summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2015-11-02net: rds: changing the return type from int to voidSaurabh Sengar
as result of function rds_iw_flush_mr_pool is nowhere checked, changing its return type from int to void. also removing the unused variable rc as there is nothing to return Signed-off-by: Saurabh Sengar <saurabh.truth@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-02Merge tag 'linux-can-fixes-for-4.3-20151030' of ↵David S. Miller
git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can Marc Kleine-Budde says: ==================== pull-request: can 2015-10-30 this is a pull request for the upcoming v4.3 release. Marek Vasut provides a patch to use the correct attrlen in the nla_put() in the can_fill_info() function. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-02Merge tag 'pinctrl-v4.4-1' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl Pull pin control updates from Linus Walleij: "This is the big bulk of pin control changes for the v4.4 kernel development cycle. Development pace is high in pin control again this merge window. 28 contributors, 83 patches. It hits a few sites outside the pin control subsystem: - Device tree bindings in Documentation (as usual) - MAINTAINERS - drivers/base/* for the "init" state handling by Doug Anderson. This has been ACKed by Greg. - drivers/usb/renesas_usbhs/rcar2.c, for a dependent Renesas change in the USB subsystem. This has been ACKed by both Greg and Felipe. - arch/arm/boot/dts/sama5d2.dtsi - this should ideally have gone through the ARM SoC tree but ended up here. This time I am using Geert Uytterhoeven as submaintainer for SH PFC since the are three-four people working in parallel with new Renesas ASICs. Summary of changes: Infrastructure: - Doug Anderson wrote a patch adding an "init" state different from the "default" state for pin control state handling in the core framework. This is applied before the driver's probe() call if defined and takes precedence over "default". If both are defined, "init" will be applied *before* probe() and "default" will be applied *after* probe(). Significant subdriver improvements: - SH PFC is switched to getting GPIO ranges from the device tree ranges property on DT platforms. - Got rid of CONFIG_ARCH_SHMOBILE_LEGACY, we are all modernized. - Got rid of SH PFC hardcoded IRQ numbers. - Allwinner sunxi external interrupt through the "r" controller. - Moved the Cygnus driver to use DT-provided GPIO ranges. New drivers: - Atmel PIO4 pin controller for the SAMA4D2 family New subdrivers: - Rockchip RK3036 subdriver - Renesas SH PFC R8A7795 subdriver - Allwinner sunxi A83T PIO subdriver - Freescale i.MX7d iomux lpsr subdriver - Marvell Berlin BG4CT subdriver - SiRF Atlas 7 step B SoC subdriver - Intel Broxton SoC subdriver Apart from this, the usual slew if syntactic and semantic fixes" * tag 'pinctrl-v4.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl: (81 commits) pinctrl: pinconf: remove needless loop pinctrl: uniphier: guard uniphier directory with CONFIG_PINCTRL_UNIPHIER pinctrl: zynq: fix UTF-8 errors pinctrl: zynq: Initialize early pinctrl: at91: add missing of_node_put pinctrl: tegra-xusb: Correct lane mux options pinctrl: intel: Add Intel Broxton pin controller support pinctrl: intel: Allow requesting pins which are in ACPI mode as GPIOs pinctrl: intel: Add support for multiple GPIO chips sharing the interrupt drivers/pinctrl: Add the concept of an "init" state pinctrl: uniphier: set input-enable before pin-muxing pinctrl: cygnus: Add new compatible string for gpio controller driver pinctrl: cygnus: Remove GPIO to Pinctrl pin mapping from driver pinctrl: cygnus: Optional DT property to support pin mappings pinctrl: sunxi: Add irq pinmuxing to sun6i "r" pincontroller pinctrl: sunxi: Fix irq_of_xlate for the r_pio pinctrl block pinctrl: sh-pfc: Remove obsolete r8a7778 platform_device_id entry pinctrl: sh-pfc: Remove obsolete r8a7779 platform_device_id entry pinctrl: sh-pfc: Stop including <linux/platform_data/gpio-rcar.h> usb: renesas_usbhs: Remove unneeded #include <linux/platform_data/gpio-rcar.h> ...
2015-11-02Merge branch 'encx24j600-fixes'David S. Miller
Javier Martinez Canillas says: ==================== net: encx24j600: Fix SPI driver module autoload Recently I've been trying to fix module autoloading for all SPI drivers and found that the encx24j600 driver does not fill module alias information due missing a MODULE_DEVICE_TABLE() so module autload won't work and the driver Kconfig symbol is tristate which means the driver can be built as a module. But also the SPI id table is not correctly defined so this series fixes both issues. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-02net: encx24j600: Export missing SPI module alias informationJavier Martinez Canillas
The driver Kconfig symbol is tristate which means that it can be built as a module but the module alias information is not added to the module info so module autoload won't work since user-space won't have the information. Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-02net: encx24j600: Fix SPI id table definitionJavier Martinez Canillas
A driver's SPI id table is expected to be an array of struct spi_device_id that ends with a zero-initialized sentinel entry. But this driver defines the table as a single struct spi_device_id and sets .id_table to a pointer to this struct. But spi_match_id() has a loop that iterates while the struct spi_device_id .name[0] is not NULL, so not having a sentinel can cause a NULL pointer deference error. This patch defines the SPI id table correctly as all other SPI drivers do. Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-02Merge tag 'edac_for_4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bpLinus Torvalds
Pull EDAC updates from Borislav Petkov: "A bunch of fixes all over the place and some hw enablement this time. - Convert EDAC to debugfs wrappers and make drivers use those (Borislav Petkov) - L3 and SoC support for xgene_edac (Loc Ho) - AMD F15h, models 0x60-6f support to amd64_edac (Aravind Gopalakrishnan) - Fixes and cleanups all over the place" * tag 'edac_for_4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp: (22 commits) EDAC: Fix PAGES_TO_MiB macro misuse EDAC, altera: SoCFPGA EDAC should not look for ECC_CORR_EN EDAC: Use edac_debugfs_remove_recursive() EDAC, ppc4xx_edac: Fix module autoload for OF platform driver Documentation/EDAC: Add reference documents section for amd64_edac EDAC, amd64_edac: Update copyright and remove changelog EDAC, amd64_edac: Extend scrub rate support to F15hM60h EDAC: Don't allow empty DIMM labels EDAC: Fix sysfs dimm_label store operation EDAC: Fix sysfs dimm_label show operation arm64, EDAC: Add L3/SoC DT subnodes to the APM X-Gene SoC EDAC node EDAC, xgene: Add SoC support EDAC, xgene: Fix possible sprintf() overflow issue EDAC, xgene: Add L3 support EDAC, Documentation: Update X-Gene EDAC binding for L3/SoC subnodes EDAC, sb_edac: Fix TAD presence check for sbridge_mci_bind_devs() EDAC, ghes_edac: Remove redundant memory_type array EDAC, xgene: Convert to debugfs wrappers EDAC, i5100: Convert to debugfs wrappers EDAC, altera: Convert to debugfs wrappers ...
2015-11-02enic: assign affinity hint to interruptsGovindarajulu Varadarajan
The affinity hint is used by the user space daemon, irqbalancer, to indicate a preferred CPU mask for irqs. This patch sets the irq affinity hint to local numa core first, when exausted we try non-local numa cores. Also set tx xps cpus mask bassed on affinity hint. v2: remove the global affinity policy. Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-02Merge tag 'mmc-v4.4' of git://git.linaro.org/people/ulf.hansson/mmcLinus Torvalds
Pull MMC updates from Ulf Hansson: "MMC core: - Add new API to set VCCQ voltage - mmc_regulator_set_vqmmc() - Add new ioctl to allow userspace to send multi commands - Wait for card busy signalling before starting SDIO requests - Remove MMC_CLKGATE - Enable tuning for DDR50 mode - Some code clean-up/improvements to mmc pwrseq - Use highest priority for eMMC restart handler - Add DT bindings for eMMC hardware reset support - Extend the mmc_send_tuning() API - Improve ios show for debugfs - A couple of code optimizations MMC host: - Some generic OF improvements - Various code clean-ups - sirf: Add support for DDR50 - sunxi: Add support for card busy detection - mediatek: Use MMC_CAP_RUNTIME_RESUME - mediatek: Add support for eMMC HW-reset - mediatek: Add support for HS400 - dw_mmc: Convert to use the new mmc_regulator_set_vqmmc() API - dw_mmc: Add external DMA interface support - dw_mmc: Some various improvements - dw_mmc-rockchip: MMC tuning with the clock phase framework - sdhci: Properly clear IRQs during resume - sdhci: Enable tuning for DDR50 mode - sdhci-of-esdhc: Use IRQ mode for card detection - sdhci-of-esdhc: Support both BE and LE host controller - sdhci-pci: Build o2micro support in the same module - sdhci-pci: Support for new Intel host controllers - sdhci-acpi: Support for new Intel host controllers" * tag 'mmc-v4.4' of git://git.linaro.org/people/ulf.hansson/mmc: (73 commits) mmc: dw_mmc: fix the wrong setting for UHS-DDR50 mode mmc: dw_mmc: fix the CardThreshold boundary at CardThrCtl register mmc: dw_mmc: NULL dereference in error message mmc: pwrseq: Use highest priority for eMMC restart handler mmc: mediatek: add HS400 support mmc: mmc: extend the mmc_send_tuning() mmc: mediatek: add implement of ops->hw_reset() mmc: mediatek: fix got GPD checksum error interrupt when data transfer mmc: mediatek: change the argument "ddr" to "timing" mmc: mediatek: make cmd_ints_mask to const mmc: dt-bindings: update Mediatek MMC bindings mmc: core: Add DT bindings for eMMC hardware reset support mmc: omap_hsmmc: Enable omap_hsmmc for Keystone 2 mmc: sdhci-acpi: Add more ACPI HIDs for Intel controllers mmc: sdhci-pci: Add more PCI IDs for Intel controllers arm: lpc18xx_defconfig: remove CONFIG_MMC_DW_IDMAC arm: hisi_defconfig: remove CONFIG_MMC_DW_IDMAC arm: exynos_defconfig: remove CONFIG_MMC_DW_IDMAC arc: axs10x_defconfig: remove CONFIG_MMC_DW_IDMAC mips: pistachio_defconfig: remove CONFIG_MMC_DW_IDMAC ...
2015-11-02ipv4: use l4 hash for locally generated multipath flowsPaolo Abeni
This patch changes how the multipath hash is computed for locally generated flows: now the hash comprises l4 information. This allows better utilization of the available paths when the existing flows have the same source IP and the same destination IP: with l3 hash, even when multiple connections are in place simultaneously, a single path will be used, while with l4 hash we can use all the available paths. v2 changes: - use get_hash_from_flowi4() instead of implementing just another l4 hash function Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-02Merge tag 'hwmon-for-linus-v4.4' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging Pull hwmon updates from Guenter Roeck: "New driver for MAX31790, added support for TMP75C, as well as cleanups and minor improvements in various drivers" * tag 'hwmon-for-linus-v4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging: hwmon: (fam15h_power) Add max compute unit accumulated power hwmon: (fam15h_power) Enable power1_input on AMD Carrizo hwmon: (fam15h_power) Refactor attributes for dynamically added hwmon: (ina2xx) remove no longer used variable 'kind' hwmon: (nct6775) Introduce separate temperature labels for NCT6792 and NCT6793 hwmon: (nct6775) NCT6791D and NCT6792D have an additional temperature source hwmon: (ina2xx) give precedence to DT over checking for platform data. hwmon: (ina2xx) convert driver to using regmap hwmon: (coretemp) Increase limit of maximum core ID from 32 to 128. hwmon: (lm75) Add support for TMP75C hwmon: (ibmpowernv) Add OF compatibility table entry hwmon: (abx500) drop the use of IRQF_NO_SUSPEND hwmon: (max31790) Fix dereference of ERR_PTR hwmon: Driver for Maxim MAX31790
2015-11-02tracing: ftrace_event_is_function() can return booleanYaowei Bai
Make ftrace_event_is_function() return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Link: http://lkml.kernel.org/r/1443537816-5788-9-git-send-email-bywxiaobai@163.com Signed-off-by: Yaowei Bai <bywxiaobai@163.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02tracing: is_legal_op() can return booleanYaowei Bai
Make is_legal_op() return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Link: http://lkml.kernel.org/r/1443537816-5788-8-git-send-email-bywxiaobai@163.com Signed-off-by: Yaowei Bai <bywxiaobai@163.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02ring-buffer: rb_event_is_commit() can return booleanYaowei Bai
Make rb_event_is_commit() return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Link: http://lkml.kernel.org/r/1443537816-5788-7-git-send-email-bywxiaobai@163.com Signed-off-by: Yaowei Bai <bywxiaobai@163.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02ring-buffer: rb_per_cpu_empty() can return booleanYaowei Bai
Makes rb_per_cpu_empty() return bool to improve readability. No functional change. Link: http://lkml.kernel.org/r/1443537816-5788-6-git-send-email-bywxiaobai@163.com Signed-off-by: Yaowei Bai <bywxiaobai@163.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02ring_buffer: ring_buffer_empty{cpu}() can return booleanYaowei Bai
Make ring_buffer_empty() and ring_buffer_empty_cpu() return bool. No functional change. Link: http://lkml.kernel.org/r/1443537816-5788-5-git-send-email-bywxiaobai@163.com Signed-off-by: Yaowei Bai <bywxiaobai@163.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02ring-buffer: rb_is_reader_page() can return booleanYaowei Bai
Make rb_is_reader_page() return bool to improve readability due to this particular function only using either true or false as its return value. No functional change. Link: http://lkml.kernel.org/r/1443537816-5788-4-git-send-email-bywxiaobai@163.com Signed-off-by: Yaowei Bai <bywxiaobai@163.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02tracing: report_latency() in trace_irqsoff.c can return booleanYaowei Bai
This patch makes report_latency return bool due to this particular function only using either one or zero as its return value. No functional change. Link: http://lkml.kernel.org/r/1443537816-5788-3-git-send-email-bywxiaobai@163.com Signed-off-by: Yaowei Bai <bywxiaobai@163.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02tracing: report_latency() in trace_sched_wakeup.c can return booleanYaowei Bai
This patch makes report_latency return bool to improve readability, indicating whether this new latency should be reported/recorded. No functional change. Link: http://lkml.kernel.org/r/1443537816-5788-2-git-send-email-bywxiaobai@163.com Signed-off-by: Yaowei Bai <bywxiaobai@163.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02Sample: Trace_event: Correct the commentsChunyan Zhang
The commit 889204278ccf ("tracing: Update trace-event-sample with TRACE_SYSTEM_VAR documentation") changed TRACE_SYSTEM to 'sample-trace', but didn't make the according change of its name in the comments. Link: http://lkml.kernel.org/r/1443599650-23680-1-git-send-email-zhang.chunyan@linaro.org Signed-off-by: Chunyan Zhang <zhang.chunyan@linaro.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02cris: Drop reference to get_cmos_time()Guenter Roeck
Function get_cmos_time() was removed with commit 657926a83df9 ("cris: time: Cleanup of persistent clock stuff"). The remaining reference to it may cause the following build error. arch/cris/kernel/built-in.o:(___ksymtab+get_cmos_time+0x0): undefined reference to `get_cmos_time' Makefile:946: recipe for target 'vmlinux' failed Fixes: 657926a83df9 ("cris: time: Cleanup of persistent clock stuff") Cc: Xunlei Pang <pang.xunlei@linaro.org> Cc: Rabin Vincent <rabin@rab.in> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02CRIS: Drop code related to obsolete or unused kconfigsJesper Nilsson
Drop all code related to Kconfigs that don't exist. Fix one Kconfig where it was actually typo:ed (ETRAX_KGB_PORT2) Drop content related to CRIS v32 SoCs from etraxgpio.h headerfile, all use of GPIO for both ETRAX FS and ARTPEC-3 should now be through standard gpiolib instead. Signed-off-by: Jesper Nilsson <jesper.nilsson@axis.com>
2015-11-02cris: time: Cleanup of persistent clock stuffXunlei Pang
- Remove update_persistent_clock(), as it does nothing now. - Remove read_persistent_clock(), let it fall back to the weak version. Cc: Mikael Starvik <starvik@axis.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Xunlei Pang <pang.xunlei@linaro.org> Acked-by: Rabin Vincent <rabin@rab.in> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02cris: re-use helpers to dump data in hex formatAndy Shevchenko
There are native helpers such as print_hex_byte() and %*ph specifier to dump data in hex format. Re-use them instead of a custom approach. Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02CRIS v32: remove old GPIO and LEDs codeRabin Vincent
Since we now have a gpiolib driver, remove this code: The gpio-etraxfs driver (along with things like gpio-keys-polled for polling support) replaces the GIO driver implementations in mach-a3 and mach-fs. The various generic external chip drivers replace the "virtual gpio" parts. The generic gpio-leds driver replaces the LED handling. Signed-off-by: Rabin Vincent <rabin@rab.in> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02CRIS v32: remove I2C bitbanging driverRabin Vincent
Now that we have a gpiolib GPIO driver, the generic i2c-gpio driver provides this functionality. Signed-off-by: Rabin Vincent <rabin@rab.in> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02CRIS v32: add ARTPEC-3 and P1343 device treesRabin Vincent
Add a device tree for the Axis P1343 with the ARTPEC-3 SoC and on-board LEDs and RTC. Signed-off-by: Rabin Vincent <rabin@rab.in> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02CRIS v32: dev88: add GPIO, LEDs, RTC, temp sensorRabin Vincent
Add the GPIO driver to the device tree and, using it, support for the LEDs and the RTC chip (via I2C-GPIO), as well as the temperature sensor (via SPI-GPIO). Signed-off-by: Rabin Vincent <rabin@rab.in> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02CRIS: add dt-bindings symlinkRabin Vincent
Add a dt-bindings symlink to get DT include files, as on other architectures. See c58299a ("kbuild: create an "include chroot" for DT bindings") for the details. Signed-off-by: Rabin Vincent <rabin@rab.in> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02CRIS v32: increase NR_IRQSRabin Vincent
Increase NR_IQRS so we can fit in GPIO interrupts. Signed-off-by: Rabin Vincent <rabin@rab.in> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02cris: arch-v10: kgdb: Add '__used' for static variable is_dyn_brkpChen Gang
Within one C file, current gcc can optimize the global static variables according to the C code, but it will skip assembly code -- it will pass them to gas directly. if the static variable is used between C code and assembly code in one C file (e.g. is_dyn_brkp in kgdb.c), it needs '__used' to let gcc know it should be still used, or gcc may remove it for optimization. The related error in this case: LD init/built-in.o arch/cris/arch-v10/kernel/built-in.o: In function `kgdb_handle_breakpoint': (.text+0x2aca): undefined reference to `is_dyn_brkp' arch/cris/arch-v10/kernel/built-in.o: In function `is_static': kgdb.c:(.text+0x2ada): undefined reference to `is_dyn_brkp' Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02cris: arch-v10: kgdb: Use BAR instead of DTP0 for register P12Chen Gang
For arch-v10, there is no DTP0 register, and at present, assembler know BAR, so use BAR instead of DTP0, the related error (with allmodconfig): CC arch/cris/arch-v10/kernel/kgdb.o {standard input}: Assembler messages: {standard input}:6: Error: Illegal operands {standard input}:6: Error: Illegal operands Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com> Acked-by: Hans-Peter Nilsson <hp@axis.com> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02cris: kgdb: use native hex2binAndy Shevchenko
There are kernel native helpers to convert hex ascii to the binary format: hex_to_bin() and hex2bin(). Thus, no need to reimplement them customly. Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Jesper Nilsson <jespern@axis.com>
2015-11-02tracing: Update instance_rmdir() to use tracefs_remove_recursiveJiaxing Wang
Update instancd_rmdir to use tracefs_remove_recursive instead of debugfs_remove_recursive.This was left in the transition from debugfs to tracefs. Link: http://lkml.kernel.org/r/1445169490-18315-2-git-send-email-hello.wjx@gmail.com Cc: stable@vger.kernel.org # 4.1+ Fixes: 8434dc9340cd2 ("tracing: Convert the tracing facility over to use tracefs") Signed-off-by: Jiaxing Wang <hello.wjx@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-11-02pNFS/flexfiles: Add support for FF_FLAGS_NO_IO_THRU_MDSTrond Myklebust
For loosely coupled pNFS/flexfiles systems, there is often no advantage at all in going through the MDS for I/O, since the MDS is subject to the same limitations as all other clients when talking to DSes. If a DS is unresponsive, I/O through the MDS will fail. For such systems, the only scalable solution is to have the pNFS clients retry doing pNFS, and so the protocol now provides a flag that allows the pNFS server to signal this. If LAYOUTGET returns FF_FLAGS_NO_IO_THRU_MDS, then we should assume that the MDS wants the client to retry using these devices, even if they were previously marked as being unavailable. To do so, we add a helper, ff_layout_mark_devices_valid() that will be called from layoutget. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-11-02pNFS/flexfiles: When mirrored, retry failed reads by switching mirrorsTrond Myklebust
If the pNFS/flexfiles file is mirrored, and a read to one mirror fails, then we should bump the mirror index, so that we retry to a different mirror. Once we've iterated through all mirrors and all failed, we can return the layout and issue a new LAYOUTGET. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-11-02SUNRPC: Remove the TCP-only restriction in bc_svc_process()Chuck Lever
Allow the use of other transport classes when handling a backward direction RPC call. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02svcrdma: Add backward direction service for RPC/RDMA transportChuck Lever
On NFSv4.1 mount points, the Linux NFS client uses this transport endpoint to receive backward direction calls and route replies back to the NFSv4.1 server. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Acked-by: "J. Bruce Fields" <bfields@fieldses.org> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Handle incoming backward direction RPC callsChuck Lever
Introduce a code path in the rpcrdma_reply_handler() to catch incoming backward direction RPC calls and route them to the ULP's backchannel server. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Add support for sending backward direction RPC repliesChuck Lever
Backward direction RPC replies are sent via the client transport's send_request method, the same way forward direction RPC calls are sent. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Pre-allocate Work Requests for backchannelChuck Lever
Pre-allocate extra send and receive Work Requests needed to handle backchannel receives and sends. The transport doesn't know how many extra WRs to pre-allocate until the xprt_setup_backchannel() call, but that's long after the WRs are allocated during forechannel setup. So, use a fixed value for now. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Pre-allocate backward rpc_rqst and send/receive buffersChuck Lever
xprtrdma's backward direction send and receive buffers are the same size as the forechannel's inline threshold, and must be pre- registered. The consumer has no control over which receive buffer the adapter chooses to catch an incoming backwards-direction call. Any receive buffer can be used for either a forward reply or a backward call. Thus both types of RPC message must all be the same size. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02SUNRPC: Abstract backchannel operationsChuck Lever
xprt_{setup,destroy}_backchannel() won't be adequate for RPC/RMDA bi-direction. In particular, receive buffers have to be pre- registered and posted in order to receive incoming backchannel requests. Add a virtual function call to allow the insertion of appropriate backchannel setup and destruction methods for each transport. In addition, freeing a backchannel request is a little different for RPC/RDMA. Introduce an rpc_xprt_op to handle the difference. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Saving IRQs no longer needed for rb_lockChuck Lever
Now that RPC replies are processed in a workqueue, there's no need to disable IRQs when managing send and receive buffers. This saves noticeable overhead per RPC. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Remove reply taskletChuck Lever
Clean up: The reply tasklet is no longer used. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Use workqueue to process RPC/RDMA repliesChuck Lever
The reply tasklet is fast, but it's single threaded. After reply traffic saturates a single CPU, there's no more reply processing capacity. Replace the tasklet with a workqueue to spread reply handling across all CPUs. This also moves RPC/RDMA reply handling out of the soft IRQ context and into a context that allows sleeps. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Replace send and receive arraysChuck Lever
The rb_send_bufs and rb_recv_bufs arrays are used to implement a pair of stacks for keeping track of free rpcrdma_req and rpcrdma_rep structs. Replace those arrays with free lists. To allow more than 512 RPCs in-flight at once, each of these arrays would be larger than a page (assuming 8-byte addresses and 4KB pages). Allowing up to 64K in-flight RPCs (as TCP now does), each buffer array would have to be 128 pages. That's an order-6 allocation. (Not that we're going there.) A list is easier to expand dynamically. Instead of allocating a larger array of pointers and copying the existing pointers to the new array, simply append more buffers to each list. This also makes it simpler to manage receive buffers that might catch backwards-direction calls, or to post receive buffers in bulk to amortize the overhead of ib_post_recv. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Reviewed-by: Devesh Sharma <devesh.sharma@avagotech.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Refactor reply handler error handlingChuck Lever
Clean up: The error cases in rpcrdma_reply_handler() almost never execute. Ensure the compiler places them out of the hot path. No behavior change expected. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Reviewed-by: Devesh Sharma <devesh.sharma@avagotech.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Prevent loss of completion signalsChuck Lever
Commit 8301a2c047cc ("xprtrdma: Limit work done by completion handler") was supposed to prevent xprtrdma's upcall handlers from starving other softIRQ work by letting them return to the provider before all CQEs have been polled. The logic assumes the provider will call the upcall handler again immediately if the CQ is re-armed while there are still queued CQEs. This assumption is invalid. The IBTA spec says that after a CQ is armed, the hardware must interrupt only when a new CQE is inserted. xprtrdma can't rely on the provider calling again, even though some providers do. Therefore, leaving CQEs on queue makes sense only when there is another mechanism that ensures all remaining CQEs are consumed in a timely fashion. xprtrdma does not have such a mechanism. If a CQE remains queued, the transport can wait forever to send the next RPC. Finally, move the wcs array back onto the stack to ensure that the poll array is always local to the CPU where the completion upcall is running. Fixes: 8301a2c047cc ("xprtrdma: Limit work done by completion ...") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Reviewed-by: Devesh Sharma <devesh.sharma@avagotech.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2015-11-02xprtrdma: Re-arm after missed eventsChuck Lever
ib_req_notify_cq(IB_CQ_REPORT_MISSED_EVENTS) returns a positive value if WCs were added to a CQ after the last completion upcall but before the CQ has been re-armed. Commit 7f23f6f6e388 ("xprtrmda: Reduce lock contention in completion handlers") assumed that when ib_req_notify_cq() returned a positive RC, the CQ had also been successfully re-armed, making it safe to return control to the provider without losing any completion signals. That is an invalid assumption. Change both completion handlers to continue polling while ib_req_notify_cq() returns a positive value. Fixes: 7f23f6f6e388 ("xprtrmda: Reduce lock contention in ...") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Reviewed-by: Devesh Sharma <devesh.sharma@avagotech.com> Tested-By: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
generated by cgit (git 2.34.1) at 2025-09-15 10:02:16 +0000