Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-12-29 14:21:47 +00:00
Code Issues Packages Projects Releases Wiki Activity
906fed29f4
linux/tools/perf/Makefile.perf
Linus Torvalds 7ab89417ed perf tools changes for v6.7 
Build
 -----
 * Compile BPF programs by default if clang (>= 12.0.1) is available to
   enable more features like kernel lock contention, off-cpu profiling,
   kwork, sample filtering and so on.  It can be disabled by passing
   BUILD_BPF_SKEL=0 to make.
 
 * Produce better error messages for bison on debug build (make DEBUG=1)
   by defining YYDEBUG symbol internally.
 
 perf record
 -----------
 * Track sideband events (like FORK/MMAP) from all CPUs even if perf record
   targets a subset of CPUs only (using -C option).  Otherwise it may lose
   some information happened on a CPU out of the target list.
 
 * Fix checking raw sched_switch tracepoint argument using system BTF.
   This affects off-cpu profiling which attaches a BPF program to the raw
   tracepoint.
 
 perf lock contention
 --------------------
 * Add --lock-cgroup option to see contention by cgroups.  This should be
   used with BPF only (using -b option).
 
     $ sudo perf lock con -ab --lock-cgroup -- sleep 1
      contended   total wait     max wait     avg wait   cgroup
 
            835     14.06 ms     41.19 us     16.83 us   /system.slice/led.service
             25    122.38 us     13.77 us      4.89 us   /
             44     23.73 us      3.87 us       539 ns   /user.slice/user-657345.slice/session-c4.scope
              1       491 ns       491 ns       491 ns   /system.slice/connectd.service
 
 * Add -G/--cgroup-filter option to see contention only for given cgroups.
   This can be useful when you identified a cgroup in the above command and
   want to investigate more on it.  It also works with other output options
   like -t/--threads and -l/--lock-addr.
 
     $ sudo perf lock con -ab -G /user.slice/user-657345.slice/session-c4.scope -- sleep 1
      contended   total wait     max wait     avg wait         type   caller
 
              8     77.11 us     17.98 us      9.64 us     spinlock   futex_wake+0xc8
              2     24.56 us     14.66 us     12.28 us     spinlock   tick_do_update_jiffies64+0x25
              1      4.97 us      4.97 us      4.97 us     spinlock   futex_q_lock+0x2a
 
 * Use per-cpu array for better spinlock tracking.  This is to improve
   performance of the BPF program and to avoid nested contention on a lock
   in the BPF hash map.
 
 * Update callstack check for PowerPC.  To find a representative caller of a
   lock, it needs to look up the call stacks.  It ends the lookup when it sees
   0 in the call stack buffer.  However, PowerPC call stacks can have 0 values
   in the beginning so skip them when it expects valid call stacks after.
 
 perf kwork
 ----------
 * Support 'sched' class (for -k option) so that it can see task scheduling
   event (using sched_switch tracepoint) as well as irq and workqueue items.
 
 * Add perf kwork top subcommand to show more accurate cpu utilization with
   sched class above.  It works both with a recorded data (using perf kwork
   record command) and BPF (using -b option).  Unlike perf top command, it
   does not support interactive mode (yet).
 
     $ sudo perf kwork top -b -k sched
     Starting trace, Hit <Ctrl+C> to stop and report
     ^C
     Total  : 160702.425 ms, 8 cpus
     %Cpu(s):  36.00% id,   0.00% hi,   0.00% si
     %Cpu0   [||||||||||||||||||              61.66%]
     %Cpu1   [||||||||||||||||||              61.27%]
     %Cpu2   [|||||||||||||||||||             66.40%]
     %Cpu3   [||||||||||||||||||              61.28%]
     %Cpu4   [||||||||||||||||||              61.82%]
     %Cpu5   [|||||||||||||||||||||||         77.41%]
     %Cpu6   [||||||||||||||||||              61.73%]
     %Cpu7   [||||||||||||||||||              63.25%]
 
           PID     SPID    %CPU           RUNTIME  COMMMAND
       -------------------------------------------------------------
             0        0   38.72       8089.463 ms  [swapper/1]
             0        0   38.71       8084.547 ms  [swapper/3]
             0        0   38.33       8007.532 ms  [swapper/0]
             0        0   38.26       7992.985 ms  [swapper/6]
             0        0   38.17       7971.865 ms  [swapper/4]
             0        0   36.74       7447.765 ms  [swapper/7]
             0        0   33.59       6486.942 ms  [swapper/2]
             0        0   22.58       3771.268 ms  [swapper/5]
          9545     9351    2.48        447.136 ms  sched-messaging
          9574     9351    2.09        418.583 ms  sched-messaging
          9724     9351    2.05        372.407 ms  sched-messaging
          9531     9351    2.01        368.804 ms  sched-messaging
          9512     9351    2.00        362.250 ms  sched-messaging
          9514     9351    1.95        357.767 ms  sched-messaging
          9538     9351    1.86        384.476 ms  sched-messaging
          9712     9351    1.84        386.490 ms  sched-messaging
          9723     9351    1.83        380.021 ms  sched-messaging
          9722     9351    1.82        382.738 ms  sched-messaging
          9517     9351    1.81        354.794 ms  sched-messaging
          9559     9351    1.79        344.305 ms  sched-messaging
          9725     9351    1.77        365.315 ms  sched-messaging
     <SNIP>
 
 * Add hard/soft-irq statistics to perf kwork top.  This will show the
   total CPU utilization with IRQ stats like below:
 
     $ sudo perf kwork top -b -k sched,irq,softirq
     Starting trace, Hit <Ctrl+C> to stop and report
     ^C
     Total  :  12554.889 ms, 8 cpus
     %Cpu(s):  96.23% id,   0.10% hi,   0.19% si      <---- here
     %Cpu0   [|                                4.60%]
     %Cpu1   [|                                4.59%]
     %Cpu2   [                                 2.73%]
     %Cpu3   [|                                3.81%]
     <SNIP>
 
 perf bench
 ----------
 * Add -G/--cgroups option to perf bench sched pipe.  The pipe bench is
   good to measure context switch overhead.  With this option, it puts
   the reader and writer tasks in separate cgroups to enforce context
   switch between two different cgroups.
 
   Also it needs to set CPU affinity of the tasks in a CPU to accurately
   measure the impact of cgroup context switches.
 
     $ sudo perf stat -e context-switches,cgroup-switches -- \
     > taskset -c 0 perf bench sched pipe -l 100000
     # Running 'sched/pipe' benchmark:
     # Executed 100000 pipe operations between two processes
 
          Total time: 0.307 [sec]
 
            3.078180 usecs/op
              324867 ops/sec
 
      Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 100000':
 
                200,026      context-switches
                     63      cgroup-switches
 
            0.321637922 seconds time elapsed
 
   You can see small number of cgroup-switches because both write and read
   tasks are in the same cgroup.
 
     $ sudo mkdir /sys/fs/cgroup/{AAA,BBB}
 
     $ sudo perf stat -e context-switches,cgroup-switches -- \
     > taskset -c 0 perf bench sched pipe -l 100000 -G AAA,BBB
     # Running 'sched/pipe' benchmark:
     # Executed 100000 pipe operations between two processes
 
          Total time: 0.351 [sec]
 
            3.512990 usecs/op
              284657 ops/sec
 
      Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 100000 -G AAA,BBB':
 
                200,020      context-switches
                200,019      cgroup-switches
 
            0.365034567 seconds time elapsed
 
   Now context-switches and cgroup-switches are almost same.  And you can
   see the pipe operation took little more.
 
 * Kill child processes when perf bench sched messaging exited abnormally.
   Otherwise it'd leave the child doing unnecessary work.
 
 perf test
 ---------
 * Fix various shellcheck issues on the tests written in shell script.
 
 * Skip tests when condition is not satisfied:
   - object code reading test for non-text section addresses.
   - CoreSight test if cs_etm// event is not available.
   - lock contention test if not enough CPUs.
 
 Event parsing
 -------------
 * Make PMU alias name loading lazy to reduce the startup time in the
   event parsing code for perf record, stat and others in the general
   case.
 
 * Lazily compute PMU default config.  In the same sense, delay PMU
   initialization until it's really needed to reduce the startup cost.
 
 * Fix event term values that are raw events.  The event specification
   can have several terms including event name.  But sometimes it clashes
   with raw event encoding which starts with 'r' and has hex-digits.
 
   For example, an event named 'read' should be processed as a normal
   event but it was mis-treated as a raw encoding and caused a failure.
 
     $ perf stat -e 'uncore_imc_free_running/event=read/' -a sleep 1
     event syntax error: '..nning/event=read/'
                                       \___ parser error
     Run 'perf list' for a list of valid events
 
      Usage: perf stat [<options>] [<command>]
 
         -e, --event <event> event selector. use 'perf list' to list available events
 
 Event metrics
 -------------
 * Add "Compat" regex to match event with multiple identifiers.
 
 * Usual updates for Intel, Power10, Arm telemetry/CMN and AmpereOne.
 
 Misc
 ----
 * Assorted memory leak fixes and footprint reduction.
 
 * Add "bpf_skeletons" to perf version --build-options so that users can
   check whether their perf tools have BPF support easily.
 
 * Fix unaligned access in Intel-PT packet decoder found by undefined-behavior
   sanitizer.
 
 * Avoid frequency mode for the dummy event.  Surprisingly it'd impact
   kernel timer tick handler performance by force iterating all PMU events.
 
 * Update bash shell completion for events and metrics.
 
 Signed-off-by: Namhyung Kim <namhyung@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQSo2x5BnqMqsoHtzsmMstVUGiXMgwUCZUMg7wAKCRCMstVUGiXM
 g8FvAQC9KED6H8rlH7UTvxE6fM947EJbldwGrNA1zGx++Ucd3gD/ewA2A6SUcIh6
 Tua/XovmYOQbuDYOwlRHe+sdDag0sgg=
 =GrCE
 -----END PGP SIGNATURE-----

Merge tag 'perf-tools-for-v6.7-1-2023-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Namhyung Kim:
 "Build:

   - Compile BPF programs by default if clang (>= 12.0.1) is available
     to enable more features like kernel lock contention, off-cpu
     profiling, kwork, sample filtering and so on.

     This can be disabled by passing BUILD_BPF_SKEL=0 to make.

   - Produce better error messages for bison on debug build (make
     DEBUG=1) by defining YYDEBUG symbol internally.

  perf record:

   - Track sideband events (like FORK/MMAP) from all CPUs even if perf
     record targets a subset of CPUs only (using -C option). Otherwise
     it may lose some information happened on a CPU out of the target
     list.

   - Fix checking raw sched_switch tracepoint argument using system BTF.
     This affects off-cpu profiling which attaches a BPF program to the
     raw tracepoint.

  perf lock contention:

   - Add --lock-cgroup option to see contention by cgroups. This should
     be used with BPF only (using -b option).

       $ sudo perf lock con -ab --lock-cgroup -- sleep 1
        contended   total wait     max wait     avg wait   cgroup

              835     14.06 ms     41.19 us     16.83 us   /system.slice/led.service
               25    122.38 us     13.77 us      4.89 us   /
               44     23.73 us      3.87 us       539 ns   /user.slice/user-657345.slice/session-c4.scope
                1       491 ns       491 ns       491 ns   /system.slice/connectd.service

   - Add -G/--cgroup-filter option to see contention only for given
     cgroups.

     This can be useful when you identified a cgroup in the above
     command and want to investigate more on it. It also works with
     other output options like -t/--threads and -l/--lock-addr.

       $ sudo perf lock con -ab -G /user.slice/user-657345.slice/session-c4.scope -- sleep 1
        contended   total wait     max wait     avg wait         type   caller

                8     77.11 us     17.98 us      9.64 us     spinlock   futex_wake+0xc8
                2     24.56 us     14.66 us     12.28 us     spinlock   tick_do_update_jiffies64+0x25
                1      4.97 us      4.97 us      4.97 us     spinlock   futex_q_lock+0x2a

   - Use per-cpu array for better spinlock tracking. This is to improve
     performance of the BPF program and to avoid nested contention on a
     lock in the BPF hash map.

   - Update callstack check for PowerPC. To find a representative caller
     of a lock, it needs to look up the call stacks. It ends the lookup
     when it sees 0 in the call stack buffer. However, PowerPC call
     stacks can have 0 values in the beginning so skip them when it
     expects valid call stacks after.

  perf kwork:

   - Support 'sched' class (for -k option) so that it can see task
     scheduling event (using sched_switch tracepoint) as well as irq and
     workqueue items.

   - Add perf kwork top subcommand to show more accurate cpu utilization
     with sched class above. It works both with a recorded data (using
     perf kwork record command) and BPF (using -b option). Unlike perf
     top command, it does not support interactive mode (yet).

       $ sudo perf kwork top -b -k sched
       Starting trace, Hit <Ctrl+C> to stop and report
       ^C
       Total  : 160702.425 ms, 8 cpus
       %Cpu(s):  36.00% id,   0.00% hi,   0.00% si
       %Cpu0   [||||||||||||||||||              61.66%]
       %Cpu1   [||||||||||||||||||              61.27%]
       %Cpu2   [|||||||||||||||||||             66.40%]
       %Cpu3   [||||||||||||||||||              61.28%]
       %Cpu4   [||||||||||||||||||              61.82%]
       %Cpu5   [|||||||||||||||||||||||         77.41%]
       %Cpu6   [||||||||||||||||||              61.73%]
       %Cpu7   [||||||||||||||||||              63.25%]

             PID     SPID    %CPU           RUNTIME  COMMMAND
         -------------------------------------------------------------
               0        0   38.72       8089.463 ms  [swapper/1]
               0        0   38.71       8084.547 ms  [swapper/3]
               0        0   38.33       8007.532 ms  [swapper/0]
               0        0   38.26       7992.985 ms  [swapper/6]
               0        0   38.17       7971.865 ms  [swapper/4]
               0        0   36.74       7447.765 ms  [swapper/7]
               0        0   33.59       6486.942 ms  [swapper/2]
               0        0   22.58       3771.268 ms  [swapper/5]
            9545     9351    2.48        447.136 ms  sched-messaging
            9574     9351    2.09        418.583 ms  sched-messaging
            9724     9351    2.05        372.407 ms  sched-messaging
            9531     9351    2.01        368.804 ms  sched-messaging
            9512     9351    2.00        362.250 ms  sched-messaging
            9514     9351    1.95        357.767 ms  sched-messaging
            9538     9351    1.86        384.476 ms  sched-messaging
            9712     9351    1.84        386.490 ms  sched-messaging
            9723     9351    1.83        380.021 ms  sched-messaging
            9722     9351    1.82        382.738 ms  sched-messaging
            9517     9351    1.81        354.794 ms  sched-messaging
            9559     9351    1.79        344.305 ms  sched-messaging
            9725     9351    1.77        365.315 ms  sched-messaging
       <SNIP>

   - Add hard/soft-irq statistics to perf kwork top. This will show the
     total CPU utilization with IRQ stats like below:

       $ sudo perf kwork top -b -k sched,irq,softirq
       Starting trace, Hit <Ctrl+C> to stop and report
       ^C
       Total  :  12554.889 ms, 8 cpus
       %Cpu(s):  96.23% id,   0.10% hi,   0.19% si      <---- here
       %Cpu0   [|                                4.60%]
       %Cpu1   [|                                4.59%]
       %Cpu2   [                                 2.73%]
       %Cpu3   [|                                3.81%]
       <SNIP>

  perf bench:

   - Add -G/--cgroups option to perf bench sched pipe. The pipe bench is
     good to measure context switch overhead. With this option, it puts
     the reader and writer tasks in separate cgroups to enforce context
     switch between two different cgroups.

     Also it needs to set CPU affinity of the tasks in a CPU to
     accurately measure the impact of cgroup context switches.

       $ sudo perf stat -e context-switches,cgroup-switches -- \
       > taskset -c 0 perf bench sched pipe -l 100000
       # Running 'sched/pipe' benchmark:
       # Executed 100000 pipe operations between two processes

            Total time: 0.307 [sec]

              3.078180 usecs/op
                324867 ops/sec

        Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 100000':

                  200,026      context-switches
                       63      cgroup-switches

              0.321637922 seconds time elapsed

     You can see small number of cgroup-switches because both write and
     read tasks are in the same cgroup.

       $ sudo mkdir /sys/fs/cgroup/{AAA,BBB}

       $ sudo perf stat -e context-switches,cgroup-switches -- \
       > taskset -c 0 perf bench sched pipe -l 100000 -G AAA,BBB
       # Running 'sched/pipe' benchmark:
       # Executed 100000 pipe operations between two processes

            Total time: 0.351 [sec]

              3.512990 usecs/op
                284657 ops/sec

        Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 100000 -G AAA,BBB':

                  200,020      context-switches
                  200,019      cgroup-switches

              0.365034567 seconds time elapsed

     Now context-switches and cgroup-switches are almost same. And you
     can see the pipe operation took little more.

   - Kill child processes when perf bench sched messaging exited
     abnormally. Otherwise it'd leave the child doing unnecessary work.

  perf test:

   - Fix various shellcheck issues on the tests written in shell script.

   - Skip tests when condition is not satisfied:
      - object code reading test for non-text section addresses.
      - CoreSight test if cs_etm// event is not available.
      - lock contention test if not enough CPUs.

  Event parsing:

   - Make PMU alias name loading lazy to reduce the startup time in the
     event parsing code for perf record, stat and others in the general
     case.

   - Lazily compute PMU default config. In the same sense, delay PMU
     initialization until it's really needed to reduce the startup cost.

   - Fix event term values that are raw events. The event specification
     can have several terms including event name. But sometimes it
     clashes with raw event encoding which starts with 'r' and has
     hex-digits.

     For example, an event named 'read' should be processed as a normal
     event but it was mis-treated as a raw encoding and caused a
     failure.

       $ perf stat -e 'uncore_imc_free_running/event=read/' -a sleep 1
       event syntax error: '..nning/event=read/'
                                         \___ parser error
       Run 'perf list' for a list of valid events

        Usage: perf stat [<options>] [<command>]

           -e, --event <event> event selector. use 'perf list' to list available events

  Event metrics:

   - Add "Compat" regex to match event with multiple identifiers.

   - Usual updates for Intel, Power10, Arm telemetry/CMN and AmpereOne.

  Misc:

   - Assorted memory leak fixes and footprint reduction.

   - Add "bpf_skeletons" to perf version --build-options so that users
     can check whether their perf tools have BPF support easily.

   - Fix unaligned access in Intel-PT packet decoder found by
     undefined-behavior sanitizer.

   - Avoid frequency mode for the dummy event. Surprisingly it'd impact
     kernel timer tick handler performance by force iterating all PMU
     events.

   - Update bash shell completion for events and metrics"

* tag 'perf-tools-for-v6.7-1-2023-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (187 commits)
  perf vendor events intel: Update tsx_cycles_per_elision metrics
  perf vendor events intel: Update bonnell version number to v5
  perf vendor events intel: Update westmereex events to v4
  perf vendor events intel: Update meteorlake events to v1.06
  perf vendor events intel: Update knightslanding events to v16
  perf vendor events intel: Add typo fix for ivybridge FP
  perf vendor events intel: Update a spelling in haswell/haswellx
  perf vendor events intel: Update emeraldrapids to v1.01
  perf vendor events intel: Update alderlake/alderlake events to v1.23
  perf build: Disable BPF skeletons if clang version is < 12.0.1
  perf callchain: Fix spelling mistake "statisitcs" -> "statistics"
  perf report: Fix spelling mistake "heirachy" -> "hierarchy"
  perf python: Fix binding linkage due to rename and move of evsel__increase_rlimit()
  perf tests: test_arm_coresight: Simplify source iteration
  perf vendor events intel: Add tigerlake two metrics
  perf vendor events intel: Add broadwellde two metrics
  perf vendor events intel: Fix broadwellde tma_info_system_dram_bw_use metric
  perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit
  perf callchain: Minor layout changes to callchain_list
  perf callchain: Make brtype_stat in callchain_list optional
  ...
2023-11-03 08:17:38 -10:00

1211 lines
42 KiB
Makefile
Raw Blame History

# SPDX-License-Identifier: GPL-2.0-only
include ../scripts/Makefile.include
include ../scripts/Makefile.arch
# The default target of this Makefile is...
all:
include ../scripts/utilities.mak
# Define V to have a more verbose compile.
#
# Define VF to have a more verbose feature check output.
#
# Define O to save output files in a separate directory.
#
# Define ARCH as name of target architecture if you want cross-builds.
#
# Define CROSS_COMPILE as prefix name of compiler if you want cross-builds.
#
# Define NO_LIBPERL to disable perl script extension.
#
# Define NO_LIBPYTHON to disable python script extension.
#
# Define PYTHON to point to the python binary if the default
# `python' is not correct; for example: PYTHON=python2
#
# Define PYTHON_CONFIG to point to the python-config binary if
# the default `$(PYTHON)-config' is not correct.
#
# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
#
# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
#
# Define LDFLAGS=-static to build a static binary.
#
# Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
#
# Define EXCLUDE_EXTLIBS=-lmylib to exclude libmylib from the auto-generated
# EXTLIBS.
#
# Define EXTRA_PERFLIBS to pass extra libraries to PERFLIBS.
#
# Define NO_DWARF if you do not want debug-info analysis feature at all.
#
# Define WERROR=0 to disable treating any warnings as errors.
#
# Define NO_SLANG if you do not want TUI support.
#
# Define GTK2 if you want GTK+ GUI support.
#
# Define NO_DEMANGLE if you do not want C++ symbol demangling.
#
# Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds)
#
# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf
# backtrace post unwind.
#
# Define NO_BACKTRACE if you do not want stack backtrace debug feature
#
# Define NO_LIBNUMA if you do not want numa perf benchmark
#
# Define NO_LIBAUDIT if you do not want libaudit support
#
# Define NO_LIBBIONIC if you do not want bionic support
#
# Define NO_LIBCRYPTO if you do not want libcrypto (openssl) support
# used for generating build-ids for ELFs generated by jitdump.
#
# Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
# for dwarf backtrace post unwind.
#
# Define NO_LIBTRACEEVENT=1 if you don't want libtraceevent to be linked,
# this will remove multiple features and tools, such as 'perf trace',
# that need it to read tracefs event format files, etc.
#
# Define NO_PERF_READ_VDSO32 if you do not want to build perf-read-vdso32
# for reading the 32-bit compatibility VDSO in 64-bit mode
#
# Define NO_PERF_READ_VDSOX32 if you do not want to build perf-read-vdsox32
# for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode
#
# Define NO_ZLIB if you do not want to support compressed kernel modules
#
# Define NO_LIBBABELTRACE if you do not want libbabeltrace support
# for CTF data format.
#
# Define NO_LZMA if you do not want to support compressed (xz) kernel modules
#
# Define NO_AUXTRACE if you do not want AUX area tracing support
#
# Define NO_LIBBPF if you do not want BPF support
#
# Define NO_LIBCAP if you do not want process capabilities considered by perf
#
# Define NO_SDT if you do not want to define SDT event in perf tools,
# note that it doesn't disable SDT scanning support.
#
# Define FEATURES_DUMP to provide features detection dump file
# and bypass the feature detection
#
# Define NO_JVMTI if you do not want jvmti agent built
#
# Define NO_JVMTI_CMLR (debug only) if you do not want to process CMLR
# data for java source lines.
#
# Define CORESIGHT if you DO WANT support for CoreSight trace decoding.
#
# Define NO_AIO if you do not want support of Posix AIO based trace
# streaming for record mode. Currently Posix AIO trace streaming is
# supported only when linking with glibc.
#
# Define NO_LIBZSTD if you do not want support of Zstandard based runtime
# trace compression in record mode.
#
# Define TCMALLOC to enable tcmalloc heap profiling.
#
# Define LIBBPF_DYNAMIC to enable libbpf dynamic linking.
#
# Define NO_SYSCALL_TABLE=1 to disable the use of syscall id to/from name tables
# generated from the kernel .tbl or unistd.h files and use, if available, libaudit
# for doing the conversions to/from strings/id.
#
# Define NO_LIBPFM4 to disable libpfm4 events extension.
#
# Define NO_LIBDEBUGINFOD if you do not want support debuginfod
#
# Set BUILD_BPF_SKEL to 0 to override BUILD_BPF_SKEL and not build BPF skeletons
#
# Define BUILD_NONDISTRO to enable building an linking against libbfd and
# libiberty distribution license incompatible libraries.
#
# Define EXTRA_TESTS to enable building extra tests useful mainly to perf
# developers, such as:
# x86 instruction decoder - new instructions test
#
# Define GEN_VMLINUX_H to generate vmlinux.h from the BTF.
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
LC_COLLATE=C
LC_NUMERIC=C
export LC_COLLATE LC_NUMERIC
ifeq ($(srctree),)
srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
#$(info Determined 'srctree' to be $(srctree))
endif
ifneq ($(objtree),)
#$(info Determined 'objtree' to be $(objtree))
endif
ifneq ($(OUTPUT),)
#$(info Determined 'OUTPUT' to be $(OUTPUT))
# Adding $(OUTPUT) as a directory to look for source files,
# because use generated output files as sources dependency
# for flex/bison parsers.
VPATH += $(OUTPUT)
export VPATH
endif
ifeq ($(V),1)
Q =
else
Q = @
endif
# Do not use make's built-in rules
# (this improves performance and avoids hard-to-debug behaviour);
MAKEFLAGS += -r
# Makefiles suck: This macro sets a default value of $(2) for the
# variable named by $(1), unless the variable has been set by
# environment or command line. This is necessary for CC and AR
# because make sets default values, so the simpler ?= approach
# won't work as expected.
define allow-override
$(if $(or $(findstring environment,$(origin $(1))),\
$(findstring command line,$(origin $(1)))),,\
$(eval $(1) = $(2)))
endef
LD += $(EXTRA_LDFLAGS)
HOSTCC ?= gcc
HOSTLD ?= ld
HOSTAR ?= ar
CLANG ?= clang
PKG_CONFIG = $(CROSS_COMPILE)pkg-config
RM = rm -f
LN = ln -f
MKDIR = mkdir
FIND = find
INSTALL = install
FLEX ?= flex
BISON ?= bison
STRIP = strip
AWK = awk
READELF ?= readelf
# include Makefile.config by default and rule out
# non-config cases
config := 1
NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help
ifdef MAKECMDGOALS
ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
config := 0
endif
endif
# The fixdep build - we force fixdep tool to be built as
# the first target in the separate make session not to be
# disturbed by any parallel make jobs. Once fixdep is done
# we issue the requested build with FIXDEP=1 variable.
#
# The fixdep build is disabled for $(NON_CONFIG_TARGETS)
# targets, because it's not necessary.
ifdef FIXDEP
force_fixdep := 0
else
force_fixdep := $(config)
endif
export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
export HOSTCC HOSTLD HOSTAR HOSTCFLAGS
include $(srctree)/tools/build/Makefile.include
ifeq ($(force_fixdep),1)
goals := $(filter-out all sub-make, $(MAKECMDGOALS))
$(goals) all: sub-make
sub-make: fixdep
@./check-headers.sh
$(Q)$(MAKE) FIXDEP=1 -f Makefile.perf $(goals)
else # force_fixdep
LIBAPI_DIR = $(srctree)/tools/lib/api/
LIBBPF_DIR = $(srctree)/tools/lib/bpf/
LIBSUBCMD_DIR = $(srctree)/tools/lib/subcmd/
LIBSYMBOL_DIR = $(srctree)/tools/lib/symbol/
LIBPERF_DIR = $(srctree)/tools/lib/perf/
DOC_DIR = $(srctree)/tools/perf/Documentation/
# Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
# Without this setting the output feature dump file misses some features, for
# example, liberty. Select all checkers so we won't get an incomplete feature
# dump file.
ifeq ($(config),1)
ifdef MAKECMDGOALS
ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump)
FEATURE_TESTS := all
endif
endif
include Makefile.config
endif
ifeq ($(config),0)
include $(srctree)/tools/scripts/Makefile.arch
-include arch/$(SRCARCH)/Makefile
endif
# The FEATURE_DUMP_EXPORT holds location of the actual
# FEATURE_DUMP file to be used to bypass feature detection
# (for bpf or any other subproject)
ifeq ($(FEATURES_DUMP),)
FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP)
else
FEATURE_DUMP_EXPORT := $(realpath $(FEATURES_DUMP))
endif
export prefix bindir sharedir sysconfdir DESTDIR
# sparse is architecture-neutral, which means that we need to tell it
# explicitly what architecture to check for. Fix this up for yours..
SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
# Guard against environment variables
PYRF_OBJS =
SCRIPT_SH =
SCRIPT_SH += perf-archive.sh
SCRIPT_SH += perf-iostat.sh
grep-libs = $(filter -l%,$(1))
strip-libs = $(filter-out -l%,$(1))
ifneq ($(OUTPUT),)
LIBAPI_OUTPUT = $(abspath $(OUTPUT))/libapi
else
LIBAPI_OUTPUT = $(CURDIR)/libapi
endif
LIBAPI_DESTDIR = $(LIBAPI_OUTPUT)
LIBAPI_INCLUDE = $(LIBAPI_DESTDIR)/include
LIBAPI = $(LIBAPI_OUTPUT)/libapi.a
export LIBAPI
CFLAGS += -I$(LIBAPI_OUTPUT)/include
ifneq ($(OUTPUT),)
LIBBPF_OUTPUT = $(abspath $(OUTPUT))/libbpf
else
LIBBPF_OUTPUT = $(CURDIR)/libbpf
endif
ifdef LIBBPF_STATIC
LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
CFLAGS += -I$(LIBBPF_OUTPUT)/include
endif
ifneq ($(OUTPUT),)
LIBSUBCMD_OUTPUT = $(abspath $(OUTPUT))/libsubcmd
else
LIBSUBCMD_OUTPUT = $(CURDIR)/libsubcmd
endif
LIBSUBCMD_DESTDIR = $(LIBSUBCMD_OUTPUT)
LIBSUBCMD_INCLUDE = $(LIBSUBCMD_DESTDIR)/include
LIBSUBCMD = $(LIBSUBCMD_OUTPUT)/libsubcmd.a
CFLAGS += -I$(LIBSUBCMD_OUTPUT)/include
ifneq ($(OUTPUT),)
LIBSYMBOL_OUTPUT = $(abspath $(OUTPUT))/libsymbol
else
LIBSYMBOL_OUTPUT = $(CURDIR)/libsymbol
endif
LIBSYMBOL_DESTDIR = $(LIBSYMBOL_OUTPUT)
LIBSYMBOL_INCLUDE = $(LIBSYMBOL_DESTDIR)/include
LIBSYMBOL = $(LIBSYMBOL_OUTPUT)/libsymbol.a
CFLAGS += -I$(LIBSYMBOL_OUTPUT)/include
ifneq ($(OUTPUT),)
LIBPERF_OUTPUT = $(abspath $(OUTPUT))/libperf
else
LIBPERF_OUTPUT = $(CURDIR)/libperf
endif
LIBPERF_DESTDIR = $(LIBPERF_OUTPUT)
LIBPERF_INCLUDE = $(LIBPERF_DESTDIR)/include
LIBPERF = $(LIBPERF_OUTPUT)/libperf.a
export LIBPERF
CFLAGS += -I$(LIBPERF_OUTPUT)/include
# python extension build directories
PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/
PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf*.so
# Use the detected configuration
-include $(OUTPUT).config-detected
ifeq ($(CONFIG_LIBTRACEEVENT),y)
PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
else
PYTHON_EXT_SRCS := $(shell grep -v ^\#\\\|util/trace-event.c util/python-ext-sources)
endif
PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBAPI)
SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
PROGRAMS += $(OUTPUT)perf
ifndef NO_PERF_READ_VDSO32
PROGRAMS += $(OUTPUT)perf-read-vdso32
endif
ifndef NO_PERF_READ_VDSOX32
PROGRAMS += $(OUTPUT)perf-read-vdsox32
endif
LIBJVMTI = libperf-jvmti.so
ifndef NO_JVMTI
PROGRAMS += $(OUTPUT)$(LIBJVMTI)
endif
DLFILTERS := dlfilter-test-api-v0.so dlfilter-test-api-v2.so dlfilter-show-cycles.so
DLFILTERS := $(patsubst %,$(OUTPUT)dlfilters/%,$(DLFILTERS))
# what 'all' will build and 'install' will install, in perfexecdir
ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) $(DLFILTERS)
# what 'all' will build but not install in perfexecdir
OTHER_PROGRAMS = $(OUTPUT)perf
# Set paths to tools early so that they can be used for version tests.
ifndef SHELL_PATH
SHELL_PATH = /bin/sh
endif
ifndef PERL_PATH
PERL_PATH = /usr/bin/perl
endif
export PERL_PATH
PERFLIBS = $(LIBAPI) $(LIBPERF) $(LIBSUBCMD) $(LIBSYMBOL)
ifdef LIBBPF_STATIC
PERFLIBS += $(LIBBPF)
endif
# We choose to avoid "if .. else if .. else .. endif endif"
# because maintaining the nesting to match is a pain. If
# we had "elif" things would have been much nicer...
ifneq ($(OUTPUT),)
CFLAGS += -I$(OUTPUT)
endif
ifdef GTK2
ALL_PROGRAMS += $(OUTPUT)libperf-gtk.so
GTK_IN := $(OUTPUT)gtk-in.o
endif
ifdef ASCIIDOC8
export ASCIIDOC8
endif
EXTLIBS := $(call filter-out,$(EXCLUDE_EXTLIBS),$(EXTLIBS))
LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
export INSTALL SHELL_PATH
### Build rules
SHELL = $(SHELL_PATH)
beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/
linux_uapi_dir := $(srctree)/tools/include/uapi/linux
asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
x86_arch_asm_uapi_dir := $(srctree)/tools/arch/x86/include/uapi/asm/
x86_arch_asm_dir := $(srctree)/tools/arch/x86/include/asm/
beauty_outdir := $(OUTPUT)trace/beauty/generated
beauty_ioctl_outdir := $(beauty_outdir)/ioctl
drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
drm_hdr_dir := $(srctree)/tools/include/uapi/drm
drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
# Create output directory if not already present
_dummy := $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_outdir)')
arm64_gen_sysreg_dir := $(srctree)/tools/arch/arm64/tools
arm64-sysreg-defs: FORCE
$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir)
arm64-sysreg-defs-clean:
$(call QUIET_CLEAN,arm64-sysreg-defs)
$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) clean > /dev/null
$(drm_ioctl_array): $(drm_hdr_dir)/drm.h $(drm_hdr_dir)/i915_drm.h $(drm_ioctl_tbl)
$(Q)$(SHELL) '$(drm_ioctl_tbl)' $(drm_hdr_dir) > $@
fadvise_advice_array := $(beauty_outdir)/fadvise_advice_array.c
fadvise_advice_tbl := $(srctree)/tools/perf/trace/beauty/fadvise.sh
$(fadvise_advice_array): $(linux_uapi_dir)/in.h $(fadvise_advice_tbl)
$(Q)$(SHELL) '$(fadvise_advice_tbl)' $(linux_uapi_dir) > $@
fsmount_arrays := $(beauty_outdir)/fsmount_arrays.c
fsmount_tbls := $(srctree)/tools/perf/trace/beauty/fsmount.sh
$(fsmount_arrays): $(linux_uapi_dir)/fs.h $(fsmount_tbls)
$(Q)$(SHELL) '$(fsmount_tbls)' $(linux_uapi_dir) > $@
fspick_arrays := $(beauty_outdir)/fspick_arrays.c
fspick_tbls := $(srctree)/tools/perf/trace/beauty/fspick.sh
$(fspick_arrays): $(linux_uapi_dir)/fs.h $(fspick_tbls)
$(Q)$(SHELL) '$(fspick_tbls)' $(linux_uapi_dir) > $@
fsconfig_arrays := $(beauty_outdir)/fsconfig_arrays.c
fsconfig_tbls := $(srctree)/tools/perf/trace/beauty/fsconfig.sh
$(fsconfig_arrays): $(linux_uapi_dir)/fs.h $(fsconfig_tbls)
$(Q)$(SHELL) '$(fsconfig_tbls)' $(linux_uapi_dir) > $@
pkey_alloc_access_rights_array := $(beauty_outdir)/pkey_alloc_access_rights_array.c
asm_generic_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
pkey_alloc_access_rights_tbl := $(srctree)/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
$(pkey_alloc_access_rights_array): $(asm_generic_hdr_dir)/mman-common.h $(pkey_alloc_access_rights_tbl)
$(Q)$(SHELL) '$(pkey_alloc_access_rights_tbl)' $(asm_generic_hdr_dir) > $@
sndrv_ctl_ioctl_array := $(beauty_ioctl_outdir)/sndrv_ctl_ioctl_array.c
sndrv_ctl_hdr_dir := $(srctree)/tools/include/uapi/sound
sndrv_ctl_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
$(sndrv_ctl_ioctl_array): $(sndrv_ctl_hdr_dir)/asound.h $(sndrv_ctl_ioctl_tbl)
$(Q)$(SHELL) '$(sndrv_ctl_ioctl_tbl)' $(sndrv_ctl_hdr_dir) > $@
sndrv_pcm_ioctl_array := $(beauty_ioctl_outdir)/sndrv_pcm_ioctl_array.c
sndrv_pcm_hdr_dir := $(srctree)/tools/include/uapi/sound
sndrv_pcm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
$(sndrv_pcm_ioctl_array): $(sndrv_pcm_hdr_dir)/asound.h $(sndrv_pcm_ioctl_tbl)
$(Q)$(SHELL) '$(sndrv_pcm_ioctl_tbl)' $(sndrv_pcm_hdr_dir) > $@
kcmp_type_array := $(beauty_outdir)/kcmp_type_array.c
kcmp_hdr_dir := $(srctree)/tools/include/uapi/linux/
kcmp_type_tbl := $(srctree)/tools/perf/trace/beauty/kcmp_type.sh
$(kcmp_type_array): $(kcmp_hdr_dir)/kcmp.h $(kcmp_type_tbl)
$(Q)$(SHELL) '$(kcmp_type_tbl)' $(kcmp_hdr_dir) > $@
kvm_ioctl_array := $(beauty_ioctl_outdir)/kvm_ioctl_array.c
kvm_hdr_dir := $(srctree)/tools/include/uapi/linux
kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
$(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
$(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
socket_arrays := $(beauty_outdir)/socket.c
socket_tbl := $(srctree)/tools/perf/trace/beauty/socket.sh
$(socket_arrays): $(linux_uapi_dir)/in.h $(beauty_linux_dir)/socket.h $(socket_tbl)
$(Q)$(SHELL) '$(socket_tbl)' $(linux_uapi_dir) $(beauty_linux_dir) > $@
sockaddr_arrays := $(beauty_outdir)/sockaddr.c
sockaddr_tbl := $(srctree)/tools/perf/trace/beauty/sockaddr.sh
$(sockaddr_arrays): $(beauty_linux_dir)/socket.h $(sockaddr_tbl)
$(Q)$(SHELL) '$(sockaddr_tbl)' $(beauty_linux_dir) > $@
vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
$(vhost_virtio_ioctl_array): $(vhost_virtio_hdr_dir)/vhost.h $(vhost_virtio_ioctl_tbl)
$(Q)$(SHELL) '$(vhost_virtio_ioctl_tbl)' $(vhost_virtio_hdr_dir) > $@
perf_ioctl_array := $(beauty_ioctl_outdir)/perf_ioctl_array.c
perf_hdr_dir := $(srctree)/tools/include/uapi/linux
perf_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/perf_ioctl.sh
$(perf_ioctl_array): $(perf_hdr_dir)/perf_event.h $(perf_ioctl_tbl)
$(Q)$(SHELL) '$(perf_ioctl_tbl)' $(perf_hdr_dir) > $@
madvise_behavior_array := $(beauty_outdir)/madvise_behavior_array.c
madvise_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
$(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
$(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
$(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
mremap_flags_array := $(beauty_outdir)/mremap_flags_array.c
mremap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mremap_flags.sh
$(mremap_flags_array): $(linux_uapi_dir)/mman.h $(mremap_flags_tbl)
$(Q)$(SHELL) '$(mremap_flags_tbl)' $(linux_uapi_dir) > $@
mount_flags_array := $(beauty_outdir)/mount_flags_array.c
mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl)
$(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
move_mount_flags_array := $(beauty_outdir)/move_mount_flags_array.c
move_mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/move_mount_flags.sh
$(move_mount_flags_array): $(linux_uapi_dir)/fs.h $(move_mount_flags_tbl)
$(Q)$(SHELL) '$(move_mount_flags_tbl)' $(linux_uapi_dir) > $@
mmap_prot_array := $(beauty_outdir)/mmap_prot_array.c
mmap_prot_tbl := $(srctree)/tools/perf/trace/beauty/mmap_prot.sh
$(mmap_prot_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_prot_tbl)
$(Q)$(SHELL) '$(mmap_prot_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
prctl_option_array := $(beauty_outdir)/prctl_option_array.c
prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
$(prctl_option_array): $(prctl_hdr_dir)/prctl.h $(prctl_option_tbl)
$(Q)$(SHELL) '$(prctl_option_tbl)' $(prctl_hdr_dir) > $@
usbdevfs_ioctl_array := $(beauty_ioctl_outdir)/usbdevfs_ioctl_array.c
usbdevfs_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/usbdevfs_ioctl.sh
$(usbdevfs_ioctl_array): $(linux_uapi_dir)/usbdevice_fs.h $(usbdevfs_ioctl_tbl)
$(Q)$(SHELL) '$(usbdevfs_ioctl_tbl)' $(linux_uapi_dir) > $@
x86_arch_prctl_code_array := $(beauty_outdir)/x86_arch_prctl_code_array.c
x86_arch_prctl_code_tbl := $(srctree)/tools/perf/trace/beauty/x86_arch_prctl.sh
$(x86_arch_prctl_code_array): $(x86_arch_asm_uapi_dir)/prctl.h $(x86_arch_prctl_code_tbl)
$(Q)$(SHELL) '$(x86_arch_prctl_code_tbl)' $(x86_arch_asm_uapi_dir) > $@
x86_arch_irq_vectors_array := $(beauty_outdir)/x86_arch_irq_vectors_array.c
x86_arch_irq_vectors_tbl := $(srctree)/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh
$(x86_arch_irq_vectors_array): $(x86_arch_asm_dir)/irq_vectors.h $(x86_arch_irq_vectors_tbl)
$(Q)$(SHELL) '$(x86_arch_irq_vectors_tbl)' $(x86_arch_asm_dir) > $@
x86_arch_MSRs_array := $(beauty_outdir)/x86_arch_MSRs_array.c
x86_arch_MSRs_tbl := $(srctree)/tools/perf/trace/beauty/tracepoints/x86_msr.sh
$(x86_arch_MSRs_array): $(x86_arch_asm_dir)/msr-index.h $(x86_arch_MSRs_tbl)
$(Q)$(SHELL) '$(x86_arch_MSRs_tbl)' $(x86_arch_asm_dir) > $@
rename_flags_array := $(beauty_outdir)/rename_flags_array.c
rename_flags_tbl := $(srctree)/tools/perf/trace/beauty/rename_flags.sh
$(rename_flags_array): $(linux_uapi_dir)/fs.h $(rename_flags_tbl)
$(Q)$(SHELL) '$(rename_flags_tbl)' $(linux_uapi_dir) > $@
arch_errno_name_array := $(beauty_outdir)/arch_errno_name_array.c
arch_errno_hdr_dir := $(srctree)/tools
arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh
$(arch_errno_name_array): $(arch_errno_tbl)
$(Q)$(SHELL) '$(arch_errno_tbl)' '$(patsubst -%,,$(CC))' $(arch_errno_hdr_dir) > $@
sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh
$(sync_file_range_arrays): $(linux_uapi_dir)/fs.h $(sync_file_range_tbls)
$(Q)$(SHELL) '$(sync_file_range_tbls)' $(linux_uapi_dir) > $@
TESTS_CORESIGHT_DIR := $(srctree)/tools/perf/tests/shell/coresight
tests-coresight-targets: FORCE
$(Q)$(MAKE) -C $(TESTS_CORESIGHT_DIR)
tests-coresight-targets-clean:
$(call QUIET_CLEAN, coresight)
$(Q)$(MAKE) -C $(TESTS_CORESIGHT_DIR) O=$(OUTPUT) clean >/dev/null
all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) tests-coresight-targets
# Create python binding output directory if not already present
_dummy := $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python')
$(OUTPUT)python/perf$(PYTHON_EXTENSION_SUFFIX): $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBPERF) $(LIBSUBCMD)
$(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS)' \
$(PYTHON_WORD) util/setup.py \
--quiet build_ext; \
cp $(PYTHON_EXTBUILD_LIB)perf*.so $(OUTPUT)python/
python_perf_target:
@echo "Target is: $(OUTPUT)python/perf$(PYTHON_EXTENSION_SUFFIX)"
please_set_SHELL_PATH_to_a_more_modern_shell:
$(Q)$$(:)
shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
strip: $(PROGRAMS) $(OUTPUT)perf
$(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf
PERF_IN := $(OUTPUT)perf-in.o
PMU_EVENTS_IN := $(OUTPUT)pmu-events/pmu-events-in.o
export NO_JEVENTS
build := -f $(srctree)/tools/build/Makefile.build dir=. obj
$(PERF_IN): prepare FORCE
$(Q)$(MAKE) $(build)=perf
$(PMU_EVENTS_IN): FORCE prepare
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=pmu-events obj=pmu-events
$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN)
$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \
$(PERF_IN) $(PMU_EVENTS_IN) $(LIBS) -o $@
$(GTK_IN): FORCE prepare
$(Q)$(MAKE) $(build)=gtk
$(OUTPUT)libperf-gtk.so: $(GTK_IN) $(PERFLIBS)
$(QUIET_LINK)$(CC) -o $@ -shared $(LDFLAGS) $(filter %.o,$^) $(GTK_LIBS)
$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
$(SCRIPTS) : % : %.sh
$(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
$(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
# These can record PERF_VERSION
perf.spec $(SCRIPTS) \
: $(OUTPUT)PERF-VERSION-FILE
.SUFFIXES:
#
# If a target does not match any of the later rules then prefix it by $(OUTPUT)
# This makes targets like 'make O=/tmp/perf perf.o' work in a natural way.
#
ifneq ($(OUTPUT),)
%.o: $(OUTPUT)%.o
@echo " # Redirected target $@ => $(OUTPUT)$@"
pmu-events/%.o: $(OUTPUT)pmu-events/%.o
@echo " # Redirected target $@ => $(OUTPUT)$@"
util/%.o: $(OUTPUT)util/%.o
@echo " # Redirected target $@ => $(OUTPUT)$@"
bench/%.o: $(OUTPUT)bench/%.o
@echo " # Redirected target $@ => $(OUTPUT)$@"
tests/%.o: $(OUTPUT)tests/%.o
@echo " # Redirected target $@ => $(OUTPUT)$@"
endif
# These two need to be here so that when O= is not used they take precedence
# over the general rule for .o
# get relative building directory (to $(OUTPUT))
# and '.' if it's $(OUTPUT) itself
__build-dir = $(subst $(OUTPUT),,$(dir $@))
build-dir = $(or $(__build-dir),.)
prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders \
arm64-sysreg-defs \
$(drm_ioctl_array) \
$(fadvise_advice_array) \
$(fsconfig_arrays) \
$(fsmount_arrays) \
$(fspick_arrays) \
$(pkey_alloc_access_rights_array) \
$(sndrv_pcm_ioctl_array) \
$(sndrv_ctl_ioctl_array) \
$(kcmp_type_array) \
$(kvm_ioctl_array) \
$(socket_arrays) \
$(sockaddr_arrays) \
$(vhost_virtio_ioctl_array) \
$(madvise_behavior_array) \
$(mmap_flags_array) \
$(mmap_prot_array) \
$(mremap_flags_array) \
$(mount_flags_array) \
$(move_mount_flags_array) \
$(perf_ioctl_array) \
$(prctl_option_array) \
$(usbdevfs_ioctl_array) \
$(x86_arch_irq_vectors_array) \
$(x86_arch_MSRs_array) \
$(x86_arch_prctl_code_array) \
$(rename_flags_array) \
$(arch_errno_name_array) \
$(sync_file_range_arrays) \
$(LIBAPI) \
$(LIBPERF) \
$(LIBSUBCMD) \
$(LIBSYMBOL) \
bpf-skel
ifdef LIBBPF_STATIC
prepare: $(LIBBPF)
endif
$(OUTPUT)%.o: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(OUTPUT)%.i: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(OUTPUT)%.s: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(OUTPUT)%-bison.o: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(OUTPUT)%-flex.o: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(OUTPUT)%.o: %.S prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(OUTPUT)%.i: %.S prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(OUTPUT)perf-%: %.o $(PERFLIBS)
$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
ifndef NO_PERF_READ_VDSO32
$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-map.c
$(QUIET_CC)$(CC) -m32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
endif
ifndef NO_PERF_READ_VDSOX32
$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-map.c
$(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
endif
$(OUTPUT)dlfilters/%.o: dlfilters/%.c include/perf/perf_dlfilter.h
$(Q)$(MKDIR) -p $(OUTPUT)dlfilters
$(QUIET_CC)$(CC) -c -Iinclude $(EXTRA_CFLAGS) -o $@ -fpic $<
.SECONDARY: $(DLFILTERS:.so=.o)
$(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o
$(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) -shared -o $@ $<
ifndef NO_JVMTI
LIBJVMTI_IN := $(OUTPUT)jvmti/jvmti-in.o
$(LIBJVMTI_IN): FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=jvmti obj=jvmti
$(OUTPUT)$(LIBJVMTI): $(LIBJVMTI_IN)
$(QUIET_LINK)$(CC) $(LDFLAGS) -shared -Wl,-soname -Wl,$(LIBJVMTI) -o $@ $<
endif
$(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h)
$(LIBAPI): FORCE | $(LIBAPI_OUTPUT)
$(Q)$(MAKE) -C $(LIBAPI_DIR) O=$(LIBAPI_OUTPUT) \
DESTDIR=$(LIBAPI_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBAPI)-clean:
$(call QUIET_CLEAN, libapi)
$(Q)$(RM) -r -- $(LIBAPI_OUTPUT)
$(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
$(Q)$(MAKE) -C $(LIBBPF_DIR) FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) \
O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBBPF)-clean:
$(call QUIET_CLEAN, libbpf)
$(Q)$(RM) -r -- $(LIBBPF_OUTPUT)
$(LIBPERF): FORCE | $(LIBPERF_OUTPUT)
$(Q)$(MAKE) -C $(LIBPERF_DIR) O=$(LIBPERF_OUTPUT) \
DESTDIR=$(LIBPERF_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBPERF)-clean:
$(call QUIET_CLEAN, libperf)
$(Q)$(RM) -r -- $(LIBPERF_OUTPUT)
$(LIBSUBCMD): FORCE | $(LIBSUBCMD_OUTPUT)
$(Q)$(MAKE) -C $(LIBSUBCMD_DIR) O=$(LIBSUBCMD_OUTPUT) \
DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBSUBCMD)-clean:
$(call QUIET_CLEAN, libsubcmd)
$(Q)$(RM) -r -- $(LIBSUBCMD_OUTPUT)
$(LIBSYMBOL): FORCE | $(LIBSYMBOL_OUTPUT)
$(Q)$(MAKE) -C $(LIBSYMBOL_DIR) O=$(LIBSYMBOL_OUTPUT) \
DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBSYMBOL)-clean:
$(call QUIET_CLEAN, libsymbol)
$(Q)$(RM) -r -- $(LIBSYMBOL_OUTPUT)
help:
@echo 'Perf make targets:'
@echo ' doc - make *all* documentation (see below)'
@echo ' man - make manpage documentation (access with man <foo>)'
@echo ' html - make html documentation'
@echo ' info - make GNU info documentation (access with info <foo>)'
@echo ' pdf - make pdf documentation'
@echo ' TAGS - use etags to make tag information for source browsing'
@echo ' tags - use ctags to make tag information for source browsing'
@echo ' cscope - use cscope to make interactive browsing database'
@echo ''
@echo 'Perf install targets:'
@echo ' NOTE: documentation build requires asciidoc, xmlto packages to be installed'
@echo ' HINT: use "prefix" or "DESTDIR" to install to a particular'
@echo ' path like "make prefix=/usr/local install install-doc"'
@echo ' install - install compiled binaries'
@echo ' install-doc - install *all* documentation'
@echo ' install-man - install manpage documentation'
@echo ' install-html - install html documentation'
@echo ' install-info - install GNU info documentation'
@echo ' install-pdf - install pdf documentation'
@echo ''
@echo ' quick-install-doc - alias for quick-install-man'
@echo ' quick-install-man - install the documentation quickly'
@echo ' quick-install-html - install the html documentation quickly'
@echo ''
@echo 'Perf maintainer targets:'
@echo ' clean - clean all binary objects and build output'
DOC_TARGETS := doc man html info pdf
INSTALL_DOC_TARGETS := $(patsubst %,install-%,$(DOC_TARGETS)) try-install-man
INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
# 'make doc' should call 'make -C Documentation all'
$(DOC_TARGETS):
$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all) ASCIIDOC_EXTRA=$(ASCIIDOC_EXTRA)
TAG_FOLDERS= . ../lib ../include
TAG_FILES= ../../include/uapi/linux/perf_event.h
TAGS:
$(QUIET_GEN)$(RM) TAGS; \
$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs etags -a $(TAG_FILES)
tags:
$(QUIET_GEN)$(RM) tags; \
$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs ctags -a $(TAG_FILES)
cscope:
$(QUIET_GEN)$(RM) cscope*; \
$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs cscope -b $(TAG_FILES)
### Testing rules
# GNU make supports exporting all variables by "export" without parameters.
# However, the environment gets quite big, and some programs have problems
# with that.
check: $(OUTPUT)common-cmds.h
if sparse; \
then \
for i in *.c */*.c; \
do \
sparse $(CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
done; \
else \
exit 1; \
fi
### Installation rules
ifdef GTK2
install-gtk: $(OUTPUT)libperf-gtk.so
$(call QUIET_INSTALL, 'GTK UI') \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
$(INSTALL) $(OUTPUT)libperf-gtk.so '$(DESTDIR_SQ)$(libdir_SQ)'
else
install-gtk:
endif
install-tools: all install-gtk
$(call QUIET_INSTALL, binaries) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
$(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(includedir_SQ)/perf'; \
$(INSTALL) -m 644 include/perf/perf_dlfilter.h -t '$(DESTDIR_SQ)$(includedir_SQ)/perf'
ifndef NO_PERF_READ_VDSO32
$(call QUIET_INSTALL, perf-read-vdso32) \
$(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(bindir_SQ)';
endif
ifndef NO_PERF_READ_VDSOX32
$(call QUIET_INSTALL, perf-read-vdsox32) \
$(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(bindir_SQ)';
endif
ifndef NO_JVMTI
$(call QUIET_INSTALL, $(LIBJVMTI)) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
$(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)';
endif
$(call QUIET_INSTALL, libexec) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
$(call QUIET_INSTALL, perf-archive) \
$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
$(call QUIET_INSTALL, perf-iostat) \
$(INSTALL) $(OUTPUT)perf-iostat -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
ifndef NO_LIBAUDIT
$(call QUIET_INSTALL, strace/groups) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'; \
$(INSTALL) trace/strace/groups/* -m 644 -t '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'
endif
ifndef NO_LIBPERL
$(call QUIET_INSTALL, perl-scripts) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
$(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
$(INSTALL) scripts/perl/*.pl -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'; \
$(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
endif
ifndef NO_LIBPYTHON
$(call QUIET_INSTALL, python-scripts) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'; \
$(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
$(INSTALL) scripts/python/*.py -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
endif
$(call QUIET_INSTALL, dlfilters) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/dlfilters'; \
$(INSTALL) $(DLFILTERS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/dlfilters';
$(call QUIET_INSTALL, perf_completion-script) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
$(INSTALL) perf-completion.sh -m 644 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
$(call QUIET_INSTALL, perf-tip) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(tip_instdir_SQ)'; \
$(INSTALL) Documentation/tips.txt -m 644 -t '$(DESTDIR_SQ)$(tip_instdir_SQ)'
install-tests: all install-gtk
$(call QUIET_INSTALL, tests) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
$(INSTALL) tests/attr.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
$(INSTALL) tests/pe-file.exe* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
$(INSTALL) tests/attr/* -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
$(INSTALL) tests/shell/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
$(INSTALL) tests/shell/lib/*.sh -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
$(INSTALL) tests/shell/lib/*.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight' ; \
$(INSTALL) tests/shell/coresight/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight'
$(Q)$(MAKE) -C tests/shell/coresight install-tests
install-bin: install-tools install-tests
install: install-bin try-install-man
install-python_ext:
$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
# 'make install-doc' should call 'make -C Documentation install'
$(INSTALL_DOC_TARGETS):
$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=) ASCIIDOC_EXTRA=$(ASCIIDOC_EXTRA)
### Cleaning rules
python-clean:
$(python-clean)
SKEL_OUT := $(abspath $(OUTPUT)util/bpf_skel)
SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp)
SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h
SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h
SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h
SKELETONS += $(SKEL_OUT)/kwork_top.skel.h
SKELETONS += $(SKEL_OUT)/bench_uprobe.skel.h
SKELETONS += $(SKEL_OUT)/augmented_raw_syscalls.skel.h
$(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT):
$(Q)$(MKDIR) -p $@
ifeq ($(CONFIG_PERF_BPF_SKEL),y)
BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool
# Get Clang's default includes on this system, as opposed to those seen by
# '--target=bpf'. This fixes "missing" files on some architectures/distros,
# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
#
# Use '-idirafter': Don't interfere with include mechanics except where the
# build would have failed anyways.
define get_sys_includes
$(shell $(1) $(2) -v -E - </dev/null 2>&1 \
| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
endef
ifneq ($(CROSS_COMPILE),)
CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%))
endif
CLANG_OPTIONS = -Wall
CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES)
TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi
ifneq ($(WERROR),0)
CLANG_OPTIONS += -Werror
endif
$(BPFTOOL): | $(SKEL_TMP_OUT)
$(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \
OUTPUT=$(SKEL_TMP_OUT)/ bootstrap
# Paths to search for a kernel to generate vmlinux.h from.
VMLINUX_BTF_ELF_PATHS ?= $(if $(O),$(O)/vmlinux) \
$(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
../../vmlinux \
/boot/vmlinux-$(shell uname -r)
# Paths to BTF information.
VMLINUX_BTF_BTF_PATHS ?= /sys/kernel/btf/vmlinux
# Filter out kernels that don't exist or without a BTF section.
VMLINUX_BTF_ELF_ABSPATHS ?= $(abspath $(wildcard $(VMLINUX_BTF_ELF_PATHS)))
VMLINUX_BTF_PATHS ?= $(shell for file in $(VMLINUX_BTF_ELF_ABSPATHS); \
do \
if [ -f $$file ] && ($(READELF) -S "$$file" | grep -q .BTF); \
then \
echo "$$file"; \
fi; \
done) \
$(wildcard $(VMLINUX_BTF_BTF_PATHS))
# Select the first as the source of vmlinux.h.
VMLINUX_BTF ?= $(firstword $(VMLINUX_BTF_PATHS))
ifeq ($(VMLINUX_H),)
ifeq ($(VMLINUX_BTF),)
$(error Missing bpftool input for generating vmlinux.h)
endif
endif
$(SKEL_OUT)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
ifeq ($(VMLINUX_H),)
$(QUIET_GEN)$(BPFTOOL) btf dump file $< format c > $@
else
$(Q)cp "$(VMLINUX_H)" $@
endif
$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) $(SKEL_OUT)/vmlinux.h | $(SKEL_TMP_OUT)
$(QUIET_CLANG)$(CLANG) -g -O2 --target=bpf $(CLANG_OPTIONS) $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
-c $(filter util/bpf_skel/%.bpf.c,$^) -o $@
$(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL)
$(QUIET_GENSKEL)$(BPFTOOL) gen skeleton $< > $@
bpf-skel: $(SKELETONS)
.PRECIOUS: $(SKEL_TMP_OUT)/%.bpf.o
else # CONFIG_PERF_BPF_SKEL
bpf-skel:
endif # CONFIG_PERF_BPF_SKEL
bpf-skel-clean:
$(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS)
clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $(LIBPERF)-clean arm64-sysreg-defs-clean fixdep-clean python-clean bpf-skel-clean tests-coresight-targets-clean
$(call QUIET_CLEAN, core-objs) $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-iostat $(LANG_BINDINGS)
$(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
$(Q)$(RM) $(OUTPUT).config-detected
$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)$(LIBJVMTI).so
$(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)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
$(OUTPUT)pmu-events/pmu-events.c \
$(OUTPUT)pmu-events/metric_test.log \
$(OUTPUT)$(fadvise_advice_array) \
$(OUTPUT)$(fsconfig_arrays) \
$(OUTPUT)$(fsmount_arrays) \
$(OUTPUT)$(fspick_arrays) \
$(OUTPUT)$(madvise_behavior_array) \
$(OUTPUT)$(mmap_flags_array) \
$(OUTPUT)$(mmap_prot_array) \
$(OUTPUT)$(mremap_flags_array) \
$(OUTPUT)$(mount_flags_array) \
$(OUTPUT)$(move_mount_flags_array) \
$(OUTPUT)$(drm_ioctl_array) \
$(OUTPUT)$(pkey_alloc_access_rights_array) \
$(OUTPUT)$(sndrv_ctl_ioctl_array) \
$(OUTPUT)$(sndrv_pcm_ioctl_array) \
$(OUTPUT)$(kvm_ioctl_array) \
$(OUTPUT)$(kcmp_type_array) \
$(OUTPUT)$(socket_arrays) \
$(OUTPUT)$(sockaddr_arrays) \
$(OUTPUT)$(vhost_virtio_ioctl_array) \
$(OUTPUT)$(perf_ioctl_array) \
$(OUTPUT)$(prctl_option_array) \
$(OUTPUT)$(usbdevfs_ioctl_array) \
$(OUTPUT)$(x86_arch_irq_vectors_array) \
$(OUTPUT)$(x86_arch_MSRs_array) \
$(OUTPUT)$(x86_arch_prctl_code_array) \
$(OUTPUT)$(rename_flags_array) \
$(OUTPUT)$(arch_errno_name_array) \
$(OUTPUT)$(sync_file_range_arrays)
$(call QUIET_CLEAN, Documentation) \
$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) clean >/dev/null
#
# To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)
# file if defined, with no further action.
feature-dump:
ifdef FEATURE_DUMP_COPY
@cp $(OUTPUT)FEATURE-DUMP $(FEATURE_DUMP_COPY)
@echo "FEATURE-DUMP file copied into $(FEATURE_DUMP_COPY)"
else
@echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP"
endif
FORCE:
.PHONY: all install clean config-clean strip install-gtk
.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope FORCE prepare
.PHONY: archheaders python_perf_target
endif # force_fixdep
# Delete partially updated (corrupted) files on error
.DELETE_ON_ERROR:
Reference in New Issue View Git Blame Copy Permalink