diff options
Diffstat (limited to '')
271 files changed, 3683 insertions, 1880 deletions
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index 65b3eac8856c..e8d25e784214 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -843,6 +843,10 @@ PAGE_SIZE multiple when read back. Amount of memory used to cache filesystem data, including tmpfs and shared memory. + sock + + Amount of memory used in network transmission buffers + file_mapped Amount of cached filesystem data mapped with mmap() diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt index 451fef26b4df..10587bdadbbe 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt +++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt @@ -68,7 +68,7 @@ ethernet@f0b60000 { phy1: ethernet-phy@1 { max-speed = <1000>; reg = <0x1>; - compatible = "brcm,28nm-gphy", "ethernet-phy-ieee802.3-c22"; + compatible = "ethernet-phy-ieee802.3-c22"; }; }; }; @@ -115,7 +115,7 @@ ethernet@f0ba0000 { phy0: ethernet-phy@0 { max-speed = <1000>; reg = <0x0>; - compatible = "brcm,bcm53125", "ethernet-phy-ieee802.3-c22"; + compatible = "ethernet-phy-ieee802.3-c22"; }; }; }; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt index 80411b2f0490..ecacfa44b1eb 100644 --- a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt @@ -4,8 +4,6 @@ Required properties: - compatible: should be "hisilicon,hns-dsaf-v1" or "hisilicon,hns-dsaf-v2". "hisilicon,hns-dsaf-v1" is for hip05. "hisilicon,hns-dsaf-v2" is for Hi1610 and Hi1612. -- dsa-name: dsa fabric name who provide this interface. - should be "dsafX", X is the dsaf id. - mode: dsa fabric mode string. only support one of dsaf modes like these: "2port-64vf", "6port-16rss", @@ -26,9 +24,8 @@ Required properties: Example: -dsa: dsa@c7000000 { +dsaf0: dsa@c7000000 { compatible = "hisilicon,hns-dsaf-v1"; - dsa_name = "dsaf0"; mode = "6port-16rss"; interrupt-parent = <&mbigen_dsa>; reg = <0x0 0xC0000000 0x0 0x420000 diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt index 41d19be7011e..e6a9d1c30878 100644 --- a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt @@ -4,8 +4,9 @@ Required properties: - compatible: "hisilicon,hns-nic-v1" or "hisilicon,hns-nic-v2". "hisilicon,hns-nic-v1" is for hip05. "hisilicon,hns-nic-v2" is for Hi1610 and Hi1612. -- ae-name: accelerator name who provides this interface, - is simply a name referring to the name of name in the accelerator node. +- ae-handle: accelerator engine handle for hns, + specifies a reference to the associating hardware driver node. + see Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt - port-id: is the index of port provided by DSAF (the accelerator). DSAF can connect to 8 PHYs. Port 0 to 1 are both used for adminstration purpose. They are called debug ports. @@ -41,7 +42,7 @@ Example: ethernet@0{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <0>; local-mac-address = [a2 14 e4 4b 56 76]; }; diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt index aeea50c84e92..d0cb8693963b 100644 --- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt +++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt @@ -6,12 +6,17 @@ Required properties: - interrupts: interrupt for the device - phy: See ethernet.txt file in the same directory. - phy-mode: See ethernet.txt file in the same directory -- clocks: a pointer to the reference clock for this device. +- clocks: List of clocks for this device. At least one clock is + mandatory for the core clock. If several clocks are given, then the + clock-names property must be used to identify them. Optional properties: - tx-csum-limit: maximum mtu supported by port that allow TX checksum. Value is presented in bytes. If not used, by default 1600B is set for "marvell,armada-370-neta" and 9800B for others. +- clock-names: List of names corresponding to clocks property; shall be + "core" for core clock and "bus" for the optional bus clock. + Example: diff --git a/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt b/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt index 79384113c2b0..694987d3c17a 100644 --- a/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt +++ b/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt @@ -38,7 +38,6 @@ Example : phy11: ethernet-phy@1 { reg = <1>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -48,7 +47,6 @@ Example : }; phy12: ethernet-phy@2 { reg = <2>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -58,7 +56,6 @@ Example : }; phy13: ethernet-phy@3 { reg = <3>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -68,7 +65,6 @@ Example : }; phy14: ethernet-phy@4 { reg = <4>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -85,7 +81,6 @@ Example : phy21: ethernet-phy@1 { reg = <1>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -95,7 +90,6 @@ Example : }; phy22: ethernet-phy@2 { reg = <2>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -105,7 +99,6 @@ Example : }; phy23: ethernet-phy@3 { reg = <3>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -115,7 +108,6 @@ Example : }; phy24: ethernet-phy@4 { reg = <4>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, diff --git a/Documentation/devicetree/bindings/net/mdio-mux.txt b/Documentation/devicetree/bindings/net/mdio-mux.txt index f65606f8d632..491f5bd55203 100644 --- a/Documentation/devicetree/bindings/net/mdio-mux.txt +++ b/Documentation/devicetree/bindings/net/mdio-mux.txt @@ -47,7 +47,6 @@ Example : phy11: ethernet-phy@1 { reg = <1>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -57,7 +56,6 @@ Example : }; phy12: ethernet-phy@2 { reg = <2>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -67,7 +65,6 @@ Example : }; phy13: ethernet-phy@3 { reg = <3>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -77,7 +74,6 @@ Example : }; phy14: ethernet-phy@4 { reg = <4>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -94,7 +90,6 @@ Example : phy21: ethernet-phy@1 { reg = <1>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -104,7 +99,6 @@ Example : }; phy22: ethernet-phy@2 { reg = <2>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -114,7 +108,6 @@ Example : }; phy23: ethernet-phy@3 { reg = <3>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -124,7 +117,6 @@ Example : }; phy24: ethernet-phy@4 { reg = <4>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt index 525e1658f2da..bc1c3c8bf8fa 100644 --- a/Documentation/devicetree/bindings/net/phy.txt +++ b/Documentation/devicetree/bindings/net/phy.txt @@ -17,8 +17,7 @@ Optional Properties: "ethernet-phy-ieee802.3-c22" or "ethernet-phy-ieee802.3-c45" for PHYs that implement IEEE802.3 clause 22 or IEEE802.3 clause 45 specifications. If neither of these are specified, the default is to - assume clause 22. The compatible list may also contain other - elements. + assume clause 22. If the phy's identifier is known then the list may contain an entry of the form: "ethernet-phy-idAAAA.BBBB" where @@ -28,6 +27,9 @@ Optional Properties: 4 hex digits. This is the chip vendor OUI bits 19:24, followed by 10 bits of a vendor specific ID. + The compatible list should not contain other values than those + listed here. + - max-speed: Maximum PHY supported speed (10, 100, 1000...) - broken-turn-around: If set, indicates the PHY device does not correctly diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index fde9fd06fa98..843b045b4069 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -240,8 +240,8 @@ Table 1-2: Contents of the status files (as of 4.1) RssFile size of resident file mappings RssShmem size of resident shmem memory (includes SysV shm, mapping of tmpfs and shared anonymous mappings) - VmData size of data, stack, and text segments - VmStk size of data, stack, and text segments + VmData size of private data segments + VmStk size of stack segments VmExe size of text segment VmLib size of shared library code VmPTE size of page table entries @@ -356,7 +356,7 @@ address perms offset dev inode pathname a7cb1000-a7cb2000 ---p 00000000 00:00 0 a7cb2000-a7eb2000 rw-p 00000000 00:00 0 a7eb2000-a7eb3000 ---p 00000000 00:00 0 -a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack:1001] +a7eb3000-a7ed5000 rw-p 00000000 00:00 0 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 @@ -388,7 +388,6 @@ is not associated with a file: [heap] = the heap of the program [stack] = the stack of the main process - [stack:1001] = the stack of the thread with tid 1001 [vdso] = the "virtual dynamic shared object", the kernel system call handler @@ -396,10 +395,8 @@ is not associated with a file: The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint of the individual tasks of a process. In this file you will see a mapping marked -as [stack] if that task sees it as a stack. This is a key difference from the -content of /proc/PID/maps, where you will see all mappings that are being used -as stack by all of those tasks. Hence, for the example above, the task-level -map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this: +as [stack] if that task sees it as a stack. Hence, for the example above, the +task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this: 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 87d40a72f6a1..551ecf09c8dd 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1496,6 +1496,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. could change it dynamically, usually by /sys/module/printk/parameters/ignore_loglevel. + ignore_rlimit_data + Ignore RLIMIT_DATA setting for data mappings, + print warning at first misuse. Can be changed via + /sys/module/kernel/parameters/ignore_rlimit_data. + ihash_entries= [KNL] Set number of hash buckets for inode cache. diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ceb44a095a27..73b36d7c7b0d 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -594,7 +594,7 @@ tcp_fastopen - INTEGER tcp_syn_retries - INTEGER Number of times initial SYNs for an active TCP connection attempt - will be retransmitted. Should not be higher than 255. Default value + will be retransmitted. Should not be higher than 127. Default value is 6, which corresponds to 63seconds till the last retransmission with the current initial RTO of 1second. With this the final timeout for an active TCP connection attempt will happen after 127seconds. diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index a93b414672a7..f886fbb1ad05 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -58,6 +58,8 @@ show up in /proc/sys/kernel: - panic_on_stackoverflow - panic_on_unrecovered_nmi - panic_on_warn +- perf_cpu_time_max_percent +- perf_event_paranoid - pid_max - powersave-nap [ PPC only ] - printk @@ -639,6 +641,17 @@ allowed to execute. ============================================================== +perf_event_paranoid: + +Controls use of the performance events system by unprivileged +users (without CAP_SYS_ADMIN). The default value is 1. + + -1: Allow use of (almost) all events by all users +>=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK +>=1: Disallow CPU event access by users without CAP_SYS_ADMIN +>=2: Disallow kernel profiling by users without CAP_SYS_ADMIN + +============================================================== pid_max: diff --git a/MAINTAINERS b/MAINTAINERS index 30aca4aa5467..24c5b9a29670 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -967,6 +967,8 @@ M: Rob Herring <robh@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-highbank/ +F: arch/arm/boot/dts/highbank.dts +F: arch/arm/boot/dts/ecx-*.dts* ARM/CAVIUM NETWORKS CNS3XXX MACHINE SUPPORT M: Krzysztof Halasa <khalasa@piap.pl> @@ -1042,6 +1044,7 @@ M: Barry Song <baohua@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://git.kernel.org/pub/scm/linux/kernel/git/baohua/linux.git S: Maintained +F: arch/arm/boot/dts/prima2* F: arch/arm/mach-prima2/ F: drivers/clk/sirf/ F: drivers/clocksource/timer-prima2.c @@ -1143,6 +1146,10 @@ W: http://www.hisilicon.com S: Supported T: git git://github.com/hisilicon/linux-hisi.git F: arch/arm/mach-hisi/ +F: arch/arm/boot/dts/hi3* +F: arch/arm/boot/dts/hip* +F: arch/arm/boot/dts/hisi* +F: arch/arm64/boot/dts/hisilicon/ ARM/HP JORNADA 7XX MACHINE SUPPORT M: Kristoffer Ericson <kristoffer.ericson@gmail.com> @@ -1219,6 +1226,7 @@ M: Santosh Shilimkar <ssantosh@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-keystone/ +F: arch/arm/boot/dts/k2* T: git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git ARM/TEXAS INSTRUMENT KEYSTONE CLOCK FRAMEWORK @@ -1287,6 +1295,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-berlin/ F: arch/arm/boot/dts/berlin* +F: arch/arm64/boot/dts/marvell/berlin* ARM/Marvell Dove/MV78xx0/Orion SOC support @@ -1425,6 +1434,7 @@ S: Maintained F: arch/arm/boot/dts/qcom-*.dts F: arch/arm/boot/dts/qcom-*.dtsi F: arch/arm/mach-qcom/ +F: arch/arm64/boot/dts/qcom/* F: drivers/soc/qcom/ F: drivers/tty/serial/msm_serial.h F: drivers/tty/serial/msm_serial.c @@ -1484,6 +1494,8 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/s3c* +F: arch/arm/boot/dts/s5p* +F: arch/arm/boot/dts/samsung* F: arch/arm/boot/dts/exynos* F: arch/arm64/boot/dts/exynos/ F: arch/arm/plat-samsung/ @@ -1563,6 +1575,7 @@ S: Maintained F: arch/arm/mach-socfpga/ F: arch/arm/boot/dts/socfpga* F: arch/arm/configs/socfpga_defconfig +F: arch/arm64/boot/dts/altera/ W: http://www.rocketboards.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git @@ -1716,7 +1729,7 @@ M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/vexpress* -F: arch/arm64/boot/dts/arm/vexpress* +F: arch/arm64/boot/dts/arm/ F: arch/arm/mach-vexpress/ F: */*/vexpress* F: */*/*/vexpress* @@ -2343,6 +2356,7 @@ F: arch/arm/mach-bcm/ F: arch/arm/boot/dts/bcm113* F: arch/arm/boot/dts/bcm216* F: arch/arm/boot/dts/bcm281* +F: arch/arm64/boot/dts/broadcom/ F: arch/arm/configs/bcm_defconfig F: drivers/mmc/host/sdhci-bcm-kona.c F: drivers/clocksource/bcm_kona_timer.c @@ -8818,6 +8832,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://github.com/hzhuang1/linux.git T: git git://github.com/rjarzmik/linux.git S: Maintained +F: arch/arm/boot/dts/pxa* F: arch/arm/mach-pxa/ F: drivers/dma/pxa* F: drivers/pcmcia/pxa2xx* @@ -8847,6 +8862,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://github.com/hzhuang1/linux.git T: git git://git.linaro.org/people/ycmiao/pxa-linux.git S: Maintained +F: arch/arm/boot/dts/mmp* F: arch/arm/mach-mmp/ PXA MMCI DRIVER @@ -10173,7 +10189,7 @@ F: drivers/net/ethernet/natsemi/sonic.* SONICS SILICON BACKPLANE DRIVER (SSB) M: Michael Buesch <m@bues.ch> -L: netdev@vger.kernel.org +L: linux-wireless@vger.kernel.org S: Maintained F: drivers/ssb/ F: include/linux/ssb/ @@ -10291,6 +10307,7 @@ L: spear-devel@list.st.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) W: http://www.st.com/spear S: Maintained +F: arch/arm/boot/dts/spear* F: arch/arm/mach-spear/ SPEAR CLOCK FRAMEWORK SUPPORT @@ -12133,7 +12150,7 @@ F: drivers/net/hamradio/*scc.c F: drivers/net/hamradio/z8530.h ZBUD COMPRESSED PAGE ALLOCATOR -M: Seth Jennings <sjennings@variantweb.net> +M: Seth Jennings <sjenning@redhat.com> L: linux-mm@kvack.org S: Maintained F: mm/zbud.c @@ -12188,7 +12205,7 @@ F: include/linux/zsmalloc.h F: Documentation/vm/zsmalloc.txt ZSWAP COMPRESSED SWAP CACHING -M: Seth Jennings <sjennings@variantweb.net> +M: Seth Jennings <sjenning@redhat.com> L: linux-mm@kvack.org S: Maintained F: mm/zswap.c diff --git a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi index da7b6e613257..933cba359918 100644 --- a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi @@ -23,9 +23,8 @@ soc0: soc@000000000 { }; }; - dsa: dsa@c7000000 { + dsaf0: dsa@c7000000 { compatible = "hisilicon,hns-dsaf-v1"; - dsa_name = "dsaf0"; mode = "6port-16rss"; interrupt-parent = <&mbigen_dsa>; @@ -127,7 +126,7 @@ soc0: soc@000000000 { eth0: ethernet@0{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <0>; local-mac-address = [00 00 00 01 00 58]; status = "disabled"; @@ -135,14 +134,14 @@ soc0: soc@000000000 { }; eth1: ethernet@1{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <1>; status = "disabled"; dma-coherent; }; eth2: ethernet@2{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <2>; local-mac-address = [00 00 00 01 00 5a]; status = "disabled"; @@ -150,7 +149,7 @@ soc0: soc@000000000 { }; eth3: ethernet@3{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <3>; local-mac-address = [00 00 00 01 00 5b]; status = "disabled"; @@ -158,7 +157,7 @@ soc0: soc@000000000 { }; eth4: ethernet@4{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <4>; local-mac-address = [00 00 00 01 00 5c]; status = "disabled"; @@ -166,7 +165,7 @@ soc0: soc@000000000 { }; eth5: ethernet@5{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <5>; local-mac-address = [00 00 00 01 00 5d]; status = "disabled"; @@ -174,7 +173,7 @@ soc0: soc@000000000 { }; eth6: ethernet@6{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <6>; local-mac-address = [00 00 00 01 00 5e]; status = "disabled"; @@ -182,7 +181,7 @@ soc0: soc@000000000 { }; eth7: ethernet@7{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <7>; local-mac-address = [00 00 00 01 00 5f]; status = "disabled"; diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 712b13047b41..3a33124e9112 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -157,7 +157,9 @@ ENTRY(chacha20_4block_xor_ssse3) # done with the slightly better performing SSSE3 byte shuffling, # 7/12-bit word rotation uses traditional shift+OR. - sub $0x40,%rsp + mov %rsp,%r11 + sub $0x80,%rsp + and $~63,%rsp # x0..15[0-3] = s0..3[0..3] movq 0x00(%rdi),%xmm1 @@ -620,6 +622,6 @@ ENTRY(chacha20_4block_xor_ssse3) pxor %xmm1,%xmm15 movdqu %xmm15,0xf0(%rsi) - add $0x40,%rsp + mov %r11,%rsp ret ENDPROC(chacha20_4block_xor_ssse3) diff --git a/block/ioctl.c b/block/ioctl.c index 77f5d17779d6..d8996bbd7f12 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -434,42 +434,6 @@ bool blkdev_dax_capable(struct block_device *bdev) return true; } - -static int blkdev_daxset(struct block_device *bdev, unsigned long argp) -{ - unsigned long arg; - int rc = 0; - - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - - if (get_user(arg, (int __user *)(argp))) - return -EFAULT; - arg = !!arg; - if (arg == !!(bdev->bd_inode->i_flags & S_DAX)) - return 0; - - if (arg) - arg = S_DAX; - - if (arg && !blkdev_dax_capable(bdev)) - return -ENOTTY; - - inode_lock(bdev->bd_inode); - if (bdev->bd_map_count == 0) - inode_set_flags(bdev->bd_inode, arg, S_DAX); - else - rc = -EBUSY; - inode_unlock(bdev->bd_inode); - return rc; -} -#else -static int blkdev_daxset(struct block_device *bdev, int arg) -{ - if (arg) - return -ENOTTY; - return 0; -} #endif static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, @@ -634,8 +598,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKTRACESETUP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); - case BLKDAXSET: - return blkdev_daxset(bdev, arg); case BLKDAXGET: return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX)); break; diff --git a/block/partition-generic.c b/block/partition-generic.c index 746935a5973c..fefd01b496a0 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -16,6 +16,7 @@ #include <linux/kmod.h> #include <linux/ctype.h> #include <linux/genhd.h> +#include <linux/dax.h> #include <linux/blktrace_api.h> #include "partitions/check.h" @@ -550,13 +551,24 @@ int invalidate_partitions(struct gendisk *disk, struct block_device *bdev) return 0; } -unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) +static struct page *read_pagecache_sector(struct block_device *bdev, sector_t n) { struct address_space *mapping = bdev->bd_inode->i_mapping; + + return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)), + NULL); +} + +unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) +{ struct page *page; - page = read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)), - NULL); + /* don't populate page cache for dax capable devices */ + if (IS_DAX(bdev->bd_inode)) + page = read_dax_sector(bdev, n); + else + page = read_pagecache_sector(bdev, n); + if (!IS_ERR(page)) { if (PageError(page)) goto fail; diff --git a/crypto/Kconfig b/crypto/Kconfig index 7240821137fd..3be07ad1d80d 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -472,11 +472,13 @@ config CRYPTO_CRCT10DIF_PCLMUL config CRYPTO_GHASH tristate "GHASH digest algorithm" select CRYPTO_GF128MUL + select CRYPTO_HASH help GHASH is message digest algorithm for GCM (Galois/Counter Mode). config CRYPTO_POLY1305 tristate "Poly1305 authenticator algorithm" + select CRYPTO_HASH help Poly1305 authenticator algorithm, RFC7539. diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 608a7562839d..68a5ceaa04c8 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -54,7 +54,8 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); if (!ctx->more) { - err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(crypto_ahash_init(&ctx->req), + &ctx->completion); if (err) goto unlock; } @@ -125,6 +126,7 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page, } else { if (!ctx->more) { err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(err, &ctx->completion); if (err) goto unlock; } diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c index 758acabf2d81..8f3056cd0399 100644 --- a/crypto/asymmetric_keys/pkcs7_parser.c +++ b/crypto/asymmetric_keys/pkcs7_parser.c @@ -547,9 +547,7 @@ int pkcs7_sig_note_set_of_authattrs(void *context, size_t hdrlen, struct pkcs7_signed_info *sinfo = ctx->sinfo; if (!test_bit(sinfo_has_content_type, &sinfo->aa_set) || - !test_bit(sinfo_has_message_digest, &sinfo->aa_set) || - (ctx->msg->data_type == OID_msIndirectData && - !test_bit(sinfo_has_ms_opus_info, &sinfo->aa_set))) { + !test_bit(sinfo_has_message_digest, &sinfo->aa_set)) { pr_warn("Missing required AuthAttr\n"); return -EBADMSG; } diff --git a/crypto/shash.c b/crypto/shash.c index 88a27de79848..359754591653 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -354,11 +354,10 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm) crt->final = shash_async_final; crt->finup = shash_async_finup; crt->digest = shash_async_digest; + crt->setkey = shash_async_setkey; + + crt->has_setkey = alg->setkey != shash_no_setkey; - if (alg->setkey) { - crt->setkey = shash_async_setkey; - crt->has_setkey = true; - } if (alg->export) crt->export = shash_async_export; if (alg->import) diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig index dbf22719462f..ff00331bff49 100644 --- a/drivers/char/hw_random/Kconfig +++ b/drivers/char/hw_random/Kconfig @@ -372,6 +372,7 @@ config HW_RANDOM_XGENE config HW_RANDOM_STM32 tristate "STMicroelectronics STM32 random number generator" depends on HW_RANDOM && (ARCH_STM32 || COMPILE_TEST) + depends on HAS_IOMEM help This driver provides kernel-side support for the Random Number Generator hardware found on STM32 microcontrollers. diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 9fda22e3387e..7fddd8696211 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -68,6 +68,7 @@ #include <linux/of_platform.h> #include <linux/of_address.h> #include <linux/of_irq.h> +#include <linux/acpi.h> #ifdef CONFIG_PARISC #include <asm/hardware.h> /* for register_parisc_driver() stuff */ @@ -2054,8 +2055,6 @@ static int hardcode_find_bmc(void) #ifdef CONFIG_ACPI -#include <linux/acpi.h> - /* * Once we get an ACPI failure, we don't try any more, because we go * through the tables sequentially. Once we don't find a table, there diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index 6dd3317ca365..3eb3f1279fb7 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -400,7 +400,7 @@ static int atmel_aes_hw_init(struct atmel_aes_dev *dd) { int err; - err = clk_prepare_enable(dd->iclk); + err = clk_enable(dd->iclk); if (err) return err; @@ -430,7 +430,7 @@ static int atmel_aes_hw_version_init(struct atmel_aes_dev *dd) dev_info(dd->dev, "version: 0x%x\n", dd->hw_version); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); return 0; } @@ -448,7 +448,7 @@ static inline bool atmel_aes_is_encrypt(const struct atmel_aes_dev *dd) static inline int atmel_aes_complete(struct atmel_aes_dev *dd, int err) { - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); dd->flags &= ~AES_FLAGS_BUSY; if (dd->is_async) @@ -2091,10 +2091,14 @@ static int atmel_aes_probe(struct platform_device *pdev) goto res_err; } - err = atmel_aes_hw_version_init(aes_dd); + err = clk_prepare(aes_dd->iclk); if (err) goto res_err; + err = atmel_aes_hw_version_init(aes_dd); + if (err) + goto iclk_unprepare; + atmel_aes_get_cap(aes_dd); err = atmel_aes_buff_init(aes_dd); @@ -2127,6 +2131,8 @@ err_algs: err_aes_dma: atmel_aes_buff_cleanup(aes_dd); err_aes_buff: +iclk_unprepare: + clk_unprepare(aes_dd->iclk); res_err: tasklet_kill(&aes_dd->done_task); tasklet_kill(&aes_dd->queue_task); @@ -2155,6 +2161,8 @@ static int atmel_aes_remove(struct platform_device *pdev) atmel_aes_dma_cleanup(aes_dd); atmel_aes_buff_cleanup(aes_dd); + clk_unprepare(aes_dd->iclk); + return 0; } diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 8abb4bc548cc..69d4a1326fee 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -534,8 +534,8 @@ static int caam_probe(struct platform_device *pdev) * long pointers in master configuration register */ clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH | - MCFGR_WDENABLE | (sizeof(dma_addr_t) == sizeof(u64) ? - MCFGR_LONG_PTR : 0)); + MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE | + (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0)); /* * Read the Compile Time paramters and SCFGR to determine diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 52f708bcf77f..d50c701b19d6 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -313,6 +313,10 @@ int of_hwspin_lock_get_id(struct device_node *np, int index) hwlock = radix_tree_deref_slot(slot); if (unlikely(!hwlock)) continue; + if (radix_tree_is_indirect_ptr(hwlock)) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (hwlock->bank->dev->of_node == args.np) { ret = 0; diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 9fe33fc3c2b9..cf34681af4f6 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1532,7 +1532,7 @@ int mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, /* no PVID with ranges, otherwise it's a bug */ if (pvid) - err = _mv88e6xxx_port_pvid_set(ds, port, vid); + err = _mv88e6xxx_port_pvid_set(ds, port, vlan->vid_end); unlock: mutex_unlock(&ps->smi_mutex); @@ -2163,7 +2163,8 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) * database, and allow every port to egress frames on all other ports. */ reg = BIT(ps->num_ports) - 1; /* all ports */ - ret = _mv88e6xxx_port_vlan_map_set(ds, port, reg & ~port); + reg &= ~BIT(port); /* except itself */ + ret = _mv88e6xxx_port_vlan_map_set(ds, port, reg); if (ret) goto abort; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index a4799c1fc7d4..5eb9b20c0eea 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -628,6 +628,7 @@ static int xgene_enet_register_irq(struct net_device *ndev) int ret; ring = pdata->rx_ring; + irq_set_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq, IRQF_SHARED, ring->irq_name, ring); if (ret) @@ -635,6 +636,7 @@ static int xgene_enet_register_irq(struct net_device *ndev) if (pdata->cq_cnt) { ring = pdata->tx_ring->cp_ring; + irq_set_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq, IRQF_SHARED, ring->irq_name, ring); if (ret) { @@ -649,15 +651,19 @@ static int xgene_enet_register_irq(struct net_device *ndev) static void xgene_enet_free_irq(struct net_device *ndev) { struct xgene_enet_pdata *pdata; + struct xgene_enet_desc_ring *ring; struct device *dev; pdata = netdev_priv(ndev); dev = ndev_to_dev(ndev); - devm_free_irq(dev, pdata->rx_ring->irq, pdata->rx_ring); + ring = pdata->rx_ring; + irq_clear_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); + devm_free_irq(dev, ring->irq, ring); if (pdata->cq_cnt) { - devm_free_irq(dev, pdata->tx_ring->cp_ring->irq, - pdata->tx_ring->cp_ring); + ring = pdata->tx_ring->cp_ring; + irq_clear_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); + devm_free_irq(dev, ring->irq, ring); } } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 70d5b62c125a..248dfc40a761 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -25,6 +25,7 @@ #include <linux/acpi.h> #include <linux/clk.h> #include <linux/efi.h> +#include <linux/irq.h> #include <linux/io.h> #include <linux/of_platform.h> #include <linux/of_net.h> diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index ecc4a334c507..f71ab2647a3b 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -302,7 +302,7 @@ static int nb8800_poll(struct napi_struct *napi, int budget) nb8800_tx_done(dev); again: - while (work < budget) { + do { struct nb8800_rx_buf *rxb; unsigned int len; @@ -330,7 +330,7 @@ again: rxd->report = 0; last = next; work++; - } + } while (work < budget); if (work) { priv->rx_descs[last].desc.config |= DESC_EOC; diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 8550df189ceb..19f7cd02e085 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -151,8 +151,11 @@ config BNX2X_VXLAN config BGMAC tristate "BCMA bus GBit core support" - depends on BCMA_HOST_SOC && HAS_DMA && (BCM47XX || ARCH_BCM_5301X) + depends on BCMA && BCMA_HOST_SOC + depends on HAS_DMA + depends on BCM47XX || ARCH_BCM_5301X || COMPILE_TEST select PHYLIB + select FIXED_PHY ---help--- This driver supports GBit MAC and BCM4706 GBit MAC cores on BCMA bus. They can be found on BCM47xx SoCs and provide gigabit ethernet. diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index df835f5e46d8..5dc89e527e7d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1490,10 +1490,11 @@ static void bnxt_free_tx_skbs(struct bnxt *bp) last = tx_buf->nr_frags; j += 2; - for (k = 0; k < last; k++, j = NEXT_TX(j)) { + for (k = 0; k < last; k++, j++) { + int ring_idx = j & bp->tx_ring_mask; skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; - tx_buf = &txr->tx_buf_ring[j]; + tx_buf = &txr->tx_buf_ring[ring_idx]; dma_unmap_page( &pdev->dev, dma_unmap_addr(tx_buf, mapping), @@ -3406,7 +3407,7 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp, struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr; u16 error_code; - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, -1, -1); + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1); req.ring_type = ring_type; req.ring_id = cpu_to_le16(ring->fw_ring_id); @@ -4819,8 +4820,6 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->multicast += le64_to_cpu(hw_stats->rx_mcast_pkts); - stats->rx_dropped += le64_to_cpu(hw_stats->rx_drop_pkts); - stats->tx_dropped += le64_to_cpu(hw_stats->tx_drop_pkts); } diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 0d775964b060..457c3bc8cfff 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -401,7 +401,7 @@ int bcmgenet_mii_probe(struct net_device *dev) * Ethernet MAC ISRs */ if (priv->internal_phy) - priv->mii_bus->irq[phydev->mdio.addr] = PHY_IGNORE_INTERRUPT; + priv->phydev->irq = PHY_IGNORE_INTERRUPT; return 0; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 9293675df7ba..49eea8981332 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -12016,7 +12016,7 @@ static int tg3_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, int ret; u32 offset, len, b_offset, odd_len; u8 *buf; - __be32 start, end; + __be32 start = 0, end; if (tg3_flag(tp, NO_NVRAM) || eeprom->magic != TG3_EEPROM_MAGIC) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 9d9984a87d42..50c94104f19c 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -2823,7 +2823,7 @@ static int macb_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct device_node *phy_node; const struct macb_config *macb_config = NULL; - struct clk *pclk, *hclk, *tx_clk; + struct clk *pclk, *hclk = NULL, *tx_clk = NULL; unsigned int queue_mask, num_queues; struct macb_platform_data *pdata; bool native_io; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index b89504405b72..872765527081 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1526,7 +1526,6 @@ static int liquidio_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; - u32 remainder; unsigned long flags; struct lio *lio = container_of(ptp, struct lio, ptp_info); struct octeon_device *oct = (struct octeon_device *)lio->oct_dev; @@ -1536,8 +1535,7 @@ static int liquidio_ptp_gettime(struct ptp_clock_info *ptp, ns += lio->ptp_adjust; spin_unlock_irqrestore(&lio->ptp_lock, flags); - ts->tv_sec = div_u64_rem(ns, 1000000000ULL, &remainder); - ts->tv_nsec = remainder; + *ts = ns_to_timespec64(ns); return 0; } diff --git a/drivers/net/ethernet/ezchip/Kconfig b/drivers/net/ethernet/ezchip/Kconfig index 48ecbc8aaaea..b423ad380b6a 100644 --- a/drivers/net/ethernet/ezchip/Kconfig +++ b/drivers/net/ethernet/ezchip/Kconfig @@ -18,6 +18,7 @@ if NET_VENDOR_EZCHIP config EZCHIP_NPS_MANAGEMENT_ENET tristate "EZchip NPS management enet support" depends on OF_IRQ && OF_NET + depends on HAS_IOMEM ---help--- Simple LAN device for debug or management purposes. Device supports interrupts for RX and TX(completion). diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile index 4097c58d17a7..cbe21dc7e37e 100644 --- a/drivers/net/ethernet/freescale/Makefile +++ b/drivers/net/ethernet/freescale/Makefile @@ -4,6 +4,9 @@ obj-$(CONFIG_FEC) += fec.o fec-objs :=fec_main.o fec_ptp.o +CFLAGS_fec_main.o := -D__CHECK_ENDIAN__ +CFLAGS_fec_ptp.o := -D__CHECK_ENDIAN__ + obj-$(CONFIG_FEC_MPC52xx) += fec_mpc52xx.o ifeq ($(CONFIG_FEC_MPC52xx_MDIO),y) obj-$(CONFIG_FEC_MPC52xx) += fec_mpc52xx_phy.o diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 99d33e2d35e6..2106d72c91dc 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -19,8 +19,7 @@ #include <linux/timecounter.h> #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || \ - defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28) + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) /* * Just figures, Motorola would have to change the offsets for * registers in the same peripheral device on different models @@ -190,28 +189,45 @@ /* * Define the buffer descriptor structure. + * + * Evidently, ARM SoCs have the FEC block generated in a + * little endian mode so adjust endianness accordingly. */ -#if defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28) +#if defined(CONFIG_ARM) +#define fec32_to_cpu le32_to_cpu +#define fec16_to_cpu le16_to_cpu +#define cpu_to_fec32 cpu_to_le32 +#define cpu_to_fec16 cpu_to_le16 +#define __fec32 __le32 +#define __fec16 __le16 + struct bufdesc { - unsigned short cbd_datlen; /* Data length */ - unsigned short cbd_sc; /* Control and status info */ - unsigned long cbd_bufaddr; /* Buffer address */ + __fec16 cbd_datlen; /* Data length */ + __fec16 cbd_sc; /* Control and status info */ + __fec32 cbd_bufaddr; /* Buffer address */ }; #else +#define fec32_to_cpu be32_to_cpu +#define fec16_to_cpu be16_to_cpu +#define cpu_to_fec32 cpu_to_be32 +#define cpu_to_fec16 cpu_to_be16 +#define __fec32 __be32 +#define __fec16 __be16 + struct bufdesc { - unsigned short cbd_sc; /* Control and status info */ - unsigned short cbd_datlen; /* Data length */ - unsigned long cbd_bufaddr; /* Buffer address */ + __fec16 cbd_sc; /* Control and status info */ + __fec16 cbd_datlen; /* Data length */ + __fec32 cbd_bufaddr; /* Buffer address */ }; #endif struct bufdesc_ex { struct bufdesc desc; - unsigned long cbd_esc; - unsigned long cbd_prot; - unsigned long cbd_bdu; - unsigned long ts; - unsigned short res0[4]; + __fec32 cbd_esc; + __fec32 cbd_prot; + __fec32 cbd_bdu; + __fec32 ts; + __fec16 res0[4]; }; /* diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 502da6f48f95..41c81f6ec630 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -332,11 +332,13 @@ static void fec_dump(struct net_device *ndev) bdp = txq->tx_bd_base; do { - pr_info("%3u %c%c 0x%04x 0x%08lx %4u %p\n", + pr_info("%3u %c%c 0x%04x 0x%08x %4u %p\n", index, bdp == txq->cur_tx ? 'S' : ' ', bdp == txq->dirty_tx ? 'H' : ' ', - bdp->cbd_sc, bdp->cbd_bufaddr, bdp->cbd_datlen, + fec16_to_cpu(bdp->cbd_sc), + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), txq->tx_skbuff[index]); bdp = fec_enet_get_nextdesc(bdp, fep, 0); index++; @@ -389,7 +391,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, bdp = fec_enet_get_nextdesc(bdp, fep, queue); ebdp = (struct bufdesc_ex *)bdp; - status = bdp->cbd_sc; + status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; status |= (BD_ENET_TX_TC | BD_ENET_TX_READY); frag_len = skb_shinfo(skb)->frags[frag].size; @@ -411,7 +413,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, if (skb->ip_summed == CHECKSUM_PARTIAL) estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS; ebdp->cbd_bdu = 0; - ebdp->cbd_esc = estatus; + ebdp->cbd_esc = cpu_to_fec32(estatus); } bufaddr = page_address(this_frag->page.p) + this_frag->page_offset; @@ -435,9 +437,9 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, goto dma_mapping_error; } - bdp->cbd_bufaddr = addr; - bdp->cbd_datlen = frag_len; - bdp->cbd_sc = status; + bdp->cbd_bufaddr = cpu_to_fec32(addr); + bdp->cbd_datlen = cpu_to_fec16(frag_len); + bdp->cbd_sc = cpu_to_fec16(status); } return bdp; @@ -445,8 +447,8 @@ dma_mapping_error: bdp = txq->cur_tx; for (i = 0; i < frag; i++) { bdp = fec_enet_get_nextdesc(bdp, fep, queue); - dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, - bdp->cbd_datlen, DMA_TO_DEVICE); + dma_unmap_single(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), DMA_TO_DEVICE); } return ERR_PTR(-ENOMEM); } @@ -483,7 +485,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq, /* Fill in a Tx ring entry */ bdp = txq->cur_tx; last_bdp = bdp; - status = bdp->cbd_sc; + status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; /* Set buffer length and buffer pointer */ @@ -539,21 +541,21 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq, estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS; ebdp->cbd_bdu = 0; - ebdp->cbd_esc = estatus; + ebdp->cbd_esc = cpu_to_fec32(estatus); } index = fec_enet_get_bd_index(txq->tx_bd_base, last_bdp, fep); /* Save skb pointer */ txq->tx_skbuff[index] = skb; - bdp->cbd_datlen = buflen; - bdp->cbd_bufaddr = addr; + bdp->cbd_datlen = cpu_to_fec16(buflen); + bdp->cbd_bufaddr = cpu_to_fec32(addr); /* Send it on its way. Tell FEC it's ready, interrupt when done, * it's the last BD of the frame, and to put the CRC on the end. */ status |= (BD_ENET_TX_READY | BD_ENET_TX_TC); - bdp->cbd_sc = status; + bdp->cbd_sc = cpu_to_fec16(status); /* If this was the last BD in the ring, start at the beginning again. */ bdp = fec_enet_get_nextdesc(last_bdp, fep, queue); @@ -585,7 +587,7 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, unsigned int estatus = 0; dma_addr_t addr; - status = bdp->cbd_sc; + status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; status |= (BD_ENET_TX_TC | BD_ENET_TX_READY); @@ -607,8 +609,8 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, return NETDEV_TX_BUSY; } - bdp->cbd_datlen = size; - bdp->cbd_bufaddr = addr; + bdp->cbd_datlen = cpu_to_fec16(size); + bdp->cbd_bufaddr = cpu_to_fec32(addr); if (fep->bufdesc_ex) { if (fep->quirks & FEC_QUIRK_HAS_AVB) @@ -616,7 +618,7 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_PARTIAL) estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS; ebdp->cbd_bdu = 0; - ebdp->cbd_esc = estatus; + ebdp->cbd_esc = cpu_to_fec32(estatus); } /* Handle the last BD specially */ @@ -625,10 +627,10 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, if (is_last) { status |= BD_ENET_TX_INTR; if (fep->bufdesc_ex) - ebdp->cbd_esc |= BD_ENET_TX_INT; + ebdp->cbd_esc |= cpu_to_fec32(BD_ENET_TX_INT); } - bdp->cbd_sc = status; + bdp->cbd_sc = cpu_to_fec16(status); return 0; } @@ -647,7 +649,7 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq, unsigned short status; unsigned int estatus = 0; - status = bdp->cbd_sc; + status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; status |= (BD_ENET_TX_TC | BD_ENET_TX_READY); @@ -671,8 +673,8 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq, } } - bdp->cbd_bufaddr = dmabuf; - bdp->cbd_datlen = hdr_len; + bdp->cbd_bufaddr = cpu_to_fec32(dmabuf); + bdp->cbd_datlen = cpu_to_fec16(hdr_len); if (fep->bufdesc_ex) { if (fep->quirks & FEC_QUIRK_HAS_AVB) @@ -680,10 +682,10 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq, if (skb->ip_summed == CHECKSUM_PARTIAL) estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS; ebdp->cbd_bdu = 0; - ebdp->cbd_esc = estatus; + ebdp->cbd_esc = cpu_to_fec32(estatus); } - bdp->cbd_sc = status; + bdp->cbd_sc = cpu_to_fec16(status); return 0; } @@ -823,15 +825,15 @@ static void fec_enet_bd_init(struct net_device *dev) /* Initialize the BD for every fragment in the page. */ if (bdp->cbd_bufaddr) - bdp->cbd_sc = BD_ENET_RX_EMPTY; + bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY); else - bdp->cbd_sc = 0; + bdp->cbd_sc = cpu_to_fec16(0); bdp = fec_enet_get_nextdesc(bdp, fep, q); } /* Set the last buffer to wrap */ bdp = fec_enet_get_prevdesc(bdp, fep, q); - bdp->cbd_sc |= BD_SC_WRAP; + bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); rxq->cur_rx = rxq->rx_bd_base; } @@ -844,18 +846,18 @@ static void fec_enet_bd_init(struct net_device *dev) for (i = 0; i < txq->tx_ring_size; i++) { /* Initialize the BD for every fragment in the page. */ - bdp->cbd_sc = 0; + bdp->cbd_sc = cpu_to_fec16(0); if (txq->tx_skbuff[i]) { dev_kfree_skb_any(txq->tx_skbuff[i]); txq->tx_skbuff[i] = NULL; } - bdp->cbd_bufaddr = 0; + bdp->cbd_bufaddr = cpu_to_fec32(0); bdp = fec_enet_get_nextdesc(bdp, fep, q); } /* Set the last buffer to wrap */ bdp = fec_enet_get_prevdesc(bdp, fep, q); - bdp->cbd_sc |= BD_SC_WRAP; + bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); txq->dirty_tx = bdp; } } @@ -947,8 +949,10 @@ fec_restart(struct net_device *ndev) */ if (fep->quirks & FEC_QUIRK_ENET_MAC) { memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN); - writel(cpu_to_be32(temp_mac[0]), fep->hwp + FEC_ADDR_LOW); - writel(cpu_to_be32(temp_mac[1]), fep->hwp + FEC_ADDR_HIGH); + writel((__force u32)cpu_to_be32(temp_mac[0]), + fep->hwp + FEC_ADDR_LOW); + writel((__force u32)cpu_to_be32(temp_mac[1]), + fep->hwp + FEC_ADDR_HIGH); } /* Clear any outstanding interrupt. */ @@ -1222,7 +1226,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) while (bdp != READ_ONCE(txq->cur_tx)) { /* Order the load of cur_tx and cbd_sc */ rmb(); - status = READ_ONCE(bdp->cbd_sc); + status = fec16_to_cpu(READ_ONCE(bdp->cbd_sc)); if (status & BD_ENET_TX_READY) break; @@ -1230,10 +1234,12 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) skb = txq->tx_skbuff[index]; txq->tx_skbuff[index] = NULL; - if (!IS_TSO_HEADER(txq, bdp->cbd_bufaddr)) - dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, - bdp->cbd_datlen, DMA_TO_DEVICE); - bdp->cbd_bufaddr = 0; + if (!IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr))) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), + DMA_TO_DEVICE); + bdp->cbd_bufaddr = cpu_to_fec32(0); if (!skb) { bdp = fec_enet_get_nextdesc(bdp, fep, queue_id); continue; @@ -1264,7 +1270,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) struct skb_shared_hwtstamps shhwtstamps; struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - fec_enet_hwtstamp(fep, ebdp->ts, &shhwtstamps); + fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps); skb_tstamp_tx(skb, &shhwtstamps); } @@ -1324,10 +1330,8 @@ fec_enet_new_rxbdp(struct net_device *ndev, struct bufdesc *bdp, struct sk_buff if (off) skb_reserve(skb, fep->rx_align + 1 - off); - bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, skb->data, - FEC_ENET_RX_FRSIZE - fep->rx_align, - DMA_FROM_DEVICE); - if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) { + bdp->cbd_bufaddr = cpu_to_fec32(dma_map_single(&fep->pdev->dev, skb->data, FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE)); + if (dma_mapping_error(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr))) { if (net_ratelimit()) netdev_err(ndev, "Rx DMA memory map failed\n"); return -ENOMEM; @@ -1349,7 +1353,8 @@ static bool fec_enet_copybreak(struct net_device *ndev, struct sk_buff **skb, if (!new_skb) return false; - dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr, + dma_sync_single_for_cpu(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE); if (!swap) @@ -1396,7 +1401,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) */ bdp = rxq->cur_rx; - while (!((status = bdp->cbd_sc) & BD_ENET_RX_EMPTY)) { + while (!((status = fec16_to_cpu(bdp->cbd_sc)) & BD_ENET_RX_EMPTY)) { if (pkt_received >= budget) break; @@ -1438,7 +1443,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) /* Process the incoming frame. */ ndev->stats.rx_packets++; - pkt_len = bdp->cbd_datlen; + pkt_len = fec16_to_cpu(bdp->cbd_datlen); ndev->stats.rx_bytes += pkt_len; index = fec_enet_get_bd_index(rxq->rx_bd_base, bdp, fep); @@ -1456,7 +1461,8 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) ndev->stats.rx_dropped++; goto rx_processing_done; } - dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE); } @@ -1475,7 +1481,8 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) /* If this is a VLAN packet remove the VLAN Tag */ vlan_packet_rcvd = false; if ((ndev->features & NETIF_F_HW_VLAN_CTAG_RX) && - fep->bufdesc_ex && (ebdp->cbd_esc & BD_ENET_RX_VLAN)) { + fep->bufdesc_ex && + (ebdp->cbd_esc & cpu_to_fec32(BD_ENET_RX_VLAN))) { /* Push and remove the vlan tag */ struct vlan_hdr *vlan_header = (struct vlan_hdr *) (data + ETH_HLEN); @@ -1491,12 +1498,12 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) /* Get receive timestamp from the skb */ if (fep->hwts_rx_en && fep->bufdesc_ex) - fec_enet_hwtstamp(fep, ebdp->ts, + fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), skb_hwtstamps(skb)); if (fep->bufdesc_ex && (fep->csum_flags & FLAG_RX_CSUM_ENABLED)) { - if (!(ebdp->cbd_esc & FLAG_RX_CSUM_ERROR)) { + if (!(ebdp->cbd_esc & cpu_to_fec32(FLAG_RX_CSUM_ERROR))) { /* don't check it */ skb->ip_summed = CHECKSUM_UNNECESSARY; } else { @@ -1513,7 +1520,8 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) napi_gro_receive(&fep->napi, skb); if (is_copybreak) { - dma_sync_single_for_device(&fep->pdev->dev, bdp->cbd_bufaddr, + dma_sync_single_for_device(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE); } else { @@ -1527,12 +1535,12 @@ rx_processing_done: /* Mark the buffer empty */ status |= BD_ENET_RX_EMPTY; - bdp->cbd_sc = status; + bdp->cbd_sc = cpu_to_fec16(status); if (fep->bufdesc_ex) { struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - ebdp->cbd_esc = BD_ENET_RX_INT; + ebdp->cbd_esc = cpu_to_fec32(BD_ENET_RX_INT); ebdp->cbd_prot = 0; ebdp->cbd_bdu = 0; } @@ -2145,8 +2153,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev) /* List of registers that can be safety be read to dump them with ethtool */ #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || \ - defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28) + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) static u32 fec_enet_register_offset[] = { FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL, @@ -2662,7 +2669,7 @@ static void fec_enet_free_buffers(struct net_device *ndev) rxq->rx_skbuff[i] = NULL; if (skb) { dma_unmap_single(&fep->pdev->dev, - bdp->cbd_bufaddr, + fec32_to_cpu(bdp->cbd_bufaddr), FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE); dev_kfree_skb(skb); @@ -2777,11 +2784,11 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue) } rxq->rx_skbuff[i] = skb; - bdp->cbd_sc = BD_ENET_RX_EMPTY; + bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY); if (fep->bufdesc_ex) { struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - ebdp->cbd_esc = BD_ENET_RX_INT; + ebdp->cbd_esc = cpu_to_fec32(BD_ENET_RX_INT); } bdp = fec_enet_get_nextdesc(bdp, fep, queue); @@ -2789,7 +2796,7 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue) /* Set the last buffer to wrap. */ bdp = fec_enet_get_prevdesc(bdp, fep, queue); - bdp->cbd_sc |= BD_SC_WRAP; + bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); return 0; err_alloc: @@ -2812,12 +2819,12 @@ fec_enet_alloc_txq_buffers(struct net_device *ndev, unsigned int queue) if (!txq->tx_bounce[i]) goto err_alloc; - bdp->cbd_sc = 0; - bdp->cbd_bufaddr = 0; + bdp->cbd_sc = cpu_to_fec16(0); + bdp->cbd_bufaddr = cpu_to_fec32(0); if (fep->bufdesc_ex) { struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - ebdp->cbd_esc = BD_ENET_TX_INT; + ebdp->cbd_esc = cpu_to_fec32(BD_ENET_TX_INT); } bdp = fec_enet_get_nextdesc(bdp, fep, queue); @@ -2825,7 +2832,7 @@ fec_enet_alloc_txq_buffers(struct net_device *ndev, unsigned int queue) /* Set the last buffer to wrap. */ bdp = fec_enet_get_prevdesc(bdp, fep, queue); - bdp->cbd_sc |= BD_SC_WRAP; + bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); return 0; diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c index 52e0091b4fb2..1ba359f17ec6 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c @@ -552,7 +552,7 @@ static void tx_restart(struct net_device *dev) cbd_t __iomem *prev_bd; cbd_t __iomem *last_tx_bd; - last_tx_bd = fep->tx_bd_base + ((fpi->tx_ring - 1) * sizeof(cbd_t)); + last_tx_bd = fep->tx_bd_base + (fpi->tx_ring - 1); /* get the current bd held in TBPTR and scan back from this point */ recheck_bd = curr_tbptr = (cbd_t __iomem *) diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index b3645297477e..3bfe36f9405b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -95,21 +95,17 @@ static struct hnae_buf_ops hnae_bops = { static int __ae_match(struct device *dev, const void *data) { struct hnae_ae_dev *hdev = cls_to_ae_dev(dev); - const char *ae_id = data; - if (!strncmp(ae_id, hdev->name, AE_NAME_SIZE)) - return 1; - - return 0; + return hdev->dev->of_node == data; } -static struct hnae_ae_dev *find_ae(const char *ae_id) +static struct hnae_ae_dev *find_ae(const struct device_node *ae_node) { struct device *dev; - WARN_ON(!ae_id); + WARN_ON(!ae_node); - dev = class_find_device(hnae_class, NULL, ae_id, __ae_match); + dev = class_find_device(hnae_class, NULL, ae_node, __ae_match); return dev ? cls_to_ae_dev(dev) : NULL; } @@ -316,7 +312,8 @@ EXPORT_SYMBOL(hnae_reinit_handle); * return handle ptr or ERR_PTR */ struct hnae_handle *hnae_get_handle(struct device *owner_dev, - const char *ae_id, u32 port_id, + const struct device_node *ae_node, + u32 port_id, struct hnae_buf_ops *bops) { struct hnae_ae_dev *dev; @@ -324,7 +321,7 @@ struct hnae_handle *hnae_get_handle(struct device *owner_dev, int i, j; int ret; - dev = find_ae(ae_id); + dev = find_ae(ae_node); if (!dev) return ERR_PTR(-ENODEV); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index 6ca94dc3dda3..1cbcb9fa3fb5 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -524,8 +524,11 @@ struct hnae_handle { #define ring_to_dev(ring) ((ring)->q->dev->dev) -struct hnae_handle *hnae_get_handle(struct device *owner_dev, const char *ae_id, - u32 port_id, struct hnae_buf_ops *bops); +struct hnae_handle *hnae_get_handle(struct device *owner_dev, + const struct device_node *ae_node, + u32 port_id, + struct hnae_buf_ops *bops); + void hnae_put_handle(struct hnae_handle *handle); int hnae_ae_register(struct hnae_ae_dev *dev, struct module *owner); void hnae_ae_unregister(struct hnae_ae_dev *dev); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index 522b264866b4..a0070d0e740d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -847,6 +847,7 @@ static struct hnae_ae_ops hns_dsaf_ops = { int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev) { struct hnae_ae_dev *ae_dev = &dsaf_dev->ae_dev; + static atomic_t id = ATOMIC_INIT(-1); switch (dsaf_dev->dsaf_ver) { case AE_VERSION_1: @@ -858,6 +859,9 @@ int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev) default: break; } + + snprintf(ae_dev->name, AE_NAME_SIZE, "%s%d", DSAF_DEVICE_NAME, + (int)atomic_inc_return(&id)); ae_dev->ops = &hns_dsaf_ops; ae_dev->dev = dsaf_dev->dev; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 1c33bd06bd5c..9439f04962e1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -35,7 +35,7 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev) int ret, i; u32 desc_num; u32 buf_size; - const char *name, *mode_str; + const char *mode_str; struct device_node *np = dsaf_dev->dev->of_node; if (of_device_is_compatible(np, "hisilicon,hns-dsaf-v1")) @@ -43,14 +43,6 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev) else dsaf_dev->dsaf_ver = AE_VERSION_2; - ret = of_property_read_string(np, "dsa_name", &name); - if (ret) { - dev_err(dsaf_dev->dev, "get dsaf name fail, ret=%d!\n", ret); - return ret; - } - strncpy(dsaf_dev->ae_dev.name, name, AE_NAME_SIZE); - dsaf_dev->ae_dev.name[AE_NAME_SIZE - 1] = '\0'; - ret = of_property_read_string(np, "mode", &mode_str); if (ret) { dev_err(dsaf_dev->dev, "get dsaf mode fail, ret=%d!\n", ret); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 31c312f9826e..40205b910f80 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -18,6 +18,7 @@ struct hns_mac_cb; #define DSAF_DRV_NAME "hns_dsaf" #define DSAF_MOD_VERSION "v1.0" +#define DSAF_DEVICE_NAME "dsaf" #define HNS_DSAF_DEBUG_NW_REG_OFFSET 0x100000 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 0e30846a24f8..3f77ff77abbc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1802,7 +1802,7 @@ static int hns_nic_try_get_ae(struct net_device *ndev) int ret; h = hnae_get_handle(&priv->netdev->dev, - priv->ae_name, priv->port_id, NULL); + priv->ae_node, priv->port_id, NULL); if (IS_ERR_OR_NULL(h)) { ret = PTR_ERR(h); dev_dbg(priv->dev, "has not handle, register notifier!\n"); @@ -1880,13 +1880,16 @@ static int hns_nic_dev_probe(struct platform_device *pdev) else priv->enet_ver = AE_VERSION_2; - ret = of_property_read_string(node, "ae-name", &priv->ae_name); - if (ret) - goto out_read_string_fail; + priv->ae_node = (void *)of_parse_phandle(node, "ae-handle", 0); + if (IS_ERR_OR_NULL(priv->ae_node)) { + ret = PTR_ERR(priv->ae_node); + dev_err(dev, "not find ae-handle\n"); + goto out_read_prop_fail; + } ret = of_property_read_u32(node, "port-id", &priv->port_id); if (ret) - goto out_read_string_fail; + goto out_read_prop_fail; hns_init_mac_addr(ndev); @@ -1945,7 +1948,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev) out_notify_fail: (void)cancel_work_sync(&priv->service_task); -out_read_string_fail: +out_read_prop_fail: free_netdev(ndev); return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h index 4b75270f014e..c68ab3d34fc2 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h @@ -51,7 +51,7 @@ struct hns_nic_ops { }; struct hns_nic_priv { - const char *ae_name; + const struct device_node *ae_node; u32 enet_ver; u32 port_id; int phy_mode; diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c index 1d5c3e16d8f4..3daf2d4a7ca0 100644 --- a/drivers/net/ethernet/hp/hp100.c +++ b/drivers/net/ethernet/hp/hp100.c @@ -194,7 +194,6 @@ static const char *hp100_isa_tbl[] = { }; #endif -#ifdef CONFIG_EISA static struct eisa_device_id hp100_eisa_tbl[] = { { "HWPF180" }, /* HP J2577 rev A */ { "HWP1920" }, /* HP 27248B */ @@ -205,9 +204,7 @@ static struct eisa_device_id hp100_eisa_tbl[] = { { "" } /* Mandatory final entry ! */ }; MODULE_DEVICE_TABLE(eisa, hp100_eisa_tbl); -#endif -#ifdef CONFIG_PCI static const struct pci_device_id hp100_pci_tbl[] = { {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_J2585A, PCI_ANY_ID, PCI_ANY_ID,}, {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_J2585B, PCI_ANY_ID, PCI_ANY_ID,}, @@ -219,7 +216,6 @@ static const struct pci_device_id hp100_pci_tbl[] = { {} /* Terminating entry */ }; MODULE_DEVICE_TABLE(pci, hp100_pci_tbl); -#endif static int hp100_rx_ratio = HP100_DEFAULT_RX_RATIO; static int hp100_priority_tx = HP100_DEFAULT_PRIORITY_TX; @@ -2842,7 +2838,6 @@ static void cleanup_dev(struct net_device *d) free_netdev(d); } -#ifdef CONFIG_EISA static int hp100_eisa_probe(struct device *gendev) { struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private)); @@ -2884,9 +2879,7 @@ static struct eisa_driver hp100_eisa_driver = { .remove = hp100_eisa_remove, } }; -#endif -#ifdef CONFIG_PCI static int hp100_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -2955,7 +2948,6 @@ static struct pci_driver hp100_pci_driver = { .probe = hp100_pci_probe, .remove = hp100_pci_remove, }; -#endif /* * module section @@ -3032,23 +3024,17 @@ static int __init hp100_module_init(void) err = hp100_isa_init(); if (err && err != -ENODEV) goto out; -#ifdef CONFIG_EISA err = eisa_driver_register(&hp100_eisa_driver); if (err && err != -ENODEV) goto out2; -#endif -#ifdef CONFIG_PCI err = pci_register_driver(&hp100_pci_driver); if (err && err != -ENODEV) goto out3; -#endif out: return err; out3: -#ifdef CONFIG_EISA eisa_driver_unregister (&hp100_eisa_driver); out2: -#endif hp100_isa_cleanup(); goto out; } @@ -3057,12 +3043,8 @@ static int __init hp100_module_init(void) static void __exit hp100_module_exit(void) { hp100_isa_cleanup(); -#ifdef CONFIG_EISA eisa_driver_unregister (&hp100_eisa_driver); -#endif -#ifdef CONFIG_PCI pci_unregister_driver (&hp100_pci_driver); -#endif } module_init(hp100_module_init) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index bb4612c159fd..8f3b53e0dc46 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7117,9 +7117,7 @@ static void i40e_service_task(struct work_struct *work) i40e_watchdog_subtask(pf); i40e_fdir_reinit_subtask(pf); i40e_sync_filters_subtask(pf); -#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE) i40e_sync_udp_filters_subtask(pf); -#endif i40e_clean_adminq_subtask(pf); i40e_service_event_complete(pf); @@ -8515,6 +8513,8 @@ static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port) } #endif + +#if IS_ENABLED(CONFIG_VXLAN) /** * i40e_add_vxlan_port - Get notifications about VXLAN ports that come up * @netdev: This physical port's netdev @@ -8524,7 +8524,6 @@ static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port) static void i40e_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { -#if IS_ENABLED(CONFIG_VXLAN) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8557,7 +8556,6 @@ static void i40e_add_vxlan_port(struct net_device *netdev, pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN; pf->pending_udp_bitmap |= BIT_ULL(next_idx); pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; -#endif } /** @@ -8569,7 +8567,6 @@ static void i40e_add_vxlan_port(struct net_device *netdev, static void i40e_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { -#if IS_ENABLED(CONFIG_VXLAN) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8592,9 +8589,10 @@ static void i40e_del_vxlan_port(struct net_device *netdev, netdev_warn(netdev, "vxlan port %d was not found, not deleting\n", ntohs(port)); } -#endif } +#endif +#if IS_ENABLED(CONFIG_GENEVE) /** * i40e_add_geneve_port - Get notifications about GENEVE ports that come up * @netdev: This physical port's netdev @@ -8604,7 +8602,6 @@ static void i40e_del_vxlan_port(struct net_device *netdev, static void i40e_add_geneve_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { -#if IS_ENABLED(CONFIG_GENEVE) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8639,7 +8636,6 @@ static void i40e_add_geneve_port(struct net_device *netdev, pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; dev_info(&pf->pdev->dev, "adding geneve port %d\n", ntohs(port)); -#endif } /** @@ -8651,7 +8647,6 @@ static void i40e_add_geneve_port(struct net_device *netdev, static void i40e_del_geneve_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { -#if IS_ENABLED(CONFIG_GENEVE) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8677,8 +8672,8 @@ static void i40e_del_geneve_port(struct net_device *netdev, netdev_warn(netdev, "geneve port %d was not found, not deleting\n", ntohs(port)); } -#endif } +#endif static int i40e_get_phys_port_id(struct net_device *netdev, struct netdev_phys_item_id *ppid) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 720516b0e8ee..47bd8b3145a7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2313,8 +2313,8 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, struct iphdr *this_ip_hdr; u32 network_hdr_len; u8 l4_hdr = 0; - struct udphdr *oudph; - struct iphdr *oiph; + struct udphdr *oudph = NULL; + struct iphdr *oiph = NULL; u32 l4_tunnel = 0; if (skb->encapsulation) { diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index a0c03834a2f7..55831188bc32 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -762,10 +762,10 @@ txq_put_data_tso(struct net_device *dev, struct tx_queue *txq, if (length <= 8 && (uintptr_t)data & 0x7) { /* Copy unaligned small data fragment to TSO header data area */ - memcpy(txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE, + memcpy(txq->tso_hdrs + tx_index * TSO_HEADER_SIZE, data, length); desc->buf_ptr = txq->tso_hdrs_dma - + txq->tx_curr_desc * TSO_HEADER_SIZE; + + tx_index * TSO_HEADER_SIZE; } else { /* Alignment is okay, map buffer and hand off to hardware */ txq->tx_desc_mapping[tx_index] = DESC_DMA_MAP_SINGLE; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index fabc8df40392..662c2ee268c7 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -11,28 +11,28 @@ * warranty of any kind, whether express or implied. */ -#include <linux/kernel.h> -#include <linux/netdevice.h> +#include <linux/clk.h> +#include <linux/cpu.h> #include <linux/etherdevice.h> -#include <linux/platform_device.h> -#include <linux/skbuff.h> +#include <linux/if_vlan.h> #include <linux/inetdevice.h> -#include <linux/mbus.h> -#include <linux/module.h> #include <linux/interrupt.h> -#include <linux/if_vlan.h> -#include <net/ip.h> -#include <net/ipv6.h> #include <linux/io.h> -#include <net/tso.h> +#include <linux/kernel.h> +#include <linux/mbus.h> +#include <linux/module.h> +#include <linux/netdevice.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include <linux/of_address.h> #include <linux/phy.h> -#include <linux/clk.h> -#include <linux/cpu.h> +#include <linux/platform_device.h> +#include <linux/skbuff.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/tso.h> /* Registers */ #define MVNETA_RXQ_CONFIG_REG(q) (0x1400 + ((q) << 2)) @@ -373,6 +373,8 @@ struct mvneta_port { /* Core clock */ struct clk *clk; + /* AXI clock */ + struct clk *clk_bus; u8 mcast_count[256]; u16 tx_ring_size; u16 rx_ring_size; @@ -3242,26 +3244,25 @@ static void mvneta_ethtool_update_stats(struct mvneta_port *pp) const struct mvneta_statistic *s; void __iomem *base = pp->base; u32 high, low, val; + u64 val64; int i; for (i = 0, s = mvneta_statistics; s < mvneta_statistics + ARRAY_SIZE(mvneta_statistics); s++, i++) { - val = 0; - switch (s->type) { case T_REG_32: val = readl_relaxed(base + s->offset); + pp->ethtool_stats[i] += val; break; case T_REG_64: /* Docs say to read low 32-bit then high */ low = readl_relaxed(base + s->offset); high = readl_relaxed(base + s->offset + 4); - val = (u64)high << 32 | low; + val64 = (u64)high << 32 | low; + pp->ethtool_stats[i] += val64; break; } - - pp->ethtool_stats[i] += val; } } @@ -3605,7 +3606,9 @@ static int mvneta_probe(struct platform_device *pdev) pp->indir[0] = rxq_def; - pp->clk = devm_clk_get(&pdev->dev, NULL); + pp->clk = devm_clk_get(&pdev->dev, "core"); + if (IS_ERR(pp->clk)) + pp->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(pp->clk)) { err = PTR_ERR(pp->clk); goto err_put_phy_node; @@ -3613,6 +3616,10 @@ static int mvneta_probe(struct platform_device *pdev) clk_prepare_enable(pp->clk); + pp->clk_bus = devm_clk_get(&pdev->dev, "bus"); + if (!IS_ERR(pp->clk_bus)) + clk_prepare_enable(pp->clk_bus); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); pp->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(pp->base)) { @@ -3724,6 +3731,7 @@ err_free_stats: err_free_ports: free_percpu(pp->ports); err_clk: + clk_disable_unprepare(pp->clk_bus); clk_disable_unprepare(pp->clk); err_put_phy_node: of_node_put(phy_node); @@ -3741,6 +3749,7 @@ static int mvneta_remove(struct platform_device *pdev) struct mvneta_port *pp = netdev_priv(dev); unregister_netdev(dev); + clk_disable_unprepare(pp->clk_bus); clk_disable_unprepare(pp->clk); free_percpu(pp->ports); free_percpu(pp->stats); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0c5237264e3e..bb77e2207804 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -1044,6 +1044,92 @@ static inline void mlxsw_reg_sftr_pack(char *payload, mlxsw_reg_sftr_port_mask_set(payload, port, 1); } +/* SFDF - Switch Filtering DB Flush + * -------------------------------- + * The switch filtering DB flush register is used to flush the FDB. + * Note that FDB notifications are flushed as well. + */ +#define MLXSW_REG_SFDF_ID 0x2013 +#define MLXSW_REG_SFDF_LEN 0x14 + +static const struct mlxsw_reg_info mlxsw_reg_sfdf = { + .id = MLXSW_REG_SFDF_ID, + .len = MLXSW_REG_SFDF_LEN, +}; + +/* reg_sfdf_swid + * Switch partition ID. + * Access: Index + */ +MLXSW_ITEM32(reg, sfdf, swid, 0x00, 24, 8); + +enum mlxsw_reg_sfdf_flush_type { + MLXSW_REG_SFDF_FLUSH_PER_SWID, + MLXSW_REG_SFDF_FLUSH_PER_FID, + MLXSW_REG_SFDF_FLUSH_PER_PORT, + MLXSW_REG_SFDF_FLUSH_PER_PORT_AND_FID, + MLXSW_REG_SFDF_FLUSH_PER_LAG, + MLXSW_REG_SFDF_FLUSH_PER_LAG_AND_FID, +}; + +/* reg_sfdf_flush_type + * Flush type. + * 0 - All SWID dynamic entries are flushed. + * 1 - All FID dynamic entries are flushed. + * 2 - All dynamic entries pointing to port are flushed. + * 3 - All FID dynamic entries pointing to port are flushed. + * 4 - All dynamic entries pointing to LAG are flushed. + * 5 - All FID dynamic entries pointing to LAG are flushed. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, flush_type, 0x04, 28, 4); + +/* reg_sfdf_flush_static + * Static. + * 0 - Flush only dynamic entries. + * 1 - Flush both dynamic and static entries. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, flush_static, 0x04, 24, 1); + +static inline void mlxsw_reg_sfdf_pack(char *payload, + enum mlxsw_reg_sfdf_flush_type type) +{ + MLXSW_REG_ZERO(sfdf, payload); + mlxsw_reg_sfdf_flush_type_set(payload, type); + mlxsw_reg_sfdf_flush_static_set(payload, true); +} + +/* reg_sfdf_fid + * FID to flush. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, fid, 0x0C, 0, 16); + +/* reg_sfdf_system_port + * Port to flush. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, system_port, 0x0C, 0, 16); + +/* reg_sfdf_port_fid_system_port + * Port to flush, pointed to by FID. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, port_fid_system_port, 0x08, 0, 16); + +/* reg_sfdf_lag_id + * LAG ID to flush. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, lag_id, 0x0C, 0, 10); + +/* reg_sfdf_lag_fid_lag_id + * LAG ID to flush, pointed to by FID. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, lag_fid_lag_id, 0x08, 0, 10); + /* SLDR - Switch LAG Descriptor Register * ----------------------------------------- * The switch LAG descriptor register is populated by LAG descriptors. @@ -1701,20 +1787,20 @@ MLXSW_ITEM32(reg, pmlp, width, 0x00, 0, 8); * Module number. * Access: RW */ -MLXSW_ITEM32_INDEXED(reg, pmlp, module, 0x04, 0, 8, 0x04, 0, false); +MLXSW_ITEM32_INDEXED(reg, pmlp, module, 0x04, 0, 8, 0x04, 0x00, false); /* reg_pmlp_tx_lane * Tx Lane. When rxtx field is cleared, this field is used for Rx as well. * Access: RW */ -MLXSW_ITEM32_INDEXED(reg, pmlp, tx_lane, 0x04, 16, 2, 0x04, 16, false); +MLXSW_ITEM32_INDEXED(reg, pmlp, tx_lane, 0x04, 16, 2, 0x04, 0x00, false); /* reg_pmlp_rx_lane * Rx Lane. When rxtx field is cleared, this field is ignored and Rx lane is * equal to Tx lane. * Access: RW */ -MLXSW_ITEM32_INDEXED(reg, pmlp, rx_lane, 0x04, 24, 2, 0x04, 24, false); +MLXSW_ITEM32_INDEXED(reg, pmlp, rx_lane, 0x04, 24, 2, 0x04, 0x00, false); static inline void mlxsw_reg_pmlp_pack(char *payload, u8 local_port) { @@ -3121,6 +3207,8 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "SFGC"; case MLXSW_REG_SFTR_ID: return "SFTR"; + case MLXSW_REG_SFDF_ID: + return "SFDF"; case MLXSW_REG_SLDR_ID: return "SLDR"; case MLXSW_REG_SLCR_ID: diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index ce6845d534a8..217856bdd400 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1979,6 +1979,115 @@ static struct mlxsw_driver mlxsw_sp_driver = { .profile = &mlxsw_sp_config_profile, }; +static int +mlxsw_sp_port_fdb_flush_by_port(const struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char sfdf_pl[MLXSW_REG_SFDF_LEN]; + + mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_PORT); + mlxsw_reg_sfdf_system_port_set(sfdf_pl, mlxsw_sp_port->local_port); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); +} + +static int +mlxsw_sp_port_fdb_flush_by_port_fid(const struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char sfdf_pl[MLXSW_REG_SFDF_LEN]; + + mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_PORT_AND_FID); + mlxsw_reg_sfdf_fid_set(sfdf_pl, fid); + mlxsw_reg_sfdf_port_fid_system_port_set(sfdf_pl, + mlxsw_sp_port->local_port); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); +} + +static int +mlxsw_sp_port_fdb_flush_by_lag_id(const struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char sfdf_pl[MLXSW_REG_SFDF_LEN]; + + mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_LAG); + mlxsw_reg_sfdf_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); +} + +static int +mlxsw_sp_port_fdb_flush_by_lag_id_fid(const struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char sfdf_pl[MLXSW_REG_SFDF_LEN]; + + mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_LAG_AND_FID); + mlxsw_reg_sfdf_fid_set(sfdf_pl, fid); + mlxsw_reg_sfdf_lag_fid_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); +} + +static int +__mlxsw_sp_port_fdb_flush(const struct mlxsw_sp_port *mlxsw_sp_port) +{ + int err, last_err = 0; + u16 vid; + + for (vid = 1; vid < VLAN_N_VID - 1; vid++) { + err = mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_port, vid); + if (err) + last_err = err; + } + + return last_err; +} + +static int +__mlxsw_sp_port_fdb_flush_lagged(const struct mlxsw_sp_port *mlxsw_sp_port) +{ + int err, last_err = 0; + u16 vid; + + for (vid = 1; vid < VLAN_N_VID - 1; vid++) { + err = mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_port, vid); + if (err) + last_err = err; + } + + return last_err; +} + +static int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port) +{ + if (!list_empty(&mlxsw_sp_port->vports_list)) + if (mlxsw_sp_port->lagged) + return __mlxsw_sp_port_fdb_flush_lagged(mlxsw_sp_port); + else + return __mlxsw_sp_port_fdb_flush(mlxsw_sp_port); + else + if (mlxsw_sp_port->lagged) + return mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port); + else + return mlxsw_sp_port_fdb_flush_by_port(mlxsw_sp_port); +} + +static int mlxsw_sp_vport_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_vport); + u16 fid = mlxsw_sp_vfid_to_fid(vfid); + + if (mlxsw_sp_vport->lagged) + return mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_vport, + fid); + else + return mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_vport, fid); +} + static bool mlxsw_sp_port_dev_check(const struct net_device *dev) { return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; @@ -2006,10 +2115,14 @@ static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port) return 0; } -static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port) +static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, + bool flush_fdb) { struct net_device *dev = mlxsw_sp_port->dev; + if (flush_fdb && mlxsw_sp_port_fdb_flush(mlxsw_sp_port)) + netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n"); + mlxsw_sp_port->learning = 0; mlxsw_sp_port->learning_sync = 0; mlxsw_sp_port->uc_flood = 0; @@ -2200,10 +2313,15 @@ err_col_port_enable: return err; } +static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *br_dev, + bool flush_fdb); + static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *lag_dev) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_port *mlxsw_sp_vport; struct mlxsw_sp_upper *lag; u16 lag_id = mlxsw_sp_port->lag_id; int err; @@ -2220,7 +2338,32 @@ static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, if (err) return err; + /* In case we leave a LAG device that has bridges built on top, + * then their teardown sequence is never issued and we need to + * invoke the necessary cleanup routines ourselves. + */ + list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list, + vport.list) { + struct net_device *br_dev; + + if (!mlxsw_sp_vport->bridged) + continue; + + br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport); + mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, false); + } + + if (mlxsw_sp_port->bridged) { + mlxsw_sp_port_active_vlans_del(mlxsw_sp_port); + mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false); + + if (lag->ref_count == 1) + mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); + } + if (lag->ref_count == 1) { + if (mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port)) + netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n"); err = mlxsw_sp_lag_destroy(mlxsw_sp, lag_id); if (err) return err; @@ -2272,9 +2415,6 @@ static int mlxsw_sp_port_lag_changed(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, info->tx_enabled); } -static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *br_dev); - static int mlxsw_sp_port_vlan_link(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *vlan_dev) { @@ -2312,7 +2452,7 @@ static int mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *br_dev; br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport); - mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev); + mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, true); } mlxsw_sp_vport->dev = mlxsw_sp_port->dev; @@ -2374,7 +2514,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, } mlxsw_sp_master_bridge_inc(mlxsw_sp, upper_dev); } else { - err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port); + err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port, + true); mlxsw_sp_master_bridge_dec(mlxsw_sp, upper_dev); if (err) { netdev_err(dev, "Failed to leave bridge\n"); @@ -2541,7 +2682,8 @@ static void mlxsw_sp_br_vfid_destroy(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *br_dev) + struct net_device *br_dev, + bool flush_fdb) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); @@ -2604,6 +2746,9 @@ static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, goto err_vport_flood_set; } + if (flush_fdb && mlxsw_sp_vport_fdb_flush(mlxsw_sp_vport)) + netdev_err(dev, "Failed to flush FDB\n"); + /* Switch between the vFIDs and destroy the old one if needed. */ new_vfid->nr_vports++; mlxsw_sp_vport->vport.vfid = new_vfid; @@ -2777,7 +2922,7 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev, if (!mlxsw_sp_vport) return NOTIFY_DONE; err = mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, - upper_dev); + upper_dev, true); if (err) { netdev_err(dev, "Failed to leave bridge\n"); return NOTIFY_BAD; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index a23dc610d259..7f42eb1c320e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -120,7 +120,6 @@ struct mlxsw_sp { } fdb_notify; #define MLXSW_SP_DEFAULT_AGEING_TIME 300 u32 ageing_time; - struct mutex fdb_lock; /* Make sure FDB sessions are atomic. */ struct mlxsw_sp_upper master_bridge; struct mlxsw_sp_upper lags[MLXSW_SP_LAG_MAX]; }; @@ -254,5 +253,6 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, __be16 __always_unused proto, u16 vid); int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid, bool set, bool only_uc); +void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 45479ef5bcf4..e492ca2cdecd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -45,6 +45,7 @@ #include <linux/if_bridge.h> #include <linux/workqueue.h> #include <linux/jiffies.h> +#include <linux/rtnetlink.h> #include <net/switchdev.h> #include "spectrum.h" @@ -124,14 +125,14 @@ static int mlxsw_sp_port_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port, int err; switch (state) { - case BR_STATE_DISABLED: /* fall-through */ case BR_STATE_FORWARDING: spms_state = MLXSW_REG_SPMS_STATE_FORWARDING; break; - case BR_STATE_LISTENING: /* fall-through */ case BR_STATE_LEARNING: spms_state = MLXSW_REG_SPMS_STATE_LEARNING; break; + case BR_STATE_LISTENING: /* fall-through */ + case BR_STATE_DISABLED: /* fall-through */ case BR_STATE_BLOCKING: spms_state = MLXSW_REG_SPMS_STATE_DISCARDING; break; @@ -936,6 +937,14 @@ static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, vlan->vid_begin, vlan->vid_end, false); } +void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port) +{ + u16 vid; + + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) + __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vid, vid, false); +} + static int mlxsw_sp_port_fdb_static_del(struct mlxsw_sp_port *mlxsw_sp_port, const struct switchdev_obj_port_fdb *fdb) @@ -1040,10 +1049,12 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, struct switchdev_obj_port_fdb *fdb, - switchdev_obj_dump_cb_t *cb) + switchdev_obj_dump_cb_t *cb, + struct net_device *orig_dev) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - u16 vport_vid = 0, vport_fid = 0; + struct mlxsw_sp_port *tmp; + u16 vport_fid = 0; char *sfd_pl; char mac[ETH_ALEN]; u16 fid; @@ -1058,13 +1069,11 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, if (!sfd_pl) return -ENOMEM; - mutex_lock(&mlxsw_sp_port->mlxsw_sp->fdb_lock); if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { u16 tmp; tmp = mlxsw_sp_vport_vfid_get(mlxsw_sp_port); vport_fid = mlxsw_sp_vfid_to_fid(tmp); - vport_vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port); } mlxsw_reg_sfd_pack(sfd_pl, MLXSW_REG_SFD_OP_QUERY_DUMP, 0); @@ -1088,12 +1097,13 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_reg_sfd_uc_unpack(sfd_pl, i, mac, &fid, &local_port); if (local_port == mlxsw_sp_port->local_port) { - if (vport_fid && vport_fid != fid) - continue; - else if (vport_fid) - fdb->vid = vport_vid; - else + if (vport_fid && vport_fid == fid) + fdb->vid = 0; + else if (!vport_fid && + !mlxsw_sp_fid_is_vfid(fid)) fdb->vid = fid; + else + continue; ether_addr_copy(fdb->addr, mac); fdb->ndm_state = NUD_REACHABLE; err = cb(&fdb->obj); @@ -1104,14 +1114,22 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, case MLXSW_REG_SFD_REC_TYPE_UNICAST_LAG: mlxsw_reg_sfd_uc_lag_unpack(sfd_pl, i, mac, &fid, &lag_id); - if (mlxsw_sp_port == - mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id)) { - if (vport_fid && vport_fid != fid) + tmp = mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id); + if (tmp && tmp->local_port == + mlxsw_sp_port->local_port) { + /* LAG records can only point to LAG + * devices or VLAN devices on top. + */ + if (!netif_is_lag_master(orig_dev) && + !is_vlan_dev(orig_dev)) continue; - else if (vport_fid) - fdb->vid = vport_vid; - else + if (vport_fid && vport_fid == fid) + fdb->vid = 0; + else if (!vport_fid && + !mlxsw_sp_fid_is_vfid(fid)) fdb->vid = fid; + else + continue; ether_addr_copy(fdb->addr, mac); fdb->ndm_state = NUD_REACHABLE; err = cb(&fdb->obj); @@ -1124,7 +1142,6 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, } while (num_rec == MLXSW_REG_SFD_REC_MAX_COUNT); out: - mutex_unlock(&mlxsw_sp_port->mlxsw_sp->fdb_lock); kfree(sfd_pl); return stored_err ? stored_err : err; } @@ -1176,7 +1193,8 @@ static int mlxsw_sp_port_obj_dump(struct net_device *dev, break; case SWITCHDEV_OBJ_ID_PORT_FDB: err = mlxsw_sp_port_fdb_dump(mlxsw_sp_port, - SWITCHDEV_OBJ_PORT_FDB(obj), cb); + SWITCHDEV_OBJ_PORT_FDB(obj), cb, + obj->orig_dev); break; default: err = -EOPNOTSUPP; @@ -1194,14 +1212,14 @@ static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = { .switchdev_port_obj_dump = mlxsw_sp_port_obj_dump, }; -static void mlxsw_sp_fdb_call_notifiers(bool learning, bool learning_sync, - bool adding, char *mac, u16 vid, +static void mlxsw_sp_fdb_call_notifiers(bool learning_sync, bool adding, + char *mac, u16 vid, struct net_device *dev) { struct switchdev_notifier_fdb_info info; unsigned long notifier_type; - if (learning && learning_sync) { + if (learning_sync) { info.addr = mac; info.vid = vid; notifier_type = adding ? SWITCHDEV_FDB_ADD : SWITCHDEV_FDB_DEL; @@ -1237,7 +1255,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n"); goto just_remove; } - vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + vid = 0; /* Override the physical port with the vPort. */ mlxsw_sp_port = mlxsw_sp_vport; } else { @@ -1257,8 +1275,7 @@ do_fdb_op: if (!do_notification) return; - mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning, - mlxsw_sp_port->learning_sync, + mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning_sync, adding, mac, vid, mlxsw_sp_port->dev); return; @@ -1273,6 +1290,7 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, bool adding) { struct mlxsw_sp_port *mlxsw_sp_port; + struct net_device *dev; char mac[ETH_ALEN]; u16 lag_vid = 0; u16 lag_id; @@ -1298,11 +1316,13 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, goto just_remove; } - vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); - lag_vid = vid; + lag_vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + dev = mlxsw_sp_vport->dev; + vid = 0; /* Override the physical port with the vPort. */ mlxsw_sp_port = mlxsw_sp_vport; } else { + dev = mlxsw_sp_lag_get(mlxsw_sp, lag_id)->dev; vid = fid; } @@ -1319,10 +1339,8 @@ do_fdb_op: if (!do_notification) return; - mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning, - mlxsw_sp_port->learning_sync, - adding, mac, vid, - mlxsw_sp_lag_get(mlxsw_sp, lag_id)->dev); + mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning_sync, adding, mac, + vid, dev); return; just_remove: @@ -1374,7 +1392,7 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work) mlxsw_sp = container_of(work, struct mlxsw_sp, fdb_notify.dw.work); - mutex_lock(&mlxsw_sp->fdb_lock); + rtnl_lock(); do { mlxsw_reg_sfn_pack(sfn_pl); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl); @@ -1387,7 +1405,7 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work) mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i); } while (num_rec); - mutex_unlock(&mlxsw_sp->fdb_lock); + rtnl_unlock(); kfree(sfn_pl); mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); @@ -1402,7 +1420,6 @@ static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp) dev_err(mlxsw_sp->bus_info->dev, "Failed to set default ageing time\n"); return err; } - mutex_init(&mlxsw_sp->fdb_lock); INIT_DELAYED_WORK(&mlxsw_sp->fdb_notify.dw, mlxsw_sp_fdb_notify_work); mlxsw_sp->fdb_notify.interval = MLXSW_SP_DEFAULT_LEARNING_INTERVAL; mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index a10c928bbd6b..00cfd95ca59d 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -28,6 +28,16 @@ #include "moxart_ether.h" +static inline void moxart_desc_write(u32 data, u32 *desc) +{ + *desc = cpu_to_le32(data); +} + +static inline u32 moxart_desc_read(u32 *desc) +{ + return le32_to_cpu(*desc); +} + static inline void moxart_emac_write(struct net_device *ndev, unsigned int reg, unsigned long value) { @@ -112,7 +122,7 @@ static void moxart_mac_enable(struct net_device *ndev) static void moxart_mac_setup_desc_ring(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); - void __iomem *desc; + void *desc; int i; for (i = 0; i < TX_DESC_NUM; i++) { @@ -121,7 +131,7 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev) priv->tx_buf[i] = priv->tx_buf_base + priv->tx_buf_size * i; } - writel(TX_DESC1_END, desc + TX_REG_OFFSET_DESC1); + moxart_desc_write(TX_DESC1_END, desc + TX_REG_OFFSET_DESC1); priv->tx_head = 0; priv->tx_tail = 0; @@ -129,8 +139,8 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev) for (i = 0; i < RX_DESC_NUM; i++) { desc = priv->rx_desc_base + i * RX_REG_DESC_SIZE; memset(desc, 0, RX_REG_DESC_SIZE); - writel(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0); - writel(RX_BUF_SIZE & RX_DESC1_BUF_SIZE_MASK, + moxart_desc_write(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0); + moxart_desc_write(RX_BUF_SIZE & RX_DESC1_BUF_SIZE_MASK, desc + RX_REG_OFFSET_DESC1); priv->rx_buf[i] = priv->rx_buf_base + priv->rx_buf_size * i; @@ -141,12 +151,12 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev) if (dma_mapping_error(&ndev->dev, priv->rx_mapping[i])) netdev_err(ndev, "DMA mapping error\n"); - writel(priv->rx_mapping[i], + moxart_desc_write(priv->rx_mapping[i], desc + RX_REG_OFFSET_DESC2 + RX_DESC2_ADDRESS_PHYS); - writel(priv->rx_buf[i], + moxart_desc_write((uintptr_t)priv->rx_buf[i], desc + RX_REG_OFFSET_DESC2 + RX_DESC2_ADDRESS_VIRT); } - writel(RX_DESC1_END, desc + RX_REG_OFFSET_DESC1); + moxart_desc_write(RX_DESC1_END, desc + RX_REG_OFFSET_DESC1); priv->rx_head = 0; @@ -201,14 +211,15 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) napi); struct net_device *ndev = priv->ndev; struct sk_buff *skb; - void __iomem *desc; + void *desc; unsigned int desc0, len; int rx_head = priv->rx_head; int rx = 0; while (rx < budget) { desc = priv->rx_desc_base + (RX_REG_DESC_SIZE * rx_head); - desc0 = readl(desc + RX_REG_OFFSET_DESC0); + desc0 = moxart_desc_read(desc + RX_REG_OFFSET_DESC0); + rmb(); /* ensure desc0 is up to date */ if (desc0 & RX_DESC0_DMA_OWN) break; @@ -250,7 +261,8 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) priv->stats.multicast++; rx_next: - writel(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0); + wmb(); /* prevent setting ownership back too early */ + moxart_desc_write(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0); rx_head = RX_NEXT(rx_head); priv->rx_head = rx_head; @@ -310,7 +322,7 @@ static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id) static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); - void __iomem *desc; + void *desc; unsigned int len; unsigned int tx_head = priv->tx_head; u32 txdes1; @@ -319,11 +331,12 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head); spin_lock_irq(&priv->txlock); - if (readl(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) { + if (moxart_desc_read(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) { net_dbg_ratelimited("no TX space for packet\n"); priv->stats.tx_dropped++; goto out_unlock; } + rmb(); /* ensure data is only read that had TX_DESC0_DMA_OWN cleared */ len = skb->len > TX_BUF_SIZE ? TX_BUF_SIZE : skb->len; @@ -337,9 +350,9 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) priv->tx_len[tx_head] = len; priv->tx_skb[tx_head] = skb; - writel(priv->tx_mapping[tx_head], + moxart_desc_write(priv->tx_mapping[tx_head], desc + TX_REG_OFFSET_DESC2 + TX_DESC2_ADDRESS_PHYS); - writel(skb->data, + moxart_desc_write((uintptr_t)skb->data, desc + TX_REG_OFFSET_DESC2 + TX_DESC2_ADDRESS_VIRT); if (skb->len < ETH_ZLEN) { @@ -354,8 +367,9 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) txdes1 = TX_DESC1_LTS | TX_DESC1_FTS | (len & TX_DESC1_BUF_SIZE_MASK); if (tx_head == TX_DESC_NUM_MASK) txdes1 |= TX_DESC1_END; - writel(txdes1, desc + TX_REG_OFFSET_DESC1); - writel(TX_DESC0_DMA_OWN, desc + TX_REG_OFFSET_DESC0); + moxart_desc_write(txdes1, desc + TX_REG_OFFSET_DESC1); + wmb(); /* flush descriptor before transferring ownership */ + moxart_desc_write(TX_DESC0_DMA_OWN, desc + TX_REG_OFFSET_DESC0); /* start to send packet */ writel(0xffffffff, priv->base + REG_TX_POLL_DEMAND); diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h index 2be9280d608c..93a9563ac7c6 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.h +++ b/drivers/net/ethernet/moxa/moxart_ether.h @@ -300,7 +300,7 @@ struct moxart_mac_priv_t { dma_addr_t rx_base; dma_addr_t rx_mapping[RX_DESC_NUM]; - void __iomem *rx_desc_base; + void *rx_desc_base; unsigned char *rx_buf_base; unsigned char *rx_buf[RX_DESC_NUM]; unsigned int rx_head; @@ -308,7 +308,7 @@ struct moxart_mac_priv_t { dma_addr_t tx_base; dma_addr_t tx_mapping[TX_DESC_NUM]; - void __iomem *tx_desc_base; + void *tx_desc_base; unsigned char *tx_buf_base; unsigned char *tx_buf[RX_DESC_NUM]; unsigned int tx_head; diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 50d5604833ed..e0993eba5df3 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -2223,8 +2223,6 @@ static irqreturn_t vxge_isr_napi(int irq, void *dev_id) return IRQ_NONE; } -#ifdef CONFIG_PCI_MSI - static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id) { struct vxge_fifo *fifo = (struct vxge_fifo *)dev_id; @@ -2442,16 +2440,13 @@ static void vxge_rem_msix_isr(struct vxgedev *vdev) if (vdev->config.intr_type == MSI_X) pci_disable_msix(vdev->pdev); } -#endif static void vxge_rem_isr(struct vxgedev *vdev) { -#ifdef CONFIG_PCI_MSI - if (vdev->config.intr_type == MSI_X) { + if (IS_ENABLED(CONFIG_PCI_MSI) && + vdev->config.intr_type == MSI_X) { vxge_rem_msix_isr(vdev); - } else -#endif - if (vdev->config.intr_type == INTA) { + } else if (vdev->config.intr_type == INTA) { synchronize_irq(vdev->pdev->irq); free_irq(vdev->pdev->irq, vdev); } @@ -2460,11 +2455,10 @@ static void vxge_rem_isr(struct vxgedev *vdev) static int vxge_add_isr(struct vxgedev *vdev) { int ret = 0; -#ifdef CONFIG_PCI_MSI int vp_idx = 0, intr_idx = 0, intr_cnt = 0, msix_idx = 0, irq_req = 0; int pci_fun = PCI_FUNC(vdev->pdev->devfn); - if (vdev->config.intr_type == MSI_X) + if (IS_ENABLED(CONFIG_PCI_MSI) && vdev->config.intr_type == MSI_X) ret = vxge_enable_msix(vdev); if (ret) { @@ -2475,7 +2469,7 @@ static int vxge_add_isr(struct vxgedev *vdev) vdev->config.intr_type = INTA; } - if (vdev->config.intr_type == MSI_X) { + if (IS_ENABLED(CONFIG_PCI_MSI) && vdev->config.intr_type == MSI_X) { for (intr_idx = 0; intr_idx < (vdev->no_of_vpath * VXGE_HW_VPATH_MSIX_ACTIVE); intr_idx++) { @@ -2576,9 +2570,8 @@ static int vxge_add_isr(struct vxgedev *vdev) vdev->vxge_entries[intr_cnt].in_use = 1; vdev->vxge_entries[intr_cnt].arg = &vdev->vpaths[0]; } -INTA_MODE: -#endif +INTA_MODE: if (vdev->config.intr_type == INTA) { snprintf(vdev->desc[0], VXGE_INTR_STRLEN, "%s:vxge:INTA", vdev->ndev->name); @@ -3889,12 +3882,12 @@ static void vxge_device_config_init(struct vxge_hw_device_config *device_config, if (max_mac_vpath > VXGE_MAX_MAC_ADDR_COUNT) max_mac_vpath = VXGE_MAX_MAC_ADDR_COUNT; -#ifndef CONFIG_PCI_MSI - vxge_debug_init(VXGE_ERR, - "%s: This Kernel does not support " - "MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME); - *intr_type = INTA; -#endif + if (!IS_ENABLED(CONFIG_PCI_MSI)) { + vxge_debug_init(VXGE_ERR, + "%s: This Kernel does not support " + "MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME); + *intr_type = INTA; + } /* Configure whether MSI-X or IRQL. */ switch (*intr_type) { diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index a4ab71d43e4e..166a7fc87e2f 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -3531,12 +3531,14 @@ static void rocker_port_fdb_learn_work(struct work_struct *work) info.addr = lw->addr; info.vid = lw->vid; + rtnl_lock(); if (learned && removing) call_switchdev_notifiers(SWITCHDEV_FDB_DEL, lw->rocker_port->dev, &info.info); else if (learned && !removing) call_switchdev_notifiers(SWITCHDEV_FDB_ADD, lw->rocker_port->dev, &info.info); + rtnl_unlock(); rocker_port_kfree(lw->trans, work); } diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index cc106d892e29..23fa29877f5b 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -389,17 +389,27 @@ static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc) if (vio_version_after_eq(&port->vio, 1, 8)) { struct vio_net_dext *dext = vio_net_ext(desc); + skb_reset_network_header(skb); + if (dext->flags & VNET_PKT_HCK_IPV4_HDRCKSUM) { if (skb->protocol == ETH_P_IP) { - struct iphdr *iph = (struct iphdr *)skb->data; + struct iphdr *iph = ip_hdr(skb); iph->check = 0; ip_send_check(iph); } } if ((dext->flags & VNET_PKT_HCK_FULLCKSUM) && - skb->ip_summed == CHECKSUM_NONE) - vnet_fullcsum(skb); + skb->ip_summed == CHECKSUM_NONE) { + if (skb->protocol == htons(ETH_P_IP)) { + struct iphdr *iph = ip_hdr(skb); + int ihl = iph->ihl * 4; + + skb_reset_transport_header(skb); + skb_set_transport_header(skb, ihl); + vnet_fullcsum(skb); + } + } if (dext->flags & VNET_PKT_HCK_IPV4_HDRCKSUM_OK) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_level = 0; diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index 657b65bf5cac..18bf3a8fdc50 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -82,7 +82,7 @@ struct cpdma_desc { struct cpdma_desc_pool { phys_addr_t phys; - u32 hw_addr; + dma_addr_t hw_addr; void __iomem *iomap; /* ioremap map */ void *cpumap; /* dma_alloc map */ int desc_size, mem_size; @@ -152,7 +152,7 @@ struct cpdma_chan { * abstract out these details */ static struct cpdma_desc_pool * -cpdma_desc_pool_create(struct device *dev, u32 phys, u32 hw_addr, +cpdma_desc_pool_create(struct device *dev, u32 phys, dma_addr_t hw_addr, int size, int align) { int bitmap_size; @@ -176,13 +176,13 @@ cpdma_desc_pool_create(struct device *dev, u32 phys, u32 hw_addr, if (phys) { pool->phys = phys; - pool->iomap = ioremap(phys, size); + pool->iomap = ioremap(phys, size); /* should be memremap? */ pool->hw_addr = hw_addr; } else { - pool->cpumap = dma_alloc_coherent(dev, size, &pool->phys, + pool->cpumap = dma_alloc_coherent(dev, size, &pool->hw_addr, GFP_KERNEL); - pool->iomap = pool->cpumap; - pool->hw_addr = pool->phys; + pool->iomap = (void __iomem __force *)pool->cpumap; + pool->phys = pool->hw_addr; /* assumes no IOMMU, don't use this value */ } if (pool->iomap) diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c index 7f975a2c8990..b0de8ecd7fe8 100644 --- a/drivers/net/fddi/defxx.c +++ b/drivers/net/fddi/defxx.c @@ -533,8 +533,8 @@ static int dfx_register(struct device *bdev) const char *print_name = dev_name(bdev); struct net_device *dev; DFX_board_t *bp; /* board pointer */ - resource_size_t bar_start[3]; /* pointers to ports */ - resource_size_t bar_len[3]; /* resource length */ + resource_size_t bar_start[3] = {0}; /* pointers to ports */ + resource_size_t bar_len[3] = {0}; /* resource length */ int alloc_size; /* total buffer size used */ struct resource *region; int err = 0; @@ -3697,8 +3697,8 @@ static void dfx_unregister(struct device *bdev) int dfx_bus_pci = dev_is_pci(bdev); int dfx_bus_tc = DFX_BUS_TC(bdev); int dfx_use_mmio = DFX_MMIO || dfx_bus_tc; - resource_size_t bar_start[3]; /* pointers to ports */ - resource_size_t bar_len[3]; /* resource lengths */ + resource_size_t bar_start[3] = {0}; /* pointers to ports */ + resource_size_t bar_len[3] = {0}; /* resource lengths */ int alloc_size; /* total buffer size used */ unregister_netdev(dev); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 7456569f53c1..0b14ac3b8d11 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -980,9 +980,9 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, opts = ip_tunnel_info_opts(info); if (key->tun_flags & TUNNEL_CSUM) - flags |= GENEVE_F_UDP_CSUM; + flags &= ~GENEVE_F_UDP_ZERO_CSUM6_TX; else - flags &= ~GENEVE_F_UDP_CSUM; + flags |= GENEVE_F_UDP_ZERO_CSUM6_TX; err = geneve6_build_skb(dst, skb, key->tun_flags, vni, info->options_len, opts, diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index f4130af09244..fcb92c0d0eb9 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -624,6 +624,7 @@ struct nvsp_message { #define RNDIS_PKT_ALIGN_DEFAULT 8 struct multi_send_data { + struct sk_buff *skb; /* skb containing the pkt */ struct hv_netvsc_packet *pkt; /* netvsc pkt pending */ u32 count; /* counter of batched packets */ }; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 059fc5231601..ec313fc08d82 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -841,6 +841,18 @@ static inline int netvsc_send_pkt( return ret; } +/* Move packet out of multi send data (msd), and clear msd */ +static inline void move_pkt_msd(struct hv_netvsc_packet **msd_send, + struct sk_buff **msd_skb, + struct multi_send_data *msdp) +{ + *msd_skb = msdp->skb; + *msd_send = msdp->pkt; + msdp->skb = NULL; + msdp->pkt = NULL; + msdp->count = 0; +} + int netvsc_send(struct hv_device *device, struct hv_netvsc_packet *packet, struct rndis_message *rndis_msg, @@ -855,6 +867,7 @@ int netvsc_send(struct hv_device *device, unsigned int section_index = NETVSC_INVALID_INDEX; struct multi_send_data *msdp; struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL; + struct sk_buff *msd_skb = NULL; bool try_batch; bool xmit_more = (skb != NULL) ? skb->xmit_more : false; @@ -897,10 +910,8 @@ int netvsc_send(struct hv_device *device, net_device->send_section_size) { section_index = netvsc_get_next_send_section(net_device); if (section_index != NETVSC_INVALID_INDEX) { - msd_send = msdp->pkt; - msdp->pkt = NULL; - msdp->count = 0; - msd_len = 0; + move_pkt_msd(&msd_send, &msd_skb, msdp); + msd_len = 0; } } @@ -919,31 +930,31 @@ int netvsc_send(struct hv_device *device, packet->total_data_buflen += msd_len; } - if (msdp->pkt) - dev_kfree_skb_any(skb); + if (msdp->skb) + dev_kfree_skb_any(msdp->skb); if (xmit_more && !packet->cp_partial) { + msdp->skb = skb; msdp->pkt = packet; msdp->count++; } else { cur_send = packet; + msdp->skb = NULL; msdp->pkt = NULL; msdp->count = 0; } } else { - msd_send = msdp->pkt; - msdp->pkt = NULL; - msdp->count = 0; + move_pkt_msd(&msd_send, &msd_skb, msdp); cur_send = packet; } if (msd_send) { - m_ret = netvsc_send_pkt(msd_send, net_device, pb, skb); + m_ret = netvsc_send_pkt(msd_send, net_device, NULL, msd_skb); if (m_ret != 0) { netvsc_free_send_slot(net_device, msd_send->send_buf_index); - dev_kfree_skb_any(skb); + dev_kfree_skb_any(msd_skb); } } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 1c8db9afdcda..1d3a66563bac 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -196,65 +196,6 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size, return ppi; } -union sub_key { - u64 k; - struct { - u8 pad[3]; - u8 kb; - u32 ka; - }; -}; - -/* Toeplitz hash function - * data: network byte order - * return: host byte order - */ -static u32 comp_hash(u8 *key, int klen, void *data, int dlen) -{ - union sub_key subk; - int k_next = 4; - u8 dt; - int i, j; - u32 ret = 0; - - subk.k = 0; - subk.ka = ntohl(*(u32 *)key); - - for (i = 0; i < dlen; i++) { - subk.kb = key[k_next]; - k_next = (k_next + 1) % klen; - dt = ((u8 *)data)[i]; - for (j = 0; j < 8; j++) { - if (dt & 0x80) - ret ^= subk.ka; - dt <<= 1; - subk.k <<= 1; - } - } - - return ret; -} - -static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb) -{ - struct flow_keys flow; - int data_len; - - if (!skb_flow_dissect_flow_keys(skb, &flow, 0) || - !(flow.basic.n_proto == htons(ETH_P_IP) || - flow.basic.n_proto == htons(ETH_P_IPV6))) - return false; - - if (flow.basic.ip_proto == IPPROTO_TCP) - data_len = 12; - else - data_len = 8; - - *hash = comp_hash(netvsc_hash_key, HASH_KEYLEN, &flow, data_len); - - return true; -} - static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, void *accel_priv, select_queue_fallback_t fallback) { @@ -267,11 +208,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1) return 0; - if (netvsc_set_hash(&hash, skb)) { - q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] % - ndev->real_num_tx_queues; - skb_set_hash(skb, hash, PKT_HASH_TYPE_L3); - } + hash = skb_get_hash(skb); + q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] % + ndev->real_num_tx_queues; if (!nvsc_dev->chn_table[q_idx]) q_idx = 0; diff --git a/drivers/net/irda/bfin_sir.h b/drivers/net/irda/bfin_sir.h index 29cbde8501ed..d47cf14bb4a5 100644 --- a/drivers/net/irda/bfin_sir.h +++ b/drivers/net/irda/bfin_sir.h @@ -82,9 +82,6 @@ struct bfin_sir_self { #define DRIVER_NAME "bfin_sir" -#define port_membase(port) (((struct bfin_sir_port *)(port))->membase) -#define get_lsr_cache(port) (((struct bfin_sir_port *)(port))->lsr) -#define put_lsr_cache(port, v) (((struct bfin_sir_port *)(port))->lsr = (v)) #include <asm/bfin_serial.h> static const unsigned short per[][4] = { diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 6a57a005e0ca..94e688805dd2 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1323,6 +1323,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, list_add_tail_rcu(&vlan->list, &port->vlans); netif_stacked_transfer_operstate(lowerdev, dev); + linkwatch_fire_event(dev); return 0; @@ -1522,6 +1523,7 @@ static int macvlan_device_event(struct notifier_block *unused, port = macvlan_port_get_rtnl(dev); switch (event) { + case NETDEV_UP: case NETDEV_CHANGE: list_for_each_entry(vlan, &port->vlans, list) netif_stacked_transfer_operstate(vlan->lowerdev, diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 60994a83a0d6..f0a77020037a 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -186,6 +186,7 @@ config MDIO_GPIO config MDIO_OCTEON tristate "Support for MDIO buses on Octeon and ThunderX SOCs" depends on 64BIT + depends on HAS_IOMEM help This module provides a driver for the Octeon and ThunderX MDIO diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 180f69952779..7a240fce3a7e 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -846,6 +846,11 @@ static void decode_rxts(struct dp83640_private *dp83640, struct skb_shared_hwtstamps *shhwtstamps = NULL; struct sk_buff *skb; unsigned long flags; + u8 overflow; + + overflow = (phy_rxts->ns_hi >> 14) & 0x3; + if (overflow) + pr_debug("rx timestamp queue overflow, count %d\n", overflow); spin_lock_irqsave(&dp83640->rx_lock, flags); @@ -888,6 +893,7 @@ static void decode_txts(struct dp83640_private *dp83640, struct skb_shared_hwtstamps shhwtstamps; struct sk_buff *skb; u64 ns; + u8 overflow; /* We must already have the skb that triggered this. */ @@ -897,6 +903,17 @@ static void decode_txts(struct dp83640_private *dp83640, pr_debug("have timestamp but tx_queue empty\n"); return; } + + overflow = (phy_txts->ns_hi >> 14) & 0x3; + if (overflow) { + pr_debug("tx timestamp queue overflow, count %d\n", overflow); + while (skb) { + skb_complete_tx_timestamp(skb, NULL); + skb = skb_dequeue(&dp83640->tx_queue); + } + return; + } + ns = phy2txts(phy_txts); memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ns_to_ktime(ns); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 8763bb20988a..5590b9c182c9 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -692,25 +692,29 @@ void phy_change(struct work_struct *work) struct phy_device *phydev = container_of(work, struct phy_device, phy_queue); - if (phydev->drv->did_interrupt && - !phydev->drv->did_interrupt(phydev)) - goto ignore; + if (phy_interrupt_is_valid(phydev)) { + if (phydev->drv->did_interrupt && + !phydev->drv->did_interrupt(phydev)) + goto ignore; - if (phy_disable_interrupts(phydev)) - goto phy_err; + if (phy_disable_interrupts(phydev)) + goto phy_err; + } mutex_lock(&phydev->lock); if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state)) phydev->state = PHY_CHANGELINK; mutex_unlock(&phydev->lock); - atomic_dec(&phydev->irq_disable); - enable_irq(phydev->irq); + if (phy_interrupt_is_valid(phydev)) { + atomic_dec(&phydev->irq_disable); + enable_irq(phydev->irq); - /* Reenable interrupts */ - if (PHY_HALTED != phydev->state && - phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED)) - goto irq_enable_err; + /* Reenable interrupts */ + if (PHY_HALTED != phydev->state && + phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED)) + goto irq_enable_err; + } /* reschedule state queue work to run as soon as possible */ cancel_delayed_work_sync(&phydev->state_queue); @@ -905,10 +909,10 @@ void phy_state_machine(struct work_struct *work) phydev->adjust_link(phydev->attached_dev); break; case PHY_RUNNING: - /* Only register a CHANGE if we are polling or ignoring - * interrupts and link changed since latest checking. + /* Only register a CHANGE if we are polling and link changed + * since latest checking. */ - if (!phy_interrupt_is_valid(phydev)) { + if (phydev->irq == PHY_POLL) { old_link = phydev->link; err = phy_read_status(phydev); if (err) @@ -1000,15 +1004,21 @@ void phy_state_machine(struct work_struct *work) phy_state_to_str(old_state), phy_state_to_str(phydev->state)); - queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, - PHY_STATE_TIME * HZ); + /* Only re-schedule a PHY state machine change if we are polling the + * PHY, if PHY_IGNORE_INTERRUPT is set, then we will be moving + * between states from phy_mac_interrupt() + */ + if (phydev->irq == PHY_POLL) + queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, + PHY_STATE_TIME * HZ); } void phy_mac_interrupt(struct phy_device *phydev, int new_link) { - cancel_work_sync(&phydev->phy_queue); phydev->link = new_link; - schedule_work(&phydev->phy_queue); + + /* Trigger a state machine change */ + queue_work(system_power_efficient_wq, &phydev->phy_queue); } EXPORT_SYMBOL(phy_mac_interrupt); diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index e485f2653c82..2e21e9366f76 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -24,6 +24,10 @@ #include <linux/netdevice.h> #include <linux/smscphy.h> +struct smsc_phy_priv { + bool energy_enable; +}; + static int smsc_phy_config_intr(struct phy_device *phydev) { int rc = phy_write (phydev, MII_LAN83C185_IM, @@ -43,19 +47,14 @@ static int smsc_phy_ack_interrupt(struct phy_device *phydev) static int smsc_phy_config_init(struct phy_device *phydev) { - int __maybe_unused len; - struct device *dev __maybe_unused = &phydev->mdio.dev; - struct device_node *of_node __maybe_unused = dev->of_node; + struct smsc_phy_priv *priv = phydev->priv; + int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS); - int enable_energy = 1; if (rc < 0) return rc; - if (of_find_property(of_node, "smsc,disable-energy-detect", &len)) - enable_energy = 0; - - if (enable_energy) { + if (priv->energy_enable) { /* Enable energy detect mode for this SMSC Transceivers */ rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS, rc | MII_LAN83C185_EDPWRDOWN); @@ -110,10 +109,13 @@ static int lan911x_config_init(struct phy_device *phydev) */ static int lan87xx_read_status(struct phy_device *phydev) { + struct smsc_phy_priv *priv = phydev->priv; + int err = genphy_read_status(phydev); - int i; - if (!phydev->link) { + if (!phydev->link && priv->energy_enable) { + int i; + /* Disable EDPD to wake up PHY */ int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS); if (rc < 0) @@ -149,6 +151,26 @@ static int lan87xx_read_status(struct phy_device *phydev) return err; } +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; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->energy_enable = true; + + if (of_property_read_bool(of_node, "smsc,disable-energy-detect")) + priv->energy_enable = false; + + phydev->priv = priv; + + return 0; +} + static struct phy_driver smsc_phy_driver[] = { { .phy_id = 0x0007c0a0, /* OUI=0x00800f, Model#=0x0a */ @@ -159,6 +181,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, @@ -180,6 +204,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, @@ -201,6 +227,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = lan87xx_read_status, @@ -222,6 +250,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, @@ -242,6 +272,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = lan87xx_read_status, @@ -263,6 +295,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = lan87xx_read_status, diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 90868ca5e341..ae0905ed4a32 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -129,24 +129,27 @@ static int lookup_chan_dst(u16 call_id, __be32 d_addr) return i < MAX_CALLID; } -static int add_chan(struct pppox_sock *sock) +static int add_chan(struct pppox_sock *sock, + struct pptp_addr *sa) { static int call_id; spin_lock(&chan_lock); - if (!sock->proto.pptp.src_addr.call_id) { + if (!sa->call_id) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1); if (call_id == MAX_CALLID) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1); if (call_id == MAX_CALLID) goto out_err; } - sock->proto.pptp.src_addr.call_id = call_id; - } else if (test_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap)) + sa->call_id = call_id; + } else if (test_bit(sa->call_id, callid_bitmap)) { goto out_err; + } - set_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap); - rcu_assign_pointer(callid_sock[sock->proto.pptp.src_addr.call_id], sock); + sock->proto.pptp.src_addr = *sa; + set_bit(sa->call_id, callid_bitmap); + rcu_assign_pointer(callid_sock[sa->call_id], sock); spin_unlock(&chan_lock); return 0; @@ -416,7 +419,6 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); - struct pptp_opt *opt = &po->proto.pptp; int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) @@ -424,10 +426,22 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); - opt->src_addr = sp->sa_addr.pptp; - if (add_chan(po)) + if (sk->sk_state & PPPOX_DEAD) { + error = -EALREADY; + goto out; + } + + if (sk->sk_state & PPPOX_BOUND) { error = -EBUSY; + goto out; + } + + if (add_chan(po, &sp->sa_addr.pptp)) + error = -EBUSY; + else + sk->sk_state |= PPPOX_BOUND; +out: release_sock(sk); return error; } @@ -498,7 +512,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, } opt->dst_addr = sp->sa_addr.pptp; - sk->sk_state = PPPOX_CONNECTED; + sk->sk_state |= PPPOX_CONNECTED; end: release_sock(sk); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 2ed53331bfb2..1c299b8a162d 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -36,7 +36,7 @@ #define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>" #define DRIVER_DESC "LAN78XX USB 3.0 Gigabit Ethernet Devices" #define DRIVER_NAME "lan78xx" -#define DRIVER_VERSION "1.0.1" +#define DRIVER_VERSION "1.0.2" #define TX_TIMEOUT_JIFFIES (5 * HZ) #define THROTTLE_JIFFIES (HZ / 8) @@ -462,32 +462,53 @@ static int lan78xx_read_raw_eeprom(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { u32 val; + u32 saved; int i, ret; + int retval; - ret = lan78xx_eeprom_confirm_not_busy(dev); - if (ret) - return ret; + /* depends on chip, some EEPROM pins are muxed with LED function. + * disable & restore LED function to access EEPROM. + */ + ret = lan78xx_read_reg(dev, HW_CFG, &val); + saved = val; + if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) { + val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_); + ret = lan78xx_write_reg(dev, HW_CFG, val); + } + + retval = lan78xx_eeprom_confirm_not_busy(dev); + if (retval) + return retval; for (i = 0; i < length; i++) { val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_READ_; val |= (offset & E2P_CMD_EPC_ADDR_MASK_); ret = lan78xx_write_reg(dev, E2P_CMD, val); - if (unlikely(ret < 0)) - return -EIO; + if (unlikely(ret < 0)) { + retval = -EIO; + goto exit; + } - ret = lan78xx_wait_eeprom(dev); - if (ret < 0) - return ret; + retval = lan78xx_wait_eeprom(dev); + if (retval < 0) + goto exit; ret = lan78xx_read_reg(dev, E2P_DATA, &val); - if (unlikely(ret < 0)) - return -EIO; + if (unlikely(ret < 0)) { + retval = -EIO; + goto exit; + } data[i] = val & 0xFF; offset++; } - return 0; + retval = 0; +exit: + if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) + ret = lan78xx_write_reg(dev, HW_CFG, saved); + + return retval; } static int lan78xx_read_eeprom(struct lan78xx_net *dev, u32 offset, @@ -509,44 +530,67 @@ static int lan78xx_write_raw_eeprom(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { u32 val; + u32 saved; int i, ret; + int retval; - ret = lan78xx_eeprom_confirm_not_busy(dev); - if (ret) - return ret; + /* depends on chip, some EEPROM pins are muxed with LED function. + * disable & restore LED function to access EEPROM. + */ + ret = lan78xx_read_reg(dev, HW_CFG, &val); + saved = val; + if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) { + val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_); + ret = lan78xx_write_reg(dev, HW_CFG, val); + } + + retval = lan78xx_eeprom_confirm_not_busy(dev); + if (retval) + goto exit; /* Issue write/erase enable command */ val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_EWEN_; ret = lan78xx_write_reg(dev, E2P_CMD, val); - if (unlikely(ret < 0)) - return -EIO; + if (unlikely(ret < 0)) { + retval = -EIO; + goto exit; + } - ret = lan78xx_wait_eeprom(dev); - if (ret < 0) - return ret; + retval = lan78xx_wait_eeprom(dev); + if (retval < 0) + goto exit; for (i = 0; i < length; i++) { /* Fill data register */ val = data[i]; ret = lan78xx_write_reg(dev, E2P_DATA, val); - if (ret < 0) - return ret; + if (ret < 0) { + retval = -EIO; + goto exit; + } /* Send "write" command */ val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_WRITE_; val |= (offset & E2P_CMD_EPC_ADDR_MASK_); ret = lan78xx_write_reg(dev, E2P_CMD, val); - if (ret < 0) - return ret; + if (ret < 0) { + retval = -EIO; + goto exit; + } - ret = lan78xx_wait_eeprom(dev); - if (ret < 0) - return ret; + retval = lan78xx_wait_eeprom(dev); + if (retval < 0) + goto exit; offset++; } - return 0; + retval = 0; +exit: + if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) + ret = lan78xx_write_reg(dev, HW_CFG, saved); + + return retval; } static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, @@ -904,7 +948,6 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) if (!phydev->link && dev->link_on) { dev->link_on = false; - netif_carrier_off(dev->net); /* reset MAC */ ret = lan78xx_read_reg(dev, MAC_CR, &buf); @@ -914,6 +957,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) ret = lan78xx_write_reg(dev, MAC_CR, buf); if (unlikely(ret < 0)) return -EIO; + + phy_mac_interrupt(phydev, 0); } else if (phydev->link && !dev->link_on) { dev->link_on = true; @@ -953,7 +998,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) ethtool_cmd_speed(&ecmd), ecmd.duplex, ladv, radv); ret = lan78xx_update_flowcontrol(dev, ecmd.duplex, ladv, radv); - netif_carrier_on(dev->net); + phy_mac_interrupt(phydev, 1); } return ret; @@ -1495,7 +1540,6 @@ done: static int lan78xx_mdio_init(struct lan78xx_net *dev) { int ret; - int i; dev->mdiobus = mdiobus_alloc(); if (!dev->mdiobus) { @@ -1511,10 +1555,6 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev) snprintf(dev->mdiobus->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); - /* handle our own interrupt */ - for (i = 0; i < PHY_MAX_ADDR; i++) - dev->mdiobus->irq[i] = PHY_IGNORE_INTERRUPT; - switch (dev->devid & ID_REV_CHIP_ID_MASK_) { case 0x78000000: case 0x78500000: @@ -1558,6 +1598,16 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) return -EIO; } + /* Enable PHY interrupts. + * We handle our own interrupt + */ + ret = phy_read(phydev, LAN88XX_INT_STS); + ret = phy_write(phydev, LAN88XX_INT_MASK, + LAN88XX_INT_MASK_MDINTPIN_EN_ | + LAN88XX_INT_MASK_LINK_CHANGE_); + + phydev->irq = PHY_IGNORE_INTERRUPT; + ret = phy_connect_direct(dev->net, phydev, lan78xx_link_status_change, PHY_INTERFACE_MODE_GMII); @@ -1580,14 +1630,6 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) SUPPORTED_Pause | SUPPORTED_Asym_Pause); genphy_config_aneg(phydev); - /* Workaround to enable PHY interrupt. - * phy_start_interrupts() is API for requesting and enabling - * PHY interrupt. However, USB-to-Ethernet device can't use - * request_irq() called in phy_start_interrupts(). - * Set PHY to PHY_HALTED and call phy_start() - * to make a call to phy_enable_interrupts() - */ - phy_stop(phydev); phy_start(phydev); netif_dbg(dev, ifup, dev->net, "phy initialised successfully"); @@ -2221,7 +2263,9 @@ netdev_tx_t lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net) if (skb2) { skb_queue_tail(&dev->txq_pend, skb2); - if (skb_queue_len(&dev->txq_pend) > 10) + /* throttle TX patch at slower than SUPER SPEED USB */ + if ((dev->udev->speed < USB_SPEED_SUPER) && + (skb_queue_len(&dev->txq_pend) > 10)) netif_stop_queue(net); } else { netif_dbg(dev, tx_err, dev->net, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 2d88c799d2ac..65439188c582 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -73,7 +73,7 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static int vxlan_net_id; static struct rtnl_link_ops vxlan_link_ops; -static const u8 all_zeros_mac[ETH_ALEN]; +static const u8 all_zeros_mac[ETH_ALEN + 2]; static int vxlan_sock_add(struct vxlan_dev *vxlan); @@ -1985,11 +1985,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, vxlan->cfg.port_max, true); if (info) { - if (info->key.tun_flags & TUNNEL_CSUM) - flags |= VXLAN_F_UDP_CSUM; - else - flags &= ~VXLAN_F_UDP_CSUM; - ttl = info->key.ttl; tos = info->key.tos; @@ -2004,8 +1999,15 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto drop; sk = vxlan->vn4_sock->sock->sk; - if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)) - df = htons(IP_DF); + if (info) { + if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + + if (info->key.tun_flags & TUNNEL_CSUM) + flags |= VXLAN_F_UDP_CSUM; + else + flags &= ~VXLAN_F_UDP_CSUM; + } memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0; @@ -2101,6 +2103,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; } + if (info) { + if (info->key.tun_flags & TUNNEL_CSUM) + flags &= ~VXLAN_F_UDP_ZERO_CSUM6_TX; + else + flags |= VXLAN_F_UDP_ZERO_CSUM6_TX; + } + ttl = ttl ? : ip6_dst_hoplimit(ndst); err = vxlan6_xmit_skb(ndst, sk, skb, dev, &saddr, &dst->sin6.sin6_addr, 0, ttl, src_port, dst_port, htonl(vni << 8), md, diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c index a7afdeee698c..73fb4232f9f2 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom.c +++ b/drivers/net/wireless/ath/ath9k/eeprom.c @@ -150,18 +150,18 @@ int ath9k_hw_nvram_swap_data(struct ath_hw *ah, bool *swap_needed, int size) return -EIO; } - if (magic == AR5416_EEPROM_MAGIC) { - *swap_needed = false; - } else if (swab16(magic) == AR5416_EEPROM_MAGIC) { + *swap_needed = false; + if (swab16(magic) == AR5416_EEPROM_MAGIC) { if (ah->ah_flags & AH_NO_EEP_SWAP) { ath_info(common, "Ignoring endianness difference in EEPROM magic bytes.\n"); - - *swap_needed = false; } else { *swap_needed = true; } - } else { + } else if (magic != AR5416_EEPROM_MAGIC) { + if (ath9k_hw_use_flash(ah)) + return 0; + ath_err(common, "Invalid EEPROM Magic (0x%04x).\n", magic); return -EINVAL; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index 53637399bb99..b98db8a0a069 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -879,11 +879,24 @@ int brcmf_sdiod_abort(struct brcmf_sdio_dev *sdiodev, uint fn) return 0; } -static void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev) +void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev) { + struct sdio_func *func; + struct mmc_host *host; + uint max_blocks; uint nents; int err; + func = sdiodev->func[2]; + host = func->card->host; + sdiodev->sg_support = host->max_segs > 1; + max_blocks = min_t(uint, host->max_blk_count, 511u); + sdiodev->max_request_size = min_t(uint, host->max_req_size, + max_blocks * func->cur_blksize); + sdiodev->max_segment_count = min_t(uint, host->max_segs, + SG_MAX_SINGLE_ALLOC); + sdiodev->max_segment_size = host->max_seg_size; + if (!sdiodev->sg_support) return; @@ -1021,9 +1034,6 @@ static void brcmf_sdiod_host_fixup(struct mmc_host *host) static int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev) { - struct sdio_func *func; - struct mmc_host *host; - uint max_blocks; int ret = 0; sdiodev->num_funcs = 2; @@ -1054,26 +1064,6 @@ static int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev) goto out; } - /* - * determine host related variables after brcmf_sdiod_probe() - * as func->cur_blksize is properly set and F2 init has been - * completed successfully. - */ - func = sdiodev->func[2]; - host = func->card->host; - sdiodev->sg_support = host->max_segs > 1; - max_blocks = min_t(uint, host->max_blk_count, 511u); - sdiodev->max_request_size = min_t(uint, host->max_req_size, - max_blocks * func->cur_blksize); - sdiodev->max_segment_count = min_t(uint, host->max_segs, - SG_MAX_SINGLE_ALLOC); - sdiodev->max_segment_size = host->max_seg_size; - - /* allocate scatter-gather table. sg support - * will be disabled upon allocation failure. - */ - brcmf_sdiod_sgtable_alloc(sdiodev); - ret = brcmf_sdiod_freezer_attach(sdiodev); if (ret) goto out; @@ -1084,7 +1074,7 @@ static int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev) ret = -ENODEV; goto out; } - brcmf_sdiod_host_fixup(host); + brcmf_sdiod_host_fixup(sdiodev->func[2]->card->host); out: if (ret) brcmf_sdiod_remove(sdiodev); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c index 4265b50faa98..cfee477a6eb1 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/netdevice.h> +#include <linux/module.h> #include <brcmu_wifi.h> #include <brcmu_utils.h> #include "core.h" diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index dd6614332836..a14d9d9da094 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -4114,6 +4114,11 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev) goto fail; } + /* allocate scatter-gather table. sg support + * will be disabled upon allocation failure. + */ + brcmf_sdiod_sgtable_alloc(bus->sdiodev); + /* Query the F2 block size, set roundup accordingly */ bus->blocksize = bus->sdiodev->func[2]->cur_blksize; bus->roundup = min(max_roundup, bus->blocksize); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h index 5ec7a6d87672..23f223150cef 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h @@ -342,6 +342,7 @@ int brcmf_sdiod_ramrw(struct brcmf_sdio_dev *sdiodev, bool write, u32 address, /* Issue an abort to the specified function */ int brcmf_sdiod_abort(struct brcmf_sdio_dev *sdiodev, uint fn); +void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev); void brcmf_sdiod_change_state(struct brcmf_sdio_dev *sdiodev, enum brcmf_sdiod_state state); #ifdef CONFIG_PM_SLEEP diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-7000.c b/drivers/net/wireless/intel/iwlwifi/iwl-7000.c index e60cf141ed79..fa41a5e1c890 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-7000.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-7000.c @@ -74,16 +74,19 @@ #define IWL7260_UCODE_API_MAX 17 #define IWL7265_UCODE_API_MAX 17 #define IWL7265D_UCODE_API_MAX 20 +#define IWL3168_UCODE_API_MAX 20 /* Oldest version we won't warn about */ #define IWL7260_UCODE_API_OK 13 #define IWL7265_UCODE_API_OK 13 #define IWL7265D_UCODE_API_OK 13 +#define IWL3168_UCODE_API_OK 20 /* Lowest firmware API version supported */ #define IWL7260_UCODE_API_MIN 13 #define IWL7265_UCODE_API_MIN 13 #define IWL7265D_UCODE_API_MIN 13 +#define IWL3168_UCODE_API_MIN 20 /* NVM versions */ #define IWL7260_NVM_VERSION 0x0a1d @@ -92,6 +95,8 @@ #define IWL3160_TX_POWER_VERSION 0xffff /* meaningless */ #define IWL3165_NVM_VERSION 0x709 #define IWL3165_TX_POWER_VERSION 0xffff /* meaningless */ +#define IWL3168_NVM_VERSION 0xd01 +#define IWL3168_TX_POWER_VERSION 0xffff /* meaningless */ #define IWL7265_NVM_VERSION 0x0a1d #define IWL7265_TX_POWER_VERSION 0xffff /* meaningless */ #define IWL7265D_NVM_VERSION 0x0c11 @@ -109,6 +114,9 @@ #define IWL3160_FW_PRE "iwlwifi-3160-" #define IWL3160_MODULE_FIRMWARE(api) IWL3160_FW_PRE __stringify(api) ".ucode" +#define IWL3168_FW_PRE "iwlwifi-3168-" +#define IWL3168_MODULE_FIRMWARE(api) IWL3168_FW_PRE __stringify(api) ".ucode" + #define IWL7265_FW_PRE "iwlwifi-7265-" #define IWL7265_MODULE_FIRMWARE(api) IWL7265_FW_PRE __stringify(api) ".ucode" @@ -180,6 +188,12 @@ static const struct iwl_ht_params iwl7000_ht_params = { .ucode_api_ok = IWL7265_UCODE_API_OK, \ .ucode_api_min = IWL7265_UCODE_API_MIN +#define IWL_DEVICE_3008 \ + IWL_DEVICE_7000_COMMON, \ + .ucode_api_max = IWL3168_UCODE_API_MAX, \ + .ucode_api_ok = IWL3168_UCODE_API_OK, \ + .ucode_api_min = IWL3168_UCODE_API_MIN + #define IWL_DEVICE_7005D \ IWL_DEVICE_7000_COMMON, \ .ucode_api_max = IWL7265D_UCODE_API_MAX, \ @@ -299,11 +313,11 @@ const struct iwl_cfg iwl3165_2ac_cfg = { const struct iwl_cfg iwl3168_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 3168", - .fw_name_pre = IWL7265D_FW_PRE, - IWL_DEVICE_7000, + .fw_name_pre = IWL3168_FW_PRE, + IWL_DEVICE_3008, .ht_params = &iwl7000_ht_params, - .nvm_ver = IWL3165_NVM_VERSION, - .nvm_calib_ver = IWL3165_TX_POWER_VERSION, + .nvm_ver = IWL3168_NVM_VERSION, + .nvm_calib_ver = IWL3168_TX_POWER_VERSION, .pwr_tx_backoffs = iwl7265_pwr_tx_backoffs, .dccm_len = IWL7265_DCCM_LEN, }; @@ -376,5 +390,6 @@ const struct iwl_cfg iwl7265d_n_cfg = { MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); +MODULE_FIRMWARE(IWL3168_MODULE_FIRMWARE(IWL3168_UCODE_API_OK)); MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7265_UCODE_API_OK)); MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7265D_UCODE_API_OK)); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h index 0036d18334af..ba3f0bbddde8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h @@ -510,6 +510,9 @@ struct iwl_mvm_tx_resp { * @scd_ssn: the index of the last contiguously sent packet * @txed: number of Txed frames in this batch * @txed_2_done: number of Acked frames in this batch + * @reduced_txp: power reduced according to TPC. This is the actual value and + * not a copy from the LQ command. Thus, if not the first rate was used + * for Tx-ing then this value will be set to 0 by FW. */ struct iwl_mvm_ba_notif { __le32 sta_addr_lo32; @@ -524,7 +527,8 @@ struct iwl_mvm_ba_notif { __le16 scd_ssn; u8 txed; u8 txed_2_done; - __le16 reserved1; + u8 reduced_txp; + u8 reserved1; } __packed; /* diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 7bb6fd0e4391..94caa88df442 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -2,6 +2,7 @@ * * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License as @@ -724,14 +725,28 @@ static int _rs_collect_tx_data(struct iwl_mvm *mvm, return 0; } -static int rs_collect_tx_data(struct iwl_mvm *mvm, - struct iwl_lq_sta *lq_sta, - struct iwl_scale_tbl_info *tbl, - int scale_index, int attempts, int successes, - u8 reduced_txp) +static int rs_collect_tpc_data(struct iwl_mvm *mvm, + struct iwl_lq_sta *lq_sta, + struct iwl_scale_tbl_info *tbl, + int scale_index, int attempts, int successes, + u8 reduced_txp) +{ + struct iwl_rate_scale_data *window = NULL; + + if (WARN_ON_ONCE(reduced_txp > TPC_MAX_REDUCTION)) + return -EINVAL; + + window = &tbl->tpc_win[reduced_txp]; + return _rs_collect_tx_data(mvm, tbl, scale_index, attempts, successes, + window); +} + +static int rs_collect_tlc_data(struct iwl_mvm *mvm, + struct iwl_lq_sta *lq_sta, + struct iwl_scale_tbl_info *tbl, + int scale_index, int attempts, int successes) { struct iwl_rate_scale_data *window = NULL; - int ret; if (scale_index < 0 || scale_index >= IWL_RATE_COUNT) return -EINVAL; @@ -745,16 +760,6 @@ static int rs_collect_tx_data(struct iwl_mvm *mvm, /* Select window for current tx bit rate */ window = &(tbl->win[scale_index]); - - ret = _rs_collect_tx_data(mvm, tbl, scale_index, attempts, successes, - window); - if (ret) - return ret; - - if (WARN_ON_ONCE(reduced_txp > TPC_MAX_REDUCTION)) - return -EINVAL; - - window = &tbl->tpc_win[reduced_txp]; return _rs_collect_tx_data(mvm, tbl, scale_index, attempts, successes, window); } @@ -1301,17 +1306,30 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, * first index into rate scale table. */ if (info->flags & IEEE80211_TX_STAT_AMPDU) { - /* ampdu_ack_len = 0 marks no BA was received. In this case - * treat it as a single frame loss as we don't want the success - * ratio to dip too quickly because a BA wasn't received + rs_collect_tpc_data(mvm, lq_sta, curr_tbl, lq_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len, + reduced_txp); + + /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat + * it as a single frame loss as we don't want the success ratio + * to dip too quickly because a BA wasn't received. + * For TPC, there's no need for this optimisation since we want + * to recover very quickly from a bad power reduction and, + * therefore we'd like the success ratio to get an immediate hit + * when failing to get a BA, so we'd switch back to a lower or + * zero power reduction. When FW transmits agg with a rate + * different from the initial rate, it will not use reduced txp + * and will send BA notification twice (one empty with reduced + * txp equal to the value from LQ and one with reduced txp 0). + * We need to update counters for each txp level accordingly. */ if (info->status.ampdu_ack_len == 0) info->status.ampdu_len = 1; - rs_collect_tx_data(mvm, lq_sta, curr_tbl, lq_rate.index, - info->status.ampdu_len, - info->status.ampdu_ack_len, - reduced_txp); + rs_collect_tlc_data(mvm, lq_sta, curr_tbl, lq_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len); /* Update success/fail counts if not searching for new mode */ if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { @@ -1344,9 +1362,13 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, else continue; - rs_collect_tx_data(mvm, lq_sta, tmp_tbl, lq_rate.index, - 1, i < retries ? 0 : legacy_success, - reduced_txp); + rs_collect_tpc_data(mvm, lq_sta, tmp_tbl, + lq_rate.index, 1, + i < retries ? 0 : legacy_success, + reduced_txp); + rs_collect_tlc_data(mvm, lq_sta, tmp_tbl, + lq_rate.index, 1, + i < retries ? 0 : legacy_success); } /* Update success/fail counts if not searching for new mode */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 8bf48a7d0f4e..0914ec2fd574 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1029,7 +1029,6 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); mvmsta->tid_data[tid].rate_n_flags = le32_to_cpu(tx_resp->initial_rate); - mvmsta->tid_data[tid].reduced_tpc = tx_resp->reduced_tpc; mvmsta->tid_data[tid].tx_time = le16_to_cpu(tx_resp->wireless_media_time); } @@ -1060,7 +1059,7 @@ static void iwl_mvm_tx_info_from_ba_notif(struct ieee80211_tx_info *info, /* TODO: not accounted if the whole A-MPDU failed */ info->status.tx_time = tid_data->tx_time; info->status.status_driver_data[0] = - (void *)(uintptr_t)tid_data->reduced_tpc; + (void *)(uintptr_t)ba_notif->reduced_txp; info->status.status_driver_data[1] = (void *)(uintptr_t)tid_data->rate_n_flags; } @@ -1133,6 +1132,8 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) scd_flow, ba_resp_scd_ssn, ba_notif->txed, ba_notif->txed_2_done); + IWL_DEBUG_TX_REPLY(mvm, "reduced txp from ba notif %d\n", + ba_notif->reduced_txp); tid_data->next_reclaimed = ba_resp_scd_ssn; iwl_mvm_check_ratid_empty(mvm, sta, tid); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 6261a68cae90..00335ea6b3eb 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -378,7 +378,10 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x3165, 0x8110, iwl3165_2ac_cfg)}, /* 3168 Series */ + {IWL_PCI_DEVICE(0x24FB, 0x2010, iwl3168_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FB, 0x2110, iwl3168_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FB, 0x2050, iwl3168_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FB, 0x2150, iwl3168_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FB, 0x0000, iwl3168_2ac_cfg)}, /* 7265 Series */ @@ -475,6 +478,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x24F3, 0x0000, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x0010, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x8010, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x0810, iwl8265_2ac_cfg)}, /* 9000 Series */ {IWL_PCI_DEVICE(0x9DF0, 0x2A10, iwl5165_2ac_cfg)}, diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index c32889a1e39c..a28414c50edf 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -991,7 +991,8 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, goto nla_put_failure; } - if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER, ETH_ALEN, hdr->addr2)) + if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER, + ETH_ALEN, data->addresses[1].addr)) goto nla_put_failure; /* We get the skb->data */ @@ -2736,7 +2737,7 @@ static struct mac80211_hwsim_data *get_hwsim_data_ref_from_addr(const u8 *addr) spin_lock_bh(&hwsim_radio_lock); list_for_each_entry(data, &hwsim_radios, list) { - if (mac80211_hwsim_addr_match(data, addr)) { + if (memcmp(data->addresses[1].addr, addr, ETH_ALEN) == 0) { _found = true; break; } diff --git a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c index 9a3966cd6fbe..155f343981fe 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c @@ -273,8 +273,10 @@ static void rt2400pci_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field32(®, RXCSR0_DROP_CONTROL, !(filter_flags & FIF_CONTROL)); - rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, RXCSR0_DROP_TODS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field32(®, RXCSR0_DROP_VERSION_ERROR, 1); rt2x00mmio_register_write(rt2x00dev, RXCSR0, reg); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c index 1a6740b4d396..2553cdd74066 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c @@ -274,8 +274,10 @@ static void rt2500pci_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field32(®, RXCSR0_DROP_CONTROL, !(filter_flags & FIF_CONTROL)); - rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, RXCSR0_DROP_TODS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field32(®, RXCSR0_DROP_VERSION_ERROR, 1); rt2x00_set_field32(®, RXCSR0_DROP_MCAST, diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c index d26018f30b7d..2d64611de300 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c @@ -437,8 +437,10 @@ static void rt2500usb_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field16(®, TXRX_CSR2_DROP_CONTROL, !(filter_flags & FIF_CONTROL)); - rt2x00_set_field16(®, TXRX_CSR2_DROP_NOT_TO_ME, 1); + rt2x00_set_field16(®, TXRX_CSR2_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field16(®, TXRX_CSR2_DROP_TODS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field16(®, TXRX_CSR2_DROP_VERSION_ERROR, 1); rt2x00_set_field16(®, TXRX_CSR2_DROP_MULTICAST, diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 9733b31a780d..a26afcab03ed 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -1490,7 +1490,8 @@ void rt2800_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_FCSFAIL)); rt2x00_set_field32(®, RX_FILTER_CFG_DROP_PHY_ERROR, !(filter_flags & FIF_PLCPFAIL)); - rt2x00_set_field32(®, RX_FILTER_CFG_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, RX_FILTER_CFG_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, RX_FILTER_CFG_DROP_NOT_MY_BSSD, 0); rt2x00_set_field32(®, RX_FILTER_CFG_DROP_VER_ERROR, 1); rt2x00_set_field32(®, RX_FILTER_CFG_DROP_MULTICAST, diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h index 3282ddb766f4..26427140a963 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h @@ -669,6 +669,7 @@ enum rt2x00_state_flags { CONFIG_POWERSAVING, CONFIG_HT_DISABLED, CONFIG_QOS_DISABLED, + CONFIG_MONITORING, /* * Mark we currently are sequentially reading TX_STA_FIFO register diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00config.c b/drivers/net/wireless/ralink/rt2x00/rt2x00config.c index 7e8bb1198ae9..6a1f508d472f 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00config.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00config.c @@ -277,6 +277,11 @@ void rt2x00lib_config(struct rt2x00_dev *rt2x00dev, else clear_bit(CONFIG_POWERSAVING, &rt2x00dev->flags); + if (conf->flags & IEEE80211_CONF_MONITOR) + set_bit(CONFIG_MONITORING, &rt2x00dev->flags); + else + clear_bit(CONFIG_MONITORING, &rt2x00dev->flags); + rt2x00dev->curr_band = conf->chandef.chan->band; rt2x00dev->curr_freq = conf->chandef.chan->center_freq; rt2x00dev->tx_power = conf->power_level; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c index 3c26ee65a415..13da95a24cf7 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c @@ -385,11 +385,6 @@ void rt2x00mac_configure_filter(struct ieee80211_hw *hw, *total_flags |= FIF_PSPOLL; } - /* - * Check if there is any work left for us. - */ - if (rt2x00dev->packet_filter == *total_flags) - return; rt2x00dev->packet_filter = *total_flags; rt2x00dev->ops->lib->config_filter(rt2x00dev, *total_flags); diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.c b/drivers/net/wireless/ralink/rt2x00/rt61pci.c index c0e730ea1b69..24a3436ef952 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt61pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.c @@ -530,8 +530,10 @@ static void rt61pci_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field32(®, TXRX_CSR0_DROP_CONTROL, !(filter_flags & (FIF_CONTROL | FIF_PSPOLL))); - rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, TXRX_CSR0_DROP_TO_DS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field32(®, TXRX_CSR0_DROP_VERSION_ERROR, 1); rt2x00_set_field32(®, TXRX_CSR0_DROP_MULTICAST, diff --git a/drivers/net/wireless/ralink/rt2x00/rt73usb.c b/drivers/net/wireless/ralink/rt2x00/rt73usb.c index 7081e13b4fd6..7bbc86931168 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt73usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt73usb.c @@ -480,8 +480,10 @@ static void rt73usb_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field32(®, TXRX_CSR0_DROP_CONTROL, !(filter_flags & (FIF_CONTROL | FIF_PSPOLL))); - rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, TXRX_CSR0_DROP_TO_DS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field32(®, TXRX_CSR0_DROP_VERSION_ERROR, 1); rt2x00_set_field32(®, TXRX_CSR0_DROP_MULTICAST, diff --git a/drivers/net/wireless/realtek/rtlwifi/regd.c b/drivers/net/wireless/realtek/rtlwifi/regd.c index a62bf0a65c32..5be34118e0af 100644 --- a/drivers/net/wireless/realtek/rtlwifi/regd.c +++ b/drivers/net/wireless/realtek/rtlwifi/regd.c @@ -351,7 +351,6 @@ static const struct ieee80211_regdomain *_rtl_regdomain_select( case COUNTRY_CODE_SPAIN: case COUNTRY_CODE_FRANCE: case COUNTRY_CODE_ISRAEL: - case COUNTRY_CODE_WORLD_WIDE_13: return &rtl_regdom_12_13; case COUNTRY_CODE_MKK: case COUNTRY_CODE_MKK1: @@ -360,6 +359,7 @@ static const struct ieee80211_regdomain *_rtl_regdomain_select( return &rtl_regdom_14_60_64; case COUNTRY_CODE_GLOBAL_DOMAIN: return &rtl_regdom_14; + case COUNTRY_CODE_WORLD_WIDE_13: case COUNTRY_CODE_WORLD_WIDE_13_5G_ALL: return &rtl_regdom_12_13_5g_all; default: diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index d6abf191122a..96ccd4e943db 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -364,6 +364,7 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) RING_IDX cons, prod; unsigned short id; struct sk_buff *skb; + bool more_to_do; BUG_ON(!netif_carrier_ok(queue->info->netdev)); @@ -398,18 +399,8 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) queue->tx.rsp_cons = prod; - /* - * Set a new event, then check for race with update of tx_cons. - * Note that it is essential to schedule a callback, no matter - * how few buffers are pending. Even if there is space in the - * transmit ring, higher layers may be blocked because too much - * data is outstanding: in such cases notification from Xen is - * likely to be the only kick that we'll get. - */ - queue->tx.sring->rsp_event = - prod + ((queue->tx.sring->req_prod - prod) >> 1) + 1; - mb(); /* update shared area */ - } while ((cons == prod) && (prod != queue->tx.sring->rsp_prod)); + RING_FINAL_CHECK_FOR_RESPONSES(&queue->tx, more_to_do); + } while (more_to_do); xennet_maybe_wake_tx(queue); } diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 8ebfcaae3f5a..9edf7eb7d17c 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -1277,10 +1277,12 @@ static ssize_t mode_show(struct device *dev, device_lock(dev); claim = ndns->claim; - if (pmem_should_map_pages(dev) || (claim && is_nd_pfn(claim))) - mode = "memory"; - else if (claim && is_nd_btt(claim)) + if (claim && is_nd_btt(claim)) mode = "safe"; + else if (claim && is_nd_pfn(claim)) + mode = "memory"; + else if (!claim && pmem_should_map_pages(dev)) + mode = "memory"; else mode = "raw"; rc = sprintf(buf, "%s\n", mode); diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 0cc9048b86e2..ae81a2f1da50 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -301,10 +301,8 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn) switch (le32_to_cpu(pfn_sb->mode)) { case PFN_MODE_RAM: - break; case PFN_MODE_PMEM: - /* TODO: allocate from PMEM support */ - return -ENOTTY; + break; default: return -ENXIO; } diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 86829f8064a6..5648317d355f 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -143,11 +143,31 @@ int of_mdio_parse_addr(struct device *dev, const struct device_node *np) } EXPORT_SYMBOL(of_mdio_parse_addr); +/* The following is a list of PHY compatible strings which appear in + * some DTBs. The compatible string is never matched against a PHY + * driver, so is pointless. We only expect devices which are not PHYs + * to have a compatible string, so they can be matched to an MDIO + * driver. Encourage users to upgrade their DT blobs to remove these. + */ +static const struct of_device_id whitelist_phys[] = { + { .compatible = "brcm,40nm-ephy" }, + { .compatible = "marvell,88E1111", }, + { .compatible = "marvell,88e1116", }, + { .compatible = "marvell,88e1118", }, + { .compatible = "marvell,88e1149r", }, + { .compatible = "marvell,88e1310", }, + { .compatible = "marvell,88E1510", }, + { .compatible = "marvell,88E1514", }, + { .compatible = "moxa,moxart-rtl8201cp", }, + {} +}; + /* * Return true if the child node is for a phy. It must either: * o Compatible string of "ethernet-phy-idX.X" * o Compatible string of "ethernet-phy-ieee802.3-c45" * o Compatible string of "ethernet-phy-ieee802.3-c22" + * o In the white list above (and issue a warning) * o No compatibility string * * A device which is not a phy is expected to have a compatible string @@ -166,6 +186,13 @@ static bool of_mdiobus_child_is_phy(struct device_node *child) if (of_device_is_compatible(child, "ethernet-phy-ieee802.3-c22")) return true; + if (of_match_node(whitelist_phys, child)) { + pr_warn(FW_WARN + "%s: Whitelisted compatible string. Please remove\n", + child->full_name); + return true; + } + if (!of_find_property(child, "compatible", NULL)) return true; @@ -256,11 +283,19 @@ static int of_phy_match(struct device *dev, void *phy_np) struct phy_device *of_phy_find_device(struct device_node *phy_np) { struct device *d; + struct mdio_device *mdiodev; + if (!phy_np) return NULL; d = bus_find_device(&mdio_bus_type, NULL, phy_np, of_phy_match); - return d ? to_phy_device(d) : NULL; + if (d) { + mdiodev = to_mdio_device(d); + if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) + return to_phy_device(d); + } + + return NULL; } EXPORT_SYMBOL(of_phy_find_device); diff --git a/drivers/ptp/ptp_ixp46x.c b/drivers/ptp/ptp_ixp46x.c index 934c139916c6..ee4f183ef9ee 100644 --- a/drivers/ptp/ptp_ixp46x.c +++ b/drivers/ptp/ptp_ixp46x.c @@ -178,7 +178,6 @@ static int ptp_ixp_adjtime(struct ptp_clock_info *ptp, s64 delta) static int ptp_ixp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; - u32 remainder; unsigned long flags; struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps); struct ixp46x_ts_regs *regs = ixp_clock->regs; @@ -189,8 +188,7 @@ static int ptp_ixp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) spin_unlock_irqrestore(®ister_lock, flags); - ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder); - ts->tv_nsec = remainder; + *ts = ns_to_timespec64(ns); return 0; } @@ -202,8 +200,7 @@ static int ptp_ixp_settime(struct ptp_clock_info *ptp, struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps); struct ixp46x_ts_regs *regs = ixp_clock->regs; - ns = ts->tv_sec * 1000000000ULL; - ns += ts->tv_nsec; + ns = timespec64_to_ns(ts); spin_lock_irqsave(®ister_lock, flags); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 503ab8b46c0b..5e820674432c 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1261,7 +1261,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma) } sfp->mmap_called = 1; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_private_data = sfp; vma->vm_ops = &sg_mmap_vm_ops; return 0; diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index cde5ff7529eb..d1a750760cf3 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -613,9 +613,10 @@ out: return err; } -static int ssb_bus_register(struct ssb_bus *bus, - ssb_invariants_func_t get_invariants, - unsigned long baseaddr) +static int __maybe_unused +ssb_bus_register(struct ssb_bus *bus, + ssb_invariants_func_t get_invariants, + unsigned long baseaddr) { int err; diff --git a/fs/block_dev.c b/fs/block_dev.c index 7b9cd49622b1..afb437484362 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1736,37 +1736,13 @@ static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL); } -static void blkdev_vm_open(struct vm_area_struct *vma) -{ - struct inode *bd_inode = bdev_file_inode(vma->vm_file); - struct block_device *bdev = I_BDEV(bd_inode); - - inode_lock(bd_inode); - bdev->bd_map_count++; - inode_unlock(bd_inode); -} - -static void blkdev_vm_close(struct vm_area_struct *vma) -{ - struct inode *bd_inode = bdev_file_inode(vma->vm_file); - struct block_device *bdev = I_BDEV(bd_inode); - - inode_lock(bd_inode); - bdev->bd_map_count--; - inode_unlock(bd_inode); -} - static const struct vm_operations_struct blkdev_dax_vm_ops = { - .open = blkdev_vm_open, - .close = blkdev_vm_close, .fault = blkdev_dax_fault, .pmd_fault = blkdev_dax_pmd_fault, .pfn_mkwrite = blkdev_dax_fault, }; static const struct vm_operations_struct blkdev_default_vm_ops = { - .open = blkdev_vm_open, - .close = blkdev_vm_close, .fault = filemap_fault, .map_pages = filemap_map_pages, }; @@ -1774,18 +1750,14 @@ static const struct vm_operations_struct blkdev_default_vm_ops = { static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *bd_inode = bdev_file_inode(file); - struct block_device *bdev = I_BDEV(bd_inode); file_accessed(file); - inode_lock(bd_inode); - bdev->bd_map_count++; if (IS_DAX(bd_inode)) { vma->vm_ops = &blkdev_dax_vm_ops; vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; } else { vma->vm_ops = &blkdev_default_vm_ops; } - inode_unlock(bd_inode); return 0; } diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index a5b8eb69a8f4..6402eaf8ab95 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1261,6 +1261,9 @@ COMPATIBLE_IOCTL(HCIUNBLOCKADDR) COMPATIBLE_IOCTL(HCIINQUIRY) COMPATIBLE_IOCTL(HCIUARTSETPROTO) COMPATIBLE_IOCTL(HCIUARTGETPROTO) +COMPATIBLE_IOCTL(HCIUARTGETDEVICE) +COMPATIBLE_IOCTL(HCIUARTSETFLAGS) +COMPATIBLE_IOCTL(HCIUARTGETFLAGS) COMPATIBLE_IOCTL(RFCOMMCREATEDEV) COMPATIBLE_IOCTL(RFCOMMRELEASEDEV) COMPATIBLE_IOCTL(RFCOMMGETDEVLIST) @@ -58,6 +58,26 @@ static void dax_unmap_atomic(struct block_device *bdev, blk_queue_exit(bdev->bd_queue); } +struct page *read_dax_sector(struct block_device *bdev, sector_t n) +{ + struct page *page = alloc_pages(GFP_KERNEL, 0); + struct blk_dax_ctl dax = { + .size = PAGE_SIZE, + .sector = n & ~((((int) PAGE_SIZE) / 512) - 1), + }; + long rc; + + if (!page) + return ERR_PTR(-ENOMEM); + + rc = dax_map_atomic(bdev, &dax); + if (rc < 0) + return ERR_PTR(rc); + memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE); + dax_unmap_atomic(bdev, &dax); + return page; +} + /* * dax_clear_blocks() is called from within transaction context from XFS, * and hence this means the stack from this point must follow GFP_NOFS diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 5bcd92d50e82..0cb1abd535e3 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1215,7 +1215,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task, hdr->pgio_mirror_idx + 1, &hdr->pgio_mirror_idx)) goto out_eagain; - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &hdr->lseg->pls_layout->plh_flags); pnfs_read_resend_pnfs(hdr); return task->tk_status; diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 29898a9550fa..eb370460ce20 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -412,7 +412,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, OP_ILLEGAL, GFP_NOIO); if (!fail_return) { if (ff_layout_has_available_ds(lseg)) - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lseg->pls_layout->plh_flags); else pnfs_error_mark_layout_for_return(ino, lseg); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index a3592cc34a20..482b6e94bb37 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -52,9 +52,7 @@ static DEFINE_SPINLOCK(pnfs_spinlock); */ static LIST_HEAD(pnfs_modules_tbl); -static int -pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, - enum pnfs_iomode iomode, bool sync); +static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo); /* Return the registered pnfs layout driver module matching given id */ static struct pnfs_layoutdriver_type * @@ -243,6 +241,8 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) { struct inode *inode = lo->plh_inode; + pnfs_layoutreturn_before_put_layout_hdr(lo); + if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) { if (!list_empty(&lo->plh_segs)) WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n"); @@ -345,58 +345,6 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo, rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq); } -/* Return true if layoutreturn is needed */ -static bool -pnfs_layout_need_return(struct pnfs_layout_hdr *lo, - struct pnfs_layout_segment *lseg) -{ - struct pnfs_layout_segment *s; - - if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) - return false; - - list_for_each_entry(s, &lo->plh_segs, pls_list) - if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) - return false; - - return true; -} - -static bool -pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) -{ - if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) - return false; - lo->plh_return_iomode = 0; - pnfs_get_layout_hdr(lo); - clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); - return true; -} - -static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, - struct pnfs_layout_hdr *lo, struct inode *inode) -{ - lo = lseg->pls_layout; - inode = lo->plh_inode; - - spin_lock(&inode->i_lock); - if (pnfs_layout_need_return(lo, lseg)) { - nfs4_stateid stateid; - enum pnfs_iomode iomode; - bool send; - - nfs4_stateid_copy(&stateid, &lo->plh_stateid); - iomode = lo->plh_return_iomode; - send = pnfs_prepare_layoutreturn(lo); - spin_unlock(&inode->i_lock); - if (send) { - /* Send an async layoutreturn so we dont deadlock */ - pnfs_send_layoutreturn(lo, &stateid, iomode, false); - } - } else - spin_unlock(&inode->i_lock); -} - void pnfs_put_lseg(struct pnfs_layout_segment *lseg) { @@ -410,15 +358,8 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) atomic_read(&lseg->pls_refcount), test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); - /* Handle the case where refcount != 1 */ - if (atomic_add_unless(&lseg->pls_refcount, -1, 1)) - return; - lo = lseg->pls_layout; inode = lo->plh_inode; - /* Do we need a layoutreturn? */ - if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) - pnfs_layoutreturn_before_put_lseg(lseg, lo, inode); if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) { if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) { @@ -937,6 +878,17 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); } +static bool +pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) +{ + if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + return false; + lo->plh_return_iomode = 0; + pnfs_get_layout_hdr(lo); + clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); + return true; +} + static int pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, enum pnfs_iomode iomode, bool sync) @@ -971,6 +923,48 @@ out: return status; } +/* Return true if layoutreturn is needed */ +static bool +pnfs_layout_need_return(struct pnfs_layout_hdr *lo) +{ + struct pnfs_layout_segment *s; + + if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) + return false; + + /* Defer layoutreturn until all lsegs are done */ + list_for_each_entry(s, &lo->plh_segs, pls_list) { + if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) + return false; + } + + return true; +} + +static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct inode *inode= lo->plh_inode; + + if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) + return; + spin_lock(&inode->i_lock); + if (pnfs_layout_need_return(lo)) { + nfs4_stateid stateid; + enum pnfs_iomode iomode; + bool send; + + nfs4_stateid_copy(&stateid, &lo->plh_stateid); + iomode = lo->plh_return_iomode; + send = pnfs_prepare_layoutreturn(lo); + spin_unlock(&inode->i_lock); + if (send) { + /* Send an async layoutreturn so we dont deadlock */ + pnfs_send_layoutreturn(lo, &stateid, iomode, false); + } + } else + spin_unlock(&inode->i_lock); +} + /* * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr * when the layout segment list is empty. @@ -1091,7 +1085,7 @@ bool pnfs_roc(struct inode *ino) nfs4_stateid_copy(&stateid, &lo->plh_stateid); /* always send layoutreturn if being marked so */ - if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + if (test_and_clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) layoutreturn = pnfs_prepare_layoutreturn(lo); @@ -1772,7 +1766,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, pnfs_set_plh_return_iomode(lo, return_range->iomode); if (!mark_lseg_invalid(lseg, tmp_list)) remaining++; - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } return remaining; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 9f4e2a47f4aa..1ac1db5f6dad 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -94,8 +94,8 @@ enum { NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */ NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */ NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */ - NFS_LAYOUT_RETURN, /* Return this layout ASAP */ - NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */ + NFS_LAYOUT_RETURN, /* layoutreturn in progress */ + NFS_LAYOUT_RETURN_REQUESTED, /* Return this layout ASAP */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ }; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index a3cc6d2fc896..a76b9ea7722e 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1254,15 +1254,15 @@ static const struct file_operations o2hb_debug_fops = { void o2hb_exit(void) { - kfree(o2hb_db_livenodes); - kfree(o2hb_db_liveregions); - kfree(o2hb_db_quorumregions); - kfree(o2hb_db_failedregions); debugfs_remove(o2hb_debug_failedregions); debugfs_remove(o2hb_debug_quorumregions); debugfs_remove(o2hb_debug_liveregions); debugfs_remove(o2hb_debug_livenodes); debugfs_remove(o2hb_debug_dir); + kfree(o2hb_db_livenodes); + kfree(o2hb_db_liveregions); + kfree(o2hb_db_quorumregions); + kfree(o2hb_db_failedregions); } static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir, @@ -1438,13 +1438,15 @@ static void o2hb_region_release(struct config_item *item) kfree(reg->hr_slots); - kfree(reg->hr_db_regnum); - kfree(reg->hr_db_livenodes); debugfs_remove(reg->hr_debug_livenodes); debugfs_remove(reg->hr_debug_regnum); debugfs_remove(reg->hr_debug_elapsed_time); debugfs_remove(reg->hr_debug_pinned); debugfs_remove(reg->hr_debug_dir); + kfree(reg->hr_db_livenodes); + kfree(reg->hr_db_regnum); + kfree(reg->hr_debug_elapsed_time); + kfree(reg->hr_debug_pinned); spin_lock(&o2hb_live_lock); list_del(®->hr_all_item); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 85d16c67c33e..fa95ab2d3674 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -259,23 +259,29 @@ static int do_maps_open(struct inode *inode, struct file *file, sizeof(struct proc_maps_private)); } -static pid_t pid_of_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, bool is_pid) +/* + * Indicate if the VMA is a stack for the given task; for + * /proc/PID/maps that is the stack of the main task. + */ +static int is_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, int is_pid) { - struct inode *inode = priv->inode; - struct task_struct *task; - pid_t ret = 0; + int stack = 0; + + if (is_pid) { + stack = vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; + } else { + struct inode *inode = priv->inode; + struct task_struct *task; - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) { - task = task_of_stack(task, vma, is_pid); + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) - ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); + stack = vma_is_stack_for_task(vma, task); + rcu_read_unlock(); } - rcu_read_unlock(); - - return ret; + return stack; } static void @@ -335,8 +341,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) name = arch_vma_name(vma); if (!name) { - pid_t tid; - if (!mm) { name = "[vdso]"; goto done; @@ -348,21 +352,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } - tid = pid_of_stack(priv, vma, is_pid); - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) { - name = "[stack]"; - } else { - /* Thread stack in /proc/PID/maps */ - seq_pad(m, ' '); - seq_printf(m, "[stack:%d]", tid); - } - } + if (is_stack(priv, vma, is_pid)) + name = "[stack]"; } done: @@ -1552,18 +1543,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { + pte_t huge_pte = huge_ptep_get(pte); struct numa_maps *md; struct page *page; - if (!pte_present(*pte)) + if (!pte_present(huge_pte)) return 0; - page = pte_page(*pte); + page = pte_page(huge_pte); if (!page) return 0; md = walk->private; - gather_stats(page, md, pte_dirty(*pte), 1); + gather_stats(page, md, pte_dirty(huge_pte), 1); return 0; } @@ -1617,19 +1609,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) seq_file_path(m, file, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { seq_puts(m, " heap"); - } else { - pid_t tid = pid_of_stack(proc_priv, vma, is_pid); - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) - seq_puts(m, " stack"); - else - seq_printf(m, " stack:%d", tid); - } + } else if (is_stack(proc_priv, vma, is_pid)) { + seq_puts(m, " stack"); } if (is_vm_hugetlb_page(vma)) diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index e0d64c92e4f6..faacb0c0d857 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -123,23 +123,26 @@ unsigned long task_statm(struct mm_struct *mm, return size; } -static pid_t pid_of_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, bool is_pid) +static int is_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, int is_pid) { - struct inode *inode = priv->inode; - struct task_struct *task; - pid_t ret = 0; - - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) { - task = task_of_stack(task, vma, is_pid); + struct mm_struct *mm = vma->vm_mm; + int stack = 0; + + if (is_pid) { + stack = vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack; + } else { + struct inode *inode = priv->inode; + struct task_struct *task; + + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) - ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); + stack = vma_is_stack_for_task(vma, task); + rcu_read_unlock(); } - rcu_read_unlock(); - - return ret; + return stack; } /* @@ -181,21 +184,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, if (file) { seq_pad(m, ' '); seq_file_path(m, file, ""); - } else if (mm) { - pid_t tid = pid_of_stack(priv, vma, is_pid); - - if (tid != 0) { - seq_pad(m, ' '); - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) - seq_printf(m, "[stack]"); - else - seq_printf(m, "[stack:%d]", tid); - } + } else if (mm && is_stack(priv, vma, is_pid)) { + seq_pad(m, ' '); + seq_printf(m, "[stack]"); } seq_putc(m, '\n'); diff --git a/include/linux/dax.h b/include/linux/dax.h index 8204c3dc3800..818e45078929 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,17 @@ int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, dax_iodone_t); int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, dax_iodone_t); + +#ifdef CONFIG_FS_DAX +struct page *read_dax_sector(struct block_device *bdev, sector_t n); +#else +static inline struct page *read_dax_sector(struct block_device *bdev, + sector_t n) +{ + return ERR_PTR(-ENXIO); +} +#endif + #ifdef CONFIG_TRANSPARENT_HUGEPAGE int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, unsigned int flags, get_block_t, dax_iodone_t); diff --git a/include/linux/fs.h b/include/linux/fs.h index 1a2046275cdf..ae681002100a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -484,9 +484,6 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -#ifdef CONFIG_FS_DAX - int bd_map_count; -#endif }; /* @@ -2907,7 +2904,7 @@ extern void replace_mount_options(struct super_block *sb, char *options); static inline bool io_is_direct(struct file *filp) { - return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp)); + return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); } static inline int iocb_flags(struct file *file) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9ae48d4aeb5e..792c8981e633 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -51,7 +51,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ - MEMCG_SOCK, + MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS, MEMCG_NR_STAT, }; diff --git a/include/linux/mm.h b/include/linux/mm.h index f1cd22f2df1a..516e14944339 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -201,11 +201,13 @@ extern unsigned int kobjsize(const void *objp); #endif #ifdef CONFIG_STACK_GROWSUP -#define VM_STACK_FLAGS (VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) +#define VM_STACK VM_GROWSUP #else -#define VM_STACK_FLAGS (VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) +#define VM_STACK VM_GROWSDOWN #endif +#define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) + /* * Special vmas that are non-mergable, non-mlock()able. * Note: mm/huge_memory.c VM_NO_THP depends on this definition. @@ -1341,8 +1343,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma, !vma_growsup(vma->vm_next, addr); } -extern struct task_struct *task_of_stack(struct task_struct *task, - struct vm_area_struct *vma, bool in_group); +int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d3ebb9d21a53..624b78b848b8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -424,9 +424,9 @@ struct mm_struct { unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ unsigned long pinned_vm; /* Refcount permanently increased */ - unsigned long data_vm; /* VM_WRITE & ~VM_SHARED/GROWSDOWN */ - unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE */ - unsigned long stack_vm; /* VM_GROWSUP/DOWN */ + unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ + unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ + unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 33bb1b19273e..7b6c2cfee390 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -682,6 +682,12 @@ typedef struct pglist_data { */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + spinlock_t split_queue_lock; + struct list_head split_queue; + unsigned long split_queue_len; +#endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5ac140dcb789..289c2314d766 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -512,7 +512,6 @@ static inline void napi_enable(struct napi_struct *n) clear_bit(NAPI_STATE_NPSVC, &n->state); } -#ifdef CONFIG_SMP /** * napi_synchronize - wait until NAPI is not running * @n: napi context @@ -523,12 +522,12 @@ static inline void napi_enable(struct napi_struct *n) */ static inline void napi_synchronize(const struct napi_struct *n) { - while (test_bit(NAPI_STATE_SCHED, &n->state)) - msleep(1); + if (IS_ENABLED(CONFIG_SMP)) + while (test_bit(NAPI_STATE_SCHED, &n->state)) + msleep(1); + else + barrier(); } -#else -# define napi_synchronize(n) barrier() -#endif enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, diff --git a/include/linux/of.h b/include/linux/of.h index dd10626a615f..dc6e39696b64 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -929,7 +929,7 @@ static inline int of_get_available_child_count(const struct device_node *np) return num; } -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && !defined(MODULE) #define _OF_DECLARE(table, name, compat, fn, fn_type) \ static const struct of_device_id __of_table_##name \ __used __section(__##table##_of_table) \ diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 0703b5360d31..37448ab5fb5c 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -29,7 +29,7 @@ static inline pfn_t pfn_to_pfn_t(unsigned long pfn) return __pfn_to_pfn_t(pfn, 0); } -extern pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags); +extern pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags); static inline bool pfn_t_has_page(pfn_t pfn) { @@ -48,7 +48,7 @@ static inline struct page *pfn_t_to_page(pfn_t pfn) return NULL; } -static inline dma_addr_t pfn_t_to_phys(pfn_t pfn) +static inline phys_addr_t pfn_t_to_phys(pfn_t pfn) { return PFN_PHYS(pfn_t_to_pfn(pfn)); } diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7c88ad156a29..00b17c526c1f 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -379,6 +379,22 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags); /** + * radix_tree_iter_retry - retry this chunk of the iteration + * @iter: iterator state + * + * If we iterate over a tree protected only by the RCU lock, a race + * against deletion or creation may result in seeing a slot for which + * radix_tree_deref_retry() returns true. If so, call this function + * and continue the iteration. + */ +static inline __must_check +void **radix_tree_iter_retry(struct radix_tree_iter *iter) +{ + iter->next_index = iter->index; + return NULL; +} + +/** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 52899291f401..5ee3c689c863 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -252,6 +252,12 @@ struct l2cap_conn_rsp { #define L2CAP_PSM_3DSP 0x0021 #define L2CAP_PSM_IPSP 0x0023 /* 6LoWPAN */ +#define L2CAP_PSM_DYN_START 0x1001 +#define L2CAP_PSM_DYN_END 0xffff +#define L2CAP_PSM_AUTO_END 0x10ff +#define L2CAP_PSM_LE_DYN_START 0x0080 +#define L2CAP_PSM_LE_DYN_END 0x00ff + /* channel identifier */ #define L2CAP_CID_SIGNALING 0x0001 #define L2CAP_CID_CONN_LESS 0x0002 diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 6816f0fa5693..30a56ab2ccfb 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -44,6 +44,24 @@ static inline bool skb_valid_dst(const struct sk_buff *skb) return dst && !(dst->flags & DST_METADATA); } +static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, + const struct sk_buff *skb_b) +{ + const struct metadata_dst *a, *b; + + if (!(skb_a->_skb_refdst | skb_b->_skb_refdst)) + return 0; + + a = (const struct metadata_dst *) skb_dst(skb_a); + b = (const struct metadata_dst *) skb_dst(skb_b); + + if (!a != !b || a->u.tun_info.options_len != b->u.tun_info.options_len) + return 1; + + return memcmp(&a->u.tun_info, &b->u.tun_info, + sizeof(a->u.tun_info) + a->u.tun_info.options_len); +} + struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags); struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 877f682989b8..295d291269e2 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -64,8 +64,16 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) void ip6_route_input(struct sk_buff *skb); -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6); +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags); + +static inline struct dst_entry *ip6_route_output(struct net *net, + const struct sock *sk, + struct flowi6 *fl6) +{ + return ip6_route_output_flags(net, sk, fl6, 0); +} + struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, int flags); diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 788ef58a66b9..62e17d1319ff 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -79,12 +79,10 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *proto); -#ifdef CONFIG_LOCKDEP -# define CONNTRACK_LOCKS 8 -#else -# define CONNTRACK_LOCKS 1024 -#endif +#define CONNTRACK_LOCKS 1024 + extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; +void nf_conntrack_lock(spinlock_t *lock); extern spinlock_t nf_conntrack_expect_lock; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 20e72129be1c..205630bb5010 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -756,7 +756,6 @@ struct sctp_transport { /* Reference counting. */ atomic_t refcnt; - __u32 dead:1, /* RTO-Pending : A flag used to track if one of the DATA * chunks sent to this address is currently being * used to compute a RTT. If this flag is 0, @@ -766,7 +765,7 @@ struct sctp_transport { * calculation completes (i.e. the DATA chunk * is SACK'd) clear this flag. */ - rto_pending:1, + __u32 rto_pending:1, /* * hb_sent : a flag that signals that we have a pending @@ -955,7 +954,7 @@ void sctp_transport_route(struct sctp_transport *, union sctp_addr *, void sctp_transport_pmtu(struct sctp_transport *, struct sock *sk); void sctp_transport_free(struct sctp_transport *); void sctp_transport_reset_timers(struct sctp_transport *); -void sctp_transport_hold(struct sctp_transport *); +int sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); void sctp_transport_raise_cwnd(struct sctp_transport *, __u32, __u32); diff --git a/include/net/sock.h b/include/net/sock.h index b9e7b3d863a0..f5ea148853e2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1036,18 +1036,6 @@ struct proto { #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif -#ifdef CONFIG_MEMCG_KMEM - /* - * cgroup specific init/deinit functions. Called once for all - * protocols that implement it, from cgroups populate function. - * This function has to setup any files the protocol want to - * appear in the kmem cgroup filesystem. - */ - int (*init_cgroup)(struct mem_cgroup *memcg, - struct cgroup_subsys *ss); - void (*destroy_cgroup)(struct mem_cgroup *memcg); - struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg); -#endif int (*diag_destroy)(struct sock *sk, int err); }; diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 7dda3d7adba8..aecd30308d50 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -16,7 +16,7 @@ struct sock_reuseport { }; extern int reuseport_alloc(struct sock *sk); -extern int reuseport_add_sock(struct sock *sk, const struct sock *sk2); +extern int reuseport_add_sock(struct sock *sk, struct sock *sk2); extern void reuseport_detach_sock(struct sock *sk); extern struct sock *reuseport_select_sock(struct sock *sk, u32 hash, diff --git a/include/net/tcp.h b/include/net/tcp.h index 8ea19977ea53..f6f8f032c73e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -216,7 +216,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ -/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */ +/* TCP initial congestion window as per rfc6928 */ #define TCP_INIT_CWND 10 /* Bit Flags for sysctl_tcp_fastopen */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 41e0433b4a83..149bec83a907 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -222,7 +222,6 @@ struct fsxattr { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) -#define BLKDAXSET _IO(0x12,128) #define BLKDAXGET _IO(0x12,129) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ diff --git a/kernel/memremap.c b/kernel/memremap.c index e517a16cb426..70ee3775de24 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -150,7 +150,7 @@ void devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(devm_memunmap); -pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags) +pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags) { return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); } @@ -183,7 +183,11 @@ EXPORT_SYMBOL(put_zone_device_page); static void pgmap_radix_release(struct resource *res) { - resource_size_t key; + resource_size_t key, align_start, align_size, align_end; + + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + align_end = align_start + align_size - 1; mutex_lock(&pgmap_lock); for (key = res->start; key <= res->end; key += SECTION_SIZE) @@ -226,12 +230,11 @@ static void devm_memremap_pages_release(struct device *dev, void *data) percpu_ref_put(pgmap->ref); } - pgmap_radix_release(res); - /* pages are dead and unused, undo the arch mapping */ align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(resource_size(res), SECTION_SIZE); arch_remove_memory(align_start, align_size); + pgmap_radix_release(res); dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc, "%s: failed to free all reserved pages\n", __func__); } @@ -267,7 +270,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, { int is_ram = region_intersects(res->start, resource_size(res), "System RAM"); - resource_size_t key, align_start, align_size; + resource_size_t key, align_start, align_size, align_end; struct dev_pagemap *pgmap; struct page_map *page_map; unsigned long pfn; @@ -309,7 +312,10 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, mutex_lock(&pgmap_lock); error = 0; - for (key = res->start; key <= res->end; key += SECTION_SIZE) { + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + align_end = align_start + align_size - 1; + for (key = align_start; key <= align_end; key += SECTION_SIZE) { struct dev_pagemap *dup; rcu_read_lock(); @@ -336,8 +342,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (nid < 0) nid = numa_mem_id(); - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(resource_size(res), SECTION_SIZE); error = arch_add_memory(nid, align_start, align_size, true); if (error) goto err_add_memory; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index dda9e6742950..202df6cffcca 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -126,6 +126,13 @@ check_stack(unsigned long ip, unsigned long *stack) } /* + * Some archs may not have the passed in ip in the dump. + * If that happens, we need to show everything. + */ + if (i == stack_trace_max.nr_entries) + i = 0; + + /* * Now find where in the stack these are. */ x = 0; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index fcf5d98574ce..6b79e9026e24 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1019,9 +1019,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } @@ -1098,9 +1102,13 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c index 98866a770770..25b5cbfb7615 100644 --- a/lib/test-string_helpers.c +++ b/lib/test-string_helpers.c @@ -327,36 +327,67 @@ out: } #define string_get_size_maxbuf 16 -#define test_string_get_size_one(size, blk_size, units, exp_result) \ +#define test_string_get_size_one(size, blk_size, exp_result10, exp_result2) \ do { \ - BUILD_BUG_ON(sizeof(exp_result) >= string_get_size_maxbuf); \ - __test_string_get_size((size), (blk_size), (units), \ - (exp_result)); \ + BUILD_BUG_ON(sizeof(exp_result10) >= string_get_size_maxbuf); \ + BUILD_BUG_ON(sizeof(exp_result2) >= string_get_size_maxbuf); \ + __test_string_get_size((size), (blk_size), (exp_result10), \ + (exp_result2)); \ } while (0) -static __init void __test_string_get_size(const u64 size, const u64 blk_size, - const enum string_size_units units, - const char *exp_result) +static __init void test_string_get_size_check(const char *units, + const char *exp, + char *res, + const u64 size, + const u64 blk_size) { - char buf[string_get_size_maxbuf]; - - string_get_size(size, blk_size, units, buf, sizeof(buf)); - if (!memcmp(buf, exp_result, strlen(exp_result) + 1)) + if (!memcmp(res, exp, strlen(exp) + 1)) return; - buf[sizeof(buf) - 1] = '\0'; - pr_warn("Test 'test_string_get_size_one' failed!\n"); - pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %d\n", + res[string_get_size_maxbuf - 1] = '\0'; + + pr_warn("Test 'test_string_get_size' failed!\n"); + pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %s)\n", size, blk_size, units); - pr_warn("expected: '%s', got '%s'\n", exp_result, buf); + pr_warn("expected: '%s', got '%s'\n", exp, res); +} + +static __init void __test_string_get_size(const u64 size, const u64 blk_size, + const char *exp_result10, + const char *exp_result2) +{ + char buf10[string_get_size_maxbuf]; + char buf2[string_get_size_maxbuf]; + + string_get_size(size, blk_size, STRING_UNITS_10, buf10, sizeof(buf10)); + string_get_size(size, blk_size, STRING_UNITS_2, buf2, sizeof(buf2)); + + test_string_get_size_check("STRING_UNITS_10", exp_result10, buf10, + size, blk_size); + + test_string_get_size_check("STRING_UNITS_2", exp_result2, buf2, + size, blk_size); } static __init void test_string_get_size(void) { - test_string_get_size_one(16384, 512, STRING_UNITS_2, "8.00 MiB"); - test_string_get_size_one(8192, 4096, STRING_UNITS_10, "32.7 MB"); - test_string_get_size_one(1, 512, STRING_UNITS_10, "512 B"); + /* small values */ + test_string_get_size_one(0, 512, "0 B", "0 B"); + test_string_get_size_one(1, 512, "512 B", "512 B"); + test_string_get_size_one(1100, 1, "1.10 kB", "1.07 KiB"); + + /* normal values */ + test_string_get_size_one(16384, 512, "8.39 MB", "8.00 MiB"); + test_string_get_size_one(500118192, 512, "256 GB", "238 GiB"); + test_string_get_size_one(8192, 4096, "33.6 MB", "32.0 MiB"); + + /* weird block sizes */ + test_string_get_size_one(3000, 1900, "5.70 MB", "5.44 MiB"); + + /* huge values */ + test_string_get_size_one(U64_MAX, 4096, "75.6 ZB", "64.0 ZiB"); + test_string_get_size_one(4096, U64_MAX, "75.6 ZB", "64.0 ZiB"); } static int __init test_string_helpers_init(void) @@ -430,10 +430,8 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * Anon pages in shared mappings are surprising: now * just reject it. */ - if (!is_cow_mapping(vm_flags)) { - WARN_ON_ONCE(vm_flags & VM_MAYWRITE); + if (!is_cow_mapping(vm_flags)) return -EFAULT; - } } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index fd3a07b3e6f4..36c070167b71 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -138,9 +138,6 @@ static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; -static DEFINE_SPINLOCK(split_queue_lock); -static LIST_HEAD(split_queue); -static unsigned long split_queue_len; static struct shrinker deferred_split_shrinker; static void set_recommended_min_free_kbytes(void) @@ -861,7 +858,8 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, return false; entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); - pgtable_trans_huge_deposit(mm, pmd, pgtable); + if (pgtable) + pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); atomic_long_inc(&mm->nr_ptes); return true; @@ -1039,13 +1037,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, spinlock_t *dst_ptl, *src_ptl; struct page *src_page; pmd_t pmd; - pgtable_t pgtable; + pgtable_t pgtable = NULL; int ret; - ret = -ENOMEM; - pgtable = pte_alloc_one(dst_mm, addr); - if (unlikely(!pgtable)) - goto out; + if (!vma_is_dax(vma)) { + ret = -ENOMEM; + pgtable = pte_alloc_one(dst_mm, addr); + if (unlikely(!pgtable)) + goto out; + } dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); @@ -1076,7 +1076,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } - if (pmd_trans_huge(pmd)) { + if (!vma_is_dax(vma)) { /* thp accounting separate from pmd_devmap accounting */ src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); @@ -3358,6 +3358,7 @@ int total_mapcount(struct page *page) int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); + struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); struct anon_vma *anon_vma; int count, mapcount, ret; bool mlocked; @@ -3401,19 +3402,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) lru_add_drain(); /* Prevent deferred_split_scan() touching ->_count */ - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); count = page_count(head); mapcount = total_mapcount(head); if (!mapcount && count == 1) { if (!list_empty(page_deferred_list(head))) { - split_queue_len--; + pgdata->split_queue_len--; list_del(page_deferred_list(head)); } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); __split_huge_page(page, list); ret = 0; } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); pr_alert("total_mapcount: %u, page_count(): %u\n", mapcount, count); if (PageTail(page)) @@ -3421,7 +3422,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) dump_page(page, "total_mapcount(head) > 0"); BUG(); } else { - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); unfreeze_page(anon_vma, head); ret = -EBUSY; } @@ -3436,64 +3437,65 @@ out: void free_transhuge_page(struct page *page) { + struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); unsigned long flags; - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); if (!list_empty(page_deferred_list(page))) { - split_queue_len--; + pgdata->split_queue_len--; list_del(page_deferred_list(page)); } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); free_compound_page(page); } void deferred_split_huge_page(struct page *page) { + struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); unsigned long flags; VM_BUG_ON_PAGE(!PageTransHuge(page), page); - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); if (list_empty(page_deferred_list(page))) { - list_add_tail(page_deferred_list(page), &split_queue); - split_queue_len++; + list_add_tail(page_deferred_list(page), &pgdata->split_queue); + pgdata->split_queue_len++; } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); } static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { - /* - * Split a page from split_queue will free up at least one page, - * at most HPAGE_PMD_NR - 1. We don't track exact number. - * Let's use HPAGE_PMD_NR / 2 as ballpark. - */ - return ACCESS_ONCE(split_queue_len) * HPAGE_PMD_NR / 2; + struct pglist_data *pgdata = NODE_DATA(sc->nid); + return ACCESS_ONCE(pgdata->split_queue_len); } static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { + struct pglist_data *pgdata = NODE_DATA(sc->nid); unsigned long flags; LIST_HEAD(list), *pos, *next; struct page *page; int split = 0; - spin_lock_irqsave(&split_queue_lock, flags); - list_splice_init(&split_queue, &list); - + spin_lock_irqsave(&pgdata->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, mapping); page = compound_head(page); - /* race with put_compound_page() */ - if (!get_page_unless_zero(page)) { + if (get_page_unless_zero(page)) { + list_move(page_deferred_list(page), &list); + } else { + /* We lost race with put_compound_page() */ list_del_init(page_deferred_list(page)); - split_queue_len--; + pgdata->split_queue_len--; } + if (!--sc->nr_to_scan) + break; } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, mapping); @@ -3505,17 +3507,24 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, put_page(page); } - spin_lock_irqsave(&split_queue_lock, flags); - list_splice_tail(&list, &split_queue); - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); + list_splice_tail(&list, &pgdata->split_queue); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); - return split * HPAGE_PMD_NR / 2; + /* + * Stop shrinker if we didn't split any page, but the queue is empty. + * This can happen if pages were freed under us. + */ + if (!split && list_empty(&pgdata->split_queue)) + return SHRINK_STOP; + return split; } static struct shrinker deferred_split_shrinker = { .count_objects = deferred_split_count, .scan_objects = deferred_split_scan, .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_NUMA_AWARE, }; #ifdef CONFIG_DEBUG_FS diff --git a/mm/internal.h b/mm/internal.h index ed8b5ffcf9b1..a38a21ebddb4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -216,6 +216,37 @@ static inline bool is_cow_mapping(vm_flags_t flags) return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } +/* + * These three helpers classifies VMAs for virtual memory accounting. + */ + +/* + * Executable code area - executable, not writable, not stack + */ +static inline bool is_exec_mapping(vm_flags_t flags) +{ + return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; +} + +/* + * Stack area - atomatically grows in one direction + * + * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: + * do_mmap() forbids all other combinations. + */ +static inline bool is_stack_mapping(vm_flags_t flags) +{ + return (flags & VM_STACK) == VM_STACK; +} + +/* + * Data area - private, writable, not stack + */ +static inline bool is_data_mapping(vm_flags_t flags) +{ + return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; +} + /* mm/util.c */ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node *rb_parent); diff --git a/mm/memory.c b/mm/memory.c index 30991f83d0bf..635451abc8f7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1591,10 +1591,15 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ - if (!HAVE_PTE_SPECIAL && pfn_t_valid(pfn)) { + if (!HAVE_PTE_SPECIAL && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; - page = pfn_t_to_page(pfn); + /* + * At this point we are committed to insert_page() + * regardless of whether the caller specified flags that + * result in pfn_t_has_page() == false. + */ + page = pfn_to_page(pfn_t_to_pfn(pfn)); return insert_page(vma, addr, page, vma->vm_page_prot); } return insert_pfn(vma, addr, pfn, vma->vm_page_prot); @@ -2232,11 +2237,6 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, page_cache_get(old_page); - /* - * Only catch write-faults on shared writable pages, - * read-only shared pages can get COWed by - * get_user_pages(.write=1, .force=1). - */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; diff --git a/mm/mmap.c b/mm/mmap.c index 84b12624ceb0..cfc0cdca421e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -42,6 +42,7 @@ #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> +#include <linux/moduleparam.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -69,6 +70,8 @@ const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif +static bool ignore_rlimit_data = true; +core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, @@ -2982,9 +2985,17 @@ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; - if ((flags & (VM_WRITE | VM_SHARED | (VM_STACK_FLAGS & - (VM_GROWSUP | VM_GROWSDOWN)))) == VM_WRITE) - return mm->data_vm + npages <= rlimit(RLIMIT_DATA); + if (is_data_mapping(flags) && + mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { + if (ignore_rlimit_data) + pr_warn_once("%s (%d): VmData %lu exceed data ulimit " + "%lu. Will be forbidden soon.\n", + current->comm, current->pid, + (mm->data_vm + npages) << PAGE_SHIFT, + rlimit(RLIMIT_DATA)); + else + return false; + } return true; } @@ -2993,11 +3004,11 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { mm->total_vm += npages; - if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC) + if (is_exec_mapping(flags)) mm->exec_vm += npages; - else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN))) + else if (is_stack_mapping(flags)) mm->stack_vm += npages; - else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) + else if (is_data_mapping(flags)) mm->data_vm += npages; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 63358d9f9aa9..ea2c4d3e0c03 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5210,6 +5210,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) pgdat->numabalancing_migrate_nr_pages = 0; pgdat->numabalancing_migrate_next_window = jiffies; #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + spin_lock_init(&pgdat->split_queue_lock); + INIT_LIST_HEAD(&pgdat->split_queue); + pgdat->split_queue_len = 0; +#endif init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); pgdat_page_ext_init(pgdat); diff --git a/mm/util.c b/mm/util.c index c108a6542d05..4fb14ca5a419 100644 --- a/mm/util.c +++ b/mm/util.c @@ -230,36 +230,11 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, } /* Check if the vma is being used as a stack by this task */ -static int vm_is_stack_for_task(struct task_struct *t, - struct vm_area_struct *vma) +int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t) { return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } -/* - * Check if the vma is being used as a stack. - * If is_group is non-zero, check in the entire thread group or else - * just check in the current task. Returns the task_struct of the task - * that the vma is stack for. Must be called under rcu_read_lock(). - */ -struct task_struct *task_of_stack(struct task_struct *task, - struct vm_area_struct *vma, bool in_group) -{ - if (vm_is_stack_for_task(task, vma)) - return task; - - if (in_group) { - struct task_struct *t; - - for_each_thread(task, t) { - if (vm_is_stack_for_task(t, vma)) - return t; - } - } - - return NULL; -} - #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm) { diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 9a6c0704211c..149fdf6c5c56 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -248,9 +248,8 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, if (tree) { spin_lock(&vmpr->sr_lock); - vmpr->tree_scanned += scanned; + scanned = vmpr->tree_scanned += scanned; vmpr->tree_reclaimed += reclaimed; - scanned = vmpr->scanned; spin_unlock(&vmpr->sr_lock); if (scanned < vmpressure_win) diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index d040365ba98e..8a4cc2f7f0db 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -307,6 +307,9 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, /* check that it's our buffer */ if (lowpan_is_ipv6(*skb_network_header(skb))) { + /* Pull off the 1-byte of 6lowpan header. */ + skb_pull(skb, 1); + /* Copy the packet so that the IPv6 header is * properly aligned. */ @@ -317,6 +320,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; + local_skb->dev = dev; skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); @@ -335,6 +339,8 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, if (!local_skb) goto drop; + local_skb->dev = dev; + ret = iphc_decompress(local_skb, dev, chan); if (ret < 0) { kfree_skb(local_skb); @@ -343,7 +349,6 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; - local_skb->dev = dev; if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 41b5f3813f02..c78ee2dc9323 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -688,21 +688,29 @@ static u8 update_white_list(struct hci_request *req) * command to remove it from the controller. */ list_for_each_entry(b, &hdev->le_white_list, list) { - struct hci_cp_le_del_from_white_list cp; + /* If the device is neither in pend_le_conns nor + * pend_le_reports then remove it from the whitelist. + */ + if (!hci_pend_le_action_lookup(&hdev->pend_le_conns, + &b->bdaddr, b->bdaddr_type) && + !hci_pend_le_action_lookup(&hdev->pend_le_reports, + &b->bdaddr, b->bdaddr_type)) { + struct hci_cp_le_del_from_white_list cp; + + cp.bdaddr_type = b->bdaddr_type; + bacpy(&cp.bdaddr, &b->bdaddr); - if (hci_pend_le_action_lookup(&hdev->pend_le_conns, - &b->bdaddr, b->bdaddr_type) || - hci_pend_le_action_lookup(&hdev->pend_le_reports, - &b->bdaddr, b->bdaddr_type)) { - white_list_entries++; + hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, + sizeof(cp), &cp); continue; } - cp.bdaddr_type = b->bdaddr_type; - bacpy(&cp.bdaddr, &b->bdaddr); + if (hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) { + /* White list can not be used with RPAs */ + return 0x00; + } - hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, - sizeof(cp), &cp); + white_list_entries++; } /* Since all no longer valid white list entries have been diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 39a5149f3010..eb4f5f24cbe3 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -197,10 +197,20 @@ int l2cap_add_psm(struct l2cap_chan *chan, bdaddr_t *src, __le16 psm) chan->sport = psm; err = 0; } else { - u16 p; + u16 p, start, end, incr; + + if (chan->src_type == BDADDR_BREDR) { + start = L2CAP_PSM_DYN_START; + end = L2CAP_PSM_AUTO_END; + incr = 2; + } else { + start = L2CAP_PSM_LE_DYN_START; + end = L2CAP_PSM_LE_DYN_END; + incr = 1; + } err = -EINVAL; - for (p = 0x1001; p < 0x1100; p += 2) + for (p = start; p <= end; p += incr) if (!__l2cap_global_chan_by_addr(cpu_to_le16(p), src)) { chan->psm = cpu_to_le16(p); chan->sport = cpu_to_le16(p); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 1bb551527044..e4cae72895a7 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -58,7 +58,7 @@ static int l2cap_validate_bredr_psm(u16 psm) return -EINVAL; /* Restrict usage of well-known PSMs */ - if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) + if (psm < L2CAP_PSM_DYN_START && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; return 0; @@ -67,11 +67,11 @@ static int l2cap_validate_bredr_psm(u16 psm) static int l2cap_validate_le_psm(u16 psm) { /* Valid LE_PSM ranges are defined only until 0x00ff */ - if (psm > 0x00ff) + if (psm > L2CAP_PSM_LE_DYN_END) return -EINVAL; /* Restrict fixed, SIG assigned PSM values to CAP_NET_BIND_SERVICE */ - if (psm <= 0x007f && !capable(CAP_NET_BIND_SERVICE)) + if (psm < L2CAP_PSM_LE_DYN_START && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; return 0; @@ -125,6 +125,9 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) goto done; } + bacpy(&chan->src, &la.l2_bdaddr); + chan->src_type = la.l2_bdaddr_type; + if (la.l2_cid) err = l2cap_add_scid(chan, __le16_to_cpu(la.l2_cid)); else @@ -156,9 +159,6 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) break; } - bacpy(&chan->src, &la.l2_bdaddr); - chan->src_type = la.l2_bdaddr_type; - if (chan->psm && bdaddr_type_is_le(chan->src_type)) chan->mode = L2CAP_MODE_LE_FLOWCTL; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index ffed8a1d4f27..4b175df35184 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1072,22 +1072,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) hcon->dst_type = smp->remote_irk->addr_type; queue_work(hdev->workqueue, &conn->id_addr_update_work); } - - /* When receiving an indentity resolving key for - * a remote device that does not use a resolvable - * private address, just remove the key so that - * it is possible to use the controller white - * list for scanning. - * - * Userspace will have been told to not store - * this key at this point. So it is safe to - * just remove it. - */ - if (!bacmp(&smp->remote_irk->rpa, BDADDR_ANY)) { - list_del_rcu(&smp->remote_irk->list); - kfree_rcu(smp->remote_irk, rcu); - smp->remote_irk = NULL; - } } if (smp->csrk) { diff --git a/net/bridge/br.c b/net/bridge/br.c index a1abe4936fe1..3addc05b9a16 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,6 +121,7 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; +/* called with RTNL */ static int br_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -130,7 +131,6 @@ static int br_switchdev_event(struct notifier_block *unused, struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; - rtnl_lock(); p = br_port_get_rtnl(dev); if (!p) goto out; @@ -155,7 +155,6 @@ static int br_switchdev_event(struct notifier_block *unused, } out: - rtnl_unlock(); return err; } diff --git a/net/core/dev.c b/net/core/dev.c index cc9e3652cf93..8cba3d852f25 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4351,6 +4351,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; + diffs |= skb_metadata_dst_cmp(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); @@ -4548,10 +4549,12 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) break; case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { + skb_dst_drop(skb); kmem_cache_free(skbuff_head_cache, skb); - else + } else { __kfree_skb(skb); + } break; case GRO_HELD: diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 1df98c557440..e92b759d906c 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -93,10 +93,17 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) * @sk2: Socket belonging to the existing reuseport group. * May return ENOMEM and not add socket to group under memory pressure. */ -int reuseport_add_sock(struct sock *sk, const struct sock *sk2) +int reuseport_add_sock(struct sock *sk, struct sock *sk2) { struct sock_reuseport *reuse; + if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { + int err = reuseport_alloc(sk2); + + if (err) + return err; + } + spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)), diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index c22920525e5d..775824720b6b 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -353,6 +353,7 @@ config INET_ESP select CRYPTO_CBC select CRYPTO_SHA1 select CRYPTO_DES + select CRYPTO_ECHAINIV ---help--- Support for IPsec ESP. diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 7aea0ccb6be6..d07fc076bea0 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1394,9 +1394,10 @@ found: struct fib_info *fi = fa->fa_info; int nhsel, err; - if ((index >= (1ul << fa->fa_slen)) && - ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen != KEYLENGTH))) - continue; + if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { + if (index >= (1ul << fa->fa_slen)) + continue; + } if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) continue; if (fi->fib_dead) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8bb8e7ad8548..6029157a19ed 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -361,13 +361,20 @@ struct sock *inet_diag_find_one_icsk(struct net *net, req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) - else if (req->sdiag_family == AF_INET6) - sk = inet6_lookup(net, hashinfo, - (struct in6_addr *)req->id.idiag_dst, - req->id.idiag_dport, - (struct in6_addr *)req->id.idiag_src, - req->id.idiag_sport, - req->id.idiag_if); + else if (req->sdiag_family == AF_INET6) { + if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && + ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) + sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3], + req->id.idiag_dport, req->id.idiag_src[3], + req->id.idiag_sport, req->id.idiag_if); + else + sk = inet6_lookup(net, hashinfo, + (struct in6_addr *)req->id.idiag_dst, + req->id.idiag_dport, + (struct in6_addr *)req->id.idiag_src, + req->id.idiag_sport, + req->id.idiag_if); + } #endif else return ERR_PTR(-EINVAL); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 3f00810b7288..187c6fcc3027 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -661,6 +661,7 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) struct ipq *qp; IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); + skb_orphan(skb); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index b1209b63381f..d77eb0c3b684 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -316,7 +316,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; - if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) { + if (sysctl_ip_early_demux && + !skb_dst(skb) && + !skb->sk && + !ip_is_fragment(iph)) { const struct net_protocol *ipprot; int protocol = iph->protocol; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 67f7c9de0b16..2ed9dd2b5f2f 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -143,7 +143,11 @@ static char dhcp_client_identifier[253] __initdata; /* Persistent data: */ +#ifdef IPCONFIG_DYNAMIC static int ic_proto_used; /* Protocol used, if any */ +#else +#define ic_proto_used 0 +#endif static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */ static u8 ic_domain[64]; /* DNS (not NIS) domain name */ diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 6fb869f646bf..a04dee536b8e 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -27,8 +27,6 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, { int err; - skb_orphan(skb); - local_bh_disable(); err = ip_defrag(net, skb, user); local_bh_enable(); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fd17eec93525..19746b3fcbbe 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include <asm/uaccess.h> #include <asm/ioctls.h> +#include <asm/unaligned.h> #include <net/busy_poll.h> int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; @@ -2638,6 +2639,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; unsigned int start; + u64 rate64; u32 rate; memset(info, 0, sizeof(*info)); @@ -2703,15 +2705,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_retrans = tp->total_retrans; rate = READ_ONCE(sk->sk_pacing_rate); - info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_pacing_rate); rate = READ_ONCE(sk->sk_max_pacing_rate); - info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_max_pacing_rate); do { start = u64_stats_fetch_begin_irq(&tp->syncp); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; + put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked); + put_unaligned(tp->bytes_received, &info->tcpi_bytes_received); } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); info->tcpi_segs_out = tp->segs_out; info->tcpi_segs_in = tp->segs_in; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0003d409fec5..1c2a73406261 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2164,8 +2164,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int cnt, oldcnt; - int err; + int cnt, oldcnt, lost; unsigned int mss; /* Use SACK to deduce losses of new sequences sent during recovery */ const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; @@ -2205,9 +2204,10 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) break; mss = tcp_skb_mss(skb); - err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, - mss, GFP_ATOMIC); - if (err < 0) + /* If needed, chop off the prefix to mark as lost. */ + lost = (packets - oldcnt) * mss; + if (lost < skb->len && + tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } @@ -2366,8 +2366,6 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) tp->snd_ssthresh = tp->prior_ssthresh; tcp_ecn_withdraw_cwr(tp); } - } else { - tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh); } tp->snd_cwnd_stamp = tcp_time_stamp; tp->undo_marker = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5ced3e4013e3..a4d523709ab3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -707,7 +707,8 @@ release_sk1: outside socket context is ugly, certainly. What can I do? */ -static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, +static void tcp_v4_send_ack(struct net *net, + struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) @@ -722,7 +723,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, ]; } rep; struct ip_reply_arg arg; - struct net *net = dev_net(skb_dst(skb)->dev); memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); @@ -784,7 +784,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v4_send_ack(sock_net(sk), skb, + tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, @@ -803,8 +804,10 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? - tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : + tcp_sk(sk)->snd_nxt; + + tcp_v4_send_ack(sock_net(sk), skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, tcp_time_stamp, req->ts_recent, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index dc45b538e237..be0b21852b13 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -499,6 +499,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -512,14 +513,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } @@ -563,6 +568,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -601,14 +607,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index bb7dabe2ebbf..40c897515ddc 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -69,6 +69,7 @@ config INET6_ESP select CRYPTO_CBC select CRYPTO_SHA1 select CRYPTO_DES + select CRYPTO_ECHAINIV ---help--- Support for IPsec ESP. diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 517c55b01ba8..428162155280 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -162,6 +162,9 @@ ipv4_connected: fl6.fl6_dport = inet->inet_dport; fl6.fl6_sport = inet->inet_sport; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST)) fl6.flowi6_oif = np->mcast_oif; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 23de98f976d5..a163102f1803 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -909,6 +909,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct rt6_info *rt; #endif int err; + int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, @@ -940,10 +941,13 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, dst_release(*dst); *dst = NULL; } + + if (fl6->flowi6_oif) + flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) - *dst = ip6_route_output(net, sk, fl6); + *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3c8834bc822d..ed446639219c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1183,11 +1183,10 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); } -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6) +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags) { struct dst_entry *dst; - int flags = 0; bool any_src; dst = l3mdev_rt6_dst_by_oif(net, fl6); @@ -1208,7 +1207,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); } -EXPORT_SYMBOL(ip6_route_output); +EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index e794ef66a401..2066d1c25a11 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -201,14 +201,14 @@ static int ipip6_tunnel_create(struct net_device *dev) if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; + dev->rtnl_link_ops = &sit_link_ops; + err = register_netdevice(dev); if (err < 0) goto out; ipip6_tunnel_clone_6rd(dev, sitn); - dev->rtnl_link_ops = &sit_link_ops; - dev_hold(dev); ipip6_tunnel_link(sitn, t); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5d2c2afffe7b..22e28a44e3c8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -257,6 +257,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -270,14 +271,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } @@ -321,6 +326,7 @@ struct sock *__udp6_lib_lookup(struct net *net, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -358,14 +364,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } diff --git a/net/irda/ircomm/ircomm_param.c b/net/irda/ircomm/ircomm_param.c index 3c4caa60c926..5728e76ca6d5 100644 --- a/net/irda/ircomm/ircomm_param.c +++ b/net/irda/ircomm/ircomm_param.c @@ -134,11 +134,10 @@ int ircomm_param_request(struct ircomm_tty_cb *self, __u8 pi, int flush) return -1; } skb_put(skb, count); + pr_debug("%s(), skb->len=%d\n", __func__, skb->len); spin_unlock_irqrestore(&self->spinlock, flags); - pr_debug("%s(), skb->len=%d\n", __func__ , skb->len); - if (flush) { /* ircomm_tty_do_softint will take care of the rest */ schedule_work(&self->tqueue); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ef50a94d3eb7..fc3598a922b0 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -708,6 +708,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, if (!addr || addr->sa_family != AF_IUCV) return -EINVAL; + if (addr_len < sizeof(struct sockaddr_iucv)) + return -EINVAL; + lock_sock(sk); if (sk->sk_state != IUCV_OPEN) { err = -EBADFD; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index f7fc0e00497f..978d3bc31df7 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1733,7 +1733,6 @@ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local) if (sdata->vif.type != NL80211_IFTYPE_ADHOC) continue; sdata->u.ibss.last_scan_completed = jiffies; - ieee80211_queue_work(&local->hw, &sdata->work); } mutex_unlock(&local->iflist_mtx); } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 6bcf0faa4a89..8190bf27ebff 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -248,6 +248,7 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for scan work complete */ flush_workqueue(local->workqueue); + flush_work(&local->sched_scan_stopped_work); WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), "%s called with hardware scan in progress\n", __func__); @@ -256,6 +257,11 @@ static void ieee80211_restart_work(struct work_struct *work) list_for_each_entry(sdata, &local->interfaces, list) flush_delayed_work(&sdata->dec_tailroom_needed_wk); ieee80211_scan_cancel(local); + + /* make sure any new ROC will consider local->in_reconfig */ + flush_delayed_work(&local->roc_work); + flush_work(&local->hw_roc_done); + ieee80211_reconfig(local); rtnl_unlock(); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index fa28500f28fd..6f85b6ab8e51 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1370,17 +1370,6 @@ out: sdata_unlock(sdata); } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata; - - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) - if (ieee80211_vif_is_mesh(&sdata->vif) && - ieee80211_sdata_running(sdata)) - ieee80211_queue_work(&local->hw, &sdata->work); - rcu_read_unlock(); -} void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) { diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index a1596344c3ba..4a8019f79fb2 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -362,14 +362,10 @@ static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) return sdata->u.mesh.mesh_pp_id == IEEE80211_PATH_PROTOCOL_HWMP; } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local); - void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata); void ieee80211s_stop(void); #else -static inline void -ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) {} static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return false; } static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 1c342e2592c4..bfbb1acafdd1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4005,8 +4005,6 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) if (!ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR)) ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.monitor_work); - /* and do all the other regular work too */ - ieee80211_queue_work(&sdata->local->hw, &sdata->work); } } diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 8b2f4eaac2ba..55a9c5b94ce1 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -252,14 +252,11 @@ static bool ieee80211_recalc_sw_work(struct ieee80211_local *local, static void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc, unsigned long start_time) { - struct ieee80211_local *local = roc->sdata->local; - if (WARN_ON(roc->notified)) return; roc->start_time = start_time; roc->started = true; - roc->hw_begun = true; if (roc->mgmt_tx_cookie) { if (!WARN_ON(!roc->frame)) { @@ -274,9 +271,6 @@ static void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc, } roc->notified = true; - - if (!local->ops->remain_on_channel) - ieee80211_recalc_sw_work(local, start_time); } static void ieee80211_hw_roc_start(struct work_struct *work) @@ -291,6 +285,7 @@ static void ieee80211_hw_roc_start(struct work_struct *work) if (!roc->started) break; + roc->hw_begun = true; ieee80211_handle_roc_started(roc, local->hw_roc_start_time); } @@ -413,6 +408,10 @@ void ieee80211_start_next_roc(struct ieee80211_local *local) return; } + /* defer roc if driver is not started (i.e. during reconfig) */ + if (local->in_reconfig) + return; + roc = list_first_entry(&local->roc_list, struct ieee80211_roc_work, list); @@ -534,8 +533,10 @@ ieee80211_coalesce_hw_started_roc(struct ieee80211_local *local, * begin, otherwise they'll both be marked properly by the work * struct that runs once the driver notifies us of the beginning */ - if (cur_roc->hw_begun) + if (cur_roc->hw_begun) { + new_roc->hw_begun = true; ieee80211_handle_roc_started(new_roc, now); + } return true; } @@ -658,6 +659,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, queued = true; roc->on_channel = tmp->on_channel; ieee80211_handle_roc_started(roc, now); + ieee80211_recalc_sw_work(local, now); break; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index a413e52f7691..ae980ce8daff 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -314,6 +314,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) bool was_scanning = local->scanning; struct cfg80211_scan_request *scan_req; struct ieee80211_sub_if_data *scan_sdata; + struct ieee80211_sub_if_data *sdata; lockdep_assert_held(&local->mtx); @@ -373,7 +374,16 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); - ieee80211_mesh_notify_scan_completed(local); + + /* Requeue all the work that might have been ignored while + * the scan was in progress; if there was none this will + * just be a no-op for the particular interface. + */ + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (ieee80211_sdata_running(sdata)) + ieee80211_queue_work(&sdata->local->hw, &sdata->work); + } + if (was_scanning) ieee80211_start_next_roc(local); } @@ -1213,6 +1223,14 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw) trace_api_sched_scan_stopped(local); + /* + * this shouldn't really happen, so for simplicity + * simply ignore it, and let mac80211 reconfigure + * the sched scan later on. + */ + if (local->in_reconfig) + return; + schedule_work(&local->sched_scan_stopped_work); } EXPORT_SYMBOL(ieee80211_sched_scan_stopped); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 4402ad5b27d1..a4a4f89d3ba0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1453,7 +1453,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, more_data = ieee80211_sta_ps_more_data(sta, ignored_acs, reason, driver_release_tids); - if (reason == IEEE80211_FRAME_RELEASE_PSPOLL) + if (driver_release_tids && reason == IEEE80211_FRAME_RELEASE_PSPOLL) driver_release_tids = BIT(find_highest_prio_tid(driver_release_tids)); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 5bad05e9af90..6101deb805a8 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -51,6 +51,11 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, struct ieee80211_hdr *hdr = (void *)skb->data; int ac; + if (info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER) { + ieee80211_free_txskb(&local->hw, skb); + return; + } + /* * This skb 'survived' a round-trip through the driver, and * hopefully the driver didn't mangle it too badly. However, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 3943d4bf289c..58f58bd5202f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2043,16 +2043,26 @@ int ieee80211_reconfig(struct ieee80211_local *local) */ if (sched_scan_req->n_scan_plans > 1 || __ieee80211_request_sched_scan_start(sched_scan_sdata, - sched_scan_req)) + sched_scan_req)) { + RCU_INIT_POINTER(local->sched_scan_sdata, NULL); + RCU_INIT_POINTER(local->sched_scan_req, NULL); sched_scan_stopped = true; + } mutex_unlock(&local->mtx); if (sched_scan_stopped) cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy); wake_up: - local->in_reconfig = false; - barrier(); + if (local->in_reconfig) { + local->in_reconfig = false; + barrier(); + + /* Restart deferred ROCs */ + mutex_lock(&local->mtx); + ieee80211_start_next_roc(local); + mutex_unlock(&local->mtx); + } if (local->monitors == local->open_count && local->monitors > 0) ieee80211_add_virtual_monitor(local); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 43d8c9896fa3..f0f688db6213 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -164,8 +164,6 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - if (e.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) e.cidr = HOST_MASK; @@ -377,8 +375,6 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - if (e.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) e.cidr = HOST_MASK; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3cb3cb831591..58882de06bd7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -66,6 +66,21 @@ EXPORT_SYMBOL_GPL(nf_conntrack_locks); __cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock); EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock); +static __read_mostly spinlock_t nf_conntrack_locks_all_lock; +static __read_mostly bool nf_conntrack_locks_all; + +void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) +{ + spin_lock(lock); + while (unlikely(nf_conntrack_locks_all)) { + spin_unlock(lock); + spin_lock(&nf_conntrack_locks_all_lock); + spin_unlock(&nf_conntrack_locks_all_lock); + spin_lock(lock); + } +} +EXPORT_SYMBOL_GPL(nf_conntrack_lock); + static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2) { h1 %= CONNTRACK_LOCKS; @@ -82,12 +97,12 @@ static bool nf_conntrack_double_lock(struct net *net, unsigned int h1, h1 %= CONNTRACK_LOCKS; h2 %= CONNTRACK_LOCKS; if (h1 <= h2) { - spin_lock(&nf_conntrack_locks[h1]); + nf_conntrack_lock(&nf_conntrack_locks[h1]); if (h1 != h2) spin_lock_nested(&nf_conntrack_locks[h2], SINGLE_DEPTH_NESTING); } else { - spin_lock(&nf_conntrack_locks[h2]); + nf_conntrack_lock(&nf_conntrack_locks[h2]); spin_lock_nested(&nf_conntrack_locks[h1], SINGLE_DEPTH_NESTING); } @@ -102,16 +117,19 @@ static void nf_conntrack_all_lock(void) { int i; - for (i = 0; i < CONNTRACK_LOCKS; i++) - spin_lock_nested(&nf_conntrack_locks[i], i); + spin_lock(&nf_conntrack_locks_all_lock); + nf_conntrack_locks_all = true; + + for (i = 0; i < CONNTRACK_LOCKS; i++) { + spin_lock(&nf_conntrack_locks[i]); + spin_unlock(&nf_conntrack_locks[i]); + } } static void nf_conntrack_all_unlock(void) { - int i; - - for (i = 0; i < CONNTRACK_LOCKS; i++) - spin_unlock(&nf_conntrack_locks[i]); + nf_conntrack_locks_all = false; + spin_unlock(&nf_conntrack_locks_all_lock); } unsigned int nf_conntrack_htable_size __read_mostly; @@ -757,7 +775,7 @@ restart: hash = hash_bucket(_hash, net); for (; i < net->ct.htable_size; i++) { lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS]; - spin_lock(lockp); + nf_conntrack_lock(lockp); if (read_seqcount_retry(&net->ct.generation, sequence)) { spin_unlock(lockp); goto restart; @@ -1382,7 +1400,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), for (; *bucket < net->ct.htable_size; (*bucket)++) { lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS]; local_bh_disable(); - spin_lock(lockp); + nf_conntrack_lock(lockp); if (*bucket < net->ct.htable_size) { hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index bd9d31537905..3b40ec575cd5 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -425,7 +425,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, } local_bh_disable(); for (i = 0; i < net->ct.htable_size; i++) { - spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); if (i < net->ct.htable_size) { hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) unhelp(h, me); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index dbb1bb3edb45..355e8552fd5b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -840,7 +840,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) { restart: lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; - spin_lock(lockp); + nf_conntrack_lock(lockp); if (cb->args[0] >= net->ct.htable_size) { spin_unlock(lockp); goto out; diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index b6605e000801..5eefe4a355c6 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -224,12 +224,12 @@ static int __init nf_tables_netdev_init(void) nft_register_chain_type(&nft_filter_chain_netdev); ret = register_pernet_subsys(&nf_tables_netdev_net_ops); - if (ret < 0) + if (ret < 0) { nft_unregister_chain_type(&nft_filter_chain_netdev); - + return ret; + } register_netdevice_notifier(&nf_tables_netdev_notifier); - - return ret; + return 0; } static void __exit nf_tables_netdev_exit(void) diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 5d010f27ac01..94837d236ab0 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -307,12 +307,12 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) local_bh_disable(); for (i = 0; i < net->ct.htable_size; i++) { - spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); if (i < net->ct.htable_size) { hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) untimeout(h, timeout); } - spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); } local_bh_enable(); } diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 383c17138399..b78c28ba465f 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -46,16 +46,14 @@ static void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 8; i++) { - src64 = get_unaligned_be64(&src[i]); - src64 = be64_to_cpu((__force __be64)src64); + src64 = get_unaligned((u64 *)&src[i]); put_unaligned_be64(src64, &dst[i]); } break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 8; i++) { src64 = get_unaligned_be64(&src[i]); - src64 = (__force u64)cpu_to_be64(src64); - put_unaligned_be64(src64, &dst[i]); + put_unaligned(src64, (u64 *)&dst[i]); } break; } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a0eb2161e3ef..d4a4619fcebc 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -127,6 +127,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, NF_CT_LABELS_MAX_SIZE - size); return; } +#endif case NFT_CT_BYTES: /* fallthrough */ case NFT_CT_PKTS: { const struct nf_conn_acct *acct = nf_conn_acct_find(ct); @@ -138,7 +139,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, memcpy(dest, &count, sizeof(count)); return; } -#endif default: break; } diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index b7c43def0dc6..e118397254af 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -228,7 +228,7 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par) { struct ipv6hdr *ipv6h = ipv6_hdr(skb); u8 nexthdr; - __be16 frag_off; + __be16 frag_off, oldlen, newlen; int tcphoff; int ret; @@ -244,7 +244,12 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par) return NF_DROP; if (ret > 0) { ipv6h = ipv6_hdr(skb); - ipv6h->payload_len = htons(ntohs(ipv6h->payload_len) + ret); + oldlen = ipv6h->payload_len; + newlen = htons(ntohs(oldlen) + ret); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, oldlen), + newlen); + ipv6h->payload_len = newlen; } return XT_CONTINUE; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 81dc1bb6e016..f1ffb34e253f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2831,7 +2831,8 @@ static int netlink_dump(struct sock *sk) * reasonable static buffer based on the expected largest dump of a * single netdev. The outcome is MSG_TRUNC error. */ - skb_reserve(skb, skb_tailroom(skb) - alloc_size); + if (!netlink_rx_is_mmaped(sk)) + skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); len = cb->dump(skb, cb); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f53bf3b6558b..cf5b69ab1829 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1095,17 +1095,6 @@ static unsigned int rfkill_fop_poll(struct file *file, poll_table *wait) return res; } -static bool rfkill_readable(struct rfkill_data *data) -{ - bool r; - - mutex_lock(&data->mtx); - r = !list_empty(&data->events); - mutex_unlock(&data->mtx); - - return r; -} - static ssize_t rfkill_fop_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { @@ -1122,8 +1111,11 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, goto out; } mutex_unlock(&data->mtx); + /* since we re-check and it just compares pointers, + * using !list_empty() without locking isn't a problem + */ ret = wait_event_interruptible(data->read_wait, - rfkill_readable(data)); + !list_empty(&data->events)); mutex_lock(&data->mtx); if (ret) diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index f26bdea875c1..a1cd778240cd 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -403,6 +403,8 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch) if (len <= cl->deficit) { cl->deficit -= len; skb = qdisc_dequeue_peeked(cl->qdisc); + if (unlikely(skb == NULL)) + goto out; if (cl->qdisc->q.qlen == 0) list_del(&cl->alist); diff --git a/net/sctp/input.c b/net/sctp/input.c index bf61dfb8e09e..49d2cc751386 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -935,15 +935,22 @@ static struct sctp_association *__sctp_lookup_association( struct sctp_transport **pt) { struct sctp_transport *t; + struct sctp_association *asoc = NULL; + rcu_read_lock(); t = sctp_addrs_lookup_transport(net, local, peer); - if (!t || t->dead) - return NULL; + if (!t || !sctp_transport_hold(t)) + goto out; - sctp_association_hold(t->asoc); + asoc = t->asoc; + sctp_association_hold(asoc); *pt = t; - return t->asoc; + sctp_transport_put(t); + +out: + rcu_read_unlock(); + return asoc; } /* Look up an association. protected by RCU read lock */ @@ -955,9 +962,7 @@ struct sctp_association *sctp_lookup_association(struct net *net, { struct sctp_association *asoc; - rcu_read_lock(); asoc = __sctp_lookup_association(net, laddr, paddr, transportp); - rcu_read_unlock(); return asoc; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 684c5b31563b..ded7d931a6a5 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -165,8 +165,6 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa list_for_each_entry_rcu(transport, &assoc->peer.transport_addr_list, transports) { addr = &transport->ipaddr; - if (transport->dead) - continue; af = sctp_get_af_specific(addr->sa.sa_family); if (af->cmp_addr(addr, primary)) { @@ -380,6 +378,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) } transport = (struct sctp_transport *)v; + if (!sctp_transport_hold(transport)) + return 0; assoc = transport->asoc; epb = &assoc->base; sk = epb->sk; @@ -412,6 +412,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) sk->sk_rcvbuf); seq_printf(seq, "\n"); + sctp_transport_put(transport); + return 0; } @@ -489,12 +491,12 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) } tsp = (struct sctp_transport *)v; + if (!sctp_transport_hold(tsp)) + return 0; assoc = tsp->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, transports) { - if (tsp->dead) - continue; /* * The remote address (ADDR) */ @@ -544,6 +546,8 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } + sctp_transport_put(tsp); + return 0; } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 2e21384697c2..b5327bb77458 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -259,12 +259,6 @@ void sctp_generate_t3_rtx_event(unsigned long peer) goto out_unlock; } - /* Is this transport really dead and just waiting around for - * the timer to let go of the reference? - */ - if (transport->dead) - goto out_unlock; - /* Run through the state machine. */ error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_T3_RTX), @@ -380,12 +374,6 @@ void sctp_generate_heartbeat_event(unsigned long data) goto out_unlock; } - /* Is this structure just waiting around for us to actually - * get destroyed? - */ - if (transport->dead) - goto out_unlock; - error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_HEARTBEAT), asoc->state, asoc->ep, asoc, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9bb80ec4c08f..5ca2ebfe0be8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6636,6 +6636,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; @@ -6659,6 +6660,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->sinfo->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index aab9e3f29755..a431c14044a4 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -132,8 +132,6 @@ fail: */ void sctp_transport_free(struct sctp_transport *transport) { - transport->dead = 1; - /* Try to delete the heartbeat timer. */ if (del_timer(&transport->hb_timer)) sctp_transport_put(transport); @@ -169,7 +167,7 @@ static void sctp_transport_destroy_rcu(struct rcu_head *head) */ static void sctp_transport_destroy(struct sctp_transport *transport) { - if (unlikely(!transport->dead)) { + if (unlikely(atomic_read(&transport->refcnt))) { WARN(1, "Attempt to destroy undead transport %p!\n", transport); return; } @@ -296,9 +294,9 @@ void sctp_transport_route(struct sctp_transport *transport, } /* Hold a reference to a transport. */ -void sctp_transport_hold(struct sctp_transport *transport) +int sctp_transport_hold(struct sctp_transport *transport) { - atomic_inc(&transport->refcnt); + return atomic_add_unless(&transport->refcnt, 1, 0); } /* Release a reference to a transport and clean up diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index ebc661d3b6e3..47f7da58a7f0 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -20,6 +20,7 @@ #include <linux/list.h> #include <linux/workqueue.h> #include <linux/if_vlan.h> +#include <linux/rtnetlink.h> #include <net/ip_fib.h> #include <net/switchdev.h> @@ -567,7 +568,6 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, } EXPORT_SYMBOL_GPL(switchdev_port_obj_dump); -static DEFINE_MUTEX(switchdev_mutex); static RAW_NOTIFIER_HEAD(switchdev_notif_chain); /** @@ -582,9 +582,9 @@ int register_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&switchdev_mutex); + rtnl_lock(); err = raw_notifier_chain_register(&switchdev_notif_chain, nb); - mutex_unlock(&switchdev_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(register_switchdev_notifier); @@ -600,9 +600,9 @@ int unregister_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&switchdev_mutex); + rtnl_lock(); err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb); - mutex_unlock(&switchdev_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); @@ -616,16 +616,17 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); * Call all network notifier blocks. This should be called by driver * when it needs to propagate hardware event. * Return values are same as for atomic_notifier_call_chain(). + * rtnl_lock must be held. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info) { int err; + ASSERT_RTNL(); + info->dev = dev; - mutex_lock(&switchdev_mutex); err = raw_notifier_call_chain(&switchdev_notif_chain, val, info); - mutex_unlock(&switchdev_mutex); return err; } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 350cca33ee0a..69ee2eeef968 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -289,15 +289,14 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid, struct sockaddr_tipc *addr, void *usr_data, void *buf, size_t len) { - struct tipc_subscriber *subscriber = usr_data; + struct tipc_subscriber *subscrb = usr_data; struct tipc_subscription *sub = NULL; struct tipc_net *tn = net_generic(net, tipc_net_id); - tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscriber, &sub); - if (sub) - tipc_nametbl_subscribe(sub); - else - tipc_conn_terminate(tn->topsrv, subscriber->conid); + if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub)) + return tipc_conn_terminate(tn->topsrv, subscrb->conid); + + tipc_nametbl_subscribe(sub); } /* Handle one request to establish a new subscriber */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c5bf5ef2bf89..49d5093eb055 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2339,6 +2339,7 @@ again: if (signal_pending(current)) { err = sock_intr_errno(timeo); + scm_destroy(&scm); goto out; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3b0ce1c484a3..547ceecc0523 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -231,20 +231,22 @@ static const struct ieee80211_regdomain world_regdom = { /* IEEE 802.11b/g, channels 1..11 */ REG_RULE(2412-10, 2462+10, 40, 6, 20, 0), /* IEEE 802.11b/g, channels 12..13. */ - REG_RULE(2467-10, 2472+10, 40, 6, 20, - NL80211_RRF_NO_IR), + REG_RULE(2467-10, 2472+10, 20, 6, 20, + NL80211_RRF_NO_IR | NL80211_RRF_AUTO_BW), /* IEEE 802.11 channel 14 - Only JP enables * this and for 802.11b only */ REG_RULE(2484-10, 2484+10, 20, 6, 20, NL80211_RRF_NO_IR | NL80211_RRF_NO_OFDM), /* IEEE 802.11a, channel 36..48 */ - REG_RULE(5180-10, 5240+10, 160, 6, 20, - NL80211_RRF_NO_IR), + REG_RULE(5180-10, 5240+10, 80, 6, 20, + NL80211_RRF_NO_IR | + NL80211_RRF_AUTO_BW), /* IEEE 802.11a, channel 52..64 - DFS required */ - REG_RULE(5260-10, 5320+10, 160, 6, 20, + REG_RULE(5260-10, 5320+10, 80, 6, 20, NL80211_RRF_NO_IR | + NL80211_RRF_AUTO_BW | NL80211_RRF_DFS), /* IEEE 802.11a, channel 100..144 - DFS required */ @@ -2745,7 +2747,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) const struct ieee80211_power_rule *power_rule = NULL; char bw[32], cac_time[32]; - pr_info(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n"); + pr_debug(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n"); for (i = 0; i < rd->n_reg_rules; i++) { reg_rule = &rd->reg_rules[i]; @@ -2772,7 +2774,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) * in certain regions */ if (power_rule->max_antenna_gain) - pr_info(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n", + pr_debug(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, bw, @@ -2780,7 +2782,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) power_rule->max_eirp, cac_time); else - pr_info(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n", + pr_debug(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, bw, @@ -2813,35 +2815,35 @@ static void print_regdomain(const struct ieee80211_regdomain *rd) struct cfg80211_registered_device *rdev; rdev = cfg80211_rdev_by_wiphy_idx(lr->wiphy_idx); if (rdev) { - pr_info("Current regulatory domain updated by AP to: %c%c\n", + pr_debug("Current regulatory domain updated by AP to: %c%c\n", rdev->country_ie_alpha2[0], rdev->country_ie_alpha2[1]); } else - pr_info("Current regulatory domain intersected:\n"); + pr_debug("Current regulatory domain intersected:\n"); } else - pr_info("Current regulatory domain intersected:\n"); + pr_debug("Current regulatory domain intersected:\n"); } else if (is_world_regdom(rd->alpha2)) { - pr_info("World regulatory domain updated:\n"); + pr_debug("World regulatory domain updated:\n"); } else { if (is_unknown_alpha2(rd->alpha2)) - pr_info("Regulatory domain changed to driver built-in settings (unknown country)\n"); + pr_debug("Regulatory domain changed to driver built-in settings (unknown country)\n"); else { if (reg_request_cell_base(lr)) - pr_info("Regulatory domain changed to country: %c%c by Cell Station\n", + pr_debug("Regulatory domain changed to country: %c%c by Cell Station\n", rd->alpha2[0], rd->alpha2[1]); else - pr_info("Regulatory domain changed to country: %c%c\n", + pr_debug("Regulatory domain changed to country: %c%c\n", rd->alpha2[0], rd->alpha2[1]); } } - pr_info(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region)); + pr_debug(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region)); print_rd_rules(rd); } static void print_regdomain_info(const struct ieee80211_regdomain *rd) { - pr_info("Regulatory domain: %c%c\n", rd->alpha2[0], rd->alpha2[1]); + pr_debug("Regulatory domain: %c%c\n", rd->alpha2[0], rd->alpha2[1]); print_rd_rules(rd); } @@ -2862,7 +2864,8 @@ static int reg_set_rd_user(const struct ieee80211_regdomain *rd, return -EALREADY; if (!is_valid_rd(rd)) { - pr_err("Invalid regulatory domain detected:\n"); + pr_err("Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } @@ -2898,7 +2901,8 @@ static int reg_set_rd_driver(const struct ieee80211_regdomain *rd, return -EALREADY; if (!is_valid_rd(rd)) { - pr_err("Invalid regulatory domain detected:\n"); + pr_err("Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } @@ -2956,7 +2960,8 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd, */ if (!is_valid_rd(rd)) { - pr_err("Invalid regulatory domain detected:\n"); + pr_err("Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 02db3cdff20f..7bff2ea831cf 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -27,7 +27,7 @@ endef # the rule that uses them - an example for that is the 'bionic' # feature check. ] # -FEATURE_TESTS ?= \ +FEATURE_TESTS_BASIC := \ backtrace \ dwarf \ fortify-source \ @@ -56,6 +56,25 @@ FEATURE_TESTS ?= \ get_cpuid \ bpf +# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list +# of all feature tests +FEATURE_TESTS_EXTRA := \ + bionic \ + compile-32 \ + compile-x32 \ + cplus-demangle \ + hello \ + libbabeltrace \ + liberty \ + liberty-z \ + libunwind-debug-frame + +FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC) + +ifeq ($(FEATURE_TESTS),all) + FEATURE_TESTS := $(FEATURE_TESTS_BASIC) $(FEATURE_TESTS_EXTRA) +endif + FEATURE_DISPLAY ?= \ dwarf \ glibc \ @@ -100,6 +119,14 @@ ifeq ($(feature-all), 1) # test-all.c passed - just set all the core feature flags to 1: # $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat))) + # + # test-all.c does not comprise these tests, so we need to + # for this case to get features proper values + # + $(call feature_check,compile-32) + $(call feature_check,compile-x32) + $(call feature_check,bionic) + $(call feature_check,libbabeltrace) else $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat))) endif diff --git a/tools/build/feature/test-compile.c b/tools/build/feature/test-compile.c index 31dbf45bf99c..c54e6551ae4c 100644 --- a/tools/build/feature/test-compile.c +++ b/tools/build/feature/test-compile.c @@ -1,4 +1,6 @@ +#include <stdio.h> int main(void) { + printf("Hello World!\n"); return 0; } diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 8334a5a9d5d7..7e543c3102d4 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -201,6 +201,7 @@ struct bpf_object { Elf_Data *data; } *reloc; int nr_reloc; + int maps_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -350,6 +351,7 @@ static struct bpf_object *bpf_object__new(const char *path, */ obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; + obj->efile.maps_shndx = -1; obj->loaded = false; @@ -529,12 +531,12 @@ bpf_object__init_maps(struct bpf_object *obj, void *data, } static int -bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx) +bpf_object__init_maps_name(struct bpf_object *obj) { int i; Elf_Data *symbols = obj->efile.symbols; - if (!symbols || maps_shndx < 0) + if (!symbols || obj->efile.maps_shndx < 0) return -EINVAL; for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { @@ -544,7 +546,7 @@ bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx) if (!gelf_getsym(symbols, i, &sym)) continue; - if (sym.st_shndx != maps_shndx) + if (sym.st_shndx != obj->efile.maps_shndx) continue; map_name = elf_strptr(obj->efile.elf, @@ -572,7 +574,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Scn *scn = NULL; - int idx = 0, err = 0, maps_shndx = -1; + int idx = 0, err = 0; /* Elf is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { @@ -625,7 +627,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) else if (strcmp(name, "maps") == 0) { err = bpf_object__init_maps(obj, data->d_buf, data->d_size); - maps_shndx = idx; + obj->efile.maps_shndx = idx; } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", @@ -674,8 +676,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) pr_warning("Corrupted ELF file: index of strtab invalid\n"); return LIBBPF_ERRNO__FORMAT; } - if (maps_shndx >= 0) - err = bpf_object__init_maps_name(obj, maps_shndx); + if (obj->efile.maps_shndx >= 0) + err = bpf_object__init_maps_name(obj); out: return err; } @@ -697,7 +699,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) static int bpf_program__collect_reloc(struct bpf_program *prog, size_t nr_maps, GElf_Shdr *shdr, - Elf_Data *data, Elf_Data *symbols) + Elf_Data *data, Elf_Data *symbols, + int maps_shndx) { int i, nrels; @@ -724,9 +727,6 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__FORMAT; } - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - pr_debug("relocation: insn_idx=%u\n", insn_idx); - if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { @@ -735,6 +735,15 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__FORMAT; } + if (sym.st_shndx != maps_shndx) { + pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", + prog->section_name, sym.st_shndx); + return -LIBBPF_ERRNO__RELOC; + } + + insn_idx = rel.r_offset / sizeof(struct bpf_insn); + pr_debug("relocation: insn_idx=%u\n", insn_idx); + if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n", insn_idx, insns[insn_idx].code); @@ -863,7 +872,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) err = bpf_program__collect_reloc(prog, nr_maps, shdr, data, - obj->efile.symbols); + obj->efile.symbols, + obj->efile.maps_shndx); if (err) return err; } diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index b9ca1e304158..74589c68558a 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -62,7 +62,7 @@ Given a $HOME/.perfconfig like this: medium = green, default normal = lightgray, default selected = white, lightgray - code = blue, default + jump_arrows = blue, default addr = magenta, default root = white, blue @@ -98,6 +98,204 @@ Given a $HOME/.perfconfig like this: order = caller sort-key = function +Variables +~~~~~~~~~ + +colors.*:: + The variables for customizing the colors used in the output for the + 'report', 'top' and 'annotate' in the TUI. They should specify the + foreground and background colors, separated by a comma, for example: + + medium = green, lightgray + + If you want to use the color configured for you terminal, just leave it + as 'default', for example: + + medium = default, lightgray + + Available colors: + red, yellow, green, cyan, gray, black, blue, + white, default, magenta, lightgray + + colors.top:: + 'top' means a overhead percentage which is more than 5%. + And values of this variable specify percentage colors. + Basic key values are foreground-color 'red' and + background-color 'default'. + colors.medium:: + 'medium' means a overhead percentage which has more than 0.5%. + Default values are 'green' and 'default'. + colors.normal:: + 'normal' means the rest of overhead percentages + except 'top', 'medium', 'selected'. + Default values are 'lightgray' and 'default'. + colors.selected:: + This selects the colors for the current entry in a list of entries + from sub-commands (top, report, annotate). + Default values are 'black' and 'lightgray'. + colors.jump_arrows:: + Colors for jump arrows on assembly code listings + such as 'jns', 'jmp', 'jane', etc. + Default values are 'blue', 'default'. + colors.addr:: + This selects colors for addresses from 'annotate'. + Default values are 'magenta', 'default'. + colors.root:: + Colors for headers in the output of a sub-commands (top, report). + Default values are 'white', 'blue'. + +tui.*, gtk.*:: + Subcommands that can be configured here are 'top', 'report' and 'annotate'. + These values are booleans, for example: + + [tui] + top = true + + will make the TUI be the default for the 'top' subcommand. Those will be + available if the required libs were detected at tool build time. + +buildid.*:: + buildid.dir:: + Each executable and shared library in modern distributions comes with a + content based identifier that, if available, will be inserted in a + 'perf.data' file header to, at analysis time find what is needed to do + symbol resolution, code annotation, etc. + + The recording tools also stores a hard link or copy in a per-user + directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms + and /proc/kcore files to be used at analysis time. + + The buildid.dir variable can be used to either change this directory + cache location, or to disable it altogether. If you want to disable it, + set buildid.dir to /dev/null. The default is $HOME/.debug + +annotate.*:: + These options work only for TUI. + These are in control of addresses, jump function, source code + in lines of assembly code from a specific program. + + annotate.hide_src_code:: + If a program which is analyzed has source code, + this option lets 'annotate' print a list of assembly code with the source code. + For example, let's see a part of a program. There're four lines. + If this option is 'true', they can be printed + without source code from a program as below. + + │ push %rbp + │ mov %rsp,%rbp + │ sub $0x10,%rsp + │ mov (%rdi),%rdx + + But if this option is 'false', source code of the part + can be also printed as below. Default is 'false'. + + │ struct rb_node *rb_next(const struct rb_node *node) + │ { + │ push %rbp + │ mov %rsp,%rbp + │ sub $0x10,%rsp + │ struct rb_node *parent; + │ + │ if (RB_EMPTY_NODE(node)) + │ mov (%rdi),%rdx + │ return n; + + annotate.use_offset:: + Basing on a first address of a loaded function, offset can be used. + Instead of using original addresses of assembly code, + addresses subtracted from a base address can be printed. + Let's illustrate an example. + If a base address is 0XFFFFFFFF81624d50 as below, + + ffffffff81624d50 <load0> + + an address on assembly code has a specific absolute address as below + + ffffffff816250b8:│ mov 0x8(%r14),%rdi + + but if use_offset is 'true', an address subtracted from a base address is printed. + Default is true. This option is only applied to TUI. + + 368:│ mov 0x8(%r14),%rdi + + annotate.jump_arrows:: + There can be jump instruction among assembly code. + Depending on a boolean value of jump_arrows, + arrows can be printed or not which represent + where do the instruction jump into as below. + + │ ┌──jmp 1333 + │ │ xchg %ax,%ax + │1330:│ mov %r15,%r10 + │1333:└─→cmp %r15,%r14 + + If jump_arrow is 'false', the arrows isn't printed as below. + Default is 'false'. + + │ ↓ jmp 1333 + │ xchg %ax,%ax + │1330: mov %r15,%r10 + │1333: cmp %r15,%r14 + + annotate.show_linenr:: + When showing source code if this option is 'true', + line numbers are printed as below. + + │1628 if (type & PERF_SAMPLE_IDENTIFIER) { + │ ↓ jne 508 + │1628 data->id = *array; + │1629 array++; + │1630 } + + However if this option is 'false', they aren't printed as below. + Default is 'false'. + + │ if (type & PERF_SAMPLE_IDENTIFIER) { + │ ↓ jne 508 + │ data->id = *array; + │ array++; + │ } + + annotate.show_nr_jumps:: + Let's see a part of assembly code. + + │1382: movb $0x1,-0x270(%rbp) + + If use this, the number of branches jumping to that address can be printed as below. + Default is 'false'. + + │1 1382: movb $0x1,-0x270(%rbp) + + annotate.show_total_period:: + To compare two records on an instruction base, with this option + provided, display total number of samples that belong to a line + in assembly code. If this option is 'true', total periods are printed + instead of percent values as below. + + 302 │ mov %eax,%eax + + But if this option is 'false', percent values for overhead are printed i.e. + Default is 'false'. + + 99.93 │ mov %eax,%eax + +hist.*:: + hist.percentage:: + This option control the way to calculate overhead of filtered entries - + that means the value of this option is effective only if there's a + filter (by comm, dso or symbol name). Suppose a following example: + + Overhead Symbols + ........ ....... + 33.33% foo + 33.33% bar + 33.33% baz + + This is an original overhead and we'll filter out the first 'foo' + entry. The value of 'relative' would increase the overhead of 'bar' + and 'baz' to 50.00% for each, while 'absolute' would show their + current overhead (33.33%). + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 8a301f6afb37..89cab84e92fd 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -117,6 +117,22 @@ OPTIONS And default sort keys are changed to comm, dso_from, symbol_from, dso_to and symbol_to, see '--branch-stack'. + If the --mem-mode option is used, the following sort keys are also available + (incompatible with --branch-stack): + symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline. + + - symbol_daddr: name of data symbol being executed on at the time of sample + - dso_daddr: name of library or module containing the data being executed + on at the time of the sample + - locked: whether the bus was locked at the time of the sample + - tlb: type of tlb access for the data at the time of the sample + - mem: type of memory access for the data at the time of the sample + - snoop: type of snoop (if any) for the data at the time of the sample + - dcacheline: the cacheline the data address is on at the time of the sample + + And the default sort keys are changed to local_weight, mem, sym, dso, + symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. + If the data file has tracepoint event(s), following (dynamic) sort keys are also available: trace, trace_fields, [<event>.]<field>[/raw] @@ -151,22 +167,6 @@ OPTIONS By default, every sort keys not specified in -F will be appended automatically. - If --mem-mode option is used, following sort keys are also available - (incompatible with --branch-stack): - symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline. - - - symbol_daddr: name of data symbol being executed on at the time of sample - - dso_daddr: name of library or module containing the data being executed - on at the time of sample - - locked: whether the bus was locked at the time of sample - - tlb: type of tlb access for the data at the time of sample - - mem: type of memory access for the data at the time of sample - - snoop: type of snoop (if any) for the data at the time of sample - - dcacheline: the cacheline the data address is on at the time of sample - - And default sort keys are changed to local_weight, mem, sym, dso, - symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. - -p:: --parent=<regex>:: A regex filter to identify parent. The parent is a caller of this @@ -351,7 +351,10 @@ OPTIONS --percent-limit:: Do not show entries which have an overhead under that percent. - (Default: 0). + (Default: 0). Note that this option also sets the percent limit (threshold) + of callchains. However the default value of callchain threshold is + different than the default value of hist entries. Please see the + --call-graph option for details. --percentage:: Determine how to display the overhead percentage of filtered entries. diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example index 767ea2436e1c..1d8d5bc4cd2d 100644 --- a/tools/perf/Documentation/perfconfig.example +++ b/tools/perf/Documentation/perfconfig.example @@ -5,7 +5,7 @@ medium = green, lightgray normal = black, lightgray selected = lightgray, magenta - code = blue, lightgray + jump_arrows = blue, lightgray addr = magenta, lightgray [tui] diff --git a/tools/perf/Makefile b/tools/perf/Makefile index dcd9a70c7193..4b68f465195c 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -75,10 +75,17 @@ clean: $(make) # -# The build-test target is not really parallel, don't print the jobs info: +# The build-test target is not really parallel, don't print the jobs info, +# it also uses only the tests/make targets that don't pollute the source +# repository, i.e. that uses O= or builds the tarpkg outside the source +# repo directories. +# +# For a full test, use: +# +# make -C tools/perf -f tests/make # build-test: - @$(MAKE) SHUF=1 -f tests/make --no-print-directory + @$(MAKE) SHUF=1 -f tests/make REUSE_FEATURES_DUMP=1 MK=Makefile --no-print-directory tarpkg out # # All other targets get passed through: diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5d34815c7ccb..0ef3d97d7954 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -165,7 +165,16 @@ ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),) endif endif +# Set FEATURE_TESTS to 'all' so all possible feature checkers are executed. +# Without this setting the output feature dump file misses some features, for +# example, liberty. Select all checkers so we won't get an incomplete feature +# dump file. ifeq ($(config),1) +ifdef MAKECMDGOALS +ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump) +FEATURE_TESTS := all +endif +endif include config/Makefile endif @@ -618,7 +627,7 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \ - $(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c + $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index 7fbca175099e..9f9cea3478fd 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -1,3 +1,5 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif + +HAVE_KVM_STAT_SUPPORT := 1 diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 7b8b0d1a1b62..c8fe2074d217 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,5 +1,6 @@ libperf-y += header.o libperf-y += sym-handling.o +libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_DWARF) += skip-callchain-idx.o diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h new file mode 100644 index 000000000000..0dd6b7f2d44f --- /dev/null +++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h @@ -0,0 +1,123 @@ +#ifndef ARCH_PERF_BOOK3S_HV_HCALLS_H +#define ARCH_PERF_BOOK3S_HV_HCALLS_H + +/* + * PowerPC HCALL codes : hcall code to name mapping + */ +#define kvm_trace_symbol_hcall \ + {0x4, "H_REMOVE"}, \ + {0x8, "H_ENTER"}, \ + {0xc, "H_READ"}, \ + {0x10, "H_CLEAR_MOD"}, \ + {0x14, "H_CLEAR_REF"}, \ + {0x18, "H_PROTECT"}, \ + {0x1c, "H_GET_TCE"}, \ + {0x20, "H_PUT_TCE"}, \ + {0x24, "H_SET_SPRG0"}, \ + {0x28, "H_SET_DABR"}, \ + {0x2c, "H_PAGE_INIT"}, \ + {0x30, "H_SET_ASR"}, \ + {0x34, "H_ASR_ON"}, \ + {0x38, "H_ASR_OFF"}, \ + {0x3c, "H_LOGICAL_CI_LOAD"}, \ + {0x40, "H_LOGICAL_CI_STORE"}, \ + {0x44, "H_LOGICAL_CACHE_LOAD"}, \ + {0x48, "H_LOGICAL_CACHE_STORE"}, \ + {0x4c, "H_LOGICAL_ICBI"}, \ + {0x50, "H_LOGICAL_DCBF"}, \ + {0x54, "H_GET_TERM_CHAR"}, \ + {0x58, "H_PUT_TERM_CHAR"}, \ + {0x5c, "H_REAL_TO_LOGICAL"}, \ + {0x60, "H_HYPERVISOR_DATA"}, \ + {0x64, "H_EOI"}, \ + {0x68, "H_CPPR"}, \ + {0x6c, "H_IPI"}, \ + {0x70, "H_IPOLL"}, \ + {0x74, "H_XIRR"}, \ + {0x78, "H_MIGRATE_DMA"}, \ + {0x7c, "H_PERFMON"}, \ + {0xdc, "H_REGISTER_VPA"}, \ + {0xe0, "H_CEDE"}, \ + {0xe4, "H_CONFER"}, \ + {0xe8, "H_PROD"}, \ + {0xec, "H_GET_PPP"}, \ + {0xf0, "H_SET_PPP"}, \ + {0xf4, "H_PURR"}, \ + {0xf8, "H_PIC"}, \ + {0xfc, "H_REG_CRQ"}, \ + {0x100, "H_FREE_CRQ"}, \ + {0x104, "H_VIO_SIGNAL"}, \ + {0x108, "H_SEND_CRQ"}, \ + {0x110, "H_COPY_RDMA"}, \ + {0x114, "H_REGISTER_LOGICAL_LAN"}, \ + {0x118, "H_FREE_LOGICAL_LAN"}, \ + {0x11c, "H_ADD_LOGICAL_LAN_BUFFER"}, \ + {0x120, "H_SEND_LOGICAL_LAN"}, \ + {0x124, "H_BULK_REMOVE"}, \ + {0x130, "H_MULTICAST_CTRL"}, \ + {0x134, "H_SET_XDABR"}, \ + {0x138, "H_STUFF_TCE"}, \ + {0x13c, "H_PUT_TCE_INDIRECT"}, \ + {0x14c, "H_CHANGE_LOGICAL_LAN_MAC"}, \ + {0x150, "H_VTERM_PARTNER_INFO"}, \ + {0x154, "H_REGISTER_VTERM"}, \ + {0x158, "H_FREE_VTERM"}, \ + {0x15c, "H_RESET_EVENTS"}, \ + {0x160, "H_ALLOC_RESOURCE"}, \ + {0x164, "H_FREE_RESOURCE"}, \ + {0x168, "H_MODIFY_QP"}, \ + {0x16c, "H_QUERY_QP"}, \ + {0x170, "H_REREGISTER_PMR"}, \ + {0x174, "H_REGISTER_SMR"}, \ + {0x178, "H_QUERY_MR"}, \ + {0x17c, "H_QUERY_MW"}, \ + {0x180, "H_QUERY_HCA"}, \ + {0x184, "H_QUERY_PORT"}, \ + {0x188, "H_MODIFY_PORT"}, \ + {0x18c, "H_DEFINE_AQP1"}, \ + {0x190, "H_GET_TRACE_BUFFER"}, \ + {0x194, "H_DEFINE_AQP0"}, \ + {0x198, "H_RESIZE_MR"}, \ + {0x19c, "H_ATTACH_MCQP"}, \ + {0x1a0, "H_DETACH_MCQP"}, \ + {0x1a4, "H_CREATE_RPT"}, \ + {0x1a8, "H_REMOVE_RPT"}, \ + {0x1ac, "H_REGISTER_RPAGES"}, \ + {0x1b0, "H_DISABLE_AND_GETC"}, \ + {0x1b4, "H_ERROR_DATA"}, \ + {0x1b8, "H_GET_HCA_INFO"}, \ + {0x1bc, "H_GET_PERF_COUNT"}, \ + {0x1c0, "H_MANAGE_TRACE"}, \ + {0x1d4, "H_FREE_LOGICAL_LAN_BUFFER"}, \ + {0x1d8, "H_POLL_PENDING"}, \ + {0x1e4, "H_QUERY_INT_STATE"}, \ + {0x244, "H_ILLAN_ATTRIBUTES"}, \ + {0x250, "H_MODIFY_HEA_QP"}, \ + {0x254, "H_QUERY_HEA_QP"}, \ + {0x258, "H_QUERY_HEA"}, \ + {0x25c, "H_QUERY_HEA_PORT"}, \ + {0x260, "H_MODIFY_HEA_PORT"}, \ + {0x264, "H_REG_BCMC"}, \ + {0x268, "H_DEREG_BCMC"}, \ + {0x26c, "H_REGISTER_HEA_RPAGES"}, \ + {0x270, "H_DISABLE_AND_GET_HEA"}, \ + {0x274, "H_GET_HEA_INFO"}, \ + {0x278, "H_ALLOC_HEA_RESOURCE"}, \ + {0x284, "H_ADD_CONN"}, \ + {0x288, "H_DEL_CONN"}, \ + {0x298, "H_JOIN"}, \ + {0x2a4, "H_VASI_STATE"}, \ + {0x2b0, "H_ENABLE_CRQ"}, \ + {0x2b8, "H_GET_EM_PARMS"}, \ + {0x2d0, "H_SET_MPP"}, \ + {0x2d4, "H_GET_MPP"}, \ + {0x2ec, "H_HOME_NODE_ASSOCIATIVITY"}, \ + {0x2f4, "H_BEST_ENERGY"}, \ + {0x2fc, "H_XIRR_X"}, \ + {0x300, "H_RANDOM"}, \ + {0x304, "H_COP"}, \ + {0x314, "H_GET_MPP_X"}, \ + {0x31c, "H_SET_MODE"}, \ + {0xf000, "H_RTAS"} \ + +#endif diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h new file mode 100644 index 000000000000..e68ba2da8970 --- /dev/null +++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h @@ -0,0 +1,33 @@ +#ifndef ARCH_PERF_BOOK3S_HV_EXITS_H +#define ARCH_PERF_BOOK3S_HV_EXITS_H + +/* + * PowerPC Interrupt vectors : exit code to name mapping + */ + +#define kvm_trace_symbol_exit \ + {0x0, "RETURN_TO_HOST"}, \ + {0x100, "SYSTEM_RESET"}, \ + {0x200, "MACHINE_CHECK"}, \ + {0x300, "DATA_STORAGE"}, \ + {0x380, "DATA_SEGMENT"}, \ + {0x400, "INST_STORAGE"}, \ + {0x480, "INST_SEGMENT"}, \ + {0x500, "EXTERNAL"}, \ + {0x501, "EXTERNAL_LEVEL"}, \ + {0x502, "EXTERNAL_HV"}, \ + {0x600, "ALIGNMENT"}, \ + {0x700, "PROGRAM"}, \ + {0x800, "FP_UNAVAIL"}, \ + {0x900, "DECREMENTER"}, \ + {0x980, "HV_DECREMENTER"}, \ + {0xc00, "SYSCALL"}, \ + {0xd00, "TRACE"}, \ + {0xe00, "H_DATA_STORAGE"}, \ + {0xe20, "H_INST_STORAGE"}, \ + {0xe40, "H_EMUL_ASSIST"}, \ + {0xf00, "PERFMON"}, \ + {0xf20, "ALTIVEC"}, \ + {0xf40, "VSX"} + +#endif diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c new file mode 100644 index 000000000000..74eee30398f8 --- /dev/null +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -0,0 +1,170 @@ +#include "util/kvm-stat.h" +#include "util/parse-events.h" +#include "util/debug.h" + +#include "book3s_hv_exits.h" +#include "book3s_hcalls.h" + +#define NR_TPS 4 + +const char *vcpu_id_str = "vcpu_id"; +const int decode_str_len = 40; +const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter"; +const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit"; + +define_exit_reasons_table(hv_exit_reasons, kvm_trace_symbol_exit); +define_exit_reasons_table(hcall_reasons, kvm_trace_symbol_hcall); + +/* Tracepoints specific to ppc_book3s_hv */ +const char *ppc_book3s_hv_kvm_tp[] = { + "kvm_hv:kvm_guest_enter", + "kvm_hv:kvm_guest_exit", + "kvm_hv:kvm_hcall_enter", + "kvm_hv:kvm_hcall_exit", + NULL, +}; + +/* 1 extra placeholder for NULL */ +const char *kvm_events_tp[NR_TPS + 1]; +const char *kvm_exit_reason; + +static void hcall_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = perf_evsel__intval(evsel, sample, "req"); +} + +static const char *get_hcall_exit_reason(u64 exit_code) +{ + struct exit_reasons_table *tbl = hcall_reasons; + + while (tbl->reason != NULL) { + if (tbl->exit_code == exit_code) + return tbl->reason; + tbl++; + } + + pr_debug("Unknown hcall code: %lld\n", + (unsigned long long)exit_code); + return "UNKNOWN"; +} + +static bool hcall_event_end(struct perf_evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return (!strcmp(evsel->name, kvm_events_tp[3])); +} + +static bool hcall_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + if (!strcmp(evsel->name, kvm_events_tp[2])) { + hcall_event_get_key(evsel, sample, key); + return true; + } + + return false; +} +static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + const char *hcall_reason = get_hcall_exit_reason(key->key); + + scnprintf(decode, decode_str_len, "%s", hcall_reason); +} + +static struct kvm_events_ops hcall_events = { + .is_begin_event = hcall_event_begin, + .is_end_event = hcall_event_end, + .decode_key = hcall_event_decode_key, + .name = "HCALL-EVENT", +}; + +static struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +struct kvm_reg_events_ops kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { .name = "hcall", .ops = &hcall_events }, + { NULL, NULL }, +}; + +const char * const kvm_skip_events[] = { + NULL, +}; + + +static int is_tracepoint_available(const char *str, struct perf_evlist *evlist) +{ + struct parse_events_error err; + int ret; + + err.str = NULL; + ret = parse_events(evlist, str, &err); + if (err.str) + pr_err("%s : %s\n", str, err.str); + return ret; +} + +static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm, + struct perf_evlist *evlist) +{ + const char **events_ptr; + int i, nr_tp = 0, err = -1; + + /* Check for book3s_hv tracepoints */ + for (events_ptr = ppc_book3s_hv_kvm_tp; *events_ptr; events_ptr++) { + err = is_tracepoint_available(*events_ptr, evlist); + if (err) + return -1; + nr_tp++; + } + + for (i = 0; i < nr_tp; i++) + kvm_events_tp[i] = ppc_book3s_hv_kvm_tp[i]; + + kvm_events_tp[i] = NULL; + kvm_exit_reason = "trap"; + kvm->exit_reasons = hv_exit_reasons; + kvm->exit_reasons_isa = "HV"; + + return 0; +} + +/* Wrapper to setup kvm tracepoints */ +static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm) +{ + struct perf_evlist *evlist = perf_evlist__new(); + + if (evlist == NULL) + return -ENOMEM; + + /* Right now, only supported on book3s_hv */ + return ppc__setup_book3s_hv(kvm, evlist); +} + +int setup_kvm_events_tp(struct perf_kvm_stat *kvm) +{ + return ppc__setup_kvm_tp(kvm); +} + +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) +{ + int ret; + + ret = ppc__setup_kvm_tp(kvm); + if (ret) { + kvm->exit_reasons = NULL; + kvm->exit_reasons_isa = NULL; + } + + return ret; +} diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index a5dbc07ec9dc..ed57df2e6d68 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -10,7 +10,7 @@ */ #include "../../util/kvm-stat.h" -#include <asm/kvm_perf.h> +#include <asm/sie.h> define_exit_reasons_table(sie_exit_reasons, sie_intercept_code); define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes); @@ -18,6 +18,12 @@ define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes); define_exit_reasons_table(sie_diagnose_codes, diagnose_codes); define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes); +const char *vcpu_id_str = "id"; +const int decode_str_len = 40; +const char *kvm_exit_reason = "icptcode"; +const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter"; +const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit"; + static void event_icpt_insn_get_key(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key) @@ -73,7 +79,7 @@ static struct kvm_events_ops exit_events = { .name = "VM-EXIT" }; -const char * const kvm_events_tp[] = { +const char *kvm_events_tp[] = { "kvm:kvm_s390_sie_enter", "kvm:kvm_s390_sie_exit", "kvm:kvm_s390_intercept_instruction", diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 8d8150f1cf9b..d66f9ad4df2e 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -60,7 +60,9 @@ struct branch { u64 misc; }; -static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused) +static size_t +intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { return INTEL_BTS_AUXTRACE_PRIV_SIZE; } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index f05daacc9e78..6f7d453b0e32 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -273,7 +273,9 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu) return attr; } -static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused) +static size_t +intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { return INTEL_PT_AUXTRACE_PRIV_SIZE; } diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index 14e4e668fad7..b63d4be655a2 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -1,5 +1,7 @@ #include "../../util/kvm-stat.h" -#include <asm/kvm_perf.h> +#include <asm/svm.h> +#include <asm/vmx.h> +#include <asm/kvm.h> define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS); define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS); @@ -11,6 +13,12 @@ static struct kvm_events_ops exit_events = { .name = "VM-EXIT" }; +const char *vcpu_id_str = "vcpu_id"; +const int decode_str_len = 20; +const char *kvm_exit_reason = "exit_reason"; +const char *kvm_entry_trace = "kvm:kvm_entry"; +const char *kvm_exit_trace = "kvm:kvm_exit"; + /* * For the mmio events, we treat: * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry @@ -65,7 +73,7 @@ static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char *decode) { - scnprintf(decode, DECODE_STR_LEN, "%#lx:%s", + scnprintf(decode, decode_str_len, "%#lx:%s", (unsigned long)key->key, key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); } @@ -109,7 +117,7 @@ static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char *decode) { - scnprintf(decode, DECODE_STR_LEN, "%#llx:%s", + scnprintf(decode, decode_str_len, "%#llx:%s", (unsigned long long)key->key, key->info ? "POUT" : "PIN"); } @@ -121,7 +129,7 @@ static struct kvm_events_ops ioport_events = { .name = "IO Port Access" }; -const char * const kvm_events_tp[] = { +const char *kvm_events_tp[] = { "kvm:kvm_entry", "kvm:kvm_exit", "kvm:kvm_mmio", diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index cc5c1267c738..cfe366375c4b 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -245,7 +245,7 @@ static int __cmd_annotate(struct perf_annotate *ann) hists__collapse_resort(hists, NULL); /* Don't sort callchain */ perf_evsel__reset_sample_bit(pos, CALLCHAIN); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(pos, NULL); if (symbol_conf.event_group && !perf_evsel__is_group_leader(pos)) diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index d93bff7fc0e4..632efc6b79a0 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -38,19 +38,7 @@ static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid) static int build_id_cache__kcore_dir(char *dir, size_t sz) { - struct timeval tv; - struct tm tm; - char dt[32]; - - if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm)) - return -1; - - if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm)) - return -1; - - scnprintf(dir, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000); - - return 0; + return fetch_current_timestamp(dir, sz); } static bool same_kallsyms_reloc(const char *from_dir, char *to_dir) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 4418d9214872..bff666458b28 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -30,7 +30,6 @@ #include <math.h> #ifdef HAVE_KVM_STAT_SUPPORT -#include <asm/kvm_perf.h> #include "util/kvm-stat.h" void exit_event_get_key(struct perf_evsel *evsel, @@ -38,12 +37,12 @@ void exit_event_get_key(struct perf_evsel *evsel, struct event_key *key) { key->info = 0; - key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON); + key->key = perf_evsel__intval(evsel, sample, kvm_exit_reason); } bool kvm_exit_event(struct perf_evsel *evsel) { - return !strcmp(evsel->name, KVM_EXIT_TRACE); + return !strcmp(evsel->name, kvm_exit_trace); } bool exit_event_begin(struct perf_evsel *evsel, @@ -59,7 +58,7 @@ bool exit_event_begin(struct perf_evsel *evsel, bool kvm_entry_event(struct perf_evsel *evsel) { - return !strcmp(evsel->name, KVM_ENTRY_TRACE); + return !strcmp(evsel->name, kvm_entry_trace); } bool exit_event_end(struct perf_evsel *evsel, @@ -91,7 +90,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm, const char *exit_reason = get_exit_reason(kvm, key->exit_reasons, key->key); - scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason); + scnprintf(decode, decode_str_len, "%s", exit_reason); } static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) @@ -357,7 +356,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm, time_diff = sample->time - time_begin; if (kvm->duration && time_diff > kvm->duration) { - char decode[DECODE_STR_LEN]; + char decode[decode_str_len]; kvm->events_ops->decode_key(kvm, &event->key, decode); if (!skip_event(decode)) { @@ -385,7 +384,8 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread, return NULL; } - vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID); + vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, + vcpu_id_str); thread__set_priv(thread, vcpu_record); } @@ -574,7 +574,7 @@ static void show_timeofday(void) static void print_result(struct perf_kvm_stat *kvm) { - char decode[DECODE_STR_LEN]; + char decode[decode_str_len]; struct kvm_event *event; int vcpu = kvm->trace_vcpu; @@ -585,7 +585,7 @@ static void print_result(struct perf_kvm_stat *kvm) pr_info("\n\n"); print_vcpu_info(kvm); - pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name); + pr_info("%*s ", decode_str_len, kvm->events_ops->name); pr_info("%10s ", "Samples"); pr_info("%9s ", "Samples%"); @@ -604,7 +604,7 @@ static void print_result(struct perf_kvm_stat *kvm) min = get_event_min(event, vcpu); kvm->events_ops->decode_key(kvm, &event->key, decode); - pr_info("%*s ", DECODE_STR_LEN, decode); + pr_info("%*s ", decode_str_len, decode); pr_info("%10llu ", (unsigned long long)ecount); pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100); pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100); @@ -1132,6 +1132,11 @@ exit: _p; \ }) +int __weak setup_kvm_events_tp(struct perf_kvm_stat *kvm __maybe_unused) +{ + return 0; +} + static int kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) { @@ -1148,7 +1153,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) NULL }; const char * const *events_tp; + int ret; + events_tp_size = 0; + ret = setup_kvm_events_tp(kvm); + if (ret < 0) { + pr_err("Unable to setup the kvm tracepoints\n"); + return ret; + } for (events_tp = kvm_events_tp; *events_tp; events_tp++) events_tp_size++; @@ -1377,6 +1389,12 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, /* * generate the event list */ + err = setup_kvm_events_tp(kvm); + if (err < 0) { + pr_err("Unable to setup the kvm tracepoints\n"); + return err; + } + kvm->evlist = kvm_live_event_list(); if (kvm->evlist == NULL) { err = -1; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 319712a4e02b..0ee0d5cd31a7 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -49,7 +49,9 @@ struct record { const char *progname; int realtime_prio; bool no_buildid; + bool no_buildid_set; bool no_buildid_cache; + bool no_buildid_cache_set; bool buildid_all; unsigned long long samples; }; @@ -1097,10 +1099,12 @@ struct option __record_options[] = { OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"), OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples, "don't sample"), - OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache, - "do not update the buildid cache"), - OPT_BOOLEAN('B', "no-buildid", &record.no_buildid, - "do not collect buildids in perf.data"), + OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache, + &record.no_buildid_cache_set, + "do not update the buildid cache"), + OPT_BOOLEAN_SET('B', "no-buildid", &record.no_buildid, + &record.no_buildid_set, + "do not collect buildids in perf.data"), OPT_CALLBACK('G', "cgroup", &record.evlist, "name", "monitor event in cgroup name only", parse_cgroups), diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 2bf537f190a0..1eab50ac1ef6 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -75,7 +75,10 @@ static int report__config(const char *var, const char *value, void *cb) return 0; } if (!strcmp(var, "report.percent-limit")) { - rep->min_percent = strtof(value, NULL); + double pcnt = strtof(value, NULL); + + rep->min_percent = pcnt; + callchain_param.min_percent = pcnt; return 0; } if (!strcmp(var, "report.children")) { @@ -504,7 +507,7 @@ static void report__output_resort(struct report *rep) ui_progress__init(&prog, rep->nr_entries, "Sorting events for output..."); evlist__for_each(rep->session->evlist, pos) - hists__output_resort(evsel__hists(pos), &prog); + perf_evsel__output_resort(pos, &prog); ui_progress__finish(); } @@ -633,8 +636,10 @@ parse_percent_limit(const struct option *opt, const char *str, int unset __maybe_unused) { struct report *rep = opt->value; + double pcnt = strtof(str, NULL); - rep->min_percent = strtof(str, NULL); + rep->min_percent = pcnt; + callchain_param.min_percent = pcnt; return 0; } @@ -907,15 +912,6 @@ repeat: symbol_conf.cumulate_callchain = false; } - if (setup_sorting(session->evlist) < 0) { - if (sort_order) - parse_options_usage(report_usage, options, "s", 1); - if (field_order) - parse_options_usage(sort_order ? NULL : report_usage, - options, "F", 1); - goto error; - } - /* Force tty output for header output and per-thread stat. */ if (report.header || report.header_only || report.show_threads) use_browser = 0; @@ -925,6 +921,15 @@ repeat: else use_browser = 0; + if (setup_sorting(session->evlist) < 0) { + if (sort_order) + parse_options_usage(report_usage, options, "s", 1); + if (field_order) + parse_options_usage(sort_order ? NULL : report_usage, + options, "F", 1); + goto error; + } + if (report.header || report.header_only) { perf_session__fprintf_info(session, stdout, report.show_full_info); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index bf01cbb0ef23..a75de3940b97 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -252,7 +252,8 @@ static void perf_top__print_sym_table(struct perf_top *top) char bf[160]; int printed = 0; const int win_width = top->winsize.ws_col - 1; - struct hists *hists = evsel__hists(top->sym_evsel); + struct perf_evsel *evsel = top->sym_evsel; + struct hists *hists = evsel__hists(evsel); puts(CONSOLE_CLEAR); @@ -288,7 +289,7 @@ static void perf_top__print_sym_table(struct perf_top *top) } hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); @@ -540,6 +541,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) static void perf_top__sort_new_samples(void *arg) { struct perf_top *t = arg; + struct perf_evsel *evsel = t->sym_evsel; struct hists *hists; perf_top__reset_sample_counters(t); @@ -547,7 +549,7 @@ static void perf_top__sort_new_samples(void *arg) if (t->evlist->selected != NULL) t->sym_evsel = t->evlist->selected; - hists = evsel__hists(t->sym_evsel); + hists = evsel__hists(evsel); if (t->evlist->enabled) { if (t->zero) { @@ -559,7 +561,7 @@ static void perf_top__sort_new_samples(void *arg) } hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); } static void *display_thread_tui(void *arg) @@ -1243,6 +1245,13 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) /* display thread wants entries to be collapsed in a different tree */ sort__need_collapse = 1; + if (top.use_stdio) + use_browser = 0; + else if (top.use_tui) + use_browser = 1; + + setup_browser(false); + if (setup_sorting(top.evlist) < 0) { if (sort_order) parse_options_usage(top_usage, options, "s", 1); @@ -1252,13 +1261,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) goto out_delete_evlist; } - if (top.use_stdio) - use_browser = 0; - else if (top.use_tui) - use_browser = 1; - - setup_browser(false); - status = target__validate(target); if (status) { target__strerror(target, status, errbuf, BUFSIZ); diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 511141b102e8..0045a5ddd0ca 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -61,50 +61,45 @@ endif ifeq ($(LIBUNWIND_LIBS),) NO_LIBUNWIND := 1 -else - # - # For linking with debug library, run like: - # - # make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ - # - ifdef LIBUNWIND_DIR - LIBUNWIND_CFLAGS = -I$(LIBUNWIND_DIR)/include - LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib - endif - LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS) - - # Set per-feature check compilation flags - FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS) - FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) - FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS) - FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) endif +# +# For linking with debug library, run like: +# +# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ +# +ifdef LIBUNWIND_DIR + LIBUNWIND_CFLAGS = -I$(LIBUNWIND_DIR)/include + LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib +endif +LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS) + +# Set per-feature check compilation flags +FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS) +FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) +FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS) +FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) ifeq ($(NO_PERF_REGS),0) CFLAGS += -DHAVE_PERF_REGS_SUPPORT endif -ifndef NO_LIBELF - # for linking with debug library, run like: - # make DEBUG=1 LIBDW_DIR=/opt/libdw/ - ifdef LIBDW_DIR - LIBDW_CFLAGS := -I$(LIBDW_DIR)/include - LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib - endif - FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) - FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw +# for linking with debug library, run like: +# make DEBUG=1 LIBDW_DIR=/opt/libdw/ +ifdef LIBDW_DIR + LIBDW_CFLAGS := -I$(LIBDW_DIR)/include + LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib endif +FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) +FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw -ifdef LIBBABELTRACE - # for linking with debug library, run like: - # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/ - ifdef LIBBABELTRACE_DIR - LIBBABELTRACE_CFLAGS := -I$(LIBBABELTRACE_DIR)/include - LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib - endif - FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) - FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf +# for linking with debug library, run like: +# make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/ +ifdef LIBBABELTRACE_DIR + LIBBABELTRACE_CFLAGS := -I$(LIBBABELTRACE_DIR)/include + LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib endif +FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) +FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi # include ARCH specific config @@ -145,28 +140,26 @@ ifdef PARSER_DEBUG $(call detected_var,PARSER_DEBUG_FLEX) endif -ifndef NO_LIBPYTHON - # Try different combinations to accommodate systems that only have - # python[2][-config] in weird combinations but always preferring - # python2 and python2-config as per pep-0394. If we catch a - # python[-config] in version 3, the version check will kill it. - PYTHON2 := $(if $(call get-executable,python2),python2,python) - override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2)) - PYTHON2_CONFIG := \ - $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config) - override PYTHON_CONFIG := \ - $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG)) +# Try different combinations to accommodate systems that only have +# python[2][-config] in weird combinations but always preferring +# python2 and python2-config as per pep-0394. If we catch a +# python[-config] in version 3, the version check will kill it. +PYTHON2 := $(if $(call get-executable,python2),python2,python) +override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2)) +PYTHON2_CONFIG := \ + $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config) +override PYTHON_CONFIG := \ + $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG)) - PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) +PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) - PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) - PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) +PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) +PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) - FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) - FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS) - FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) -endif +FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) +FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) +FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS) +FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) CFLAGS += -fno-omit-frame-pointer CFLAGS += -ggdb3 diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore index bf016c439fbd..8cc30e731c73 100644 --- a/tools/perf/tests/.gitignore +++ b/tools/perf/tests/.gitignore @@ -1,3 +1,4 @@ llvm-src-base.c llvm-src-kbuild.c llvm-src-prologue.c +llvm-src-relocation.c diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 614899b88b37..1ba628ed049a 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -31,7 +31,7 @@ perf-y += sample-parsing.o perf-y += parse-no-sample-id-all.o perf-y += kmod-path.o perf-y += thread-map.o -perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o +perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o perf-y += bpf.o perf-y += topology.o perf-y += cpumap.o @@ -59,6 +59,13 @@ $(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ $(Q)echo ';' >> $@ +$(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/Build + $(call rule_mkdir) + $(Q)echo '#include <tests/llvm.h>' > $@ + $(Q)echo 'const char test_llvm__bpf_test_relocation[] =' >> $@ + $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ + $(Q)echo ';' >> $@ + ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64)) perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o endif diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index fb80c9eb6a95..1d1bb489b4e8 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -29,14 +29,59 @@ static int fd1; static int fd2; +static int fd3; static int overflows; +static int overflows_2; + +volatile long the_var; + + +/* + * Use ASM to ensure watchpoint and breakpoint can be triggered + * at one instruction. + */ +#if defined (__x86_64__) +extern void __test_function(volatile long *ptr); +asm ( + ".globl __test_function\n" + "__test_function:\n" + "incq (%rdi)\n" + "ret\n"); +#elif defined (__aarch64__) +extern void __test_function(volatile long *ptr); +asm ( + ".globl __test_function\n" + "__test_function:\n" + "str x30, [x0]\n" + "ret\n"); + +#else +static void __test_function(volatile long *ptr) +{ + *ptr = 0x1234; +} +#endif __attribute__ ((noinline)) static int test_function(void) { + __test_function(&the_var); + the_var++; return time(NULL); } +static void sig_handler_2(int signum __maybe_unused, + siginfo_t *oh __maybe_unused, + void *uc __maybe_unused) +{ + overflows_2++; + if (overflows_2 > 10) { + ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0); + } +} + static void sig_handler(int signum __maybe_unused, siginfo_t *oh __maybe_unused, void *uc __maybe_unused) @@ -54,10 +99,11 @@ static void sig_handler(int signum __maybe_unused, */ ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0); ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0); } } -static int bp_event(void *fn, int setup_signal) +static int __event(bool is_x, void *addr, int signal) { struct perf_event_attr pe; int fd; @@ -67,8 +113,8 @@ static int bp_event(void *fn, int setup_signal) pe.size = sizeof(struct perf_event_attr); pe.config = 0; - pe.bp_type = HW_BREAKPOINT_X; - pe.bp_addr = (unsigned long) fn; + pe.bp_type = is_x ? HW_BREAKPOINT_X : HW_BREAKPOINT_W; + pe.bp_addr = (unsigned long) addr; pe.bp_len = sizeof(long); pe.sample_period = 1; @@ -86,17 +132,25 @@ static int bp_event(void *fn, int setup_signal) return TEST_FAIL; } - if (setup_signal) { - fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC); - fcntl(fd, F_SETSIG, SIGIO); - fcntl(fd, F_SETOWN, getpid()); - } + fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC); + fcntl(fd, F_SETSIG, signal); + fcntl(fd, F_SETOWN, getpid()); ioctl(fd, PERF_EVENT_IOC_RESET, 0); return fd; } +static int bp_event(void *addr, int signal) +{ + return __event(true, addr, signal); +} + +static int wp_event(void *addr, int signal) +{ + return __event(false, addr, signal); +} + static long long bp_count(int fd) { long long count; @@ -114,7 +168,7 @@ static long long bp_count(int fd) int test__bp_signal(int subtest __maybe_unused) { struct sigaction sa; - long long count1, count2; + long long count1, count2, count3; /* setup SIGIO signal handler */ memset(&sa, 0, sizeof(struct sigaction)); @@ -126,21 +180,52 @@ int test__bp_signal(int subtest __maybe_unused) return TEST_FAIL; } + sa.sa_sigaction = (void *) sig_handler_2; + if (sigaction(SIGUSR1, &sa, NULL) < 0) { + pr_debug("failed setting up signal handler 2\n"); + return TEST_FAIL; + } + /* * We create following events: * - * fd1 - breakpoint event on test_function with SIGIO + * fd1 - breakpoint event on __test_function with SIGIO * signal configured. We should get signal * notification each time the breakpoint is hit * - * fd2 - breakpoint event on sig_handler without SIGIO + * fd2 - breakpoint event on sig_handler with SIGUSR1 + * configured. We should get SIGUSR1 each time when + * breakpoint is hit + * + * fd3 - watchpoint event on __test_function with SIGIO * configured. * * Following processing should happen: - * - execute test_function - * - fd1 event breakpoint hit -> count1 == 1 - * - SIGIO is delivered -> overflows == 1 - * - fd2 event breakpoint hit -> count2 == 1 + * Exec: Action: Result: + * incq (%rdi) - fd1 event breakpoint hit -> count1 == 1 + * - SIGIO is delivered + * sig_handler - fd2 event breakpoint hit -> count2 == 1 + * - SIGUSR1 is delivered + * sig_handler_2 -> overflows_2 == 1 (nested signal) + * sys_rt_sigreturn - return from sig_handler_2 + * overflows++ -> overflows = 1 + * sys_rt_sigreturn - return from sig_handler + * incq (%rdi) - fd3 event watchpoint hit -> count3 == 1 (wp and bp in one insn) + * - SIGIO is delivered + * sig_handler - fd2 event breakpoint hit -> count2 == 2 + * - SIGUSR1 is delivered + * sig_handler_2 -> overflows_2 == 2 (nested signal) + * sys_rt_sigreturn - return from sig_handler_2 + * overflows++ -> overflows = 2 + * sys_rt_sigreturn - return from sig_handler + * the_var++ - fd3 event watchpoint hit -> count3 == 2 (standalone watchpoint) + * - SIGIO is delivered + * sig_handler - fd2 event breakpoint hit -> count2 == 3 + * - SIGUSR1 is delivered + * sig_handler_2 -> overflows_2 == 3 (nested signal) + * sys_rt_sigreturn - return from sig_handler_2 + * overflows++ -> overflows == 3 + * sys_rt_sigreturn - return from sig_handler * * The test case check following error conditions: * - we get stuck in signal handler because of debug @@ -152,11 +237,13 @@ int test__bp_signal(int subtest __maybe_unused) * */ - fd1 = bp_event(test_function, 1); - fd2 = bp_event(sig_handler, 0); + fd1 = bp_event(__test_function, SIGIO); + fd2 = bp_event(sig_handler, SIGUSR1); + fd3 = wp_event((void *)&the_var, SIGIO); ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0); ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0); + ioctl(fd3, PERF_EVENT_IOC_ENABLE, 0); /* * Kick off the test by trigering 'fd1' @@ -166,15 +253,18 @@ int test__bp_signal(int subtest __maybe_unused) ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0); ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0); count1 = bp_count(fd1); count2 = bp_count(fd2); + count3 = bp_count(fd3); close(fd1); close(fd2); + close(fd3); - pr_debug("count1 %lld, count2 %lld, overflow %d\n", - count1, count2, overflows); + pr_debug("count1 %lld, count2 %lld, count3 %lld, overflow %d, overflows_2 %d\n", + count1, count2, count3, overflows, overflows_2); if (count1 != 1) { if (count1 == 11) @@ -183,12 +273,18 @@ int test__bp_signal(int subtest __maybe_unused) pr_debug("failed: wrong count for bp1%lld\n", count1); } - if (overflows != 1) + if (overflows != 3) pr_debug("failed: wrong overflow hit\n"); - if (count2 != 1) + if (overflows_2 != 3) + pr_debug("failed: wrong overflow_2 hit\n"); + + if (count2 != 3) pr_debug("failed: wrong count for bp2\n"); - return count1 == 1 && overflows == 1 && count2 == 1 ? + if (count3 != 2) + pr_debug("failed: wrong count for bp3\n"); + + return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ? TEST_OK : TEST_FAIL; } diff --git a/tools/perf/tests/bpf-script-test-relocation.c b/tools/perf/tests/bpf-script-test-relocation.c new file mode 100644 index 000000000000..93af77421816 --- /dev/null +++ b/tools/perf/tests/bpf-script-test-relocation.c @@ -0,0 +1,50 @@ +/* + * bpf-script-test-relocation.c + * Test BPF loader checking relocation + */ +#ifndef LINUX_VERSION_CODE +# error Need LINUX_VERSION_CODE +# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig' +#endif +#define BPF_ANY 0 +#define BPF_MAP_TYPE_ARRAY 2 +#define BPF_FUNC_map_lookup_elem 1 +#define BPF_FUNC_map_update_elem 2 + +static void *(*bpf_map_lookup_elem)(void *map, void *key) = + (void *) BPF_FUNC_map_lookup_elem; +static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) = + (void *) BPF_FUNC_map_update_elem; + +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; +}; + +#define SEC(NAME) __attribute__((section(NAME), used)) +struct bpf_map_def SEC("maps") my_table = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1, +}; + +int this_is_a_global_val; + +SEC("func=sys_write") +int bpf_func__sys_write(void *ctx) +{ + int key = 0; + int value = 0; + + /* + * Incorrect relocation. Should not allow this program be + * loaded into kernel. + */ + bpf_map_update_elem(&this_is_a_global_val, &key, &value, 0); + return 0; +} +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 33689a0cf821..4aed5cb4ac2d 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -1,7 +1,11 @@ #include <stdio.h> #include <sys/epoll.h> +#include <util/util.h> #include <util/bpf-loader.h> #include <util/evlist.h> +#include <linux/bpf.h> +#include <linux/filter.h> +#include <bpf/bpf.h> #include "tests.h" #include "llvm.h" #include "debug.h" @@ -71,6 +75,15 @@ static struct { (NR_ITERS + 1) / 4, }, #endif + { + LLVM_TESTCASE_BPF_RELOCATION, + "Test BPF relocation checker", + "[bpf_relocation_test]", + "fix 'perf test LLVM' first", + "libbpf error when dealing with relocation", + NULL, + 0, + }, }; static int do_test(struct bpf_object *obj, int (*func)(void), @@ -190,7 +203,7 @@ static int __test__bpf(int idx) ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, bpf_testcase_table[idx].prog_id, - true); + true, NULL); if (ret != TEST_OK || !obj_buf || !obj_buf_sz) { pr_debug("Unable to get BPF object, %s\n", bpf_testcase_table[idx].msg_compile_fail); @@ -202,14 +215,21 @@ static int __test__bpf(int idx) obj = prepare_bpf(obj_buf, obj_buf_sz, bpf_testcase_table[idx].name); - if (!obj) { + if ((!!bpf_testcase_table[idx].target_func) != (!!obj)) { + if (!obj) + pr_debug("Fail to load BPF object: %s\n", + bpf_testcase_table[idx].msg_load_fail); + else + pr_debug("Success unexpectedly: %s\n", + bpf_testcase_table[idx].msg_load_fail); ret = TEST_FAIL; goto out; } - ret = do_test(obj, - bpf_testcase_table[idx].target_func, - bpf_testcase_table[idx].expect_result); + if (obj) + ret = do_test(obj, + bpf_testcase_table[idx].target_func, + bpf_testcase_table[idx].expect_result); out: bpf__clear(); return ret; @@ -227,6 +247,36 @@ const char *test__bpf_subtest_get_desc(int i) return bpf_testcase_table[i].desc; } +static int check_env(void) +{ + int err; + unsigned int kver_int; + char license[] = "GPL"; + + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + + err = fetch_kernel_version(&kver_int, NULL, 0); + if (err) { + pr_debug("Unable to get kernel version\n"); + return err; + } + + err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns, + sizeof(insns) / sizeof(insns[0]), + license, kver_int, NULL, 0); + if (err < 0) { + pr_err("Missing basic BPF support, skip this test: %s\n", + strerror(errno)); + return err; + } + close(err); + + return 0; +} + int test__bpf(int i) { int err; @@ -239,6 +289,9 @@ int test__bpf(int i) return TEST_SKIP; } + if (check_env()) + return TEST_SKIP; + err = __test__bpf(i); return err; } diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 5e6a86e50fb9..ecf136c385d5 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -191,7 +191,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec * function since TEST_ASSERT_VAL() returns in case of failure. */ hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(hists_to_evsel(hists), NULL); if (verbose > 2) { pr_info("use callchain: %d, cumulate callchain: %d\n", diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 351a42463444..34b945a55d4d 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -145,7 +145,7 @@ int test__hists_filter(int subtest __maybe_unused) struct hists *hists = evsel__hists(evsel); hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("Normal histogram\n"); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index b231265148d8..23cce67c7e48 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -156,7 +156,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -256,7 +256,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -310,7 +310,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -388,7 +388,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -491,7 +491,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 06f45c1d4256..70edcdfa5672 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -35,6 +35,7 @@ static int test__bpf_parsing(void *obj_buf __maybe_unused, static struct { const char *source; const char *desc; + bool should_load_fail; } bpf_source_table[__LLVM_TESTCASE_MAX] = { [LLVM_TESTCASE_BASE] = { .source = test_llvm__bpf_base_prog, @@ -48,14 +49,19 @@ static struct { .source = test_llvm__bpf_test_prologue_prog, .desc = "Compile source for BPF prologue generation test", }, + [LLVM_TESTCASE_BPF_RELOCATION] = { + .source = test_llvm__bpf_test_relocation, + .desc = "Compile source for BPF relocation test", + .should_load_fail = true, + }, }; - int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz, enum test_llvm__testcase idx, - bool force) + bool force, + bool *should_load_fail) { const char *source; const char *desc; @@ -68,6 +74,8 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf, source = bpf_source_table[idx].source; desc = bpf_source_table[idx].desc; + if (should_load_fail) + *should_load_fail = bpf_source_table[idx].should_load_fail; perf_config(perf_config_cb, NULL); @@ -136,14 +144,15 @@ int test__llvm(int subtest) int ret; void *obj_buf = NULL; size_t obj_buf_sz = 0; + bool should_load_fail = false; if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX)) return TEST_FAIL; ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, - subtest, false); + subtest, false, &should_load_fail); - if (ret == TEST_OK) { + if (ret == TEST_OK && !should_load_fail) { ret = test__bpf_parsing(obj_buf, obj_buf_sz); if (ret != TEST_OK) { pr_debug("Failed to parse test case '%s'\n", diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h index 5150b4d6ef50..0eaa604be99d 100644 --- a/tools/perf/tests/llvm.h +++ b/tools/perf/tests/llvm.h @@ -7,14 +7,17 @@ extern const char test_llvm__bpf_base_prog[]; extern const char test_llvm__bpf_test_kbuild_prog[]; extern const char test_llvm__bpf_test_prologue_prog[]; +extern const char test_llvm__bpf_test_relocation[]; enum test_llvm__testcase { LLVM_TESTCASE_BASE, LLVM_TESTCASE_KBUILD, LLVM_TESTCASE_BPF_PROLOGUE, + LLVM_TESTCASE_BPF_RELOCATION, __LLVM_TESTCASE_MAX, }; int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz, - enum test_llvm__testcase index, bool force); + enum test_llvm__testcase index, bool force, + bool *should_load_fail); #endif diff --git a/tools/perf/tests/make b/tools/perf/tests/make index f918015512af..cc72b67bde5e 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -15,6 +15,7 @@ else PERF := . PERF_O := $(PERF) O_OPT := +FULL_O := $(shell readlink -f $(PERF_O) || echo $(PERF_O)) ifneq ($(O),) FULL_O := $(shell readlink -f $(O) || echo $(O)) @@ -260,6 +261,8 @@ run := $(shell shuf -e $(run)) run_O := $(shell shuf -e $(run_O)) endif +max_width := $(shell echo $(run_O) | sed 's/ /\n/g' | wc -L) + ifdef DEBUG d := $(info run $(run)) d := $(info run_O $(run_O)) @@ -273,7 +276,7 @@ $(run): $(call clean) @TMP_DEST=$$(mktemp -d); \ cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \ - echo "- $@: $$cmd" && echo $$cmd > $@ && \ + printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1; \ echo " test: $(call test,$@)" >> $@ 2>&1; \ $(call test,$@) && \ @@ -284,7 +287,7 @@ $(run_O): @TMP_O=$$(mktemp -d); \ TMP_DEST=$$(mktemp -d); \ cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \ - echo "- $@: $$cmd" && echo $$cmd > $@ && \ + printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1 && \ echo " test: $(call test_O,$@)" >> $@ 2>&1; \ $(call test_O,$@) && \ @@ -313,11 +316,43 @@ make_kernelsrc_tools: (make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \ test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false) +FEATURES_DUMP_FILE := $(FULL_O)/BUILD_TEST_FEATURE_DUMP +FEATURES_DUMP_FILE_STATIC := $(FULL_O)/BUILD_TEST_FEATURE_DUMP_STATIC + all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools @echo OK + @rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC) out: $(run_O) @echo OK + @rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC) + +ifeq ($(REUSE_FEATURES_DUMP),1) +$(FEATURES_DUMP_FILE): + $(call clean) + @cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) feature-dump"; \ + echo "- $@: $$cmd" && echo $$cmd && \ + ( eval $$cmd ) > /dev/null 2>&1 + +$(FEATURES_DUMP_FILE_STATIC): + $(call clean) + @cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) LDFLAGS='-static' feature-dump"; \ + echo "- $@: $$cmd" && echo $$cmd && \ + ( eval $$cmd ) > /dev/null 2>&1 + +# Add feature dump dependency for run/run_O targets +$(foreach t,$(run) $(run_O),$(eval \ + $(t): $(if $(findstring make_static,$(t)),\ + $(FEATURES_DUMP_FILE_STATIC),\ + $(FEATURES_DUMP_FILE)))) + +# Append 'FEATURES_DUMP=' option to all test cases. For example: +# make_no_libbpf: NO_LIBBPF=1 --> NO_LIBBPF=1 FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP +# make_static: LDFLAGS=-static --> LDFLAGS=-static FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP_STATIC +$(foreach t,$(run),$(if $(findstring make_static,$(t)),\ + $(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE_STATIC)),\ + $(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE)))) +endif .PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools endif # ifndef MK diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index f0bfc9e8fd9f..630b0b409b97 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -110,7 +110,6 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused) */ for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) { struct symbol *pair, *first_pair; - bool backwards = true; sym = rb_entry(nd, struct symbol, rb_node); @@ -151,27 +150,14 @@ next_pair: continue; } else { - struct rb_node *nnd; -detour: - nnd = backwards ? rb_prev(&pair->rb_node) : - rb_next(&pair->rb_node); - if (nnd) { - struct symbol *next = rb_entry(nnd, struct symbol, rb_node); - - if (UM(next->start) == mem_start) { - pair = next; + pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL, NULL); + if (pair) { + if (UM(pair->start) == mem_start) goto next_pair; - } - } - if (backwards) { - backwards = false; - pair = first_pair; - goto detour; + pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", + mem_start, sym->name, pair->name); } - - pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", - mem_start, sym->name, pair->name); } } else pr_debug("%#" PRIx64 ": %s not on kallsyms\n", diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index d37202121689..af68a9d488bf 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -531,8 +531,8 @@ static struct ui_browser_colorset { .bg = "yellow", }, { - .colorset = HE_COLORSET_CODE, - .name = "code", + .colorset = HE_COLORSET_JUMP_ARROWS, + .name = "jump_arrows", .fg = "blue", .bg = "default", }, diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 01781de59532..be3b70eb5fca 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -7,7 +7,7 @@ #define HE_COLORSET_MEDIUM 51 #define HE_COLORSET_NORMAL 52 #define HE_COLORSET_SELECTED 53 -#define HE_COLORSET_CODE 54 +#define HE_COLORSET_JUMP_ARROWS 54 #define HE_COLORSET_ADDR 55 #define HE_COLORSET_ROOT 56 diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 718bd46d47fa..4fc208e82c6f 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -284,7 +284,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) to = (u64)btarget->idx; } - ui_browser__set_color(browser, HE_COLORSET_CODE); + ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS); __ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width, from, to); } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 08c09ad755d2..a5a5390476ac 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -657,9 +657,24 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser, return 1; } +static bool check_percent_display(struct rb_node *node, u64 parent_total) +{ + struct callchain_node *child; + + if (node == NULL) + return false; + + if (rb_next(node)) + return true; + + child = rb_entry(node, struct callchain_node, rb_node); + return callchain_cumul_hits(child) != parent_total; +} + static int hist_browser__show_callchain_flat(struct hist_browser *browser, struct rb_root *root, unsigned short row, u64 total, + u64 parent_total, print_callchain_entry_fn print, struct callchain_print_arg *arg, check_output_full_fn is_output_full) @@ -669,7 +684,7 @@ static int hist_browser__show_callchain_flat(struct hist_browser *browser, bool need_percent; node = rb_first(root); - need_percent = node && rb_next(node); + need_percent = check_percent_display(node, parent_total); while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); @@ -763,6 +778,7 @@ static char *hist_browser__folded_callchain_str(struct hist_browser *browser, static int hist_browser__show_callchain_folded(struct hist_browser *browser, struct rb_root *root, unsigned short row, u64 total, + u64 parent_total, print_callchain_entry_fn print, struct callchain_print_arg *arg, check_output_full_fn is_output_full) @@ -772,7 +788,7 @@ static int hist_browser__show_callchain_folded(struct hist_browser *browser, bool need_percent; node = rb_first(root); - need_percent = node && rb_next(node); + need_percent = check_percent_display(node, parent_total); while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); @@ -844,20 +860,24 @@ next: return row - first_row; } -static int hist_browser__show_callchain(struct hist_browser *browser, +static int hist_browser__show_callchain_graph(struct hist_browser *browser, struct rb_root *root, int level, unsigned short row, u64 total, + u64 parent_total, print_callchain_entry_fn print, struct callchain_print_arg *arg, check_output_full_fn is_output_full) { struct rb_node *node; int first_row = row, offset = level * LEVEL_OFFSET_STEP; - u64 new_total; bool need_percent; + u64 percent_total = total; + + if (callchain_param.mode == CHAIN_GRAPH_REL) + percent_total = parent_total; node = rb_first(root); - need_percent = node && rb_next(node); + need_percent = check_percent_display(node, parent_total); while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); @@ -878,7 +898,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser, folded_sign = callchain_list__folded(chain); row += hist_browser__show_callchain_list(browser, child, - chain, row, total, + chain, row, percent_total, was_first && need_percent, offset + extra_offset, print, arg); @@ -893,13 +913,9 @@ static int hist_browser__show_callchain(struct hist_browser *browser, if (folded_sign == '-') { const int new_level = level + (extra_offset ? 2 : 1); - if (callchain_param.mode == CHAIN_GRAPH_REL) - new_total = child->children_hit; - else - new_total = total; - - row += hist_browser__show_callchain(browser, &child->rb_root, - new_level, row, new_total, + row += hist_browser__show_callchain_graph(browser, &child->rb_root, + new_level, row, total, + child->children_hit, print, arg, is_output_full); } if (is_output_full(browser, row)) @@ -910,6 +926,45 @@ out: return row - first_row; } +static int hist_browser__show_callchain(struct hist_browser *browser, + struct hist_entry *entry, int level, + unsigned short row, + print_callchain_entry_fn print, + struct callchain_print_arg *arg, + check_output_full_fn is_output_full) +{ + u64 total = hists__total_period(entry->hists); + u64 parent_total; + int printed; + + if (symbol_conf.cumulate_callchain) + parent_total = entry->stat_acc->period; + else + parent_total = entry->stat.period; + + if (callchain_param.mode == CHAIN_FLAT) { + printed = hist_browser__show_callchain_flat(browser, + &entry->sorted_chain, row, + total, parent_total, print, arg, + is_output_full); + } else if (callchain_param.mode == CHAIN_FOLDED) { + printed = hist_browser__show_callchain_folded(browser, + &entry->sorted_chain, row, + total, parent_total, print, arg, + is_output_full); + } else { + printed = hist_browser__show_callchain_graph(browser, + &entry->sorted_chain, level, row, + total, parent_total, print, arg, + is_output_full); + } + + if (arg->is_current_entry) + browser->he_selection = entry; + + return printed; +} + struct hpp_arg { struct ui_browser *b; char folded_sign; @@ -1040,7 +1095,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, hist_browser__gotorc(browser, row, 0); - perf_hpp__for_each_format(fmt) { + hists__for_each_format(browser->hists, fmt) { if (perf_hpp__should_skip(fmt, entry->hists) || column++ < browser->b.horiz_scroll) continue; @@ -1084,38 +1139,14 @@ static int hist_browser__show_entry(struct hist_browser *browser, --row_offset; if (folded_sign == '-' && row != browser->b.rows) { - u64 total = hists__total_period(entry->hists); struct callchain_print_arg arg = { .row_offset = row_offset, .is_current_entry = current_entry, }; - if (callchain_param.mode == CHAIN_GRAPH_REL) { - if (symbol_conf.cumulate_callchain) - total = entry->stat_acc->period; - else - total = entry->stat.period; - } - - if (callchain_param.mode == CHAIN_FLAT) { - printed += hist_browser__show_callchain_flat(browser, - &entry->sorted_chain, row, total, - hist_browser__show_callchain_entry, &arg, - hist_browser__check_output_full); - } else if (callchain_param.mode == CHAIN_FOLDED) { - printed += hist_browser__show_callchain_folded(browser, - &entry->sorted_chain, row, total, - hist_browser__show_callchain_entry, &arg, - hist_browser__check_output_full); - } else { - printed += hist_browser__show_callchain(browser, - &entry->sorted_chain, 1, row, total, + printed += hist_browser__show_callchain(browser, entry, 1, row, hist_browser__show_callchain_entry, &arg, hist_browser__check_output_full); - } - - if (arg.is_current_entry) - browser->he_selection = entry; } return printed; @@ -1144,7 +1175,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char * return ret; } - perf_hpp__for_each_format(fmt) { + hists__for_each_format(browser->hists, fmt) { if (perf_hpp__should_skip(fmt, hists) || column++ < browser->b.horiz_scroll) continue; @@ -1380,15 +1411,11 @@ do_offset: static int hist_browser__fprintf_callchain(struct hist_browser *browser, struct hist_entry *he, FILE *fp) { - u64 total = hists__total_period(he->hists); struct callchain_print_arg arg = { .fp = fp, }; - if (symbol_conf.cumulate_callchain) - total = he->stat_acc->period; - - hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total, + hist_browser__show_callchain(browser, he, 1, 0, hist_browser__fprintf_callchain_entry, &arg, hist_browser__check_dump_full); return arg.printed; @@ -1414,7 +1441,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, if (symbol_conf.use_callchain) printed += fprintf(fp, "%c ", folded_sign); - perf_hpp__for_each_format(fmt) { + hists__for_each_format(browser->hists, fmt) { if (perf_hpp__should_skip(fmt, he->hists)) continue; @@ -1782,7 +1809,7 @@ static int add_thread_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct thread *thread) { - if (thread == NULL) + if (!sort__has_thread || thread == NULL) return 0; if (asprintf(optstr, "Zoom %s %s(%d) thread", @@ -1825,7 +1852,7 @@ static int add_dso_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct map *map) { - if (map == NULL) + if (!sort__has_dso || map == NULL) return 0; if (asprintf(optstr, "Zoom %s %s DSO", @@ -1850,7 +1877,7 @@ static int add_map_opt(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, struct map *map) { - if (map == NULL) + if (!sort__has_dso || map == NULL) return 0; if (asprintf(optstr, "Browse map details") < 0) @@ -1971,7 +1998,7 @@ static int add_socket_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, int socket_id) { - if (socket_id < 0) + if (!sort__has_socket || socket_id < 0) return 0; if (asprintf(optstr, "Zoom %s Processor Socket %d", @@ -2002,6 +2029,42 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb) hb->nr_non_filtered_entries = nr_entries; } +static void hist_browser__update_percent_limit(struct hist_browser *hb, + double percent) +{ + struct hist_entry *he; + struct rb_node *nd = rb_first(&hb->hists->entries); + u64 total = hists__total_period(hb->hists); + u64 min_callchain_hits = total * (percent / 100); + + hb->min_pcnt = callchain_param.min_percent = percent; + + if (!symbol_conf.use_callchain) + return; + + while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) { + he = rb_entry(nd, struct hist_entry, rb_node); + + if (callchain_param.mode == CHAIN_GRAPH_REL) { + total = he->stat.period; + + if (symbol_conf.cumulate_callchain) + total = he->stat_acc->period; + + min_callchain_hits = total * (percent / 100); + } + + callchain_param.sort(&he->sorted_chain, he->callchain, + min_callchain_hits, &callchain_param); + + /* force to re-evaluate folding state of callchains */ + he->init_have_children = false; + hist_entry__set_folding(he, false); + + nd = rb_next(nd); + } +} + static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, const char *helpline, bool left_exits, @@ -2037,6 +2100,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "E Expand all callchains\n" \ "F Toggle percentage of filtered entries\n" \ "H Display column headers\n" \ + "L Change percent limit\n" \ "m Display context menu\n" \ "S Zoom into current Processor Socket\n" \ @@ -2077,7 +2141,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, memset(options, 0, sizeof(options)); memset(actions, 0, sizeof(actions)); - perf_hpp__for_each_format(fmt) { + hists__for_each_format(browser->hists, fmt) { perf_hpp__reset_width(fmt, hists); /* * This is done just once, and activates the horizontal scrolling @@ -2192,6 +2256,24 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, top->zero = !top->zero; } continue; + case 'L': + if (ui_browser__input_window("Percent Limit", + "Please enter the value you want to hide entries under that percent.", + buf, "ENTER: OK, ESC: Cancel", + delay_secs * 2) == K_ENTER) { + char *end; + double new_percent = strtod(buf, &end); + + if (new_percent < 0 || new_percent > 100) { + ui_browser__warning(&browser->b, delay_secs * 2, + "Invalid percent: %.2f", new_percent); + continue; + } + + hist_browser__update_percent_limit(browser, new_percent); + hist_browser__reset(browser); + } + continue; case K_F1: case 'h': case '?': @@ -2263,10 +2345,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, continue; } - if (!sort__has_sym) - goto add_exit_option; - - if (browser->selection == NULL) + if (!sort__has_sym || browser->selection == NULL) goto skip_annotation; if (sort__mode == SORT_MODE__BRANCH) { @@ -2306,11 +2385,16 @@ skip_annotation: &options[nr_options], socked_id); /* perf script support */ + if (!is_report_browser(hbt)) + goto skip_scripting; + if (browser->he_selection) { - nr_options += add_script_opt(browser, - &actions[nr_options], - &options[nr_options], - thread, NULL); + if (sort__has_thread && thread) { + nr_options += add_script_opt(browser, + &actions[nr_options], + &options[nr_options], + thread, NULL); + } /* * Note that browser->selection != NULL * when browser->he_selection is not NULL, @@ -2320,16 +2404,18 @@ skip_annotation: * * See hist_browser__show_entry. */ - nr_options += add_script_opt(browser, - &actions[nr_options], - &options[nr_options], - NULL, browser->selection->sym); + if (sort__has_sym && browser->selection->sym) { + nr_options += add_script_opt(browser, + &actions[nr_options], + &options[nr_options], + NULL, browser->selection->sym); + } } nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], NULL, NULL); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); -add_exit_option: +skip_scripting: nr_options += add_exit_opt(browser, &actions[nr_options], &options[nr_options]); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 0f8dcfdfb10f..32cc38a5b57f 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -306,7 +306,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, nr_cols = 0; - perf_hpp__for_each_format(fmt) + hists__for_each_format(hists, fmt) col_types[nr_cols++] = G_TYPE_STRING; store = gtk_tree_store_newv(nr_cols, col_types); @@ -317,7 +317,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; - perf_hpp__for_each_format(fmt) { + hists__for_each_format(hists, fmt) { if (perf_hpp__should_skip(fmt, hists)) continue; @@ -367,7 +367,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; - perf_hpp__for_each_format(fmt) { + hists__for_each_format(hists, fmt) { if (perf_hpp__should_skip(fmt, h->hists)) continue; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index bf2a66e254ea..1ba4117d9c2d 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -371,7 +371,20 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, return 0; } -#define HPP__COLOR_PRINT_FNS(_name, _fn) \ +static bool perf_hpp__is_hpp_entry(struct perf_hpp_fmt *a) +{ + return a->header == hpp__header_fn; +} + +static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +{ + if (!perf_hpp__is_hpp_entry(a) || !perf_hpp__is_hpp_entry(b)) + return false; + + return a->idx == b->idx; +} + +#define HPP__COLOR_PRINT_FNS(_name, _fn, _idx) \ { \ .name = _name, \ .header = hpp__header_fn, \ @@ -381,9 +394,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, .cmp = hpp__nop_cmp, \ .collapse = hpp__nop_cmp, \ .sort = hpp__sort_ ## _fn, \ + .idx = PERF_HPP__ ## _idx, \ + .equal = hpp__equal, \ } -#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn) \ +#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn, _idx) \ { \ .name = _name, \ .header = hpp__header_fn, \ @@ -393,9 +408,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, .cmp = hpp__nop_cmp, \ .collapse = hpp__nop_cmp, \ .sort = hpp__sort_ ## _fn, \ + .idx = PERF_HPP__ ## _idx, \ + .equal = hpp__equal, \ } -#define HPP__PRINT_FNS(_name, _fn) \ +#define HPP__PRINT_FNS(_name, _fn, _idx) \ { \ .name = _name, \ .header = hpp__header_fn, \ @@ -404,22 +421,25 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, .cmp = hpp__nop_cmp, \ .collapse = hpp__nop_cmp, \ .sort = hpp__sort_ ## _fn, \ + .idx = PERF_HPP__ ## _idx, \ + .equal = hpp__equal, \ } struct perf_hpp_fmt perf_hpp__format[] = { - HPP__COLOR_PRINT_FNS("Overhead", overhead), - HPP__COLOR_PRINT_FNS("sys", overhead_sys), - HPP__COLOR_PRINT_FNS("usr", overhead_us), - HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys), - HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us), - HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc), - HPP__PRINT_FNS("Samples", samples), - HPP__PRINT_FNS("Period", period) + HPP__COLOR_PRINT_FNS("Overhead", overhead, OVERHEAD), + HPP__COLOR_PRINT_FNS("sys", overhead_sys, OVERHEAD_SYS), + HPP__COLOR_PRINT_FNS("usr", overhead_us, OVERHEAD_US), + HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys, OVERHEAD_GUEST_SYS), + HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us, OVERHEAD_GUEST_US), + HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc, OVERHEAD_ACC), + HPP__PRINT_FNS("Samples", samples, SAMPLES), + HPP__PRINT_FNS("Period", period, PERIOD) }; -LIST_HEAD(perf_hpp__list); -LIST_HEAD(perf_hpp__sort_list); - +struct perf_hpp_list perf_hpp_list = { + .fields = LIST_HEAD_INIT(perf_hpp_list.fields), + .sorts = LIST_HEAD_INIT(perf_hpp_list.sorts), +}; #undef HPP__COLOR_PRINT_FNS #undef HPP__COLOR_ACC_PRINT_FNS @@ -485,63 +505,60 @@ void perf_hpp__init(void) hpp_dimension__add_output(PERF_HPP__PERIOD); } -void perf_hpp__column_register(struct perf_hpp_fmt *format) -{ - list_add_tail(&format->list, &perf_hpp__list); -} - -void perf_hpp__column_unregister(struct perf_hpp_fmt *format) -{ - list_del(&format->list); -} - -void perf_hpp__register_sort_field(struct perf_hpp_fmt *format) +void perf_hpp_list__column_register(struct perf_hpp_list *list, + struct perf_hpp_fmt *format) { - list_add_tail(&format->sort_list, &perf_hpp__sort_list); + list_add_tail(&format->list, &list->fields); } -void perf_hpp__column_enable(unsigned col) +void perf_hpp_list__register_sort_field(struct perf_hpp_list *list, + struct perf_hpp_fmt *format) { - BUG_ON(col >= PERF_HPP__MAX_INDEX); - perf_hpp__column_register(&perf_hpp__format[col]); + list_add_tail(&format->sort_list, &list->sorts); } -void perf_hpp__column_disable(unsigned col) +void perf_hpp__column_unregister(struct perf_hpp_fmt *format) { - BUG_ON(col >= PERF_HPP__MAX_INDEX); - perf_hpp__column_unregister(&perf_hpp__format[col]); + list_del(&format->list); } void perf_hpp__cancel_cumulate(void) { + struct perf_hpp_fmt *fmt, *acc, *ovh, *tmp; + if (is_strict_order(field_order)) return; - perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC); - perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead"; + ovh = &perf_hpp__format[PERF_HPP__OVERHEAD]; + acc = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC]; + + perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) { + if (acc->equal(acc, fmt)) { + perf_hpp__column_unregister(fmt); + continue; + } + + if (ovh->equal(ovh, fmt)) + fmt->name = "Overhead"; + } +} + +static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +{ + return a->equal && a->equal(a, b); } -void perf_hpp__setup_output_field(void) +void perf_hpp__setup_output_field(struct perf_hpp_list *list) { struct perf_hpp_fmt *fmt; /* append sort keys to output field */ - perf_hpp__for_each_sort_list(fmt) { - if (!list_empty(&fmt->list)) - continue; - - /* - * sort entry fields are dynamically created, - * so they can share a same sort key even though - * the list is empty. - */ - if (perf_hpp__is_sort_entry(fmt)) { - struct perf_hpp_fmt *pos; + perf_hpp_list__for_each_sort_list(list, fmt) { + struct perf_hpp_fmt *pos; - perf_hpp__for_each_format(pos) { - if (perf_hpp__same_sort_entry(pos, fmt)) - goto next; - } + perf_hpp_list__for_each_format(list, pos) { + if (fmt_equal(fmt, pos)) + goto next; } perf_hpp__column_register(fmt); @@ -550,27 +567,17 @@ next: } } -void perf_hpp__append_sort_keys(void) +void perf_hpp__append_sort_keys(struct perf_hpp_list *list) { struct perf_hpp_fmt *fmt; /* append output fields to sort keys */ - perf_hpp__for_each_format(fmt) { - if (!list_empty(&fmt->sort_list)) - continue; + perf_hpp_list__for_each_format(list, fmt) { + struct perf_hpp_fmt *pos; - /* - * sort entry fields are dynamically created, - * so they can share a same sort key even though - * the list is empty. - */ - if (perf_hpp__is_sort_entry(fmt)) { - struct perf_hpp_fmt *pos; - - perf_hpp__for_each_sort_list(pos) { - if (perf_hpp__same_sort_entry(pos, fmt)) - goto next; - } + perf_hpp_list__for_each_sort_list(list, pos) { + if (fmt_equal(fmt, pos)) + goto next; } perf_hpp__register_sort_field(fmt); @@ -579,20 +586,29 @@ next: } } -void perf_hpp__reset_output_field(void) + +static void fmt_free(struct perf_hpp_fmt *fmt) +{ + if (fmt->free) + fmt->free(fmt); +} + +void perf_hpp__reset_output_field(struct perf_hpp_list *list) { struct perf_hpp_fmt *fmt, *tmp; /* reset output fields */ - perf_hpp__for_each_format_safe(fmt, tmp) { + perf_hpp_list__for_each_format_safe(list, fmt, tmp) { list_del_init(&fmt->list); list_del_init(&fmt->sort_list); + fmt_free(fmt); } /* reset sort keys */ - perf_hpp__for_each_sort_list_safe(fmt, tmp) { + perf_hpp_list__for_each_sort_list_safe(list, fmt, tmp) { list_del_init(&fmt->list); list_del_init(&fmt->sort_list); + fmt_free(fmt); } } @@ -606,7 +622,7 @@ unsigned int hists__sort_list_width(struct hists *hists) bool first = true; struct perf_hpp dummy_hpp; - perf_hpp__for_each_format(fmt) { + hists__for_each_format(hists, fmt) { if (perf_hpp__should_skip(fmt, hists)) continue; @@ -626,20 +642,12 @@ unsigned int hists__sort_list_width(struct hists *hists) void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) { - int idx; - if (perf_hpp__is_sort_entry(fmt)) return perf_hpp__reset_sort_width(fmt, hists); - for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { - if (fmt == &perf_hpp__format[idx]) - break; - } - - if (idx == PERF_HPP__MAX_INDEX) - return; + BUG_ON(fmt->idx >= PERF_HPP__MAX_INDEX); - switch (idx) { + switch (fmt->idx) { case PERF_HPP__OVERHEAD: case PERF_HPP__OVERHEAD_SYS: case PERF_HPP__OVERHEAD_US: @@ -667,7 +675,7 @@ void perf_hpp__set_user_width(const char *width_list_str) struct perf_hpp_fmt *fmt; const char *ptr = width_list_str; - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { char *p; int len = strtol(ptr, &p, 10); diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 387110d50b00..1a6e8f7f38c4 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -165,8 +165,28 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root, return ret; } +/* + * If have one single callchain root, don't bother printing + * its percentage (100 % in fractal mode and the same percentage + * than the hist in graph mode). This also avoid one level of column. + * + * However when percent-limit applied, it's possible that single callchain + * node have different (non-100% in fractal mode) percentage. + */ +static bool need_percent_display(struct rb_node *node, u64 parent_samples) +{ + struct callchain_node *cnode; + + if (rb_next(node)) + return true; + + cnode = rb_entry(node, struct callchain_node, rb_node); + return callchain_cumul_hits(cnode) != parent_samples; +} + static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, - u64 total_samples, int left_margin) + u64 total_samples, u64 parent_samples, + int left_margin) { struct callchain_node *cnode; struct callchain_list *chain; @@ -177,13 +197,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, int ret = 0; char bf[1024]; - /* - * If have one single callchain root, don't bother printing - * its percentage (100 % in fractal mode and the same percentage - * than the hist in graph mode). This also avoid one level of column. - */ node = rb_first(root); - if (node && !rb_next(node)) { + if (node && !need_percent_display(node, parent_samples)) { cnode = rb_entry(node, struct callchain_node, rb_node); list_for_each_entry(chain, &cnode->val, list) { /* @@ -213,9 +228,15 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, root = &cnode->rb_root; } + if (callchain_param.mode == CHAIN_GRAPH_REL) + total_samples = parent_samples; + ret += __callchain__fprintf_graph(fp, root, total_samples, 1, 1, left_margin); - ret += fprintf(fp, "\n"); + if (ret) { + /* do not add a blank line if it printed nothing */ + ret += fprintf(fp, "\n"); + } return ret; } @@ -323,16 +344,19 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he, u64 total_samples, int left_margin, FILE *fp) { + u64 parent_samples = he->stat.period; + + if (symbol_conf.cumulate_callchain) + parent_samples = he->stat_acc->period; + switch (callchain_param.mode) { case CHAIN_GRAPH_REL: - return callchain__fprintf_graph(fp, &he->sorted_chain, - symbol_conf.cumulate_callchain ? - he->stat_acc->period : he->stat.period, - left_margin); + return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples, + parent_samples, left_margin); break; case CHAIN_GRAPH_ABS: return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples, - left_margin); + parent_samples, left_margin); break; case CHAIN_FLAT: return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples); @@ -349,30 +373,6 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he, return 0; } -static size_t hist_entry__callchain_fprintf(struct hist_entry *he, - struct hists *hists, - FILE *fp) -{ - int left_margin = 0; - u64 total_period = hists->stats.total_period; - - if (field_order == NULL && (sort_order == NULL || - !prefixcmp(sort_order, "comm"))) { - struct perf_hpp_fmt *fmt; - - perf_hpp__for_each_format(fmt) { - if (!perf_hpp__is_sort_entry(fmt)) - continue; - - /* must be 'comm' sort entry */ - left_margin = fmt->width(fmt, NULL, hists_to_evsel(hists)); - left_margin -= thread__comm_len(he->thread); - break; - } - } - return hist_entry_callchain__fprintf(he, total_period, left_margin, fp); -} - static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp) { const char *sep = symbol_conf.field_sep; @@ -384,7 +384,7 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp) if (symbol_conf.exclude_other && !he->parent) return 0; - perf_hpp__for_each_format(fmt) { + hists__for_each_format(he->hists, fmt) { if (perf_hpp__should_skip(fmt, he->hists)) continue; @@ -418,6 +418,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, .buf = bf, .size = size, }; + u64 total_period = hists->stats.total_period; if (size == 0 || size > bfsz) size = hpp.size = bfsz; @@ -427,7 +428,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, ret = fprintf(fp, "%s\n", bf); if (symbol_conf.use_callchain) - ret += hist_entry__callchain_fprintf(he, hists, fp); + ret += hist_entry_callchain__fprintf(he, total_period, 0, fp); return ret; } @@ -452,7 +453,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, init_rem_hits(); - perf_hpp__for_each_format(fmt) + hists__for_each_format(hists, fmt) perf_hpp__reset_width(fmt, hists); if (symbol_conf.col_width_list_str) @@ -463,7 +464,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, fprintf(fp, "# "); - perf_hpp__for_each_format(fmt) { + hists__for_each_format(hists, fmt) { if (perf_hpp__should_skip(fmt, hists)) continue; @@ -487,7 +488,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, fprintf(fp, "# "); - perf_hpp__for_each_format(fmt) { + hists__for_each_format(hists, fmt) { unsigned int i; if (perf_hpp__should_skip(fmt, hists)) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 360fda01f3b0..ec164fe70718 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -478,10 +478,11 @@ void auxtrace_heap__pop(struct auxtrace_heap *heap) heap_array[last].ordinal); } -size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr) +size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr, + struct perf_evlist *evlist) { if (itr) - return itr->info_priv_size(itr); + return itr->info_priv_size(itr, evlist); return 0; } @@ -852,7 +853,7 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, int err; pr_debug2("Synthesizing auxtrace information\n"); - priv_size = auxtrace_record__info_priv_size(itr); + priv_size = auxtrace_record__info_priv_size(itr, session->evlist); ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size); if (!ev) return -ENOMEM; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index b86f90db1352..e5a8e2d4f2af 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -293,7 +293,8 @@ struct auxtrace_record { int (*recording_options)(struct auxtrace_record *itr, struct perf_evlist *evlist, struct record_opts *opts); - size_t (*info_priv_size)(struct auxtrace_record *itr); + size_t (*info_priv_size)(struct auxtrace_record *itr, + struct perf_evlist *evlist); int (*info_fill)(struct auxtrace_record *itr, struct perf_session *session, struct auxtrace_info_event *auxtrace_info, @@ -429,7 +430,8 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, int auxtrace_record__options(struct auxtrace_record *itr, struct perf_evlist *evlist, struct record_opts *opts); -size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr); +size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr, + struct perf_evlist *evlist); int auxtrace_record__info_fill(struct auxtrace_record *itr, struct perf_session *session, struct auxtrace_info_event *auxtrace_info, diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 6a7e273a514a..b28100ee1732 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -211,6 +211,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd) dsos__for_each_with_build_id(pos, &machine->dsos.head) { const char *name; size_t name_len; + bool in_kernel = false; if (!pos->hit) continue; @@ -227,8 +228,11 @@ static int machine__write_buildid_table(struct machine *machine, int fd) name_len = pos->long_name_len + 1; } + in_kernel = pos->kernel || + is_kernel_module(name, + PERF_RECORD_MISC_CPUMODE_UNKNOWN); err = write_buildid(name, name_len, pos->build_id, machine->pid, - pos->kernel ? kmisc : umisc, fd); + in_kernel ? kmisc : umisc, fd); if (err) break; } diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index fa935093a599..9bcf2bed3a6d 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -8,6 +8,10 @@ #include <linux/bitmap.h> #include "asm/bug.h" +static int max_cpu_num; +static int max_node_num; +static int *cpunode_map; + static struct cpu_map *cpu_map__default_new(void) { struct cpu_map *cpus; @@ -486,6 +490,32 @@ out: pr_err("Failed to read max nodes, using default of %d\n", max_node_num); } +int cpu__max_node(void) +{ + if (unlikely(!max_node_num)) + set_max_node_num(); + + return max_node_num; +} + +int cpu__max_cpu(void) +{ + if (unlikely(!max_cpu_num)) + set_max_cpu_num(); + + return max_cpu_num; +} + +int cpu__get_node(int cpu) +{ + if (unlikely(cpunode_map == NULL)) { + pr_debug("cpu_map not initialized\n"); + return -1; + } + + return cpunode_map[cpu]; +} + static int init_cpunode_map(void) { int i; diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 71c41b9efabb..81a2562aaa2b 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -57,37 +57,11 @@ static inline bool cpu_map__empty(const struct cpu_map *map) return map ? map->map[0] == -1 : true; } -int max_cpu_num; -int max_node_num; -int *cpunode_map; - int cpu__setup_cpunode_map(void); -static inline int cpu__max_node(void) -{ - if (unlikely(!max_node_num)) - pr_debug("cpu_map not initialized\n"); - - return max_node_num; -} - -static inline int cpu__max_cpu(void) -{ - if (unlikely(!max_cpu_num)) - pr_debug("cpu_map not initialized\n"); - - return max_cpu_num; -} - -static inline int cpu__get_node(int cpu) -{ - if (unlikely(cpunode_map == NULL)) { - pr_debug("cpu_map not initialized\n"); - return -1; - } - - return cpunode_map[cpu]; -} +int cpu__max_node(void); +int cpu__max_cpu(void); +int cpu__get_node(int cpu); int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, int (*f)(struct cpu_map *map, int cpu, void *data), diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index e8e9a9dbf5e3..8e6395439ca0 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -52,6 +52,11 @@ int dso__read_binary_type_filename(const struct dso *dso, debuglink--; if (*debuglink == '/') debuglink++; + + ret = -1; + if (!is_regular_file(filename)) + break; + ret = filename__read_debuglink(filename, debuglink, size - (debuglink - filename)); } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index cdbaf9b51e42..467808680ee4 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2362,12 +2362,15 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, case EPERM: case EACCES: return scnprintf(msg, size, - "You may not have permission to collect %sstats.\n" - "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" - " -1 - Not paranoid at all\n" - " 0 - Disallow raw tracepoint access for unpriv\n" - " 1 - Disallow cpu events for unpriv\n" - " 2 - Disallow kernel profiling for unpriv", + "You may not have permission to collect %sstats.\n\n" + "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" + "which controls use of the performance events system by\n" + "unprivileged users (without CAP_SYS_ADMIN).\n\n" + "The default value is 1:\n\n" + " -1: Allow use of (almost) all events by all users\n" + ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n" + ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" + ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN", target->system_wide ? "system-wide " : ""); case ENOENT: return scnprintf(msg, size, "The %s event is not supported.", diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 68a7612019dc..12f2d794dc28 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -432,8 +432,12 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, cmp = hist_entry__cmp(he, entry); if (!cmp) { - if (sample_self) + if (sample_self) { he_stat__add_period(&he->stat, period, weight); + hists->stats.total_period += period; + if (!he->filtered) + hists->stats.total_non_filtered_period += period; + } if (symbol_conf.cumulate_callchain) he_stat__add_period(he->stat_acc, period, weight); @@ -466,7 +470,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, if (!he) return NULL; - hists->nr_entries++; + if (sample_self) + hists__inc_stats(hists, he); + else + hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, hists->entries_in); @@ -951,10 +958,11 @@ out: int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) { + struct hists *hists = left->hists; struct perf_hpp_fmt *fmt; int64_t cmp = 0; - perf_hpp__for_each_sort_list(fmt) { + hists__for_each_sort_list(hists, fmt) { cmp = fmt->cmp(fmt, left, right); if (cmp) break; @@ -966,10 +974,11 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) { + struct hists *hists = left->hists; struct perf_hpp_fmt *fmt; int64_t cmp = 0; - perf_hpp__for_each_sort_list(fmt) { + hists__for_each_sort_list(hists, fmt) { cmp = fmt->collapse(fmt, left, right); if (cmp) break; @@ -1110,10 +1119,11 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { + struct hists *hists = a->hists; struct perf_hpp_fmt *fmt; int64_t cmp = 0; - perf_hpp__for_each_sort_list(fmt) { + hists__for_each_sort_list(hists, fmt) { if (perf_hpp__should_skip(fmt, a->hists)) continue; @@ -1163,9 +1173,18 @@ static void __hists__insert_output_entry(struct rb_root *entries, struct rb_node *parent = NULL; struct hist_entry *iter; - if (use_callchain) + if (use_callchain) { + if (callchain_param.mode == CHAIN_GRAPH_REL) { + u64 total = he->stat.period; + + if (symbol_conf.cumulate_callchain) + total = he->stat_acc->period; + + min_callchain_hits = total * (callchain_param.min_percent / 100); + } callchain_param.sort(&he->sorted_chain, he->callchain, min_callchain_hits, &callchain_param); + } while (*p != NULL) { parent = *p; @@ -1181,21 +1200,15 @@ static void __hists__insert_output_entry(struct rb_root *entries, rb_insert_color(&he->rb_node, entries); } -void hists__output_resort(struct hists *hists, struct ui_progress *prog) +static void output_resort(struct hists *hists, struct ui_progress *prog, + bool use_callchain) { struct rb_root *root; struct rb_node *next; struct hist_entry *n; u64 min_callchain_hits; - struct perf_evsel *evsel = hists_to_evsel(hists); - bool use_callchain; - if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph) - use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN; - else - use_callchain = symbol_conf.use_callchain; - - min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100); + min_callchain_hits = hists__total_period(hists) * (callchain_param.min_percent / 100); if (sort__need_collapse) root = &hists->entries_collapsed; @@ -1223,6 +1236,23 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog) } } +void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog) +{ + bool use_callchain; + + if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph) + use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN; + else + use_callchain = symbol_conf.use_callchain; + + output_resort(evsel__hists(evsel), prog, use_callchain); +} + +void hists__output_resort(struct hists *hists, struct ui_progress *prog) +{ + output_resort(hists, prog, symbol_conf.use_callchain); +} + static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h, enum hist_filter filter) { @@ -1254,28 +1284,6 @@ static bool hists__filter_entry_by_dso(struct hists *hists, return false; } -void hists__filter_by_dso(struct hists *hists) -{ - struct rb_node *nd; - - hists->stats.nr_non_filtered_samples = 0; - - hists__reset_filter_stats(hists); - hists__reset_col_len(hists); - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (symbol_conf.exclude_other && !h->parent) - continue; - - if (hists__filter_entry_by_dso(hists, h)) - continue; - - hists__remove_entry_filter(hists, h, HIST_FILTER__DSO); - } -} - static bool hists__filter_entry_by_thread(struct hists *hists, struct hist_entry *he) { @@ -1288,25 +1296,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists, return false; } -void hists__filter_by_thread(struct hists *hists) -{ - struct rb_node *nd; - - hists->stats.nr_non_filtered_samples = 0; - - hists__reset_filter_stats(hists); - hists__reset_col_len(hists); - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (hists__filter_entry_by_thread(hists, h)) - continue; - - hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD); - } -} - static bool hists__filter_entry_by_symbol(struct hists *hists, struct hist_entry *he) { @@ -1320,25 +1309,6 @@ static bool hists__filter_entry_by_symbol(struct hists *hists, return false; } -void hists__filter_by_symbol(struct hists *hists) -{ - struct rb_node *nd; - - hists->stats.nr_non_filtered_samples = 0; - - hists__reset_filter_stats(hists); - hists__reset_col_len(hists); - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (hists__filter_entry_by_symbol(hists, h)) - continue; - - hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL); - } -} - static bool hists__filter_entry_by_socket(struct hists *hists, struct hist_entry *he) { @@ -1351,7 +1321,9 @@ static bool hists__filter_entry_by_socket(struct hists *hists, return false; } -void hists__filter_by_socket(struct hists *hists) +typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he); + +static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter) { struct rb_node *nd; @@ -1363,13 +1335,37 @@ void hists__filter_by_socket(struct hists *hists) for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - if (hists__filter_entry_by_socket(hists, h)) + if (filter(hists, h)) continue; - hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET); + hists__remove_entry_filter(hists, h, type); } } +void hists__filter_by_thread(struct hists *hists) +{ + hists__filter_by_type(hists, HIST_FILTER__THREAD, + hists__filter_entry_by_thread); +} + +void hists__filter_by_dso(struct hists *hists) +{ + hists__filter_by_type(hists, HIST_FILTER__DSO, + hists__filter_entry_by_dso); +} + +void hists__filter_by_symbol(struct hists *hists) +{ + hists__filter_by_type(hists, HIST_FILTER__SYMBOL, + hists__filter_entry_by_symbol); +} + +void hists__filter_by_socket(struct hists *hists) +{ + hists__filter_by_type(hists, HIST_FILTER__SOCKET, + hists__filter_entry_by_socket); +} + void events_stats__inc(struct events_stats *stats, u32 type) { ++stats->nr_events[0]; @@ -1585,7 +1581,7 @@ int perf_hist_config(const char *var, const char *value) return 0; } -int __hists__init(struct hists *hists) +int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list) { memset(hists, 0, sizeof(*hists)); hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; @@ -1594,6 +1590,7 @@ int __hists__init(struct hists *hists) hists->entries = RB_ROOT; pthread_mutex_init(&hists->lock, NULL); hists->socket_filter = -1; + hists->hpp_list = hpp_list; return 0; } @@ -1630,7 +1627,7 @@ static int hists_evsel__init(struct perf_evsel *evsel) { struct hists *hists = evsel__hists(evsel); - __hists__init(hists); + __hists__init(hists, &perf_hpp_list); return 0; } @@ -1649,3 +1646,9 @@ int hists__init(void) return err; } + +void perf_hpp_list__init(struct perf_hpp_list *list) +{ + INIT_LIST_HEAD(&list->fields); + INIT_LIST_HEAD(&list->sorts); +} diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index d4ec4822a103..1c7544a8fe1a 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -75,6 +75,7 @@ struct hists { u64 event_stream; u16 col_len[HISTC_NR_COLS]; int socket_filter; + struct perf_hpp_list *hpp_list; }; struct hist_entry_iter; @@ -128,6 +129,7 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, struct hists *hists); void hist_entry__delete(struct hist_entry *he); +void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog); void hists__output_resort(struct hists *hists, struct ui_progress *prog); void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); @@ -185,7 +187,7 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel) } int hists__init(void); -int __hists__init(struct hists *hists); +int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list); struct rb_root *hists__get_rotate_entries_in(struct hists *hists); bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, @@ -214,28 +216,56 @@ struct perf_hpp_fmt { struct hist_entry *a, struct hist_entry *b); int64_t (*sort)(struct perf_hpp_fmt *fmt, struct hist_entry *a, struct hist_entry *b); + bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); + void (*free)(struct perf_hpp_fmt *fmt); struct list_head list; struct list_head sort_list; bool elide; int len; int user_len; + int idx; }; -extern struct list_head perf_hpp__list; -extern struct list_head perf_hpp__sort_list; +struct perf_hpp_list { + struct list_head fields; + struct list_head sorts; +}; + +extern struct perf_hpp_list perf_hpp_list; + +void perf_hpp_list__column_register(struct perf_hpp_list *list, + struct perf_hpp_fmt *format); +void perf_hpp_list__register_sort_field(struct perf_hpp_list *list, + struct perf_hpp_fmt *format); + +static inline void perf_hpp__column_register(struct perf_hpp_fmt *format) +{ + perf_hpp_list__column_register(&perf_hpp_list, format); +} -#define perf_hpp__for_each_format(format) \ - list_for_each_entry(format, &perf_hpp__list, list) +static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format) +{ + perf_hpp_list__register_sort_field(&perf_hpp_list, format); +} + +#define perf_hpp_list__for_each_format(_list, format) \ + list_for_each_entry(format, &(_list)->fields, list) -#define perf_hpp__for_each_format_safe(format, tmp) \ - list_for_each_entry_safe(format, tmp, &perf_hpp__list, list) +#define perf_hpp_list__for_each_format_safe(_list, format, tmp) \ + list_for_each_entry_safe(format, tmp, &(_list)->fields, list) -#define perf_hpp__for_each_sort_list(format) \ - list_for_each_entry(format, &perf_hpp__sort_list, sort_list) +#define perf_hpp_list__for_each_sort_list(_list, format) \ + list_for_each_entry(format, &(_list)->sorts, sort_list) -#define perf_hpp__for_each_sort_list_safe(format, tmp) \ - list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list) +#define perf_hpp_list__for_each_sort_list_safe(_list, format, tmp) \ + list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list) + +#define hists__for_each_format(hists, format) \ + perf_hpp_list__for_each_format((hists)->hpp_list, fmt) + +#define hists__for_each_sort_list(hists, format) \ + perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt) extern struct perf_hpp_fmt perf_hpp__format[]; @@ -254,19 +284,14 @@ enum { }; void perf_hpp__init(void); -void perf_hpp__column_register(struct perf_hpp_fmt *format); void perf_hpp__column_unregister(struct perf_hpp_fmt *format); -void perf_hpp__column_enable(unsigned col); -void perf_hpp__column_disable(unsigned col); void perf_hpp__cancel_cumulate(void); +void perf_hpp__setup_output_field(struct perf_hpp_list *list); +void perf_hpp__reset_output_field(struct perf_hpp_list *list); +void perf_hpp__append_sort_keys(struct perf_hpp_list *list); -void perf_hpp__register_sort_field(struct perf_hpp_fmt *format); -void perf_hpp__setup_output_field(void); -void perf_hpp__reset_output_field(void); -void perf_hpp__append_sort_keys(void); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); -bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format); bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists); @@ -381,4 +406,6 @@ int parse_filter_percentage(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused); int perf_hist_config(const char *var, const char *value); +void perf_hpp_list__init(struct perf_hpp_list *list); + #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 81a2eb77ba7f..05d815851be1 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -2068,6 +2068,15 @@ int intel_pt_process_auxtrace_info(union perf_event *event, err = -ENOMEM; goto err_free_queues; } + + /* + * Since this thread will not be kept in any rbtree not in a + * list, initialize its list node so that at thread__put() the + * current thread lifetime assuption is kept and we don't segfault + * at list_del_init(). + */ + INIT_LIST_HEAD(&pt->unknown_thread->node); + err = thread__set_comm(pt->unknown_thread, "unknown", 0); if (err) goto err_delete_thread; diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index ae825d4ec110..d01e73592f6e 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -122,6 +122,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm, bool kvm_exit_event(struct perf_evsel *evsel); bool kvm_entry_event(struct perf_evsel *evsel); +int setup_kvm_events_tp(struct perf_kvm_stat *kvm); #define define_exit_reasons_table(name, symbols) \ static struct exit_reasons_table name[] = { \ @@ -133,8 +134,13 @@ bool kvm_entry_event(struct perf_evsel *evsel); */ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid); -extern const char * const kvm_events_tp[]; +extern const char *kvm_events_tp[]; extern struct kvm_reg_events_ops kvm_reg_events_ops[]; extern const char * const kvm_skip_events[]; +extern const char *vcpu_id_str; +extern const int decode_str_len; +extern const char *kvm_exit_reason; +extern const char *kvm_entry_trace; +extern const char *kvm_exit_trace; #endif /* __PERF_KVM_STAT_H */ diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 2c2b443df5ba..1a3e45baf97f 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -180,6 +180,16 @@ struct symbol *machine__find_kernel_symbol(struct machine *machine, } static inline +struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, + enum map_type type, const char *name, + struct map **mapp, + symbol_filter_t filter) +{ + return map_groups__find_symbol_by_name(&machine->kmaps, type, name, + mapp, filter); +} + +static inline struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr, struct map **mapp, symbol_filter_t filter) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4f7b0efdde2f..813d9b272c81 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -399,6 +399,9 @@ static void tracepoint_error(struct parse_events_error *e, int err, { char help[BUFSIZ]; + if (!e) + return; + /* * We get error directly from syscall errno ( > 0), * or from encoded pointer's error ( < 0). diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index b597bcc8fc78..41a9c875e492 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -153,7 +153,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n if (fd == -1) return -1; - sret = read(fd, alias->unit, UNIT_MAX_LEN); + sret = read(fd, alias->unit, UNIT_MAX_LEN); if (sret < 0) goto error; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 2be10fb27172..4ce5c5e18f48 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -686,8 +686,9 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) pf->fb_ops = NULL; #if _ELFUTILS_PREREQ(0, 142) } else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa && - pf->cfi != NULL) { - if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 || + (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) { + if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 && + (dwarf_cfi_addrframe(pf->cfi_dbg, pf->addr, &frame) != 0)) || dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) { pr_warning("Failed to get call frame on 0x%jx\n", (uintmax_t)pf->addr); @@ -1015,8 +1016,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data) return DWARF_CB_OK; } -/* Find probe points from debuginfo */ -static int debuginfo__find_probes(struct debuginfo *dbg, +static int debuginfo__find_probe_location(struct debuginfo *dbg, struct probe_finder *pf) { struct perf_probe_point *pp = &pf->pev->point; @@ -1025,27 +1025,6 @@ static int debuginfo__find_probes(struct debuginfo *dbg, Dwarf_Die *diep; int ret = 0; -#if _ELFUTILS_PREREQ(0, 142) - Elf *elf; - GElf_Ehdr ehdr; - GElf_Shdr shdr; - - /* Get the call frame information from this dwarf */ - elf = dwarf_getelf(dbg->dbg); - if (elf == NULL) - return -EINVAL; - - if (gelf_getehdr(elf, &ehdr) == NULL) - return -EINVAL; - - if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) && - shdr.sh_type == SHT_PROGBITS) { - pf->cfi = dwarf_getcfi_elf(elf); - } else { - pf->cfi = dwarf_getcfi(dbg->dbg); - } -#endif - off = 0; pf->lcache = intlist__new(NULL); if (!pf->lcache) @@ -1108,6 +1087,39 @@ found: return ret; } +/* Find probe points from debuginfo */ +static int debuginfo__find_probes(struct debuginfo *dbg, + struct probe_finder *pf) +{ + int ret = 0; + +#if _ELFUTILS_PREREQ(0, 142) + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + + if (pf->cfi_eh || pf->cfi_dbg) + return debuginfo__find_probe_location(dbg, pf); + + /* Get the call frame information from this dwarf */ + elf = dwarf_getelf(dbg->dbg); + if (elf == NULL) + return -EINVAL; + + if (gelf_getehdr(elf, &ehdr) == NULL) + return -EINVAL; + + if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) && + shdr.sh_type == SHT_PROGBITS) + pf->cfi_eh = dwarf_getcfi_elf(elf); + + pf->cfi_dbg = dwarf_getcfi(dbg->dbg); +#endif + + ret = debuginfo__find_probe_location(dbg, pf); + return ret; +} + struct local_vars_finder { struct probe_finder *pf; struct perf_probe_arg *args; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index bed82716e1b4..0aec7704e395 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -76,7 +76,10 @@ struct probe_finder { /* For variable searching */ #if _ELFUTILS_PREREQ(0, 142) - Dwarf_CFI *cfi; /* Call Frame Information */ + /* Call Frame Information from .eh_frame */ + Dwarf_CFI *cfi_eh; + /* Call Frame Information from .debug_frame */ + Dwarf_CFI *cfi_dbg; #endif Dwarf_Op *fb_ops; /* Frame base attribute */ struct perf_probe_arg *pvar; /* Current target variable */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index ec722346e6ff..de620f7f40f4 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -25,6 +25,7 @@ int sort__has_parent = 0; int sort__has_sym = 0; int sort__has_dso = 0; int sort__has_socket = 0; +int sort__has_thread = 0; enum sort_mode sort__mode = SORT_MODE__NORMAL; @@ -1440,20 +1441,6 @@ struct hpp_sort_entry { struct sort_entry *se; }; -bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) -{ - struct hpp_sort_entry *hse_a; - struct hpp_sort_entry *hse_b; - - if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b)) - return false; - - hse_a = container_of(a, struct hpp_sort_entry, hpp); - hse_b = container_of(b, struct hpp_sort_entry, hpp); - - return hse_a->se == hse_b->se; -} - void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists) { struct hpp_sort_entry *hse; @@ -1539,6 +1526,33 @@ static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt, return sort_fn(a, b); } +bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format) +{ + return format->header == __sort__hpp_header; +} + +static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +{ + struct hpp_sort_entry *hse_a; + struct hpp_sort_entry *hse_b; + + if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b)) + return false; + + hse_a = container_of(a, struct hpp_sort_entry, hpp); + hse_b = container_of(b, struct hpp_sort_entry, hpp); + + return hse_a->se == hse_b->se; +} + +static void hse_free(struct perf_hpp_fmt *fmt) +{ + struct hpp_sort_entry *hse; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + free(hse); +} + static struct hpp_sort_entry * __sort_dimension__alloc_hpp(struct sort_dimension *sd) { @@ -1560,6 +1574,8 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) hse->hpp.cmp = __sort__hpp_cmp; hse->hpp.collapse = __sort__hpp_collapse; hse->hpp.sort = __sort__hpp_sort; + hse->hpp.equal = __sort__hpp_equal; + hse->hpp.free = hse_free; INIT_LIST_HEAD(&hse->hpp.list); INIT_LIST_HEAD(&hse->hpp.sort_list); @@ -1570,9 +1586,23 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) return hse; } -bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format) +static void hpp_free(struct perf_hpp_fmt *fmt) { - return format->header == __sort__hpp_header; + free(fmt); +} + +static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd) +{ + struct perf_hpp_fmt *fmt; + + fmt = memdup(hd->fmt, sizeof(*fmt)); + if (fmt) { + INIT_LIST_HEAD(&fmt->list); + INIT_LIST_HEAD(&fmt->sort_list); + fmt->free = hpp_free; + } + + return fmt; } static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd) @@ -1586,14 +1616,15 @@ static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd) return 0; } -static int __sort_dimension__add_hpp_output(struct sort_dimension *sd) +static int __sort_dimension__add_hpp_output(struct perf_hpp_list *list, + struct sort_dimension *sd) { struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd); if (hse == NULL) return -1; - perf_hpp__column_register(&hse->hpp); + perf_hpp_list__column_register(list, &hse->hpp); return 0; } @@ -1803,6 +1834,14 @@ bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt) return fmt->cmp == __sort__hde_cmp; } +static void hde_free(struct perf_hpp_fmt *fmt) +{ + struct hpp_dynamic_entry *hde; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + free(hde); +} + static struct hpp_dynamic_entry * __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field) { @@ -1827,6 +1866,7 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field) hde->hpp.cmp = __sort__hde_cmp; hde->hpp.collapse = __sort__hde_cmp; hde->hpp.sort = __sort__hde_cmp; + hde->hpp.free = hde_free; INIT_LIST_HEAD(&hde->hpp.list); INIT_LIST_HEAD(&hde->hpp.sort_list); @@ -2064,40 +2104,54 @@ static int __sort_dimension__add(struct sort_dimension *sd) static int __hpp_dimension__add(struct hpp_dimension *hd) { - if (!hd->taken) { - hd->taken = 1; + struct perf_hpp_fmt *fmt; - perf_hpp__register_sort_field(hd->fmt); - } + if (hd->taken) + return 0; + + fmt = __hpp_dimension__alloc_hpp(hd); + if (!fmt) + return -1; + + hd->taken = 1; + perf_hpp__register_sort_field(fmt); return 0; } -static int __sort_dimension__add_output(struct sort_dimension *sd) +static int __sort_dimension__add_output(struct perf_hpp_list *list, + struct sort_dimension *sd) { if (sd->taken) return 0; - if (__sort_dimension__add_hpp_output(sd) < 0) + if (__sort_dimension__add_hpp_output(list, sd) < 0) return -1; sd->taken = 1; return 0; } -static int __hpp_dimension__add_output(struct hpp_dimension *hd) +static int __hpp_dimension__add_output(struct perf_hpp_list *list, + struct hpp_dimension *hd) { - if (!hd->taken) { - hd->taken = 1; + struct perf_hpp_fmt *fmt; - perf_hpp__column_register(hd->fmt); - } + if (hd->taken) + return 0; + + fmt = __hpp_dimension__alloc_hpp(hd); + if (!fmt) + return -1; + + hd->taken = 1; + perf_hpp_list__column_register(list, fmt); return 0; } int hpp_dimension__add_output(unsigned col) { BUG_ON(col >= PERF_HPP__MAX_INDEX); - return __hpp_dimension__add_output(&hpp_sort_dimensions[col]); + return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]); } static int sort_dimension__add(const char *tok, @@ -2136,6 +2190,8 @@ static int sort_dimension__add(const char *tok, sort__has_dso = 1; } else if (sd->entry == &sort_socket) { sort__has_socket = 1; + } else if (sd->entry == &sort_thread) { + sort__has_thread = 1; } return __sort_dimension__add(sd); @@ -2188,6 +2244,26 @@ static int sort_dimension__add(const char *tok, return -ESRCH; } +static int setup_sort_list(char *str, struct perf_evlist *evlist) +{ + char *tmp, *tok; + int ret = 0; + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + ret = sort_dimension__add(tok, evlist); + if (ret == -EINVAL) { + error("Invalid --sort key: `%s'", tok); + break; + } else if (ret == -ESRCH) { + error("Unknown --sort key: `%s'", tok); + break; + } + } + + return ret; +} + static const char *get_default_sort_order(struct perf_evlist *evlist) { const char *default_sort_orders[] = { @@ -2282,7 +2358,7 @@ static char *setup_overhead(char *keys) static int __setup_sorting(struct perf_evlist *evlist) { - char *tmp, *tok, *str; + char *str; const char *sort_keys; int ret = 0; @@ -2320,17 +2396,7 @@ static int __setup_sorting(struct perf_evlist *evlist) } } - for (tok = strtok_r(str, ", ", &tmp); - tok; tok = strtok_r(NULL, ", ", &tmp)) { - ret = sort_dimension__add(tok, evlist); - if (ret == -EINVAL) { - error("Invalid --sort key: `%s'", tok); - break; - } else if (ret == -ESRCH) { - error("Unknown --sort key: `%s'", tok); - break; - } - } + ret = setup_sort_list(str, evlist); free(str); return ret; @@ -2341,7 +2407,7 @@ void perf_hpp__set_elide(int idx, bool elide) struct perf_hpp_fmt *fmt; struct hpp_sort_entry *hse; - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { if (!perf_hpp__is_sort_entry(fmt)) continue; @@ -2401,7 +2467,7 @@ void sort__setup_elide(FILE *output) struct perf_hpp_fmt *fmt; struct hpp_sort_entry *hse; - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { if (!perf_hpp__is_sort_entry(fmt)) continue; @@ -2413,7 +2479,7 @@ void sort__setup_elide(FILE *output) * It makes no sense to elide all of sort entries. * Just revert them to show up again. */ - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { if (!perf_hpp__is_sort_entry(fmt)) continue; @@ -2421,7 +2487,7 @@ void sort__setup_elide(FILE *output) return; } - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { if (!perf_hpp__is_sort_entry(fmt)) continue; @@ -2429,7 +2495,7 @@ void sort__setup_elide(FILE *output) } } -static int output_field_add(char *tok) +static int output_field_add(struct perf_hpp_list *list, char *tok) { unsigned int i; @@ -2439,7 +2505,7 @@ static int output_field_add(char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - return __sort_dimension__add_output(sd); + return __sort_dimension__add_output(list, sd); } for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { @@ -2448,7 +2514,7 @@ static int output_field_add(char *tok) if (strncasecmp(tok, hd->name, strlen(tok))) continue; - return __hpp_dimension__add_output(hd); + return __hpp_dimension__add_output(list, hd); } for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { @@ -2457,7 +2523,7 @@ static int output_field_add(char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - return __sort_dimension__add_output(sd); + return __sort_dimension__add_output(list, sd); } for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) { @@ -2466,12 +2532,32 @@ static int output_field_add(char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - return __sort_dimension__add_output(sd); + return __sort_dimension__add_output(list, sd); } return -ESRCH; } +static int setup_output_list(struct perf_hpp_list *list, char *str) +{ + char *tmp, *tok; + int ret = 0; + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + ret = output_field_add(list, tok); + if (ret == -EINVAL) { + error("Invalid --fields key: `%s'", tok); + break; + } else if (ret == -ESRCH) { + error("Unknown --fields key: `%s'", tok); + break; + } + } + + return ret; +} + static void reset_dimensions(void) { unsigned int i; @@ -2496,7 +2582,7 @@ bool is_strict_order(const char *order) static int __setup_output_field(void) { - char *tmp, *tok, *str, *strp; + char *str, *strp; int ret = -EINVAL; if (field_order == NULL) @@ -2516,17 +2602,7 @@ static int __setup_output_field(void) goto out; } - for (tok = strtok_r(strp, ", ", &tmp); - tok; tok = strtok_r(NULL, ", ", &tmp)) { - ret = output_field_add(tok); - if (ret == -EINVAL) { - error("Invalid --fields key: `%s'", tok); - break; - } else if (ret == -ESRCH) { - error("Unknown --fields key: `%s'", tok); - break; - } - } + ret = setup_output_list(&perf_hpp_list, strp); out: free(str); @@ -2560,9 +2636,9 @@ int setup_sorting(struct perf_evlist *evlist) return err; /* copy sort keys to output fields */ - perf_hpp__setup_output_field(); + perf_hpp__setup_output_field(&perf_hpp_list); /* and then copy output fields to sort keys */ - perf_hpp__append_sort_keys(); + perf_hpp__append_sort_keys(&perf_hpp_list); return 0; } @@ -2578,5 +2654,5 @@ void reset_output_field(void) sort_order = NULL; reset_dimensions(); - perf_hpp__reset_output_field(); + perf_hpp__reset_output_field(&perf_hpp_list); } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 687bbb124428..89a1273fd2da 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -32,9 +32,11 @@ extern const char default_sort_order[]; extern regex_t ignore_callees_regex; extern int have_ignore_callees; extern int sort__need_collapse; +extern int sort__has_dso; extern int sort__has_parent; extern int sort__has_sym; extern int sort__has_socket; +extern int sort__has_thread; extern enum sort_mode sort__mode; extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 2b58edccd56f..4d9b481cf3b6 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -97,7 +97,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel) } } -void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) { int i; struct perf_stat_evsel *ps = evsel->priv; @@ -108,7 +108,7 @@ void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) perf_stat_evsel_id_init(evsel); } -int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) +static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat_evsel)); if (evsel->priv == NULL) @@ -117,13 +117,13 @@ int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) return 0; } -void perf_evsel__free_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) { zfree(&evsel->priv); } -int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, - int ncpus, int nthreads) +static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, + int ncpus, int nthreads) { struct perf_counts *counts; @@ -134,13 +134,13 @@ int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, return counts ? 0 : -ENOMEM; } -void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) +static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) { perf_counts__delete(evsel->prev_raw_counts); evsel->prev_raw_counts = NULL; } -int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) +static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) { int ncpus = perf_evsel__nr_cpus(evsel); int nthreads = thread_map__nr(evsel->threads); @@ -311,6 +311,16 @@ int perf_stat_process_counter(struct perf_stat_config *config, aggr->val = aggr->ena = aggr->run = 0; + /* + * We calculate counter's data every interval, + * and the display code shows ps->res_stats + * avg value. We need to zero the stats for + * interval mode, otherwise overall avg running + * averages will be shown for each interval. + */ + if (config->interval) + init_stats(ps->res_stats); + if (counter->per_pkg) zero_per_pkg(counter); diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 086f4e128d63..2af63c9cb59f 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -74,16 +74,6 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, double avg, int cpu, enum aggr_mode aggr); -void perf_evsel__reset_stat_priv(struct perf_evsel *evsel); -int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel); -void perf_evsel__free_stat_priv(struct perf_evsel *evsel); - -int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, - int ncpus, int nthreads); -void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel); - -int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw); - int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); void perf_evlist__free_stats(struct perf_evlist *evlist); void perf_evlist__reset_stats(struct perf_evlist *evlist); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index ab02209a7cf3..90cedfa30e43 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1466,7 +1466,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ - if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) + if (is_regular_file(name) && + filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); /* @@ -1487,6 +1488,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) root_dir, name, PATH_MAX)) continue; + if (!is_regular_file(name)) + continue; + /* Name is now the name of the next image to try */ if (symsrc__init(ss, dso, name, symtab_type) < 0) continue; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index ead9509835d2..b9e2843cfbe7 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -691,3 +691,30 @@ out: return tip; } + +bool is_regular_file(const char *file) +{ + struct stat st; + + if (stat(file, &st)) + return false; + + return S_ISREG(st.st_mode); +} + +int fetch_current_timestamp(char *buf, size_t sz) +{ + struct timeval tv; + struct tm tm; + char dt[32]; + + if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm)) + return -1; + + if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm)) + return -1; + + scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000); + + return 0; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index fe915e616f9b..a8615816a00d 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -343,5 +343,7 @@ int fetch_kernel_version(unsigned int *puint, #define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x) const char *perf_tip(const char *dirpath); +bool is_regular_file(const char *file); +int fetch_current_timestamp(char *buf, size_t sz); #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 7ec7df9e7fc7..0c1a7e65bb81 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -113,7 +113,7 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res, } EXPORT_SYMBOL(__wrap_devm_memremap_pages); -pfn_t __wrap_phys_to_pfn_t(dma_addr_t addr, unsigned long flags) +pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags) { struct nfit_test_resource *nfit_res = get_nfit_res(addr); |