summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2014-12-09virtio_pci: delete vqs indirectlyMichael S. Tsirkin
VQ deletion is mostly version-specific, add another level of indirection to split the version-independent code out. Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2014-12-09virtio_pci: use priv for vq notificationMichael S. Tsirkin
slightly reduce the amount of pointer chasing this needs to do. More importantly, this will easily generalize to virtio 1.0. Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2014-12-09virtio_pci: free up vq->privMichael S. Tsirkin
We don't need to go from vq to vq info on data path, so using direct vq->priv pointer for that seems like a waste. Let's build an array of vq infos, then we can use vq->index for that lookup. Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2014-12-09virtio_pci: fix coding style for structsMichael S. Tsirkin
should be struct foo { } not struct foo { } Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2014-12-09virtio_pci: add isr fieldMichael S. Tsirkin
Use isr field instead of direct access to ioaddr. This way generalizes easily to virtio 1.0. Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2014-12-09virtio: drop legacy_only driver flagMichael S. Tsirkin
legacy_only flag is now unused, drop it from core. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
2014-12-09virtio_balloon: drop legacy_only driver flagMichael S. Tsirkin
we have blacklisted balloon in core, no need for a driver flag. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
2014-12-09virtio_ccw: rev 1 devices set VIRTIO_F_VERSION_1Michael S. Tsirkin
What does it mean if rev 1 device does not set VIRTIO_F_VERSION_1? E.g. is it native endian? Let's not even try to drive such devices: fail attempts to finalize features. virtio core will detect this and bail out. Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2014-12-09Merge branch 'next' into upstream for v3.19Paul Moore
2014-12-09bnx2x: Use correct fastpath version for VFs.Yuval Mintz
Our FW can support several fastpath HSI [for backward compatibility] but up until now VFs were always configured to use latest fastpath HSI [although VF driver might be older and use an older fastpath HSI]. For linux drivers, the differences are insignificant since driver never utilized features that were overridden by the HSI change. But for VMs running other operating systems this might be a problem. In addition, eventually FW might change fastpath HSI in such a manner that backward compatibility WILL break unless configured with proper version. This patch fixes the issue for other operating system VMs, as well as lays the ground work for forward compatibility in regard to the fastpath HSI. Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com> Signed-off-by: Ariel Elior <Ariel.Elior@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09net: tulip: Remove private "strncmp"Rasmus Villemoes
The comment says that the built-in strncmp didn't work. That is not surprising, as apparently "str" semantics are not really what is wanted (hint: de4x5_strncmp only stops when two different bytes are encountered or the end is reached; not if either byte happens to be 0). de4x5_strncmp is actually a memcmp (except for the signature and that bytes are not necessarily treated as unsigned char); since only the boolean value of the result is used we can just replace de4x5_strncmp with memcmp. Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Grant Grundler <grundler@parisc-linux.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09drivers: net : cpsw: Update Kconfig for CPSWLokesh Vutla
CPSW is present in AM33xx, AM43xx, DRA7xx. Updating the Kconfig to depend on ARCH_OMAP2PLUS instead of listing all SoC's. Signed-off-by: Lokesh Vutla <lokeshvutla@ti.com> Acked-by: Mugunthan V N <mugunthanvnm@ti.com> Reviewed-by: Felipe Balbi <balbi@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09tipc: fix missing spinlock init and nullptr oopsErik Hugne
commit 908344cdda80 ("tipc: fix bug in multicast congestion handling") introduced two bugs with the bclink wakeup function. This commit fixes the missing spinlock init for the waiting_sks list. We also eliminate the race condition between the waiting_sks length check/dequeue operations in tipc_bclink_wakeup_users by simply removing the redundant length check. Signed-off-by: Erik Hugne <erik.hugne@ericsson.com> Acked-by: Tero Aho <Tero.Aho@coriant.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09r8152: redefine REALTEK_USB_DEVICEhayeswang
Redefine REALTEK_USB_DEVICE for the desired USB interface for probe(). There are three USB interfaces for the device. USB_CLASS_COMM and USB_CLASS_CDC_DATA are for ECM mode (config #2). USB_CLASS_VENDOR_SPEC is for the vendor mode (config #1). However, we are not interesting in USB_CLASS_CDC_DATA for probe(), so redefine REALTEK_USB_DEVICE to ignore the USB interface class of USB_CLASS_CDC_DATA. Signed-off-by: Hayes Wang <hayeswang@realtek.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09net: avoid two atomic operations in fast clonesEric Dumazet
Commit ce1a4ea3f125 ("net: avoid one atomic operation in skb_clone()") took the wrong way to save one atomic operation. It is actually possible to avoid two atomic operations, if we do not change skb->fclone values, and only rely on clone_ref content to signal if the clone is available or not. skb_clone() can simply use the fast clone if clone_ref is 1. kfree_skbmem() can avoid the atomic_dec_and_test() if clone_ref is 1. Note that because we usually free the clone before the original skb, this particular attempt is only done for the original skb to have better branch prediction. SKB_FCLONE_FREE is removed. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Chris Mason <clm@fb.com> Cc: Sabrina Dubroca <sd@queasysnail.net> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09Update old iproute2 and Xen Remus linksAndrew Shewmaker
Signed-off-by: Andrew Shewmaker <agshew@gmail.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09rtnetlink: delay RTM_DELLINK notification until after ndo_uninit()Mahesh Bandewar
The commit 56bfa7ee7c ("unregister_netdevice : move RTM_DELLINK to until after ndo_uninit") tried to do this ealier but while doing so it created a problem. Unfortunately the delayed rtmsg_ifinfo() also delayed call to fill_info(). So this translated into asking driver to remove private state and then query it's private state. This could have catastropic consequences. This change breaks the rtmsg_ifinfo() into two parts - one takes the precise snapshot of the device by called fill_info() before calling the ndo_uninit() and the second part sends the notification using collected snapshot. It was brought to notice when last link is deleted from an ipvlan device when it has free-ed the port and the subsequent .fill_info() call is trying to get the info from the port. kernel: [ 255.139429] ------------[ cut here ]------------ kernel: [ 255.139439] WARNING: CPU: 12 PID: 11173 at net/core/rtnetlink.c:2238 rtmsg_ifinfo+0x100/0x110() kernel: [ 255.139493] Modules linked in: ipvlan bonding w1_therm ds2482 wire cdc_acm ehci_pci ehci_hcd i2c_dev i2c_i801 i2c_core msr cpuid bnx2x ptp pps_core mdio libcrc32c kernel: [ 255.139513] CPU: 12 PID: 11173 Comm: ip Not tainted 3.18.0-smp-DEV #167 kernel: [ 255.139514] Hardware name: Intel RML,PCH/Ibis_QC_18, BIOS 1.0.10 05/15/2012 kernel: [ 255.139515] 0000000000000009 ffff880851b6b828 ffffffff815d87f4 00000000000000e0 kernel: [ 255.139516] 0000000000000000 ffff880851b6b868 ffffffff8109c29c 0000000000000000 kernel: [ 255.139518] 00000000ffffffa6 00000000000000d0 ffffffff81aaf580 0000000000000011 kernel: [ 255.139520] Call Trace: kernel: [ 255.139527] [<ffffffff815d87f4>] dump_stack+0x46/0x58 kernel: [ 255.139531] [<ffffffff8109c29c>] warn_slowpath_common+0x8c/0xc0 kernel: [ 255.139540] [<ffffffff8109c2ea>] warn_slowpath_null+0x1a/0x20 kernel: [ 255.139544] [<ffffffff8150d570>] rtmsg_ifinfo+0x100/0x110 kernel: [ 255.139547] [<ffffffff814f78b5>] rollback_registered_many+0x1d5/0x2d0 kernel: [ 255.139549] [<ffffffff814f79cf>] unregister_netdevice_many+0x1f/0xb0 kernel: [ 255.139551] [<ffffffff8150acab>] rtnl_dellink+0xbb/0x110 kernel: [ 255.139553] [<ffffffff8150da90>] rtnetlink_rcv_msg+0xa0/0x240 kernel: [ 255.139557] [<ffffffff81329283>] ? rhashtable_lookup_compare+0x43/0x80 kernel: [ 255.139558] [<ffffffff8150d9f0>] ? __rtnl_unlock+0x20/0x20 kernel: [ 255.139562] [<ffffffff8152cb11>] netlink_rcv_skb+0xb1/0xc0 kernel: [ 255.139563] [<ffffffff8150a495>] rtnetlink_rcv+0x25/0x40 kernel: [ 255.139565] [<ffffffff8152c398>] netlink_unicast+0x178/0x230 kernel: [ 255.139567] [<ffffffff8152c75f>] netlink_sendmsg+0x30f/0x420 kernel: [ 255.139571] [<ffffffff814e0b0c>] sock_sendmsg+0x9c/0xd0 kernel: [ 255.139575] [<ffffffff811d1d7f>] ? rw_copy_check_uvector+0x6f/0x130 kernel: [ 255.139577] [<ffffffff814e11c9>] ? copy_msghdr_from_user+0x139/0x1b0 kernel: [ 255.139578] [<ffffffff814e1774>] ___sys_sendmsg+0x304/0x310 kernel: [ 255.139581] [<ffffffff81198723>] ? handle_mm_fault+0xca3/0xde0 kernel: [ 255.139585] [<ffffffff811ebc4c>] ? destroy_inode+0x3c/0x70 kernel: [ 255.139589] [<ffffffff8108e6ec>] ? __do_page_fault+0x20c/0x500 kernel: [ 255.139597] [<ffffffff811e8336>] ? dput+0xb6/0x190 kernel: [ 255.139606] [<ffffffff811f05f6>] ? mntput+0x26/0x40 kernel: [ 255.139611] [<ffffffff811d2b94>] ? __fput+0x174/0x1e0 kernel: [ 255.139613] [<ffffffff814e2129>] __sys_sendmsg+0x49/0x90 kernel: [ 255.139615] [<ffffffff814e2182>] SyS_sendmsg+0x12/0x20 kernel: [ 255.139617] [<ffffffff815df092>] system_call_fastpath+0x12/0x17 kernel: [ 255.139619] ---[ end trace 5e6703e87d984f6b ]--- Signed-off-by: Mahesh Bandewar <maheshb@google.com> Reported-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Cc: Eric Dumazet <edumazet@google.com> Cc: Roopa Prabhu <roopa@cumulusnetworks.com> Cc: David S. Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09Merge tag 'master-2014-12-01' of ↵David S. Miller
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless John W. Linville says: ==================== pull request: wireless 2014-12-03 One last(?) batch of fixes hoping to make 3.18... In this episode, we have another trio of rtlwifi fixes repairing a little more damage from the major update of the rtlwifi-family of drivers. These editing mistakes caused some memory corruption and missed a flag critical to proper interrupt handling. Together, these fix the kernel regression reported at https://bugzilla.kernel.org/show_bug.cgi?id=88951 by Catalin Iacob. Please let me know if there are problems! ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09tc_act: export uapi header filestephen hemminger
This file is used by iproute2 and should be exported. Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09Merge branch 'cxgb4-next'David S. Miller
Hariprasad Shenai says: ==================== cxgb4/cxgb4vf: T5 BAR2 and ethtool related fixes This series adds new interface to calculate BAR2 SGE queue register address for cxgb4 and cxgb4vf driver and some more sge related fixes for T5. Also adds a patch which updates the FW version displayed by ethtool after firmware flash. The patches series is created against 'net-next' tree. And includes patches on cxgb4 and cxgb4vf driver. We have included all the maintainers of respective drivers. Kindly review the change and let us know in case of any review comments. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09cxgb4: Update firmware version after flashing it via ethtoolHariprasad Shenai
After successfully loading new firmware, reload the new firmware's version number information so "ethtool -i", etc. will report the right value Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09cxgb4/cxgb4vf: Use new interfaces to calculate BAR2 SGE Queue Register addressesHariprasad Shenai
Use BAR2 Going To Sleep (GTS) for T5 and later. Use new BAR2 User Doorbells for T5 for both cxgb4 and cxgb4vf driver. Based on original work by Casey Leedom <leedom@chelsio.com> Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09cxgb4/cxgb4vf: Add code to calculate T5 BAR2 Offsets for SGE Queue RegistersHariprasad Shenai
Add new Common Code facilities for calculating T5 BAR2 Offsets for SGE Queue Registers. This new code can handle situations where Queues Per Page * SGE BAR2 Queue Register Area Size > Page Size Based on original work by Casey Leedom <leedom@chelsio.com> Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09cxgb4vf: Add and initialize some sge params for VF driverHariprasad Shenai
Add sge_vf_eq_qpp and sge_vf_iq_qpp to (struct sge_params), initialize sge_queues_per_page and sge_vf_qpp in t4vf_get_sge_params(), add new t4vf_prep_adapter() which initializes basic adapter parameters. Grab both SGE_EGRESS_QUEUES_PER_PAGE_VF and SGE_INGRESS_QUEUES_PER_PAGE_VF for VF Drivers since we need both to calculate the User Doorbell area offsets for Egress and Ingress Queues. Based on original work by Casey Leedom <leedom@chelsio.com> Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09tipc: drop tx side permission checksErik Hugne
Part of the old remote management feature is a piece of code that checked permissions on the local system to see if a certain operation was permitted, and if so pass the command to a remote node. This serves no purpose after the removal of remote management with commit 5902385a2440 ("tipc: obsolete the remote management feature") so we remove it. Signed-off-by: Erik Hugne <erik.hugne@ericsson.com> Reviewed-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09rocker: fix eth_type type in struct rocker_ctrlJiri Pirko
Signed-off-by: Jiri Pirko <jiri@resnulli.us> Signed-off-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09rocker: introduce be put/get variants and use it when appropriateJiri Pirko
This kills the sparse warnings. Signed-off-by: Jiri Pirko <jiri@resnulli.us> Signed-off-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09bnx2x: Limit 1G link enforcementYaniv Rosner
Change 1G-SFP module detection by verifying not only that it's not compliant with 10G-Ethernet, but also that it's 1G-ethernet compliant. Signed-off-by: Yaniv Rosner <Yaniv.Rosner@qlogic.com> Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09stmmac: fix max coal timer parameterGiuseppe CAVALLARO
This patch is to fix the max coalesce timer setting that can be provided by ethtool. The default value (STMMAC_COAL_TX_TIMER) was used in the set_coalesce helper instead of the max one (STMMAC_MAX_COAL_TX_TICK, so defined but not used). Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09net: sctp: use MAX_HEADER for headroom reserve in output pathDaniel Borkmann
To accomodate for enough headroom for tunnels, use MAX_HEADER instead of LL_MAX_HEADER. Robert reported that he has hit after roughly 40hrs of trinity an skb_under_panic() via SCTP output path (see reference). I couldn't reproduce it from here, but not using MAX_HEADER as elsewhere in other protocols might be one possible cause for this. In any case, it looks like accounting on chunks themself seems to look good as the skb already passed the SCTP output path and did not hit any skb_over_panic(). Given tunneling was enabled in his .config, the headroom would have been expanded by MAX_HEADER in this case. Reported-by: Robert Święcki <robert@swiecki.net> Reference: https://lkml.org/lkml/2014/12/1/507 Fixes: 594ccc14dfe4d ("[SCTP] Replace incorrect use of dev_alloc_skb with alloc_skb in sctp_packet_transmit().") Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09cxgb4: Update FW version string to match FW binary version 1.12.25.0Hariprasad Shenai
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09cxgb4: Add a check for flashing FW using ethtoolHariprasad Shenai
Don't let T4 firmware flash on a T5 adapter and vice-versa using ethtool Based on original work by Casey Leedom <leedom@chelsio.com> Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09ipv6: remove useless spin_lock/spin_unlockDuan Jiong
xchg is atomic, so there is no necessary to use spin_lock/spin_unlock to protect it. At last, remove the redundant opt = xchg(&inet6_sk(sk)->opt, opt); statement. Signed-off-by: Duan Jiong <duanj.fnst@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09Merge branch 'amd-xgbe'David S. Miller
Tom Lendacky says: ==================== amd-xgbe: AMD XGBE driver fixes 2014-12-02 The following series of patches includes two bug fixes. Unfortunately, the first patch will create a conflict when eventually merged into net-next but should be very easy to resolve. - Do not clear the interrupt bit in the xgbe_ring_data structure - Associate a Tx SKB with the proper xgbe_ring_data structure This patch series is based on net. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09amd-xgbe: Associate Tx SKB with proper ring descriptorLendacky, Thomas
The SKB for a Tx packet is associated with an xgbe_ring_data structure in the xgbe_map_tx_skb function. However, it is being saved in the structure after the last structure used when the SKB is mapped. Use the last used structure to save the SKB value. Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09amd-xgbe: Do not clear interrupt indicatorLendacky, Thomas
The interrupt value within the xgbe_ring_data structure is used as an indicator of which Rx descriptor should have the INTE bit set to generate an interrupt when that Rx descriptor is used. This bit was mistakenly cleared in the xgbe_unmap_rdata function, effectively nullifying the ethtool rx-frames support. Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09amd-xgbe: IRQ names require allocated memoryLendacky, Thomas
When requesting an irq, the name passed in must be (part of) allocated memory. The irq name was a local variable and resulted in random characters when listing /proc/interrupts. Add a character field to the xgbe_channel structure to hold the irq name and use that. Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09sunrpc/cache: convert to use string_escape_str()Andy Shevchenko
There is nice kernel helper to escape a given strings by provided rules. Let's use it instead of custom approach. Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> [bfields@redhat.com: fix length calculation] Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: only call test_bit once in svc_xprt_receivedJeff Layton
...move the WARN_ON_ONCE inside the following if block since they use the same condition. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09fs: nfsd: Fix signedness bug in compare_blobRasmus Villemoes
Bugs similar to the one in acbbe6fbb240 (kcmp: fix standard comparison bug) are in rich supply. In this variant, the problem is that struct xdr_netobj::len has type unsigned int, so the expression o1->len - o2->len _also_ has type unsigned int; it has completely well-defined semantics, and the result is some non-negative integer, which is always representable in a long long. But this means that if the conditional triggers, we are guaranteed to return a positive value from compare_blob. In this case it could be fixed by - res = o1->len - o2->len; + res = (long long)o1->len - (long long)o2->len; but I'd rather eliminate the usually broken 'return a - b;' idiom. Reviewed-by: Jeff Layton <jlayton@primarydata.com> Cc: <stable@vger.kernel.org> Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: add some tracepoints around enqueue and dequeue of svc_xprtJeff Layton
These were useful when I was tracking down a race condition between svc_xprt_do_enqueue and svc_get_next_xprt. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: convert to lockless lookup of queued server threadsJeff Layton
Testing has shown that the pool->sp_lock can be a bottleneck on a busy server. Every time data is received on a socket, the server must take that lock in order to dequeue a thread from the sp_threads list. Address this problem by eliminating the sp_threads list (which contains threads that are currently idle) and replacing it with a RQ_BUSY flag in svc_rqst. This allows us to walk the sp_all_threads list under the rcu_read_lock and find a suitable thread for the xprt by doing a test_and_set_bit. Note that we do still have a potential atomicity problem however with this approach. We don't want svc_xprt_do_enqueue to set the rqst->rq_xprt pointer unless a test_and_set_bit of RQ_BUSY returned zero (which indicates that the thread was idle). But, by the time we check that, the bit could be flipped by a waking thread. To address this, we acquire a new per-rqst spinlock (rq_lock) and take that before doing the test_and_set_bit. If that returns false, then we can set rq_xprt and drop the spinlock. Then, when the thread wakes up, it must set the bit under the same spinlock and can trust that if it was already set then the rq_xprt is also properly set. With this scheme, the case where we have an idle thread no longer needs to take the highly contended pool->sp_lock at all, and that removes the bottleneck. That still leaves one issue: What of the case where we walk the whole sp_all_threads list and don't find an idle thread? Because the search is lockess, it's possible for the queueing to race with a thread that is going to sleep. To address that, we queue the xprt and then search again. If we find an idle thread at that point, we can't attach the xprt to it directly since that might race with a different thread waking up and finding it. All we can do is wake the idle thread back up and let it attempt to find the now-queued xprt. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Tested-by: Chris Worley <chris.worley@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: fix potential races in pool_stats collectionJeff Layton
In a later patch, we'll be removing some spinlocking around the socket and thread queueing code in order to fix some contention problems. At that point, the stats counters will no longer be protected by the sp_lock. Change the counters to atomic_long_t fields, except for the "sockets_queued" counter which will still be manipulated under a spinlock. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Tested-by: Chris Worley <chris.worley@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: add a rcu_head to svc_rqst and use kfree_rcu to free itJeff Layton
...also make the manipulation of sp_all_threads list use RCU-friendly functions. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Tested-by: Chris Worley <chris.worley@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: require svc_create callers to pass in meaningful shutdown routineJeff Layton
Currently all svc_create callers pass in NULL for the shutdown parm, which then gets fixed up to be svc_rpcb_cleanup if the service uses rpcbind. Simplify this by instead having the the only caller that requires it (lockd) pass in svc_rpcb_cleanup and get rid of the special casing. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: have svc_wake_up only deal with pool 0Jeff Layton
The way that svc_wake_up works is a bit inefficient. It walks all of the available pools for a service and either wakes up a task in each one or sets the SP_TASK_PENDING flag in each one. When svc_wake_up is called, there is no need to wake up more than one thread to do this work. In practice, only lockd currently uses this function and it's single threaded anyway. Thus, this just boils down to doing a wake up of a thread in pool 0 or setting a single flag. Eliminate the for loop in this function and change it to just operate on pool 0. Also update the comments that sit above it and get rid of some code that has been commented out for years now. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: convert sp_task_pending flag to use atomic bitopsJeff Layton
In a later patch, we'll want to be able to handle this flag without holding the sp_lock. Change this field to an unsigned long flags field, and declare a new flag in it that can be managed with atomic bitops. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: move rq_cachetype field to better optimize spaceJeff Layton
There are a couple of holes in the svc_rqst field on x86_64. Move the rq_cachetype to a different location to eliminate both of them. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: move rq_splice_ok flag into rq_flagsJeff Layton
Signed-off-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-12-09sunrpc: move rq_dropme flag into rq_flagsJeff Layton
Signed-off-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
generated by cgit (git 2.34.1) at 2025-09-14 15:44:37 +0000