __maybe_unused tegra210_i2s_runtime_resume(struct device *dev) { struct tegra210_i2s *i2s = dev_get_drvdata(dev); int err; diff --git a/sound/soc/ti/davinci-i2s.c b/sound/soc/ti/davinci-i2s.c index d89b5c928c4d..dd34504c09ba 100644 --- a/sound/soc/ti/davinci-i2s.c +++ b/sound/soc/ti/davinci-i2s.c @@ -289,7 +289,7 @@ static int davinci_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai, * rate is lowered. */ inv_fs = true; - /* fall through */ + fallthrough; case SND_SOC_DAIFMT_DSP_A: dev->mode = MOD_DSP_A; break; diff --git a/sound/soc/ti/n810.c b/sound/soc/ti/n810.c index 2802a33b9c5f..ed217b34f846 100644 --- a/sound/soc/ti/n810.c +++ b/sound/soc/ti/n810.c @@ -46,7 +46,7 @@ static void n810_ext_control(struct snd_soc_dapm_context *dapm) switch (n810_jack_func) { case N810_JACK_HS: line1l = 1; - /* fall through */ + fallthrough; case N810_JACK_HP: hp = 1; break; diff --git a/sound/soc/ti/omap-dmic.c b/sound/soc/ti/omap-dmic.c index 01abf1be5d78..a26588e9c3bc 100644 --- a/sound/soc/ti/omap-dmic.c +++ b/sound/soc/ti/omap-dmic.c @@ -203,10 +203,10 @@ static int omap_dmic_dai_hw_params(struct snd_pcm_substream *substream, switch (channels) { case 6: dmic->ch_enabled |= OMAP_DMIC_UP3_ENABLE; - /* fall through */ + fallthrough; case 4: dmic->ch_enabled |= OMAP_DMIC_UP2_ENABLE; - /* fall through */ + fallthrough; case 2: dmic->ch_enabled |= OMAP_DMIC_UP1_ENABLE; break; diff --git a/sound/soc/ti/omap-mcpdm.c b/sound/soc/ti/omap-mcpdm.c index d482b62f314a..fafb2998ad0d 100644 --- a/sound/soc/ti/omap-mcpdm.c +++ b/sound/soc/ti/omap-mcpdm.c @@ -309,19 +309,19 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream, /* up to 3 channels for capture */ return -EINVAL; link_mask |= 1 << 4; - /* fall through */ + fallthrough; case 4: if (stream == SNDRV_PCM_STREAM_CAPTURE) /* up to 3 channels for capture */ return -EINVAL; link_mask |= 1 << 3; - /* fall through */ + fallthrough; case 3: link_mask |= 1 << 2; - /* fall through */ + fallthrough; case 2: link_mask |= 1 << 1; - /* fall through */ + fallthrough; case 1: link_mask |= 1 << 0; break; diff --git a/sound/soc/ti/rx51.c b/sound/soc/ti/rx51.c index 2176a95201bf..a2629ccc1dc8 100644 --- a/sound/soc/ti/rx51.c +++ b/sound/soc/ti/rx51.c @@ -55,7 +55,7 @@ static void rx51_ext_control(struct snd_soc_dapm_context *dapm) break; case RX51_JACK_HS: hs = 1; - /* fall through */ + fallthrough; case RX51_JACK_HP: hp = 1; break; diff --git a/sound/soc/txx9/txx9aclc.c b/sound/soc/txx9/txx9aclc.c index 4b1cd4da3e36..939b33ec39f5 100644 --- a/sound/soc/txx9/txx9aclc.c +++ b/sound/soc/txx9/txx9aclc.c @@ -134,9 +134,9 @@ txx9aclc_dma_submit(struct txx9aclc_dmadata *dmadata, dma_addr_t buf_dma_addr) #define NR_DMA_CHAIN 2 -static void txx9aclc_dma_tasklet(unsigned long data) +static void txx9aclc_dma_tasklet(struct tasklet_struct *t) { - struct txx9aclc_dmadata *dmadata = (struct txx9aclc_dmadata *)data; + struct txx9aclc_dmadata *dmadata = from_tasklet(dmadata, t, tasklet); struct dma_chan *chan = dmadata->dma_chan; struct dma_async_tx_descriptor *desc; struct snd_pcm_substream *substream = dmadata->substream; @@ -352,8 +352,7 @@ static int txx9aclc_dma_init(struct txx9aclc_soc_device *dev, "playback" : "capture"); return -EBUSY; } - tasklet_init(&dmadata->tasklet, txx9aclc_dma_tasklet, - (unsigned long)dmadata); + tasklet_setup(&dmadata->tasklet, txx9aclc_dma_tasklet); return 0; } diff --git a/sound/soc/zte/zx-i2s.c b/sound/soc/zte/zx-i2s.c index 568cde64ff8b..1c1a44e08a67 100644 --- a/sound/soc/zte/zx-i2s.c +++ b/sound/soc/zte/zx-i2s.c @@ -294,7 +294,7 @@ static int zx_i2s_trigger(struct snd_pcm_substream *substream, int cmd, zx_i2s_rx_dma_en(zx_i2s->reg_base, true); else zx_i2s_tx_dma_en(zx_i2s->reg_base, true); - /* fall thru */ + fallthrough; case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: if (capture) @@ -308,7 +308,7 @@ static int zx_i2s_trigger(struct snd_pcm_substream *substream, int cmd, zx_i2s_rx_dma_en(zx_i2s->reg_base, false); else zx_i2s_tx_dma_en(zx_i2s->reg_base, false); - /* fall thru */ + fallthrough; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: if (capture) diff --git a/sound/soc/zte/zx-spdif.c b/sound/soc/zte/zx-spdif.c index a3a07c0730e6..b4168bd532b7 100644 --- a/sound/soc/zte/zx-spdif.c +++ b/sound/soc/zte/zx-spdif.c @@ -218,7 +218,7 @@ static int zx_spdif_trigger(struct snd_pcm_substream *substream, int cmd, val = readl_relaxed(zx_spdif->reg_base + ZX_FIFOCTRL); val |= ZX_FIFOCTRL_TX_FIFO_RST; writel_relaxed(val, zx_spdif->reg_base + ZX_FIFOCTRL); - /* fall thru */ + fallthrough; case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: zx_spdif_cfg_tx(zx_spdif->reg_base, true); diff --git a/sound/usb/midi.c b/sound/usb/midi.c index df639fe03118..e8287a05e36b 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -344,10 +344,9 @@ static void snd_usbmidi_do_output(struct snd_usb_midi_out_endpoint *ep) spin_unlock_irqrestore(&ep->buffer_lock, flags); } -static void snd_usbmidi_out_tasklet(unsigned long data) +static void snd_usbmidi_out_tasklet(struct tasklet_struct *t) { - struct snd_usb_midi_out_endpoint *ep = - (struct snd_usb_midi_out_endpoint *) data; + struct snd_usb_midi_out_endpoint *ep = from_tasklet(ep, t, tasklet); snd_usbmidi_do_output(ep); } @@ -1441,7 +1440,7 @@ static int snd_usbmidi_out_endpoint_create(struct snd_usb_midi *umidi, } spin_lock_init(&ep->buffer_lock); - tasklet_init(&ep->tasklet, snd_usbmidi_out_tasklet, (unsigned long)ep); + tasklet_setup(&ep->tasklet, snd_usbmidi_out_tasklet); init_waitqueue_head(&ep->drain_wait); for (i = 0; i < 0x10; ++i) diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c index 884e740a785c..3b2dce1043f5 100644 --- a/sound/usb/misc/ua101.c +++ b/sound/usb/misc/ua101.c @@ -247,9 +247,9 @@ static inline void add_with_wraparound(struct ua101 *ua, *value -= ua->playback.queue_length; } -static void playback_tasklet(unsigned long data) +static void playback_tasklet(struct tasklet_struct *t) { - struct ua101 *ua = (void *)data; + struct ua101 *ua = from_tasklet(ua, t, playback_tasklet); unsigned long flags; unsigned int frames; struct ua101_urb *urb; @@ -1218,8 +1218,7 @@ static int ua101_probe(struct usb_interface *interface, spin_lock_init(&ua->lock); mutex_init(&ua->mutex); INIT_LIST_HEAD(&ua->ready_playback_urbs); - tasklet_init(&ua->playback_tasklet, - playback_tasklet, (unsigned long)ua); + tasklet_setup(&ua->playback_tasklet, playback_tasklet); init_waitqueue_head(&ua->alsa_capture_wait); init_waitqueue_head(&ua->rate_feedback_wait); init_waitqueue_head(&ua->alsa_playback_wait); diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 6b0f3a8469ef..81e987eaf063 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -2371,7 +2371,7 @@ static int build_audio_procunit(struct mixer_build *state, int unitid, int num_ins; struct usb_mixer_elem_info *cval; struct snd_kcontrol *kctl; - int i, err, nameid, type, len; + int i, err, nameid, type, len, val; const struct procunit_info *info; const struct procunit_value_info *valinfo; const struct usbmix_name_map *map; @@ -2474,6 +2474,12 @@ static int build_audio_procunit(struct mixer_build *state, int unitid, break; } + err = get_cur_ctl_value(cval, cval->control << 8, &val); + if (err < 0) { + usb_mixer_elem_info_free(cval); + return -EINVAL; + } + kctl = snd_ctl_new1(&mixer_procunit_ctl, cval); if (!kctl) { usb_mixer_elem_info_free(cval); diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 5600751803cf..b401ee894e1b 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -369,11 +369,13 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ case USB_ID(0x31e9, 0x0001): /* Solid State Logic SSL2 */ case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */ + case USB_ID(0x0499, 0x172f): /* Steinberg UR22C */ case USB_ID(0x0d9a, 0x00df): /* RTX6001 */ ep = 0x81; ifnum = 2; goto add_sync_ep_from_ifnum; case USB_ID(0x2b73, 0x000a): /* Pioneer DJ DJM-900NXS2 */ + case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */ ep = 0x82; ifnum = 0; goto add_sync_ep_from_ifnum; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index d79e3ddc5690..23eafd50126f 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2680,6 +2680,10 @@ YAMAHA_DEVICE(0x7010, "UB99"), .data = (const struct snd_usb_audio_quirk[]) { { .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_MIXER, + }, + { + .ifnum = 0, .type = QUIRK_AUDIO_FIXED_ENDPOINT, .data = &(const struct audioformat) { .formats = SNDRV_PCM_FMTBIT_S24_3LE, @@ -2690,6 +2694,32 @@ YAMAHA_DEVICE(0x7010, "UB99"), .attributes = UAC_EP_CS_ATTR_SAMPLE_RATE, .endpoint = 0x01, .ep_attr = USB_ENDPOINT_XFER_ISOC, + .datainterval = 1, + .maxpacksize = 0x024c, + .rates = SNDRV_PCM_RATE_44100 | + SNDRV_PCM_RATE_48000, + .rate_min = 44100, + .rate_max = 48000, + .nr_rates = 2, + .rate_table = (unsigned int[]) { + 44100, 48000 + } + } + }, + { + .ifnum = 0, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S24_3LE, + .channels = 2, + .iface = 0, + .altsetting = 1, + .altset_idx = 1, + .attributes = 0, + .endpoint = 0x82, + .ep_attr = USB_ENDPOINT_XFER_ISOC, + .datainterval = 1, + .maxpacksize = 0x0126, .rates = SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000, .rate_min = 44100, @@ -2797,14 +2827,24 @@ YAMAHA_DEVICE(0x7010, "UB99"), /* Lenovo ThinkStation P620 Rear Line-in, Line-out and Microphone */ { USB_DEVICE(0x17aa, 0x1046), - QUIRK_DEVICE_PROFILE("Lenovo", "ThinkStation P620 Rear", - "Lenovo-ThinkStation-P620-Rear"), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .vendor_name = "Lenovo", + .product_name = "ThinkStation P620 Rear", + .profile_name = "Lenovo-ThinkStation-P620-Rear", + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_SETUP_DISABLE_AUTOSUSPEND + } }, /* Lenovo ThinkStation P620 Internal Speaker + Front Headset */ { USB_DEVICE(0x17aa, 0x104d), - QUIRK_DEVICE_PROFILE("Lenovo", "ThinkStation P620 Main", - "Lenovo-ThinkStation-P620-Main"), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .vendor_name = "Lenovo", + .product_name = "ThinkStation P620 Main", + .profile_name = "Lenovo-ThinkStation-P620-Main", + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_SETUP_DISABLE_AUTOSUSPEND + } }, /* Native Instruments MK2 series */ @@ -3519,14 +3559,40 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), { /* * Pioneer DJ DJM-250MK2 - * PCM is 8 channels out @ 48 fixed (endpoints 0x01). - * The output from computer to the mixer is usable. + * PCM is 8 channels out @ 48 fixed (endpoint 0x01) + * and 8 channels in @ 48 fixed (endpoint 0x82). + * + * Both playback and recording is working, even simultaneously. + * + * Playback channels could be mapped to: + * - CH1 + * - CH2 + * - AUX * - * The input (phono or line to computer) is not working. - * It should be at endpoint 0x82 and probably also 8 channels, - * but it seems that it works only with Pioneer proprietary software. - * Even on officially supported OS, the Audacity was unable to record - * and Mixxx to recognize the control vinyls. + * Recording channels could be mapped to: + * - Post CH1 Fader + * - Post CH2 Fader + * - Cross Fader A + * - Cross Fader B + * - MIC + * - AUX + * - REC OUT + * + * There is remaining problem with recording directly from PHONO/LINE. + * If we map a channel to: + * - CH1 Control Tone PHONO + * - CH1 Control Tone LINE + * - CH2 Control Tone PHONO + * - CH2 Control Tone LINE + * it is silent. + * There is no signal even on other operating systems with official drivers. + * The signal appears only when a supported application is started. + * This needs to be investigated yet... + * (there is quite a lot communication on the USB in both directions) + * + * In current version this mixer could be used for playback + * and for recording from vinyls (through Post CH* Fader) + * but not for DVS (Digital Vinyl Systems) like in Mixxx. */ USB_DEVICE_VENDOR_SPEC(0x2b73, 0x0017), .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { @@ -3550,6 +3616,26 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), .rate_max = 48000, .nr_rates = 1, .rate_table = (unsigned int[]) { 48000 } + } + }, + { + .ifnum = 0, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S24_3LE, + .channels = 8, // inputs + .iface = 0, + .altsetting = 1, + .altset_idx = 1, + .endpoint = 0x82, + .ep_attr = USB_ENDPOINT_XFER_ISOC| + USB_ENDPOINT_SYNC_ASYNC| + USB_ENDPOINT_USAGE_IMPLICIT_FB, + .rates = SNDRV_PCM_RATE_48000, + .rate_min = 48000, + .rate_max = 48000, + .nr_rates = 1, + .rate_table = (unsigned int[]) { 48000 } } }, { @@ -3714,8 +3800,8 @@ ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */ * they pretend to be 96kHz mono as a workaround for stereo being broken * by that... * - * They also have swapped L-R channels, but that's for userspace to deal - * with. + * They also have an issue with initial stream alignment that causes the + * channels to be swapped and out of phase, which is dealt with in quirks.c. */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index abf99b814a0f..75bbdc691243 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -518,6 +518,15 @@ static int setup_fmt_after_resume_quirk(struct snd_usb_audio *chip, return 1; /* Continue with creating streams and mixer */ } +static int setup_disable_autosuspend(struct snd_usb_audio *chip, + struct usb_interface *iface, + struct usb_driver *driver, + const struct snd_usb_audio_quirk *quirk) +{ + driver->supports_autosuspend = 0; + return 1; /* Continue with creating streams and mixer */ +} + /* * audio-interface quirks * @@ -557,6 +566,7 @@ int snd_usb_create_quirk(struct snd_usb_audio *chip, [QUIRK_AUDIO_ALIGN_TRANSFER] = create_align_transfer_quirk, [QUIRK_AUDIO_STANDARD_MIXER] = create_standard_mixer_quirk, [QUIRK_SETUP_FMT_AFTER_RESUME] = setup_fmt_after_resume_quirk, + [QUIRK_SETUP_DISABLE_AUTOSUSPEND] = setup_disable_autosuspend, }; if (quirk->type < QUIRK_TYPE_COUNT) { @@ -1493,6 +1503,7 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs, set_format_emu_quirk(subs, fmt); break; case USB_ID(0x2b73, 0x000a): /* Pioneer DJ DJM-900NXS2 */ + case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */ pioneer_djm_set_format_quirk(subs); break; case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */ diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index b91c4c0807ec..6839915a0128 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -102,6 +102,7 @@ enum quirk_type { QUIRK_AUDIO_ALIGN_TRANSFER, QUIRK_AUDIO_STANDARD_MIXER, QUIRK_SETUP_FMT_AFTER_RESUME, + QUIRK_SETUP_DISABLE_AUTOSUSPEND, QUIRK_TYPE_COUNT }; diff --git a/sound/x86/Kconfig b/sound/x86/Kconfig index 77777192f650..4ffcc5e623c2 100644 --- a/sound/x86/Kconfig +++ b/sound/x86/Kconfig @@ -9,7 +9,7 @@ menuconfig SND_X86 if SND_X86 config HDMI_LPE_AUDIO - tristate "HDMI audio without HDaudio on Intel Atom platforms" + tristate "HDMI audio without HDAudio on Intel Atom platforms" depends on DRM_I915 select SND_PCM help diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 41e2a74252d0..083db6c2fc67 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -49,7 +49,7 @@ MAP COMMANDS | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** -| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** } +| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** } DESCRIPTION =========== diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 8462690a039b..02c99bc95c69 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -176,7 +176,11 @@ $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) $(OUTPUT)%.o: %.c $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< -clean: $(LIBBPF)-clean +feature-detect-clean: + $(call QUIET_CLEAN, feature-detect) + $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null + +clean: $(LIBBPF)-clean feature-detect-clean $(call QUIET_CLEAN, bpftool) $(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d $(Q)$(RM) -- $(BPFTOOL_BOOTSTRAP) $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index f53ed2f1a4aa..7b68e3c0a5fb 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -704,7 +704,8 @@ _bpftool() lru_percpu_hash lpm_trie array_of_maps \ hash_of_maps devmap devmap_hash sockmap cpumap \ xskmap sockhash cgroup_storage reuseport_sockarray \ - percpu_cgroup_storage queue stack' -- \ + percpu_cgroup_storage queue stack sk_storage \ + struct_ops inode_storage' -- \ "$cur" ) ) return 0 ;; diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index ede162f83eea..0e9310727281 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -67,7 +67,7 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, if (!info->btf_id || !info->nr_func_info || btf__get_from_id(info->btf_id, &prog_btf)) goto print; - finfo = (struct bpf_func_info *)info->func_info; + finfo = u64_to_ptr(info->func_info); func_type = btf__type_by_id(prog_btf, finfo->type_id); if (!func_type || !btf_is_func(func_type)) goto print; diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 8a4c2b3b0cd6..4033c46d83e7 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -19,11 +19,9 @@ #include <sys/mman.h> #include <bpf/btf.h> -#include "bpf/libbpf_internal.h" #include "json_writer.h" #include "main.h" - #define MAX_OBJ_NAME_LEN 64 static void sanitize_identifier(char *name) @@ -143,6 +141,20 @@ static int codegen_datasec_def(struct bpf_object *obj, var_name, align); return -EINVAL; } + /* Assume 32-bit architectures when generating data section + * struct memory layout. Given bpftool can't know which target + * host architecture it's emitting skeleton for, we need to be + * conservative and assume 32-bit one to ensure enough padding + * bytes are generated for pointer and long types. This will + * still work correctly for 64-bit architectures, because in + * the worst case we'll generate unnecessary padding field, + * which on 64-bit architectures is not strictly necessary and + * would be handled by natural 8-byte alignment. But it still + * will be a correct memory layout, based on recorded offsets + * in BTF. + */ + if (align > 4) + align = 4; align_off = (off + align - 1) / align * align; if (align_off != need_off) { @@ -397,7 +409,7 @@ static int do_skeleton(int argc, char **argv) { \n\ struct %1$s *obj; \n\ \n\ - obj = (typeof(obj))calloc(1, sizeof(*obj)); \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ if (!obj) \n\ return NULL; \n\ if (%1$s__create_skeleton(obj)) \n\ @@ -461,7 +473,7 @@ static int do_skeleton(int argc, char **argv) { \n\ struct bpf_object_skeleton *s; \n\ \n\ - s = (typeof(s))calloc(1, sizeof(*s)); \n\ + s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ if (!s) \n\ return -1; \n\ obj->skeleton = s; \n\ @@ -479,7 +491,7 @@ static int do_skeleton(int argc, char **argv) /* maps */ \n\ s->map_cnt = %zu; \n\ s->map_skel_sz = sizeof(*s->maps); \n\ - s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\ + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ if (!s->maps) \n\ goto err; \n\ ", @@ -515,7 +527,7 @@ static int do_skeleton(int argc, char **argv) /* programs */ \n\ s->prog_cnt = %zu; \n\ s->prog_skel_sz = sizeof(*s->progs); \n\ - s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);\n\ + s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ if (!s->progs) \n\ goto err; \n\ ", diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 1b793759170e..e77e1525d20a 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -77,6 +77,22 @@ static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr) jsonw_uint_field(wtr, "attach_type", attach_type); } +static bool is_iter_map_target(const char *target_name) +{ + return strcmp(target_name, "bpf_map_elem") == 0 || + strcmp(target_name, "bpf_sk_storage_map") == 0; +} + +static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + const char *target_name = u64_to_ptr(info->iter.target_name); + + jsonw_string_field(wtr, "target_name", target_name); + + if (is_iter_map_target(target_name)) + jsonw_uint_field(wtr, "map_id", info->iter.map.map_id); +} + static int get_prog_info(int prog_id, struct bpf_prog_info *info) { __u32 len = sizeof(*info); @@ -106,7 +122,7 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) switch (info->type) { case BPF_LINK_TYPE_RAW_TRACEPOINT: jsonw_string_field(json_wtr, "tp_name", - (const char *)info->raw_tracepoint.tp_name); + u64_to_ptr(info->raw_tracepoint.tp_name)); break; case BPF_LINK_TYPE_TRACING: err = get_prog_info(info->prog_id, &prog_info); @@ -128,6 +144,9 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) info->cgroup.cgroup_id); show_link_attach_type_json(info->cgroup.attach_type, json_wtr); break; + case BPF_LINK_TYPE_ITER: + show_iter_json(info, json_wtr); + break; case BPF_LINK_TYPE_NETNS: jsonw_uint_field(json_wtr, "netns_ino", info->netns.netns_ino); @@ -175,6 +194,16 @@ static void show_link_attach_type_plain(__u32 attach_type) printf("attach_type %u ", attach_type); } +static void show_iter_plain(struct bpf_link_info *info) +{ + const char *target_name = u64_to_ptr(info->iter.target_name); + + printf("target_name %s ", target_name); + + if (is_iter_map_target(target_name)) + printf("map_id %u ", info->iter.map.map_id); +} + static int show_link_close_plain(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; @@ -185,7 +214,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) switch (info->type) { case BPF_LINK_TYPE_RAW_TRACEPOINT: printf("\n\ttp '%s' ", - (const char *)info->raw_tracepoint.tp_name); + (const char *)u64_to_ptr(info->raw_tracepoint.tp_name)); break; case BPF_LINK_TYPE_TRACING: err = get_prog_info(info->prog_id, &prog_info); @@ -204,6 +233,9 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id); show_link_attach_type_plain(info->cgroup.attach_type); break; + case BPF_LINK_TYPE_ITER: + show_iter_plain(info); + break; case BPF_LINK_TYPE_NETNS: printf("\n\tnetns_ino %u ", info->netns.netns_ino); show_link_attach_type_plain(info->netns.attach_type); @@ -231,7 +263,7 @@ static int do_show_link(int fd) { struct bpf_link_info info; __u32 len = sizeof(info); - char raw_tp_name[256]; + char buf[256]; int err; memset(&info, 0, sizeof(info)); @@ -245,8 +277,14 @@ again: } if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT && !info.raw_tracepoint.tp_name) { - info.raw_tracepoint.tp_name = (unsigned long)&raw_tp_name; - info.raw_tracepoint.tp_name_len = sizeof(raw_tp_name); + info.raw_tracepoint.tp_name = (unsigned long)&buf; + info.raw_tracepoint.tp_name_len = sizeof(buf); + goto again; + } + if (info.type == BPF_LINK_TYPE_ITER && + !info.iter.target_name) { + info.iter.target_name = (unsigned long)&buf; + info.iter.target_name_len = sizeof(buf); goto again; } diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index e3a79b5a9960..c46e52137b87 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -21,7 +21,15 @@ /* Make sure we do not use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 -#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *)(unsigned long)ptr; +} #define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) #define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 3a27d31a1856..bc0071228f88 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -50,6 +50,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", [BPF_MAP_TYPE_RINGBUF] = "ringbuf", + [BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); @@ -1442,7 +1443,7 @@ static int do_help(int argc, char **argv) " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" - " queue | stack | sk_storage | struct_ops | ringbuf }\n" + " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2]); diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 56c3a2bae3ef..910e7bac6e9e 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -6,22 +6,27 @@ #include <fcntl.h> #include <stdlib.h> #include <string.h> +#include <time.h> #include <unistd.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> #include <net/if.h> #include <linux/if.h> #include <linux/rtnetlink.h> +#include <linux/socket.h> #include <linux/tc_act/tc_bpf.h> #include <sys/socket.h> #include <sys/stat.h> #include <sys/types.h> #include "bpf/nlattr.h" -#include "bpf/libbpf_internal.h" #include "main.h" #include "netlink_dumper.h" +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif + struct ip_devname_ifindex { char devname[64]; int ifindex; @@ -85,6 +90,266 @@ static enum net_attach_type parse_attach_type(const char *str) return net_attach_type_size; } +typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); + +typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t, void *cookie); + +static int netlink_open(__u32 *nl_pid) +{ + struct sockaddr_nl sa; + socklen_t addrlen; + int one = 1, ret; + int sock; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) + return -errno; + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + p_err("Netlink error reporting not supported"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + *nl_pid = sa.nl_pid; + return sock; + +cleanup: + close(sock); + return ret; +} + +static int netlink_recv(int sock, __u32 nl_pid, __u32 seq, + __dump_nlmsg_t _fn, dump_nlmsg_t fn, + void *cookie) +{ + bool multipart = true; + struct nlmsgerr *err; + struct nlmsghdr *nh; + char buf[4096]; + int len, ret; + + while (multipart) { + multipart = false; + len = recv(sock, buf, sizeof(buf), 0); + if (len < 0) { + ret = -errno; + goto done; + } + + if (len == 0) + break; + + for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != nl_pid) { + ret = -LIBBPF_ERRNO__WRNGPID; + goto done; + } + if (nh->nlmsg_seq != seq) { + ret = -LIBBPF_ERRNO__INVSEQ; + goto done; + } + if (nh->nlmsg_flags & NLM_F_MULTI) + multipart = true; + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + libbpf_nla_dump_errormsg(nh); + goto done; + case NLMSG_DONE: + return 0; + default: + break; + } + if (_fn) { + ret = _fn(nh, fn, cookie); + if (ret) + return ret; + } + } + } + ret = 0; +done: + return ret; +} + +static int __dump_class_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_class_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_class_nlmsg(cookie, t, tb); +} + +static int netlink_get_class(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_class_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTCLASS, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg, + dump_class_nlmsg, cookie); +} + +static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_qdisc_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_qdisc_nlmsg(cookie, t, tb); +} + +static int netlink_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_qdisc_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETQDISC, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg, + dump_qdisc_nlmsg, cookie); +} + +static int __dump_filter_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_filter_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_filter_nlmsg(cookie, t, tb); +} + +static int netlink_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + dump_nlmsg_t dump_filter_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTFILTER, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + .t.tcm_parent = handle, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg, + dump_filter_nlmsg, cookie); +} + +static int __dump_link_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct nlattr *tb[IFLA_MAX + 1], *attr; + struct ifinfomsg *ifi = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); + attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_link_nlmsg(cookie, ifi, tb); +} + +static int netlink_get_link(int sock, unsigned int nl_pid, + dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct ifinfomsg ifm; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nlh.nlmsg_type = RTM_GETLINK, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifm.ifi_family = AF_PACKET, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, + dump_link_nlmsg, cookie); +} + static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) { struct bpf_netdev_t *netinfo = cookie; @@ -168,14 +433,14 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid, tcinfo.array_len = 0; tcinfo.is_qdisc = false; - ret = libbpf_nl_get_class(sock, nl_pid, dev->ifindex, - dump_class_qdisc_nlmsg, &tcinfo); + ret = netlink_get_class(sock, nl_pid, dev->ifindex, + dump_class_qdisc_nlmsg, &tcinfo); if (ret) goto out; tcinfo.is_qdisc = true; - ret = libbpf_nl_get_qdisc(sock, nl_pid, dev->ifindex, - dump_class_qdisc_nlmsg, &tcinfo); + ret = netlink_get_qdisc(sock, nl_pid, dev->ifindex, + dump_class_qdisc_nlmsg, &tcinfo); if (ret) goto out; @@ -183,9 +448,9 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid, filter_info.ifindex = dev->ifindex; for (i = 0; i < tcinfo.used_len; i++) { filter_info.kind = tcinfo.handle_array[i].kind; - ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, - tcinfo.handle_array[i].handle, - dump_filter_nlmsg, &filter_info); + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, + tcinfo.handle_array[i].handle, + dump_filter_nlmsg, &filter_info); if (ret) goto out; } @@ -193,22 +458,22 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid, /* root, ingress and egress handle */ handle = TC_H_ROOT; filter_info.kind = "root"; - ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle, - dump_filter_nlmsg, &filter_info); + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); if (ret) goto out; handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); filter_info.kind = "clsact/ingress"; - ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle, - dump_filter_nlmsg, &filter_info); + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); if (ret) goto out; handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS); filter_info.kind = "clsact/egress"; - ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle, - dump_filter_nlmsg, &filter_info); + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); if (ret) goto out; @@ -386,7 +651,7 @@ static int do_show(int argc, char **argv) struct bpf_attach_info attach_info = {}; int i, sock, ret, filter_idx = -1; struct bpf_netdev_t dev_array; - unsigned int nl_pid; + unsigned int nl_pid = 0; char err_buf[256]; if (argc == 2) { @@ -401,7 +666,7 @@ static int do_show(int argc, char **argv) if (ret) return -1; - sock = libbpf_netlink_open(&nl_pid); + sock = netlink_open(&nl_pid); if (sock < 0) { fprintf(stderr, "failed to open netlink sock\n"); return -1; @@ -416,7 +681,7 @@ static int do_show(int argc, char **argv) jsonw_start_array(json_wtr); NET_START_OBJECT; NET_START_ARRAY("xdp", "%s:\n"); - ret = libbpf_nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array); + ret = netlink_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array); NET_END_ARRAY("\n"); if (!ret) { diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index e3b116325403..df7d8ec76036 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -134,6 +134,8 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) while (true) { ret = read(fd, buf, sizeof(buf)); if (ret < 0) { + if (errno == EAGAIN) + continue; err = -errno; p_err("failed to read PID iterator output: %d", err); goto out; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 158995d853b0..d393eb8263a6 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -428,14 +428,14 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, p_info("no instructions returned"); return -1; } - buf = (unsigned char *)(info->jited_prog_insns); + buf = u64_to_ptr(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); return -1; } - buf = (unsigned char *)info->xlated_prog_insns; + buf = u64_to_ptr(info->xlated_prog_insns); member_len = info->xlated_prog_len; } @@ -444,7 +444,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, return -1; } - func_info = (void *)info->func_info; + func_info = u64_to_ptr(info->func_info); if (info->nr_line_info) { prog_linfo = bpf_prog_linfo__new(info); @@ -462,7 +462,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, n = write(fd, buf, member_len); close(fd); - if (n != member_len) { + if (n != (ssize_t)member_len) { p_err("error writing output file: %s", n < 0 ? strerror(errno) : "short write"); return -1; @@ -492,13 +492,13 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, __u32 i; if (info->nr_jited_ksyms) { kernel_syms_load(&dd); - ksyms = (__u64 *) info->jited_ksyms; + ksyms = u64_to_ptr(info->jited_ksyms); } if (json_output) jsonw_start_array(json_wtr); - lens = (__u32 *) info->jited_func_lens; + lens = u64_to_ptr(info->jited_func_lens); for (i = 0; i < info->nr_jited_func_lens; i++) { if (ksyms) { sym = kernel_syms_search(&dd, ksyms[i]); @@ -559,7 +559,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, } else { kernel_syms_load(&dd); dd.nr_jited_ksyms = info->nr_jited_ksyms; - dd.jited_ksyms = (__u64 *) info->jited_ksyms; + dd.jited_ksyms = u64_to_ptr(info->jited_ksyms); dd.btf = btf; dd.func_info = func_info; dd.finfo_rec_size = info->func_info_rec_size; @@ -1681,7 +1681,7 @@ static char *profile_target_name(int tgt_fd) goto out; } - func_info = (struct bpf_func_info *)(info_linear->info.func_info); + func_info = u64_to_ptr(info_linear->info.func_info); t = btf__type_by_id(btf, func_info[0].type_id); if (!t) { p_err("btf %d doesn't have type %d", diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 4d9ecb975862..dfa540d8a02d 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -199,9 +199,16 @@ static char *get_id(const char *prefix_end) /* * __BTF_ID__func__vfs_truncate__0 * prefix_end = ^ + * pos = ^ */ - char *p, *id = strdup(prefix_end + sizeof("__") - 1); + int len = strlen(prefix_end); + int pos = sizeof("__") - 1; + char *p, *id; + if (pos >= len) + return NULL; + + id = strdup(prefix_end + pos); if (id) { /* * __BTF_ID__func__vfs_truncate__0 @@ -220,6 +227,24 @@ static char *get_id(const char *prefix_end) return id; } +static struct btf_id *add_set(struct object *obj, char *name) +{ + /* + * __BTF_ID__set__name + * name = ^ + * id = ^ + */ + char *id = name + sizeof(BTF_SET "__") - 1; + int len = strlen(name); + + if (id >= name + len) { + pr_err("FAILED to parse set name: %s\n", name); + return NULL; + } + + return btf_id__add(&obj->sets, id, true); +} + static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) { char *id; @@ -233,6 +258,39 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) return btf_id__add(root, id, false); } +/* + * The data of compressed section should be aligned to 4 + * (for 32bit) or 8 (for 64 bit) bytes. The binutils ld + * sets sh_addralign to 1, which makes libelf fail with + * misaligned section error during the update: + * FAILED elf_update(WRITE): invalid section alignment + * + * While waiting for ld fix, we fix the compressed sections + * sh_addralign value manualy. + */ +static int compressed_section_fix(Elf *elf, Elf_Scn *scn, GElf_Shdr *sh) +{ + int expected = gelf_getclass(elf) == ELFCLASS32 ? 4 : 8; + + if (!(sh->sh_flags & SHF_COMPRESSED)) + return 0; + + if (sh->sh_addralign == expected) + return 0; + + pr_debug2(" - fixing wrong alignment sh_addralign %u, expected %u\n", + sh->sh_addralign, expected); + + sh->sh_addralign = expected; + + if (gelf_update_shdr(scn, sh) == 0) { + printf("FAILED cannot update section header: %s\n", + elf_errmsg(-1)); + return -1; + } + return 0; +} + static int elf_collect(struct object *obj) { Elf_Scn *scn = NULL; @@ -309,6 +367,9 @@ static int elf_collect(struct object *obj) obj->efile.idlist_shndx = idx; obj->efile.idlist_addr = sh.sh_addr; } + + if (compressed_section_fix(elf, scn, &sh)) + return -1; } return 0; @@ -376,7 +437,7 @@ static int symbols_collect(struct object *obj) id = add_symbol(&obj->funcs, prefix, sizeof(BTF_FUNC) - 1); /* set */ } else if (!strncmp(prefix, BTF_SET, sizeof(BTF_SET) - 1)) { - id = add_symbol(&obj->sets, prefix, sizeof(BTF_SET) - 1); + id = add_set(obj, prefix); /* * SET objects store list's count, which is encoded * in symbol's size, together with 'cnt' field hence diff --git a/tools/build/Makefile b/tools/build/Makefile index 727050c40f09..722f1700d96a 100644 --- a/tools/build/Makefile +++ b/tools/build/Makefile @@ -38,6 +38,8 @@ clean: $(call QUIET_CLEAN, fixdep) $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)rm -f $(OUTPUT)fixdep + $(call QUIET_CLEAN, feature-detect) + $(Q)$(MAKE) -C feature/ clean >/dev/null $(OUTPUT)fixdep-in.o: FORCE $(Q)$(MAKE) $(build)=fixdep diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index c1daf4d57518..38415d251075 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -46,7 +46,6 @@ FEATURE_TESTS_BASIC := \ libelf-getphdrnum \ libelf-gelf_getnote \ libelf-getshdrstrndx \ - libelf-mmap \ libnuma \ numa_num_possible_cpus \ libperl \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index d220fe952747..b2a2347c67ed 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -25,7 +25,6 @@ FILES= \ test-libelf-getphdrnum.bin \ test-libelf-gelf_getnote.bin \ test-libelf-getshdrstrndx.bin \ - test-libelf-mmap.bin \ test-libdebuginfod.bin \ test-libnuma.bin \ test-numa_num_possible_cpus.bin \ @@ -146,9 +145,6 @@ $(OUTPUT)test-dwarf.bin: $(OUTPUT)test-dwarf_getlocations.bin: $(BUILD) $(DWARFLIBS) -$(OUTPUT)test-libelf-mmap.bin: - $(BUILD) -lelf - $(OUTPUT)test-libelf-getphdrnum.bin: $(BUILD) -lelf diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 5479e543b194..5284e6e9c756 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -30,10 +30,6 @@ # include "test-libelf.c" #undef main -#define main main_test_libelf_mmap -# include "test-libelf-mmap.c" -#undef main - #define main main_test_get_current_dir_name # include "test-get_current_dir_name.c" #undef main diff --git a/tools/build/feature/test-libelf-mmap.c b/tools/build/feature/test-libelf-mmap.c deleted file mode 100644 index 2c3ef81affe2..000000000000 --- a/tools/build/feature/test-libelf-mmap.c +++ /dev/null @@ -1,9 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <libelf.h> - -int main(void) -{ - Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0); - - return (long)elf; -} diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index 4867d549e3c1..210b086188a3 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -3,6 +3,11 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +struct btf_id_set { + u32 cnt; + u32 ids[]; +}; + #ifdef CONFIG_DEBUG_INFO_BTF #include <linux/compiler.h> /* for __PASTE */ @@ -62,7 +67,7 @@ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ "." #scope " " #name "; \n" \ #name ":; \n" \ -".popsection; \n"); \ +".popsection; \n"); #define BTF_ID_LIST(name) \ __BTF_ID_LIST(name, local) \ @@ -88,12 +93,56 @@ asm( \ ".zero 4 \n" \ ".popsection; \n"); +/* + * The BTF_SET_START/END macros pair defines sorted list of + * BTF IDs plus its members count, with following layout: + * + * BTF_SET_START(list) + * BTF_ID(type1, name1) + * BTF_ID(type2, name2) + * BTF_SET_END(list) + * + * __BTF_ID__set__list: + * .zero 4 + * list: + * __BTF_ID__type1__name1__3: + * .zero 4 + * __BTF_ID__type2__name2__4: + * .zero 4 + * + */ +#define __BTF_SET_START(name, scope) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +"." #scope " __BTF_ID__set__" #name "; \n" \ +"__BTF_ID__set__" #name ":; \n" \ +".zero 4 \n" \ +".popsection; \n"); + +#define BTF_SET_START(name) \ +__BTF_ID_LIST(name, local) \ +__BTF_SET_START(name, local) + +#define BTF_SET_START_GLOBAL(name) \ +__BTF_ID_LIST(name, globl) \ +__BTF_SET_START(name, globl) + +#define BTF_SET_END(name) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".size __BTF_ID__set__" #name ", .-" #name " \n" \ +".popsection; \n"); \ +extern struct btf_id_set name; + #else #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED #define BTF_ID_LIST_GLOBAL(name) u32 name[1]; +#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0480f893facd..8dda13880957 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -155,6 +155,7 @@ enum bpf_map_type { BPF_MAP_TYPE_DEVMAP_HASH, BPF_MAP_TYPE_STRUCT_OPS, BPF_MAP_TYPE_RINGBUF, + BPF_MAP_TYPE_INODE_STORAGE, }; /* Note that tracing related programs such as @@ -345,6 +346,14 @@ enum bpf_link_type { /* The verifier internal test flag. Behavior is undefined */ #define BPF_F_TEST_STATE_FREQ (1U << 3) +/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will + * restrict map and helper usage for such programs. Sleepable BPF programs can + * only be attached to hooks where kernel execution context allows sleeping. + * Such programs are allowed to use helpers that may sleep like + * bpf_copy_from_user(). + */ +#define BPF_F_SLEEPABLE (1U << 4) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * @@ -767,7 +776,7 @@ union bpf_attr { * * Also, note that **bpf_trace_printk**\ () is slow, and should * only be used for debugging purposes. For this reason, a notice - * bloc (spanning several lines) is printed to kernel logs and + * block (spanning several lines) is printed to kernel logs and * states that the helper should not be used "for production use" * the first time this helper is used (or more precisely, when * **trace_printk**\ () buffers are allocated). For passing values @@ -1033,14 +1042,14 @@ union bpf_attr { * * int ret; * struct bpf_tunnel_key key = {}; - * + * * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); * if (ret < 0) * return TC_ACT_SHOT; // drop packet - * + * * if (key.remote_ipv4 != 0x0a000001) * return TC_ACT_SHOT; // drop packet - * + * * return TC_ACT_OK; // accept packet * * This interface can also be used with all encapsulation devices @@ -1147,7 +1156,7 @@ union bpf_attr { * Description * Retrieve the realm or the route, that is to say the * **tclassid** field of the destination for the *skb*. The - * indentifier retrieved is a user-provided tag, similar to the + * identifier retrieved is a user-provided tag, similar to the * one used with the net_cls cgroup (see description for * **bpf_get_cgroup_classid**\ () helper), but here this tag is * held by a route (a destination entry), not by a task. @@ -2807,7 +2816,7 @@ union bpf_attr { * * **-ERANGE** if resulting value was out of range. * - * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags) * Description * Get a bpf-local-storage from a *sk*. * @@ -2823,6 +2832,9 @@ union bpf_attr { * "type". The bpf-local-storage "type" (i.e. the *map*) is * searched against all bpf-local-storages residing at *sk*. * + * *sk* is a kernel **struct sock** pointer for LSM program. + * *sk* is a **struct bpf_sock** pointer for other program types. + * * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be * used such that a new bpf-local-storage will be * created if one does not exist. *value* can be used @@ -2835,7 +2847,7 @@ union bpf_attr { * **NULL** if not found or there was an error in adding * a new bpf-local-storage. * - * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * long bpf_sk_storage_delete(struct bpf_map *map, void *sk) * Description * Delete a bpf-local-storage from a *sk*. * Return @@ -3395,6 +3407,175 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * + * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) + * Description + * Load header option. Support reading a particular TCP header + * option for bpf program (BPF_PROG_TYPE_SOCK_OPS). + * + * If *flags* is 0, it will search the option from the + * sock_ops->skb_data. The comment in "struct bpf_sock_ops" + * has details on what skb_data contains under different + * sock_ops->op. + * + * The first byte of the *searchby_res* specifies the + * kind that it wants to search. + * + * If the searching kind is an experimental kind + * (i.e. 253 or 254 according to RFC6994). It also + * needs to specify the "magic" which is either + * 2 bytes or 4 bytes. It then also needs to + * specify the size of the magic by using + * the 2nd byte which is "kind-length" of a TCP + * header option and the "kind-length" also + * includes the first 2 bytes "kind" and "kind-length" + * itself as a normal TCP header option also does. + * + * For example, to search experimental kind 254 with + * 2 byte magic 0xeB9F, the searchby_res should be + * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. + * + * To search for the standard window scale option (3), + * the searchby_res should be [ 3, 0, 0, .... 0 ]. + * Note, kind-length must be 0 for regular option. + * + * Searching for No-Op (0) and End-of-Option-List (1) are + * not supported. + * + * *len* must be at least 2 bytes which is the minimal size + * of a header option. + * + * Supported flags: + * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the + * saved_syn packet or the just-received syn packet. + * + * Return + * >0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. + * + * **-EINVAL** If param is invalid + * + * **-ENOMSG** The option is not found + * + * **-ENOENT** No syn packet available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used + * + * **-ENOSPC** Not enough space. Only *len* number of + * bytes are copied. + * + * **-EFAULT** Cannot parse the header options in the packet + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) + * Description + * Store header option. The data will be copied + * from buffer *from* with length *len* to the TCP header. + * + * The buffer *from* should have the whole option that + * includes the kind, kind-length, and the actual + * option data. The *len* must be at least kind-length + * long. The kind-length does not have to be 4 byte + * aligned. The kernel will take care of the padding + * and setting the 4 bytes aligned value to th->doff. + * + * This helper will check for duplicated option + * by searching the same option in the outgoing skb. + * + * This helper can only be called during + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** If param is invalid + * + * **-ENOSPC** Not enough space in the header. + * Nothing has been written + * + * **-EEXIST** The option has already existed + * + * **-EFAULT** Cannot parse the existing header options + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) + * Description + * Reserve *len* bytes for the bpf header option. The + * space will be used by bpf_store_hdr_opt() later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * If bpf_reserve_hdr_opt() is called multiple times, + * the total number of bytes will be reserved. + * + * This helper can only be called during + * BPF_SOCK_OPS_HDR_OPT_LEN_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** if param is invalid + * + * **-ENOSPC** Not enough space in the header. + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags) + * Description + * Get a bpf_local_storage from an *inode*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *inode* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this + * helper enforces the key must be an inode and the map must also + * be a **BPF_MAP_TYPE_INODE_STORAGE**. + * + * Underneath, the value is stored locally at *inode* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *inode*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * int bpf_inode_storage_delete(struct bpf_map *map, void *inode) + * Description + * Delete a bpf_local_storage from an *inode*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + * + * long bpf_d_path(struct path *path, char *buf, u32 sz) + * Description + * Return full path for given 'struct path' object, which + * needs to be the kernel BTF 'path' object. The path is + * returned in the provided buffer 'buf' of size 'sz' and + * is zero terminated. + * + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr) + * Description + * Read *size* bytes from user space address *user_ptr* and store + * the data in *dst*. This is a wrapper of copy_from_user(). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3539,6 +3720,13 @@ union bpf_attr { FN(skc_to_tcp_request_sock), \ FN(skc_to_udp6_sock), \ FN(get_task_stack), \ + FN(load_hdr_opt), \ + FN(store_hdr_opt), \ + FN(reserve_hdr_opt), \ + FN(inode_storage_get), \ + FN(inode_storage_delete), \ + FN(d_path), \ + FN(copy_from_user), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -3648,9 +3836,13 @@ enum { BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), }; -/* BPF_FUNC_sk_storage_get flags */ +/* BPF_FUNC_<kernel_obj>_storage_get flags */ enum { - BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0), + BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0), + /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility + * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead. + */ + BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE, }; /* BPF_FUNC_read_branch_records flags. */ @@ -4071,6 +4263,15 @@ struct bpf_link_info { __u64 cgroup_id; __u32 attach_type; } cgroup; + struct { + __aligned_u64 target_name; /* in/out: target_name buffer ptr */ + __u32 target_name_len; /* in/out: target_name buffer len */ + union { + struct { + __u32 map_id; + } map; + }; + } iter; struct { __u32 netns_ino; __u32 attach_type; @@ -4158,6 +4359,36 @@ struct bpf_sock_ops { __u64 bytes_received; __u64 bytes_acked; __bpf_md_ptr(struct bpf_sock *, sk); + /* [skb_data, skb_data_end) covers the whole TCP header. + * + * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received + * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the + * header has not been written. + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have + * been written so far. + * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes + * the 3WHS. + * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes + * the 3WHS. + * + * bpf_load_hdr_opt() can also be used to read a particular option. + */ + __bpf_md_ptr(void *, skb_data); + __bpf_md_ptr(void *, skb_data_end); + __u32 skb_len; /* The total length of a packet. + * It includes the header, options, + * and payload. + */ + __u32 skb_tcp_flags; /* tcp_flags of the header. It provides + * an easy way to check for tcp_flags + * without parsing skb_data. + * + * In particular, the skb_tcp_flags + * will still be available in + * BPF_SOCK_OPS_HDR_OPT_LEN even though + * the outgoing header has not + * been written yet. + */ }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -4166,8 +4397,51 @@ enum { BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), + /* Call bpf for all received TCP headers. The bpf prog will be + * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + * + * It could be used at the client/active side (i.e. connect() side) + * when the server told it that the server was in syncookie + * mode and required the active side to resend the bpf-written + * options. The active side can keep writing the bpf-options until + * it received a valid packet from the server side to confirm + * the earlier packet (and options) has been received. The later + * example patch is using it like this at the active side when the + * server is in syncookie mode. + * + * The bpf prog will usually turn this off in the common cases. + */ + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf when kernel has received a header option that + * the kernel cannot handle. The bpf prog will be called under + * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + */ + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + /* Call bpf when the kernel is writing header options for the + * outgoing packet. The bpf prog will first be called + * to reserve space in a skb under + * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then + * the bpf prog will be called to write the header option(s) + * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB + * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option + * related helpers that will be useful to the bpf programs. + * + * The kernel gets its chance to reserve space and write + * options first before the BPF program does. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ - BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF, + BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; /* List of known BPF sock_ops operators. @@ -4223,6 +4497,63 @@ enum { */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. */ + BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. + * It will be called to handle + * the packets received at + * an already established + * connection. + * + * sock_ops->skb_data: + * Referring to the received skb. + * It covers the TCP header only. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option. + */ + BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the + * header option later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Not available because no header has + * been written yet. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the + * outgoing skb. (e.g. SYN, ACK, FIN). + * + * bpf_reserve_hdr_opt() should + * be used to reserve space. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Referring to the outgoing skb. + * It covers the TCP header + * that has already been written + * by the kernel and the + * earlier bpf-progs. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the outgoing + * skb. (e.g. SYN, ACK, FIN). + * + * bpf_store_hdr_opt() should + * be used to write the + * option. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option that + * has already been written + * by the kernel or the + * earlier bpf-progs. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -4250,6 +4581,63 @@ enum { enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ + TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ + TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ + /* Copy the SYN pkt to optval + * + * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the + * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit + * to only getting from the saved_syn. It can either get the + * syn packet from: + * + * 1. the just-received SYN packet (only available when writing the + * SYNACK). It will be useful when it is not necessary to + * save the SYN packet for latter use. It is also the only way + * to get the SYN during syncookie mode because the syn + * packet cannot be saved during syncookie. + * + * OR + * + * 2. the earlier saved syn which was done by + * bpf_setsockopt(TCP_SAVE_SYN). + * + * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the + * SYN packet is obtained. + * + * If the bpf-prog does not need the IP[46] header, the + * bpf-prog can avoid parsing the IP header by using + * TCP_BPF_SYN. Otherwise, the bpf-prog can get both + * IP[46] and TCP header by using TCP_BPF_SYN_IP. + * + * >0: Total number of bytes copied + * -ENOSPC: Not enough space in optval. Only optlen number of + * bytes is copied. + * -ENOENT: The SYN skb is not available now and the earlier SYN pkt + * is not saved by setsockopt(TCP_SAVE_SYN). + */ + TCP_BPF_SYN = 1005, /* Copy the TCP header */ + TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ + TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ +}; + +enum { + BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0), +}; + +/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + */ +enum { + BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the + * total option spaces + * required for an established + * sk in order to calculate the + * MSS. No skb is actually + * sent. + */ + BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode + * when sending a SYN. + */ }; struct bpf_perf_event_value { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 077e7ee69e3d..3e5dcdd48a49 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1196,7 +1196,7 @@ union perf_mem_data_src { #define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ /* 1 free */ -#define PERF_MEM_SNOOPX_SHIFT 37 +#define PERF_MEM_SNOOPX_SHIFT 38 /* locked instruction */ #define PERF_MEM_LOCK_NA 0x01 /* not available */ diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index bf8ed134cb8a..adbe994610f2 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -1,6 +1,9 @@ # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) # Most of this file is copied from tools/lib/traceevent/Makefile +RM ?= rm +srctree = $(abs_srctree) + LIBBPF_VERSION := $(shell \ grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \ sort -rV | head -n1 | cut -d'_' -f2) @@ -56,7 +59,7 @@ ifndef VERBOSE endif FEATURE_USER = .libbpf -FEATURE_TESTS = libelf libelf-mmap zlib bpf reallocarray +FEATURE_TESTS = libelf zlib bpf FEATURE_DISPLAY = libelf zlib bpf INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi @@ -98,16 +101,8 @@ else CFLAGS := -g -Wall endif -ifeq ($(feature-libelf-mmap), 1) - override CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT -endif - -ifeq ($(feature-reallocarray), 0) - override CFLAGS += -DCOMPAT_NEED_REALLOCARRAY -endif - # Append required CFLAGS -override CFLAGS += $(EXTRA_WARNINGS) +override CFLAGS += $(EXTRA_WARNINGS) -Wno-switch-enum override CFLAGS += -Werror -Wall override CFLAGS += -fPIC override CFLAGS += $(INCLUDES) @@ -196,7 +191,7 @@ $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) $(OUTPUT)libbpf.a: $(BPF_IN_STATIC) - $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ + $(QUIET_LINK)$(RM) -f $@; $(AR) rcs $@ $^ $(OUTPUT)libbpf.pc: $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ @@ -269,10 +264,10 @@ install: install_lib install_pkgconfig install_headers ### Cleaning rules config-clean: - $(call QUIET_CLEAN, config) + $(call QUIET_CLEAN, feature-detect) $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null -clean: +clean: config-clean $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ @@ -299,7 +294,7 @@ cscope: cscope -b -q -I $(srctree)/include -f cscope.out tags: - rm -f TAGS tags + $(RM) -f TAGS tags ls *.c *.h | xargs $(TAGS_PROG) -a # Declare the contents of the .PHONY variable as phony. We keep that diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 0750681057c2..82b983ff6569 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -32,9 +32,6 @@ #include "libbpf.h" #include "libbpf_internal.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - /* * When building perf, unistd.h is overridden. __NR_bpf is * required to be defined explicitly. diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index eae5cccff761..bbcefb3ff5a5 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -19,32 +19,52 @@ enum bpf_field_info_kind { BPF_FIELD_RSHIFT_U64 = 5, }; +/* second argument to __builtin_btf_type_id() built-in */ +enum bpf_type_id_kind { + BPF_TYPE_ID_LOCAL = 0, /* BTF type ID in local program */ + BPF_TYPE_ID_TARGET = 1, /* BTF type ID in target kernel */ +}; + +/* second argument to __builtin_preserve_type_info() built-in */ +enum bpf_type_info_kind { + BPF_TYPE_EXISTS = 0, /* type existence in target kernel */ + BPF_TYPE_SIZE = 1, /* type size in target kernel */ +}; + +/* second argument to __builtin_preserve_enum_value() built-in */ +enum bpf_enum_value_kind { + BPF_ENUMVAL_EXISTS = 0, /* enum value existence in kernel */ + BPF_ENUMVAL_VALUE = 1, /* enum value value relocation */ +}; + #define __CORE_RELO(src, field, info) \ __builtin_preserve_field_info((src)->field, BPF_FIELD_##info) #if __BYTE_ORDER == __LITTLE_ENDIAN #define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ - bpf_probe_read((void *)dst, \ - __CORE_RELO(src, fld, BYTE_SIZE), \ - (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) + bpf_probe_read_kernel( \ + (void *)dst, \ + __CORE_RELO(src, fld, BYTE_SIZE), \ + (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) #else /* semantics of LSHIFT_64 assumes loading values into low-ordered bytes, so * for big-endian we need to adjust destination pointer accordingly, based on * field byte size */ #define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ - bpf_probe_read((void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)), \ - __CORE_RELO(src, fld, BYTE_SIZE), \ - (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) + bpf_probe_read_kernel( \ + (void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)), \ + __CORE_RELO(src, fld, BYTE_SIZE), \ + (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) #endif /* * Extract bitfield, identified by s->field, and return its value as u64. * All this is done in relocatable manner, so bitfield changes such as * signedness, bit size, offset changes, this will be handled automatically. - * This version of macro is using bpf_probe_read() to read underlying integer - * storage. Macro functions as an expression and its return type is - * bpf_probe_read()'s return value: 0, on success, <0 on error. + * This version of macro is using bpf_probe_read_kernel() to read underlying + * integer storage. Macro functions as an expression and its return type is + * bpf_probe_read_kernel()'s return value: 0, on success, <0 on error. */ #define BPF_CORE_READ_BITFIELD_PROBED(s, field) ({ \ unsigned long long val = 0; \ @@ -92,15 +112,75 @@ enum bpf_field_info_kind { __builtin_preserve_field_info(field, BPF_FIELD_EXISTS) /* - * Convenience macro to get byte size of a field. Works for integers, + * Convenience macro to get the byte size of a field. Works for integers, * struct/unions, pointers, arrays, and enums. */ #define bpf_core_field_size(field) \ __builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE) /* - * bpf_core_read() abstracts away bpf_probe_read() call and captures offset - * relocation for source address using __builtin_preserve_access_index() + * Convenience macro to get BTF type ID of a specified type, using a local BTF + * information. Return 32-bit unsigned integer with type ID from program's own + * BTF. Always succeeds. + */ +#define bpf_core_type_id_local(type) \ + __builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_LOCAL) + +/* + * Convenience macro to get BTF type ID of a target kernel's type that matches + * specified local type. + * Returns: + * - valid 32-bit unsigned type ID in kernel BTF; + * - 0, if no matching type was found in a target kernel BTF. + */ +#define bpf_core_type_id_kernel(type) \ + __builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_TARGET) + +/* + * Convenience macro to check that provided named type + * (struct/union/enum/typedef) exists in a target kernel. + * Returns: + * 1, if such type is present in target kernel's BTF; + * 0, if no matching type is found. + */ +#define bpf_core_type_exists(type) \ + __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS) + +/* + * Convenience macro to get the byte size of a provided named type + * (struct/union/enum/typedef) in a target kernel. + * Returns: + * >= 0 size (in bytes), if type is present in target kernel's BTF; + * 0, if no matching type is found. + */ +#define bpf_core_type_size(type) \ + __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_SIZE) + +/* + * Convenience macro to check that provided enumerator value is defined in + * a target kernel. + * Returns: + * 1, if specified enum type and its enumerator value are present in target + * kernel's BTF; + * 0, if no matching enum and/or enum value within that enum is found. + */ +#define bpf_core_enum_value_exists(enum_type, enum_value) \ + __builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_EXISTS) + +/* + * Convenience macro to get the integer value of an enumerator value in + * a target kernel. + * Returns: + * 64-bit value, if specified enum type and its enumerator value are + * present in target kernel's BTF; + * 0, if no matching enum and/or enum value within that enum is found. + */ +#define bpf_core_enum_value(enum_type, enum_value) \ + __builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_VALUE) + +/* + * bpf_core_read() abstracts away bpf_probe_read_kernel() call and captures + * offset relocation for source address using __builtin_preserve_access_index() * built-in, provided by Clang. * * __builtin_preserve_access_index() takes as an argument an expression of @@ -115,8 +195,8 @@ enum bpf_field_info_kind { * (local) BTF, used to record relocation. */ #define bpf_core_read(dst, sz, src) \ - bpf_probe_read(dst, sz, \ - (const void *)__builtin_preserve_access_index(src)) + bpf_probe_read_kernel(dst, sz, \ + (const void *)__builtin_preserve_access_index(src)) /* * bpf_core_read_str() is a thin wrapper around bpf_probe_read_str() @@ -124,8 +204,8 @@ enum bpf_field_info_kind { * argument. */ #define bpf_core_read_str(dst, sz, src) \ - bpf_probe_read_str(dst, sz, \ - (const void *)__builtin_preserve_access_index(src)) + bpf_probe_read_kernel_str(dst, sz, \ + (const void *)__builtin_preserve_access_index(src)) #define ___concat(a, b) a ## b #define ___apply(fn, n) ___concat(fn, n) @@ -239,15 +319,17 @@ enum bpf_field_info_kind { * int x = BPF_CORE_READ(s, a.b.c, d.e, f, g); * * BPF_CORE_READ will decompose above statement into 4 bpf_core_read (BPF - * CO-RE relocatable bpf_probe_read() wrapper) calls, logically equivalent to: + * CO-RE relocatable bpf_probe_read_kernel() wrapper) calls, logically + * equivalent to: * 1. const void *__t = s->a.b.c; * 2. __t = __t->d.e; * 3. __t = __t->f; * 4. return __t->g; * * Equivalence is logical, because there is a heavy type casting/preservation - * involved, as well as all the reads are happening through bpf_probe_read() - * calls using __builtin_preserve_access_index() to emit CO-RE relocations. + * involved, as well as all the reads are happening through + * bpf_probe_read_kernel() calls using __builtin_preserve_access_index() to + * emit CO-RE relocations. * * N.B. Only up to 9 "field accessors" are supported, which should be more * than enough for any practical purpose. diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index bc14db706b88..1106777df00b 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -32,6 +32,9 @@ #ifndef __always_inline #define __always_inline __attribute__((always_inline)) #endif +#ifndef __noinline +#define __noinline __attribute__((noinline)) +#endif #ifndef __weak #define __weak __attribute__((weak)) #endif @@ -40,7 +43,7 @@ * Helper macro to manipulate data structures */ #ifndef offsetof -#define offsetof(TYPE, MEMBER) __builtin_offsetof(TYPE, MEMBER) +#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) #endif #ifndef container_of #define container_of(ptr, type, member) \ diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c index bafca49cb1e6..3ed1a27b5f7c 100644 --- a/tools/lib/bpf/bpf_prog_linfo.c +++ b/tools/lib/bpf/bpf_prog_linfo.c @@ -8,9 +8,6 @@ #include "libbpf.h" #include "libbpf_internal.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - struct bpf_prog_linfo { void *raw_linfo; void *raw_jited_linfo; diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index eebf020cbe3e..f9ef37707888 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -289,9 +289,9 @@ struct pt_regs; #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP #else #define BPF_KPROBE_READ_RET_IP(ip, ctx) \ - ({ bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) + ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \ - ({ bpf_probe_read(&(ip), sizeof(ip), \ + ({ bpf_probe_read_kernel(&(ip), sizeof(ip), \ (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 4843e44916f7..a3d259e614b0 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -21,9 +21,6 @@ #include "libbpf_internal.h" #include "hashmap.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - #define BTF_MAX_NR_TYPES 0x7fffffffU #define BTF_MAX_STR_OFFSET 0x7fffffffU @@ -41,6 +38,7 @@ struct btf { __u32 types_size; __u32 data_size; int fd; + int ptr_sz; }; static inline __u64 ptr_to_u64(const void *ptr) @@ -60,7 +58,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) expand_by = max(btf->types_size >> 2, 16U); new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); - new_types = realloc(btf->types, sizeof(*new_types) * new_size); + new_types = libbpf_reallocarray(btf->types, new_size, sizeof(*new_types)); if (!new_types) return -ENOMEM; @@ -221,6 +219,70 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) return btf->types[type_id]; } +static int determine_ptr_size(const struct btf *btf) +{ + const struct btf_type *t; + const char *name; + int i; + + for (i = 1; i <= btf->nr_types; i++) { + t = btf__type_by_id(btf, i); + if (!btf_is_int(t)) + continue; + + name = btf__name_by_offset(btf, t->name_off); + if (!name) + continue; + + if (strcmp(name, "long int") == 0 || + strcmp(name, "long unsigned int") == 0) { + if (t->size != 4 && t->size != 8) + continue; + return t->size; + } + } + + return -1; +} + +static size_t btf_ptr_sz(const struct btf *btf) +{ + if (!btf->ptr_sz) + ((struct btf *)btf)->ptr_sz = determine_ptr_size(btf); + return btf->ptr_sz < 0 ? sizeof(void *) : btf->ptr_sz; +} + +/* Return pointer size this BTF instance assumes. The size is heuristically + * determined by looking for 'long' or 'unsigned long' integer type and + * recording its size in bytes. If BTF type information doesn't have any such + * type, this function returns 0. In the latter case, native architecture's + * pointer size is assumed, so will be either 4 or 8, depending on + * architecture that libbpf was compiled for. It's possible to override + * guessed value by using btf__set_pointer_size() API. + */ +size_t btf__pointer_size(const struct btf *btf) +{ + if (!btf->ptr_sz) + ((struct btf *)btf)->ptr_sz = determine_ptr_size(btf); + + if (btf->ptr_sz < 0) + /* not enough BTF type info to guess */ + return 0; + + return btf->ptr_sz; +} + +/* Override or set pointer size in bytes. Only values of 4 and 8 are + * supported. + */ +int btf__set_pointer_size(struct btf *btf, size_t ptr_sz) +{ + if (ptr_sz != 4 && ptr_sz != 8) + return -EINVAL; + btf->ptr_sz = ptr_sz; + return 0; +} + static bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void || btf_is_fwd(t); @@ -253,7 +315,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) size = t->size; goto done; case BTF_KIND_PTR: - size = sizeof(void *); + size = btf_ptr_sz(btf); goto done; case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: @@ -293,9 +355,9 @@ int btf__align_of(const struct btf *btf, __u32 id) switch (kind) { case BTF_KIND_INT: case BTF_KIND_ENUM: - return min(sizeof(void *), (size_t)t->size); + return min(btf_ptr_sz(btf), (size_t)t->size); case BTF_KIND_PTR: - return sizeof(void *); + return btf_ptr_sz(btf); case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: @@ -533,6 +595,18 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) if (IS_ERR(btf)) goto done; + switch (gelf_getclass(elf)) { + case ELFCLASS32: + btf__set_pointer_size(btf, 4); + break; + case ELFCLASS64: + btf__set_pointer_size(btf, 8); + break; + default: + pr_warn("failed to get ELF class (bitness) for %s\n", path); + break; + } + if (btf_ext && btf_ext_data) { *btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); @@ -1054,14 +1128,14 @@ static int btf_ext_setup_line_info(struct btf_ext *btf_ext) return btf_ext_setup_info(btf_ext, ¶m); } -static int btf_ext_setup_field_reloc(struct btf_ext *btf_ext) +static int btf_ext_setup_core_relos(struct btf_ext *btf_ext) { struct btf_ext_sec_setup_param param = { - .off = btf_ext->hdr->field_reloc_off, - .len = btf_ext->hdr->field_reloc_len, - .min_rec_size = sizeof(struct bpf_field_reloc), - .ext_info = &btf_ext->field_reloc_info, - .desc = "field_reloc", + .off = btf_ext->hdr->core_relo_off, + .len = btf_ext->hdr->core_relo_len, + .min_rec_size = sizeof(struct bpf_core_relo), + .ext_info = &btf_ext->core_relo_info, + .desc = "core_relo", }; return btf_ext_setup_info(btf_ext, ¶m); @@ -1140,10 +1214,9 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) if (err) goto done; - if (btf_ext->hdr->hdr_len < - offsetofend(struct btf_ext_header, field_reloc_len)) + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) goto done; - err = btf_ext_setup_field_reloc(btf_ext); + err = btf_ext_setup_core_relos(btf_ext); if (err) goto done; @@ -1498,7 +1571,7 @@ static int btf_dedup_hypot_map_add(struct btf_dedup *d, __u32 *new_list; d->hypot_cap += max((size_t)16, d->hypot_cap / 2); - new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap); + new_list = libbpf_reallocarray(d->hypot_list, d->hypot_cap, sizeof(__u32)); if (!new_list) return -ENOMEM; d->hypot_list = new_list; @@ -1794,8 +1867,7 @@ static int btf_dedup_strings(struct btf_dedup *d) struct btf_str_ptr *new_ptrs; strs.cap += max(strs.cnt / 2, 16U); - new_ptrs = realloc(strs.ptrs, - sizeof(strs.ptrs[0]) * strs.cap); + new_ptrs = libbpf_reallocarray(strs.ptrs, strs.cap, sizeof(strs.ptrs[0])); if (!new_ptrs) { err = -ENOMEM; goto done; @@ -2880,8 +2952,8 @@ static int btf_dedup_compact_types(struct btf_dedup *d) d->btf->nr_types = next_type_id - 1; d->btf->types_size = d->btf->nr_types; d->btf->hdr->type_len = p - types_start; - new_types = realloc(d->btf->types, - (1 + d->btf->nr_types) * sizeof(struct btf_type *)); + new_types = libbpf_reallocarray(d->btf->types, (1 + d->btf->nr_types), + sizeof(struct btf_type *)); if (!new_types) return -ENOMEM; d->btf->types = new_types; diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index f4a1a1d2b9a3..91f0ad0e0325 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -24,44 +24,6 @@ struct btf_type; struct bpf_object; -/* - * The .BTF.ext ELF section layout defined as - * struct btf_ext_header - * func_info subsection - * - * The func_info subsection layout: - * record size for struct bpf_func_info in the func_info subsection - * struct btf_sec_func_info for section #1 - * a list of bpf_func_info records for section #1 - * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h - * but may not be identical - * struct btf_sec_func_info for section #2 - * a list of bpf_func_info records for section #2 - * ...... - * - * Note that the bpf_func_info record size in .BTF.ext may not - * be the same as the one defined in include/uapi/linux/bpf.h. - * The loader should ensure that record_size meets minimum - * requirement and pass the record as is to the kernel. The - * kernel will handle the func_info properly based on its contents. - */ -struct btf_ext_header { - __u16 magic; - __u8 version; - __u8 flags; - __u32 hdr_len; - - /* All offsets are in bytes relative to the end of this header */ - __u32 func_info_off; - __u32 func_info_len; - __u32 line_info_off; - __u32 line_info_len; - - /* optional part of .BTF.ext header */ - __u32 field_reloc_off; - __u32 field_reloc_len; -}; - LIBBPF_API void btf__free(struct btf *btf); LIBBPF_API struct btf *btf__new(const void *data, __u32 size); LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext); @@ -76,6 +38,8 @@ LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); +LIBBPF_API size_t btf__pointer_size(const struct btf *btf); +LIBBPF_API int btf__set_pointer_size(struct btf *btf, size_t ptr_sz); LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index cf711168d34a..6c079b3c8679 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -13,14 +13,12 @@ #include <errno.h> #include <linux/err.h> #include <linux/btf.h> +#include <linux/kernel.h> #include "btf.h" #include "hashmap.h" #include "libbpf.h" #include "libbpf_internal.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t"; static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1; @@ -60,6 +58,7 @@ struct btf_dump { const struct btf_ext *btf_ext; btf_dump_printf_fn_t printf_fn; struct btf_dump_opts opts; + int ptr_sz; bool strip_mods; /* per-type auxiliary state */ @@ -138,6 +137,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf, d->btf_ext = btf_ext; d->printf_fn = printf_fn; d->opts.ctx = opts ? opts->ctx : NULL; + d->ptr_sz = btf__pointer_size(btf) ? : sizeof(void *); d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); if (IS_ERR(d->type_names)) { @@ -320,8 +320,7 @@ static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id) if (d->emit_queue_cnt >= d->emit_queue_cap) { new_cap = max(16, d->emit_queue_cap * 3 / 2); - new_queue = realloc(d->emit_queue, - new_cap * sizeof(new_queue[0])); + new_queue = libbpf_reallocarray(d->emit_queue, new_cap, sizeof(new_queue[0])); if (!new_queue) return -ENOMEM; d->emit_queue = new_queue; @@ -549,6 +548,9 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) } } +static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id, + const struct btf_type *t); + static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, const struct btf_type *t); static void btf_dump_emit_struct_def(struct btf_dump *d, __u32 id, @@ -671,6 +673,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) switch (kind) { case BTF_KIND_INT: + /* Emit type alias definitions if necessary */ + btf_dump_emit_missing_aliases(d, id, t); + tstate->emit_state = EMITTED; break; case BTF_KIND_ENUM: @@ -797,7 +802,7 @@ static void btf_dump_emit_bit_padding(const struct btf_dump *d, int align, int lvl) { int off_diff = m_off - cur_off; - int ptr_bits = sizeof(void *) * 8; + int ptr_bits = d->ptr_sz * 8; if (off_diff <= 0) /* no gap */ @@ -870,7 +875,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, btf_dump_printf(d, ": %d", m_sz); off = m_off + m_sz; } else { - m_sz = max(0, btf__resolve_size(d->btf, m->type)); + m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type)); off = m_off + m_sz * 8; } btf_dump_printf(d, ";"); @@ -890,6 +895,32 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, btf_dump_printf(d, " __attribute__((packed))"); } +static const char *missing_base_types[][2] = { + /* + * GCC emits typedefs to its internal __PolyX_t types when compiling Arm + * SIMD intrinsics. Alias them to standard base types. + */ + { "__Poly8_t", "unsigned char" }, + { "__Poly16_t", "unsigned short" }, + { "__Poly64_t", "unsigned long long" }, + { "__Poly128_t", "unsigned __int128" }, +}; + +static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + const char *name = btf_dump_type_name(d, id); + int i; + + for (i = 0; i < ARRAY_SIZE(missing_base_types); i++) { + if (strcmp(name, missing_base_types[i][0]) == 0) { + btf_dump_printf(d, "typedef %s %s;\n\n", + missing_base_types[i][1], name); + break; + } + } +} + static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, const struct btf_type *t) { @@ -968,8 +999,7 @@ static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id) if (d->decl_stack_cnt >= d->decl_stack_cap) { new_cap = max(16, d->decl_stack_cap * 3 / 2); - new_stack = realloc(d->decl_stack, - new_cap * sizeof(new_stack[0])); + new_stack = libbpf_reallocarray(d->decl_stack, new_cap, sizeof(new_stack[0])); if (!new_stack) return -ENOMEM; d->decl_stack = new_stack; diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index a405dad068f5..3c20b126d60d 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -15,6 +15,9 @@ /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 +/* prevent accidental re-addition of reallocarray() */ +#pragma GCC poison reallocarray + /* start with 4 buckets */ #define HASHMAP_MIN_CAP_BITS 2 diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 0a06124f7999..b688aadf09c5 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -44,7 +44,6 @@ #include <sys/vfs.h> #include <sys/utsname.h> #include <sys/resource.h> -#include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> #include <zlib.h> @@ -56,9 +55,6 @@ #include "libbpf_internal.h" #include "hashmap.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - #ifndef EM_BPF #define EM_BPF 247 #endif @@ -67,6 +63,8 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif +#define BPF_INSN_SZ (sizeof(struct bpf_insn)) + /* vsprintf() in __base_pr() uses nonliteral format string. It may break * compilation if user enables corresponding warning. Disable it explicitly. */ @@ -154,34 +152,35 @@ static void pr_perm_msg(int err) ___err; }) #endif -#ifdef HAVE_LIBELF_MMAP_SUPPORT -# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP -#else -# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ -#endif - static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; } -struct bpf_capabilities { +enum kern_feature_id { /* v4.14: kernel support for program & map names. */ - __u32 name:1; + FEAT_PROG_NAME, /* v5.2: kernel support for global data sections. */ - __u32 global_data:1; + FEAT_GLOBAL_DATA, + /* BTF support */ + FEAT_BTF, /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ - __u32 btf_func:1; + FEAT_BTF_FUNC, /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ - __u32 btf_datasec:1; - /* BPF_F_MMAPABLE is supported for arrays */ - __u32 array_mmap:1; + FEAT_BTF_DATASEC, /* BTF_FUNC_GLOBAL is supported */ - __u32 btf_func_global:1; + FEAT_BTF_GLOBAL_FUNC, + /* BPF_F_MMAPABLE is supported for arrays */ + FEAT_ARRAY_MMAP, /* kernel support for expected_attach_type in BPF_PROG_LOAD */ - __u32 exp_attach_type:1; + FEAT_EXP_ATTACH_TYPE, + /* bpf_probe_read_{kernel,user}[_str] helpers */ + FEAT_PROBE_READ_KERN, + __FEAT_CNT, }; +static bool kernel_supports(enum kern_feature_id feat_id); + enum reloc_type { RELO_LD64, RELO_CALL, @@ -209,6 +208,7 @@ struct bpf_sec_def { bool is_exp_attach_type_optional; bool is_attachable; bool is_attach_btf; + bool is_sleepable; attach_fn_t attach_fn; }; @@ -253,8 +253,6 @@ struct bpf_program { __u32 func_info_rec_size; __u32 func_info_cnt; - struct bpf_capabilities *caps; - void *line_info; __u32 line_info_rec_size; __u32 line_info_cnt; @@ -403,6 +401,7 @@ struct bpf_object { Elf_Data *rodata; Elf_Data *bss; Elf_Data *st_ops_data; + size_t shstrndx; /* section index for section name strings */ size_t strtabidx; struct { GElf_Shdr shdr; @@ -436,12 +435,18 @@ struct bpf_object { void *priv; bpf_object_clear_priv_t clear_priv; - struct bpf_capabilities caps; - char path[]; }; #define obj_elf_valid(o) ((o)->efile.elf) +static const char *elf_sym_str(const struct bpf_object *obj, size_t off); +static const char *elf_sec_str(const struct bpf_object *obj, size_t off); +static Elf_Scn *elf_sec_by_idx(const struct bpf_object *obj, size_t idx); +static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name); +static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr); +static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn); +static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn); + void bpf_program__unload(struct bpf_program *prog) { int i; @@ -503,7 +508,7 @@ static char *__bpf_program__pin_name(struct bpf_program *prog) } static int -bpf_program__init(void *data, size_t size, char *section_name, int idx, +bpf_program__init(void *data, size_t size, const char *section_name, int idx, struct bpf_program *prog) { const size_t bpf_insn_sz = sizeof(struct bpf_insn); @@ -552,7 +557,7 @@ errout: static int bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, - char *section_name, int idx) + const char *section_name, int idx) { struct bpf_program prog, *progs; int nr_progs, err; @@ -561,11 +566,10 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, if (err) return err; - prog.caps = &obj->caps; progs = obj->programs; nr_progs = obj->nr_programs; - progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0])); + progs = libbpf_reallocarray(progs, nr_progs + 1, sizeof(progs[0])); if (!progs) { /* * In this case the original obj->programs @@ -578,7 +582,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, return -ENOMEM; } - pr_debug("found program %s\n", prog.section_name); + pr_debug("elf: found program '%s'\n", prog.section_name); obj->programs = progs; obj->nr_programs = nr_progs + 1; prog.obj = obj; @@ -598,8 +602,7 @@ bpf_object__init_prog_names(struct bpf_object *obj) prog = &obj->programs[pi]; - for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; - si++) { + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; si++) { GElf_Sym sym; if (!gelf_getsym(symbols, si, &sym)) @@ -609,11 +612,9 @@ bpf_object__init_prog_names(struct bpf_object *obj) if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL) continue; - name = elf_strptr(obj->efile.elf, - obj->efile.strtabidx, - sym.st_name); + name = elf_sym_str(obj, sym.st_name); if (!name) { - pr_warn("failed to get sym name string for prog %s\n", + pr_warn("prog '%s': failed to get symbol name\n", prog->section_name); return -LIBBPF_ERRNO__LIBELF; } @@ -623,17 +624,14 @@ bpf_object__init_prog_names(struct bpf_object *obj) name = ".text"; if (!name) { - pr_warn("failed to find sym for prog %s\n", + pr_warn("prog '%s': failed to find program symbol\n", prog->section_name); return -EINVAL; } prog->name = strdup(name); - if (!prog->name) { - pr_warn("failed to allocate memory for prog sym %s\n", - name); + if (!prog->name) return -ENOMEM; - } } return 0; @@ -1066,13 +1064,18 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.obj_buf_sz = 0; } +/* if libelf is old and doesn't support mmap(), fall back to read() */ +#ifndef ELF_C_READ_MMAP +#define ELF_C_READ_MMAP ELF_C_READ +#endif + static int bpf_object__elf_init(struct bpf_object *obj) { int err = 0; GElf_Ehdr *ep; if (obj_elf_valid(obj)) { - pr_warn("elf init: internal error\n"); + pr_warn("elf: init internal error\n"); return -LIBBPF_ERRNO__LIBELF; } @@ -1090,31 +1093,44 @@ static int bpf_object__elf_init(struct bpf_object *obj) err = -errno; cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("failed to open %s: %s\n", obj->path, cp); + pr_warn("elf: failed to open %s: %s\n", obj->path, cp); return err; } - obj->efile.elf = elf_begin(obj->efile.fd, - LIBBPF_ELF_C_READ_MMAP, NULL); + obj->efile.elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL); } if (!obj->efile.elf) { - pr_warn("failed to open %s as ELF file\n", obj->path); + pr_warn("elf: failed to open %s as ELF file: %s\n", obj->path, elf_errmsg(-1)); err = -LIBBPF_ERRNO__LIBELF; goto errout; } if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) { - pr_warn("failed to get EHDR from %s\n", obj->path); + pr_warn("elf: failed to get ELF header from %s: %s\n", obj->path, elf_errmsg(-1)); err = -LIBBPF_ERRNO__FORMAT; goto errout; } ep = &obj->efile.ehdr; + if (elf_getshdrstrndx(obj->efile.elf, &obj->efile.shstrndx)) { + pr_warn("elf: failed to get section names section index for %s: %s\n", + obj->path, elf_errmsg(-1)); + err = -LIBBPF_ERRNO__FORMAT; + goto errout; + } + + /* Elf is corrupted/truncated, avoid calling elf_strptr. */ + if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) { + pr_warn("elf: failed to get section names strings from %s: %s\n", + obj->path, elf_errmsg(-1)); + return -LIBBPF_ERRNO__FORMAT; + } + /* Old LLVM set e_machine to EM_NONE */ if (ep->e_type != ET_REL || (ep->e_machine && ep->e_machine != EM_BPF)) { - pr_warn("%s is not an eBPF object file\n", obj->path); + pr_warn("elf: %s is not a valid eBPF object file\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; goto errout; } @@ -1136,7 +1152,7 @@ static int bpf_object__check_endianness(struct bpf_object *obj) #else # error "Unrecognized __BYTE_ORDER__" #endif - pr_warn("endianness mismatch.\n"); + pr_warn("elf: endianness mismatch in %s.\n", obj->path); return -LIBBPF_ERRNO__ENDIAN; } @@ -1171,55 +1187,10 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) return false; } -static int bpf_object_search_section_size(const struct bpf_object *obj, - const char *name, size_t *d_size) -{ - const GElf_Ehdr *ep = &obj->efile.ehdr; - Elf *elf = obj->efile.elf; - Elf_Scn *scn = NULL; - int idx = 0; - - while ((scn = elf_nextscn(elf, scn)) != NULL) { - const char *sec_name; - Elf_Data *data; - GElf_Shdr sh; - - idx++; - if (gelf_getshdr(scn, &sh) != &sh) { - pr_warn("failed to get section(%d) header from %s\n", - idx, obj->path); - return -EIO; - } - - sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); - if (!sec_name) { - pr_warn("failed to get section(%d) name from %s\n", - idx, obj->path); - return -EIO; - } - - if (strcmp(name, sec_name)) - continue; - - data = elf_getdata(scn, 0); - if (!data) { - pr_warn("failed to get section(%d) data from %s(%s)\n", - idx, name, obj->path); - return -EIO; - } - - *d_size = data->d_size; - return 0; - } - - return -ENOENT; -} - int bpf_object__section_size(const struct bpf_object *obj, const char *name, __u32 *size) { int ret = -ENOENT; - size_t d_size; *size = 0; if (!name) { @@ -1237,9 +1208,13 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name, if (obj->efile.st_ops_data) *size = obj->efile.st_ops_data->d_size; } else { - ret = bpf_object_search_section_size(obj, name, &d_size); - if (!ret) - *size = d_size; + Elf_Scn *scn = elf_sec_by_name(obj, name); + Elf_Data *data = elf_sec_data(obj, scn); + + if (data) { + ret = 0; /* found it */ + *size = data->d_size; + } } return *size ? 0 : ret; @@ -1264,8 +1239,7 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, GELF_ST_TYPE(sym.st_info) != STT_OBJECT) continue; - sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx, - sym.st_name); + sname = elf_sym_str(obj, sym.st_name); if (!sname) { pr_warn("failed to get sym name string for var %s\n", name); @@ -1290,7 +1264,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) return &obj->maps[obj->nr_maps++]; new_cap = max((size_t)4, obj->maps_cap * 3 / 2); - new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps)); + new_maps = libbpf_reallocarray(obj->maps, new_cap, sizeof(*obj->maps)); if (!new_maps) { pr_warn("alloc maps for object failed\n"); return ERR_PTR(-ENOMEM); @@ -1742,12 +1716,12 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) if (!symbols) return -EINVAL; - scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx); - if (scn) - data = elf_getdata(scn, NULL); + + scn = elf_sec_by_idx(obj, obj->efile.maps_shndx); + data = elf_sec_data(obj, scn); if (!scn || !data) { - pr_warn("failed to get Elf_Data from map section %d\n", - obj->efile.maps_shndx); + pr_warn("elf: failed to get legacy map definitions for %s\n", + obj->path); return -EINVAL; } @@ -1769,12 +1743,12 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) nr_maps++; } /* Assume equally sized map definitions */ - pr_debug("maps in %s: %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); + pr_debug("elf: found %d legacy map definitions (%zd bytes) in %s\n", + nr_maps, data->d_size, obj->path); if (!data->d_size || nr_maps == 0 || (data->d_size % nr_maps) != 0) { - pr_warn("unable to determine map definition size section %s, %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); + pr_warn("elf: unable to determine legacy map definition size in %s\n", + obj->path); return -EINVAL; } map_def_sz = data->d_size / nr_maps; @@ -1795,8 +1769,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) if (IS_ERR(map)) return PTR_ERR(map); - map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, - sym.st_name); + map_name = elf_sym_str(obj, sym.st_name); if (!map_name) { pr_warn("failed to get map #%d name sym string for obj %s\n", i, obj->path); @@ -1884,6 +1857,29 @@ resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id) return btf_is_func_proto(t) ? t : NULL; } +static const char *btf_kind_str(const struct btf_type *t) +{ + switch (btf_kind(t)) { + case BTF_KIND_UNKN: return "void"; + case BTF_KIND_INT: return "int"; + case BTF_KIND_PTR: return "ptr"; + case BTF_KIND_ARRAY: return "array"; + case BTF_KIND_STRUCT: return "struct"; + case BTF_KIND_UNION: return "union"; + case BTF_KIND_ENUM: return "enum"; + case BTF_KIND_FWD: return "fwd"; + case BTF_KIND_TYPEDEF: return "typedef"; + case BTF_KIND_VOLATILE: return "volatile"; + case BTF_KIND_CONST: return "const"; + case BTF_KIND_RESTRICT: return "restrict"; + case BTF_KIND_FUNC: return "func"; + case BTF_KIND_FUNC_PROTO: return "func_proto"; + case BTF_KIND_VAR: return "var"; + case BTF_KIND_DATASEC: return "datasec"; + default: return "unknown"; + } +} + /* * Fetch integer attribute of BTF map definition. Such attributes are * represented using a pointer to an array, in which dimensionality of array @@ -1900,8 +1896,8 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf, const struct btf_type *arr_t; if (!btf_is_ptr(t)) { - pr_warn("map '%s': attr '%s': expected PTR, got %u.\n", - map_name, name, btf_kind(t)); + pr_warn("map '%s': attr '%s': expected PTR, got %s.\n", + map_name, name, btf_kind_str(t)); return false; } @@ -1912,8 +1908,8 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf, return false; } if (!btf_is_array(arr_t)) { - pr_warn("map '%s': attr '%s': expected ARRAY, got %u.\n", - map_name, name, btf_kind(arr_t)); + pr_warn("map '%s': attr '%s': expected ARRAY, got %s.\n", + map_name, name, btf_kind_str(arr_t)); return false; } arr_info = btf_array(arr_t); @@ -1924,7 +1920,7 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf, static int build_map_pin_path(struct bpf_map *map, const char *path) { char buf[PATH_MAX]; - int err, len; + int len; if (!path) path = "/sys/fs/bpf"; @@ -1935,11 +1931,7 @@ static int build_map_pin_path(struct bpf_map *map, const char *path) else if (len >= PATH_MAX) return -ENAMETOOLONG; - err = bpf_map__set_pin_path(map, buf); - if (err) - return err; - - return 0; + return bpf_map__set_pin_path(map, buf); } @@ -2007,8 +1999,8 @@ static int parse_btf_map_def(struct bpf_object *obj, return -EINVAL; } if (!btf_is_ptr(t)) { - pr_warn("map '%s': key spec is not PTR: %u.\n", - map->name, btf_kind(t)); + pr_warn("map '%s': key spec is not PTR: %s.\n", + map->name, btf_kind_str(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); @@ -2049,8 +2041,8 @@ static int parse_btf_map_def(struct bpf_object *obj, return -EINVAL; } if (!btf_is_ptr(t)) { - pr_warn("map '%s': value spec is not PTR: %u.\n", - map->name, btf_kind(t)); + pr_warn("map '%s': value spec is not PTR: %s.\n", + map->name, btf_kind_str(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); @@ -2107,14 +2099,14 @@ static int parse_btf_map_def(struct bpf_object *obj, t = skip_mods_and_typedefs(obj->btf, btf_array(t)->type, NULL); if (!btf_is_ptr(t)) { - pr_warn("map '%s': map-in-map inner def is of unexpected kind %u.\n", - map->name, btf_kind(t)); + pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", + map->name, btf_kind_str(t)); return -EINVAL; } t = skip_mods_and_typedefs(obj->btf, t->type, NULL); if (!btf_is_struct(t)) { - pr_warn("map '%s': map-in-map inner def is of unexpected kind %u.\n", - map->name, btf_kind(t)); + pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", + map->name, btf_kind_str(t)); return -EINVAL; } @@ -2205,8 +2197,8 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, return -EINVAL; } if (!btf_is_var(var)) { - pr_warn("map '%s': unexpected var kind %u.\n", - map_name, btf_kind(var)); + pr_warn("map '%s': unexpected var kind %s.\n", + map_name, btf_kind_str(var)); return -EINVAL; } if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && @@ -2218,8 +2210,8 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, def = skip_mods_and_typedefs(obj->btf, var->type, NULL); if (!btf_is_struct(def)) { - pr_warn("map '%s': unexpected def kind %u.\n", - map_name, btf_kind(var)); + pr_warn("map '%s': unexpected def kind %s.\n", + map_name, btf_kind_str(var)); return -EINVAL; } if (def->size > vi->size) { @@ -2259,12 +2251,11 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, if (obj->efile.btf_maps_shndx < 0) return 0; - scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx); - if (scn) - data = elf_getdata(scn, NULL); + scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx); + data = elf_sec_data(obj, scn); if (!scn || !data) { - pr_warn("failed to get Elf_Data from map section %d (%s)\n", - obj->efile.maps_shndx, MAPS_ELF_SEC); + pr_warn("elf: failed to get %s map definitions for %s\n", + MAPS_ELF_SEC, obj->path); return -EINVAL; } @@ -2322,36 +2313,28 @@ static int bpf_object__init_maps(struct bpf_object *obj, static bool section_have_execinstr(struct bpf_object *obj, int idx) { - Elf_Scn *scn; GElf_Shdr sh; - scn = elf_getscn(obj->efile.elf, idx); - if (!scn) - return false; - - if (gelf_getshdr(scn, &sh) != &sh) + if (elf_sec_hdr(obj, elf_sec_by_idx(obj, idx), &sh)) return false; - if (sh.sh_flags & SHF_EXECINSTR) - return true; - - return false; + return sh.sh_flags & SHF_EXECINSTR; } static bool btf_needs_sanitization(struct bpf_object *obj) { - bool has_func_global = obj->caps.btf_func_global; - bool has_datasec = obj->caps.btf_datasec; - bool has_func = obj->caps.btf_func; + bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC); + bool has_datasec = kernel_supports(FEAT_BTF_DATASEC); + bool has_func = kernel_supports(FEAT_BTF_FUNC); return !has_func || !has_datasec || !has_func_global; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) { - bool has_func_global = obj->caps.btf_func_global; - bool has_datasec = obj->caps.btf_datasec; - bool has_func = obj->caps.btf_func; + bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC); + bool has_datasec = kernel_supports(FEAT_BTF_DATASEC); + bool has_func = kernel_supports(FEAT_BTF_FUNC); struct btf_type *t; int i, j, vlen; @@ -2434,6 +2417,8 @@ static int bpf_object__init_btf(struct bpf_object *obj, BTF_ELF_SEC, err); goto out; } + /* enforce 8-byte pointers for BPF-targeted BTFs */ + btf__set_pointer_size(obj->btf, 8); err = 0; } if (btf_ext_data) { @@ -2497,7 +2482,7 @@ static int bpf_object__load_vmlinux_btf(struct bpf_object *obj) int err; /* CO-RE relocations need kernel BTF */ - if (obj->btf_ext && obj->btf_ext->field_reloc_info.len) + if (obj->btf_ext && obj->btf_ext->core_relo_info.len) need_vmlinux_btf = true; bpf_object__for_each_program(prog, obj) { @@ -2531,6 +2516,15 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) if (!obj->btf) return 0; + if (!kernel_supports(FEAT_BTF)) { + if (kernel_needs_btf(obj)) { + err = -EOPNOTSUPP; + goto report; + } + pr_debug("Kernel doesn't support BTF, skipping uploading it.\n"); + return 0; + } + sanitize = btf_needs_sanitization(obj); if (sanitize) { const void *raw_data; @@ -2542,6 +2536,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) if (IS_ERR(kern_btf)) return PTR_ERR(kern_btf); + /* enforce 8-byte pointers for BPF-targeted BTFs */ + btf__set_pointer_size(obj->btf, 8); bpf_object__sanitize_btf(obj, kern_btf); } @@ -2554,6 +2550,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) } btf__free(kern_btf); } +report: if (err) { btf_mandatory = kernel_needs_btf(obj); pr_warn("Error loading .BTF into kernel: %d. %s\n", err, @@ -2565,61 +2562,199 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) return err; } +static const char *elf_sym_str(const struct bpf_object *obj, size_t off) +{ + const char *name; + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, off); + if (!name) { + pr_warn("elf: failed to get section name string at offset %zu from %s: %s\n", + off, obj->path, elf_errmsg(-1)); + return NULL; + } + + return name; +} + +static const char *elf_sec_str(const struct bpf_object *obj, size_t off) +{ + const char *name; + + name = elf_strptr(obj->efile.elf, obj->efile.shstrndx, off); + if (!name) { + pr_warn("elf: failed to get section name string at offset %zu from %s: %s\n", + off, obj->path, elf_errmsg(-1)); + return NULL; + } + + return name; +} + +static Elf_Scn *elf_sec_by_idx(const struct bpf_object *obj, size_t idx) +{ + Elf_Scn *scn; + + scn = elf_getscn(obj->efile.elf, idx); + if (!scn) { + pr_warn("elf: failed to get section(%zu) from %s: %s\n", + idx, obj->path, elf_errmsg(-1)); + return NULL; + } + return scn; +} + +static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name) +{ + Elf_Scn *scn = NULL; + Elf *elf = obj->efile.elf; + const char *sec_name; + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + sec_name = elf_sec_name(obj, scn); + if (!sec_name) + return NULL; + + if (strcmp(sec_name, name) != 0) + continue; + + return scn; + } + return NULL; +} + +static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr) +{ + if (!scn) + return -EINVAL; + + if (gelf_getshdr(scn, hdr) != hdr) { + pr_warn("elf: failed to get section(%zu) header from %s: %s\n", + elf_ndxscn(scn), obj->path, elf_errmsg(-1)); + return -EINVAL; + } + + return 0; +} + +static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn) +{ + const char *name; + GElf_Shdr sh; + + if (!scn) + return NULL; + + if (elf_sec_hdr(obj, scn, &sh)) + return NULL; + + name = elf_sec_str(obj, sh.sh_name); + if (!name) { + pr_warn("elf: failed to get section(%zu) name from %s: %s\n", + elf_ndxscn(scn), obj->path, elf_errmsg(-1)); + return NULL; + } + + return name; +} + +static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn) +{ + Elf_Data *data; + + if (!scn) + return NULL; + + data = elf_getdata(scn, 0); + if (!data) { + pr_warn("elf: failed to get section(%zu) %s data from %s: %s\n", + elf_ndxscn(scn), elf_sec_name(obj, scn) ?: "<?>", + obj->path, elf_errmsg(-1)); + return NULL; + } + + return data; +} + +static bool is_sec_name_dwarf(const char *name) +{ + /* approximation, but the actual list is too long */ + return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0; +} + +static bool ignore_elf_section(GElf_Shdr *hdr, const char *name) +{ + /* no special handling of .strtab */ + if (hdr->sh_type == SHT_STRTAB) + return true; + + /* ignore .llvm_addrsig section as well */ + if (hdr->sh_type == 0x6FFF4C03 /* SHT_LLVM_ADDRSIG */) + return true; + + /* no subprograms will lead to an empty .text section, ignore it */ + if (hdr->sh_type == SHT_PROGBITS && hdr->sh_size == 0 && + strcmp(name, ".text") == 0) + return true; + + /* DWARF sections */ + if (is_sec_name_dwarf(name)) + return true; + + if (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) { + name += sizeof(".rel") - 1; + /* DWARF section relocations */ + if (is_sec_name_dwarf(name)) + return true; + + /* .BTF and .BTF.ext don't need relocations */ + if (strcmp(name, BTF_ELF_SEC) == 0 || + strcmp(name, BTF_EXT_ELF_SEC) == 0) + return true; + } + + return false; +} + static int bpf_object__elf_collect(struct bpf_object *obj) { Elf *elf = obj->efile.elf; - GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Data *btf_ext_data = NULL; Elf_Data *btf_data = NULL; Elf_Scn *scn = NULL; int idx = 0, err = 0; - /* Elf is corrupted/truncated, avoid calling elf_strptr. */ - if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { - pr_warn("failed to get e_shstrndx from %s\n", obj->path); - return -LIBBPF_ERRNO__FORMAT; - } - while ((scn = elf_nextscn(elf, scn)) != NULL) { - char *name; + const char *name; GElf_Shdr sh; Elf_Data *data; idx++; - if (gelf_getshdr(scn, &sh) != &sh) { - pr_warn("failed to get section(%d) header from %s\n", - idx, obj->path); + + if (elf_sec_hdr(obj, scn, &sh)) return -LIBBPF_ERRNO__FORMAT; - } - name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); - if (!name) { - pr_warn("failed to get section(%d) name from %s\n", - idx, obj->path); + name = elf_sec_str(obj, sh.sh_name); + if (!name) return -LIBBPF_ERRNO__FORMAT; - } - data = elf_getdata(scn, 0); - if (!data) { - pr_warn("failed to get section(%d) data from %s(%s)\n", - idx, name, obj->path); + if (ignore_elf_section(&sh, name)) + continue; + + data = elf_sec_data(obj, scn); + if (!data) return -LIBBPF_ERRNO__FORMAT; - } - pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", + + pr_debug("elf: section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", idx, name, (unsigned long)data->d_size, (int)sh.sh_link, (unsigned long)sh.sh_flags, (int)sh.sh_type); if (strcmp(name, "license") == 0) { - err = bpf_object__init_license(obj, - data->d_buf, - data->d_size); + err = bpf_object__init_license(obj, data->d_buf, data->d_size); if (err) return err; } else if (strcmp(name, "version") == 0) { - err = bpf_object__init_kversion(obj, - data->d_buf, - data->d_size); + err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); if (err) return err; } else if (strcmp(name, "maps") == 0) { @@ -2632,8 +2767,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) btf_ext_data = data; } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { - pr_warn("bpf: multiple SYMTAB in %s\n", - obj->path); + pr_warn("elf: multiple symbol tables in %s\n", obj->path); return -LIBBPF_ERRNO__FORMAT; } obj->efile.symbols = data; @@ -2646,16 +2780,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) err = bpf_object__add_program(obj, data->d_buf, data->d_size, name, idx); - if (err) { - char errmsg[STRERR_BUFSIZE]; - char *cp; - - cp = libbpf_strerror_r(-err, errmsg, - sizeof(errmsg)); - pr_warn("failed to alloc program %s (%s): %s", - name, obj->path, cp); + if (err) return err; - } } else if (strcmp(name, DATA_SEC) == 0) { obj->efile.data = data; obj->efile.data_shndx = idx; @@ -2666,7 +2792,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) obj->efile.st_ops_data = data; obj->efile.st_ops_shndx = idx; } else { - pr_debug("skip section(%d) %s\n", idx, name); + pr_info("elf: skipping unrecognized data section(%d) %s\n", + idx, name); } } else if (sh.sh_type == SHT_REL) { int nr_sects = obj->efile.nr_reloc_sects; @@ -2677,34 +2804,33 @@ static int bpf_object__elf_collect(struct bpf_object *obj) if (!section_have_execinstr(obj, sec) && strcmp(name, ".rel" STRUCT_OPS_SEC) && strcmp(name, ".rel" MAPS_ELF_SEC)) { - pr_debug("skip relo %s(%d) for section(%d)\n", - name, idx, sec); + pr_info("elf: skipping relo section(%d) %s for section(%d) %s\n", + idx, name, sec, + elf_sec_name(obj, elf_sec_by_idx(obj, sec)) ?: "<?>"); continue; } - sects = reallocarray(sects, nr_sects + 1, - sizeof(*obj->efile.reloc_sects)); - if (!sects) { - pr_warn("reloc_sects realloc failed\n"); + sects = libbpf_reallocarray(sects, nr_sects + 1, + sizeof(*obj->efile.reloc_sects)); + if (!sects) return -ENOMEM; - } obj->efile.reloc_sects = sects; obj->efile.nr_reloc_sects++; obj->efile.reloc_sects[nr_sects].shdr = sh; obj->efile.reloc_sects[nr_sects].data = data; - } else if (sh.sh_type == SHT_NOBITS && - strcmp(name, BSS_SEC) == 0) { + } else if (sh.sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) { obj->efile.bss = data; obj->efile.bss_shndx = idx; } else { - pr_debug("skip section(%d) %s\n", idx, name); + pr_info("elf: skipping section(%d) %s (size %zu)\n", idx, name, + (size_t)sh.sh_size); } } if (!obj->efile.strtabidx || obj->efile.strtabidx > idx) { - pr_warn("Corrupted ELF file: index of strtab invalid\n"); + pr_warn("elf: symbol strings section missing or invalid in %s\n", obj->path); return -LIBBPF_ERRNO__FORMAT; } return bpf_object__init_btf(obj, btf_data, btf_ext_data); @@ -2865,14 +2991,13 @@ static int bpf_object__collect_externs(struct bpf_object *obj) if (!obj->efile.symbols) return 0; - scn = elf_getscn(obj->efile.elf, obj->efile.symbols_shndx); - if (!scn) - return -LIBBPF_ERRNO__FORMAT; - if (gelf_getshdr(scn, &sh) != &sh) + scn = elf_sec_by_idx(obj, obj->efile.symbols_shndx); + if (elf_sec_hdr(obj, scn, &sh)) return -LIBBPF_ERRNO__FORMAT; - n = sh.sh_size / sh.sh_entsize; + n = sh.sh_size / sh.sh_entsize; pr_debug("looking for externs among %d symbols...\n", n); + for (i = 0; i < n; i++) { GElf_Sym sym; @@ -2880,13 +3005,12 @@ static int bpf_object__collect_externs(struct bpf_object *obj) return -LIBBPF_ERRNO__FORMAT; if (!sym_is_extern(&sym)) continue; - ext_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, - sym.st_name); + ext_name = elf_sym_str(obj, sym.st_name); if (!ext_name || !ext_name[0]) continue; ext = obj->externs; - ext = reallocarray(ext, obj->nr_extern + 1, sizeof(*ext)); + ext = libbpf_reallocarray(ext, obj->nr_extern + 1, sizeof(*ext)); if (!ext) return -ENOMEM; obj->externs = ext; @@ -3105,7 +3229,7 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) static int bpf_program__record_reloc(struct bpf_program *prog, struct reloc_desc *reloc_desc, - __u32 insn_idx, const char *name, + __u32 insn_idx, const char *sym_name, const GElf_Sym *sym, const GElf_Rel *rel) { struct bpf_insn *insn = &prog->insns[insn_idx]; @@ -3113,22 +3237,25 @@ static int bpf_program__record_reloc(struct bpf_program *prog, struct bpf_object *obj = prog->obj; __u32 shdr_idx = sym->st_shndx; enum libbpf_map_type type; + const char *sym_sec_name; struct bpf_map *map; /* sub-program call relocation */ if (insn->code == (BPF_JMP | BPF_CALL)) { if (insn->src_reg != BPF_PSEUDO_CALL) { - pr_warn("incorrect bpf_call opcode\n"); + pr_warn("prog '%s': incorrect bpf_call opcode\n", prog->name); return -LIBBPF_ERRNO__RELOC; } /* text_shndx can be 0, if no default "main" program exists */ if (!shdr_idx || shdr_idx != obj->efile.text_shndx) { - pr_warn("bad call relo against section %u\n", shdr_idx); + sym_sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, shdr_idx)); + pr_warn("prog '%s': bad call relo against '%s' in section '%s'\n", + prog->name, sym_name, sym_sec_name); return -LIBBPF_ERRNO__RELOC; } - if (sym->st_value % 8) { - pr_warn("bad call relo offset: %zu\n", - (size_t)sym->st_value); + if (sym->st_value % BPF_INSN_SZ) { + pr_warn("prog '%s': bad call relo against '%s' at offset %zu\n", + prog->name, sym_name, (size_t)sym->st_value); return -LIBBPF_ERRNO__RELOC; } reloc_desc->type = RELO_CALL; @@ -3139,8 +3266,8 @@ static int bpf_program__record_reloc(struct bpf_program *prog, } if (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) { - pr_warn("invalid relo for insns[%d].code 0x%x\n", - insn_idx, insn->code); + pr_warn("prog '%s': invalid relo against '%s' for insns[%d].code 0x%x\n", + prog->name, sym_name, insn_idx, insn->code); return -LIBBPF_ERRNO__RELOC; } @@ -3155,12 +3282,12 @@ static int bpf_program__record_reloc(struct bpf_program *prog, break; } if (i >= n) { - pr_warn("extern relo failed to find extern for sym %d\n", - sym_idx); + pr_warn("prog '%s': extern relo failed to find extern for '%s' (%d)\n", + prog->name, sym_name, sym_idx); return -LIBBPF_ERRNO__RELOC; } - pr_debug("found extern #%d '%s' (sym %d) for insn %u\n", - i, ext->name, ext->sym_idx, insn_idx); + pr_debug("prog '%s': found extern #%d '%s' (sym %d) for insn #%u\n", + prog->name, i, ext->name, ext->sym_idx, insn_idx); reloc_desc->type = RELO_EXTERN; reloc_desc->insn_idx = insn_idx; reloc_desc->sym_off = i; /* sym_off stores extern index */ @@ -3168,18 +3295,19 @@ static int bpf_program__record_reloc(struct bpf_program *prog, } if (!shdr_idx || shdr_idx >= SHN_LORESERVE) { - pr_warn("invalid relo for \'%s\' in special section 0x%x; forgot to initialize global var?..\n", - name, shdr_idx); + pr_warn("prog '%s': invalid relo against '%s' in special section 0x%x; forgot to initialize global var?..\n", + prog->name, sym_name, shdr_idx); return -LIBBPF_ERRNO__RELOC; } type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); + sym_sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, shdr_idx)); /* generic map reference relocation */ if (type == LIBBPF_MAP_UNSPEC) { if (!bpf_object__shndx_is_maps(obj, shdr_idx)) { - pr_warn("bad map relo against section %u\n", - shdr_idx); + pr_warn("prog '%s': bad map relo against '%s' in section '%s'\n", + prog->name, sym_name, sym_sec_name); return -LIBBPF_ERRNO__RELOC; } for (map_idx = 0; map_idx < nr_maps; map_idx++) { @@ -3188,14 +3316,14 @@ static int bpf_program__record_reloc(struct bpf_program *prog, map->sec_idx != sym->st_shndx || map->sec_offset != sym->st_value) continue; - pr_debug("found map %zd (%s, sec %d, off %zu) for insn %u\n", - map_idx, map->name, map->sec_idx, + pr_debug("prog '%s': found map %zd (%s, sec %d, off %zu) for insn #%u\n", + prog->name, map_idx, map->name, map->sec_idx, map->sec_offset, insn_idx); break; } if (map_idx >= nr_maps) { - pr_warn("map relo failed to find map for sec %u, off %zu\n", - shdr_idx, (size_t)sym->st_value); + pr_warn("prog '%s': map relo failed to find map for section '%s', off %zu\n", + prog->name, sym_sec_name, (size_t)sym->st_value); return -LIBBPF_ERRNO__RELOC; } reloc_desc->type = RELO_LD64; @@ -3207,21 +3335,22 @@ static int bpf_program__record_reloc(struct bpf_program *prog, /* global data map relocation */ if (!bpf_object__shndx_is_data(obj, shdr_idx)) { - pr_warn("bad data relo against section %u\n", shdr_idx); + pr_warn("prog '%s': bad data relo against section '%s'\n", + prog->name, sym_sec_name); return -LIBBPF_ERRNO__RELOC; } for (map_idx = 0; map_idx < nr_maps; map_idx++) { map = &obj->maps[map_idx]; if (map->libbpf_type != type) continue; - pr_debug("found data map %zd (%s, sec %d, off %zu) for insn %u\n", - map_idx, map->name, map->sec_idx, map->sec_offset, - insn_idx); + pr_debug("prog '%s': found data map %zd (%s, sec %d, off %zu) for insn %u\n", + prog->name, map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); break; } if (map_idx >= nr_maps) { - pr_warn("data relo failed to find map for sec %u\n", - shdr_idx); + pr_warn("prog '%s': data relo failed to find map for section '%s'\n", + prog->name, sym_sec_name); return -LIBBPF_ERRNO__RELOC; } @@ -3237,9 +3366,17 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, Elf_Data *data, struct bpf_object *obj) { Elf_Data *symbols = obj->efile.symbols; + const char *relo_sec_name, *sec_name; + size_t sec_idx = shdr->sh_info; int err, i, nrels; - pr_debug("collecting relocating info for: '%s'\n", prog->section_name); + relo_sec_name = elf_sec_str(obj, shdr->sh_name); + sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); + if (!relo_sec_name || !sec_name) + return -EINVAL; + + pr_debug("sec '%s': collecting relocation for section(%zu) '%s'\n", + relo_sec_name, sec_idx, sec_name); nrels = shdr->sh_size / shdr->sh_entsize; prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels); @@ -3250,35 +3387,34 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, prog->nr_reloc = nrels; for (i = 0; i < nrels; i++) { - const char *name; + const char *sym_name; __u32 insn_idx; GElf_Sym sym; GElf_Rel rel; if (!gelf_getrel(data, i, &rel)) { - pr_warn("relocation: failed to get %d reloc\n", i); + pr_warn("sec '%s': failed to get relo #%d\n", relo_sec_name, i); return -LIBBPF_ERRNO__FORMAT; } if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { - pr_warn("relocation: symbol %"PRIx64" not found\n", - GELF_R_SYM(rel.r_info)); + pr_warn("sec '%s': symbol 0x%zx not found for relo #%d\n", + relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i); return -LIBBPF_ERRNO__FORMAT; } - if (rel.r_offset % sizeof(struct bpf_insn)) + if (rel.r_offset % BPF_INSN_SZ) { + pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n", + relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i); return -LIBBPF_ERRNO__FORMAT; + } - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, - sym.st_name) ? : "<?>"; + insn_idx = rel.r_offset / BPF_INSN_SZ; + sym_name = elf_sym_str(obj, sym.st_name) ?: "<?>"; - pr_debug("relo for shdr %u, symb %zu, value %zu, type %d, bind %d, name %d (\'%s\'), insn %u\n", - (__u32)sym.st_shndx, (size_t)GELF_R_SYM(rel.r_info), - (size_t)sym.st_value, GELF_ST_TYPE(sym.st_info), - GELF_ST_BIND(sym.st_info), sym.st_name, name, - insn_idx); + pr_debug("sec '%s': relo #%d: insn #%u against '%s'\n", + relo_sec_name, i, insn_idx, sym_name); err = bpf_program__record_reloc(prog, &prog->reloc_desc[i], - insn_idx, name, &sym, &rel); + insn_idx, sym_name, &sym, &rel); if (err) return err; } @@ -3429,8 +3565,14 @@ bpf_object__probe_loading(struct bpf_object *obj) return 0; } -static int -bpf_object__probe_name(struct bpf_object *obj) +static int probe_fd(int fd) +{ + if (fd >= 0) + close(fd); + return fd >= 0; +} + +static int probe_kern_prog_name(void) { struct bpf_load_program_attr attr; struct bpf_insn insns[] = { @@ -3448,16 +3590,10 @@ bpf_object__probe_name(struct bpf_object *obj) attr.license = "GPL"; attr.name = "test"; ret = bpf_load_program_xattr(&attr, NULL, 0); - if (ret >= 0) { - obj->caps.name = 1; - close(ret); - } - - return 0; + return probe_fd(ret); } -static int -bpf_object__probe_global_data(struct bpf_object *obj) +static int probe_kern_global_data(void) { struct bpf_load_program_attr prg_attr; struct bpf_create_map_attr map_attr; @@ -3478,10 +3614,11 @@ bpf_object__probe_global_data(struct bpf_object *obj) map = bpf_create_map_xattr(&map_attr); if (map < 0) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, errno); - return -errno; + __func__, cp, -ret); + return ret; } insns[0].imm = map; @@ -3493,16 +3630,23 @@ bpf_object__probe_global_data(struct bpf_object *obj) prg_attr.license = "GPL"; ret = bpf_load_program_xattr(&prg_attr, NULL, 0); - if (ret >= 0) { - obj->caps.global_data = 1; - close(ret); - } - close(map); - return 0; + return probe_fd(ret); +} + +static int probe_kern_btf(void) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); } -static int bpf_object__probe_btf_func(struct bpf_object *obj) +static int probe_kern_btf_func(void) { static const char strs[] = "\0int\0x\0a"; /* void x(int a) {} */ @@ -3515,20 +3659,12 @@ static int bpf_object__probe_btf_func(struct bpf_object *obj) /* FUNC x */ /* [3] */ BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), }; - int btf_fd; - btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs)); - if (btf_fd >= 0) { - obj->caps.btf_func = 1; - close(btf_fd); - return 1; - } - - return 0; + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); } -static int bpf_object__probe_btf_func_global(struct bpf_object *obj) +static int probe_kern_btf_func_global(void) { static const char strs[] = "\0int\0x\0a"; /* static void x(int a) {} */ @@ -3541,20 +3677,12 @@ static int bpf_object__probe_btf_func_global(struct bpf_object *obj) /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), }; - int btf_fd; - - btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs)); - if (btf_fd >= 0) { - obj->caps.btf_func_global = 1; - close(btf_fd); - return 1; - } - return 0; + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); } -static int bpf_object__probe_btf_datasec(struct bpf_object *obj) +static int probe_kern_btf_datasec(void) { static const char strs[] = "\0x\0.data"; /* static int a; */ @@ -3568,20 +3696,12 @@ static int bpf_object__probe_btf_datasec(struct bpf_object *obj) BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), BTF_VAR_SECINFO_ENC(2, 0, 4), }; - int btf_fd; - btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs)); - if (btf_fd >= 0) { - obj->caps.btf_datasec = 1; - close(btf_fd); - return 1; - } - - return 0; + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); } -static int bpf_object__probe_array_mmap(struct bpf_object *obj) +static int probe_kern_array_mmap(void) { struct bpf_create_map_attr attr = { .map_type = BPF_MAP_TYPE_ARRAY, @@ -3590,27 +3710,17 @@ static int bpf_object__probe_array_mmap(struct bpf_object *obj) .value_size = sizeof(int), .max_entries = 1, }; - int fd; - fd = bpf_create_map_xattr(&attr); - if (fd >= 0) { - obj->caps.array_mmap = 1; - close(fd); - return 1; - } - - return 0; + return probe_fd(bpf_create_map_xattr(&attr)); } -static int -bpf_object__probe_exp_attach_type(struct bpf_object *obj) +static int probe_kern_exp_attach_type(void) { struct bpf_load_program_attr attr; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int fd; memset(&attr, 0, sizeof(attr)); /* use any valid combination of program type and (optional) @@ -3624,36 +3734,91 @@ bpf_object__probe_exp_attach_type(struct bpf_object *obj) attr.insns_cnt = ARRAY_SIZE(insns); attr.license = "GPL"; - fd = bpf_load_program_xattr(&attr, NULL, 0); - if (fd >= 0) { - obj->caps.exp_attach_type = 1; - close(fd); - return 1; - } - return 0; + return probe_fd(bpf_load_program_xattr(&attr, NULL, 0)); } -static int -bpf_object__probe_caps(struct bpf_object *obj) -{ - int (*probe_fn[])(struct bpf_object *obj) = { - bpf_object__probe_name, - bpf_object__probe_global_data, - bpf_object__probe_btf_func, - bpf_object__probe_btf_func_global, - bpf_object__probe_btf_datasec, - bpf_object__probe_array_mmap, - bpf_object__probe_exp_attach_type, +static int probe_kern_probe_read_kernel(void) +{ + struct bpf_load_program_attr attr; + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ + BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ + BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), + BPF_EXIT_INSN(), }; - int i, ret; - for (i = 0; i < ARRAY_SIZE(probe_fn); i++) { - ret = probe_fn[i](obj); - if (ret < 0) - pr_debug("Probe #%d failed with %d.\n", i, ret); + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_KPROBE; + attr.insns = insns; + attr.insns_cnt = ARRAY_SIZE(insns); + attr.license = "GPL"; + + return probe_fd(bpf_load_program_xattr(&attr, NULL, 0)); +} + +enum kern_feature_result { + FEAT_UNKNOWN = 0, + FEAT_SUPPORTED = 1, + FEAT_MISSING = 2, +}; + +typedef int (*feature_probe_fn)(void); + +static struct kern_feature_desc { + const char *desc; + feature_probe_fn probe; + enum kern_feature_result res; +} feature_probes[__FEAT_CNT] = { + [FEAT_PROG_NAME] = { + "BPF program name", probe_kern_prog_name, + }, + [FEAT_GLOBAL_DATA] = { + "global variables", probe_kern_global_data, + }, + [FEAT_BTF] = { + "minimal BTF", probe_kern_btf, + }, + [FEAT_BTF_FUNC] = { + "BTF functions", probe_kern_btf_func, + }, + [FEAT_BTF_GLOBAL_FUNC] = { + "BTF global function", probe_kern_btf_func_global, + }, + [FEAT_BTF_DATASEC] = { + "BTF data section and variable", probe_kern_btf_datasec, + }, + [FEAT_ARRAY_MMAP] = { + "ARRAY map mmap()", probe_kern_array_mmap, + }, + [FEAT_EXP_ATTACH_TYPE] = { + "BPF_PROG_LOAD expected_attach_type attribute", + probe_kern_exp_attach_type, + }, + [FEAT_PROBE_READ_KERN] = { + "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, } +}; - return 0; +static bool kernel_supports(enum kern_feature_id feat_id) +{ + struct kern_feature_desc *feat = &feature_probes[feat_id]; + int ret; + + if (READ_ONCE(feat->res) == FEAT_UNKNOWN) { + ret = feat->probe(); + if (ret > 0) { + WRITE_ONCE(feat->res, FEAT_SUPPORTED); + } else if (ret == 0) { + WRITE_ONCE(feat->res, FEAT_MISSING); + } else { + pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); + WRITE_ONCE(feat->res, FEAT_MISSING); + } + } + + return READ_ONCE(feat->res) == FEAT_SUPPORTED; } static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) @@ -3755,7 +3920,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) memset(&create_attr, 0, sizeof(create_attr)); - if (obj->caps.name) + if (kernel_supports(FEAT_PROG_NAME)) create_attr.name = map->name; create_attr.map_ifindex = map->map_ifindex; create_attr.map_type = def->type; @@ -4006,6 +4171,10 @@ struct bpf_core_spec { const struct btf *btf; /* high-level spec: named fields and array indices only */ struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* original unresolved (no skip_mods_or_typedefs) root type ID */ + __u32 root_type_id; + /* CO-RE relocation kind */ + enum bpf_core_relo_kind relo_kind; /* high-level spec length */ int len; /* raw, low-level spec: 1-to-1 with accessor spec string */ @@ -4036,8 +4205,66 @@ static bool is_flex_arr(const struct btf *btf, return acc->idx == btf_vlen(t) - 1; } +static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) +{ + switch (kind) { + case BPF_FIELD_BYTE_OFFSET: return "byte_off"; + case BPF_FIELD_BYTE_SIZE: return "byte_sz"; + case BPF_FIELD_EXISTS: return "field_exists"; + case BPF_FIELD_SIGNED: return "signed"; + case BPF_FIELD_LSHIFT_U64: return "lshift_u64"; + case BPF_FIELD_RSHIFT_U64: return "rshift_u64"; + case BPF_TYPE_ID_LOCAL: return "local_type_id"; + case BPF_TYPE_ID_TARGET: return "target_type_id"; + case BPF_TYPE_EXISTS: return "type_exists"; + case BPF_TYPE_SIZE: return "type_size"; + case BPF_ENUMVAL_EXISTS: return "enumval_exists"; + case BPF_ENUMVAL_VALUE: return "enumval_value"; + default: return "unknown"; + } +} + +static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) +{ + switch (kind) { + case BPF_FIELD_BYTE_OFFSET: + case BPF_FIELD_BYTE_SIZE: + case BPF_FIELD_EXISTS: + case BPF_FIELD_SIGNED: + case BPF_FIELD_LSHIFT_U64: + case BPF_FIELD_RSHIFT_U64: + return true; + default: + return false; + } +} + +static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) +{ + switch (kind) { + case BPF_TYPE_ID_LOCAL: + case BPF_TYPE_ID_TARGET: + case BPF_TYPE_EXISTS: + case BPF_TYPE_SIZE: + return true; + default: + return false; + } +} + +static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) +{ + switch (kind) { + case BPF_ENUMVAL_EXISTS: + case BPF_ENUMVAL_VALUE: + return true; + default: + return false; + } +} + /* - * Turn bpf_field_reloc into a low- and high-level spec representation, + * Turn bpf_core_relo into a low- and high-level spec representation, * validating correctness along the way, as well as calculating resulting * field bit offset, specified by accessor string. Low-level spec captures * every single level of nestedness, including traversing anonymous @@ -4066,10 +4293,17 @@ static bool is_flex_arr(const struct btf *btf, * - field 'a' access (corresponds to '2' in low-level spec); * - array element #3 access (corresponds to '3' in low-level spec). * + * Type-based relocations (TYPE_EXISTS/TYPE_SIZE, + * TYPE_ID_LOCAL/TYPE_ID_TARGET) don't capture any field information. Their + * spec and raw_spec are kept empty. + * + * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access + * string to specify enumerator's value index that need to be relocated. */ -static int bpf_core_spec_parse(const struct btf *btf, +static int bpf_core_parse_spec(const struct btf *btf, __u32 type_id, const char *spec_str, + enum bpf_core_relo_kind relo_kind, struct bpf_core_spec *spec) { int access_idx, parsed_len, i; @@ -4084,6 +4318,15 @@ static int bpf_core_spec_parse(const struct btf *btf, memset(spec, 0, sizeof(*spec)); spec->btf = btf; + spec->root_type_id = type_id; + spec->relo_kind = relo_kind; + + /* type-based relocations don't have a field access string */ + if (core_relo_is_type_based(relo_kind)) { + if (strcmp(spec_str, "0")) + return -EINVAL; + return 0; + } /* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */ while (*spec_str) { @@ -4100,16 +4343,28 @@ static int bpf_core_spec_parse(const struct btf *btf, if (spec->raw_len == 0) return -EINVAL; - /* first spec value is always reloc type array index */ t = skip_mods_and_typedefs(btf, type_id, &id); if (!t) return -EINVAL; access_idx = spec->raw_spec[0]; - spec->spec[0].type_id = id; - spec->spec[0].idx = access_idx; + acc = &spec->spec[0]; + acc->type_id = id; + acc->idx = access_idx; spec->len++; + if (core_relo_is_enumval_based(relo_kind)) { + if (!btf_is_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t)) + return -EINVAL; + + /* record enumerator name in a first accessor */ + acc->name = btf__name_by_offset(btf, btf_enum(t)[access_idx].name_off); + return 0; + } + + if (!core_relo_is_field_based(relo_kind)) + return -EINVAL; + sz = btf__resolve_size(btf, id); if (sz < 0) return sz; @@ -4167,8 +4422,8 @@ static int bpf_core_spec_parse(const struct btf *btf, return sz; spec->bit_offset += access_idx * sz * 8; } else { - pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n", - type_id, spec_str, i, id, btf_kind(t)); + pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", + type_id, spec_str, i, id, btf_kind_str(t)); return -EINVAL; } } @@ -4218,16 +4473,16 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, { size_t local_essent_len, targ_essent_len; const char *local_name, *targ_name; - const struct btf_type *t; + const struct btf_type *t, *local_t; struct ids_vec *cand_ids; __u32 *new_ids; int i, err, n; - t = btf__type_by_id(local_btf, local_type_id); - if (!t) + local_t = btf__type_by_id(local_btf, local_type_id); + if (!local_t) return ERR_PTR(-EINVAL); - local_name = btf__name_by_offset(local_btf, t->name_off); + local_name = btf__name_by_offset(local_btf, local_t->name_off); if (str_is_empty(local_name)) return ERR_PTR(-EINVAL); local_essent_len = bpf_core_essential_name_len(local_name); @@ -4239,12 +4494,11 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, n = btf__get_nr_types(targ_btf); for (i = 1; i <= n; i++) { t = btf__type_by_id(targ_btf, i); - targ_name = btf__name_by_offset(targ_btf, t->name_off); - if (str_is_empty(targ_name)) + if (btf_kind(t) != btf_kind(local_t)) continue; - t = skip_mods_and_typedefs(targ_btf, i, NULL); - if (!btf_is_composite(t) && !btf_is_array(t)) + targ_name = btf__name_by_offset(targ_btf, t->name_off); + if (str_is_empty(targ_name)) continue; targ_essent_len = bpf_core_essential_name_len(targ_name); @@ -4252,11 +4506,12 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, continue; if (strncmp(local_name, targ_name, local_essent_len) == 0) { - pr_debug("[%d] %s: found candidate [%d] %s\n", - local_type_id, local_name, i, targ_name); - new_ids = reallocarray(cand_ids->data, - cand_ids->len + 1, - sizeof(*cand_ids->data)); + pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s\n", + local_type_id, btf_kind_str(local_t), + local_name, i, btf_kind_str(t), targ_name); + new_ids = libbpf_reallocarray(cand_ids->data, + cand_ids->len + 1, + sizeof(*cand_ids->data)); if (!new_ids) { err = -ENOMEM; goto err_out; @@ -4271,8 +4526,9 @@ err_out: return ERR_PTR(err); } -/* Check two types for compatibility, skipping const/volatile/restrict and - * typedefs, to ensure we are relocating compatible entities: +/* Check two types for compatibility for the purpose of field access + * relocation. const/volatile/restrict and typedefs are skipped to ensure we + * are relocating semantically compatible entities: * - any two STRUCTs/UNIONs are compatible and can be mixed; * - any two FWDs are compatible, if their names match (modulo flavor suffix); * - any two PTRs are always compatible; @@ -4427,6 +4683,100 @@ static int bpf_core_match_member(const struct btf *local_btf, return 0; } +/* Check local and target types for compatibility. This check is used for + * type-based CO-RE relocations and follow slightly different rules than + * field-based relocations. This function assumes that root types were already + * checked for name match. Beyond that initial root-level name check, names + * are completely ignored. Compatibility rules are as follows: + * - any two STRUCTs/UNIONs/FWDs/ENUMs/INTs are considered compatible, but + * kind should match for local and target types (i.e., STRUCT is not + * compatible with UNION); + * - for ENUMs, the size is ignored; + * - for INT, size and signedness are ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - CONST/VOLATILE/RESTRICT modifiers are ignored; + * - TYPEDEFs/PTRs are compatible if types they pointing to are compatible; + * - FUNC_PROTOs are compatible if they have compatible signature: same + * number of input args and compatible return and argument types. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ +static int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id) +{ + const struct btf_type *local_type, *targ_type; + int depth = 32; /* max recursion depth */ + + /* caller made sure that names match (ignoring flavor suffix) */ + local_type = btf__type_by_id(local_btf, local_id); + targ_type = btf__type_by_id(targ_btf, targ_id); + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; + +recur: + depth--; + if (depth < 0) + return -EINVAL; + + local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + return 1; + case BTF_KIND_INT: + /* just reject deprecated bitfield-like integers; all other + * integers are by default compatible between each other + */ + return btf_int_offset(local_type) == 0 && btf_int_offset(targ_type) == 0; + case BTF_KIND_PTR: + local_id = local_type->type; + targ_id = targ_type->type; + goto recur; + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + case BTF_KIND_FUNC_PROTO: { + struct btf_param *local_p = btf_params(local_type); + struct btf_param *targ_p = btf_params(targ_type); + __u16 local_vlen = btf_vlen(local_type); + __u16 targ_vlen = btf_vlen(targ_type); + int i, err; + + if (local_vlen != targ_vlen) + return 0; + + for (i = 0; i < local_vlen; i++, local_p++, targ_p++) { + skip_mods_and_typedefs(local_btf, local_p->type, &local_id); + skip_mods_and_typedefs(targ_btf, targ_p->type, &targ_id); + err = bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id); + if (err <= 0) + return err; + } + + /* tail recurse for return type check */ + skip_mods_and_typedefs(local_btf, local_type->type, &local_id); + skip_mods_and_typedefs(targ_btf, targ_type->type, &targ_id); + goto recur; + } + default: + pr_warn("unexpected kind %s relocated, local [%d], target [%d]\n", + btf_kind_str(local_type), local_id, targ_id); + return 0; + } +} + /* * Try to match local spec to a target type and, if successful, produce full * target spec (high-level, low-level + bit offset). @@ -4442,10 +4792,51 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, memset(targ_spec, 0, sizeof(*targ_spec)); targ_spec->btf = targ_btf; + targ_spec->root_type_id = targ_id; + targ_spec->relo_kind = local_spec->relo_kind; + + if (core_relo_is_type_based(local_spec->relo_kind)) { + return bpf_core_types_are_compat(local_spec->btf, + local_spec->root_type_id, + targ_btf, targ_id); + } local_acc = &local_spec->spec[0]; targ_acc = &targ_spec->spec[0]; + if (core_relo_is_enumval_based(local_spec->relo_kind)) { + size_t local_essent_len, targ_essent_len; + const struct btf_enum *e; + const char *targ_name; + + /* has to resolve to an enum */ + targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, &targ_id); + if (!btf_is_enum(targ_type)) + return 0; + + local_essent_len = bpf_core_essential_name_len(local_acc->name); + + for (i = 0, e = btf_enum(targ_type); i < btf_vlen(targ_type); i++, e++) { + targ_name = btf__name_by_offset(targ_spec->btf, e->name_off); + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != local_essent_len) + continue; + if (strncmp(local_acc->name, targ_name, local_essent_len) == 0) { + targ_acc->type_id = targ_id; + targ_acc->idx = i; + targ_acc->name = targ_name; + targ_spec->len++; + targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx; + targ_spec->raw_len++; + return 1; + } + } + return 0; + } + + if (!core_relo_is_field_based(local_spec->relo_kind)) + return -EINVAL; + for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) { targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, &targ_id); @@ -4502,18 +4893,29 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, } static int bpf_core_calc_field_relo(const struct bpf_program *prog, - const struct bpf_field_reloc *relo, + const struct bpf_core_relo *relo, const struct bpf_core_spec *spec, __u32 *val, bool *validate) { - const struct bpf_core_accessor *acc = &spec->spec[spec->len - 1]; - const struct btf_type *t = btf__type_by_id(spec->btf, acc->type_id); + const struct bpf_core_accessor *acc; + const struct btf_type *t; __u32 byte_off, byte_sz, bit_off, bit_sz; const struct btf_member *m; const struct btf_type *mt; bool bitfield; __s64 sz; + if (relo->kind == BPF_FIELD_EXISTS) { + *val = spec ? 1 : 0; + return 0; + } + + if (!spec) + return -EUCLEAN; /* request instruction poisoning */ + + acc = &spec->spec[spec->len - 1]; + t = btf__type_by_id(spec->btf, acc->type_id); + /* a[n] accessor needs special handling */ if (!acc->name) { if (relo->kind == BPF_FIELD_BYTE_OFFSET) { @@ -4599,21 +5001,158 @@ static int bpf_core_calc_field_relo(const struct bpf_program *prog, break; case BPF_FIELD_EXISTS: default: - pr_warn("prog '%s': unknown relo %d at insn #%d\n", - bpf_program__title(prog, false), - relo->kind, relo->insn_off / 8); - return -EINVAL; + return -EOPNOTSUPP; + } + + return 0; +} + +static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, + const struct bpf_core_spec *spec, + __u32 *val) +{ + __s64 sz; + + /* type-based relos return zero when target type is not found */ + if (!spec) { + *val = 0; + return 0; + } + + switch (relo->kind) { + case BPF_TYPE_ID_TARGET: + *val = spec->root_type_id; + break; + case BPF_TYPE_EXISTS: + *val = 1; + break; + case BPF_TYPE_SIZE: + sz = btf__resolve_size(spec->btf, spec->root_type_id); + if (sz < 0) + return -EINVAL; + *val = sz; + break; + case BPF_TYPE_ID_LOCAL: + /* BPF_TYPE_ID_LOCAL is handled specially and shouldn't get here */ + default: + return -EOPNOTSUPP; } return 0; } +static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, + const struct bpf_core_spec *spec, + __u32 *val) +{ + const struct btf_type *t; + const struct btf_enum *e; + + switch (relo->kind) { + case BPF_ENUMVAL_EXISTS: + *val = spec ? 1 : 0; + break; + case BPF_ENUMVAL_VALUE: + if (!spec) + return -EUCLEAN; /* request instruction poisoning */ + t = btf__type_by_id(spec->btf, spec->spec[0].type_id); + e = btf_enum(t) + spec->spec[0].idx; + *val = e->val; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +struct bpf_core_relo_res +{ + /* expected value in the instruction, unless validate == false */ + __u32 orig_val; + /* new value that needs to be patched up to */ + __u32 new_val; + /* relocation unsuccessful, poison instruction, but don't fail load */ + bool poison; + /* some relocations can't be validated against orig_val */ + bool validate; +}; + +/* Calculate original and target relocation values, given local and target + * specs and relocation kind. These values are calculated for each candidate. + * If there are multiple candidates, resulting values should all be consistent + * with each other. Otherwise, libbpf will refuse to proceed due to ambiguity. + * If instruction has to be poisoned, *poison will be set to true. + */ +static int bpf_core_calc_relo(const struct bpf_program *prog, + const struct bpf_core_relo *relo, + int relo_idx, + const struct bpf_core_spec *local_spec, + const struct bpf_core_spec *targ_spec, + struct bpf_core_relo_res *res) +{ + int err = -EOPNOTSUPP; + + res->orig_val = 0; + res->new_val = 0; + res->poison = false; + res->validate = true; + + if (core_relo_is_field_based(relo->kind)) { + err = bpf_core_calc_field_relo(prog, relo, local_spec, &res->orig_val, &res->validate); + err = err ?: bpf_core_calc_field_relo(prog, relo, targ_spec, &res->new_val, NULL); + } else if (core_relo_is_type_based(relo->kind)) { + err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val); + err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val); + } else if (core_relo_is_enumval_based(relo->kind)) { + err = bpf_core_calc_enumval_relo(relo, local_spec, &res->orig_val); + err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val); + } + + if (err == -EUCLEAN) { + /* EUCLEAN is used to signal instruction poisoning request */ + res->poison = true; + err = 0; + } else if (err == -EOPNOTSUPP) { + /* EOPNOTSUPP means unknown/unsupported relocation */ + pr_warn("prog '%s': relo #%d: unrecognized CO-RE relocation %s (%d) at insn #%d\n", + bpf_program__title(prog, false), relo_idx, + core_relo_kind_str(relo->kind), relo->kind, relo->insn_off / 8); + } + + return err; +} + +/* + * Turn instruction for which CO_RE relocation failed into invalid one with + * distinct signature. + */ +static void bpf_core_poison_insn(struct bpf_program *prog, int relo_idx, + int insn_idx, struct bpf_insn *insn) +{ + pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n", + bpf_program__title(prog, false), relo_idx, insn_idx); + insn->code = BPF_JMP | BPF_CALL; + insn->dst_reg = 0; + insn->src_reg = 0; + insn->off = 0; + /* if this instruction is reachable (not a dead code), + * verifier will complain with the following message: + * invalid func unknown#195896080 + */ + insn->imm = 195896080; /* => 0xbad2310 => "bad relo" */ +} + +static bool is_ldimm64(struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + /* * Patch relocatable BPF instruction. * * Patched value is determined by relocation kind and target specification. - * For field existence relocation target spec will be NULL if field is not - * found. + * For existence relocations target spec will be NULL if field/type is not found. * Expected insn->imm value is determined using relocation kind and local * spec, and is checked before patching instruction. If actual insn->imm value * is wrong, bail out with error. @@ -4621,58 +5160,43 @@ static int bpf_core_calc_field_relo(const struct bpf_program *prog, * Currently three kinds of BPF instructions are supported: * 1. rX = <imm> (assignment with immediate operand); * 2. rX += <imm> (arithmetic operations with immediate operand); + * 3. rX = <imm64> (load with 64-bit immediate value). */ -static int bpf_core_reloc_insn(struct bpf_program *prog, - const struct bpf_field_reloc *relo, +static int bpf_core_patch_insn(struct bpf_program *prog, + const struct bpf_core_relo *relo, int relo_idx, - const struct bpf_core_spec *local_spec, - const struct bpf_core_spec *targ_spec) + const struct bpf_core_relo_res *res) { __u32 orig_val, new_val; struct bpf_insn *insn; - bool validate = true; - int insn_idx, err; + int insn_idx; __u8 class; - if (relo->insn_off % sizeof(struct bpf_insn)) + if (relo->insn_off % BPF_INSN_SZ) return -EINVAL; - insn_idx = relo->insn_off / sizeof(struct bpf_insn); + insn_idx = relo->insn_off / BPF_INSN_SZ; insn = &prog->insns[insn_idx]; class = BPF_CLASS(insn->code); - if (relo->kind == BPF_FIELD_EXISTS) { - orig_val = 1; /* can't generate EXISTS relo w/o local field */ - new_val = targ_spec ? 1 : 0; - } else if (!targ_spec) { - pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n", - bpf_program__title(prog, false), relo_idx, insn_idx); - insn->code = BPF_JMP | BPF_CALL; - insn->dst_reg = 0; - insn->src_reg = 0; - insn->off = 0; - /* if this instruction is reachable (not a dead code), - * verifier will complain with the following message: - * invalid func unknown#195896080 + if (res->poison) { + /* poison second part of ldimm64 to avoid confusing error from + * verifier about "unknown opcode 00" */ - insn->imm = 195896080; /* => 0xbad2310 => "bad relo" */ + if (is_ldimm64(insn)) + bpf_core_poison_insn(prog, relo_idx, insn_idx + 1, insn + 1); + bpf_core_poison_insn(prog, relo_idx, insn_idx, insn); return 0; - } else { - err = bpf_core_calc_field_relo(prog, relo, local_spec, - &orig_val, &validate); - if (err) - return err; - err = bpf_core_calc_field_relo(prog, relo, targ_spec, - &new_val, NULL); - if (err) - return err; } + orig_val = res->orig_val; + new_val = res->new_val; + switch (class) { case BPF_ALU: case BPF_ALU64: if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; - if (validate && insn->imm != orig_val) { + if (res->validate && insn->imm != orig_val) { pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n", bpf_program__title(prog, false), relo_idx, insn_idx, insn->imm, orig_val, new_val); @@ -4687,8 +5211,8 @@ static int bpf_core_reloc_insn(struct bpf_program *prog, case BPF_LDX: case BPF_ST: case BPF_STX: - if (validate && insn->off != orig_val) { - pr_warn("prog '%s': relo #%d: unexpected insn #%d (LD/LDX/ST/STX) value: got %u, exp %u -> %u\n", + if (res->validate && insn->off != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %u -> %u\n", bpf_program__title(prog, false), relo_idx, insn_idx, insn->off, orig_val, new_val); return -EINVAL; @@ -4705,8 +5229,37 @@ static int bpf_core_reloc_insn(struct bpf_program *prog, bpf_program__title(prog, false), relo_idx, insn_idx, orig_val, new_val); break; + case BPF_LD: { + __u64 imm; + + if (!is_ldimm64(insn) || + insn[0].src_reg != 0 || insn[0].off != 0 || + insn_idx + 1 >= prog->insns_cnt || + insn[1].code != 0 || insn[1].dst_reg != 0 || + insn[1].src_reg != 0 || insn[1].off != 0) { + pr_warn("prog '%s': relo #%d: insn #%d (LDIMM64) has unexpected form\n", + bpf_program__title(prog, false), relo_idx, insn_idx); + return -EINVAL; + } + + imm = insn[0].imm + ((__u64)insn[1].imm << 32); + if (res->validate && imm != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %u -> %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, (unsigned long long)imm, + orig_val, new_val); + return -EINVAL; + } + + insn[0].imm = new_val; + insn[1].imm = 0; /* currently only 32-bit values are supported */ + pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %u\n", + bpf_program__title(prog, false), relo_idx, insn_idx, + (unsigned long long)imm, new_val); + break; + } default: - pr_warn("prog '%s': relo #%d: trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + pr_warn("prog '%s': relo #%d: trying to relocate unrecognized insn #%d, code:0x%x, src:0x%x, dst:0x%x, off:0x%x, imm:0x%x\n", bpf_program__title(prog, false), relo_idx, insn_idx, insn->code, insn->src_reg, insn->dst_reg, insn->off, insn->imm); @@ -4723,29 +5276,48 @@ static int bpf_core_reloc_insn(struct bpf_program *prog, static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) { const struct btf_type *t; + const struct btf_enum *e; const char *s; __u32 type_id; int i; - type_id = spec->spec[0].type_id; + type_id = spec->root_type_id; t = btf__type_by_id(spec->btf, type_id); s = btf__name_by_offset(spec->btf, t->name_off); - libbpf_print(level, "[%u] %s + ", type_id, s); - for (i = 0; i < spec->raw_len; i++) - libbpf_print(level, "%d%s", spec->raw_spec[i], - i == spec->raw_len - 1 ? " => " : ":"); + libbpf_print(level, "[%u] %s %s", type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s); + + if (core_relo_is_type_based(spec->relo_kind)) + return; - libbpf_print(level, "%u.%u @ &x", - spec->bit_offset / 8, spec->bit_offset % 8); + if (core_relo_is_enumval_based(spec->relo_kind)) { + t = skip_mods_and_typedefs(spec->btf, type_id, NULL); + e = btf_enum(t) + spec->raw_spec[0]; + s = btf__name_by_offset(spec->btf, e->name_off); - for (i = 0; i < spec->len; i++) { - if (spec->spec[i].name) - libbpf_print(level, ".%s", spec->spec[i].name); - else - libbpf_print(level, "[%u]", spec->spec[i].idx); + libbpf_print(level, "::%s = %u", s, e->val); + return; } + if (core_relo_is_field_based(spec->relo_kind)) { + for (i = 0; i < spec->len; i++) { + if (spec->spec[i].name) + libbpf_print(level, ".%s", spec->spec[i].name); + else if (i > 0 || spec->spec[i].idx > 0) + libbpf_print(level, "[%u]", spec->spec[i].idx); + } + + libbpf_print(level, " ("); + for (i = 0; i < spec->raw_len; i++) + libbpf_print(level, "%s%d", i == 0 ? "" : ":", spec->raw_spec[i]); + + if (spec->bit_offset % 8) + libbpf_print(level, " @ offset %u.%u)", + spec->bit_offset / 8, spec->bit_offset % 8); + else + libbpf_print(level, " @ offset %u)", spec->bit_offset / 8); + return; + } } static size_t bpf_core_hash_fn(const void *key, void *ctx) @@ -4809,22 +5381,23 @@ static void *u32_as_hash_key(__u32 x) * CPU-wise compared to prebuilding a map from all local type names to * a list of candidate type names. It's also sped up by caching resolved * list of matching candidates per each local "root" type ID, that has at - * least one bpf_field_reloc associated with it. This list is shared + * least one bpf_core_relo associated with it. This list is shared * between multiple relocations for the same type ID and is updated as some * of the candidates are pruned due to structural incompatibility. */ -static int bpf_core_reloc_field(struct bpf_program *prog, - const struct bpf_field_reloc *relo, - int relo_idx, - const struct btf *local_btf, - const struct btf *targ_btf, - struct hashmap *cand_cache) +static int bpf_core_apply_relo(struct bpf_program *prog, + const struct bpf_core_relo *relo, + int relo_idx, + const struct btf *local_btf, + const struct btf *targ_btf, + struct hashmap *cand_cache) { const char *prog_name = bpf_program__title(prog, false); - struct bpf_core_spec local_spec, cand_spec, targ_spec; + struct bpf_core_spec local_spec, cand_spec, targ_spec = {}; const void *type_key = u32_as_hash_key(relo->type_id); - const struct btf_type *local_type, *cand_type; - const char *local_name, *cand_name; + struct bpf_core_relo_res cand_res, targ_res; + const struct btf_type *local_type; + const char *local_name; struct ids_vec *cand_ids; __u32 local_id, cand_id; const char *spec_str; @@ -4836,32 +5409,49 @@ static int bpf_core_reloc_field(struct bpf_program *prog, return -EINVAL; local_name = btf__name_by_offset(local_btf, local_type->name_off); - if (str_is_empty(local_name)) + if (!local_name) return -EINVAL; spec_str = btf__name_by_offset(local_btf, relo->access_str_off); if (str_is_empty(spec_str)) return -EINVAL; - err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec); + err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec); if (err) { - pr_warn("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n", - prog_name, relo_idx, local_id, local_name, spec_str, - err); + pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n", + prog_name, relo_idx, local_id, btf_kind_str(local_type), + str_is_empty(local_name) ? "<anon>" : local_name, + spec_str, err); return -EINVAL; } - pr_debug("prog '%s': relo #%d: kind %d, spec is ", prog_name, relo_idx, - relo->kind); + pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog_name, + relo_idx, core_relo_kind_str(relo->kind), relo->kind); bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); libbpf_print(LIBBPF_DEBUG, "\n"); + /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ + if (relo->kind == BPF_TYPE_ID_LOCAL) { + targ_res.validate = true; + targ_res.poison = false; + targ_res.orig_val = local_spec.root_type_id; + targ_res.new_val = local_spec.root_type_id; + goto patch_insn; + } + + /* libbpf doesn't support candidate search for anonymous types */ + if (str_is_empty(spec_str)) { + pr_warn("prog '%s': relo #%d: <%s> (%d) relocation doesn't support anonymous types\n", + prog_name, relo_idx, core_relo_kind_str(relo->kind), relo->kind); + return -EOPNOTSUPP; + } + if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) { cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf); if (IS_ERR(cand_ids)) { - pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld", - prog_name, relo_idx, local_id, local_name, - PTR_ERR(cand_ids)); + pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld", + prog_name, relo_idx, local_id, btf_kind_str(local_type), + local_name, PTR_ERR(cand_ids)); return PTR_ERR(cand_ids); } err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL); @@ -4873,36 +5463,51 @@ static int bpf_core_reloc_field(struct bpf_program *prog, for (i = 0, j = 0; i < cand_ids->len; i++) { cand_id = cand_ids->data[i]; - cand_type = btf__type_by_id(targ_btf, cand_id); - cand_name = btf__name_by_offset(targ_btf, cand_type->name_off); - - err = bpf_core_spec_match(&local_spec, targ_btf, - cand_id, &cand_spec); - pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ", - prog_name, relo_idx, i, cand_name); - bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); - libbpf_print(LIBBPF_DEBUG, ": %d\n", err); + err = bpf_core_spec_match(&local_spec, targ_btf, cand_id, &cand_spec); if (err < 0) { - pr_warn("prog '%s': relo #%d: matching error: %d\n", - prog_name, relo_idx, err); + pr_warn("prog '%s': relo #%d: error matching candidate #%d ", + prog_name, relo_idx, i); + bpf_core_dump_spec(LIBBPF_WARN, &cand_spec); + libbpf_print(LIBBPF_WARN, ": %d\n", err); return err; } + + pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog_name, + relo_idx, err == 0 ? "non-matching" : "matching", i); + bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + libbpf_print(LIBBPF_DEBUG, "\n"); + if (err == 0) continue; + err = bpf_core_calc_relo(prog, relo, relo_idx, &local_spec, &cand_spec, &cand_res); + if (err) + return err; + if (j == 0) { + targ_res = cand_res; targ_spec = cand_spec; } else if (cand_spec.bit_offset != targ_spec.bit_offset) { - /* if there are many candidates, they should all - * resolve to the same bit offset + /* if there are many field relo candidates, they + * should all resolve to the same bit offset */ - pr_warn("prog '%s': relo #%d: offset ambiguity: %u != %u\n", + pr_warn("prog '%s': relo #%d: field offset ambiguity: %u != %u\n", prog_name, relo_idx, cand_spec.bit_offset, targ_spec.bit_offset); return -EINVAL; + } else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) { + /* all candidates should result in the same relocation + * decision and value, otherwise it's dangerous to + * proceed due to ambiguity + */ + pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %u != %s %u\n", + prog_name, relo_idx, + cand_res.poison ? "failure" : "success", cand_res.new_val, + targ_res.poison ? "failure" : "success", targ_res.new_val); + return -EINVAL; } - cand_ids->data[j++] = cand_spec.spec[0].type_id; + cand_ids->data[j++] = cand_spec.root_type_id; } /* @@ -4921,19 +5526,25 @@ static int bpf_core_reloc_field(struct bpf_program *prog, * as well as expected case, depending whether instruction w/ * relocation is guarded in some way that makes it unreachable (dead * code) if relocation can't be resolved. This is handled in - * bpf_core_reloc_insn() uniformly by replacing that instruction with + * bpf_core_patch_insn() uniformly by replacing that instruction with * BPF helper call insn (using invalid helper ID). If that instruction * is indeed unreachable, then it will be ignored and eliminated by * verifier. If it was an error, then verifier will complain and point * to a specific instruction number in its log. */ - if (j == 0) - pr_debug("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", - prog_name, relo_idx, local_id, local_name, spec_str); + if (j == 0) { + pr_debug("prog '%s': relo #%d: no matching targets found\n", + prog_name, relo_idx); - /* bpf_core_reloc_insn should know how to handle missing targ_spec */ - err = bpf_core_reloc_insn(prog, relo, relo_idx, &local_spec, - j ? &targ_spec : NULL); + /* calculate single target relo result explicitly */ + err = bpf_core_calc_relo(prog, relo, relo_idx, &local_spec, NULL, &targ_res); + if (err) + return err; + } + +patch_insn: + /* bpf_core_patch_insn() should know how to handle missing targ_spec */ + err = bpf_core_patch_insn(prog, relo, relo_idx, &targ_res); if (err) { pr_warn("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n", prog_name, relo_idx, relo->insn_off, err); @@ -4944,10 +5555,10 @@ static int bpf_core_reloc_field(struct bpf_program *prog, } static int -bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) +bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) { const struct btf_ext_info_sec *sec; - const struct bpf_field_reloc *rec; + const struct bpf_core_relo *rec; const struct btf_ext_info *seg; struct hashmap_entry *entry; struct hashmap *cand_cache = NULL; @@ -4956,6 +5567,9 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) const char *sec_name; int i, err = 0; + if (obj->btf_ext->core_relo_info.len == 0) + return 0; + if (targ_btf_path) targ_btf = btf__parse_elf(targ_btf_path, NULL); else @@ -4971,7 +5585,7 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) goto out; } - seg = &obj->btf_ext->field_reloc_info; + seg = &obj->btf_ext->core_relo_info; for_each_btf_ext_sec(seg, sec) { sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); if (str_is_empty(sec_name)) { @@ -4992,15 +5606,15 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) goto out; } - pr_debug("prog '%s': performing %d CO-RE offset relocs\n", + pr_debug("sec '%s': found %d CO-RE relocations\n", sec_name, sec->num_info); for_each_btf_ext_rec(seg, sec, i, rec) { - err = bpf_core_reloc_field(prog, rec, i, obj->btf, - targ_btf, cand_cache); + err = bpf_core_apply_relo(prog, rec, i, obj->btf, + targ_btf, cand_cache); if (err) { pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", - sec_name, i, err); + prog->name, i, err); goto out; } } @@ -5020,17 +5634,6 @@ out: } static int -bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) -{ - int err = 0; - - if (obj->btf_ext->field_reloc_info.len) - err = bpf_core_reloc_fields(obj, targ_btf_path); - - return err; -} - -static int bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, struct reloc_desc *relo) { @@ -5046,7 +5649,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, return -LIBBPF_ERRNO__RELOC; } new_cnt = prog->insns_cnt + text->insns_cnt; - new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn)); + new_insn = libbpf_reallocarray(prog->insns, new_cnt, sizeof(*insn)); if (!new_insn) { pr_warn("oom in prog realloc\n"); return -ENOMEM; @@ -5131,7 +5734,8 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return err; break; default: - pr_warn("relo #%d: bad relo type %d\n", i, relo->type); + pr_warn("prog '%s': relo #%d: bad relo type %d\n", + prog->name, i, relo->type); return -EINVAL; } } @@ -5166,7 +5770,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) err = bpf_program__relocate(prog, obj); if (err) { - pr_warn("failed to relocate '%s'\n", prog->section_name); + pr_warn("prog '%s': failed to relocate data references: %d\n", + prog->name, err); return err; } break; @@ -5181,7 +5786,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) err = bpf_program__relocate(prog, obj); if (err) { - pr_warn("failed to relocate '%s'\n", prog->section_name); + pr_warn("prog '%s': failed to relocate calls: %d\n", + prog->name, err); return err; } } @@ -5194,7 +5800,8 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, static int bpf_object__collect_map_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data *data) { - int i, j, nrels, new_sz, ptr_sz = sizeof(void *); + const int bpf_ptr_sz = 8, host_ptr_sz = sizeof(void *); + int i, j, nrels, new_sz; const struct btf_var_secinfo *vi = NULL; const struct btf_type *sec, *var, *def; const struct btf_member *member; @@ -5224,8 +5831,7 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, i, (size_t)GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; } - name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, - sym.st_name) ? : "<?>"; + name = elf_sym_str(obj, sym.st_name) ?: "<?>"; if (sym.st_shndx != obj->efile.btf_maps_shndx) { pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", i, name); @@ -5243,7 +5849,7 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, vi = btf_var_secinfos(sec) + map->btf_var_idx; if (vi->offset <= rel.r_offset && - rel.r_offset + sizeof(void *) <= vi->offset + vi->size) + rel.r_offset + bpf_ptr_sz <= vi->offset + vi->size) break; } if (j == obj->nr_maps) { @@ -5279,17 +5885,20 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, return -EINVAL; moff = rel.r_offset - vi->offset - moff; - if (moff % ptr_sz) + /* here we use BPF pointer size, which is always 64 bit, as we + * are parsing ELF that was built for BPF target + */ + if (moff % bpf_ptr_sz) return -EINVAL; - moff /= ptr_sz; + moff /= bpf_ptr_sz; if (moff >= map->init_slots_sz) { new_sz = moff + 1; - tmp = realloc(map->init_slots, new_sz * ptr_sz); + tmp = libbpf_reallocarray(map->init_slots, new_sz, host_ptr_sz); if (!tmp) return -ENOMEM; map->init_slots = tmp; memset(map->init_slots + map->init_slots_sz, 0, - (new_sz - map->init_slots_sz) * ptr_sz); + (new_sz - map->init_slots_sz) * host_ptr_sz); map->init_slots_sz = new_sz; } map->init_slots[moff] = targ_map; @@ -5339,6 +5948,51 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) return 0; } +static bool insn_is_helper_call(struct bpf_insn *insn, enum bpf_func_id *func_id) +{ + if (BPF_CLASS(insn->code) == BPF_JMP && + BPF_OP(insn->code) == BPF_CALL && + BPF_SRC(insn->code) == BPF_K && + insn->src_reg == 0 && + insn->dst_reg == 0) { + *func_id = insn->imm; + return true; + } + return false; +} + +static int bpf_object__sanitize_prog(struct bpf_object* obj, struct bpf_program *prog) +{ + struct bpf_insn *insn = prog->insns; + enum bpf_func_id func_id; + int i; + + for (i = 0; i < prog->insns_cnt; i++, insn++) { + if (!insn_is_helper_call(insn, &func_id)) + continue; + + /* on kernels that don't yet support + * bpf_probe_read_{kernel,user}[_str] helpers, fall back + * to bpf_probe_read() which works well for old kernels + */ + switch (func_id) { + case BPF_FUNC_probe_read_kernel: + case BPF_FUNC_probe_read_user: + if (!kernel_supports(FEAT_PROBE_READ_KERN)) + insn->imm = BPF_FUNC_probe_read; + break; + case BPF_FUNC_probe_read_kernel_str: + case BPF_FUNC_probe_read_user_str: + if (!kernel_supports(FEAT_PROBE_READ_KERN)) + insn->imm = BPF_FUNC_probe_read_str; + break; + default: + break; + } + } + return 0; +} + static int load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *license, __u32 kern_version, int *pfd) @@ -5355,12 +6009,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = prog->type; /* old kernels might not support specifying expected_attach_type */ - if (!prog->caps->exp_attach_type && prog->sec_def && + if (!kernel_supports(FEAT_EXP_ATTACH_TYPE) && prog->sec_def && prog->sec_def->is_exp_attach_type_optional) load_attr.expected_attach_type = 0; else load_attr.expected_attach_type = prog->expected_attach_type; - if (prog->caps->name) + if (kernel_supports(FEAT_PROG_NAME)) load_attr.name = prog->name; load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; @@ -5378,7 +6032,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, } /* specify func_info/line_info only if kernel supports them */ btf_fd = bpf_object__btf_fd(prog->obj); - if (btf_fd >= 0 && prog->obj->caps.btf_func) { + if (btf_fd >= 0 && kernel_supports(FEAT_BTF_FUNC)) { load_attr.prog_btf_fd = btf_fd; load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; @@ -5416,7 +6070,7 @@ retry_load: free(log_buf); goto retry_load; } - ret = -errno; + ret = errno ? -errno : -LIBBPF_ERRNO__LOAD; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warn("load bpf program failed: %s\n", cp); pr_perm_msg(ret); @@ -5555,11 +6209,17 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; + err = bpf_object__sanitize_prog(obj, prog); + if (err) + return err; + } + + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; if (bpf_program__is_function_storage(prog, obj)) continue; if (!prog->load) { - pr_debug("prog '%s'('%s'): skipped loading\n", - prog->name, prog->section_name); + pr_debug("prog '%s': skipped loading\n", prog->name); continue; } prog->log_level |= log_level; @@ -5632,6 +6292,8 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, /* couldn't guess, but user might manually specify */ continue; + if (prog->sec_def->is_sleepable) + prog->prog_flags |= BPF_F_SLEEPABLE; bpf_program__set_type(prog, prog->sec_def->prog_type); bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type); @@ -5741,11 +6403,11 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) bpf_object__for_each_map(m, obj) { if (!bpf_map__is_internal(m)) continue; - if (!obj->caps.global_data) { + if (!kernel_supports(FEAT_GLOBAL_DATA)) { pr_warn("kernel doesn't support global data\n"); return -ENOTSUP; } - if (!obj->caps.array_mmap) + if (!kernel_supports(FEAT_ARRAY_MMAP)) m->def.map_flags ^= BPF_F_MMAPABLE; } @@ -5895,7 +6557,6 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) } err = bpf_object__probe_loading(obj); - err = err ? : bpf_object__probe_caps(obj); err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); err = err ? : bpf_object__sanitize_and_load_btf(obj); err = err ? : bpf_object__sanitize_maps(obj); @@ -6012,9 +6673,10 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, } if (bpf_obj_pin(prog->instances.fds[instance], path)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("failed to pin program: %s\n", cp); - return -errno; + return err; } pr_debug("pinned program '%s'\n", path); @@ -6703,7 +7365,7 @@ int bpf_program__fd(const struct bpf_program *prog) size_t bpf_program__size(const struct bpf_program *prog) { - return prog->insns_cnt * sizeof(struct bpf_insn); + return prog->insns_cnt * BPF_INSN_SZ; } int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, @@ -6900,6 +7562,21 @@ static const struct bpf_sec_def section_defs[] = { .expected_attach_type = BPF_TRACE_FEXIT, .is_attach_btf = true, .attach_fn = attach_trace), + SEC_DEF("fentry.s/", TRACING, + .expected_attach_type = BPF_TRACE_FENTRY, + .is_attach_btf = true, + .is_sleepable = true, + .attach_fn = attach_trace), + SEC_DEF("fmod_ret.s/", TRACING, + .expected_attach_type = BPF_MODIFY_RETURN, + .is_attach_btf = true, + .is_sleepable = true, + .attach_fn = attach_trace), + SEC_DEF("fexit.s/", TRACING, + .expected_attach_type = BPF_TRACE_FEXIT, + .is_attach_btf = true, + .is_sleepable = true, + .attach_fn = attach_trace), SEC_DEF("freplace/", EXT, .is_attach_btf = true, .attach_fn = attach_trace), @@ -6907,6 +7584,11 @@ static const struct bpf_sec_def section_defs[] = { .is_attach_btf = true, .expected_attach_type = BPF_LSM_MAC, .attach_fn = attach_lsm), + SEC_DEF("lsm.s/", LSM, + .is_attach_btf = true, + .is_sleepable = true, + .expected_attach_type = BPF_LSM_MAC, + .attach_fn = attach_lsm), SEC_DEF("iter/", TRACING, .expected_attach_type = BPF_TRACE_ITER, .is_attach_btf = true, @@ -7112,8 +7794,7 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, return -LIBBPF_ERRNO__FORMAT; } - name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, - sym.st_name) ? : "<?>"; + name = elf_sym_str(obj, sym.st_name) ?: "<?>"; map = find_struct_ops_map_by_offset(obj, rel.r_offset); if (!map) { pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n", @@ -7630,7 +8311,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, prog->prog_ifindex = attr->ifindex; prog->log_level = attr->log_level; - prog->prog_flags = attr->prog_flags; + prog->prog_flags |= attr->prog_flags; if (!first_prog) first_prog = prog; } @@ -8584,7 +9265,7 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, struct perf_buffer_params p = {}; struct perf_event_attr attr = { 0, }; - attr.config = PERF_COUNT_SW_BPF_OUTPUT, + attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; attr.sample_type = PERF_SAMPLE_RAW; attr.sample_period = 1; @@ -8822,6 +9503,11 @@ static int perf_buffer__process_records(struct perf_buffer *pb, return 0; } +int perf_buffer__epoll_fd(const struct perf_buffer *pb) +{ + return pb->epoll_fd; +} + int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) { int i, cnt, err; @@ -8839,6 +9525,55 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) return cnt < 0 ? -errno : cnt; } +/* Return number of PERF_EVENT_ARRAY map slots set up by this perf_buffer + * manager. + */ +size_t perf_buffer__buffer_cnt(const struct perf_buffer *pb) +{ + return pb->cpu_cnt; +} + +/* + * Return perf_event FD of a ring buffer in *buf_idx* slot of + * PERF_EVENT_ARRAY BPF map. This FD can be polled for new data using + * select()/poll()/epoll() Linux syscalls. + */ +int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx) +{ + struct perf_cpu_buf *cpu_buf; + + if (buf_idx >= pb->cpu_cnt) + return -EINVAL; + + cpu_buf = pb->cpu_bufs[buf_idx]; + if (!cpu_buf) + return -ENOENT; + + return cpu_buf->fd; +} + +/* + * Consume data from perf ring buffer corresponding to slot *buf_idx* in + * PERF_EVENT_ARRAY BPF map without waiting/polling. If there is no data to + * consume, do nothing and return success. + * Returns: + * - 0 on success; + * - <0 on failure. + */ +int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx) +{ + struct perf_cpu_buf *cpu_buf; + + if (buf_idx >= pb->cpu_cnt) + return -EINVAL; + + cpu_buf = pb->cpu_bufs[buf_idx]; + if (!cpu_buf) + return -ENOENT; + + return perf_buffer__process_records(pb, cpu_buf); +} + int perf_buffer__consume(struct perf_buffer *pb) { int i, err; @@ -8851,7 +9586,7 @@ int perf_buffer__consume(struct perf_buffer *pb) err = perf_buffer__process_records(pb, cpu_buf); if (err) { - pr_warn("error while processing records: %d\n", err); + pr_warn("perf_buffer: failed to process records in buffer #%d: %d\n", i, err); return err; } } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 5ecb4069a9f0..308e0ded8f14 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -588,8 +588,12 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt, const struct perf_buffer_raw_opts *opts); LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); +LIBBPF_API int perf_buffer__epoll_fd(const struct perf_buffer *pb); LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms); LIBBPF_API int perf_buffer__consume(struct perf_buffer *pb); +LIBBPF_API int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx); +LIBBPF_API size_t perf_buffer__buffer_cnt(const struct perf_buffer *pb); +LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx); typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 0c4722bfdd0a..3fedcdc4ae2f 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -295,5 +295,16 @@ LIBBPF_0.1.0 { bpf_program__set_sk_lookup; btf__parse; btf__parse_raw; + btf__pointer_size; btf__set_fd; + btf__set_pointer_size; } LIBBPF_0.0.9; + +LIBBPF_0.2.0 { + global: + perf_buffer__buffer_cnt; + perf_buffer__buffer_fd; + perf_buffer__epoll_fd; + perf_buffer__consume_buffer; + xsk_socket__create_shared; +} LIBBPF_0.1.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 50d70e90d5f1..4d1c366fca2c 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -9,6 +9,15 @@ #ifndef __LIBBPF_LIBBPF_INTERNAL_H #define __LIBBPF_LIBBPF_INTERNAL_H +#include <stdlib.h> +#include <limits.h> + +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +/* prevent accidental re-addition of reallocarray() */ +#pragma GCC poison reallocarray + #include "libbpf.h" #define BTF_INFO_ENC(kind, kind_flag, vlen) \ @@ -23,6 +32,12 @@ #define BTF_PARAM_ENC(name, type) (name), (type) #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) +#ifndef likely +#define likely(x) __builtin_expect(!!(x), 1) +#endif +#ifndef unlikely +#define unlikely(x) __builtin_expect(!!(x), 0) +#endif #ifndef min # define min(x, y) ((x) < (y) ? (x) : (y)) #endif @@ -63,6 +78,33 @@ do { \ #define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) #define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) +#ifndef __has_builtin +#define __has_builtin(x) 0 +#endif +/* + * Re-implement glibc's reallocarray() for libbpf internal-only use. + * reallocarray(), unfortunately, is not available in all versions of glibc, + * so requires extra feature detection and using reallocarray() stub from + * <tools/libc_compat.h> and COMPAT_NEED_REALLOCARRAY. All this complicates + * build of libbpf unnecessarily and is just a maintenance burden. Instead, + * it's trivial to implement libbpf-specific internal version and use it + * throughout libbpf. + */ +static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size) +{ + size_t total; + +#if __has_builtin(__builtin_mul_overflow) + if (unlikely(__builtin_mul_overflow(nmemb, size, &total))) + return NULL; +#else + if (size == 0 || nmemb > ULONG_MAX / size) + return NULL; + total = nmemb * size; +#endif + return realloc(ptr, total); +} + static inline bool libbpf_validate_opts(const char *opts, size_t opts_sz, size_t user_sz, const char *type_name) @@ -105,18 +147,6 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name, int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, __u32 *off); -struct nlattr; -typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); -int libbpf_netlink_open(unsigned int *nl_pid); -int libbpf_nl_get_link(int sock, unsigned int nl_pid, - libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); -int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); -int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); -int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, - libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); - struct btf_ext_info { /* * info points to the individual info section (e.g. func_info and @@ -138,6 +168,44 @@ struct btf_ext_info { i < (sec)->num_info; \ i++, rec = (void *)rec + (seg)->rec_size) +/* + * The .BTF.ext ELF section layout defined as + * struct btf_ext_header + * func_info subsection + * + * The func_info subsection layout: + * record size for struct bpf_func_info in the func_info subsection + * struct btf_sec_func_info for section #1 + * a list of bpf_func_info records for section #1 + * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h + * but may not be identical + * struct btf_sec_func_info for section #2 + * a list of bpf_func_info records for section #2 + * ...... + * + * Note that the bpf_func_info record size in .BTF.ext may not + * be the same as the one defined in include/uapi/linux/bpf.h. + * The loader should ensure that record_size meets minimum + * requirement and pass the record as is to the kernel. The + * kernel will handle the func_info properly based on its contents. + */ +struct btf_ext_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 func_info_off; + __u32 func_info_len; + __u32 line_info_off; + __u32 line_info_len; + + /* optional part of .BTF.ext header */ + __u32 core_relo_off; + __u32 core_relo_len; +}; + struct btf_ext { union { struct btf_ext_header *hdr; @@ -145,7 +213,7 @@ struct btf_ext { }; struct btf_ext_info func_info; struct btf_ext_info line_info; - struct btf_ext_info field_reloc_info; + struct btf_ext_info core_relo_info; __u32 data_size; }; @@ -170,32 +238,40 @@ struct bpf_line_info_min { __u32 line_col; }; -/* bpf_field_info_kind encodes which aspect of captured field has to be - * adjusted by relocations. Currently supported values are: - * - BPF_FIELD_BYTE_OFFSET: field offset (in bytes); - * - BPF_FIELD_EXISTS: field existence (1, if field exists; 0, otherwise); +/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value + * has to be adjusted by relocations. */ -enum bpf_field_info_kind { +enum bpf_core_relo_kind { BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ - BPF_FIELD_BYTE_SIZE = 1, + BPF_FIELD_BYTE_SIZE = 1, /* field size in bytes */ BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ - BPF_FIELD_SIGNED = 3, - BPF_FIELD_LSHIFT_U64 = 4, - BPF_FIELD_RSHIFT_U64 = 5, + BPF_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ + BPF_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ + BPF_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ + BPF_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ + BPF_TYPE_ID_TARGET = 7, /* type ID in target kernel */ + BPF_TYPE_EXISTS = 8, /* type existence in target kernel */ + BPF_TYPE_SIZE = 9, /* type size in bytes */ + BPF_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ + BPF_ENUMVAL_VALUE = 11, /* enum value integer value */ }; -/* The minimum bpf_field_reloc checked by the loader +/* The minimum bpf_core_relo checked by the loader * - * Field relocation captures the following data: + * CO-RE relocation captures the following data: * - insn_off - instruction offset (in bytes) within a BPF program that needs * its insn->imm field to be relocated with actual field info; * - type_id - BTF type ID of the "root" (containing) entity of a relocatable - * field; + * type or field; * - access_str_off - offset into corresponding .BTF string section. String - * itself encodes an accessed field using a sequence of field and array - * indicies, separated by colon (:). It's conceptually very close to LLVM's - * getelementptr ([0]) instruction's arguments for identifying offset to - * a field. + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; * * Example to provide a better feel. * @@ -226,11 +302,11 @@ enum bpf_field_info_kind { * * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction */ -struct bpf_field_reloc { +struct bpf_core_relo { __u32 insn_off; __u32 type_id; __u32 access_str_off; - enum bpf_field_info_kind kind; + enum bpf_core_relo_kind kind; }; #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 5a3d3f078408..5482a9b7ae2d 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -17,9 +17,6 @@ #include "libbpf.h" #include "libbpf_internal.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - static bool grep(const char *buffer, const char *pattern) { return !!strstr(buffer, pattern); @@ -173,7 +170,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, return btf_fd; } -static int load_sk_storage_btf(void) +static int load_local_storage_btf(void) { const char strs[] = "\0bpf_spin_lock\0val\0cnt\0l"; /* struct bpf_spin_lock { @@ -232,12 +229,13 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) key_size = 0; break; case BPF_MAP_TYPE_SK_STORAGE: + case BPF_MAP_TYPE_INODE_STORAGE: btf_key_type_id = 1; btf_value_type_id = 3; value_size = 8; max_entries = 0; map_flags = BPF_F_NO_PREALLOC; - btf_fd = load_sk_storage_btf(); + btf_fd = load_local_storage_btf(); if (btf_fd < 0) return false; break; diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 312f887570b2..4dd73de00b6f 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -15,13 +15,12 @@ #include "libbpf_internal.h" #include "nlattr.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - #ifndef SOL_NETLINK #define SOL_NETLINK 270 #endif +typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); + typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t, void *cookie); @@ -31,7 +30,7 @@ struct xdp_id_md { struct xdp_link_info info; }; -int libbpf_netlink_open(__u32 *nl_pid) +static int libbpf_netlink_open(__u32 *nl_pid) { struct sockaddr_nl sa; socklen_t addrlen; @@ -283,6 +282,9 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } +static int libbpf_nl_get_link(int sock, unsigned int nl_pid, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); + int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags) { @@ -368,121 +370,3 @@ int libbpf_nl_get_link(int sock, unsigned int nl_pid, return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, dump_link_nlmsg, cookie); } - -static int __dump_class_nlmsg(struct nlmsghdr *nlh, - libbpf_dump_nlmsg_t dump_class_nlmsg, - void *cookie) -{ - struct nlattr *tb[TCA_MAX + 1], *attr; - struct tcmsg *t = NLMSG_DATA(nlh); - int len; - - len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); - attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); - if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) - return -LIBBPF_ERRNO__NLPARSE; - - return dump_class_nlmsg(cookie, t, tb); -} - -int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie) -{ - struct { - struct nlmsghdr nlh; - struct tcmsg t; - } req = { - .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), - .nlh.nlmsg_type = RTM_GETTCLASS, - .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, - .t.tcm_family = AF_UNSPEC, - .t.tcm_ifindex = ifindex, - }; - int seq = time(NULL); - - req.nlh.nlmsg_seq = seq; - if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) - return -errno; - - return bpf_netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg, - dump_class_nlmsg, cookie); -} - -static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh, - libbpf_dump_nlmsg_t dump_qdisc_nlmsg, - void *cookie) -{ - struct nlattr *tb[TCA_MAX + 1], *attr; - struct tcmsg *t = NLMSG_DATA(nlh); - int len; - - len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); - attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); - if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) - return -LIBBPF_ERRNO__NLPARSE; - - return dump_qdisc_nlmsg(cookie, t, tb); -} - -int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie) -{ - struct { - struct nlmsghdr nlh; - struct tcmsg t; - } req = { - .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), - .nlh.nlmsg_type = RTM_GETQDISC, - .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, - .t.tcm_family = AF_UNSPEC, - .t.tcm_ifindex = ifindex, - }; - int seq = time(NULL); - - req.nlh.nlmsg_seq = seq; - if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) - return -errno; - - return bpf_netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg, - dump_qdisc_nlmsg, cookie); -} - -static int __dump_filter_nlmsg(struct nlmsghdr *nlh, - libbpf_dump_nlmsg_t dump_filter_nlmsg, - void *cookie) -{ - struct nlattr *tb[TCA_MAX + 1], *attr; - struct tcmsg *t = NLMSG_DATA(nlh); - int len; - - len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); - attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); - if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) - return -LIBBPF_ERRNO__NLPARSE; - - return dump_filter_nlmsg(cookie, t, tb); -} - -int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, - libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie) -{ - struct { - struct nlmsghdr nlh; - struct tcmsg t; - } req = { - .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), - .nlh.nlmsg_type = RTM_GETTFILTER, - .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, - .t.tcm_family = AF_UNSPEC, - .t.tcm_ifindex = ifindex, - .t.tcm_parent = handle, - }; - int seq = time(NULL); - - req.nlh.nlmsg_seq = seq; - if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) - return -errno; - - return bpf_netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg, - dump_filter_nlmsg, cookie); -} diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 0ad41dfea8eb..b607fa9852b1 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -7,14 +7,11 @@ */ #include <errno.h> -#include "nlattr.h" -#include "libbpf_internal.h" -#include <linux/rtnetlink.h> #include <string.h> #include <stdio.h> - -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 +#include <linux/rtnetlink.h> +#include "nlattr.h" +#include "libbpf_internal.h" static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = { [LIBBPF_NLA_U8] = sizeof(uint8_t), diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 4fc6c6cbb4eb..5c6522c89af1 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -16,15 +16,11 @@ #include <asm/barrier.h> #include <sys/mman.h> #include <sys/epoll.h> -#include <tools/libc_compat.h> #include "libbpf.h" #include "libbpf_internal.h" #include "bpf.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - struct ring { ring_buffer_sample_fn sample_cb; void *ctx; @@ -82,12 +78,12 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, return -EINVAL; } - tmp = reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings)); + tmp = libbpf_reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings)); if (!tmp) return -ENOMEM; rb->rings = tmp; - tmp = reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events)); + tmp = libbpf_reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events)); if (!tmp) return -ENOMEM; rb->events = tmp; diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index f7f4efb70a4c..49c324594792 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -20,6 +20,7 @@ #include <linux/if_ether.h> #include <linux/if_packet.h> #include <linux/if_xdp.h> +#include <linux/list.h> #include <linux/sockios.h> #include <net/if.h> #include <sys/ioctl.h> @@ -32,9 +33,6 @@ #include "libbpf_internal.h" #include "xsk.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - #ifndef SOL_XDP #define SOL_XDP 283 #endif @@ -48,26 +46,35 @@ #endif struct xsk_umem { - struct xsk_ring_prod *fill; - struct xsk_ring_cons *comp; + struct xsk_ring_prod *fill_save; + struct xsk_ring_cons *comp_save; char *umem_area; struct xsk_umem_config config; int fd; int refcount; + struct list_head ctx_list; +}; + +struct xsk_ctx { + struct xsk_ring_prod *fill; + struct xsk_ring_cons *comp; + __u32 queue_id; + struct xsk_umem *umem; + int refcount; + int ifindex; + struct list_head list; + int prog_fd; + int xsks_map_fd; + char ifname[IFNAMSIZ]; }; struct xsk_socket { struct xsk_ring_cons *rx; struct xsk_ring_prod *tx; __u64 outstanding_tx; - struct xsk_umem *umem; + struct xsk_ctx *ctx; struct xsk_socket_config config; int fd; - int ifindex; - int prog_fd; - int xsks_map_fd; - __u32 queue_id; - char ifname[IFNAMSIZ]; }; struct xsk_nl_info { @@ -203,15 +210,73 @@ static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off) return -EINVAL; } +static int xsk_create_umem_rings(struct xsk_umem *umem, int fd, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp) +{ + struct xdp_mmap_offsets off; + void *map; + int err; + + err = setsockopt(fd, SOL_XDP, XDP_UMEM_FILL_RING, + &umem->config.fill_size, + sizeof(umem->config.fill_size)); + if (err) + return -errno; + + err = setsockopt(fd, SOL_XDP, XDP_UMEM_COMPLETION_RING, + &umem->config.comp_size, + sizeof(umem->config.comp_size)); + if (err) + return -errno; + + err = xsk_get_mmap_offsets(fd, &off); + if (err) + return -errno; + + map = mmap(NULL, off.fr.desc + umem->config.fill_size * sizeof(__u64), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, + XDP_UMEM_PGOFF_FILL_RING); + if (map == MAP_FAILED) + return -errno; + + fill->mask = umem->config.fill_size - 1; + fill->size = umem->config.fill_size; + fill->producer = map + off.fr.producer; + fill->consumer = map + off.fr.consumer; + fill->flags = map + off.fr.flags; + fill->ring = map + off.fr.desc; + fill->cached_cons = umem->config.fill_size; + + map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, + XDP_UMEM_PGOFF_COMPLETION_RING); + if (map == MAP_FAILED) { + err = -errno; + goto out_mmap; + } + + comp->mask = umem->config.comp_size - 1; + comp->size = umem->config.comp_size; + comp->producer = map + off.cr.producer; + comp->consumer = map + off.cr.consumer; + comp->flags = map + off.cr.flags; + comp->ring = map + off.cr.desc; + + return 0; + +out_mmap: + munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64)); + return err; +} + int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, const struct xsk_umem_config *usr_config) { - struct xdp_mmap_offsets off; struct xdp_umem_reg mr; struct xsk_umem *umem; - void *map; int err; if (!umem_area || !umem_ptr || !fill || !comp) @@ -230,6 +295,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, } umem->umem_area = umem_area; + INIT_LIST_HEAD(&umem->ctx_list); xsk_set_umem_config(&umem->config, usr_config); memset(&mr, 0, sizeof(mr)); @@ -244,71 +310,16 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, err = -errno; goto out_socket; } - err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_FILL_RING, - &umem->config.fill_size, - sizeof(umem->config.fill_size)); - if (err) { - err = -errno; - goto out_socket; - } - err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_COMPLETION_RING, - &umem->config.comp_size, - sizeof(umem->config.comp_size)); - if (err) { - err = -errno; - goto out_socket; - } - err = xsk_get_mmap_offsets(umem->fd, &off); - if (err) { - err = -errno; - goto out_socket; - } - - map = mmap(NULL, off.fr.desc + umem->config.fill_size * sizeof(__u64), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd, - XDP_UMEM_PGOFF_FILL_RING); - if (map == MAP_FAILED) { - err = -errno; + err = xsk_create_umem_rings(umem, umem->fd, fill, comp); + if (err) goto out_socket; - } - - umem->fill = fill; - fill->mask = umem->config.fill_size - 1; - fill->size = umem->config.fill_size; - fill->producer = map + off.fr.producer; - fill->consumer = map + off.fr.consumer; - fill->flags = map + off.fr.flags; - fill->ring = map + off.fr.desc; - fill->cached_prod = *fill->producer; - /* cached_cons is "size" bigger than the real consumer pointer - * See xsk_prod_nb_free - */ - fill->cached_cons = *fill->consumer + umem->config.fill_size; - - map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd, - XDP_UMEM_PGOFF_COMPLETION_RING); - if (map == MAP_FAILED) { - err = -errno; - goto out_mmap; - } - - umem->comp = comp; - comp->mask = umem->config.comp_size - 1; - comp->size = umem->config.comp_size; - comp->producer = map + off.cr.producer; - comp->consumer = map + off.cr.consumer; - comp->flags = map + off.cr.flags; - comp->ring = map + off.cr.desc; - comp->cached_prod = *comp->producer; - comp->cached_cons = *comp->consumer; + umem->fill_save = fill; + umem->comp_save = comp; *umem_ptr = umem; return 0; -out_mmap: - munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64)); out_socket: close(umem->fd); out_umem_alloc: @@ -342,6 +353,7 @@ DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) static int xsk_load_xdp_prog(struct xsk_socket *xsk) { static const int log_buf_size = 16 * 1024; + struct xsk_ctx *ctx = xsk->ctx; char log_buf[log_buf_size]; int err, prog_fd; @@ -369,7 +381,7 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) /* *(u32 *)(r10 - 4) = r2 */ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -4), /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), + BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), /* r3 = XDP_PASS */ BPF_MOV64_IMM(BPF_REG_3, 2), /* call bpf_redirect_map */ @@ -381,7 +393,7 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) /* r2 += -4 */ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), + BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), /* call bpf_map_lookup_elem */ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), /* r1 = r0 */ @@ -393,7 +405,7 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) /* r2 = *(u32 *)(r10 - 4) */ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_10, -4), /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), + BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), /* r3 = 0 */ BPF_MOV64_IMM(BPF_REG_3, 0), /* call bpf_redirect_map */ @@ -411,19 +423,21 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) return prog_fd; } - err = bpf_set_link_xdp_fd(xsk->ifindex, prog_fd, xsk->config.xdp_flags); + err = bpf_set_link_xdp_fd(xsk->ctx->ifindex, prog_fd, + xsk->config.xdp_flags); if (err) { close(prog_fd); return err; } - xsk->prog_fd = prog_fd; + ctx->prog_fd = prog_fd; return 0; } static int xsk_get_max_queues(struct xsk_socket *xsk) { struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + struct xsk_ctx *ctx = xsk->ctx; struct ifreq ifr = {}; int fd, err, ret; @@ -432,7 +446,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) return -errno; ifr.ifr_data = (void *)&channels; - memcpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); + memcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ - 1); ifr.ifr_name[IFNAMSIZ - 1] = '\0'; err = ioctl(fd, SIOCETHTOOL, &ifr); if (err && errno != EOPNOTSUPP) { @@ -460,6 +474,7 @@ out: static int xsk_create_bpf_maps(struct xsk_socket *xsk) { + struct xsk_ctx *ctx = xsk->ctx; int max_queues; int fd; @@ -472,15 +487,17 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk) if (fd < 0) return fd; - xsk->xsks_map_fd = fd; + ctx->xsks_map_fd = fd; return 0; } static void xsk_delete_bpf_maps(struct xsk_socket *xsk) { - bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id); - close(xsk->xsks_map_fd); + struct xsk_ctx *ctx = xsk->ctx; + + bpf_map_delete_elem(ctx->xsks_map_fd, &ctx->queue_id); + close(ctx->xsks_map_fd); } static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) @@ -488,10 +505,11 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) __u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info); __u32 map_len = sizeof(struct bpf_map_info); struct bpf_prog_info prog_info = {}; + struct xsk_ctx *ctx = xsk->ctx; struct bpf_map_info map_info; int fd, err; - err = bpf_obj_get_info_by_fd(xsk->prog_fd, &prog_info, &prog_len); + err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len); if (err) return err; @@ -505,11 +523,11 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) prog_info.nr_map_ids = num_maps; prog_info.map_ids = (__u64)(unsigned long)map_ids; - err = bpf_obj_get_info_by_fd(xsk->prog_fd, &prog_info, &prog_len); + err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len); if (err) goto out_map_ids; - xsk->xsks_map_fd = -1; + ctx->xsks_map_fd = -1; for (i = 0; i < prog_info.nr_map_ids; i++) { fd = bpf_map_get_fd_by_id(map_ids[i]); @@ -523,7 +541,7 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) } if (!strcmp(map_info.name, "xsks_map")) { - xsk->xsks_map_fd = fd; + ctx->xsks_map_fd = fd; continue; } @@ -531,7 +549,7 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) } err = 0; - if (xsk->xsks_map_fd == -1) + if (ctx->xsks_map_fd == -1) err = -ENOENT; out_map_ids: @@ -541,16 +559,19 @@ out_map_ids: static int xsk_set_bpf_maps(struct xsk_socket *xsk) { - return bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, + struct xsk_ctx *ctx = xsk->ctx; + + return bpf_map_update_elem(ctx->xsks_map_fd, &ctx->queue_id, &xsk->fd, 0); } static int xsk_setup_xdp_prog(struct xsk_socket *xsk) { + struct xsk_ctx *ctx = xsk->ctx; __u32 prog_id = 0; int err; - err = bpf_get_link_xdp_id(xsk->ifindex, &prog_id, + err = bpf_get_link_xdp_id(ctx->ifindex, &prog_id, xsk->config.xdp_flags); if (err) return err; @@ -566,12 +587,12 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) return err; } } else { - xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id); - if (xsk->prog_fd < 0) + ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (ctx->prog_fd < 0) return -errno; err = xsk_lookup_bpf_maps(xsk); if (err) { - close(xsk->prog_fd); + close(ctx->prog_fd); return err; } } @@ -580,25 +601,110 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) err = xsk_set_bpf_maps(xsk); if (err) { xsk_delete_bpf_maps(xsk); - close(xsk->prog_fd); + close(ctx->prog_fd); return err; } return 0; } -int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, - __u32 queue_id, struct xsk_umem *umem, - struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, - const struct xsk_socket_config *usr_config) +static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex, + __u32 queue_id) +{ + struct xsk_ctx *ctx; + + if (list_empty(&umem->ctx_list)) + return NULL; + + list_for_each_entry(ctx, &umem->ctx_list, list) { + if (ctx->ifindex == ifindex && ctx->queue_id == queue_id) { + ctx->refcount++; + return ctx; + } + } + + return NULL; +} + +static void xsk_put_ctx(struct xsk_ctx *ctx) +{ + struct xsk_umem *umem = ctx->umem; + struct xdp_mmap_offsets off; + int err; + + if (--ctx->refcount == 0) { + err = xsk_get_mmap_offsets(umem->fd, &off); + if (!err) { + munmap(ctx->fill->ring - off.fr.desc, + off.fr.desc + umem->config.fill_size * + sizeof(__u64)); + munmap(ctx->comp->ring - off.cr.desc, + off.cr.desc + umem->config.comp_size * + sizeof(__u64)); + } + + list_del(&ctx->list); + free(ctx); + } +} + +static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk, + struct xsk_umem *umem, int ifindex, + const char *ifname, __u32 queue_id, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp) +{ + struct xsk_ctx *ctx; + int err; + + ctx = calloc(1, sizeof(*ctx)); + if (!ctx) + return NULL; + + if (!umem->fill_save) { + err = xsk_create_umem_rings(umem, xsk->fd, fill, comp); + if (err) { + free(ctx); + return NULL; + } + } else if (umem->fill_save != fill || umem->comp_save != comp) { + /* Copy over rings to new structs. */ + memcpy(fill, umem->fill_save, sizeof(*fill)); + memcpy(comp, umem->comp_save, sizeof(*comp)); + } + + ctx->ifindex = ifindex; + ctx->refcount = 1; + ctx->umem = umem; + ctx->queue_id = queue_id; + memcpy(ctx->ifname, ifname, IFNAMSIZ - 1); + ctx->ifname[IFNAMSIZ - 1] = '\0'; + + umem->fill_save = NULL; + umem->comp_save = NULL; + ctx->fill = fill; + ctx->comp = comp; + list_add(&ctx->list, &umem->ctx_list); + return ctx; +} + +int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, + const char *ifname, + __u32 queue_id, struct xsk_umem *umem, + struct xsk_ring_cons *rx, + struct xsk_ring_prod *tx, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_socket_config *usr_config) { void *rx_map = NULL, *tx_map = NULL; struct sockaddr_xdp sxdp = {}; struct xdp_mmap_offsets off; struct xsk_socket *xsk; - int err; + struct xsk_ctx *ctx; + int err, ifindex; - if (!umem || !xsk_ptr || !(rx || tx)) + if (!umem || !xsk_ptr || !(rx || tx) || !fill || !comp) return -EFAULT; xsk = calloc(1, sizeof(*xsk)); @@ -609,10 +715,10 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, if (err) goto out_xsk_alloc; - if (umem->refcount && - !(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { - pr_warn("Error: shared umems not supported by libbpf supplied XDP program.\n"); - err = -EBUSY; + xsk->outstanding_tx = 0; + ifindex = if_nametoindex(ifname); + if (!ifindex) { + err = -errno; goto out_xsk_alloc; } @@ -626,16 +732,16 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, xsk->fd = umem->fd; } - xsk->outstanding_tx = 0; - xsk->queue_id = queue_id; - xsk->umem = umem; - xsk->ifindex = if_nametoindex(ifname); - if (!xsk->ifindex) { - err = -errno; - goto out_socket; + ctx = xsk_get_ctx(umem, ifindex, queue_id); + if (!ctx) { + ctx = xsk_create_ctx(xsk, umem, ifindex, ifname, queue_id, + fill, comp); + if (!ctx) { + err = -ENOMEM; + goto out_socket; + } } - memcpy(xsk->ifname, ifname, IFNAMSIZ - 1); - xsk->ifname[IFNAMSIZ - 1] = '\0'; + xsk->ctx = ctx; if (rx) { err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING, @@ -643,7 +749,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, sizeof(xsk->config.rx_size)); if (err) { err = -errno; - goto out_socket; + goto out_put_ctx; } } if (tx) { @@ -652,14 +758,14 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, sizeof(xsk->config.tx_size)); if (err) { err = -errno; - goto out_socket; + goto out_put_ctx; } } err = xsk_get_mmap_offsets(xsk->fd, &off); if (err) { err = -errno; - goto out_socket; + goto out_put_ctx; } if (rx) { @@ -669,7 +775,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, xsk->fd, XDP_PGOFF_RX_RING); if (rx_map == MAP_FAILED) { err = -errno; - goto out_socket; + goto out_put_ctx; } rx->mask = xsk->config.rx_size - 1; @@ -708,10 +814,10 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, xsk->tx = tx; sxdp.sxdp_family = PF_XDP; - sxdp.sxdp_ifindex = xsk->ifindex; - sxdp.sxdp_queue_id = xsk->queue_id; + sxdp.sxdp_ifindex = ctx->ifindex; + sxdp.sxdp_queue_id = ctx->queue_id; if (umem->refcount > 1) { - sxdp.sxdp_flags = XDP_SHARED_UMEM; + sxdp.sxdp_flags |= XDP_SHARED_UMEM; sxdp.sxdp_shared_umem_fd = umem->fd; } else { sxdp.sxdp_flags = xsk->config.bind_flags; @@ -723,7 +829,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, goto out_mmap_tx; } - xsk->prog_fd = -1; + ctx->prog_fd = -1; if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { err = xsk_setup_xdp_prog(xsk); @@ -742,6 +848,8 @@ out_mmap_rx: if (rx) munmap(rx_map, off.rx.desc + xsk->config.rx_size * sizeof(struct xdp_desc)); +out_put_ctx: + xsk_put_ctx(ctx); out_socket: if (--umem->refcount) close(xsk->fd); @@ -750,25 +858,24 @@ out_xsk_alloc: return err; } -int xsk_umem__delete(struct xsk_umem *umem) +int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, + __u32 queue_id, struct xsk_umem *umem, + struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, + const struct xsk_socket_config *usr_config) { - struct xdp_mmap_offsets off; - int err; + return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem, + rx, tx, umem->fill_save, + umem->comp_save, usr_config); +} +int xsk_umem__delete(struct xsk_umem *umem) +{ if (!umem) return 0; if (umem->refcount) return -EBUSY; - err = xsk_get_mmap_offsets(umem->fd, &off); - if (!err) { - munmap(umem->fill->ring - off.fr.desc, - off.fr.desc + umem->config.fill_size * sizeof(__u64)); - munmap(umem->comp->ring - off.cr.desc, - off.cr.desc + umem->config.comp_size * sizeof(__u64)); - } - close(umem->fd); free(umem); @@ -778,15 +885,16 @@ int xsk_umem__delete(struct xsk_umem *umem) void xsk_socket__delete(struct xsk_socket *xsk) { size_t desc_sz = sizeof(struct xdp_desc); + struct xsk_ctx *ctx = xsk->ctx; struct xdp_mmap_offsets off; int err; if (!xsk) return; - if (xsk->prog_fd != -1) { + if (ctx->prog_fd != -1) { xsk_delete_bpf_maps(xsk); - close(xsk->prog_fd); + close(ctx->prog_fd); } err = xsk_get_mmap_offsets(xsk->fd, &off); @@ -799,14 +907,15 @@ void xsk_socket__delete(struct xsk_socket *xsk) munmap(xsk->tx->ring - off.tx.desc, off.tx.desc + xsk->config.tx_size * desc_sz); } - } - xsk->umem->refcount--; + xsk_put_ctx(ctx); + + ctx->umem->refcount--; /* Do not close an fd that also has an associated umem connected * to it. */ - if (xsk->fd != xsk->umem->fd) + if (xsk->fd != ctx->umem->fd) close(xsk->fd); free(xsk); } diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index 584f6820a639..1069c46364ff 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -234,6 +234,15 @@ LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk, struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, const struct xsk_socket_config *config); +LIBBPF_API int +xsk_socket__create_shared(struct xsk_socket **xsk_ptr, + const char *ifname, + __u32 queue_id, struct xsk_umem *umem, + struct xsk_ring_cons *rx, + struct xsk_ring_prod *tx, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_socket_config *config); /* Returns 0 for success and -EBUSY if the umem is still in use. */ LIBBPF_API int xsk_umem__delete(struct xsk_umem *umem); diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 3ba566de821c..5acc18b32606 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -5259,7 +5259,7 @@ static int print_arg_pointer(struct trace_seq *s, const char *format, int plen, default: ret = 0; val = eval_num_arg(data, size, event, arg); - trace_seq_printf(s, "%p", (void *)val); + trace_seq_printf(s, "%p", (void *)(intptr_t)val); break; } diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 3f72d8e261f3..bd50cdff08a8 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -33,6 +33,10 @@ OPTIONS - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. + - a symbolic or raw PMU event followed by an optional colon + and a list of event modifiers, e.g., cpu-cycles:p. See the + linkperf:perf-list[1] man page for details on event modifiers. + - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where 'param1', 'param2', etc are defined as formats for the PMU in /sys/bus/event_source/devices/<pmu>/format/*. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index c9bfefc051fb..db420dd75e43 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -39,6 +39,10 @@ report:: - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. + - a symbolic or raw PMU event followed by an optional colon + and a list of event modifiers, e.g., cpu-cycles:p. See the + linkperf:perf-list[1] man page for details on event modifiers. + - a symbolically formed event like 'pmu/param1=0x3,param2/' where param1 and param2 are defined as formats for the PMU in /sys/bus/event_source/devices/<pmu>/format/* @@ -416,6 +420,9 @@ counts for all hardware threads in a core but show the sum counts per hardware thread. This is essentially a replacement for the any bit and convenient for post processing. +--summary:: +Print summary for interval mode (-I). + EXAMPLES -------- diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 190be4fa5c21..81bb099f6f06 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -483,10 +483,6 @@ ifndef NO_LIBELF EXTLIBS += -lelf $(call detected,CONFIG_LIBELF) - ifeq ($(feature-libelf-mmap), 1) - CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT - endif - ifeq ($(feature-libelf-getphdrnum), 1) CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT endif diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c index 8d624aea1c5e..b2924e3181dc 100644 --- a/tools/perf/bench/synthesize.c +++ b/tools/perf/bench/synthesize.c @@ -162,8 +162,8 @@ static int do_run_multi_threaded(struct target *target, init_stats(&event_stats); for (i = 0; i < multi_iterations; i++) { session = perf_session__new(NULL, false, NULL); - if (!session) - return -ENOMEM; + if (IS_ERR(session)) + return PTR_ERR(session); atomic_set(&event_count, 0); gettimeofday(&start, NULL); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f91352f847c0..772f1057647f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -2452,7 +2452,7 @@ static struct option __record_options[] = { OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize, "synthesize non-sample events at the end of output"), OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"), - OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"), + OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "do not record bpf events"), OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq, "Fail if the specified frequency can't be used"), OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'", diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ece1cddfcd7c..3c74c9c0f3c3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1332,6 +1332,9 @@ int cmd_report(int argc, const char **argv) if (report.mmaps_mode) report.tasks_mode = true; + if (dump_trace) + report.tool.ordered_events = false; + if (quiet) perf_quiet_option(); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 0c7d599fa555..e6fc297cee91 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -2584,7 +2584,8 @@ static int timehist_sched_change_event(struct perf_tool *tool, } if (!sched->idle_hist || thread->tid == 0) { - timehist_update_runtime_stats(tr, t, tprev); + if (!cpu_list || test_bit(sample->cpu, cpu_bitmap)) + timehist_update_runtime_stats(tr, t, tprev); if (sched->idle_hist) { struct idle_thread_runtime *itr = (void *)tr; @@ -2857,6 +2858,9 @@ static void timehist_print_summary(struct perf_sched *sched, printf("\nIdle stats:\n"); for (i = 0; i < idle_max_cpu; ++i) { + if (cpu_list && !test_bit(i, cpu_bitmap)) + continue; + t = idle_threads[i]; if (!t) continue; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 483a28ef4ec4..fddc97cac984 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -404,7 +404,7 @@ static void read_counters(struct timespec *rs) { struct evsel *counter; - if (!stat_config.summary && (read_affinity_counters(rs) < 0)) + if (!stat_config.stop_read_counter && (read_affinity_counters(rs) < 0)) return; evlist__for_each_entry(evsel_list, counter) { @@ -897,9 +897,9 @@ try_again_reset: if (stat_config.walltime_run_table) stat_config.walltime_run[run_idx] = t1 - t0; - if (interval) { + if (interval && stat_config.summary) { stat_config.interval = 0; - stat_config.summary = true; + stat_config.stop_read_counter = true; init_stats(&walltime_nsecs_stats); update_stats(&walltime_nsecs_stats, t1 - t0); @@ -1164,6 +1164,8 @@ static struct option stat_options[] = { "Use with 'percore' event qualifier to show the event " "counts of one hardware thread by sum up total hardware " "threads of same physical core"), + OPT_BOOLEAN(0, "summary", &stat_config.summary, + "print summary for interval mode"), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 994c230027bb..7c64134472c7 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1746,6 +1746,7 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } +#ifdef HAVE_LIBBPF_SUPPORT if (!top.record_opts.no_bpf_event) { top.sb_evlist = evlist__new(); @@ -1759,6 +1760,7 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } } +#endif if (perf_evlist__start_sb_thread(top.sb_evlist, target)) { pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index fa86c5f997cc..fc9c158bfa13 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -137,7 +137,7 @@ static char *fixregex(char *s) return s; /* allocate space for a new string */ - fixed = (char *) malloc(len + 1); + fixed = (char *) malloc(len + esc_count + 1); if (!fixed) return NULL; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 5d20bf8397f0..cd77e334e577 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -197,7 +197,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), perf_mmap__read_done(&md->core); } - if (count != expect) { + if (count != expect * evlist->core.nr_entries) { pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count); goto out_delete_evlist; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 7f9f87a470c3..aae0fd9045c1 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -719,7 +719,7 @@ static int test__group2(struct evlist *evlist) TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel)); @@ -842,7 +842,7 @@ static int test__group3(struct evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel)); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index fc0838a7abc2..23db8acc492d 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -70,6 +70,9 @@ static struct pmu_event pme_test[] = { { .metric_expr = "1/m3", .metric_name = "M3", +}, +{ + .name = NULL, } }; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index be9c4c0549bc..a07626f07208 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -3629,8 +3629,8 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, { int nr_entries = evlist->core.nr_entries; -single_entry: if (perf_evlist__single_entry(evlist)) { +single_entry: { struct evsel *first = evlist__first(evlist); return perf_evsel__hists_browse(first, nr_entries, help, @@ -3638,6 +3638,7 @@ single_entry: env, warn_lost_event, annotation_opts); } + } if (symbol_conf.event_group) { struct evsel *pos; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 302a14d0aca9..93e063f22be5 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -182,15 +182,15 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) if (payload & BIT(EV_TLB_ACCESS)) decoder->record.type |= ARM_SPE_TLB_ACCESS; - if ((idx == 1 || idx == 2 || idx == 3) && + if ((idx == 2 || idx == 4 || idx == 8) && (payload & BIT(EV_LLC_MISS))) decoder->record.type |= ARM_SPE_LLC_MISS; - if ((idx == 1 || idx == 2 || idx == 3) && + if ((idx == 2 || idx == 4 || idx == 8) && (payload & BIT(EV_LLC_ACCESS))) decoder->record.type |= ARM_SPE_LLC_ACCESS; - if ((idx == 1 || idx == 2 || idx == 3) && + if ((idx == 2 || idx == 4 || idx == 8) && (payload & BIT(EV_REMOTE_ACCESS))) decoder->record.type |= ARM_SPE_REMOTE_ACCESS; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index c283223fb31f..a2a369e2fbb6 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1344,8 +1344,15 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR; } - if (etm->synth_opts.last_branch) + if (etm->synth_opts.last_branch) { attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + /* + * We don't use the hardware index, but the sample generation + * code uses the new format branch_stack with this field, + * so the event attributes must indicate that it's present. + */ + attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX; + } if (etm->synth_opts.instructions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 2a8d245351e7..0af4e81c46e2 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -3017,8 +3017,15 @@ static int intel_pt_synth_events(struct intel_pt *pt, if (pt->synth_opts.callchain) attr.sample_type |= PERF_SAMPLE_CALLCHAIN; - if (pt->synth_opts.last_branch) + if (pt->synth_opts.last_branch) { attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + /* + * We don't use the hardware index, but the sample generation + * code uses the new format branch_stack with this field, + * so the event attributes must indicate that it's present. + */ + attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX; + } if (pt->synth_opts.instructions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 208b813e00ea..85587de027a5 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -736,12 +736,6 @@ int machine__process_switch_event(struct machine *machine __maybe_unused, return 0; } -static int is_bpf_image(const char *name) -{ - return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 || - strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0; -} - static int machine__process_ksymbol_register(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 1d7210804639..cc0faf8f1321 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -267,6 +267,22 @@ bool __map__is_bpf_prog(const struct map *map) return name && (strstr(name, "bpf_prog_") == name); } +bool __map__is_bpf_image(const struct map *map) +{ + const char *name; + + if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) + return true; + + /* + * If PERF_RECORD_KSYMBOL is not included, the dso will not have + * type of DSO_BINARY_TYPE__BPF_IMAGE. In such cases, we can + * guess the type based on name. + */ + name = map->dso->short_name; + return name && is_bpf_image(name); +} + bool __map__is_ool(const struct map *map) { return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 9e312ae2d656..c2f5d28fe73a 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -147,12 +147,14 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, bool __map__is_kernel(const struct map *map); bool __map__is_extra_kernel_map(const struct map *map); bool __map__is_bpf_prog(const struct map *map); +bool __map__is_bpf_image(const struct map *map); bool __map__is_ool(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) && - !__map__is_bpf_prog(map) && !__map__is_ool(map); + !__map__is_bpf_prog(map) && !__map__is_ool(map) && + !__map__is_bpf_image(map); } bool map__has_symbols(const struct map *map); @@ -164,4 +166,9 @@ static inline bool is_entry_trampoline(const char *name) return !strcmp(name, ENTRY_TRAMPOLINE_NAME); } +static inline bool is_bpf_image(const char *name) +{ + return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 || + strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0; +} #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9f7260e69113..c4d2394e2b2d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -37,6 +37,7 @@ #include "util/evsel_config.h" #include "util/event.h" #include "util/pfm.h" +#include "perf.h" #define MAX_NAME_LEN 100 @@ -1533,19 +1534,23 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel = __add_event(list, &parse_state->idx, &attr, true, get_config_name(head_config), pmu, &config_terms, auto_merge_stats, NULL); - if (evsel) { - evsel->unit = info.unit; - evsel->scale = info.scale; - evsel->per_pkg = info.per_pkg; - evsel->snapshot = info.snapshot; - evsel->metric_expr = info.metric_expr; - evsel->metric_name = info.metric_name; - evsel->pmu_name = name ? strdup(name) : NULL; - evsel->use_uncore_alias = use_uncore_alias; - evsel->percore = config_term_percore(&evsel->config_terms); - } + if (!evsel) + return -ENOMEM; + + evsel->pmu_name = name ? strdup(name) : NULL; + evsel->use_uncore_alias = use_uncore_alias; + evsel->percore = config_term_percore(&evsel->config_terms); - return evsel ? 0 : -ENOMEM; + if (parse_state->fake_pmu) + return 0; + + evsel->unit = info.unit; + evsel->scale = info.scale; + evsel->per_pkg = info.per_pkg; + evsel->snapshot = info.snapshot; + evsel->metric_expr = info.metric_expr; + evsel->metric_name = info.metric_name; + return 0; } int parse_events_multi_pmu_add(struct parse_events_state *parse_state, @@ -1794,6 +1799,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, if (*str == 'u') { if (!exclude) exclude = eu = ek = eh = 1; + if (!exclude_GH && !perf_guest) + eG = 1; eu = 0; } else if (*str == 'k') { if (!exclude) diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index b9fb91fdc5de..645bf4f1859f 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -511,7 +511,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $6, $4); + (void *)(uintptr_t) $2, $6, $4); free($6); if (err) { free(list); @@ -528,7 +528,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, $4)) { + (void *)(uintptr_t) $2, NULL, $4)) { free(list); YYABORT; } @@ -544,7 +544,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $4, 0); + (void *)(uintptr_t) $2, $4, 0); free($4); if (err) { free(list); @@ -561,7 +561,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, 0)) { + (void *)(uintptr_t) $2, NULL, 0)) { free(list); YYABORT; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index ffbc9d35a383..7a5f03764702 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -87,7 +87,7 @@ static int perf_session__process_compressed_event(struct perf_session *session, session->decomp_last = decomp; } - pr_debug("decomp (B): %ld to %ld\n", src_size, decomp_size); + pr_debug("decomp (B): %zd to %zd\n", src_size, decomp_size); return 0; } diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 57d0706e1330..493ec372fdec 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -117,7 +117,7 @@ static void aggr_printout(struct perf_stat_config *config, cpu_map__id_to_die(id), config->csv_output ? 0 : -3, cpu_map__id_to_cpu(id), config->csv_sep); - } else { + } else if (id > -1) { fprintf(config->output, "CPU%*d%s", config->csv_output ? 0 : -7, evsel__cpus(evsel)->map[id], diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index f8778cffd941..aa3bed48511b 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -113,6 +113,7 @@ struct perf_stat_config { bool summary; bool metric_no_group; bool metric_no_merge; + bool stop_read_counter; FILE *output; unsigned int interval; unsigned int timeout; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 1f5fcb828a21..5151a8c0b791 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -663,6 +663,7 @@ static bool symbol__is_idle(const char *name) "exit_idle", "mwait_idle", "mwait_idle_with_hints", + "mwait_idle_with_hints.constprop.0", "poll_idle", "ppc64_runlatch_off", "pseries_dedicated_idle_sleep", diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index ff4f4c47e148..03e264a27cd3 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -28,7 +28,7 @@ struct option; * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP; * for newer versions we can use mmap to reduce memory usage: */ -#ifdef HAVE_LIBELF_MMAP_SUPPORT +#ifdef ELF_C_READ_MMAP # define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP #else # define PERF_ELF_C_READ_MMAP ELF_C_READ diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c index d2202392ffdb..48dd2b018c47 100644 --- a/tools/perf/util/zstd.c +++ b/tools/perf/util/zstd.c @@ -99,7 +99,7 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size while (input.pos < input.size) { ret = ZSTD_decompressStream(data->dstream, &output, &input); if (ZSTD_isError(ret)) { - pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n", + pr_err("failed to decompress (B): %zd -> %zd, dst_size %zd : %s\n", src_size, output.size, dst_size, ZSTD_getErrorName(ret)); break; } diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1bb204cee853..9a0946ddb705 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -6,7 +6,6 @@ test_lpm_map test_tag FEATURE-DUMP.libbpf fixdep -test_align test_dev_cgroup /test_progs* test_tcpbpf_user diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index a83b5827532f..65d3d9aaeb31 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -32,7 +32,7 @@ LDLIBS += -lcap -lelf -lz -lrt -lpthread # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ - test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ + test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ test_cgroup_storage \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \ @@ -316,7 +316,7 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_BPF_PROGS_DIR)/%.c \ $(TRUNNER_BPF_PROGS_DIR)/*.h \ $$(INCLUDE_DIR)/vmlinux.h \ - $$(BPFOBJ) | $(TRUNNER_OUTPUT) + $(wildcard $(BPFDIR)/bpf_*.h) | $(TRUNNER_OUTPUT) $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS), \ $(TRUNNER_BPF_LDFLAGS)) diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index e885d351595f..66acfcf15ff2 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -43,3 +43,24 @@ This is due to a llvm BPF backend bug. The fix https://reviews.llvm.org/D78466 has been pushed to llvm 10.x release branch and will be available in 10.0.1. The fix is available in llvm 11.0.0 trunk. + +BPF CO-RE-based tests and Clang version +======================================= + +A set of selftests use BPF target-specific built-ins, which might require +bleeding-edge Clang versions (Clang 12 nightly at this time). + +Few sub-tests of core_reloc test suit (part of test_progs test runner) require +the following built-ins, listed with corresponding Clang diffs introducing +them to Clang/LLVM. These sub-tests are going to be skipped if Clang is too +old to support them, they shouldn't cause build failures or runtime test +failures: + + - __builtin_btf_type_id() ([0], [1], [2]); + - __builtin_preserve_type_info(), __builtin_preserve_enum_value() ([3], [4]). + + [0] https://reviews.llvm.org/D74572 + [1] https://reviews.llvm.org/D74668 + [2] https://reviews.llvm.org/D85174 + [3] https://reviews.llvm.org/D83878 + [4] https://reviews.llvm.org/D83242 diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index 944ad4721c83..1a427685a8a8 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -317,6 +317,7 @@ extern const struct bench bench_trig_tp; extern const struct bench bench_trig_rawtp; extern const struct bench bench_trig_kprobe; extern const struct bench bench_trig_fentry; +extern const struct bench bench_trig_fentry_sleep; extern const struct bench bench_trig_fmodret; extern const struct bench bench_rb_libbpf; extern const struct bench bench_rb_custom; @@ -338,6 +339,7 @@ static const struct bench *benchs[] = { &bench_trig_rawtp, &bench_trig_kprobe, &bench_trig_fentry, + &bench_trig_fentry_sleep, &bench_trig_fmodret, &bench_rb_libbpf, &bench_rb_custom, diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 49c22832f216..2a0b6c9885a4 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -90,6 +90,12 @@ static void trigger_fentry_setup() attach_bpf(ctx.skel->progs.bench_trigger_fentry); } +static void trigger_fentry_sleep_setup() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.bench_trigger_fentry_sleep); +} + static void trigger_fmodret_setup() { setup_ctx(); @@ -155,6 +161,17 @@ const struct bench bench_trig_fentry = { .report_final = hits_drops_report_final, }; +const struct bench bench_trig_fentry_sleep = { + .name = "trig-fentry-sleep", + .validate = trigger_validate, + .setup = trigger_fentry_sleep_setup, + .producer_thread = trigger_producer, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + const struct bench bench_trig_fmodret = { .name = "trig-fmodret", .validate = trigger_validate, diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index f56655690f9b..12ee40284da0 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -104,6 +104,43 @@ error_close: return -1; } +int fastopen_connect(int server_fd, const char *data, unsigned int data_len, + int timeout_ms) +{ + struct sockaddr_storage addr; + socklen_t addrlen = sizeof(addr); + struct sockaddr_in *addr_in; + int fd, ret; + + if (getsockname(server_fd, (struct sockaddr *)&addr, &addrlen)) { + log_err("Failed to get server addr"); + return -1; + } + + addr_in = (struct sockaddr_in *)&addr; + fd = socket(addr_in->sin_family, SOCK_STREAM, 0); + if (fd < 0) { + log_err("Failed to create client socket"); + return -1; + } + + if (settimeo(fd, timeout_ms)) + goto error_close; + + ret = sendto(fd, data, data_len, MSG_FASTOPEN, (struct sockaddr *)&addr, + addrlen); + if (ret != data_len) { + log_err("sendto(data, %u) != %d\n", data_len, ret); + goto error_close; + } + + return fd; + +error_close: + save_errno_close(fd); + return -1; +} + static int connect_fd_to_addr(int fd, const struct sockaddr_storage *addr, socklen_t addrlen) diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index c3728f6667e4..7205f8afdba1 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -37,6 +37,8 @@ int start_server(int family, int type, const char *addr, __u16 port, int timeout_ms); int connect_to_fd(int server_fd, int timeout_ms); int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms); +int fastopen_connect(int server_fd, const char *data, unsigned int data_len, + int timeout_ms); int make_sockaddr(int family, const char *addr_str, __u16 port, struct sockaddr_storage *addr, socklen_t *len); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index 7afa4160416f..284d5921c345 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -159,15 +159,15 @@ void test_bpf_obj_id(void) /* Check getting link info */ info_len = sizeof(struct bpf_link_info) * 2; bzero(&link_infos[i], info_len); - link_infos[i].raw_tracepoint.tp_name = (__u64)&tp_name; + link_infos[i].raw_tracepoint.tp_name = ptr_to_u64(&tp_name); link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name); err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]), &link_infos[i], &info_len); if (CHECK(err || link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT || link_infos[i].prog_id != prog_infos[i].id || - link_infos[i].raw_tracepoint.tp_name != (__u64)&tp_name || - strcmp((char *)link_infos[i].raw_tracepoint.tp_name, + link_infos[i].raw_tracepoint.tp_name != ptr_to_u64(&tp_name) || + strcmp(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter") || info_len != sizeof(struct bpf_link_info), "get-link-info(fd)", @@ -178,7 +178,7 @@ void test_bpf_obj_id(void) link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, link_infos[i].id, link_infos[i].prog_id, prog_infos[i].id, - (char *)link_infos[i].raw_tracepoint.tp_name, + (const char *)u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index cb33a7ee4e04..39fb81d9daeb 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -12,15 +12,16 @@ void btf_dump_printf(void *ctx, const char *fmt, va_list args) static struct btf_dump_test_case { const char *name; const char *file; + bool known_ptr_sz; struct btf_dump_opts opts; } btf_dump_test_cases[] = { - {"btf_dump: syntax", "btf_dump_test_case_syntax", {}}, - {"btf_dump: ordering", "btf_dump_test_case_ordering", {}}, - {"btf_dump: padding", "btf_dump_test_case_padding", {}}, - {"btf_dump: packing", "btf_dump_test_case_packing", {}}, - {"btf_dump: bitfields", "btf_dump_test_case_bitfields", {}}, - {"btf_dump: multidim", "btf_dump_test_case_multidim", {}}, - {"btf_dump: namespacing", "btf_dump_test_case_namespacing", {}}, + {"btf_dump: syntax", "btf_dump_test_case_syntax", true, {}}, + {"btf_dump: ordering", "btf_dump_test_case_ordering", false, {}}, + {"btf_dump: padding", "btf_dump_test_case_padding", true, {}}, + {"btf_dump: packing", "btf_dump_test_case_packing", true, {}}, + {"btf_dump: bitfields", "btf_dump_test_case_bitfields", true, {}}, + {"btf_dump: multidim", "btf_dump_test_case_multidim", false, {}}, + {"btf_dump: namespacing", "btf_dump_test_case_namespacing", false, {}}, }; static int btf_dump_all_types(const struct btf *btf, @@ -62,6 +63,18 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t) goto done; } + /* tests with t->known_ptr_sz have no "long" or "unsigned long" type, + * so it's impossible to determine correct pointer size; but if they + * do, it should be 8 regardless of host architecture, becaues BPF + * target is always 64-bit + */ + if (!t->known_ptr_sz) { + btf__set_pointer_size(btf, 8); + } else { + CHECK(btf__pointer_size(btf) != 8, "ptr_sz", "exp %d, got %zu\n", + 8, btf__pointer_size(btf)); + } + snprintf(out_file, sizeof(out_file), "/tmp/%s.output.XXXXXX", t->file); fd = mkstemp(out_file); if (CHECK(fd < 0, "create_tmp", "failed to create file: %d\n", fd)) { diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index 6ccecbd39476..540fea4c91a5 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -53,7 +53,7 @@ static int kern_sync_rcu(void) return err; } -void test_btf_map_in_map(void) +static void test_lookup_update(void) { int err, key = 0, val, i; struct test_btf_map_in_map *skel; @@ -143,3 +143,36 @@ void test_btf_map_in_map(void) cleanup: test_btf_map_in_map__destroy(skel); } + +static void test_diff_size(void) +{ + struct test_btf_map_in_map *skel; + int err, inner_map_fd, zero = 0; + + skel = test_btf_map_in_map__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) + return; + + inner_map_fd = bpf_map__fd(skel->maps.sockarr_sz2); + err = bpf_map_update_elem(bpf_map__fd(skel->maps.outer_sockarr), &zero, + &inner_map_fd, 0); + CHECK(err, "outer_sockarr inner map size check", + "cannot use a different size inner_map\n"); + + inner_map_fd = bpf_map__fd(skel->maps.inner_map_sz2); + err = bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &zero, + &inner_map_fd, 0); + CHECK(!err, "outer_arr inner map size check", + "incorrectly updated with a different size inner_map\n"); + + test_btf_map_in_map__destroy(skel); +} + +void test_btf_map_in_map(void) +{ + if (test__start_subtest("lookup_update")) + test_lookup_update(); + + if (test__start_subtest("diff_size")) + test_diff_size(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_extern.c b/tools/testing/selftests/bpf/prog_tests/core_extern.c index b093787e9448..1931a158510e 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_extern.c +++ b/tools/testing/selftests/bpf/prog_tests/core_extern.c @@ -159,8 +159,8 @@ void test_core_extern(void) exp = (uint64_t *)&t->data; for (j = 0; j < n; j++) { CHECK(got[j] != exp[j], "check_res", - "result #%d: expected %lx, but got %lx\n", - j, exp[j], got[j]); + "result #%d: expected %llx, but got %llx\n", + j, (__u64)exp[j], (__u64)got[j]); } cleanup: test_core_extern__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 084ed26a7d78..30e40ff4b0d8 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -3,6 +3,9 @@ #include "progs/core_reloc_types.h" #include <sys/mman.h> #include <sys/syscall.h> +#include <bpf/btf.h> + +static int duration = 0; #define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name) @@ -177,14 +180,13 @@ .fails = true, \ } -#define EXISTENCE_CASE_COMMON(name) \ +#define FIELD_EXISTS_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_existence.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o", \ - .relaxed_core_relocs = true + .btf_src_file = "btf__core_reloc_" #name ".o" \ -#define EXISTENCE_ERR_CASE(name) { \ - EXISTENCE_CASE_COMMON(name), \ +#define FIELD_EXISTS_ERR_CASE(name) { \ + FIELD_EXISTS_CASE_COMMON(name), \ .fails = true, \ } @@ -237,8 +239,8 @@ .union_sz = sizeof(((type *)0)->union_field), \ .arr_sz = sizeof(((type *)0)->arr_field), \ .arr_elem_sz = sizeof(((type *)0)->arr_field[0]), \ - .ptr_sz = sizeof(((type *)0)->ptr_field), \ - .enum_sz = sizeof(((type *)0)->enum_field), \ + .ptr_sz = 8, /* always 8-byte pointer for BPF */ \ + .enum_sz = sizeof(((type *)0)->enum_field), \ } #define SIZE_CASE(name) { \ @@ -253,6 +255,61 @@ .fails = true, \ } +#define TYPE_BASED_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_type_based.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" \ + +#define TYPE_BASED_CASE(name, ...) { \ + TYPE_BASED_CASE_COMMON(name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_type_based_output) \ + __VA_ARGS__, \ + .output_len = sizeof(struct core_reloc_type_based_output), \ +} + +#define TYPE_BASED_ERR_CASE(name) { \ + TYPE_BASED_CASE_COMMON(name), \ + .fails = true, \ +} + +#define TYPE_ID_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_type_id.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" \ + +#define TYPE_ID_CASE(name, setup_fn) { \ + TYPE_ID_CASE_COMMON(name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_type_id_output) {}, \ + .output_len = sizeof(struct core_reloc_type_id_output), \ + .setup = setup_fn, \ +} + +#define TYPE_ID_ERR_CASE(name) { \ + TYPE_ID_CASE_COMMON(name), \ + .fails = true, \ +} + +#define ENUMVAL_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_enumval.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" \ + +#define ENUMVAL_CASE(name, ...) { \ + ENUMVAL_CASE_COMMON(name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_enumval_output) \ + __VA_ARGS__, \ + .output_len = sizeof(struct core_reloc_enumval_output), \ +} + +#define ENUMVAL_ERR_CASE(name) { \ + ENUMVAL_CASE_COMMON(name), \ + .fails = true, \ +} + +struct core_reloc_test_case; + +typedef int (*setup_test_fn)(struct core_reloc_test_case *test); + struct core_reloc_test_case { const char *case_name; const char *bpf_obj_file; @@ -264,8 +321,136 @@ struct core_reloc_test_case { bool fails; bool relaxed_core_relocs; bool direct_raw_tp; + setup_test_fn setup; }; +static int find_btf_type(const struct btf *btf, const char *name, __u32 kind) +{ + int id; + + id = btf__find_by_name_kind(btf, name, kind); + if (CHECK(id <= 0, "find_type_id", "failed to find '%s', kind %d: %d\n", name, kind, id)) + return -1; + + return id; +} + +static int setup_type_id_case_local(struct core_reloc_test_case *test) +{ + struct core_reloc_type_id_output *exp = (void *)test->output; + struct btf *local_btf = btf__parse(test->bpf_obj_file, NULL); + struct btf *targ_btf = btf__parse(test->btf_src_file, NULL); + const struct btf_type *t; + const char *name; + int i; + + if (CHECK(IS_ERR(local_btf), "local_btf", "failed: %ld\n", PTR_ERR(local_btf)) || + CHECK(IS_ERR(targ_btf), "targ_btf", "failed: %ld\n", PTR_ERR(targ_btf))) { + btf__free(local_btf); + btf__free(targ_btf); + return -EINVAL; + } + + exp->local_anon_struct = -1; + exp->local_anon_union = -1; + exp->local_anon_enum = -1; + exp->local_anon_func_proto_ptr = -1; + exp->local_anon_void_ptr = -1; + exp->local_anon_arr = -1; + + for (i = 1; i <= btf__get_nr_types(local_btf); i++) + { + t = btf__type_by_id(local_btf, i); + /* we are interested only in anonymous types */ + if (t->name_off) + continue; + + if (btf_is_struct(t) && btf_vlen(t) && + (name = btf__name_by_offset(local_btf, btf_members(t)[0].name_off)) && + strcmp(name, "marker_field") == 0) { + exp->local_anon_struct = i; + } else if (btf_is_union(t) && btf_vlen(t) && + (name = btf__name_by_offset(local_btf, btf_members(t)[0].name_off)) && + strcmp(name, "marker_field") == 0) { + exp->local_anon_union = i; + } else if (btf_is_enum(t) && btf_vlen(t) && + (name = btf__name_by_offset(local_btf, btf_enum(t)[0].name_off)) && + strcmp(name, "MARKER_ENUM_VAL") == 0) { + exp->local_anon_enum = i; + } else if (btf_is_ptr(t) && (t = btf__type_by_id(local_btf, t->type))) { + if (btf_is_func_proto(t) && (t = btf__type_by_id(local_btf, t->type)) && + btf_is_int(t) && (name = btf__name_by_offset(local_btf, t->name_off)) && + strcmp(name, "_Bool") == 0) { + /* ptr -> func_proto -> _Bool */ + exp->local_anon_func_proto_ptr = i; + } else if (btf_is_void(t)) { + /* ptr -> void */ + exp->local_anon_void_ptr = i; + } + } else if (btf_is_array(t) && (t = btf__type_by_id(local_btf, btf_array(t)->type)) && + btf_is_int(t) && (name = btf__name_by_offset(local_btf, t->name_off)) && + strcmp(name, "_Bool") == 0) { + /* _Bool[] */ + exp->local_anon_arr = i; + } + } + + exp->local_struct = find_btf_type(local_btf, "a_struct", BTF_KIND_STRUCT); + exp->local_union = find_btf_type(local_btf, "a_union", BTF_KIND_UNION); + exp->local_enum = find_btf_type(local_btf, "an_enum", BTF_KIND_ENUM); + exp->local_int = find_btf_type(local_btf, "int", BTF_KIND_INT); + exp->local_struct_typedef = find_btf_type(local_btf, "named_struct_typedef", BTF_KIND_TYPEDEF); + exp->local_func_proto_typedef = find_btf_type(local_btf, "func_proto_typedef", BTF_KIND_TYPEDEF); + exp->local_arr_typedef = find_btf_type(local_btf, "arr_typedef", BTF_KIND_TYPEDEF); + + btf__free(local_btf); + btf__free(targ_btf); + return 0; +} + +static int setup_type_id_case_success(struct core_reloc_test_case *test) { + struct core_reloc_type_id_output *exp = (void *)test->output; + struct btf *targ_btf = btf__parse(test->btf_src_file, NULL); + int err; + + err = setup_type_id_case_local(test); + if (err) + return err; + + targ_btf = btf__parse(test->btf_src_file, NULL); + + exp->targ_struct = find_btf_type(targ_btf, "a_struct", BTF_KIND_STRUCT); + exp->targ_union = find_btf_type(targ_btf, "a_union", BTF_KIND_UNION); + exp->targ_enum = find_btf_type(targ_btf, "an_enum", BTF_KIND_ENUM); + exp->targ_int = find_btf_type(targ_btf, "int", BTF_KIND_INT); + exp->targ_struct_typedef = find_btf_type(targ_btf, "named_struct_typedef", BTF_KIND_TYPEDEF); + exp->targ_func_proto_typedef = find_btf_type(targ_btf, "func_proto_typedef", BTF_KIND_TYPEDEF); + exp->targ_arr_typedef = find_btf_type(targ_btf, "arr_typedef", BTF_KIND_TYPEDEF); + + btf__free(targ_btf); + return 0; +} + +static int setup_type_id_case_failure(struct core_reloc_test_case *test) +{ + struct core_reloc_type_id_output *exp = (void *)test->output; + int err; + + err = setup_type_id_case_local(test); + if (err) + return err; + + exp->targ_struct = 0; + exp->targ_union = 0; + exp->targ_enum = 0; + exp->targ_int = 0; + exp->targ_struct_typedef = 0; + exp->targ_func_proto_typedef = 0; + exp->targ_arr_typedef = 0; + + return 0; +} + static struct core_reloc_test_case test_cases[] = { /* validate we can find kernel image and use its BTF for relocs */ { @@ -364,7 +549,7 @@ static struct core_reloc_test_case test_cases[] = { /* validate field existence checks */ { - EXISTENCE_CASE_COMMON(existence), + FIELD_EXISTS_CASE_COMMON(existence), .input = STRUCT_TO_CHAR_PTR(core_reloc_existence) { .a = 1, .b = 2, @@ -388,7 +573,7 @@ static struct core_reloc_test_case test_cases[] = { .output_len = sizeof(struct core_reloc_existence_output), }, { - EXISTENCE_CASE_COMMON(existence___minimal), + FIELD_EXISTS_CASE_COMMON(existence___minimal), .input = STRUCT_TO_CHAR_PTR(core_reloc_existence___minimal) { .a = 42, }, @@ -408,12 +593,12 @@ static struct core_reloc_test_case test_cases[] = { .output_len = sizeof(struct core_reloc_existence_output), }, - EXISTENCE_ERR_CASE(existence__err_int_sz), - EXISTENCE_ERR_CASE(existence__err_int_type), - EXISTENCE_ERR_CASE(existence__err_int_kind), - EXISTENCE_ERR_CASE(existence__err_arr_kind), - EXISTENCE_ERR_CASE(existence__err_arr_value_type), - EXISTENCE_ERR_CASE(existence__err_struct_type), + FIELD_EXISTS_ERR_CASE(existence__err_int_sz), + FIELD_EXISTS_ERR_CASE(existence__err_int_type), + FIELD_EXISTS_ERR_CASE(existence__err_int_kind), + FIELD_EXISTS_ERR_CASE(existence__err_arr_kind), + FIELD_EXISTS_ERR_CASE(existence__err_arr_value_type), + FIELD_EXISTS_ERR_CASE(existence__err_struct_type), /* bitfield relocation checks */ BITFIELDS_CASE(bitfields, { @@ -432,31 +617,137 @@ static struct core_reloc_test_case test_cases[] = { .sb4 = -1, .sb20 = -0x17654321, .u32 = 0xBEEF, - .s32 = -0x3FEDCBA987654321, + .s32 = -0x3FEDCBA987654321LL, }), BITFIELDS_CASE(bitfields___bitfield_vs_int, { - .ub1 = 0xFEDCBA9876543210, + .ub1 = 0xFEDCBA9876543210LL, .ub2 = 0xA6, - .ub7 = -0x7EDCBA987654321, - .sb4 = -0x6123456789ABCDE, - .sb20 = 0xD00D, + .ub7 = -0x7EDCBA987654321LL, + .sb4 = -0x6123456789ABCDELL, + .sb20 = 0xD00DLL, .u32 = -0x76543, - .s32 = 0x0ADEADBEEFBADB0B, + .s32 = 0x0ADEADBEEFBADB0BLL, }), BITFIELDS_CASE(bitfields___just_big_enough, { - .ub1 = 0xF, - .ub2 = 0x0812345678FEDCBA, + .ub1 = 0xFLL, + .ub2 = 0x0812345678FEDCBALL, }), BITFIELDS_ERR_CASE(bitfields___err_too_big_bitfield), /* size relocation checks */ SIZE_CASE(size), SIZE_CASE(size___diff_sz), + SIZE_ERR_CASE(size___err_ambiguous), + + /* validate type existence and size relocations */ + TYPE_BASED_CASE(type_based, { + .struct_exists = 1, + .union_exists = 1, + .enum_exists = 1, + .typedef_named_struct_exists = 1, + .typedef_anon_struct_exists = 1, + .typedef_struct_ptr_exists = 1, + .typedef_int_exists = 1, + .typedef_enum_exists = 1, + .typedef_void_ptr_exists = 1, + .typedef_func_proto_exists = 1, + .typedef_arr_exists = 1, + .struct_sz = sizeof(struct a_struct), + .union_sz = sizeof(union a_union), + .enum_sz = sizeof(enum an_enum), + .typedef_named_struct_sz = sizeof(named_struct_typedef), + .typedef_anon_struct_sz = sizeof(anon_struct_typedef), + .typedef_struct_ptr_sz = sizeof(struct_ptr_typedef), + .typedef_int_sz = sizeof(int_typedef), + .typedef_enum_sz = sizeof(enum_typedef), + .typedef_void_ptr_sz = sizeof(void_ptr_typedef), + .typedef_func_proto_sz = sizeof(func_proto_typedef), + .typedef_arr_sz = sizeof(arr_typedef), + }), + TYPE_BASED_CASE(type_based___all_missing, { + /* all zeros */ + }), + TYPE_BASED_CASE(type_based___diff_sz, { + .struct_exists = 1, + .union_exists = 1, + .enum_exists = 1, + .typedef_named_struct_exists = 1, + .typedef_anon_struct_exists = 1, + .typedef_struct_ptr_exists = 1, + .typedef_int_exists = 1, + .typedef_enum_exists = 1, + .typedef_void_ptr_exists = 1, + .typedef_func_proto_exists = 1, + .typedef_arr_exists = 1, + .struct_sz = sizeof(struct a_struct___diff_sz), + .union_sz = sizeof(union a_union___diff_sz), + .enum_sz = sizeof(enum an_enum___diff_sz), + .typedef_named_struct_sz = sizeof(named_struct_typedef___diff_sz), + .typedef_anon_struct_sz = sizeof(anon_struct_typedef___diff_sz), + .typedef_struct_ptr_sz = sizeof(struct_ptr_typedef___diff_sz), + .typedef_int_sz = sizeof(int_typedef___diff_sz), + .typedef_enum_sz = sizeof(enum_typedef___diff_sz), + .typedef_void_ptr_sz = sizeof(void_ptr_typedef___diff_sz), + .typedef_func_proto_sz = sizeof(func_proto_typedef___diff_sz), + .typedef_arr_sz = sizeof(arr_typedef___diff_sz), + }), + TYPE_BASED_CASE(type_based___incompat, { + .enum_exists = 1, + .enum_sz = sizeof(enum an_enum), + }), + TYPE_BASED_CASE(type_based___fn_wrong_args, { + .struct_exists = 1, + .struct_sz = sizeof(struct a_struct), + }), + + /* BTF_TYPE_ID_LOCAL/BTF_TYPE_ID_TARGET tests */ + TYPE_ID_CASE(type_id, setup_type_id_case_success), + TYPE_ID_CASE(type_id___missing_targets, setup_type_id_case_failure), + + /* Enumerator value existence and value relocations */ + ENUMVAL_CASE(enumval, { + .named_val1_exists = true, + .named_val2_exists = true, + .named_val3_exists = true, + .anon_val1_exists = true, + .anon_val2_exists = true, + .anon_val3_exists = true, + .named_val1 = 1, + .named_val2 = 2, + .anon_val1 = 0x10, + .anon_val2 = 0x20, + }), + ENUMVAL_CASE(enumval___diff, { + .named_val1_exists = true, + .named_val2_exists = true, + .named_val3_exists = true, + .anon_val1_exists = true, + .anon_val2_exists = true, + .anon_val3_exists = true, + .named_val1 = 101, + .named_val2 = 202, + .anon_val1 = 0x11, + .anon_val2 = 0x22, + }), + ENUMVAL_CASE(enumval___val3_missing, { + .named_val1_exists = true, + .named_val2_exists = true, + .named_val3_exists = false, + .anon_val1_exists = true, + .anon_val2_exists = true, + .anon_val3_exists = false, + .named_val1 = 111, + .named_val2 = 222, + .anon_val1 = 0x111, + .anon_val2 = 0x222, + }), + ENUMVAL_ERR_CASE(enumval___err_missing), }; struct data { char in[256]; char out[256]; + bool skip; uint64_t my_pid_tgid; }; @@ -472,7 +763,7 @@ void test_core_reloc(void) struct bpf_object_load_attr load_attr = {}; struct core_reloc_test_case *test_case; const char *tp_name, *probe_name; - int err, duration = 0, i, equal; + int err, i, equal; struct bpf_link *link = NULL; struct bpf_map *data_map; struct bpf_program *prog; @@ -488,11 +779,13 @@ void test_core_reloc(void) if (!test__start_subtest(test_case->case_name)) continue; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, - .relaxed_core_relocs = test_case->relaxed_core_relocs, - ); + if (test_case->setup) { + err = test_case->setup(test_case); + if (CHECK(err, "test_setup", "test #%d setup failed: %d\n", i, err)) + continue; + } - obj = bpf_object__open_file(test_case->bpf_obj_file, &opts); + obj = bpf_object__open_file(test_case->bpf_obj_file, NULL); if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n", test_case->bpf_obj_file, PTR_ERR(obj))) continue; @@ -515,15 +808,10 @@ void test_core_reloc(void) load_attr.log_level = 0; load_attr.target_btf_path = test_case->btf_src_file; err = bpf_object__load_xattr(&load_attr); - if (test_case->fails) { - CHECK(!err, "obj_load_fail", - "should fail to load prog '%s'\n", probe_name); + if (err) { + if (!test_case->fails) + CHECK(false, "obj_load", "failed to load prog '%s': %d\n", probe_name, err); goto cleanup; - } else { - if (CHECK(err, "obj_load", - "failed to load prog '%s': %d\n", - probe_name, err)) - goto cleanup; } data_map = bpf_object__find_map_by_name(obj, "test_cor.bss"); @@ -551,6 +839,16 @@ void test_core_reloc(void) /* trigger test run */ usleep(1); + if (data->skip) { + test__skip(); + goto cleanup; + } + + if (test_case->fails) { + CHECK(false, "obj_load_fail", "should fail to load prog '%s'\n", probe_name); + goto cleanup; + } + equal = memcmp(data->out, test_case->output, test_case->output_len) == 0; if (CHECK(!equal, "check_result", diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c new file mode 100644 index 000000000000..fc12e0d445ff --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/d_path.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <test_progs.h> +#include <sys/stat.h> +#include <linux/sched.h> +#include <sys/syscall.h> + +#define MAX_PATH_LEN 128 +#define MAX_FILES 7 + +#include "test_d_path.skel.h" + +static int duration; + +static struct { + __u32 cnt; + char paths[MAX_FILES][MAX_PATH_LEN]; +} src; + +static int set_pathname(int fd, pid_t pid) +{ + char buf[MAX_PATH_LEN]; + + snprintf(buf, MAX_PATH_LEN, "/proc/%d/fd/%d", pid, fd); + return readlink(buf, src.paths[src.cnt++], MAX_PATH_LEN); +} + +static int trigger_fstat_events(pid_t pid) +{ + int sockfd = -1, procfd = -1, devfd = -1; + int localfd = -1, indicatorfd = -1; + int pipefd[2] = { -1, -1 }; + struct stat fileStat; + int ret = -1; + + /* unmountable pseudo-filesystems */ + if (CHECK(pipe(pipefd) < 0, "trigger", "pipe failed\n")) + return ret; + /* unmountable pseudo-filesystems */ + sockfd = socket(AF_INET, SOCK_STREAM, 0); + if (CHECK(sockfd < 0, "trigger", "socket failed\n")) + goto out_close; + /* mountable pseudo-filesystems */ + procfd = open("/proc/self/comm", O_RDONLY); + if (CHECK(procfd < 0, "trigger", "open /proc/self/comm failed\n")) + goto out_close; + devfd = open("/dev/urandom", O_RDONLY); + if (CHECK(devfd < 0, "trigger", "open /dev/urandom failed\n")) + goto out_close; + localfd = open("/tmp/d_path_loadgen.txt", O_CREAT | O_RDONLY, 0644); + if (CHECK(localfd < 0, "trigger", "open /tmp/d_path_loadgen.txt failed\n")) + goto out_close; + /* bpf_d_path will return path with (deleted) */ + remove("/tmp/d_path_loadgen.txt"); + indicatorfd = open("/tmp/", O_PATH); + if (CHECK(indicatorfd < 0, "trigger", "open /tmp/ failed\n")) + goto out_close; + + ret = set_pathname(pipefd[0], pid); + if (CHECK(ret < 0, "trigger", "set_pathname failed for pipe[0]\n")) + goto out_close; + ret = set_pathname(pipefd[1], pid); + if (CHECK(ret < 0, "trigger", "set_pathname failed for pipe[1]\n")) + goto out_close; + ret = set_pathname(sockfd, pid); + if (CHECK(ret < 0, "trigger", "set_pathname failed for socket\n")) + goto out_close; + ret = set_pathname(procfd, pid); + if (CHECK(ret < 0, "trigger", "set_pathname failed for proc\n")) + goto out_close; + ret = set_pathname(devfd, pid); + if (CHECK(ret < 0, "trigger", "set_pathname failed for dev\n")) + goto out_close; + ret = set_pathname(localfd, pid); + if (CHECK(ret < 0, "trigger", "set_pathname failed for file\n")) + goto out_close; + ret = set_pathname(indicatorfd, pid); + if (CHECK(ret < 0, "trigger", "set_pathname failed for dir\n")) + goto out_close; + + /* triggers vfs_getattr */ + fstat(pipefd[0], &fileStat); + fstat(pipefd[1], &fileStat); + fstat(sockfd, &fileStat); + fstat(procfd, &fileStat); + fstat(devfd, &fileStat); + fstat(localfd, &fileStat); + fstat(indicatorfd, &fileStat); + +out_close: + /* triggers filp_close */ + close(pipefd[0]); + close(pipefd[1]); + close(sockfd); + close(procfd); + close(devfd); + close(localfd); + close(indicatorfd); + return ret; +} + +void test_d_path(void) +{ + struct test_d_path__bss *bss; + struct test_d_path *skel; + int err; + + skel = test_d_path__open_and_load(); + if (CHECK(!skel, "setup", "d_path skeleton failed\n")) + goto cleanup; + + err = test_d_path__attach(skel); + if (CHECK(err, "setup", "attach failed: %d\n", err)) + goto cleanup; + + bss = skel->bss; + bss->my_pid = getpid(); + + err = trigger_fstat_events(bss->my_pid); + if (err < 0) + goto cleanup; + + for (int i = 0; i < MAX_FILES; i++) { + CHECK(strncmp(src.paths[i], bss->paths_stat[i], MAX_PATH_LEN), + "check", + "failed to get stat path[%d]: %s vs %s\n", + i, src.paths[i], bss->paths_stat[i]); + CHECK(strncmp(src.paths[i], bss->paths_close[i], MAX_PATH_LEN), + "check", + "failed to get close path[%d]: %s vs %s\n", + i, src.paths[i], bss->paths_close[i]); + /* The d_path helper returns size plus NUL char, hence + 1 */ + CHECK(bss->rets_stat[i] != strlen(bss->paths_stat[i]) + 1, + "check", + "failed to match stat return [%d]: %d vs %zd [%s]\n", + i, bss->rets_stat[i], strlen(bss->paths_stat[i]) + 1, + bss->paths_stat[i]); + CHECK(bss->rets_close[i] != strlen(bss->paths_stat[i]) + 1, + "check", + "failed to match stat return [%d]: %d vs %zd [%s]\n", + i, bss->rets_close[i], strlen(bss->paths_close[i]) + 1, + bss->paths_stat[i]); + } + +cleanup: + test_d_path__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index a895bfed55db..a550dab9ba7a 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -16,7 +16,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, __u32 duration = 0, retval; struct bpf_map *data_map; const int zero = 0; - u64 *result = NULL; + __u64 *result = NULL; err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &pkt_obj, &pkt_fd); @@ -29,7 +29,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, link = calloc(sizeof(struct bpf_link *), prog_cnt); prog = calloc(sizeof(struct bpf_program *), prog_cnt); - result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64)); + result = malloc((prog_cnt + 32 /* spare */) * sizeof(__u64)); if (CHECK(!link || !prog || !result, "alloc_memory", "failed to alloc memory")) goto close_prog; @@ -72,7 +72,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, goto close_prog; for (i = 0; i < prog_cnt; i++) - if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %ld\n", + if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %llu\n", result[i])) goto close_prog; @@ -123,6 +123,7 @@ static void test_func_replace(void) "freplace/get_skb_len", "freplace/get_skb_ifindex", "freplace/get_constant", + "freplace/test_pkt_write_access_subprog", }; test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o", "./test_pkt_access.o", @@ -141,10 +142,77 @@ static void test_func_replace_verify(void) prog_name, false); } +static void test_func_sockmap_update(void) +{ + const char *prog_name[] = { + "freplace/cls_redirect", + }; + test_fexit_bpf2bpf_common("./freplace_cls_redirect.o", + "./test_cls_redirect.o", + ARRAY_SIZE(prog_name), + prog_name, false); +} + +static void test_obj_load_failure_common(const char *obj_file, + const char *target_obj_file) + +{ + /* + * standalone test that asserts failure to load freplace prog + * because of invalid return code. + */ + struct bpf_object *obj = NULL, *pkt_obj; + int err, pkt_fd; + __u32 duration = 0; + + err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, + &pkt_obj, &pkt_fd); + /* the target prog should load fine */ + if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n", + target_obj_file, err, errno)) + return; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .attach_prog_fd = pkt_fd, + ); + + obj = bpf_object__open_file(obj_file, &opts); + if (CHECK(IS_ERR_OR_NULL(obj), "obj_open", + "failed to open %s: %ld\n", obj_file, + PTR_ERR(obj))) + goto close_prog; + + /* It should fail to load the program */ + err = bpf_object__load(obj); + if (CHECK(!err, "bpf_obj_load should fail", "err %d\n", err)) + goto close_prog; + +close_prog: + if (!IS_ERR_OR_NULL(obj)) + bpf_object__close(obj); + bpf_object__close(pkt_obj); +} + +static void test_func_replace_return_code(void) +{ + /* test invalid return code in the replaced program */ + test_obj_load_failure_common("./freplace_connect_v4_prog.o", + "./connect4_prog.o"); +} + +static void test_func_map_prog_compatibility(void) +{ + /* test with spin lock map value in the replaced program */ + test_obj_load_failure_common("./freplace_attach_probe.o", + "./test_attach_probe.o"); +} + void test_fexit_bpf2bpf(void) { test_target_no_callees(); test_target_yes_callees(); test_func_replace(); test_func_replace_verify(); + test_func_sockmap_update(); + test_func_replace_return_code(); + test_func_map_prog_compatibility(); } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index f11f187990e9..cd6dc80edf18 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -591,7 +591,7 @@ void test_flow_dissector(void) CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) || err || tattr.retval != 1, tests[i].name, - "err %d errno %d retval %d duration %d size %u/%lu\n", + "err %d errno %d retval %d duration %d size %u/%zu\n", err, errno, tattr.retval, tattr.duration, tattr.data_size_out, sizeof(flow_keys)); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index e3cb62b0a110..9efa7e50eab2 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -5,7 +5,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) { int i, err, map_fd; - uint64_t num; + __u64 num; map_fd = bpf_find_map(__func__, obj, "result_number"); if (CHECK_FAIL(map_fd < 0)) @@ -14,7 +14,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) struct { char *name; uint32_t key; - uint64_t num; + __u64 num; } tests[] = { { "relocate .bss reference", 0, 0 }, { "relocate .data reference", 1, 42 }, @@ -32,7 +32,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num); CHECK(err || num != tests[i].num, tests[i].name, - "err %d result %lx expected %lx\n", + "err %d result %llx expected %llx\n", err, num, tests[i].num); } } diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 43d0b5578f46..9c3c5c0f068f 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -21,7 +21,7 @@ void test_mmap(void) const long page_size = sysconf(_SC_PAGE_SIZE); int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd, rdmap_fd; struct bpf_map *data_map, *bss_map; - void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2; + void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp0, *tmp1, *tmp2; struct test_mmap__bss *bss_data; struct bpf_map_info map_info; __u32 map_info_sz = sizeof(map_info); @@ -183,16 +183,23 @@ void test_mmap(void) /* check some more advanced mmap() manipulations */ + tmp0 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_ANONYMOUS, + -1, 0); + if (CHECK(tmp0 == MAP_FAILED, "adv_mmap0", "errno %d\n", errno)) + goto cleanup; + /* map all but last page: pages 1-3 mapped */ - tmp1 = mmap(NULL, 3 * page_size, PROT_READ, MAP_SHARED, + tmp1 = mmap(tmp0, 3 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED, data_map_fd, 0); - if (CHECK(tmp1 == MAP_FAILED, "adv_mmap1", "errno %d\n", errno)) + if (CHECK(tmp0 != tmp1, "adv_mmap1", "tmp0: %p, tmp1: %p\n", tmp0, tmp1)) { + munmap(tmp0, 4 * page_size); goto cleanup; + } /* unmap second page: pages 1, 3 mapped */ err = munmap(tmp1 + page_size, page_size); if (CHECK(err, "adv_mmap2", "errno %d\n", errno)) { - munmap(tmp1, map_sz); + munmap(tmp1, 4 * page_size); goto cleanup; } @@ -201,7 +208,7 @@ void test_mmap(void) MAP_SHARED | MAP_FIXED, data_map_fd, 0); if (CHECK(tmp2 == MAP_FAILED, "adv_mmap3", "errno %d\n", errno)) { munmap(tmp1, page_size); - munmap(tmp1 + 2*page_size, page_size); + munmap(tmp1 + 2*page_size, 2 * page_size); goto cleanup; } CHECK(tmp1 + page_size != tmp2, "adv_mmap4", @@ -211,7 +218,7 @@ void test_mmap(void) tmp2 = mmap(tmp1, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED, data_map_fd, 0); if (CHECK(tmp2 == MAP_FAILED, "adv_mmap5", "errno %d\n", errno)) { - munmap(tmp1, 3 * page_size); /* unmap page 1 */ + munmap(tmp1, 4 * page_size); /* unmap page 1 */ goto cleanup; } CHECK(tmp1 != tmp2, "adv_mmap6", "tmp1: %p, tmp2: %p\n", tmp1, tmp2); diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index c33ec180b3f2..ca9f0895ec84 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -7,6 +7,8 @@ #include "test_perf_buffer.skel.h" #include "bpf/libbpf_internal.h" +static int duration; + /* AddressSanitizer sometimes crashes due to data dereference below, due to * this being mmap()'ed memory. Disable instrumentation with * no_sanitize_address attribute @@ -24,13 +26,31 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) CPU_SET(cpu, cpu_seen); } +int trigger_on_cpu(int cpu) +{ + cpu_set_t cpu_set; + int err; + + CPU_ZERO(&cpu_set); + CPU_SET(cpu, &cpu_set); + + err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); + if (err && CHECK(err, "set_affinity", "cpu #%d, err %d\n", cpu, err)) + return err; + + usleep(1); + + return 0; +} + void test_perf_buffer(void) { - int err, on_len, nr_on_cpus = 0, nr_cpus, i, duration = 0; + int err, on_len, nr_on_cpus = 0, nr_cpus, i; struct perf_buffer_opts pb_opts = {}; struct test_perf_buffer *skel; - cpu_set_t cpu_set, cpu_seen; + cpu_set_t cpu_seen; struct perf_buffer *pb; + int last_fd = -1, fd; bool *online; nr_cpus = libbpf_num_possible_cpus(); @@ -63,6 +83,9 @@ void test_perf_buffer(void) if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) goto out_close; + CHECK(perf_buffer__epoll_fd(pb) < 0, "epoll_fd", + "bad fd: %d\n", perf_buffer__epoll_fd(pb)); + /* trigger kprobe on every CPU */ CPU_ZERO(&cpu_seen); for (i = 0; i < nr_cpus; i++) { @@ -71,16 +94,8 @@ void test_perf_buffer(void) continue; } - CPU_ZERO(&cpu_set); - CPU_SET(i, &cpu_set); - - err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), - &cpu_set); - if (err && CHECK(err, "set_affinity", "cpu #%d, err %d\n", - i, err)) + if (trigger_on_cpu(i)) goto out_close; - - usleep(1); } /* read perf buffer */ @@ -92,6 +107,34 @@ void test_perf_buffer(void) "expect %d, seen %d\n", nr_on_cpus, CPU_COUNT(&cpu_seen))) goto out_free_pb; + if (CHECK(perf_buffer__buffer_cnt(pb) != nr_cpus, "buf_cnt", + "got %zu, expected %d\n", perf_buffer__buffer_cnt(pb), nr_cpus)) + goto out_close; + + for (i = 0; i < nr_cpus; i++) { + if (i >= on_len || !online[i]) + continue; + + fd = perf_buffer__buffer_fd(pb, i); + CHECK(fd < 0 || last_fd == fd, "fd_check", "last fd %d == fd %d\n", last_fd, fd); + last_fd = fd; + + err = perf_buffer__consume_buffer(pb, i); + if (CHECK(err, "drain_buf", "cpu %d, err %d\n", i, err)) + goto out_close; + + CPU_CLR(i, &cpu_seen); + if (trigger_on_cpu(i)) + goto out_close; + + err = perf_buffer__consume_buffer(pb, i); + if (CHECK(err, "consume_buf", "cpu %d, err %d\n", i, err)) + goto out_close; + + if (CHECK(!CPU_ISSET(i, &cpu_seen), "cpu_seen", "cpu %d not seen\n", i)) + goto out_close; + } + out_free_pb: perf_buffer__free(pb); out_close: diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c index dde2b7ae7bc9..935a294f049a 100644 --- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c +++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c @@ -28,7 +28,7 @@ void test_prog_run_xattr(void) "err %d errno %d retval %d\n", err, errno, tattr.retval); CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out", - "incorrect output size, want %lu have %u\n", + "incorrect output size, want %zu have %u\n", sizeof(pkt_v4), tattr.data_size_out); CHECK_ATTR(buf[5] != 0, "overflow", diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c index 3b127cab4864..8826c652adad 100644 --- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c +++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c @@ -47,6 +47,15 @@ BTF_ID(struct, S) BTF_ID(union, U) BTF_ID(func, func) +BTF_SET_START(test_set) +BTF_ID(typedef, S) +BTF_ID(typedef, T) +BTF_ID(typedef, U) +BTF_ID(struct, S) +BTF_ID(union, U) +BTF_ID(func, func) +BTF_SET_END(test_set) + static int __resolve_symbol(struct btf *btf, int type_id) { @@ -116,12 +125,40 @@ int test_resolve_btfids(void) */ for (j = 0; j < ARRAY_SIZE(test_lists); j++) { test_list = test_lists[j]; - for (i = 0; i < ARRAY_SIZE(test_symbols) && !ret; i++) { + for (i = 0; i < ARRAY_SIZE(test_symbols); i++) { ret = CHECK(test_list[i] != test_symbols[i].id, "id_check", "wrong ID for %s (%d != %d)\n", test_symbols[i].name, test_list[i], test_symbols[i].id); + if (ret) + return ret; + } + } + + /* Check BTF_SET_START(test_set) IDs */ + for (i = 0; i < test_set.cnt; i++) { + bool found = false; + + for (j = 0; j < ARRAY_SIZE(test_symbols); j++) { + if (test_symbols[j].id != test_set.ids[i]) + continue; + found = true; + break; + } + + ret = CHECK(!found, "id_check", + "ID %d not found in test_symbols\n", + test_set.ids[i]); + if (ret) + break; + + if (i > 0) { + ret = CHECK(test_set.ids[i - 1] > test_set.ids[i], + "sort_check", + "test_set is not sorted\n"); + if (ret) + break; } } diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 47fa04adc147..a49a26f95a8b 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -49,7 +49,7 @@ configure_stack(void) sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf", "direct-action object-file ./test_sk_assign.o", "section classifier/sk_assign_test", - (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : ""); + (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose"); if (CHECK(system(tc_cmd), "BPF load failed;", "run with -vv for more info\n")) return false; @@ -268,6 +268,7 @@ void test_sk_assign(void) int server = -1; int server_map; int self_net; + int i; self_net = open(NS_SELF, O_RDONLY); if (CHECK_FAIL(self_net < 0)) { @@ -286,7 +287,7 @@ void test_sk_assign(void) goto cleanup; } - for (int i = 0; i < ARRAY_SIZE(tests) && !READ_ONCE(stop); i++) { + for (i = 0; i < ARRAY_SIZE(tests) && !READ_ONCE(stop); i++) { struct test_sk_cfg *test = &tests[i]; const struct sockaddr *addr; const int zero = 0; diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c index c571584c00f5..9ff0412e1fd3 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -309,6 +309,7 @@ static void v4_to_v6(struct sockaddr_storage *ss) v6->sin6_addr.s6_addr[10] = 0xff; v6->sin6_addr.s6_addr[11] = 0xff; memcpy(&v6->sin6_addr.s6_addr[12], &v4.sin_addr.s_addr, 4); + memset(&v6->sin6_addr.s6_addr[0], 0, 10); } static int udp_recv_send(int server_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index 25de86af2d03..fafeddaad6a9 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -81,7 +81,7 @@ void test_skb_ctx(void) CHECK_ATTR(tattr.ctx_size_out != sizeof(skb), "ctx_size_out", - "incorrect output size, want %lu have %u\n", + "incorrect output size, want %zu have %u\n", sizeof(skb), tattr.ctx_size_out); for (i = 0; i < 5; i++) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 96e7b7f84c65..0b79d78b98db 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -4,6 +4,8 @@ #include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" +#include "test_sockmap_update.skel.h" +#include "test_sockmap_invalid_update.skel.h" #define TCP_REPAIR 19 /* TCP sock is under repair right now */ @@ -101,6 +103,74 @@ out: test_skmsg_load_helpers__destroy(skel); } +static void test_sockmap_update(enum bpf_map_type map_type) +{ + struct bpf_prog_test_run_attr tattr; + int err, prog, src, dst, duration = 0; + struct test_sockmap_update *skel; + __u64 src_cookie, dst_cookie; + const __u32 zero = 0; + char dummy[14] = {0}; + __s64 sk; + + sk = connected_socket_v4(); + if (CHECK(sk == -1, "connected_socket_v4", "cannot connect\n")) + return; + + skel = test_sockmap_update__open_and_load(); + if (CHECK(!skel, "open_and_load", "cannot load skeleton\n")) + goto close_sk; + + prog = bpf_program__fd(skel->progs.copy_sock_map); + src = bpf_map__fd(skel->maps.src); + if (map_type == BPF_MAP_TYPE_SOCKMAP) + dst = bpf_map__fd(skel->maps.dst_sock_map); + else + dst = bpf_map__fd(skel->maps.dst_sock_hash); + + err = bpf_map_update_elem(src, &zero, &sk, BPF_NOEXIST); + if (CHECK(err, "update_elem(src)", "errno=%u\n", errno)) + goto out; + + err = bpf_map_lookup_elem(src, &zero, &src_cookie); + if (CHECK(err, "lookup_elem(src, cookie)", "errno=%u\n", errno)) + goto out; + + tattr = (struct bpf_prog_test_run_attr){ + .prog_fd = prog, + .repeat = 1, + .data_in = dummy, + .data_size_in = sizeof(dummy), + }; + + err = bpf_prog_test_run_xattr(&tattr); + if (CHECK_ATTR(err || !tattr.retval, "bpf_prog_test_run", + "errno=%u retval=%u\n", errno, tattr.retval)) + goto out; + + err = bpf_map_lookup_elem(dst, &zero, &dst_cookie); + if (CHECK(err, "lookup_elem(dst, cookie)", "errno=%u\n", errno)) + goto out; + + CHECK(dst_cookie != src_cookie, "cookie mismatch", "%llu != %llu\n", + dst_cookie, src_cookie); + +out: + test_sockmap_update__destroy(skel); +close_sk: + close(sk); +} + +static void test_sockmap_invalid_update(void) +{ + struct test_sockmap_invalid_update *skel; + int duration = 0; + + skel = test_sockmap_invalid_update__open_and_load(); + if (CHECK(skel, "open_and_load", "verifier accepted map_update\n")) + test_sockmap_invalid_update__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -111,4 +181,10 @@ void test_sockmap_basic(void) test_skmsg_helpers(BPF_MAP_TYPE_SOCKMAP); if (test__start_subtest("sockhash sk_msg load helpers")) test_skmsg_helpers(BPF_MAP_TYPE_SOCKHASH); + if (test__start_subtest("sockmap update")) + test_sockmap_update(BPF_MAP_TYPE_SOCKMAP); + if (test__start_subtest("sockhash update")) + test_sockmap_update(BPF_MAP_TYPE_SOCKHASH); + if (test__start_subtest("sockmap update in unsafe context")) + test_sockmap_invalid_update(); } diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c new file mode 100644 index 000000000000..24ba0d21b641 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c @@ -0,0 +1,622 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#define _GNU_SOURCE +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <linux/compiler.h> + +#include "test_progs.h" +#include "cgroup_helpers.h" +#include "network_helpers.h" +#include "test_tcp_hdr_options.h" +#include "test_tcp_hdr_options.skel.h" +#include "test_misc_tcp_hdr_options.skel.h" + +#define LO_ADDR6 "::eB9F" +#define CG_NAME "/tcpbpf-hdr-opt-test" + +struct bpf_test_option exp_passive_estab_in; +struct bpf_test_option exp_active_estab_in; +struct bpf_test_option exp_passive_fin_in; +struct bpf_test_option exp_active_fin_in; +struct hdr_stg exp_passive_hdr_stg; +struct hdr_stg exp_active_hdr_stg = { .active = true, }; + +static struct test_misc_tcp_hdr_options *misc_skel; +static struct test_tcp_hdr_options *skel; +static int lport_linum_map_fd; +static int hdr_stg_map_fd; +static __u32 duration; +static int cg_fd; + +struct sk_fds { + int srv_fd; + int passive_fd; + int active_fd; + int passive_lport; + int active_lport; +}; + +static int add_lo_addr(void) +{ + char ip_addr_cmd[256]; + int cmdlen; + + cmdlen = snprintf(ip_addr_cmd, sizeof(ip_addr_cmd), + "ip -6 addr add %s/128 dev lo scope host", + LO_ADDR6); + + if (CHECK(cmdlen >= sizeof(ip_addr_cmd), "compile ip cmd", + "failed to add host addr %s to lo. ip cmdlen is too long\n", + LO_ADDR6)) + return -1; + + if (CHECK(system(ip_addr_cmd), "run ip cmd", + "failed to add host addr %s to lo\n", LO_ADDR6)) + return -1; + + return 0; +} + +static int create_netns(void) +{ + if (CHECK(unshare(CLONE_NEWNET), "create netns", + "unshare(CLONE_NEWNET): %s (%d)", + strerror(errno), errno)) + return -1; + + if (CHECK(system("ip link set dev lo up"), "run ip cmd", + "failed to bring lo link up\n")) + return -1; + + if (add_lo_addr()) + return -1; + + return 0; +} + +static int write_sysctl(const char *sysctl, const char *value) +{ + int fd, err, len; + + fd = open(sysctl, O_WRONLY); + if (CHECK(fd == -1, "open sysctl", "open(%s): %s (%d)\n", + sysctl, strerror(errno), errno)) + return -1; + + len = strlen(value); + err = write(fd, value, len); + close(fd); + if (CHECK(err != len, "write sysctl", + "write(%s, %s): err:%d %s (%d)\n", + sysctl, value, err, strerror(errno), errno)) + return -1; + + return 0; +} + +static void print_hdr_stg(const struct hdr_stg *hdr_stg, const char *prefix) +{ + fprintf(stderr, "%s{active:%u, resend_syn:%u, syncookie:%u, fastopen:%u}\n", + prefix ? : "", hdr_stg->active, hdr_stg->resend_syn, + hdr_stg->syncookie, hdr_stg->fastopen); +} + +static void print_option(const struct bpf_test_option *opt, const char *prefix) +{ + fprintf(stderr, "%s{flags:0x%x, max_delack_ms:%u, rand:0x%x}\n", + prefix ? : "", opt->flags, opt->max_delack_ms, opt->rand); +} + +static void sk_fds_close(struct sk_fds *sk_fds) +{ + close(sk_fds->srv_fd); + close(sk_fds->passive_fd); + close(sk_fds->active_fd); +} + +static int sk_fds_shutdown(struct sk_fds *sk_fds) +{ + int ret, abyte; + + shutdown(sk_fds->active_fd, SHUT_WR); + ret = read(sk_fds->passive_fd, &abyte, sizeof(abyte)); + if (CHECK(ret != 0, "read-after-shutdown(passive_fd):", + "ret:%d %s (%d)\n", + ret, strerror(errno), errno)) + return -1; + + shutdown(sk_fds->passive_fd, SHUT_WR); + ret = read(sk_fds->active_fd, &abyte, sizeof(abyte)); + if (CHECK(ret != 0, "read-after-shutdown(active_fd):", + "ret:%d %s (%d)\n", + ret, strerror(errno), errno)) + return -1; + + return 0; +} + +static int sk_fds_connect(struct sk_fds *sk_fds, bool fast_open) +{ + const char fast[] = "FAST!!!"; + struct sockaddr_in6 addr6; + socklen_t len; + + sk_fds->srv_fd = start_server(AF_INET6, SOCK_STREAM, LO_ADDR6, 0, 0); + if (CHECK(sk_fds->srv_fd == -1, "start_server", "%s (%d)\n", + strerror(errno), errno)) + goto error; + + if (fast_open) + sk_fds->active_fd = fastopen_connect(sk_fds->srv_fd, fast, + sizeof(fast), 0); + else + sk_fds->active_fd = connect_to_fd(sk_fds->srv_fd, 0); + + if (CHECK_FAIL(sk_fds->active_fd == -1)) { + close(sk_fds->srv_fd); + goto error; + } + + len = sizeof(addr6); + if (CHECK(getsockname(sk_fds->srv_fd, (struct sockaddr *)&addr6, + &len), "getsockname(srv_fd)", "%s (%d)\n", + strerror(errno), errno)) + goto error_close; + sk_fds->passive_lport = ntohs(addr6.sin6_port); + + len = sizeof(addr6); + if (CHECK(getsockname(sk_fds->active_fd, (struct sockaddr *)&addr6, + &len), "getsockname(active_fd)", "%s (%d)\n", + strerror(errno), errno)) + goto error_close; + sk_fds->active_lport = ntohs(addr6.sin6_port); + + sk_fds->passive_fd = accept(sk_fds->srv_fd, NULL, 0); + if (CHECK(sk_fds->passive_fd == -1, "accept(srv_fd)", "%s (%d)\n", + strerror(errno), errno)) + goto error_close; + + if (fast_open) { + char bytes_in[sizeof(fast)]; + int ret; + + ret = read(sk_fds->passive_fd, bytes_in, sizeof(bytes_in)); + if (CHECK(ret != sizeof(fast), "read fastopen syn data", + "expected=%lu actual=%d\n", sizeof(fast), ret)) { + close(sk_fds->passive_fd); + goto error_close; + } + } + + return 0; + +error_close: + close(sk_fds->active_fd); + close(sk_fds->srv_fd); + +error: + memset(sk_fds, -1, sizeof(*sk_fds)); + return -1; +} + +static int check_hdr_opt(const struct bpf_test_option *exp, + const struct bpf_test_option *act, + const char *hdr_desc) +{ + if (CHECK(memcmp(exp, act, sizeof(*exp)), + "expected-vs-actual", "unexpected %s\n", hdr_desc)) { + print_option(exp, "expected: "); + print_option(act, " actual: "); + return -1; + } + + return 0; +} + +static int check_hdr_stg(const struct hdr_stg *exp, int fd, + const char *stg_desc) +{ + struct hdr_stg act; + + if (CHECK(bpf_map_lookup_elem(hdr_stg_map_fd, &fd, &act), + "map_lookup(hdr_stg_map_fd)", "%s %s (%d)\n", + stg_desc, strerror(errno), errno)) + return -1; + + if (CHECK(memcmp(exp, &act, sizeof(*exp)), + "expected-vs-actual", "unexpected %s\n", stg_desc)) { + print_hdr_stg(exp, "expected: "); + print_hdr_stg(&act, " actual: "); + return -1; + } + + return 0; +} + +static int check_error_linum(const struct sk_fds *sk_fds) +{ + unsigned int nr_errors = 0; + struct linum_err linum_err; + int lport; + + lport = sk_fds->passive_lport; + if (!bpf_map_lookup_elem(lport_linum_map_fd, &lport, &linum_err)) { + fprintf(stderr, + "bpf prog error out at lport:passive(%d), linum:%u err:%d\n", + lport, linum_err.linum, linum_err.err); + nr_errors++; + } + + lport = sk_fds->active_lport; + if (!bpf_map_lookup_elem(lport_linum_map_fd, &lport, &linum_err)) { + fprintf(stderr, + "bpf prog error out at lport:active(%d), linum:%u err:%d\n", + lport, linum_err.linum, linum_err.err); + nr_errors++; + } + + return nr_errors; +} + +static void check_hdr_and_close_fds(struct sk_fds *sk_fds) +{ + if (sk_fds_shutdown(sk_fds)) + goto check_linum; + + if (check_hdr_stg(&exp_passive_hdr_stg, sk_fds->passive_fd, + "passive_hdr_stg")) + goto check_linum; + + if (check_hdr_stg(&exp_active_hdr_stg, sk_fds->active_fd, + "active_hdr_stg")) + goto check_linum; + + if (check_hdr_opt(&exp_passive_estab_in, &skel->bss->passive_estab_in, + "passive_estab_in")) + goto check_linum; + + if (check_hdr_opt(&exp_active_estab_in, &skel->bss->active_estab_in, + "active_estab_in")) + goto check_linum; + + if (check_hdr_opt(&exp_passive_fin_in, &skel->bss->passive_fin_in, + "passive_fin_in")) + goto check_linum; + + check_hdr_opt(&exp_active_fin_in, &skel->bss->active_fin_in, + "active_fin_in"); + +check_linum: + CHECK_FAIL(check_error_linum(sk_fds)); + sk_fds_close(sk_fds); +} + +static void prepare_out(void) +{ + skel->bss->active_syn_out = exp_passive_estab_in; + skel->bss->passive_synack_out = exp_active_estab_in; + + skel->bss->active_fin_out = exp_passive_fin_in; + skel->bss->passive_fin_out = exp_active_fin_in; +} + +static void reset_test(void) +{ + size_t optsize = sizeof(struct bpf_test_option); + int lport, err; + + memset(&skel->bss->passive_synack_out, 0, optsize); + memset(&skel->bss->passive_fin_out, 0, optsize); + + memset(&skel->bss->passive_estab_in, 0, optsize); + memset(&skel->bss->passive_fin_in, 0, optsize); + + memset(&skel->bss->active_syn_out, 0, optsize); + memset(&skel->bss->active_fin_out, 0, optsize); + + memset(&skel->bss->active_estab_in, 0, optsize); + memset(&skel->bss->active_fin_in, 0, optsize); + + skel->data->test_kind = TCPOPT_EXP; + skel->data->test_magic = 0xeB9F; + + memset(&exp_passive_estab_in, 0, optsize); + memset(&exp_active_estab_in, 0, optsize); + memset(&exp_passive_fin_in, 0, optsize); + memset(&exp_active_fin_in, 0, optsize); + + memset(&exp_passive_hdr_stg, 0, sizeof(exp_passive_hdr_stg)); + memset(&exp_active_hdr_stg, 0, sizeof(exp_active_hdr_stg)); + exp_active_hdr_stg.active = true; + + err = bpf_map_get_next_key(lport_linum_map_fd, NULL, &lport); + while (!err) { + bpf_map_delete_elem(lport_linum_map_fd, &lport); + err = bpf_map_get_next_key(lport_linum_map_fd, &lport, &lport); + } +} + +static void fastopen_estab(void) +{ + struct bpf_link *link; + struct sk_fds sk_fds; + + hdr_stg_map_fd = bpf_map__fd(skel->maps.hdr_stg_map); + lport_linum_map_fd = bpf_map__fd(skel->maps.lport_linum_map); + + exp_passive_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS; + exp_passive_estab_in.rand = 0xfa; + exp_passive_estab_in.max_delack_ms = 11; + + exp_active_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS; + exp_active_estab_in.rand = 0xce; + exp_active_estab_in.max_delack_ms = 22; + + exp_passive_hdr_stg.fastopen = true; + + prepare_out(); + + /* Allow fastopen without fastopen cookie */ + if (write_sysctl("/proc/sys/net/ipv4/tcp_fastopen", "1543")) + return; + + link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd); + if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n", + PTR_ERR(link))) + return; + + if (sk_fds_connect(&sk_fds, true)) { + bpf_link__destroy(link); + return; + } + + check_hdr_and_close_fds(&sk_fds); + bpf_link__destroy(link); +} + +static void syncookie_estab(void) +{ + struct bpf_link *link; + struct sk_fds sk_fds; + + hdr_stg_map_fd = bpf_map__fd(skel->maps.hdr_stg_map); + lport_linum_map_fd = bpf_map__fd(skel->maps.lport_linum_map); + + exp_passive_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS; + exp_passive_estab_in.rand = 0xfa; + exp_passive_estab_in.max_delack_ms = 11; + + exp_active_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS | + OPTION_F_RESEND; + exp_active_estab_in.rand = 0xce; + exp_active_estab_in.max_delack_ms = 22; + + exp_passive_hdr_stg.syncookie = true; + exp_active_hdr_stg.resend_syn = true, + + prepare_out(); + + /* Clear the RESEND to ensure the bpf prog can learn + * want_cookie and set the RESEND by itself. + */ + skel->bss->passive_synack_out.flags &= ~OPTION_F_RESEND; + + /* Enforce syncookie mode */ + if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "2")) + return; + + link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd); + if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n", + PTR_ERR(link))) + return; + + if (sk_fds_connect(&sk_fds, false)) { + bpf_link__destroy(link); + return; + } + + check_hdr_and_close_fds(&sk_fds); + bpf_link__destroy(link); +} + +static void fin(void) +{ + struct bpf_link *link; + struct sk_fds sk_fds; + + hdr_stg_map_fd = bpf_map__fd(skel->maps.hdr_stg_map); + lport_linum_map_fd = bpf_map__fd(skel->maps.lport_linum_map); + + exp_passive_fin_in.flags = OPTION_F_RAND; + exp_passive_fin_in.rand = 0xfa; + + exp_active_fin_in.flags = OPTION_F_RAND; + exp_active_fin_in.rand = 0xce; + + prepare_out(); + + if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1")) + return; + + link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd); + if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n", + PTR_ERR(link))) + return; + + if (sk_fds_connect(&sk_fds, false)) { + bpf_link__destroy(link); + return; + } + + check_hdr_and_close_fds(&sk_fds); + bpf_link__destroy(link); +} + +static void __simple_estab(bool exprm) +{ + struct bpf_link *link; + struct sk_fds sk_fds; + + hdr_stg_map_fd = bpf_map__fd(skel->maps.hdr_stg_map); + lport_linum_map_fd = bpf_map__fd(skel->maps.lport_linum_map); + + exp_passive_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS; + exp_passive_estab_in.rand = 0xfa; + exp_passive_estab_in.max_delack_ms = 11; + + exp_active_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS; + exp_active_estab_in.rand = 0xce; + exp_active_estab_in.max_delack_ms = 22; + + prepare_out(); + + if (!exprm) { + skel->data->test_kind = 0xB9; + skel->data->test_magic = 0; + } + + if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1")) + return; + + link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd); + if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n", + PTR_ERR(link))) + return; + + if (sk_fds_connect(&sk_fds, false)) { + bpf_link__destroy(link); + return; + } + + check_hdr_and_close_fds(&sk_fds); + bpf_link__destroy(link); +} + +static void no_exprm_estab(void) +{ + __simple_estab(false); +} + +static void simple_estab(void) +{ + __simple_estab(true); +} + +static void misc(void) +{ + const char send_msg[] = "MISC!!!"; + char recv_msg[sizeof(send_msg)]; + const unsigned int nr_data = 2; + struct bpf_link *link; + struct sk_fds sk_fds; + int i, ret; + + lport_linum_map_fd = bpf_map__fd(misc_skel->maps.lport_linum_map); + + if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1")) + return; + + link = bpf_program__attach_cgroup(misc_skel->progs.misc_estab, cg_fd); + if (CHECK(IS_ERR(link), "attach_cgroup(misc_estab)", "err: %ld\n", + PTR_ERR(link))) + return; + + if (sk_fds_connect(&sk_fds, false)) { + bpf_link__destroy(link); + return; + } + + for (i = 0; i < nr_data; i++) { + /* MSG_EOR to ensure skb will not be combined */ + ret = send(sk_fds.active_fd, send_msg, sizeof(send_msg), + MSG_EOR); + if (CHECK(ret != sizeof(send_msg), "send(msg)", "ret:%d\n", + ret)) + goto check_linum; + + ret = read(sk_fds.passive_fd, recv_msg, sizeof(recv_msg)); + if (CHECK(ret != sizeof(send_msg), "read(msg)", "ret:%d\n", + ret)) + goto check_linum; + } + + if (sk_fds_shutdown(&sk_fds)) + goto check_linum; + + CHECK(misc_skel->bss->nr_syn != 1, "unexpected nr_syn", + "expected (1) != actual (%u)\n", + misc_skel->bss->nr_syn); + + CHECK(misc_skel->bss->nr_data != nr_data, "unexpected nr_data", + "expected (%u) != actual (%u)\n", + nr_data, misc_skel->bss->nr_data); + + /* The last ACK may have been delayed, so it is either 1 or 2. */ + CHECK(misc_skel->bss->nr_pure_ack != 1 && + misc_skel->bss->nr_pure_ack != 2, + "unexpected nr_pure_ack", + "expected (1 or 2) != actual (%u)\n", + misc_skel->bss->nr_pure_ack); + + CHECK(misc_skel->bss->nr_fin != 1, "unexpected nr_fin", + "expected (1) != actual (%u)\n", + misc_skel->bss->nr_fin); + +check_linum: + CHECK_FAIL(check_error_linum(&sk_fds)); + sk_fds_close(&sk_fds); + bpf_link__destroy(link); +} + +struct test { + const char *desc; + void (*run)(void); +}; + +#define DEF_TEST(name) { #name, name } +static struct test tests[] = { + DEF_TEST(simple_estab), + DEF_TEST(no_exprm_estab), + DEF_TEST(syncookie_estab), + DEF_TEST(fastopen_estab), + DEF_TEST(fin), + DEF_TEST(misc), +}; + +void test_tcp_hdr_options(void) +{ + int i; + + skel = test_tcp_hdr_options__open_and_load(); + if (CHECK(!skel, "open and load skel", "failed")) + return; + + misc_skel = test_misc_tcp_hdr_options__open_and_load(); + if (CHECK(!misc_skel, "open and load misc test skel", "failed")) + goto skel_destroy; + + cg_fd = test__join_cgroup(CG_NAME); + if (CHECK_FAIL(cg_fd < 0)) + goto skel_destroy; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (!test__start_subtest(tests[i].desc)) + continue; + + if (create_netns()) + break; + + tests[i].run(); + + reset_test(); + } + + close(cg_fd); +skel_destroy: + test_misc_tcp_hdr_options__destroy(misc_skel); + test_tcp_hdr_options__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c new file mode 100644 index 000000000000..172c999e523c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define _GNU_SOURCE +#include <sched.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <test_progs.h> + +#define TDIR "/sys/kernel/debug" + +static int read_iter(char *file) +{ + /* 1024 should be enough to get contiguous 4 "iter" letters at some point */ + char buf[1024]; + int fd, len; + + fd = open(file, 0); + if (fd < 0) + return -1; + while ((len = read(fd, buf, sizeof(buf))) > 0) + if (strstr(buf, "iter")) { + close(fd); + return 0; + } + close(fd); + return -1; +} + +static int fn(void) +{ + int err, duration = 0; + + err = unshare(CLONE_NEWNS); + if (CHECK(err, "unshare", "failed: %d\n", errno)) + goto out; + + err = mount("", "/", "", MS_REC | MS_PRIVATE, NULL); + if (CHECK(err, "mount /", "failed: %d\n", errno)) + goto out; + + err = umount(TDIR); + if (CHECK(err, "umount " TDIR, "failed: %d\n", errno)) + goto out; + + err = mount("none", TDIR, "tmpfs", 0, NULL); + if (CHECK(err, "mount", "mount root failed: %d\n", errno)) + goto out; + + err = mkdir(TDIR "/fs1", 0777); + if (CHECK(err, "mkdir "TDIR"/fs1", "failed: %d\n", errno)) + goto out; + err = mkdir(TDIR "/fs2", 0777); + if (CHECK(err, "mkdir "TDIR"/fs2", "failed: %d\n", errno)) + goto out; + + err = mount("bpf", TDIR "/fs1", "bpf", 0, NULL); + if (CHECK(err, "mount bpffs "TDIR"/fs1", "failed: %d\n", errno)) + goto out; + err = mount("bpf", TDIR "/fs2", "bpf", 0, NULL); + if (CHECK(err, "mount bpffs " TDIR "/fs2", "failed: %d\n", errno)) + goto out; + + err = read_iter(TDIR "/fs1/maps.debug"); + if (CHECK(err, "reading " TDIR "/fs1/maps.debug", "failed\n")) + goto out; + err = read_iter(TDIR "/fs2/progs.debug"); + if (CHECK(err, "reading " TDIR "/fs2/progs.debug", "failed\n")) + goto out; +out: + umount(TDIR "/fs1"); + umount(TDIR "/fs2"); + rmdir(TDIR "/fs1"); + rmdir(TDIR "/fs2"); + umount(TDIR); + exit(err); +} + +void test_test_bpffs(void) +{ + int err, duration = 0, status = 0; + pid_t pid; + + pid = fork(); + if (CHECK(pid == -1, "clone", "clone failed %d", errno)) + return; + if (pid == 0) + fn(); + err = waitpid(pid, &status, 0); + if (CHECK(err == -1 && errno != ECHILD, "waitpid", "failed %d", errno)) + return; + if (CHECK(WEXITSTATUS(status), "bpffs test ", "failed %d", WEXITSTATUS(status))) + return; +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 25b068591e9a..193002b14d7f 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -19,7 +19,7 @@ static int libbpf_debug_print(enum libbpf_print_level level, log_buf = va_arg(args, char *); if (!log_buf) goto out; - if (strstr(log_buf, err_str) == 0) + if (err_str && strstr(log_buf, err_str) == 0) found = true; out: printf(format, log_buf); diff --git a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c new file mode 100644 index 000000000000..91cd6f357246 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2020 Google LLC. + */ + +#include <test_progs.h> +#include <linux/limits.h> + +#include "local_storage.skel.h" +#include "network_helpers.h" + +int create_and_unlink_file(void) +{ + char fname[PATH_MAX] = "/tmp/fileXXXXXX"; + int fd; + + fd = mkstemp(fname); + if (fd < 0) + return fd; + + close(fd); + unlink(fname); + return 0; +} + +void test_test_local_storage(void) +{ + struct local_storage *skel = NULL; + int err, duration = 0, serv_sk = -1; + + skel = local_storage__open_and_load(); + if (CHECK(!skel, "skel_load", "lsm skeleton failed\n")) + goto close_prog; + + err = local_storage__attach(skel); + if (CHECK(err, "attach", "lsm attach failed: %d\n", err)) + goto close_prog; + + skel->bss->monitored_pid = getpid(); + + err = create_and_unlink_file(); + if (CHECK(err < 0, "exec_cmd", "err %d errno %d\n", err, errno)) + goto close_prog; + + CHECK(skel->data->inode_storage_result != 0, "inode_storage_result", + "inode_local_storage not set\n"); + + serv_sk = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (CHECK(serv_sk < 0, "start_server", "failed to start server\n")) + goto close_prog; + + CHECK(skel->data->sk_storage_result != 0, "sk_storage_result", + "sk_local_storage not set\n"); + + close(serv_sk); + +close_prog: + local_storage__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c index b17eb2045c1d..6ab29226c99b 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c +++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c @@ -10,6 +10,7 @@ #include <unistd.h> #include <malloc.h> #include <stdlib.h> +#include <unistd.h> #include "lsm.skel.h" @@ -55,6 +56,7 @@ void test_test_lsm(void) { struct lsm *skel = NULL; int err, duration = 0; + int buf = 1234; skel = lsm__open_and_load(); if (CHECK(!skel, "skel_load", "lsm skeleton failed\n")) @@ -81,6 +83,13 @@ void test_test_lsm(void) CHECK(skel->bss->mprotect_count != 1, "mprotect_count", "mprotect_count = %d\n", skel->bss->mprotect_count); + syscall(__NR_setdomainname, &buf, -2L); + syscall(__NR_setdomainname, 0, -3L); + syscall(__NR_setdomainname, ~0L, -4L); + + CHECK(skel->bss->copy_test != 3, "copy_test", + "copy_test = %d\n", skel->bss->copy_test); + close_prog: lsm__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/varlen.c b/tools/testing/selftests/bpf/prog_tests/varlen.c index c75525eab02c..dd324b4933db 100644 --- a/tools/testing/selftests/bpf/prog_tests/varlen.c +++ b/tools/testing/selftests/bpf/prog_tests/varlen.c @@ -44,25 +44,25 @@ void test_varlen(void) CHECK_VAL(bss->payload1_len2, size2); CHECK_VAL(bss->total1, size1 + size2); CHECK(memcmp(bss->payload1, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); CHECK_VAL(data->payload2_len1, size1); CHECK_VAL(data->payload2_len2, size2); CHECK_VAL(data->total2, size1 + size2); CHECK(memcmp(data->payload2, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); CHECK_VAL(data->payload3_len1, size1); CHECK_VAL(data->payload3_len2, size2); CHECK_VAL(data->total3, size1 + size2); CHECK(memcmp(data->payload3, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); CHECK_VAL(data->payload4_len1, size1); CHECK_VAL(data->payload4_len2, size2); CHECK_VAL(data->total4, size1 + size2); CHECK(memcmp(data->payload4, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); cleanup: test_varlen__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval.c new file mode 100644 index 000000000000..48e62f3f074f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enumval x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___diff.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___diff.c new file mode 100644 index 000000000000..53e5e5a76888 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___diff.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enumval___diff x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___err_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___err_missing.c new file mode 100644 index 000000000000..d024fb2ac06e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___err_missing.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enumval___err_missing x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___val3_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___val3_missing.c new file mode 100644 index 000000000000..9de6595d250c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___val3_missing.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enumval___val3_missing x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_size___err_ambiguous.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___err_ambiguous.c new file mode 100644 index 000000000000..f3e9904df9c2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___err_ambiguous.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_size___err_ambiguous1 x, + struct core_reloc_size___err_ambiguous2 y) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based.c new file mode 100644 index 000000000000..fc3f69e58c71 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___all_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___all_missing.c new file mode 100644 index 000000000000..51511648b4ec --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___all_missing.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based___all_missing x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___diff_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___diff_sz.c new file mode 100644 index 000000000000..67db3dceb279 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___diff_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based___diff_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___fn_wrong_args.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___fn_wrong_args.c new file mode 100644 index 000000000000..b357fc65431d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___fn_wrong_args.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based___fn_wrong_args x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___incompat.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___incompat.c new file mode 100644 index 000000000000..8ddf20d33d9e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___incompat.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based___incompat x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id.c new file mode 100644 index 000000000000..abbe5bddcefd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_id x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id___missing_targets.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id___missing_targets.c new file mode 100644 index 000000000000..24e7caf4f013 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id___missing_targets.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_id___missing_targets x) {} diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h index 34d84717c946..e6e616cb7bc9 100644 --- a/tools/testing/selftests/bpf/progs/core_reloc_types.h +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -1,5 +1,10 @@ #include <stdint.h> #include <stdbool.h> + +void preserce_ptr_sz_fn(long x) {} + +#define __bpf_aligned __attribute__((aligned(8))) + /* * KERNEL */ @@ -444,51 +449,51 @@ struct core_reloc_primitives { char a; int b; enum core_reloc_primitives_enum c; - void *d; - int (*f)(const char *); + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___diff_enum_def { char a; int b; - void *d; - int (*f)(const char *); + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; enum { X = 100, Y = 200, - } c; /* inline enum def with differing set of values */ + } c __bpf_aligned; /* inline enum def with differing set of values */ }; struct core_reloc_primitives___diff_func_proto { - void (*f)(int); /* incompatible function prototype */ - void *d; - enum core_reloc_primitives_enum c; + void (*f)(int) __bpf_aligned; /* incompatible function prototype */ + void *d __bpf_aligned; + enum core_reloc_primitives_enum c __bpf_aligned; int b; char a; }; struct core_reloc_primitives___diff_ptr_type { - const char * const d; /* different pointee type + modifiers */ - char a; + const char * const d __bpf_aligned; /* different pointee type + modifiers */ + char a __bpf_aligned; int b; enum core_reloc_primitives_enum c; - int (*f)(const char *); + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___err_non_enum { char a[1]; int b; int c; /* int instead of enum */ - void *d; - int (*f)(const char *); + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___err_non_int { char a[1]; - int *b; /* ptr instead of int */ - enum core_reloc_primitives_enum c; - void *d; - int (*f)(const char *); + int *b __bpf_aligned; /* ptr instead of int */ + enum core_reloc_primitives_enum c __bpf_aligned; + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___err_non_ptr { @@ -496,7 +501,7 @@ struct core_reloc_primitives___err_non_ptr { int b; enum core_reloc_primitives_enum c; int d; /* int instead of ptr */ - int (*f)(const char *); + int (*f)(const char *) __bpf_aligned; }; /* @@ -507,7 +512,7 @@ struct core_reloc_mods_output { }; typedef const int int_t; -typedef const char *char_ptr_t; +typedef const char *char_ptr_t __bpf_aligned; typedef const int arr_t[7]; struct core_reloc_mods_substruct { @@ -523,9 +528,9 @@ typedef struct { struct core_reloc_mods { int a; int_t b; - char *c; + char *c __bpf_aligned; char_ptr_t d; - int e[3]; + int e[3] __bpf_aligned; arr_t f; struct core_reloc_mods_substruct g; core_reloc_mods_substruct_t h; @@ -535,9 +540,9 @@ struct core_reloc_mods { struct core_reloc_mods___mod_swap { int b; int_t a; - char *d; + char *d __bpf_aligned; char_ptr_t c; - int f[3]; + int f[3] __bpf_aligned; arr_t e; struct { int y; @@ -555,7 +560,7 @@ typedef arr1_t arr2_t; typedef arr2_t arr3_t; typedef arr3_t arr4_t; -typedef const char * const volatile fancy_char_ptr_t; +typedef const char * const volatile fancy_char_ptr_t __bpf_aligned; typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt; @@ -567,7 +572,7 @@ struct core_reloc_mods___typedefs { arr4_t e; fancy_char_ptr_t d; fancy_char_ptr_t c; - int3_t b; + int3_t b __bpf_aligned; int3_t a; }; @@ -647,7 +652,7 @@ struct core_reloc_misc_extensible { }; /* - * EXISTENCE + * FIELD EXISTENCE */ struct core_reloc_existence_output { int a_exists; @@ -739,19 +744,19 @@ struct core_reloc_bitfields___bit_sz_change { int8_t sb4: 1; /* 4 -> 1 */ int32_t sb20: 30; /* 20 -> 30 */ /* non-bitfields */ - uint16_t u32; /* 32 -> 16 */ - int64_t s32; /* 32 -> 64 */ + uint16_t u32; /* 32 -> 16 */ + int64_t s32 __bpf_aligned; /* 32 -> 64 */ }; /* turn bitfield into non-bitfield and vice versa */ struct core_reloc_bitfields___bitfield_vs_int { uint64_t ub1; /* 3 -> 64 non-bitfield */ uint8_t ub2; /* 20 -> 8 non-bitfield */ - int64_t ub7; /* 7 -> 64 non-bitfield signed */ - int64_t sb4; /* 4 -> 64 non-bitfield signed */ - uint64_t sb20; /* 20 -> 16 non-bitfield unsigned */ - int32_t u32: 20; /* 32 non-bitfield -> 20 bitfield */ - uint64_t s32: 60; /* 32 non-bitfield -> 60 bitfield */ + int64_t ub7 __bpf_aligned; /* 7 -> 64 non-bitfield signed */ + int64_t sb4 __bpf_aligned; /* 4 -> 64 non-bitfield signed */ + uint64_t sb20 __bpf_aligned; /* 20 -> 16 non-bitfield unsigned */ + int32_t u32: 20; /* 32 non-bitfield -> 20 bitfield */ + uint64_t s32: 60 __bpf_aligned; /* 32 non-bitfield -> 60 bitfield */ }; struct core_reloc_bitfields___just_big_enough { @@ -804,3 +809,353 @@ struct core_reloc_size___diff_sz { void *ptr_field; enum { OTHER_VALUE = 0xFFFFFFFFFFFFFFFF } enum_field; }; + +/* Error case of two candidates with the fields (int_field) at the same + * offset, but with differing final relocation values: size 4 vs size 1 + */ +struct core_reloc_size___err_ambiguous1 { + /* int at offset 0 */ + int int_field; + + struct { int x; } struct_field; + union { int x; } union_field; + int arr_field[4]; + void *ptr_field; + enum { VALUE___1 = 123 } enum_field; +}; + +struct core_reloc_size___err_ambiguous2 { + /* char at offset 0 */ + char int_field; + + struct { int x; } struct_field; + union { int x; } union_field; + int arr_field[4]; + void *ptr_field; + enum { VALUE___2 = 123 } enum_field; +}; + +/* + * TYPE EXISTENCE & SIZE + */ +struct core_reloc_type_based_output { + bool struct_exists; + bool union_exists; + bool enum_exists; + bool typedef_named_struct_exists; + bool typedef_anon_struct_exists; + bool typedef_struct_ptr_exists; + bool typedef_int_exists; + bool typedef_enum_exists; + bool typedef_void_ptr_exists; + bool typedef_func_proto_exists; + bool typedef_arr_exists; + + int struct_sz; + int union_sz; + int enum_sz; + int typedef_named_struct_sz; + int typedef_anon_struct_sz; + int typedef_struct_ptr_sz; + int typedef_int_sz; + int typedef_enum_sz; + int typedef_void_ptr_sz; + int typedef_func_proto_sz; + int typedef_arr_sz; +}; + +struct a_struct { + int x; +}; + +union a_union { + int y; + int z; +}; + +typedef struct a_struct named_struct_typedef; + +typedef struct { int x, y, z; } anon_struct_typedef; + +typedef struct { + int a, b, c; +} *struct_ptr_typedef; + +enum an_enum { + AN_ENUM_VAL1 = 1, + AN_ENUM_VAL2 = 2, + AN_ENUM_VAL3 = 3, +}; + +typedef int int_typedef; + +typedef enum { TYPEDEF_ENUM_VAL1, TYPEDEF_ENUM_VAL2 } enum_typedef; + +typedef void *void_ptr_typedef; + +typedef int (*func_proto_typedef)(long); + +typedef char arr_typedef[20]; + +struct core_reloc_type_based { + struct a_struct f1; + union a_union f2; + enum an_enum f3; + named_struct_typedef f4; + anon_struct_typedef f5; + struct_ptr_typedef f6; + int_typedef f7; + enum_typedef f8; + void_ptr_typedef f9; + func_proto_typedef f10; + arr_typedef f11; +}; + +/* no types in target */ +struct core_reloc_type_based___all_missing { +}; + +/* different type sizes, extra modifiers, anon vs named enums, etc */ +struct a_struct___diff_sz { + long x; + int y; + char z; +}; + +union a_union___diff_sz { + char yy; + char zz; +}; + +typedef struct a_struct___diff_sz named_struct_typedef___diff_sz; + +typedef struct { long xx, yy, zzz; } anon_struct_typedef___diff_sz; + +typedef struct { + char aa[1], bb[2], cc[3]; +} *struct_ptr_typedef___diff_sz; + +enum an_enum___diff_sz { + AN_ENUM_VAL1___diff_sz = 0x123412341234, + AN_ENUM_VAL2___diff_sz = 2, +}; + +typedef unsigned long int_typedef___diff_sz; + +typedef enum an_enum___diff_sz enum_typedef___diff_sz; + +typedef const void * const void_ptr_typedef___diff_sz; + +typedef int_typedef___diff_sz (*func_proto_typedef___diff_sz)(char); + +typedef int arr_typedef___diff_sz[2]; + +struct core_reloc_type_based___diff_sz { + struct a_struct___diff_sz f1; + union a_union___diff_sz f2; + enum an_enum___diff_sz f3; + named_struct_typedef___diff_sz f4; + anon_struct_typedef___diff_sz f5; + struct_ptr_typedef___diff_sz f6; + int_typedef___diff_sz f7; + enum_typedef___diff_sz f8; + void_ptr_typedef___diff_sz f9; + func_proto_typedef___diff_sz f10; + arr_typedef___diff_sz f11; +}; + +/* incompatibilities between target and local types */ +union a_struct___incompat { /* union instead of struct */ + int x; +}; + +struct a_union___incompat { /* struct instead of union */ + int y; + int z; +}; + +/* typedef to union, not to struct */ +typedef union a_struct___incompat named_struct_typedef___incompat; + +/* typedef to void pointer, instead of struct */ +typedef void *anon_struct_typedef___incompat; + +/* extra pointer indirection */ +typedef struct { + int a, b, c; +} **struct_ptr_typedef___incompat; + +/* typedef of a struct with int, instead of int */ +typedef struct { int x; } int_typedef___incompat; + +/* typedef to func_proto, instead of enum */ +typedef int (*enum_typedef___incompat)(void); + +/* pointer to char instead of void */ +typedef char *void_ptr_typedef___incompat; + +/* void return type instead of int */ +typedef void (*func_proto_typedef___incompat)(long); + +/* multi-dimensional array instead of a single-dimensional */ +typedef int arr_typedef___incompat[20][2]; + +struct core_reloc_type_based___incompat { + union a_struct___incompat f1; + struct a_union___incompat f2; + /* the only valid one is enum, to check that something still succeeds */ + enum an_enum f3; + named_struct_typedef___incompat f4; + anon_struct_typedef___incompat f5; + struct_ptr_typedef___incompat f6; + int_typedef___incompat f7; + enum_typedef___incompat f8; + void_ptr_typedef___incompat f9; + func_proto_typedef___incompat f10; + arr_typedef___incompat f11; +}; + +/* func_proto with incompatible signature */ +typedef void (*func_proto_typedef___fn_wrong_ret1)(long); +typedef int * (*func_proto_typedef___fn_wrong_ret2)(long); +typedef struct { int x; } int_struct_typedef; +typedef int_struct_typedef (*func_proto_typedef___fn_wrong_ret3)(long); +typedef int (*func_proto_typedef___fn_wrong_arg)(void *); +typedef int (*func_proto_typedef___fn_wrong_arg_cnt1)(long, long); +typedef int (*func_proto_typedef___fn_wrong_arg_cnt2)(void); + +struct core_reloc_type_based___fn_wrong_args { + /* one valid type to make sure relos still work */ + struct a_struct f1; + func_proto_typedef___fn_wrong_ret1 f2; + func_proto_typedef___fn_wrong_ret2 f3; + func_proto_typedef___fn_wrong_ret3 f4; + func_proto_typedef___fn_wrong_arg f5; + func_proto_typedef___fn_wrong_arg_cnt1 f6; + func_proto_typedef___fn_wrong_arg_cnt2 f7; +}; + +/* + * TYPE ID MAPPING (LOCAL AND TARGET) + */ +struct core_reloc_type_id_output { + int local_anon_struct; + int local_anon_union; + int local_anon_enum; + int local_anon_func_proto_ptr; + int local_anon_void_ptr; + int local_anon_arr; + + int local_struct; + int local_union; + int local_enum; + int local_int; + int local_struct_typedef; + int local_func_proto_typedef; + int local_arr_typedef; + + int targ_struct; + int targ_union; + int targ_enum; + int targ_int; + int targ_struct_typedef; + int targ_func_proto_typedef; + int targ_arr_typedef; +}; + +struct core_reloc_type_id { + struct a_struct f1; + union a_union f2; + enum an_enum f3; + named_struct_typedef f4; + func_proto_typedef f5; + arr_typedef f6; +}; + +struct core_reloc_type_id___missing_targets { + /* nothing */ +}; + +/* + * ENUMERATOR VALUE EXISTENCE AND VALUE RELOCATION + */ +struct core_reloc_enumval_output { + bool named_val1_exists; + bool named_val2_exists; + bool named_val3_exists; + bool anon_val1_exists; + bool anon_val2_exists; + bool anon_val3_exists; + + int named_val1; + int named_val2; + int anon_val1; + int anon_val2; +}; + +enum named_enum { + NAMED_ENUM_VAL1 = 1, + NAMED_ENUM_VAL2 = 2, + NAMED_ENUM_VAL3 = 3, +}; + +typedef enum { + ANON_ENUM_VAL1 = 0x10, + ANON_ENUM_VAL2 = 0x20, + ANON_ENUM_VAL3 = 0x30, +} anon_enum; + +struct core_reloc_enumval { + enum named_enum f1; + anon_enum f2; +}; + +/* differing enumerator values */ +enum named_enum___diff { + NAMED_ENUM_VAL1___diff = 101, + NAMED_ENUM_VAL2___diff = 202, + NAMED_ENUM_VAL3___diff = 303, +}; + +typedef enum { + ANON_ENUM_VAL1___diff = 0x11, + ANON_ENUM_VAL2___diff = 0x22, + ANON_ENUM_VAL3___diff = 0x33, +} anon_enum___diff; + +struct core_reloc_enumval___diff { + enum named_enum___diff f1; + anon_enum___diff f2; +}; + +/* missing (optional) third enum value */ +enum named_enum___val3_missing { + NAMED_ENUM_VAL1___val3_missing = 111, + NAMED_ENUM_VAL2___val3_missing = 222, +}; + +typedef enum { + ANON_ENUM_VAL1___val3_missing = 0x111, + ANON_ENUM_VAL2___val3_missing = 0x222, +} anon_enum___val3_missing; + +struct core_reloc_enumval___val3_missing { + enum named_enum___val3_missing f1; + anon_enum___val3_missing f2; +}; + +/* missing (mandatory) second enum value, should fail */ +enum named_enum___err_missing { + NAMED_ENUM_VAL1___err_missing = 1, + NAMED_ENUM_VAL3___err_missing = 3, +}; + +typedef enum { + ANON_ENUM_VAL1___err_missing = 0x111, + ANON_ENUM_VAL3___err_missing = 0x222, +} anon_enum___err_missing; + +struct core_reloc_enumval___err_missing { + enum named_enum___err_missing f1; + anon_enum___err_missing f2; +}; diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c index 98e1efe14549..49a84a3a2306 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/stddef.h> +#include <linux/if_ether.h> #include <linux/ipv6.h> #include <linux/bpf.h> +#include <linux/tcp.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> #include <bpf/bpf_tracing.h> @@ -151,4 +153,29 @@ int new_get_constant(long val) test_get_constant = 1; return test_get_constant; /* original get_constant() returns val - 122 */ } + +__u64 test_pkt_write_access_subprog = 0; +SEC("freplace/test_pkt_write_access_subprog") +int new_test_pkt_write_access_subprog(struct __sk_buff *skb, __u32 off) +{ + + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + struct tcphdr *tcp; + + if (off > sizeof(struct ethhdr) + sizeof(struct ipv6hdr)) + return -1; + + tcp = data + off; + if (tcp + 1 > data_end) + return -1; + + /* make modifications to the packet data */ + tcp->check++; + tcp->syn = 0; + + test_pkt_write_access_subprog = 1; + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_attach_probe.c b/tools/testing/selftests/bpf/progs/freplace_attach_probe.c new file mode 100644 index 000000000000..bb2a77c5b62b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_attach_probe.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define VAR_NUM 2 + +struct hmap_elem { + struct bpf_spin_lock lock; + int var[VAR_NUM]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct hmap_elem); +} hash_map SEC(".maps"); + +SEC("freplace/handle_kprobe") +int new_handle_kprobe(struct pt_regs *ctx) +{ + struct hmap_elem zero = {}, *val; + int key = 0; + + val = bpf_map_lookup_elem(&hash_map, &key); + if (!val) + return 1; + /* spin_lock in hash map */ + bpf_spin_lock(&val->lock); + val->var[0] = 99; + bpf_spin_unlock(&val->lock); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c new file mode 100644 index 000000000000..68a5a9db928a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/pkt_cls.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +struct bpf_map_def SEC("maps") sock_map = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 2, +}; + +SEC("freplace/cls_redirect") +int freplace_cls_redirect_test(struct __sk_buff *skb) +{ + int ret = 0; + const int zero = 0; + struct bpf_sock *sk; + + sk = bpf_map_lookup_elem(&sock_map, &zero); + if (!sk) + return TC_ACT_SHOT; + + ret = bpf_map_update_elem(&sock_map, &zero, sk, 0); + bpf_sk_release(sk); + + return ret == 0 ? TC_ACT_OK : TC_ACT_SHOT; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c new file mode 100644 index 000000000000..544e5ac90461 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/stddef.h> +#include <linux/ipv6.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +SEC("freplace/connect_v4_prog") +int new_connect_v4_prog(struct bpf_sock_addr *ctx) +{ + // return value thats in invalid range + return 255; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c new file mode 100644 index 000000000000..0758ba229ae0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/local_storage.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +#define DUMMY_STORAGE_VALUE 0xdeadbeef + +int monitored_pid = 0; +int inode_storage_result = -1; +int sk_storage_result = -1; + +struct dummy_storage { + __u32 value; +}; + +struct { + __uint(type, BPF_MAP_TYPE_INODE_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct dummy_storage); +} inode_storage_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct dummy_storage); +} sk_storage_map SEC(".maps"); + +/* TODO Use vmlinux.h once BTF pruning for embedded types is fixed. + */ +struct sock {} __attribute__((preserve_access_index)); +struct sockaddr {} __attribute__((preserve_access_index)); +struct socket { + struct sock *sk; +} __attribute__((preserve_access_index)); + +struct inode {} __attribute__((preserve_access_index)); +struct dentry { + struct inode *d_inode; +} __attribute__((preserve_access_index)); +struct file { + struct inode *f_inode; +} __attribute__((preserve_access_index)); + + +SEC("lsm/inode_unlink") +int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + struct dummy_storage *storage; + + if (pid != monitored_pid) + return 0; + + storage = bpf_inode_storage_get(&inode_storage_map, victim->d_inode, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + + if (storage->value == DUMMY_STORAGE_VALUE) + inode_storage_result = -1; + + inode_storage_result = + bpf_inode_storage_delete(&inode_storage_map, victim->d_inode); + + return 0; +} + +SEC("lsm/socket_bind") +int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, + int addrlen) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + struct dummy_storage *storage; + + if (pid != monitored_pid) + return 0; + + storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + + if (storage->value == DUMMY_STORAGE_VALUE) + sk_storage_result = -1; + + sk_storage_result = bpf_sk_storage_delete(&sk_storage_map, sock->sk); + return 0; +} + +SEC("lsm/socket_post_create") +int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, + int protocol, int kern) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + struct dummy_storage *storage; + + if (pid != monitored_pid) + return 0; + + storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + + storage->value = DUMMY_STORAGE_VALUE; + + return 0; +} + +SEC("lsm/file_open") +int BPF_PROG(file_open, struct file *file) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + struct dummy_storage *storage; + + if (pid != monitored_pid) + return 0; + + if (!file->f_inode) + return 0; + + storage = bpf_inode_storage_get(&inode_storage_map, file->f_inode, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + + storage->value = DUMMY_STORAGE_VALUE; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c index b4598d4bc4f7..ff4d343b94b5 100644 --- a/tools/testing/selftests/bpf/progs/lsm.c +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -9,6 +9,27 @@ #include <bpf/bpf_tracing.h> #include <errno.h> +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} lru_hash SEC(".maps"); + char _license[] SEC("license") = "GPL"; int monitored_pid = 0; @@ -36,13 +57,54 @@ int BPF_PROG(test_int_hook, struct vm_area_struct *vma, return ret; } -SEC("lsm/bprm_committed_creds") +SEC("lsm.s/bprm_committed_creds") int BPF_PROG(test_void_hook, struct linux_binprm *bprm) { __u32 pid = bpf_get_current_pid_tgid() >> 32; + char args[64]; + __u32 key = 0; + __u64 *value; if (monitored_pid == pid) bprm_count++; + bpf_copy_from_user(args, sizeof(args), (void *)bprm->vma->vm_mm->arg_start); + bpf_copy_from_user(args, sizeof(args), (void *)bprm->mm->arg_start); + + value = bpf_map_lookup_elem(&array, &key); + if (value) + *value = 0; + value = bpf_map_lookup_elem(&hash, &key); + if (value) + *value = 0; + value = bpf_map_lookup_elem(&lru_hash, &key); + if (value) + *value = 0; + + return 0; +} +SEC("lsm/task_free") /* lsm/ is ok, lsm.s/ fails */ +int BPF_PROG(test_task_free, struct task_struct *task) +{ + return 0; +} + +int copy_test = 0; + +SEC("fentry.s/__x64_sys_setdomainname") +int BPF_PROG(test_sys_setdomainname, struct pt_regs *regs) +{ + void *ptr = (void *)PT_REGS_PARM1(regs); + int len = PT_REGS_PARM2(regs); + int buf = 0; + long ret; + + ret = bpf_copy_from_user(&buf, sizeof(buf), ptr); + if (len == -2 && ret == 0 && buf == 1234) + copy_test++; + if (len == -3 && ret == -EFAULT) + copy_test++; + if (len == -4 && ret == -EFAULT) + copy_test++; return 0; } diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index 473665cac67e..982a2d8aa844 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -589,7 +589,7 @@ static inline int check_stack(void) return 1; } -struct bpf_sk_storage_map { +struct bpf_local_storage_map { struct bpf_map map; } __attribute__((preserve_access_index)); @@ -602,8 +602,8 @@ struct { static inline int check_sk_storage(void) { - struct bpf_sk_storage_map *sk_storage = - (struct bpf_sk_storage_map *)&m_sk_storage; + struct bpf_local_storage_map *sk_storage = + (struct bpf_local_storage_map *)&m_sk_storage; struct bpf_map *map = (struct bpf_map *)&m_sk_storage; VERIFY(check(&sk_storage->map, map, sizeof(__u32), sizeof(__u32), 0)); diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c index e5093796be97..193fe0198b21 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c @@ -11,6 +11,13 @@ struct inner_map { } inner_map1 SEC(".maps"), inner_map2 SEC(".maps"); +struct inner_map_sz2 { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, int); +} inner_map_sz2 SEC(".maps"); + struct outer_arr { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 3); @@ -50,6 +57,30 @@ struct outer_hash { }, }; +struct sockarr_sz1 { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sockarr_sz1 SEC(".maps"); + +struct sockarr_sz2 { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, int); +} sockarr_sz2 SEC(".maps"); + +struct outer_sockarr_sz1 { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __array(values, struct sockarr_sz1); +} outer_sockarr SEC(".maps") = { + .values = { (void *)&sockarr_sz1 }, +}; + int input = 0; SEC("raw_tp/sys_enter") diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_enumval.c b/tools/testing/selftests/bpf/progs/test_core_reloc_enumval.c new file mode 100644 index 000000000000..e7ef3dada2bf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_enumval.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; + bool skip; +} data = {}; + +enum named_enum { + NAMED_ENUM_VAL1 = 1, + NAMED_ENUM_VAL2 = 2, + NAMED_ENUM_VAL3 = 3, +}; + +typedef enum { + ANON_ENUM_VAL1 = 0x10, + ANON_ENUM_VAL2 = 0x20, + ANON_ENUM_VAL3 = 0x30, +} anon_enum; + +struct core_reloc_enumval_output { + bool named_val1_exists; + bool named_val2_exists; + bool named_val3_exists; + bool anon_val1_exists; + bool anon_val2_exists; + bool anon_val3_exists; + + int named_val1; + int named_val2; + int anon_val1; + int anon_val2; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_enumval(void *ctx) +{ +#if __has_builtin(__builtin_preserve_enum_value) + struct core_reloc_enumval_output *out = (void *)&data.out; + enum named_enum named = 0; + anon_enum anon = 0; + + out->named_val1_exists = bpf_core_enum_value_exists(named, NAMED_ENUM_VAL1); + out->named_val2_exists = bpf_core_enum_value_exists(enum named_enum, NAMED_ENUM_VAL2); + out->named_val3_exists = bpf_core_enum_value_exists(enum named_enum, NAMED_ENUM_VAL3); + + out->anon_val1_exists = bpf_core_enum_value_exists(anon, ANON_ENUM_VAL1); + out->anon_val2_exists = bpf_core_enum_value_exists(anon_enum, ANON_ENUM_VAL2); + out->anon_val3_exists = bpf_core_enum_value_exists(anon_enum, ANON_ENUM_VAL3); + + out->named_val1 = bpf_core_enum_value(named, NAMED_ENUM_VAL1); + out->named_val2 = bpf_core_enum_value(named, NAMED_ENUM_VAL2); + /* NAMED_ENUM_VAL3 value is optional */ + + out->anon_val1 = bpf_core_enum_value(anon, ANON_ENUM_VAL1); + out->anon_val2 = bpf_core_enum_value(anon, ANON_ENUM_VAL2); + /* ANON_ENUM_VAL3 value is optional */ +#else + data.skip = true; +#endif + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c index aba928fd60d3..145028b52ad8 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c @@ -3,6 +3,7 @@ #include <linux/bpf.h> #include <stdint.h> +#include <stdbool.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> @@ -11,6 +12,7 @@ char _license[] SEC("license") = "GPL"; struct { char in[256]; char out[256]; + bool skip; uint64_t my_pid_tgid; } data = {}; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_type_based.c b/tools/testing/selftests/bpf/progs/test_core_reloc_type_based.c new file mode 100644 index 000000000000..fb60f8195c53 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_type_based.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; + bool skip; +} data = {}; + +struct a_struct { + int x; +}; + +union a_union { + int y; + int z; +}; + +typedef struct a_struct named_struct_typedef; + +typedef struct { int x, y, z; } anon_struct_typedef; + +typedef struct { + int a, b, c; +} *struct_ptr_typedef; + +enum an_enum { + AN_ENUM_VAL1 = 1, + AN_ENUM_VAL2 = 2, + AN_ENUM_VAL3 = 3, +}; + +typedef int int_typedef; + +typedef enum { TYPEDEF_ENUM_VAL1, TYPEDEF_ENUM_VAL2 } enum_typedef; + +typedef void *void_ptr_typedef; + +typedef int (*func_proto_typedef)(long); + +typedef char arr_typedef[20]; + +struct core_reloc_type_based_output { + bool struct_exists; + bool union_exists; + bool enum_exists; + bool typedef_named_struct_exists; + bool typedef_anon_struct_exists; + bool typedef_struct_ptr_exists; + bool typedef_int_exists; + bool typedef_enum_exists; + bool typedef_void_ptr_exists; + bool typedef_func_proto_exists; + bool typedef_arr_exists; + + int struct_sz; + int union_sz; + int enum_sz; + int typedef_named_struct_sz; + int typedef_anon_struct_sz; + int typedef_struct_ptr_sz; + int typedef_int_sz; + int typedef_enum_sz; + int typedef_void_ptr_sz; + int typedef_func_proto_sz; + int typedef_arr_sz; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_type_based(void *ctx) +{ +#if __has_builtin(__builtin_preserve_type_info) + struct core_reloc_type_based_output *out = (void *)&data.out; + + out->struct_exists = bpf_core_type_exists(struct a_struct); + out->union_exists = bpf_core_type_exists(union a_union); + out->enum_exists = bpf_core_type_exists(enum an_enum); + out->typedef_named_struct_exists = bpf_core_type_exists(named_struct_typedef); + out->typedef_anon_struct_exists = bpf_core_type_exists(anon_struct_typedef); + out->typedef_struct_ptr_exists = bpf_core_type_exists(struct_ptr_typedef); + out->typedef_int_exists = bpf_core_type_exists(int_typedef); + out->typedef_enum_exists = bpf_core_type_exists(enum_typedef); + out->typedef_void_ptr_exists = bpf_core_type_exists(void_ptr_typedef); + out->typedef_func_proto_exists = bpf_core_type_exists(func_proto_typedef); + out->typedef_arr_exists = bpf_core_type_exists(arr_typedef); + + out->struct_sz = bpf_core_type_size(struct a_struct); + out->union_sz = bpf_core_type_size(union a_union); + out->enum_sz = bpf_core_type_size(enum an_enum); + out->typedef_named_struct_sz = bpf_core_type_size(named_struct_typedef); + out->typedef_anon_struct_sz = bpf_core_type_size(anon_struct_typedef); + out->typedef_struct_ptr_sz = bpf_core_type_size(struct_ptr_typedef); + out->typedef_int_sz = bpf_core_type_size(int_typedef); + out->typedef_enum_sz = bpf_core_type_size(enum_typedef); + out->typedef_void_ptr_sz = bpf_core_type_size(void_ptr_typedef); + out->typedef_func_proto_sz = bpf_core_type_size(func_proto_typedef); + out->typedef_arr_sz = bpf_core_type_size(arr_typedef); +#else + data.skip = true; +#endif + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c new file mode 100644 index 000000000000..22aba3f6e344 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; + bool skip; +} data = {}; + +/* some types are shared with test_core_reloc_type_based.c */ +struct a_struct { + int x; +}; + +union a_union { + int y; + int z; +}; + +enum an_enum { + AN_ENUM_VAL1 = 1, + AN_ENUM_VAL2 = 2, + AN_ENUM_VAL3 = 3, +}; + +typedef struct a_struct named_struct_typedef; + +typedef int (*func_proto_typedef)(long); + +typedef char arr_typedef[20]; + +struct core_reloc_type_id_output { + int local_anon_struct; + int local_anon_union; + int local_anon_enum; + int local_anon_func_proto_ptr; + int local_anon_void_ptr; + int local_anon_arr; + + int local_struct; + int local_union; + int local_enum; + int local_int; + int local_struct_typedef; + int local_func_proto_typedef; + int local_arr_typedef; + + int targ_struct; + int targ_union; + int targ_enum; + int targ_int; + int targ_struct_typedef; + int targ_func_proto_typedef; + int targ_arr_typedef; +}; + +/* preserve types even if Clang doesn't support built-in */ +struct a_struct t1 = {}; +union a_union t2 = {}; +enum an_enum t3 = 0; +named_struct_typedef t4 = {}; +func_proto_typedef t5 = 0; +arr_typedef t6 = {}; + +SEC("raw_tracepoint/sys_enter") +int test_core_type_id(void *ctx) +{ + /* We use __builtin_btf_type_id() in this tests, but up until the time + * __builtin_preserve_type_info() was added it contained a bug that + * would make this test fail. The bug was fixed ([0]) with addition of + * __builtin_preserve_type_info(), though, so that's what we are using + * to detect whether this test has to be executed, however strange + * that might look like. + * + * [0] https://reviews.llvm.org/D85174 + */ +#if __has_builtin(__builtin_preserve_type_info) + struct core_reloc_type_id_output *out = (void *)&data.out; + + out->local_anon_struct = bpf_core_type_id_local(struct { int marker_field; }); + out->local_anon_union = bpf_core_type_id_local(union { int marker_field; }); + out->local_anon_enum = bpf_core_type_id_local(enum { MARKER_ENUM_VAL = 123 }); + out->local_anon_func_proto_ptr = bpf_core_type_id_local(_Bool(*)(int)); + out->local_anon_void_ptr = bpf_core_type_id_local(void *); + out->local_anon_arr = bpf_core_type_id_local(_Bool[47]); + + out->local_struct = bpf_core_type_id_local(struct a_struct); + out->local_union = bpf_core_type_id_local(union a_union); + out->local_enum = bpf_core_type_id_local(enum an_enum); + out->local_int = bpf_core_type_id_local(int); + out->local_struct_typedef = bpf_core_type_id_local(named_struct_typedef); + out->local_func_proto_typedef = bpf_core_type_id_local(func_proto_typedef); + out->local_arr_typedef = bpf_core_type_id_local(arr_typedef); + + out->targ_struct = bpf_core_type_id_kernel(struct a_struct); + out->targ_union = bpf_core_type_id_kernel(union a_union); + out->targ_enum = bpf_core_type_id_kernel(enum an_enum); + out->targ_int = bpf_core_type_id_kernel(int); + out->targ_struct_typedef = bpf_core_type_id_kernel(named_struct_typedef); + out->targ_func_proto_typedef = bpf_core_type_id_kernel(func_proto_typedef); + out->targ_arr_typedef = bpf_core_type_id_kernel(arr_typedef); +#else + data.skip = true; +#endif + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_d_path.c b/tools/testing/selftests/bpf/progs/test_d_path.c new file mode 100644 index 000000000000..61f007855649 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_d_path.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define MAX_PATH_LEN 128 +#define MAX_FILES 7 + +pid_t my_pid = 0; +__u32 cnt_stat = 0; +__u32 cnt_close = 0; +char paths_stat[MAX_FILES][MAX_PATH_LEN] = {}; +char paths_close[MAX_FILES][MAX_PATH_LEN] = {}; +int rets_stat[MAX_FILES] = {}; +int rets_close[MAX_FILES] = {}; + +SEC("fentry/vfs_getattr") +int BPF_PROG(prog_stat, struct path *path, struct kstat *stat, + __u32 request_mask, unsigned int query_flags) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + __u32 cnt = cnt_stat; + int ret; + + if (pid != my_pid) + return 0; + + if (cnt >= MAX_FILES) + return 0; + ret = bpf_d_path(path, paths_stat[cnt], MAX_PATH_LEN); + + rets_stat[cnt] = ret; + cnt_stat++; + return 0; +} + +SEC("fentry/filp_close") +int BPF_PROG(prog_close, struct file *file, void *id) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + __u32 cnt = cnt_close; + int ret; + + if (pid != my_pid) + return 0; + + if (cnt >= MAX_FILES) + return 0; + ret = bpf_d_path(&file->f_path, + paths_close[cnt], MAX_PATH_LEN); + + rets_close[cnt] = ret; + cnt_close++; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c new file mode 100644 index 000000000000..3a216d1d0226 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c @@ -0,0 +1,325 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <stddef.h> +#include <errno.h> +#include <stdbool.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/socket.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#define BPF_PROG_TEST_TCP_HDR_OPTIONS +#include "test_tcp_hdr_options.h" + +__u16 last_addr16_n = __bpf_htons(0xeB9F); +__u16 active_lport_n = 0; +__u16 active_lport_h = 0; +__u16 passive_lport_n = 0; +__u16 passive_lport_h = 0; + +/* options received at passive side */ +unsigned int nr_pure_ack = 0; +unsigned int nr_data = 0; +unsigned int nr_syn = 0; +unsigned int nr_fin = 0; + +/* Check the header received from the active side */ +static int __check_active_hdr_in(struct bpf_sock_ops *skops, bool check_syn) +{ + union { + struct tcphdr th; + struct ipv6hdr ip6; + struct tcp_exprm_opt exprm_opt; + struct tcp_opt reg_opt; + __u8 data[100]; /* IPv6 (40) + Max TCP hdr (60) */ + } hdr = {}; + __u64 load_flags = check_syn ? BPF_LOAD_HDR_OPT_TCP_SYN : 0; + struct tcphdr *pth; + int ret; + + hdr.reg_opt.kind = 0xB9; + + /* The option is 4 bytes long instead of 2 bytes */ + ret = bpf_load_hdr_opt(skops, &hdr.reg_opt, 2, load_flags); + if (ret != -ENOSPC) + RET_CG_ERR(ret); + + /* Test searching magic with regular kind */ + hdr.reg_opt.len = 4; + ret = bpf_load_hdr_opt(skops, &hdr.reg_opt, sizeof(hdr.reg_opt), + load_flags); + if (ret != -EINVAL) + RET_CG_ERR(ret); + + hdr.reg_opt.len = 0; + ret = bpf_load_hdr_opt(skops, &hdr.reg_opt, sizeof(hdr.reg_opt), + load_flags); + if (ret != 4 || hdr.reg_opt.len != 4 || hdr.reg_opt.kind != 0xB9 || + hdr.reg_opt.data[0] != 0xfa || hdr.reg_opt.data[1] != 0xce) + RET_CG_ERR(ret); + + /* Test searching experimental option with invalid kind length */ + hdr.exprm_opt.kind = TCPOPT_EXP; + hdr.exprm_opt.len = 5; + hdr.exprm_opt.magic = 0; + ret = bpf_load_hdr_opt(skops, &hdr.exprm_opt, sizeof(hdr.exprm_opt), + load_flags); + if (ret != -EINVAL) + RET_CG_ERR(ret); + + /* Test searching experimental option with 0 magic value */ + hdr.exprm_opt.len = 4; + ret = bpf_load_hdr_opt(skops, &hdr.exprm_opt, sizeof(hdr.exprm_opt), + load_flags); + if (ret != -ENOMSG) + RET_CG_ERR(ret); + + hdr.exprm_opt.magic = __bpf_htons(0xeB9F); + ret = bpf_load_hdr_opt(skops, &hdr.exprm_opt, sizeof(hdr.exprm_opt), + load_flags); + if (ret != 4 || hdr.exprm_opt.len != 4 || + hdr.exprm_opt.kind != TCPOPT_EXP || + hdr.exprm_opt.magic != __bpf_htons(0xeB9F)) + RET_CG_ERR(ret); + + if (!check_syn) + return CG_OK; + + /* Test loading from skops->syn_skb if sk_state == TCP_NEW_SYN_RECV + * + * Test loading from tp->saved_syn for other sk_state. + */ + ret = bpf_getsockopt(skops, SOL_TCP, TCP_BPF_SYN_IP, &hdr.ip6, + sizeof(hdr.ip6)); + if (ret != -ENOSPC) + RET_CG_ERR(ret); + + if (hdr.ip6.saddr.s6_addr16[7] != last_addr16_n || + hdr.ip6.daddr.s6_addr16[7] != last_addr16_n) + RET_CG_ERR(0); + + ret = bpf_getsockopt(skops, SOL_TCP, TCP_BPF_SYN_IP, &hdr, sizeof(hdr)); + if (ret < 0) + RET_CG_ERR(ret); + + pth = (struct tcphdr *)(&hdr.ip6 + 1); + if (pth->dest != passive_lport_n || pth->source != active_lport_n) + RET_CG_ERR(0); + + ret = bpf_getsockopt(skops, SOL_TCP, TCP_BPF_SYN, &hdr, sizeof(hdr)); + if (ret < 0) + RET_CG_ERR(ret); + + if (hdr.th.dest != passive_lport_n || hdr.th.source != active_lport_n) + RET_CG_ERR(0); + + return CG_OK; +} + +static int check_active_syn_in(struct bpf_sock_ops *skops) +{ + return __check_active_hdr_in(skops, true); +} + +static int check_active_hdr_in(struct bpf_sock_ops *skops) +{ + struct tcphdr *th; + + if (__check_active_hdr_in(skops, false) == CG_ERR) + return CG_ERR; + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + if (tcp_hdrlen(th) < skops->skb_len) + nr_data++; + + if (th->fin) + nr_fin++; + + if (th->ack && !th->fin && tcp_hdrlen(th) == skops->skb_len) + nr_pure_ack++; + + return CG_OK; +} + +static int active_opt_len(struct bpf_sock_ops *skops) +{ + int err; + + /* Reserve more than enough to allow the -EEXIST test in + * the write_active_opt(). + */ + err = bpf_reserve_hdr_opt(skops, 12, 0); + if (err) + RET_CG_ERR(err); + + return CG_OK; +} + +static int write_active_opt(struct bpf_sock_ops *skops) +{ + struct tcp_exprm_opt exprm_opt = {}; + struct tcp_opt win_scale_opt = {}; + struct tcp_opt reg_opt = {}; + struct tcphdr *th; + int err, ret; + + exprm_opt.kind = TCPOPT_EXP; + exprm_opt.len = 4; + exprm_opt.magic = __bpf_htons(0xeB9F); + + reg_opt.kind = 0xB9; + reg_opt.len = 4; + reg_opt.data[0] = 0xfa; + reg_opt.data[1] = 0xce; + + win_scale_opt.kind = TCPOPT_WINDOW; + + err = bpf_store_hdr_opt(skops, &exprm_opt, sizeof(exprm_opt), 0); + if (err) + RET_CG_ERR(err); + + /* Store the same exprm option */ + err = bpf_store_hdr_opt(skops, &exprm_opt, sizeof(exprm_opt), 0); + if (err != -EEXIST) + RET_CG_ERR(err); + + err = bpf_store_hdr_opt(skops, ®_opt, sizeof(reg_opt), 0); + if (err) + RET_CG_ERR(err); + err = bpf_store_hdr_opt(skops, ®_opt, sizeof(reg_opt), 0); + if (err != -EEXIST) + RET_CG_ERR(err); + + /* Check the option has been written and can be searched */ + ret = bpf_load_hdr_opt(skops, &exprm_opt, sizeof(exprm_opt), 0); + if (ret != 4 || exprm_opt.len != 4 || exprm_opt.kind != TCPOPT_EXP || + exprm_opt.magic != __bpf_htons(0xeB9F)) + RET_CG_ERR(ret); + + reg_opt.len = 0; + ret = bpf_load_hdr_opt(skops, ®_opt, sizeof(reg_opt), 0); + if (ret != 4 || reg_opt.len != 4 || reg_opt.kind != 0xB9 || + reg_opt.data[0] != 0xfa || reg_opt.data[1] != 0xce) + RET_CG_ERR(ret); + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + if (th->syn) { + active_lport_h = skops->local_port; + active_lport_n = th->source; + + /* Search the win scale option written by kernel + * in the SYN packet. + */ + ret = bpf_load_hdr_opt(skops, &win_scale_opt, + sizeof(win_scale_opt), 0); + if (ret != 3 || win_scale_opt.len != 3 || + win_scale_opt.kind != TCPOPT_WINDOW) + RET_CG_ERR(ret); + + /* Write the win scale option that kernel + * has already written. + */ + err = bpf_store_hdr_opt(skops, &win_scale_opt, + sizeof(win_scale_opt), 0); + if (err != -EEXIST) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int handle_hdr_opt_len(struct bpf_sock_ops *skops) +{ + __u8 tcp_flags = skops_tcp_flags(skops); + + if ((tcp_flags & TCPHDR_SYNACK) == TCPHDR_SYNACK) + /* Check the SYN from bpf_sock_ops_kern->syn_skb */ + return check_active_syn_in(skops); + + /* Passive side should have cleared the write hdr cb by now */ + if (skops->local_port == passive_lport_h) + RET_CG_ERR(0); + + return active_opt_len(skops); +} + +static int handle_write_hdr_opt(struct bpf_sock_ops *skops) +{ + if (skops->local_port == passive_lport_h) + RET_CG_ERR(0); + + return write_active_opt(skops); +} + +static int handle_parse_hdr(struct bpf_sock_ops *skops) +{ + /* Passive side is not writing any non-standard/unknown + * option, so the active side should never be called. + */ + if (skops->local_port == active_lport_h) + RET_CG_ERR(0); + + return check_active_hdr_in(skops); +} + +static int handle_passive_estab(struct bpf_sock_ops *skops) +{ + int err; + + /* No more write hdr cb */ + bpf_sock_ops_cb_flags_set(skops, + skops->bpf_sock_ops_cb_flags & + ~BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG); + + /* Recheck the SYN but check the tp->saved_syn this time */ + err = check_active_syn_in(skops); + if (err == CG_ERR) + return err; + + nr_syn++; + + /* The ack has header option written by the active side also */ + return check_active_hdr_in(skops); +} + +SEC("sockops/misc_estab") +int misc_estab(struct bpf_sock_ops *skops) +{ + int true_val = 1; + + switch (skops->op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + passive_lport_h = skops->local_port; + passive_lport_n = __bpf_htons(passive_lport_h); + bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN, + &true_val, sizeof(true_val)); + set_hdr_cb_flags(skops); + break; + case BPF_SOCK_OPS_TCP_CONNECT_CB: + set_hdr_cb_flags(skops); + break; + case BPF_SOCK_OPS_PARSE_HDR_OPT_CB: + return handle_parse_hdr(skops); + case BPF_SOCK_OPS_HDR_OPT_LEN_CB: + return handle_hdr_opt_len(skops); + case BPF_SOCK_OPS_WRITE_HDR_OPT_CB: + return handle_write_hdr_opt(skops); + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + return handle_passive_estab(skops); + } + + return CG_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c index e72eba4a93d2..852051064507 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c @@ -79,6 +79,24 @@ int get_skb_ifindex(int val, struct __sk_buff *skb, int var) return skb->ifindex * val * var; } +__attribute__ ((noinline)) +int test_pkt_write_access_subprog(struct __sk_buff *skb, __u32 off) +{ + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + struct tcphdr *tcp = NULL; + + if (off > sizeof(struct ethhdr) + sizeof(struct ipv6hdr)) + return -1; + + tcp = data + off; + if (tcp + 1 > data_end) + return -1; + /* make modification to the packet data */ + tcp->check++; + return 0; +} + SEC("classifier/test_pkt_access") int test_pkt_access(struct __sk_buff *skb) { @@ -117,6 +135,8 @@ int test_pkt_access(struct __sk_buff *skb) if (test_pkt_access_subprog3(3, skb) != skb->len * 3 * skb->ifindex) return TC_ACT_SHOT; if (tcp) { + if (test_pkt_write_access_subprog(skb, (void *)tcp - data)) + return TC_ACT_SHOT; if (((void *)(tcp) + 20) > data_end || proto != 6) return TC_ACT_SHOT; barrier(); /* to force ordering of checks */ diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_invalid_update.c b/tools/testing/selftests/bpf/progs/test_sockmap_invalid_update.c new file mode 100644 index 000000000000..02a59e220cbc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_invalid_update.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} map SEC(".maps"); + +SEC("sockops") +int bpf_sockmap(struct bpf_sock_ops *skops) +{ + __u32 key = 0; + + if (skops->sk) + bpf_map_update_elem(&map, &key, skops->sk, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_update.c b/tools/testing/selftests/bpf/progs/test_sockmap_update.c new file mode 100644 index 000000000000..9d0c9f28cab2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_update.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} src SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} dst_sock_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} dst_sock_hash SEC(".maps"); + +SEC("classifier/copy_sock_map") +int copy_sock_map(void *ctx) +{ + struct bpf_sock *sk; + bool failed = false; + __u32 key = 0; + + sk = bpf_map_lookup_elem(&src, &key); + if (!sk) + return SK_DROP; + + if (bpf_map_update_elem(&dst_sock_map, &key, sk, 0)) + failed = true; + + if (bpf_map_update_elem(&dst_sock_hash, &key, sk, 0)) + failed = true; + + bpf_sk_release(sk); + return failed ? SK_DROP : SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c new file mode 100644 index 000000000000..9197a23df3da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c @@ -0,0 +1,623 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <stddef.h> +#include <errno.h> +#include <stdbool.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <linux/tcp.h> +#include <linux/socket.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#define BPF_PROG_TEST_TCP_HDR_OPTIONS +#include "test_tcp_hdr_options.h" + +#ifndef sizeof_field +#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) +#endif + +__u8 test_kind = TCPOPT_EXP; +__u16 test_magic = 0xeB9F; + +struct bpf_test_option passive_synack_out = {}; +struct bpf_test_option passive_fin_out = {}; + +struct bpf_test_option passive_estab_in = {}; +struct bpf_test_option passive_fin_in = {}; + +struct bpf_test_option active_syn_out = {}; +struct bpf_test_option active_fin_out = {}; + +struct bpf_test_option active_estab_in = {}; +struct bpf_test_option active_fin_in = {}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct hdr_stg); +} hdr_stg_map SEC(".maps"); + +static bool skops_want_cookie(const struct bpf_sock_ops *skops) +{ + return skops->args[0] == BPF_WRITE_HDR_TCP_SYNACK_COOKIE; +} + +static bool skops_current_mss(const struct bpf_sock_ops *skops) +{ + return skops->args[0] == BPF_WRITE_HDR_TCP_CURRENT_MSS; +} + +static __u8 option_total_len(__u8 flags) +{ + __u8 i, len = 1; /* +1 for flags */ + + if (!flags) + return 0; + + /* RESEND bit does not use a byte */ + for (i = OPTION_RESEND + 1; i < __NR_OPTION_FLAGS; i++) + len += !!TEST_OPTION_FLAGS(flags, i); + + if (test_kind == TCPOPT_EXP) + return len + TCP_BPF_EXPOPT_BASE_LEN; + else + return len + 2; /* +1 kind, +1 kind-len */ +} + +static void write_test_option(const struct bpf_test_option *test_opt, + __u8 *data) +{ + __u8 offset = 0; + + data[offset++] = test_opt->flags; + if (TEST_OPTION_FLAGS(test_opt->flags, OPTION_MAX_DELACK_MS)) + data[offset++] = test_opt->max_delack_ms; + + if (TEST_OPTION_FLAGS(test_opt->flags, OPTION_RAND)) + data[offset++] = test_opt->rand; +} + +static int store_option(struct bpf_sock_ops *skops, + const struct bpf_test_option *test_opt) +{ + union { + struct tcp_exprm_opt exprm; + struct tcp_opt regular; + } write_opt; + int err; + + if (test_kind == TCPOPT_EXP) { + write_opt.exprm.kind = TCPOPT_EXP; + write_opt.exprm.len = option_total_len(test_opt->flags); + write_opt.exprm.magic = __bpf_htons(test_magic); + write_opt.exprm.data32 = 0; + write_test_option(test_opt, write_opt.exprm.data); + err = bpf_store_hdr_opt(skops, &write_opt.exprm, + sizeof(write_opt.exprm), 0); + } else { + write_opt.regular.kind = test_kind; + write_opt.regular.len = option_total_len(test_opt->flags); + write_opt.regular.data32 = 0; + write_test_option(test_opt, write_opt.regular.data); + err = bpf_store_hdr_opt(skops, &write_opt.regular, + sizeof(write_opt.regular), 0); + } + + if (err) + RET_CG_ERR(err); + + return CG_OK; +} + +static int parse_test_option(struct bpf_test_option *opt, const __u8 *start) +{ + opt->flags = *start++; + + if (TEST_OPTION_FLAGS(opt->flags, OPTION_MAX_DELACK_MS)) + opt->max_delack_ms = *start++; + + if (TEST_OPTION_FLAGS(opt->flags, OPTION_RAND)) + opt->rand = *start++; + + return 0; +} + +static int load_option(struct bpf_sock_ops *skops, + struct bpf_test_option *test_opt, bool from_syn) +{ + union { + struct tcp_exprm_opt exprm; + struct tcp_opt regular; + } search_opt; + int ret, load_flags = from_syn ? BPF_LOAD_HDR_OPT_TCP_SYN : 0; + + if (test_kind == TCPOPT_EXP) { + search_opt.exprm.kind = TCPOPT_EXP; + search_opt.exprm.len = 4; + search_opt.exprm.magic = __bpf_htons(test_magic); + search_opt.exprm.data32 = 0; + ret = bpf_load_hdr_opt(skops, &search_opt.exprm, + sizeof(search_opt.exprm), load_flags); + if (ret < 0) + return ret; + return parse_test_option(test_opt, search_opt.exprm.data); + } else { + search_opt.regular.kind = test_kind; + search_opt.regular.len = 0; + search_opt.regular.data32 = 0; + ret = bpf_load_hdr_opt(skops, &search_opt.regular, + sizeof(search_opt.regular), load_flags); + if (ret < 0) + return ret; + return parse_test_option(test_opt, search_opt.regular.data); + } +} + +static int synack_opt_len(struct bpf_sock_ops *skops) +{ + struct bpf_test_option test_opt = {}; + __u8 optlen; + int err; + + if (!passive_synack_out.flags) + return CG_OK; + + err = load_option(skops, &test_opt, true); + + /* bpf_test_option is not found */ + if (err == -ENOMSG) + return CG_OK; + + if (err) + RET_CG_ERR(err); + + optlen = option_total_len(passive_synack_out.flags); + if (optlen) { + err = bpf_reserve_hdr_opt(skops, optlen, 0); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int write_synack_opt(struct bpf_sock_ops *skops) +{ + struct bpf_test_option opt; + + if (!passive_synack_out.flags) + /* We should not even be called since no header + * space has been reserved. + */ + RET_CG_ERR(0); + + opt = passive_synack_out; + if (skops_want_cookie(skops)) + SET_OPTION_FLAGS(opt.flags, OPTION_RESEND); + + return store_option(skops, &opt); +} + +static int syn_opt_len(struct bpf_sock_ops *skops) +{ + __u8 optlen; + int err; + + if (!active_syn_out.flags) + return CG_OK; + + optlen = option_total_len(active_syn_out.flags); + if (optlen) { + err = bpf_reserve_hdr_opt(skops, optlen, 0); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int write_syn_opt(struct bpf_sock_ops *skops) +{ + if (!active_syn_out.flags) + RET_CG_ERR(0); + + return store_option(skops, &active_syn_out); +} + +static int fin_opt_len(struct bpf_sock_ops *skops) +{ + struct bpf_test_option *opt; + struct hdr_stg *hdr_stg; + __u8 optlen; + int err; + + if (!skops->sk) + RET_CG_ERR(0); + + hdr_stg = bpf_sk_storage_get(&hdr_stg_map, skops->sk, NULL, 0); + if (!hdr_stg) + RET_CG_ERR(0); + + if (hdr_stg->active) + opt = &active_fin_out; + else + opt = &passive_fin_out; + + optlen = option_total_len(opt->flags); + if (optlen) { + err = bpf_reserve_hdr_opt(skops, optlen, 0); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int write_fin_opt(struct bpf_sock_ops *skops) +{ + struct bpf_test_option *opt; + struct hdr_stg *hdr_stg; + + if (!skops->sk) + RET_CG_ERR(0); + + hdr_stg = bpf_sk_storage_get(&hdr_stg_map, skops->sk, NULL, 0); + if (!hdr_stg) + RET_CG_ERR(0); + + if (hdr_stg->active) + opt = &active_fin_out; + else + opt = &passive_fin_out; + + if (!opt->flags) + RET_CG_ERR(0); + + return store_option(skops, opt); +} + +static int resend_in_ack(struct bpf_sock_ops *skops) +{ + struct hdr_stg *hdr_stg; + + if (!skops->sk) + return -1; + + hdr_stg = bpf_sk_storage_get(&hdr_stg_map, skops->sk, NULL, 0); + if (!hdr_stg) + return -1; + + return !!hdr_stg->resend_syn; +} + +static int nodata_opt_len(struct bpf_sock_ops *skops) +{ + int resend; + + resend = resend_in_ack(skops); + if (resend < 0) + RET_CG_ERR(0); + + if (resend) + return syn_opt_len(skops); + + return CG_OK; +} + +static int write_nodata_opt(struct bpf_sock_ops *skops) +{ + int resend; + + resend = resend_in_ack(skops); + if (resend < 0) + RET_CG_ERR(0); + + if (resend) + return write_syn_opt(skops); + + return CG_OK; +} + +static int data_opt_len(struct bpf_sock_ops *skops) +{ + /* Same as the nodata version. Mostly to show + * an example usage on skops->skb_len. + */ + return nodata_opt_len(skops); +} + +static int write_data_opt(struct bpf_sock_ops *skops) +{ + return write_nodata_opt(skops); +} + +static int current_mss_opt_len(struct bpf_sock_ops *skops) +{ + /* Reserve maximum that may be needed */ + int err; + + err = bpf_reserve_hdr_opt(skops, option_total_len(OPTION_MASK), 0); + if (err) + RET_CG_ERR(err); + + return CG_OK; +} + +static int handle_hdr_opt_len(struct bpf_sock_ops *skops) +{ + __u8 tcp_flags = skops_tcp_flags(skops); + + if ((tcp_flags & TCPHDR_SYNACK) == TCPHDR_SYNACK) + return synack_opt_len(skops); + + if (tcp_flags & TCPHDR_SYN) + return syn_opt_len(skops); + + if (tcp_flags & TCPHDR_FIN) + return fin_opt_len(skops); + + if (skops_current_mss(skops)) + /* The kernel is calculating the MSS */ + return current_mss_opt_len(skops); + + if (skops->skb_len) + return data_opt_len(skops); + + return nodata_opt_len(skops); +} + +static int handle_write_hdr_opt(struct bpf_sock_ops *skops) +{ + __u8 tcp_flags = skops_tcp_flags(skops); + struct tcphdr *th; + + if ((tcp_flags & TCPHDR_SYNACK) == TCPHDR_SYNACK) + return write_synack_opt(skops); + + if (tcp_flags & TCPHDR_SYN) + return write_syn_opt(skops); + + if (tcp_flags & TCPHDR_FIN) + return write_fin_opt(skops); + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + if (skops->skb_len > tcp_hdrlen(th)) + return write_data_opt(skops); + + return write_nodata_opt(skops); +} + +static int set_delack_max(struct bpf_sock_ops *skops, __u8 max_delack_ms) +{ + __u32 max_delack_us = max_delack_ms * 1000; + + return bpf_setsockopt(skops, SOL_TCP, TCP_BPF_DELACK_MAX, + &max_delack_us, sizeof(max_delack_us)); +} + +static int set_rto_min(struct bpf_sock_ops *skops, __u8 peer_max_delack_ms) +{ + __u32 min_rto_us = peer_max_delack_ms * 1000; + + return bpf_setsockopt(skops, SOL_TCP, TCP_BPF_RTO_MIN, &min_rto_us, + sizeof(min_rto_us)); +} + +static int handle_active_estab(struct bpf_sock_ops *skops) +{ + struct hdr_stg init_stg = { + .active = true, + }; + int err; + + err = load_option(skops, &active_estab_in, false); + if (err && err != -ENOMSG) + RET_CG_ERR(err); + + init_stg.resend_syn = TEST_OPTION_FLAGS(active_estab_in.flags, + OPTION_RESEND); + if (!skops->sk || !bpf_sk_storage_get(&hdr_stg_map, skops->sk, + &init_stg, + BPF_SK_STORAGE_GET_F_CREATE)) + RET_CG_ERR(0); + + if (init_stg.resend_syn) + /* Don't clear the write_hdr cb now because + * the ACK may get lost and retransmit may + * be needed. + * + * PARSE_ALL_HDR cb flag is set to learn if this + * resend_syn option has received by the peer. + * + * The header option will be resent until a valid + * packet is received at handle_parse_hdr() + * and all hdr cb flags will be cleared in + * handle_parse_hdr(). + */ + set_parse_all_hdr_cb_flags(skops); + else if (!active_fin_out.flags) + /* No options will be written from now */ + clear_hdr_cb_flags(skops); + + if (active_syn_out.max_delack_ms) { + err = set_delack_max(skops, active_syn_out.max_delack_ms); + if (err) + RET_CG_ERR(err); + } + + if (active_estab_in.max_delack_ms) { + err = set_rto_min(skops, active_estab_in.max_delack_ms); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int handle_passive_estab(struct bpf_sock_ops *skops) +{ + struct hdr_stg init_stg = {}; + struct tcphdr *th; + int err; + + err = load_option(skops, &passive_estab_in, true); + if (err == -ENOENT) { + /* saved_syn is not found. It was in syncookie mode. + * We have asked the active side to resend the options + * in ACK, so try to find the bpf_test_option from ACK now. + */ + err = load_option(skops, &passive_estab_in, false); + init_stg.syncookie = true; + } + + /* ENOMSG: The bpf_test_option is not found which is fine. + * Bail out now for all other errors. + */ + if (err && err != -ENOMSG) + RET_CG_ERR(err); + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + if (th->syn) { + /* Fastopen */ + + /* Cannot clear cb_flags to stop write_hdr cb. + * synack is not sent yet for fast open. + * Even it was, the synack may need to be retransmitted. + * + * PARSE_ALL_HDR cb flag is set to learn + * if synack has reached the peer. + * All cb_flags will be cleared in handle_parse_hdr(). + */ + set_parse_all_hdr_cb_flags(skops); + init_stg.fastopen = true; + } else if (!passive_fin_out.flags) { + /* No options will be written from now */ + clear_hdr_cb_flags(skops); + } + + if (!skops->sk || + !bpf_sk_storage_get(&hdr_stg_map, skops->sk, &init_stg, + BPF_SK_STORAGE_GET_F_CREATE)) + RET_CG_ERR(0); + + if (passive_synack_out.max_delack_ms) { + err = set_delack_max(skops, passive_synack_out.max_delack_ms); + if (err) + RET_CG_ERR(err); + } + + if (passive_estab_in.max_delack_ms) { + err = set_rto_min(skops, passive_estab_in.max_delack_ms); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int handle_parse_hdr(struct bpf_sock_ops *skops) +{ + struct hdr_stg *hdr_stg; + struct tcphdr *th; + + if (!skops->sk) + RET_CG_ERR(0); + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + hdr_stg = bpf_sk_storage_get(&hdr_stg_map, skops->sk, NULL, 0); + if (!hdr_stg) + RET_CG_ERR(0); + + if (hdr_stg->resend_syn || hdr_stg->fastopen) + /* The PARSE_ALL_HDR cb flag was turned on + * to ensure that the previously written + * options have reached the peer. + * Those previously written option includes: + * - Active side: resend_syn in ACK during syncookie + * or + * - Passive side: SYNACK during fastopen + * + * A valid packet has been received here after + * the 3WHS, so the PARSE_ALL_HDR cb flag + * can be cleared now. + */ + clear_parse_all_hdr_cb_flags(skops); + + if (hdr_stg->resend_syn && !active_fin_out.flags) + /* Active side resent the syn option in ACK + * because the server was in syncookie mode. + * A valid packet has been received, so + * clear header cb flags if there is no + * more option to send. + */ + clear_hdr_cb_flags(skops); + + if (hdr_stg->fastopen && !passive_fin_out.flags) + /* Passive side was in fastopen. + * A valid packet has been received, so + * the SYNACK has reached the peer. + * Clear header cb flags if there is no more + * option to send. + */ + clear_hdr_cb_flags(skops); + + if (th->fin) { + struct bpf_test_option *fin_opt; + int err; + + if (hdr_stg->active) + fin_opt = &active_fin_in; + else + fin_opt = &passive_fin_in; + + err = load_option(skops, fin_opt, false); + if (err && err != -ENOMSG) + RET_CG_ERR(err); + } + + return CG_OK; +} + +SEC("sockops/estab") +int estab(struct bpf_sock_ops *skops) +{ + int true_val = 1; + + switch (skops->op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN, + &true_val, sizeof(true_val)); + set_hdr_cb_flags(skops); + break; + case BPF_SOCK_OPS_TCP_CONNECT_CB: + set_hdr_cb_flags(skops); + break; + case BPF_SOCK_OPS_PARSE_HDR_OPT_CB: + return handle_parse_hdr(skops); + case BPF_SOCK_OPS_HDR_OPT_LEN_CB: + return handle_hdr_opt_len(skops); + case BPF_SOCK_OPS_WRITE_HDR_OPT_CB: + return handle_write_hdr_opt(skops); + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + return handle_passive_estab(skops); + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + return handle_active_estab(skops); + } + + return CG_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 1f1966e86e9f..3e6912e4df3d 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -54,6 +54,7 @@ SEC("sockops") int bpf_testcb(struct bpf_sock_ops *skops) { char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)]; + struct bpf_sock_ops *reuse = skops; struct tcphdr *thdr; int good_call_rv = 0; int bad_call_rv = 0; @@ -62,6 +63,46 @@ int bpf_testcb(struct bpf_sock_ops *skops) int v = 0; int op; + /* Test reading fields in bpf_sock_ops using single register */ + asm volatile ( + "%[reuse] = *(u32 *)(%[reuse] +96)" + : [reuse] "+r"(reuse) + :); + + asm volatile ( + "%[op] = *(u32 *)(%[skops] +96)" + : [op] "+r"(op) + : [skops] "r"(skops) + :); + + asm volatile ( + "r9 = %[skops];\n" + "r8 = *(u32 *)(r9 +164);\n" + "*(u32 *)(r9 +164) = r8;\n" + :: [skops] "r"(skops) + : "r9", "r8"); + + asm volatile ( + "r1 = %[skops];\n" + "r1 = *(u64 *)(r1 +184);\n" + "if r1 == 0 goto +1;\n" + "r1 = *(u32 *)(r1 +4);\n" + :: [skops] "r"(skops):"r1"); + + asm volatile ( + "r9 = %[skops];\n" + "r9 = *(u64 *)(r9 +184);\n" + "if r9 == 0 goto +1;\n" + "r9 = *(u32 *)(r9 +4);\n" + :: [skops] "r"(skops):"r9"); + + asm volatile ( + "r1 = %[skops];\n" + "r2 = *(u64 *)(r1 +184);\n" + "if r2 == 0 goto +1;\n" + "r2 = *(u32 *)(r2 +4);\n" + :: [skops] "r"(skops):"r1", "r2"); + op = (int) skops->op; update_event_map(op); diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c index cd4b72c55dfe..913acdffd90f 100644 --- a/tools/testing/selftests/bpf/progs/test_varlen.c +++ b/tools/testing/selftests/bpf/progs/test_varlen.c @@ -15,9 +15,9 @@ int test_pid = 0; bool capture = false; /* .bss */ -long payload1_len1 = 0; -long payload1_len2 = 0; -long total1 = 0; +__u64 payload1_len1 = 0; +__u64 payload1_len2 = 0; +__u64 total1 = 0; char payload1[MAX_LEN + MAX_LEN] = {}; /* .data */ diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c index 29fa09d6a6c6..e9dfa0313d1b 100644 --- a/tools/testing/selftests/bpf/progs/test_vmlinux.c +++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c @@ -19,12 +19,14 @@ SEC("tp/syscalls/sys_enter_nanosleep") int handle__tp(struct trace_event_raw_sys_enter *args) { struct __kernel_timespec *ts; + long tv_nsec; if (args->id != __NR_nanosleep) return 0; ts = (void *)args->args[0]; - if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC) + if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || + tv_nsec != MY_TV_NSEC) return 0; tp_called = true; @@ -35,12 +37,14 @@ SEC("raw_tp/sys_enter") int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id) { struct __kernel_timespec *ts; + long tv_nsec; if (id != __NR_nanosleep) return 0; ts = (void *)PT_REGS_PARM1_CORE(regs); - if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC) + if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || + tv_nsec != MY_TV_NSEC) return 0; raw_tp_called = true; @@ -51,12 +55,14 @@ SEC("tp_btf/sys_enter") int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id) { struct __kernel_timespec *ts; + long tv_nsec; if (id != __NR_nanosleep) return 0; ts = (void *)PT_REGS_PARM1_CORE(regs); - if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC) + if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || + tv_nsec != MY_TV_NSEC) return 0; tp_btf_called = true; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 8b36b6640e7e..9a4d09590b3d 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -39,6 +39,13 @@ int bench_trigger_fentry(void *ctx) return 0; } +SEC("fentry.s/__x64_sys_getpgid") +int bench_trigger_fentry_sleep(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} + SEC("fmod_ret/__x64_sys_getpgid") int bench_trigger_fmodret(void *ctx) { diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 305fae8f80a9..c75fc6447186 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -3883,7 +3883,7 @@ static int test_big_btf_info(unsigned int test_num) info_garbage.garbage = 0; err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len); if (CHECK(err || info_len != sizeof(*info), - "err:%d errno:%d info_len:%u sizeof(*info):%lu", + "err:%d errno:%d info_len:%u sizeof(*info):%zu", err, errno, info_len, sizeof(*info))) { err = -1; goto done; @@ -4094,7 +4094,7 @@ static int do_test_get_info(unsigned int test_num) if (CHECK(err || !info.id || info_len != sizeof(info) || info.btf_size != raw_btf_size || (ret = memcmp(raw_btf, user_btf, expected_nbytes)), - "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%lu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d", + "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%zu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d", err, errno, info.id, info_len, sizeof(info), raw_btf_size, info.btf_size, expected_nbytes, ret)) { err = -1; @@ -4730,7 +4730,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind, nexpected_line = snprintf(expected_line, line_size, "%s%u: {%u,0,%d,0x%x,0x%x,0x%x," - "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s," + "{%llu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s," "%u,0x%x,[[%d,%d],[%d,%d]]}\n", percpu_map ? "\tcpu" : "", percpu_map ? cpu : next_key, @@ -4738,7 +4738,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind, v->unused_bits2a, v->bits28, v->unused_bits2b, - v->ui64, + (__u64)v->ui64, v->ui8a[0], v->ui8a[1], v->ui8a[2], v->ui8a[3], v->ui8a[4], v->ui8a[5], diff --git a/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c b/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c index ed253f252cd0..ec53b1ef90d2 100644 --- a/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c +++ b/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c @@ -156,4 +156,5 @@ cleanup: bpf_object__close(obj); } } + return 0; } diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 754cf611723e..0d92ebcb335d 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1274,6 +1274,8 @@ static void __run_parallel(unsigned int tasks, pid_t pid[tasks]; int i; + fflush(stdout); + for (i = 0; i < tasks; i++) { pid[i] = fork(); if (pid[i] == 0) { diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index b1e4dadacd9b..22943b58d752 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -618,7 +618,9 @@ int cd_flavor_subdir(const char *exec_name) if (!flavor) return 0; flavor++; - fprintf(stdout, "Switching to flavor '%s' subdirectory...\n", flavor); + if (env.verbosity > VERBOSE_NONE) + fprintf(stdout, "Switching to flavor '%s' subdirectory...\n", flavor); + return chdir(flavor); } diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 6e09bf738473..dbb820dde138 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -135,6 +135,11 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *) (unsigned long) ptr; +} + int bpf_find_map(const char *test, struct bpf_object *obj, const char *name); int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); diff --git a/tools/testing/selftests/bpf/test_tcp_hdr_options.h b/tools/testing/selftests/bpf/test_tcp_hdr_options.h new file mode 100644 index 000000000000..78a8cf9eab42 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcp_hdr_options.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ + +#ifndef _TEST_TCP_HDR_OPTIONS_H +#define _TEST_TCP_HDR_OPTIONS_H + +struct bpf_test_option { + __u8 flags; + __u8 max_delack_ms; + __u8 rand; +} __attribute__((packed)); + +enum { + OPTION_RESEND, + OPTION_MAX_DELACK_MS, + OPTION_RAND, + __NR_OPTION_FLAGS, +}; + +#define OPTION_F_RESEND (1 << OPTION_RESEND) +#define OPTION_F_MAX_DELACK_MS (1 << OPTION_MAX_DELACK_MS) +#define OPTION_F_RAND (1 << OPTION_RAND) +#define OPTION_MASK ((1 << __NR_OPTION_FLAGS) - 1) + +#define TEST_OPTION_FLAGS(flags, option) (1 & ((flags) >> (option))) +#define SET_OPTION_FLAGS(flags, option) ((flags) |= (1 << (option))) + +/* Store in bpf_sk_storage */ +struct hdr_stg { + bool active; + bool resend_syn; /* active side only */ + bool syncookie; /* passive side only */ + bool fastopen; /* passive side only */ +}; + +struct linum_err { + unsigned int linum; + int err; +}; + +#define TCPHDR_FIN 0x01 +#define TCPHDR_SYN 0x02 +#define TCPHDR_RST 0x04 +#define TCPHDR_PSH 0x08 +#define TCPHDR_ACK 0x10 +#define TCPHDR_URG 0x20 +#define TCPHDR_ECE 0x40 +#define TCPHDR_CWR 0x80 +#define TCPHDR_SYNACK (TCPHDR_SYN | TCPHDR_ACK) + +#define TCPOPT_EOL 0 +#define TCPOPT_NOP 1 +#define TCPOPT_WINDOW 3 +#define TCPOPT_EXP 254 + +#define TCP_BPF_EXPOPT_BASE_LEN 4 +#define MAX_TCP_HDR_LEN 60 +#define MAX_TCP_OPTION_SPACE 40 + +#ifdef BPF_PROG_TEST_TCP_HDR_OPTIONS + +#define CG_OK 1 +#define CG_ERR 0 + +#ifndef SOL_TCP +#define SOL_TCP 6 +#endif + +struct tcp_exprm_opt { + __u8 kind; + __u8 len; + __u16 magic; + union { + __u8 data[4]; + __u32 data32; + }; +} __attribute__((packed)); + +struct tcp_opt { + __u8 kind; + __u8 len; + union { + __u8 data[4]; + __u32 data32; + }; +} __attribute__((packed)); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 2); + __type(key, int); + __type(value, struct linum_err); +} lport_linum_map SEC(".maps"); + +static inline unsigned int tcp_hdrlen(const struct tcphdr *th) +{ + return th->doff << 2; +} + +static inline __u8 skops_tcp_flags(const struct bpf_sock_ops *skops) +{ + return skops->skb_tcp_flags; +} + +static inline void clear_hdr_cb_flags(struct bpf_sock_ops *skops) +{ + bpf_sock_ops_cb_flags_set(skops, + skops->bpf_sock_ops_cb_flags & + ~(BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)); +} + +static inline void set_hdr_cb_flags(struct bpf_sock_ops *skops) +{ + bpf_sock_ops_cb_flags_set(skops, + skops->bpf_sock_ops_cb_flags | + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG); +} +static inline void +clear_parse_all_hdr_cb_flags(struct bpf_sock_ops *skops) +{ + bpf_sock_ops_cb_flags_set(skops, + skops->bpf_sock_ops_cb_flags & + ~BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG); +} + +static inline void +set_parse_all_hdr_cb_flags(struct bpf_sock_ops *skops) +{ + bpf_sock_ops_cb_flags_set(skops, + skops->bpf_sock_ops_cb_flags | + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG); +} + +#define RET_CG_ERR(__err) ({ \ + struct linum_err __linum_err; \ + int __lport; \ + \ + __linum_err.linum = __LINE__; \ + __linum_err.err = __err; \ + __lport = skops->local_port; \ + bpf_map_update_elem(&lport_linum_map, &__lport, &__linum_err, BPF_NOEXIST); \ + clear_hdr_cb_flags(skops); \ + clear_parse_all_hdr_cb_flags(skops); \ + return CG_ERR; \ +}) + +#endif /* BPF_PROG_TEST_TCP_HDR_OPTIONS */ + +#endif /* _TEST_TCP_HDR_OPTIONS_H */ diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 78a6bae56ea6..9be395d9dc64 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -114,6 +114,7 @@ struct bpf_test { bpf_testdata_struct_t retvals[MAX_TEST_RUNS]; }; enum bpf_attach_type expected_attach_type; + const char *kfunc; }; /* Note we want this to be 64 bit aligned so that the end of our array is @@ -984,8 +985,24 @@ static void do_test_single(struct bpf_test *test, bool unpriv, attr.log_level = 4; attr.prog_flags = pflags; + if (prog_type == BPF_PROG_TYPE_TRACING && test->kfunc) { + attr.attach_btf_id = libbpf_find_vmlinux_btf_id(test->kfunc, + attr.expected_attach_type); + if (attr.attach_btf_id < 0) { + printf("FAIL\nFailed to find BTF ID for '%s'!\n", + test->kfunc); + (*errors)++; + return; + } + } + fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog)); - if (fd_prog < 0 && !bpf_probe_prog_type(prog_type, 0)) { + + /* BPF_PROG_TYPE_TRACING requires more setup and + * bpf_probe_prog_type won't give correct answer + */ + if (fd_prog < 0 && prog_type != BPF_PROG_TYPE_TRACING && + !bpf_probe_prog_type(prog_type, 0)) { printf("SKIP (unsupported program type %d)\n", prog_type); skips++; goto close_fds; diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 4d6645f2874c..dac40de3f868 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -557,3 +557,149 @@ .result = ACCEPT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, +{ + "bounds check for reg = 0, reg xor 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_XOR, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .result = ACCEPT, +}, +{ + "bounds check for reg32 = 0, reg32 xor 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(BPF_REG_1, 0), + BPF_ALU32_IMM(BPF_XOR, BPF_REG_1, 1), + BPF_JMP32_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .result = ACCEPT, +}, +{ + "bounds check for reg = 2, reg xor 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_1, 2), + BPF_ALU64_IMM(BPF_XOR, BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .result = ACCEPT, +}, +{ + "bounds check for reg = any, reg xor 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_XOR, BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .result = REJECT, + .errstr = "invalid access to map value", + .errstr_unpriv = "invalid access to map value", +}, +{ + "bounds check for reg32 = any, reg32 xor 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU32_IMM(BPF_XOR, BPF_REG_1, 3), + BPF_JMP32_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .result = REJECT, + .errstr = "invalid access to map value", + .errstr_unpriv = "invalid access to map value", +}, +{ + "bounds check for reg > 0, reg xor 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLE, BPF_REG_1, 0, 3), + BPF_ALU64_IMM(BPF_XOR, BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .result = ACCEPT, +}, +{ + "bounds check for reg32 > 0, reg32 xor 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP32_IMM(BPF_JLE, BPF_REG_1, 0, 3), + BPF_ALU32_IMM(BPF_XOR, BPF_REG_1, 3), + BPF_JMP32_IMM(BPF_JGE, BPF_REG_1, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .result = ACCEPT, +}, diff --git a/tools/testing/selftests/bpf/verifier/d_path.c b/tools/testing/selftests/bpf/verifier/d_path.c new file mode 100644 index 000000000000..b988396379a7 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/d_path.c @@ -0,0 +1,37 @@ +{ + "d_path accept", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 0), + BPF_LD_IMM64(BPF_REG_3, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_d_path), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACING, + .expected_attach_type = BPF_TRACE_FENTRY, + .kfunc = "dentry_open", +}, +{ + "d_path reject", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 0), + BPF_LD_IMM64(BPF_REG_3, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_d_path), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "helper call is not allowed in probe", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACING, + .expected_attach_type = BPF_TRACE_FENTRY, + .kfunc = "d_path", +}, diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh index 47edf099a17e..508a702f0021 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh @@ -207,7 +207,7 @@ __rate_test() RET=0 - devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 16 + devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 512 devlink trap group set $DEVLINK_DEV group l3_drops policer $id # Send packets at highest possible rate and make sure they are dropped @@ -220,8 +220,8 @@ __rate_test() rate=$(trap_rate_get) pct=$((100 * (rate - 1000) / 1000)) - ((-5 <= pct && pct <= 5)) - check_err $? "Expected rate 1000 pps, got $rate pps, which is $pct% off. Required accuracy is +-5%" + ((-10 <= pct && pct <= 10)) + check_err $? "Expected rate 1000 pps, got $rate pps, which is $pct% off. Required accuracy is +-10%" log_info "Expected rate 1000 pps, measured rate $rate pps" drop_rate=$(policer_drop_rate_get $id) @@ -288,35 +288,12 @@ __burst_test() RET=0 - devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 32 + devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 512 devlink trap group set $DEVLINK_DEV group l3_drops policer $id - # Send a burst of 64 packets and make sure that about 32 are received - # and the rest are dropped by the policer - log_info "=== Tx burst size: 64, Policer burst size: 32 pps ===" - - t0_rx=$(devlink_trap_rx_packets_get blackhole_route) - t0_drop=$(devlink_trap_policer_rx_dropped_get $id) - - start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac -c 64 - - t1_rx=$(devlink_trap_rx_packets_get blackhole_route) - t1_drop=$(devlink_trap_policer_rx_dropped_get $id) - - rx=$((t1_rx - t0_rx)) - pct=$((100 * (rx - 32) / 32)) - ((-20 <= pct && pct <= 20)) - check_err $? "Expected burst size of 32 packets, got $rx packets, which is $pct% off. Required accuracy is +-20%" - log_info "Expected burst size of 32 packets, measured burst size of $rx packets" - - drop=$((t1_drop - t0_drop)) - (( drop > 0 )) - check_err $? "Expected non-zero policer drops, got 0" - log_info "Measured policer drops of $drop packets" - # Send a burst of 16 packets and make sure that 16 are received # and that none are dropped by the policer - log_info "=== Tx burst size: 16, Policer burst size: 32 pps ===" + log_info "=== Tx burst size: 16, Policer burst size: 512 ===" t0_rx=$(devlink_trap_rx_packets_get blackhole_route) t0_drop=$(devlink_trap_policer_rx_dropped_get $id) diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh index 4b96561c462f..3e3e06ea5703 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh @@ -24,6 +24,13 @@ tc_police_switch_destroy() simple_if_fini $swp1 } +tc_police_addr() +{ + local num=$1; shift + + printf "2001:db8:1::%x" $num +} + tc_police_rules_create() { local count=$1; shift @@ -34,8 +41,9 @@ tc_police_rules_create() for ((i = 0; i < count; ++i)); do cat >> $TC_POLICE_BATCH_FILE <<-EOF filter add dev $swp1 ingress \ - prot ip \ - flower skip_sw \ + prot ipv6 \ + pref 1000 \ + flower skip_sw dst_ip $(tc_police_addr $i) \ action police rate 10mbit burst 100k \ conform-exceed drop/ok EOF diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index 8162c58a1234..b8d14f9db5f9 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -40,11 +40,11 @@ static void guest_code(void) /* Single step test, covers 2 basic instructions and 2 emulated */ asm volatile("ss_start: " - "xor %%rax,%%rax\n\t" + "xor %%eax,%%eax\n\t" "cpuid\n\t" "movl $0x1a0,%%ecx\n\t" "rdmsr\n\t" - : : : "rax", "ecx"); + : : : "eax", "ebx", "ecx", "edx"); /* DR6.BD test */ asm volatile("bd_start: mov %%dr0, %%rax" : : : "rax"); diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 3b42c06b5985..5a57ea02802d 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -24,8 +24,7 @@ CONFIG_IP_NF_NAT=m CONFIG_NF_TABLES=m CONFIG_NF_TABLES_IPV6=y CONFIG_NF_TABLES_IPV4=y -CONFIG_NFT_CHAIN_NAT_IPV6=m -CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_NAT=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_NETEM=y diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 22dc2f3d428b..b74884d52913 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -739,6 +739,36 @@ ipv6_fcnal_runtime() run_cmd "$IP nexthop replace id 81 via 172.16.1.1 dev veth1" log_test $? 2 "Nexthop replace of group entry - v6 route, v4 nexthop" + run_cmd "$IP nexthop add id 86 via 2001:db8:92::2 dev veth3" + run_cmd "$IP nexthop add id 87 via 172.16.1.1 dev veth1" + run_cmd "$IP nexthop add id 88 via 172.16.1.1 dev veth1" + run_cmd "$IP nexthop add id 124 group 86/87/88" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 2 "IPv6 route can not have a group with v4 and v6 gateways" + + run_cmd "$IP nexthop del id 88" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 2 "IPv6 route can not have a group with v4 and v6 gateways" + + run_cmd "$IP nexthop del id 87" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 0 "IPv6 route using a group after removing v4 gateways" + + run_cmd "$IP ro delete 2001:db8:101::1/128" + run_cmd "$IP nexthop add id 87 via 172.16.1.1 dev veth1" + run_cmd "$IP nexthop add id 88 via 172.16.1.1 dev veth1" + run_cmd "$IP nexthop replace id 124 group 86/87/88" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 2 "IPv6 route can not have a group with v4 and v6 gateways" + + run_cmd "$IP nexthop replace id 88 via 2001:db8:92::2 dev veth3" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 2 "IPv6 route can not have a group with v4 and v6 gateways" + + run_cmd "$IP nexthop replace id 87 via 2001:db8:92::2 dev veth3" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 0 "IPv6 route using a group after replacing v4 gateways" + $IP nexthop flush >/dev/null 2>&1 # diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh index c33bfd7ba214..13db1cb50e57 100644 --- a/tools/testing/selftests/net/forwarding/mirror_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -31,7 +31,7 @@ mirror_test() local t0=$(tc_rule_stats_get $dev $pref) $MZ $vrf_name ${sip:+-A $sip} -B $dip -a own -b bc -q \ - -c 10 -d 100ms -t icmp type=8 + -c 10 -d 100msec -t icmp type=8 sleep 0.5 local t1=$(tc_rule_stats_get $dev $pref) local delta=$((t1 - t0)) diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index 18c5de53558a..bf361f30d6ef 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -180,6 +180,8 @@ setup() ;; r[12]) ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1 ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1 + ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0 + ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0 ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1 ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10 diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 090620c3e10c..a54966531a64 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -65,8 +65,8 @@ static void die_usage(void) fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n"); fprintf(stderr, "\t-R num -- set SO_RCVBUF to num\n"); fprintf(stderr, "\t-p num -- use port num\n"); - fprintf(stderr, "\t-m [MPTCP|TCP] -- use tcp or mptcp sockets\n"); - fprintf(stderr, "\t-s [mmap|poll] -- use poll (default) or mmap\n"); + fprintf(stderr, "\t-s [MPTCP|TCP] -- use mptcp(default) or tcp sockets\n"); + fprintf(stderr, "\t-m [poll|mmap|sendfile] -- use poll(default)/mmap+write/sendfile\n"); fprintf(stderr, "\t-u -- check mptcp ulp\n"); fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n"); exit(1); diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 57d75b7f6220..e4df9ba64824 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -14,9 +14,8 @@ capture=false timeout=30 ipv6=true ethtool_random_on=true -tc_delay="$((RANDOM%400))" +tc_delay="$((RANDOM%50))" tc_loss=$((RANDOM%101)) -tc_reorder="" testmode="" sndbuf=0 rcvbuf=0 @@ -628,30 +627,32 @@ for sender in "$ns1" "$ns2" "$ns3" "$ns4";do do_ping "$ns4" $sender dead:beef:3::1 done -[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss +[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms echo -n "INFO: Using loss of $tc_loss " test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms " +reorder_delay=$(($tc_delay / 4)) + if [ -z "${tc_reorder}" ]; then reorder1=$((RANDOM%10)) reorder1=$((100 - reorder1)) reorder2=$((RANDOM%100)) - if [ $tc_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then + if [ $reorder_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then tc_reorder="reorder ${reorder1}% ${reorder2}%" - echo -n "$tc_reorder " + echo -n "$tc_reorder with delay ${reorder_delay}ms " fi elif [ "$tc_reorder" = "0" ];then tc_reorder="" -elif [ "$tc_delay" -gt 0 ];then +elif [ "$reorder_delay" -gt 0 ];then # reordering requires some delay tc_reorder="reorder $tc_reorder" - echo -n "$tc_reorder " + echo -n "$tc_reorder with delay ${reorder_delay}ms " fi echo "on ns3eth4" -tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${tc_delay}ms $tc_reorder +tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder for sender in $ns1 $ns2 $ns3 $ns4;do run_tests_lo "$ns1" "$sender" 10.0.1.1 1 diff --git a/tools/testing/selftests/net/psock_snd.sh b/tools/testing/selftests/net/psock_snd.sh index 6331d91b86a6..170be65e0816 100755 --- a/tools/testing/selftests/net/psock_snd.sh +++ b/tools/testing/selftests/net/psock_snd.sh @@ -45,7 +45,7 @@ echo "raw vnet hdr" echo "raw csum_off" ./in_netns.sh ./psock_snd -v -c -echo "raw csum_off with bad offset (fails)" +echo "raw csum_off with bad offset (expected to fail)" (! ./in_netns.sh ./psock_snd -v -c -C) @@ -57,7 +57,7 @@ echo "raw min size" echo "raw mtu size" ./in_netns.sh ./psock_snd -l "${mss}" -echo "raw mtu size + 1 (fails)" +echo "raw mtu size + 1 (expected to fail)" (! ./in_netns.sh ./psock_snd -l "${mss_exceeds}") # fails due to ARPHRD_ETHER check in packet_extra_vlan_len_allowed @@ -65,19 +65,19 @@ echo "raw mtu size + 1 (fails)" # echo "raw vlan mtu size" # ./in_netns.sh ./psock_snd -V -l "${mss}" -echo "raw vlan mtu size + 1 (fails)" +echo "raw vlan mtu size + 1 (expected to fail)" (! ./in_netns.sh ./psock_snd -V -l "${mss_exceeds}") echo "dgram mtu size" ./in_netns.sh ./psock_snd -d -l "${mss}" -echo "dgram mtu size + 1 (fails)" +echo "dgram mtu size + 1 (expected to fail)" (! ./in_netns.sh ./psock_snd -d -l "${mss_exceeds}") -echo "raw truncate hlen (fails: does not arrive)" +echo "raw truncate hlen (expected to fail: does not arrive)" (! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen}))") -echo "raw truncate hlen - 1 (fails: EINVAL)" +echo "raw truncate hlen - 1 (expected to fail: EINVAL)" (! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen} - 1))") @@ -86,13 +86,13 @@ echo "raw truncate hlen - 1 (fails: EINVAL)" echo "raw gso min size" ./in_netns.sh ./psock_snd -v -c -g -l "${mss_exceeds}" -echo "raw gso min size - 1 (fails)" +echo "raw gso min size - 1 (expected to fail)" (! ./in_netns.sh ./psock_snd -v -c -g -l "${mss}") echo "raw gso max size" ./in_netns.sh ./psock_snd -v -c -g -l "${max_mss}" -echo "raw gso max size + 1 (fails)" +echo "raw gso max size + 1 (expected to fail)" (! ./in_netns.sh ./psock_snd -v -c -g -l "${max_mss_exceeds}") echo "OK. All tests passed" diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index a61b7b3da549..00f837c9bc6c 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -123,6 +123,28 @@ void hash_zone(void *zone, unsigned int length) #define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1)) #define ALIGN_PTR_UP(p, ptr_align_to) ((typeof(p))ALIGN_UP((unsigned long)(p), ptr_align_to)) + +static void *mmap_large_buffer(size_t need, size_t *allocated) +{ + void *buffer; + size_t sz; + + /* Attempt to use huge pages if possible. */ + sz = ALIGN_UP(need, map_align); + buffer = mmap(NULL, sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + + if (buffer == (void *)-1) { + sz = need; + buffer = mmap(NULL, sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (buffer != (void *)-1) + fprintf(stderr, "MAP_HUGETLB attempt failed, look at /sys/kernel/mm/hugepages for optimal performance\n"); + } + *allocated = sz; + return buffer; +} + void *child_thread(void *arg) { unsigned long total_mmap = 0, total = 0; @@ -135,6 +157,7 @@ void *child_thread(void *arg) void *addr = NULL; double throughput; struct rusage ru; + size_t buffer_sz; int lu, fd; fd = (int)(unsigned long)arg; @@ -142,9 +165,9 @@ void *child_thread(void *arg) gettimeofday(&t0, NULL); fcntl(fd, F_SETFL, O_NDELAY); - buffer = malloc(chunk_size); - if (!buffer) { - perror("malloc"); + buffer = mmap_large_buffer(chunk_size, &buffer_sz); + if (buffer == (void *)-1) { + perror("mmap"); goto error; } if (zflg) { @@ -179,6 +202,10 @@ void *child_thread(void *arg) total_mmap += zc.length; if (xflg) hash_zone(addr, zc.length); + /* It is more efficient to unmap the pages right now, + * instead of doing this in next TCP_ZEROCOPY_RECEIVE. + */ + madvise(addr, zc.length, MADV_DONTNEED); total += zc.length; } if (zc.recv_skip_hint) { @@ -230,7 +257,7 @@ end: ru.ru_nvcsw); } error: - free(buffer); + munmap(buffer, buffer_sz); close(fd); if (zflg) munmap(raddr, chunk_size + map_align); @@ -347,6 +374,7 @@ int main(int argc, char *argv[]) uint64_t total = 0; char *host = NULL; int fd, c, on = 1; + size_t buffer_sz; char *buffer; int sflg = 0; int mss = 0; @@ -437,8 +465,8 @@ int main(int argc, char *argv[]) } do_accept(fdlisten); } - buffer = mmap(NULL, chunk_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + buffer = mmap_large_buffer(chunk_size, &buffer_sz); if (buffer == (char *)-1) { perror("mmap"); exit(1); @@ -484,6 +512,6 @@ int main(int argc, char *argv[]) total += wr; } close(fd); - munmap(buffer, chunk_size); + munmap(buffer, buffer_sz); return 0; } diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index d3e0809ab368..431296c0f91c 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -2,13 +2,18 @@ # SPDX-License-Identifier: GPL-2.0 # # This tests basic flowtable functionality. -# Creates following topology: +# Creates following default topology: # # Originator (MTU 9000) <-Router1-> MTU 1500 <-Router2-> Responder (MTU 2000) # Router1 is the one doing flow offloading, Router2 has no special # purpose other than having a link that is smaller than either Originator # and responder, i.e. TCPMSS announced values are too large and will still # result in fragmentation and/or PMTU discovery. +# +# You can check with different Orgininator/Link/Responder MTU eg: +# nft_flowtable.sh -o8000 -l1500 -r2000 +# + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -21,29 +26,17 @@ ns2out="" log_netns=$(sysctl -n net.netfilter.nf_log_all_netns) -nft --version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without nft tool" - exit $ksft_skip -fi - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi - -which nc > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without nc (netcat)" - exit $ksft_skip -fi +checktool (){ + if ! $1 > /dev/null 2>&1; then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} -ip netns add nsr1 -if [ $? -ne 0 ];then - echo "SKIP: Could not create net namespace" - exit $ksft_skip -fi +checktool "nft --version" "run test without nft tool" +checktool "ip -Version" "run test without ip tool" +checktool "which nc" "run test without nc (netcat)" +checktool "ip netns add nsr1" "create net namespace" ip netns add ns1 ip netns add ns2 @@ -89,11 +82,41 @@ ip -net nsr2 addr add dead:2::1/64 dev veth1 # ns2 is going via nsr2 with a smaller mtu, so that TCPMSS announced by both peers # is NOT the lowest link mtu. -ip -net nsr1 link set veth0 mtu 9000 -ip -net ns1 link set eth0 mtu 9000 +omtu=9000 +lmtu=1500 +rmtu=2000 + +usage(){ + echo "nft_flowtable.sh [OPTIONS]" + echo + echo "MTU options" + echo " -o originator" + echo " -l link" + echo " -r responder" + exit 1 +} + +while getopts "o:l:r:" o +do + case $o in + o) omtu=$OPTARG;; + l) lmtu=$OPTARG;; + r) rmtu=$OPTARG;; + *) usage;; + esac +done + +if ! ip -net nsr1 link set veth0 mtu $omtu; then + exit 1 +fi + +ip -net ns1 link set eth0 mtu $omtu + +if ! ip -net nsr2 link set veth1 mtu $rmtu; then + exit 1 +fi -ip -net nsr2 link set veth1 mtu 2000 -ip -net ns2 link set eth0 mtu 2000 +ip -net ns2 link set eth0 mtu $rmtu # transfer-net between nsr1 and nsr2. # these addresses are not used for connections. @@ -113,7 +136,10 @@ for i in 1 2; do ip -net ns$i route add default via 10.0.$i.1 ip -net ns$i addr add dead:$i::99/64 dev eth0 ip -net ns$i route add default via dead:$i::1 - ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null + if ! ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then + echo "ERROR: Check Originator/Responder values (problem during address addition)" + exit 1 + fi # don't set ip DF bit for first two tests ip netns exec ns$i sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null @@ -147,7 +173,7 @@ table inet filter { # as PMTUd is off. # This rule is deleted for the last test, when we expect PMTUd # to kick in and ensure all packets meet mtu requirements. - meta length gt 1500 accept comment something-to-grep-for + meta length gt $lmtu accept comment something-to-grep-for # next line blocks connection w.o. working offload. # we only do this for reverse dir, because we expect packets to @@ -171,15 +197,13 @@ if [ $? -ne 0 ]; then fi # test basic connectivity -ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null -if [ $? -ne 0 ];then +if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then echo "ERROR: ns1 cannot reach ns2" 1>&2 bash exit 1 fi -ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null -if [ $? -ne 0 ];then +if ! ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then echo "ERROR: ns2 cannot reach ns1" 1>&2 exit 1 fi @@ -196,7 +220,6 @@ ns2out=$(mktemp) make_file() { name=$1 - who=$2 SIZE=$((RANDOM % (1024 * 8))) TSIZE=$((SIZE * 1024)) @@ -215,8 +238,7 @@ check_transfer() out=$2 what=$3 - cmp "$in" "$out" > /dev/null 2>&1 - if [ $? -ne 0 ] ;then + if ! cmp "$in" "$out" > /dev/null 2>&1; then echo "FAIL: file mismatch for $what" 1>&2 ls -l "$in" ls -l "$out" @@ -243,17 +265,21 @@ test_tcp_forwarding_ip() sleep 3 - kill $lpid - kill $cpid + if ps -p $lpid > /dev/null;then + kill $lpid + fi + + if ps -p $cpid > /dev/null;then + kill $cpid + fi + wait - check_transfer "$ns1in" "$ns2out" "ns1 -> ns2" - if [ $? -ne 0 ];then + if ! check_transfer "$ns1in" "$ns2out" "ns1 -> ns2"; then lret=1 fi - check_transfer "$ns2in" "$ns1out" "ns1 <- ns2" - if [ $? -ne 0 ];then + if ! check_transfer "$ns2in" "$ns1out" "ns1 <- ns2"; then lret=1 fi @@ -282,13 +308,12 @@ test_tcp_forwarding_nat() return $lret } -make_file "$ns1in" "ns1" -make_file "$ns2in" "ns2" +make_file "$ns1in" +make_file "$ns2in" # First test: # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed. -test_tcp_forwarding ns1 ns2 -if [ $? -eq 0 ] ;then +if test_tcp_forwarding ns1 ns2; then echo "PASS: flow offloaded for ns1/ns2" else echo "FAIL: flow offload for ns1/ns2:" 1>&2 @@ -319,9 +344,7 @@ table ip nat { } EOF -test_tcp_forwarding_nat ns1 ns2 - -if [ $? -eq 0 ] ;then +if test_tcp_forwarding_nat ns1 ns2; then echo "PASS: flow offloaded for ns1/ns2 with NAT" else echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2 @@ -333,8 +356,7 @@ fi # Same as second test, but with PMTU discovery enabled. handle=$(ip netns exec nsr1 nft -a list table inet filter | grep something-to-grep-for | cut -d \# -f 2) -ip netns exec nsr1 nft delete rule inet filter forward $handle -if [ $? -ne 0 ] ;then +if ! ip netns exec nsr1 nft delete rule inet filter forward $handle; then echo "FAIL: Could not delete large-packet accept rule" exit 1 fi @@ -342,8 +364,7 @@ fi ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null -test_tcp_forwarding_nat ns1 ns2 -if [ $? -eq 0 ] ;then +if test_tcp_forwarding_nat ns1 ns2; then echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery" else echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2 @@ -389,8 +410,7 @@ ip -net ns2 route del 192.168.10.1 via 10.0.2.1 ip -net ns2 route add default via 10.0.2.1 ip -net ns2 route add default via dead:2::1 -test_tcp_forwarding ns1 ns2 -if [ $? -eq 0 ] ;then +if test_tcp_forwarding ns1 ns2; then echo "PASS: ipsec tunnel mode for ns1/ns2" else echo "FAIL: ipsec tunnel mode for ns1/ns2" diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore index 91c775c23c66..aac4a59f9e28 100644 --- a/tools/testing/selftests/powerpc/mm/.gitignore +++ b/tools/testing/selftests/powerpc/mm/.gitignore @@ -2,6 +2,7 @@ hugetlb_vs_thp_test subpage_prot tempfile +prot_sao segv_errors wild_bctr large_vm_fork_separation diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index 250ce172e0da..defe488d6bf1 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -2,7 +2,7 @@ noarg: $(MAKE) -C ../ -TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot segv_errors wild_bctr \ +TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \ large_vm_fork_separation bad_accesses pkey_exec_prot \ pkey_siginfo stack_expansion_signal stack_expansion_ldst @@ -14,6 +14,8 @@ include ../../lib.mk $(TEST_GEN_PROGS): ../harness.c ../utils.c +$(OUTPUT)/prot_sao: ../utils.c + $(OUTPUT)/wild_bctr: CFLAGS += -m64 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64 $(OUTPUT)/bad_accesses: CFLAGS += -m64 diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c new file mode 100644 index 000000000000..e0cf8ebbf8cd --- /dev/null +++ b/tools/testing/selftests/powerpc/mm/prot_sao.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2016, Michael Ellerman, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> + +#include <asm/cputable.h> + +#include "utils.h" + +#define SIZE (64 * 1024) + +int test_prot_sao(void) +{ + char *p; + + /* SAO was introduced in 2.06 and removed in 3.1 */ + SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06) || + have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* + * Ensure we can ask for PROT_SAO. + * We can't really verify that it does the right thing, but at least we + * confirm the kernel will accept it. + */ + p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + FAIL_IF(p == MAP_FAILED); + + /* Write to the mapping, to at least cause a fault */ + memset(p, 0xaa, SIZE); + + return 0; +} + +int main(void) +{ + return test_harness(test_prot_sao, "prot-sao"); +} diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index c41f24b517f4..65c141ebfbbd 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -462,6 +462,17 @@ static int test_vsys_x(void) return 0; } +/* + * Debuggers expect ptrace() to be able to peek at the vsyscall page. + * Use process_vm_readv() as a proxy for ptrace() to test this. We + * want it to work in the vsyscall=emulate case and to fail in the + * vsyscall=xonly case. + * + * It's worth noting that this ABI is a bit nutty. write(2) can't + * read from the vsyscall page on any kernel version or mode. The + * fact that ptrace() ever worked was a nice courtesy of old kernels, + * but the code to support it is fairly gross. + */ static int test_process_vm_readv(void) { #ifdef __x86_64__ @@ -477,8 +488,12 @@ static int test_process_vm_readv(void) remote.iov_len = 4096; ret = process_vm_readv(getpid(), &local, 1, &remote, 1, 0); if (ret != 4096) { - printf("[OK]\tprocess_vm_readv() failed (ret = %d, errno = %d)\n", ret, errno); - return 0; + /* + * We expect process_vm_readv() to work if and only if the + * vsyscall page is readable. + */ + printf("[%s]\tprocess_vm_readv() failed (ret = %d, errno = %d)\n", vsyscall_map_r ? "FAIL" : "OK", ret, errno); + return vsyscall_map_r ? 1 : 0; } if (vsyscall_map_r) { @@ -488,6 +503,9 @@ static int test_process_vm_readv(void) printf("[FAIL]\tIt worked but returned incorrect data\n"); return 1; } + } else { + printf("[FAIL]\tprocess_rm_readv() succeeded, but it should have failed in this configuration\n"); + return 1; } #endif diff --git a/tools/usb/Build b/tools/usb/Build new file mode 100644 index 000000000000..2ad6f9745816 --- /dev/null +++ b/tools/usb/Build @@ -0,0 +1,2 @@ +testusb-y += testusb.o +ffs-test-y += ffs-test.o diff --git a/tools/usb/Makefile b/tools/usb/Makefile index 01d758d73b6d..1b128e551b2e 100644 --- a/tools/usb/Makefile +++ b/tools/usb/Makefile @@ -1,14 +1,51 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for USB tools +include ../scripts/Makefile.include -PTHREAD_LIBS = -lpthread -WARNINGS = -Wall -Wextra -CFLAGS = $(WARNINGS) -g -I../include -LDFLAGS = $(PTHREAD_LIBS) +bindir ?= /usr/bin -all: testusb ffs-test -%: %.c - $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS) +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif + +# Do not use make's built-in rules +# (this improves performance and avoids hard-to-debug behaviour); +MAKEFLAGS += -r + +override CFLAGS += -O2 -Wall -Wextra -g -D_GNU_SOURCE -I$(OUTPUT)include -I$(srctree)/tools/include +override LDFLAGS += -lpthread + +ALL_TARGETS := testusb ffs-test +ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) + +all: $(ALL_PROGRAMS) + +export srctree OUTPUT CC LD CFLAGS +include $(srctree)/tools/build/Makefile.include + +TESTUSB_IN := $(OUTPUT)testusb-in.o +$(TESTUSB_IN): FORCE + $(Q)$(MAKE) $(build)=testusb +$(OUTPUT)testusb: $(TESTUSB_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS) + +FFS_TEST_IN := $(OUTPUT)ffs-test-in.o +$(FFS_TEST_IN): FORCE + $(Q)$(MAKE) $(build)=ffs-test +$(OUTPUT)ffs-test: $(FFS_TEST_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS) clean: - $(RM) testusb ffs-test + rm -f $(ALL_PROGRAMS) + find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.o.cmd' -delete + +install: $(ALL_PROGRAMS) + install -d -m 755 $(DESTDIR)$(bindir); \ + for program in $(ALL_PROGRAMS); do \ + install $$program $(DESTDIR)$(bindir); \ + done + +FORCE: + +.PHONY: all install clean FORCE prepare diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 737666db02de..67cd0b88a6b6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -482,7 +482,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; - need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end); + need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end, + range->flags); need_tlb_flush |= kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) |