aboutsummaryrefslogtreecommitdiff
path: root/tools
AgeCommit message (Collapse)AuthorFilesLines
2017-01-19selftests: Add intel_pstate to TARGETSStafford Horne1-0/+1
This test was missing from the TARGETS list. The test requires patches to cpupower to pass correctly. Cc: Prarit Bhargava <[email protected]> Signed-off-by: Stafford Horne <[email protected]> Signed-off-by: Shuah Khan <[email protected]>
2017-01-19selftests/intel_pstate: Update makefile to match new styleStafford Horne1-9/+4
Recent changes from Bamvor (88baa78d1f318) have standardized the variable names like TEST_GEN_FILES and removed the need for make targets all and clean. These changes bring the intel_pstate test inline with those changes. Cc: Prarit Bhargava <[email protected]> Signed-off-by: Stafford Horne <[email protected]> Signed-off-by: Shuah Khan <[email protected]>
2017-01-19selftests/intel_pstate: Fix warning on loop index overflowStafford Horne1-1/+1
The build was showing the warning: aperf.c:60:27: warning: iteration 2147483647 invokes undefined behavior [-Waggressive-loop-optimizations] for (i=0; i<0x8fffffff; i++) { This change sets i, cpu and fd to unsigned int as they should not need to be signed. Cc: Prarit Bhargava <[email protected]> Signed-off-by: Stafford Horne <[email protected]> Signed-off-by: Shuah Khan <[email protected]>
2017-01-19cpupower: Restore format of frequency-info limitStafford Horne1-9/+12
The intel_pstate kselftest expects that the output of `cpupower frequency-info -l | tail -1 | awk ' { print $1 } '` to get frequency limits. This does not work after the following two changes. - 562e5f1a3: rework the "cpupower frequency-info" command (Jacob Tanenbaum) removed parsable limit output - ce512b840: Do not analyse offlined cpus (Thomas Renninger) added newline to break limit parsing more This change preserves human readable output if wanted as well as parsable output for scripts/tests. Cc: Thomas Renninger <[email protected]> Cc: "Shreyas B. Prabhu" <[email protected]> Cc: "Rafael J. Wysocki" <[email protected]> Cc: [email protected] Signed-off-by: Stafford Horne <[email protected]> Signed-off-by: Shuah Khan <[email protected]>
2017-01-19selftests/futex: Add headers to makefile dependenciesStafford Horne1-1/+4
The futex makefile did not contain dependencies for all headers, so if we make changes to logging.h rebuild will not happen. Add headers to fix it up. Signed-off-by: Stafford Horne <[email protected]> Signed-off-by: Shuah Khan <[email protected]>
2017-01-19selftests/futex: Add stdio used for loggingStafford Horne1-0/+1
Fix missing printf compile warnings. Signed-off-by: Stafford Horne <[email protected]> Signed-off-by: Shuah Khan <[email protected]>
2017-01-19Merge tag 'iio-for-4.11a' of ↵Greg Kroah-Hartman1-0/+2
git://git.kernel.org/pub/scm/linux/kernel/git/jic23/iio into staging-next Jonathan writes: First round of new device support, features and cleanups for IIO in the 4.11 cycle. It's shaping to be another fairly busy cycle. Lots more on the way! New device support * ads7950 - new driver supporting ads7950, ads7951, ads7952, ads7953, ads7954, ads7955, ads7956, ads7957, ads7958, ads7959, ads7960, and ads7961 ADCs. * cm3605 - New driver for this light sensor and proximity sensor which is an analog part with some additional digital controls. * hx711 - New driver. Core new stuff * Gravity sensor type. This is a processed datastream in which the device will try to work out which way is down. * Split the buffer.h file into two parts. One provides the interface to 'use' a buffer, the second provides the internals of the buffer functionality as needed by implementations of buffers. - Move documentation inline so as to allow use of private: tag when generating documentation. - Add some utility functions for the few things that are directly done with the buffers. - Stop exporting functions that no-one uses outside of the core code. - Push docs down by the code in the c file where they should have always been. - Fix typo in kernel-doc for buffer. - push down some includes that were previously happening implicitly. - stop enabling the timestamp of the dummy device. Features and cleanups * ad5592r - ACPI support * ad5593r -ACPI support. * ad5933 - Fix a false comment about size of a particular register. * ad7150 - replace S_IRUGO | S_IWUSR with 0644. I'm not that keen on these patches in general, but as it was nicely presented I took this one anyway. As a general rule will only take these as part of a larger driver cleanup. - don't eat an error but rather reutnr it in the write_event_config callback. * ad7606 - replace non standard range attibute with _scale * ade7753 - use usleep_range for short sleeps * ade7754 - use usleep_range for short sleeps * ade7758 - use usleep_range for short sleeps * ade7759 - use usleep_range for short sleeps * ade7854 - use usleep_range for short sleeps * adis16201 - fix description * adis16203 - fix description - fix copyright year * adis16209 - fix description * adt7316 - Add braces to arms of if else statement (for consistency) - Alignment fixes. * axp288 - Fix up an issue with accidental overwrites of data. * bmi160 - add deivce tables for i2c and spi to support correctly identifying the full dt name (including manufacturer). - device tree binding. * bmp280 - use usleep_range for short sleeps. * cm3232 - return error from cm3232_reg_init rather than eating it if the last write fails. * dummy driver - remove a semicolor found at end of a function defintition. * exynos-adc - use usleep_range for short sleeps. * hid-sensor (accel) - Add timestamp support. The hardware can provide timestamps so lets support them. If not fall back to timestamps estimated in kernel. * hid-sensor (light) - Add a duplicate ID for the light channels so as to keep existing interface whilst also using the more standard IIO interface. * hts221 - acpi probing * imx25-gcq - Add a macro call to allow this driver to be automatically loaded. * isl29028 - reorganise code to avoid deep nesting of if statements. - move chip test and default regs into a function suitable or sharing with power management code. - tidy up some code alignment. * lidar-lite-v3 - introduce compatible strings that make it clear Garmin have consideral friends. * mma8452 - avoid returning signed value when unsigned is appropriate * spmi-vadc - Update function for generic voltage conversion to take into account that different channels on this device should be handled differently. - Rework code to allow per channel voltage scaling and support the standard options for this hardware. - Fixup three minor issues with the above patches for this part. These all effect test builds rather than the native builds for the part, but good to clean them up anyway. * st_sensors - support device matching from the ACPI DST tables. - acpi based probing for accelerometers - acpi based probing for pressure sensors - Allow pressure sensors to read negative values. - Export sampling frequency for lps25h and lps331ap. - Add support for the old DT bindings from the period when these deivces were often supported through windows. Docs fixup: * typo in sysfs-bus-iio
2017-01-19objtool: Fix IRET's opcodeJiri Slaby1-1/+1
The IRET opcode is 0xcf according to the Intel manual and also to objdump of my vmlinux: 1ea8: 48 cf iretq Fix the opcode in arch_decode_instruction(). The previous value (0xc5) seems to correspond to LDS. Signed-off-by: Jiri Slaby <[email protected]> Acked-by: Josh Poimboeuf <[email protected]> Cc: Andy Lutomirski <[email protected]> Cc: Borislav Petkov <[email protected]> Cc: Brian Gerst <[email protected]> Cc: Denys Vlasenko <[email protected]> Cc: H. Peter Anvin <[email protected]> Cc: Linus Torvalds <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Thomas Gleixner <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Ingo Molnar <[email protected]>
2017-01-18perf unwind: Fix looking up dwarf unwind stack infoMatija Glavinic Pecotic2-16/+86
Using perf with call graph method dwarf fails to provide backtrace support for stripped binary even though .gnu_debuglink points to *.dbg flavor with properly populated debug symbols. Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and 4.10.rc3. Perf is configured with libunwind, and unwind dwarf support [1]. Test code (stress_bt.c) can be found on [2]. Running (explicitly disable other unwinding methods): $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ perf record -N --call-graph dwarf ./stress_bt $ perf report results in properly generated call graph. Stripping the binary and running it results with missing call graph. Expected result is to have call graph: $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ objcopy --only-keep-debug stress_bt stress_bt.dbg $ objcopy --strip-debug stress_bt $ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt $ perf record -N --call-graph dwarf ./stress_bt $ perf report Problem is that perf doesn't try to read symbols pointed by gnu debuglink. Patch adds checking, and reading of the symbols from debuglink and symsrc. Order of the check is to first check within dso, then check whether symsrc is defined and try to read from it. Finally, debuglink is checked. Default locations of debug files are discussed in [3] and [4]. Comments on RFC are on [5]. [1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding [2] [1]#Backtrace_stress_application [3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html [4] https://sourceware.org/binutils/docs/binutils/objcopy.html [5] https://lkml.org/lkml/2016/8/22/473 Signed-off-by: Matija Glavinic Pecotic <[email protected]> Acked-by: Jiri Olsa <[email protected]> Cc: Alexander Sverdlin <[email protected]> Cc: Masami Hiramatsu <[email protected]> Cc: Namhyung Kim <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-18selftest/powerpc: Wrong PMC initialized in pmc56_overflow testMadhavan Srinivasan1-1/+1
Test uses PMC2 to count the event. But PMC1 is being initialized. Patch to fix it. Fixes: 3752e453f6ba ('selftests/powerpc: Add tests of PMU EBBs') Signed-off-by: Madhavan Srinivasan <[email protected]> Signed-off-by: Michael Ellerman <[email protected]>
2017-01-17bpf: Fix test_lru_sanity5() in test_lru_map.cMartin KaFai Lau1-26/+27
test_lru_sanity5() fails when the number of online cpus is fewer than the number of possible cpus. It can be reproduced with qemu by using cmd args "--smp cpus=2,maxcpus=8". The problem is the loop in test_lru_sanity5() is testing 'i' which is incorrect. This patch: 1. Make sched_next_online() always return -1 if it cannot find a next cpu to schedule the process. 2. In test_lru_sanity5(), the parent process does sched_setaffinity() first (through sched_next_online()) and the forked process will inherit it according to the 'man sched_setaffinity'. Fixes: 5db58faf989f ("bpf: Add tests for the LRU bpf_htab") Reported-by: Daniel Borkmann <[email protected]> Signed-off-by: Martin KaFai Lau <[email protected]> Acked-by: Daniel Borkmann <[email protected]> Acked-by: Alexei Starovoitov <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2017-01-17Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller9-45/+107
2017-01-17Merge tag 'perf-urgent-for-mingo-4.10-20170117' of ↵Ingo Molnar3-41/+72
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent Pull 'perf probe' fixes from Arnaldo Carvalho de Melo <[email protected]> - Show correct locations for 'perf probe' on modules (Masami Hiramatsu) - Correctly handle 'perf probe's on GCC generated functions in modules (Masami Hiramatsu) Signed-off-by: Arnaldo Carvalho de Melo <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
2017-01-17perf evlist: Fix typo in deliver_sample()Soramichi AKIYAMA1-1/+1
This patch fixes a typo: s/delievery/delivery/ Signed-off-by: Soramichi Akiyama <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-17perf tools: Move two variables usied in libperf from perf.cSoramichi AKIYAMA5-5/+5
The use_browser and perf_version_string variables are both declared in perf.c but they are also referenced by other functions of libperf.a. Therefore a user linking an own main() with libperf.a must declare those two variables in their files even if the files never use the browser or the version information. This patch fixes this issue by moving use_browser and perf_version_string out of perf.c to some other files. Signed-off-by: Soramichi Akiyama <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-17perf sched timehist: Show total wait times for summaryNamhyung Kim1-3/+41
When --state option is given, the summary will show total run, sleep, iowait, preempt and delay time instead of statistics of runtime. $ perf sched timehist -s --state Wait-time summary comm parent sched-in run-time sleep iowait preempt delay (count) (msec) (msec) (msec) (msec) (msec) --------------------------------------------------------------------- systemd[1] 0 3 0.497 1.685 0.000 0.000 0.061 ksoftirqd/0[3] 2 21 0.434 989.948 0.000 0.000 0.325 rcu_preempt[7] 2 28 0.386 993.211 0.000 0.000 0.712 migration/0[10] 2 12 0.126 50.174 0.000 0.000 0.044 watchdog/0[11] 2 1 0.009 0.000 0.000 0.000 0.016 migration/1[13] 2 2 0.029 11.755 0.000 0.000 0.007 <SNIP> Signed-off-by: Namhyung Kim <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: David Ahern <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Minchan Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-17perf sched timehist: Add --state optionNamhyung Kim2-4/+36
The --state option is to show task state when switched out. The state is printed as a single character like in the /proc but I added 'I' for idle state rather than 'R'. $ perf sched timehist --state | head Samples do not have callchains. time cpu task name wait time sch delay run time state [tid/pid] (msec) (msec) (msec) -------- --- ----------------------- -------- ------------------ ----- 1.753791 [3] <idle> 0.000 0.000 0.000 I 1.753834 [1] perf[27469] 0.000 0.000 0.000 S 1.753904 [3] perf[27470] 0.000 0.006 0.112 S 1.753914 [1] <idle> 0.000 0.000 0.079 I 1.753915 [3] migration/3[23] 0.000 0.002 0.011 S 1.754287 [2] <idle> 0.000 0.000 0.000 I 1.754335 [2] transmission[1773/1739] 0.000 0.004 0.047 S Signed-off-by: Namhyung Kim <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: David Ahern <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Minchan Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-17perf sched timehist: Account thread wait time separatelyNamhyung Kim1-6/+44
Separate thread wait time into 3 parts - sleep, iowait and preempt based on the prev_state of the last event. Signed-off-by: Namhyung Kim <[email protected]> Cc: David Ahern <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Minchan Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] [ Fix the build on centos:5 where 'wait' shadows a global declaration ] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-16x86/cpufeature: Add AVX512_VPOPCNTDQ featurePiotr Luc1-0/+1
Vector population count instructions for dwords and qwords are going to be available in future Intel Xeon & Xeon Phi processors. Bit 14 of CPUID[level:0x07, ECX] indicates that the instructions are supported by a processor. The specification can be found in the Intel Software Developer Manual (SDM) and in the Instruction Set Extensions Programming Reference (ISE). Populate the feature bit and clear it when xsave is disabled. Signed-off-by: Piotr Luc <[email protected]> Reviewed-by: Borislav Petkov <[email protected]> Cc: Paolo Bonzini <[email protected]> Cc: [email protected] Cc: Radim Krčmář <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Thomas Gleixner <[email protected]>
2017-01-16perf probe: Fix to probe on gcc generated functions in modulesMasami Hiramatsu3-18/+37
Fix to probe on gcc generated functions on modules. Since probing on a module is based on its symbol name, it should be adjusted on actual symbols. E.g. without this fix, perf probe shows probe definition on non-exist symbol as below. $ perf probe -m build-x86_64/net/netfilter/nf_nat.ko -F in_range* in_range.isra.12 $ perf probe -m build-x86_64/net/netfilter/nf_nat.ko -D in_range p:probe/in_range nf_nat:in_range+0 With this fix, perf probe correctly shows a probe on gcc-generated symbol. $ perf probe -m build-x86_64/net/netfilter/nf_nat.ko -D in_range p:probe/in_range nf_nat:in_range.isra.12+0 This also fixes same problem on online module as below. $ perf probe -m i915 -D assert_plane p:probe/assert_plane i915:assert_plane.constprop.134+0 Signed-off-by: Masami Hiramatsu <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/148411450673.9978.14905987549651656075.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-16perf probe: Add error checks to offline probe post-processingMasami Hiramatsu1-17/+33
Add error check codes on post processing and improve it for offline probe events as: - post processing fails if no matched symbol found in map(-ENOENT) or strdup() failed(-ENOMEM). - Even if the symbol name is the same, it updates symbol address and offset. Signed-off-by: Masami Hiramatsu <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/148411443738.9978.4617979132625405545.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-16perf probe: Fix to show correct locations for events on modulesMasami Hiramatsu1-7/+3
Fix to show correct locations for events on modules by relocating given address instead of retrying after failure. This happens when the module text size is big enough, bigger than sh_addr, because the original code retries with given address + sh_addr if it failed to find CU DIE at the given address. Any address smaller than sh_addr always fails and it retries with the correct address, but addresses bigger than sh_addr will get a CU DIE which is on the given address (not adjusted by sh_addr). In my environment(x86-64), the sh_addr of ".text" section is 0x10030. Since i915 is a huge kernel module, we can see this issue as below. $ grep "[Tt] .*\[i915\]" /proc/kallsyms | sort | head -n1 ffffffffc0270000 t i915_switcheroo_can_switch [i915] ffffffffc0270000 + 0x10030 = ffffffffc0280030, so we'll check symbols cross this boundary. $ grep "[Tt] .*\[i915\]" /proc/kallsyms | grep -B1 ^ffffffffc028\ | head -n 2 ffffffffc027ff80 t haswell_init_clock_gating [i915] ffffffffc0280110 t valleyview_init_clock_gating [i915] So setup probes on both function and see what happen. $ sudo ./perf probe -m i915 -a haswell_init_clock_gating \ -a valleyview_init_clock_gating Added new events: probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915) You can now use it in all perf tools, such as: perf record -e probe:valleyview_init_clock_gating -aR sleep 1 $ sudo ./perf probe -l probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) probe:valleyview_init_clock_gating (on i915_vga_set_decode:4@gpu/drm/i915/i915_drv.c in i915) As you can see, haswell_init_clock_gating is correctly shown, but valleyview_init_clock_gating is not. With this patch, both events are shown correctly. $ sudo ./perf probe -l probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) Committer notes: In my case: # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating Added new events: probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915) You can now use it in all perf tools, such as: perf record -e probe:valleyview_init_clock_gating -aR sleep 1 # perf probe -l probe:haswell_init_clock_gating (on i915_getparam+432@gpu/drm/i915/i915_drv.c in i915) probe:valleyview_init_clock_gating (on __i915_printk+240@gpu/drm/i915/i915_drv.c in i915) # # readelf -SW /lib/modules/4.9.0+/build/vmlinux | egrep -w '.text|Name' [Nr] Name Type Address Off Size ES Flg Lk Inf Al [ 1] .text PROGBITS ffffffff81000000 200000 822fd3 00 AX 0 0 4096 # So both are b0rked, now with the fix: # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating Added new events: probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915) You can now use it in all perf tools, such as: perf record -e probe:valleyview_init_clock_gating -aR sleep 1 # perf probe -l probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) # Both looks correct. Signed-off-by: Masami Hiramatsu <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/148411436777.9978.1440275861947194930.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-16perf script: Also allow forcing reading of non-root owned files by rootYannick Brosseau1-1/+2
In 2059fc7a5a9e ("perf symbols: Allow forcing reading of non-root owned files by root") 'perf report' was added the option of forcing reading of non-root owned symbol file. This add the same behavior for perf script. Reported-by: Mark Drayton <[email protected]> Signed-off-by: Yannick Brosseau <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: [email protected] Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-16perf script: Fix man page about --dump-raw-trace optionMichael Petlan1-2/+2
The "--dump-raw-script" is not a valid option, replace it with the valid one, "--dump-raw-trace" Signed-off-by: Michael Petlan <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Thomas Gleixner <[email protected]> Fixes: 133dc4c39c57 ("perf: Rename 'perf trace' to 'perf script'") LPU-Reference: [email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-16tools lib subcmd: Fix missing member nameSoramichi AKIYAMA1-9/+9
This patch adds missing member names to struct initializations. Although in C99 for struct S {int x, int y} two init codes struct S s = {.x = (a), (b)} and struct S s = {.x = (a), .y = (b)} are the same, it is better to explicitly write .y (.argh in this patch) for readability and robustness against language/compiler evolutions. Signed-off-by: Soramichi Akiyama <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-16perf tools: Remove unneccessary feature-dwarf warningDavid Carrillo-Cisneros1-2/+4
Don't warn for feature-dwarf==0 if user explicitily disabled DWARF by using NO_DWARF=1. Signed-off-by: David Carrillo-Cisneros <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Stephane Eranian <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-16perf pmu: Factor out scale conversion codeAndi Kleen1-28/+34
Move the scale factor parsing code to an own function to reuse it in an upcoming patch. v2: Return error in case strdup returns NULL. Signed-off-by: Andi Kleen <[email protected]> Acked-by: Jiri Olsa <[email protected]> Link: http://lkml.kernel.org/r/[email protected] [ Keep returning -ENOMEM when strdup() fails in perf_pmu__parse_scale()/convert_scale() ] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-16Merge 4.10-rc4 into driver-core-nextGreg Kroah-Hartman14-50/+111
We want the sysfs file revert and other fixes in here as well for testing. Signed-off-by: Greg Kroah-Hartman <[email protected]>
2017-01-16Merge 4.10-rc4 into usb-nextGreg Kroah-Hartman14-50/+111
We need the USB fixes in here to make merges easier/possible with the other sub-maintainer USB trees. Signed-off-by: Greg Kroah-Hartman <[email protected]>
2017-01-15Merge branch 'perf-urgent-for-linus' of ↵Linus Torvalds9-45/+107
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull perf fixes from Ingo Molnar: "Misc race fixes uncovered by fuzzing efforts, a Sparse fix, two PMU driver fixes, plus miscellanous tooling fixes" * 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: perf/x86: Reject non sampling events with precise_ip perf/x86/intel: Account interrupts for PEBS errors perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race perf/core: Fix sys_perf_event_open() vs. hotplug perf/x86/intel: Use ULL constant to prevent undefined shift behaviour perf/x86/intel/uncore: Fix hardcoded socket 0 assumption in the Haswell init code perf/x86: Set pmu->module in Intel PMU modules perf probe: Fix to probe on gcc generated symbols for offline kernel perf probe: Fix --funcs to show correct symbols for offline module perf symbols: Robustify reading of build-id from sysfs perf tools: Install tools/lib/traceevent plugins with install-bin tools lib traceevent: Fix prev/next_prio for deadline tasks perf record: Fix --switch-output documentation and comment perf record: Make __record_options static tools lib subcmd: Add OPT_STRING_OPTARG_SET option perf probe: Fix to get correct modname from elf header samples/bpf trace_output_user: Remove duplicate sys/ioctl.h include samples/bpf sock_example: Avoid getting ethhdr from two includes perf sched timehist: Show total scheduling time
2017-01-14torture: Enable DEBUG_OBJECTS_RCU_HEAD for Tiny RCUPaul E. McKenney1-1/+1
The RCU torture tests currently do not run any Tiny RCU scenarios for CONFIG_DEBUG_OBJECTS_RCU_HEAD=y. This is a hole in the test, given that someone might need this in real life and given that Tiny RCU uses different callback-handling code than does Tree RCU. This commit therefore enables this Kconfig option for scenario TINY02. Reported-by: "Ahmed, Iftekhar" <[email protected]> Signed-off-by: Paul E. McKenney <[email protected]> Reviewed-by: Josh Triplett <[email protected]>
2017-01-14torture: Update RCU test scenario documentationPaul E. McKenney1-2/+31
Signed-off-by: Paul E. McKenney <[email protected]> Reviewed-by: Josh Triplett <[email protected]>
2017-01-14torture: Run a couple scenarios with CONFIG_RCU_EQS_DEBUGPaul E. McKenney2-0/+2
This commit runs TREE04 and TREE08 with CONFIG_RCU_EQS_DEBUG=y, enabling dyntick-counter checking on those two tests. Signed-off-by: Paul E. McKenney <[email protected]> Reviewed-by: Josh Triplett <[email protected]>
2017-01-14torture: Run one test with DEBUG_LOCK_ALLOC but not PROVE_LOCKINGPaul E. McKenney1-2/+1
This commit sets CONFIG_DEBUG_LOCK_ALLOC but not CONFIG_PROVE_LOCKING for TREE08 in order to have at least one test with this configuration. Signed-off-by: Paul E. McKenney <[email protected]> Reviewed-by: Josh Triplett <[email protected]>
2017-01-14torture: Run at least one test with CONFIG_DEBUG_OBJECTS_RCU_HEADPaul E. McKenney1-0/+1
This commit enables the CONFIG_DEBUG_OBJECTS_RCU_HEAD Kconfig option in TREE02 in order to do at least some testing with this enabled. Signed-off-by: Paul E. McKenney <[email protected]> Reviewed-by: Josh Triplett <[email protected]>
2017-01-14torture: Add tests without slow grace period setup/cleanupPaul E. McKenney8-3/+21
This commit moves CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP, CONFIG_RCU_TORTURE_TEST_SLOW_INIT, and CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT from CFcommon to all of the TREE scenarios other than TREE08 and TREE09 in order to do at least some testing without these Kconfig options set. Signed-off-by: Paul E. McKenney <[email protected]> Reviewed-by: Josh Triplett <[email protected]>
2017-01-14torture: Add CONFIG_PROVE_RCU_REPEATEDLY=y for TINY02Paul E. McKenney1-0/+1
This commit adds CONFIG_PROVE_RCU_REPEATEDLY=y, which has been untested for quite some time. Signed-off-by: Paul E. McKenney <[email protected]> Reviewed-by: Josh Triplett <[email protected]>
2017-01-14torture: Add a check for CONFIG_RCU_STALL_COMMON for TINY01Paul E. McKenney1-0/+1
This commit verifies coverage of testing with CONFIG_RCU_STALL_COMMON=n. Signed-off-by: Paul E. McKenney <[email protected]> Reviewed-by: Josh Triplett <[email protected]>
2017-01-14locking/ww_mutex: Add ww_mutex to tools/testing/selftestsChris Wilson1-0/+10
Add the minimal test running (modprobe test-ww_mutex) to the kselftests CI framework. Signed-off-by: Chris Wilson <[email protected]> Signed-off-by: Peter Zijlstra (Intel) <[email protected]> Cc: Andrew Morton <[email protected]> Cc: Linus Torvalds <[email protected]> Cc: Paul E. McKenney <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Shuah Khan <[email protected]> Cc: Thomas Gleixner <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Ingo Molnar <[email protected]>
2017-01-14locking/ww_mutex: Add ww_mutex to locktorture testChris Wilson3-0/+8
Although ww_mutexes degenerate into mutexes, it would be useful to torture the deadlock handling between multiple ww_mutexes in addition to torturing the regular mutexes. Signed-off-by: Chris Wilson <[email protected]> Signed-off-by: Peter Zijlstra (Intel) <[email protected]> Cc: Andrew Morton <[email protected]> Cc: Linus Torvalds <[email protected]> Cc: Maarten Lankhorst <[email protected]> Cc: Nicolai Hähnle <[email protected]> Cc: Paul E. McKenney <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Thomas Gleixner <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Ingo Molnar <[email protected]>
2017-01-12tools: psock_lib: harden socket filter used by psock testsSowmini Varadhan1-7/+32
The filter added by sock_setfilter is intended to only permit packets matching the pattern set up by create_payload(), but we only check the ip_len, and a single test-character in the IP packet to ensure this condition. Harden the filter by adding additional constraints so that we only permit UDP/IPv4 packets that meet the ip_len and test-character requirements. Include the bpf_asm src as a comment, in case this needs to be enhanced in the future Signed-off-by: Sowmini Varadhan <[email protected]> Acked-by: Daniel Borkmann <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2017-01-12bpf: allow b/h/w/dw access for bpf's cb in ctxDaniel Borkmann1-3/+439
When structs are used to store temporary state in cb[] buffer that is used with programs and among tail calls, then the generated code will not always access the buffer in bpf_w chunks. We can ease programming of it and let this act more natural by allowing for aligned b/h/w/dw sized access for cb[] ctx member. Various test cases are attached as well for the selftest suite. Potentially, this can also be reused for other program types to pass data around. Signed-off-by: Daniel Borkmann <[email protected]> Acked-by: Alexei Starovoitov <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2017-01-11tools: Sync x86's vmx.h with the kernelArnaldo Carvalho de Melo1-0/+5
To pick the changes from: 1b07304c587d ("KVM: nVMX: support descriptor table exits") That adds entries to VMX_EXIT_REASONS, that is used by tools/perf/arch/x86/util/kvm-stat.c. This also picks the changes in: 1dc35dacc16b ("KVM: nVMX: check host CR3 on vmentry and vmexit") But these are not used in 'perf kvm stat', do it just to silence the kernel/tools file cache coherency detector: $ make -C tools/perf make: Entering directory '/home/acme/git/linux/tools/perf' BUILD: Doing 'make -j4' parallel build Warning: arch/x86/include/uapi/asm/vmx.h differs from kernel Cc: Adrian Hunter <[email protected]> Cc: David Ahern <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Ladi Prosek <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Paolo Bonzini <[email protected]> Cc: Wang Nan <[email protected]> Link: http://lkml.kernel.org/n/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-11perf record: Add switch-output time option argumentJiri Olsa2-2/+44
It's now possible to specify the threshold time for perf.data like: $ perf record --switch-output=30s ... Once it's reached, the current data are dumped in to the perf.data.<timestamp> file and session does on. $ perf record --switch-output=30s ... [ perf record: dump data: Woken up 44 times ] [ perf record: Dump perf.data.2017010213043746 ] ... The time is expected to be a number with appended unit character - s/m/h/d. Signed-off-by: Jiri Olsa <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Acked-by: Wang Nan <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-11perf record: Add switch-output size warningJiri Olsa3-1/+24
Adding switch-output size warning if the requested size of lower than the wakeup ring buffer size. $ perf record --switch-output=1K ls WARNING: switch-output data size lower than wakeup kernel buffer size (258K) expect bigger perf.data sizes ... Signed-off-by: Jiri Olsa <[email protected]> Suggested-and-Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Wang Nan <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-11perf record: Add switch-output size option argumentJiri Olsa2-16/+63
It's now possible to specify the threshold size for perf.data like: $ perf record --switch-output=2G ... Once it's reached, the current data are dumped in to the perf.data.<timestamp> file and session does on. $ perf record --switch-output=2G ... [ perf record: dump data: Woken up 7244 times ] [ perf record: Dump perf.data.2017010214093746 ] ... The size is expected to be a number with appended unit character - B/K/M/G. Signed-off-by: Jiri Olsa <[email protected]> Acked-by: Wang Nan <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-11perf record: Change switch-output option to take optional argumentJiri Olsa1-2/+26
Next patches will add --switch-output option arguments, changing the option to allow that and adding its default value to 'signal'. Signed-off-by: Jiri Olsa <[email protected]> Acked-by: Wang Nan <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-11perf record: Add struct switch_outputJiri Olsa1-6/+10
Next patches will add more --switch-output option arguments, so preparing the data holder. Signed-off-by: Jiri Olsa <[email protected]> Acked-by: Wang Nan <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-11perf tools: Add unit_number__scnprintf functionJiri Olsa7-2/+63
Add unit_number__scnprintf function to display size units and use it in -m option info message. Before: $ perf record -m 10M ls rounding mmap pages size to 16777216 bytes (4096 pages) ... After: $ perf record -m 10M ls rounding mmap pages size to 16M (4096 pages) ... Signed-off-by: Jiri Olsa <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Wang Nan <[email protected]> Link: http://lkml.kernel.org/r/[email protected] [ Rename it to unit_number__scnprintf for consistency ] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2017-01-11perf evlist: Fix typo in perf_evlist__start_workload()Soramichi Akiyama1-1/+1
This patch fixes a typo: s/enable to/unable to/ Signed-off-by: Soramichi AKIYAMA <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Fixes: bcf3145fbeb1 ("perf evlist: Enhance perf_evlist__start_workload()") Link: http://lkml.kernel.org/r/[email protected] [ Wasn't applying, fixed it up by hand, added Fixes: tag ] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.