- 28 May, 2020 40 commits
-
-
Ian Rogers authored
If allocated, perf_pkg_mask and metric_events need freeing. Signed-off-by:
Ian Rogers <irogers@google.com> Reviewed-by:
Andi Kleen <ak@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20200512235918.10732-1-irogers@google.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Arnaldo Carvalho de Melo authored
When applying a patch by Ian I incorrectly converted to zfree() an expression that involved testing some other struct member, not the one being freed, which lead to bugs reproduceable by: $ perf stat -e i/bs,tsc,L2/o sleep 1 WARNING: multiple event parsing errors Segmentation fault (core dumped) $ Fix it by restoring the test for pos->free_str before freeing pos->val.str, but continue using zfree(&pos->val.str) to set that member to NULL after freeing it. Reported-by:
-
Jiri Olsa authored
Adrian reported that is_bpf_image is not working the way it was intended - passing on trampolines and dispatcher names. Instead it returned true for all the bpf names. The reason even this logic worked properly is that all bpf objects, even trampolines and dispatcher, were assigned DSO_BINARY_TYPE__BPF_IMAGE binary_type. The later for bpf_prog objects, the binary_type was fixed in bpf load event processing, which is executed after the ksymbol code. Fixing the is_bpf_image logic, so it properly recognizes trampoline and dispatcher objects. Fixes: 3c29d448 ("perf annotate: Add basic support for bpf_image") Reported-by:
Adrian Hunter <adrian.hunter@intel.com> Signed-off-by:
Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200512122310.3154754-1-jolsa@kernel.orgSigned-off-by:
-
Ian Rogers authored
When the event is passed as list, the default events should be listed as per 'perf mem record -e list'. Previous behavior is: $ perf c2c record -e list failed: event 'list' not found, use '-e list' to get list of available events Usage: perf c2c record [<options>] [<command>] or: perf c2c record [<options>] -- <command> [<options>] -e, --event <event> event selector. Use 'perf mem record -e list' to list available events $ New behavior: $ perf c2c record -e list ldlat-loads : available ldlat-stores : available v3: is a rebase. v2: addresses review comments by Jiri Olsa. https://lore.kernel.org/lkml/20191127081844.GH32367@krava/Signed-off-by: -
Paul A. Clarke authored
Add the following metrics to the POWER9 'cpi_breakdown' metricgroup: - ict_noslot_br_mpred_cpi - ict_noslot_br_mpred_icmiss_cpi - ict_noslot_cyc_other_cpi - ict_noslot_disp_held_cpi - ict_noslot_disp_held_hb_full_cpi - ict_noslot_disp_held_issq_cpi - ict_noslot_disp_held_other_cpi - ict_noslot_disp_held_sync_cpi - ict_noslot_disp_held_tbegin_cpi - ict_noslot_ic_l2_cpi - ict_noslot_ic_l3_cpi - ict_noslot_ic_l3miss_cpi - ict_noslot_ic_miss_cpi Signed-off-by:
Paul Clarke <pc@us.ibm.com> Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Reviewed-by:
Kajol Jain <kjain@linux.ibm.com> Tested-by:
-
Ian Rogers authored
During the processing of /proc during event synthesis new processes may start. Add a dummy event if /proc is to be processed, to capture mmaps for starting processes. This reuses the existing logic for initial-delay. v3 fixes the attr test of test-record-C0 v2 fixes the dummy event configuration and a branch stack issue. Suggested-by:
Stephane Eranian <eranian@google.com> Signed-off-by:
-
Ian Rogers authored
A dummy event never triggers any actual counter and therefore cannot be used with branch_stack Signed-off-by:
-
Jin Yao authored
A big uncore event group is split into multiple small groups which only include the uncore events from the same PMU. This has been supported in the commit 3cdc5c2c ("perf parse-events: Handle uncore event aliases in small groups properly"). If the event's PMU name starts to repeat, it must be a new event. That can be used to distinguish the leader from other members. But now it only compares the pointer of pmu_name (leader->pmu_name == evsel->pmu_name). If we use "perf stat -M LLC_MISSES.PCIE_WRITE -a" on cascadelakex, the event list is: evsel->name evsel->pmu_name --------------------------------------------------------------- unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_4 (as leader) unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_2 unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_0 unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_5 unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_3 unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_1 unc_iio_data_req_of_cpu.mem_write.part1 uncore_iio_4 ...... For the event "unc_iio_data_req_of_cpu.mem_write.part1" with "uncore_iio_4", it should be the event from PMU "uncore_iio_4". It's not a new leader for this PMU. But if we use "(leader->pmu_name == evsel->pmu_name)", the check would be failed and the event is stored to leaders[] as a new PMU leader. So this patch uses strcmp to compare the PMU name between events. Fixes: d4953f7e ("perf parse-events: Fix 3 use after frees found with clang ASAN") Signed-off-by:
Jin Yao <yao.jin@linux.intel.com> Acked-by:
-
Paul A. Clarke authored
Add another digit of precision to the perf metrics output. Before: $ /usr/bin/perf stat --metrics run_cpi /bin/ls [...] 4,345,526 pm_run_cyc # 1.1 run_cpi 3,818,069 pm_run_inst_cmpl [...] $ /usr/bin/perf stat --metrics run_cpi --metric-only /bin/ls [...] run_cpi 1.1 [...] After: $ perf stat --metrics run_cpi /bin/ls [...] 4,280,882 pm_run_cyc # 1.12 run_cpi 3,817,016 pm_run_inst_cmpl [...] $ perf stat --metrics run_cpi --metric-only /bin/ls [...] run_cpi 1.06 [...] Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: -
Ian Rogers authored
If an expression yields 0 and is then divided-by/modulus-by then the parsing aborts. Add a debug error message to better enable debugging when this happens. Signed-off-by:
-
Ian Rogers authored
Mismatched parentheses. Fixes: 7f3cf5ac (perf vendor events power9: Cpi_breakdown & estimated_dcache_miss_cpi metrics) Signed-off-by:
-
Ian Rogers authored
Mismatched parentheses. Fixes: dd81eafa (perf vendor events power8: Cpi_breakdown & estimated_dcache_miss_cpi metrics) Signed-off-by:
-
Ian Rogers authored
Only effects parser debugging (disabled by default). Enables displaying '--accepting rule at line .. ("..."). Signed-off-by: -
Ian Rogers authored
This is expected in expr.y and metrics use floating point values such as x86 broadwell IFetch_Line_Utilization. Fixes: 26226a97 (perf expr: Move expr lexer to flex) Signed-off-by:
-
Ian Rogers authored
Large metrics such as Branch_Misprediction_Cost_SMT on x86 broadwell need more space. Signed-off-by:
-
Ian Rogers authored
Corrects parse errors in expr__find_other of expressions with min. Signed-off-by:
-
Ian Rogers authored
Remove over escaping with \\. Fixes: fd550098 (perf vendor events intel: Update metrics from TMAM 3.5) Signed-off-by:
-
Ian Rogers authored
Remove over escaping with \\. Remove extraneous if 1 if 0 == 1 else 0 else 0. Fixes: fd550098 (perf vendor events intel: Update metrics from TMAM 3.5) Signed-off-by:
-
Ian Rogers authored
Current expression allows 2 escaped '-,=' characters. However, some metrics require more, for example Haswell DRAM_BW_Use. Fixes: 26226a97 (perf expr: Move expr lexer to flex) Signed-off-by:
-
Jiri Olsa authored
In case the callchains were deleted in pipe mode, we need to ensure that the IP fields are enabled, otherwise the callchain is not displayed. Enabling IP and SYM, which should be enough for callchains. Committer testing: Before: Committer Testing: before: # ls # perf record -g -e 'syscalls:*' sleep 0.1 2>/dev/null | perf script | tail sleep 5677 [0] 5034.295882: syscalls:sys_exit_mmap: 0x7fcbcfa74000 sleep 5677 [0] 5034.295885: syscalls:sys_enter_close: fd: 0x00000003 sleep 5677 [0] 5034.295886: syscalls:sys_exit_close: 0x0 sleep 5677 [0] 5034.295911: syscalls:sys_enter_nanosleep: rqtp: 0x7fff775b33a0, rmtp: 0x00000000 sleep 5677 [0] 5034.396021: syscalls:sys_exit_nanosleep: 0x0 sleep 5677 [0] 5034.396027: syscalls:sys_enter_close: fd: 0x00000001 sleep 5677 [0] 5034.396028: syscalls:sys_exit_close: 0x0 sleep 5677 [0] 5034.396029: syscalls:sys_enter_close: fd: 0x00000002 sleep 5677 [0] 5034.396029: syscalls:sys_exit_close: 0x0 sleep 5677 [0] 5034.396032: syscalls:sys_enter_exit_group: error_code: 0x00000000 # # ls # After: # perf record --call-graph=dwarf -e 'syscalls:sys_enter*' sleep 0.1 2>/dev/null | perf script | tail -37 sleep 33010 [000] 5400.625269: syscalls:sys_enter_nanosleep: rqtp: 0x7fff2d0e7860, rmtp: 0x00000000 7f1406f131a7 __GI___nanosleep (inlined) 561c4f996966 [unknown] 561c4f99673f [unknown] 561c4f9937af [unknown] 7f1406e6c1a2 __libc_start_main 561c4f99388d [unknown] sleep 33010 [000] 5400.725391: syscalls:sys_enter_close: fd: 0x00000001 7f1406f3c3cb __GI___close_nocancel (inlined) 7f1406ec7d6f _IO_new_file_close_it (inlined) 7f1406ebafa5 _IO_new_fclose (inlined) 561c4f996a40 [unknown] 561c4f993d79 [unknown] 7f1406e83e86 __run_exit_handlers 7f1406e8403f __GI_exit (inlined) 7f1406e6c1a9 __libc_start_main 561c4f99388d [unknown] sleep 33010 [000] 5400.725395: syscalls:sys_enter_close: fd: 0x00000002 7f1406f3c3cb __GI___close_nocancel (inlined) 7f1406ec7d6f _IO_new_file_close_it (inlined) 7f1406ebafa5 _IO_new_fclose (inlined) 561c4f996a40 [unknown] 561c4f993da2 [unknown] 7f1406e83e86 __run_exit_handlers 7f1406e8403f __GI_exit (inlined) 7f1406e6c1a9 __libc_start_main 561c4f99388d [unknown] sleep 33010 [000] 5400.725399: syscalls:sys_enter_exit_group: error_code: 0x00000000 7f1406f13466 __GI__exit (inlined) 7f1406e83fa1 __run_exit_handlers 7f1406e8403f __GI_exit (inlined) 7f1406e6c1a9 __libc_start_main 561c4f99388d [unknown] # And, if we install coreutils-debuginfo, we'll have those [unknown] resolved, those are for the /usr/bin/sleep binary, use: # dnf debuginfo-install coreutils On Fedora and derivatives, then: # perf record --call-graph=dwarf -e 'syscalls:sys_enter*' sleep 0.1 2>/dev/null | perf script | tail -37 sleep 33046 [009] 5533.910074: syscalls:sys_enter_nanosleep: rqtp: 0x7ffea6fa7ab0, rmtp: 0x00000000 7f5f786e81a7 __GI___nanosleep (inlined) 564472454966 rpl_nanosleep 56447245473f xnanosleep 5644724517af main 7f5f786411a2 __libc_start_main 56447245188d _start sleep 33046 [009] 5534.010218: syscalls:sys_enter_close: fd: 0x00000001 7f5f787113cb __GI___close_nocancel (inlined) 7f5f7869cd6f _IO_new_file_close_it (inlined) 7f5f7868ffa5 _IO_new_fclose (inlined) 564472454a40 close_stream 564472451d79 close_stdout 7f5f78658e86 __run_exit_handlers 7f5f7865903f __GI_exit (inlined) 7f5f786411a9 __libc_start_main 56447245188d _start sleep 33046 [009] 5534.010224: syscalls:sys_enter_close: fd: 0x00000002 7f5f787113cb __GI___close_nocancel (inlined) 7f5f7869cd6f _IO_new_file_close_it (inlined) 7f5f7868ffa5 _IO_new_fclose (inlined) 564472454a40 close_stream 564472451da2 close_stdout 7f5f78658e86 __run_exit_handlers 7f5f7865903f __GI_exit (inlined) 7f5f786411a9 __libc_start_main 56447245188d _start sleep 33046 [009] 5534.010229: syscalls:sys_enter_exit_group: error_code: 0x00000000 7f5f786e8466 __GI__exit (inlined) 7f5f78658fa1 __run_exit_handlers 7f5f7865903f __GI_exit (inlined) 7f5f786411a9 __libc_start_main 56447245188d _start # Reported-by:Paul Khuong <pvk@pvk.ca> Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Tested-by:
-
Jiri Olsa authored
Callchains are automatically initialized by checking on event's sample_type. For pipe mode we need to put this check into attr event code. Moving the callchains setup code into callchain_param_setup function and calling it from attr event process code. This enables pipe output having callchains, like: # perf record -g -e 'raw_syscalls:sys_enter' true | perf script # perf record -g -e 'raw_syscalls:sys_enter' true | perf report Committer notes: We still need the next patch for the above output to work. Reported-by:
-
Jiri Olsa authored
Ian came with the idea of having support to read the pipe data also from file. Currently pipe mode files fail like: $ perf record -o - sleep 1 > /tmp/perf.pipe.data $ perf report -i /tmp/perf.pipe.data incompatible file format (rerun with -v to learn more) This patch adds the support to do that by trying the pipe header first, and if its successfully detected, switching the perf data to pipe mode. Committer testing: # ls # perf record -a -o - sleep 1 > /tmp/perf.pipe.data [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.000 MB - ] # ls # perf report -i /tmp/perf.pipe.data | head -25 # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 511 of event 'cycles' # Event count (approx.): 178447276 # # Overhead Command Shared Object Symbol # ........ ........ ................. ........................................................................................... # 65.49% swapper [kernel.kallsyms] [k] native_safe_halt 6.45% chromium libblink_core.so [.] blink::SelectorChecker::CheckOne 4.08% chromium libblink_core.so [.] blink::SelectorQuery::ExecuteForTraverseRoot<blink::AllElementsSelectorQueryTrait> 2.25% chromium libblink_core.so [.] blink::SelectorQuery::FindTraverseRootsAndExecute<blink::AllElementsSelectorQueryTrait> 2.11% chromium libblink_core.so [.] blink::SelectorChecker::MatchSelector 1.91% chromium libblink_core.so [.] blink::Node::OwnerShadowHost 1.31% chromium libblink_core.so [.] blink::Node::parentNode@plt 1.22% chromium libblink_core.so [.] blink::Node::parentNode 0.59% chromium libblink_core.so [.] blink::AnyAttributeMatches 0.58% chromium libv8.so [.] v8::internal::GlobalHandles::Create 0.58% chromium libblink_core.so [.] blink::NodeTraversal::NextAncestorSibling 0.55% chromium libv8.so [.] v8::internal::RegExpGlobalCache::RegExpGlobalCache 0.55% chromium libblink_core.so [.] blink::Node::ContainingShadowRoot 0.55% chromium libblink_core.so [.] blink::NodeTraversal::NextAncestorSibling@plt # Original-patch-by: -
Jiri Olsa authored
There's no need to set 'fd' position in pipe mode, the file descriptor is already in proper place. Moreover the lseek will fail on pipe descriptor and that's why it's been working properly. I was tempted to remove the lseek calls completely, because it seems that tracing data event was always synthesized only in pipe mode, so there's no need for 'file' mode handling. But I guess there was a reason behind this and there might (however unlikely) be a perf.data that we could break processing for. Signed-off-by:
-
Jiri Olsa authored
Even with fully built tree, we still display extra output when make is invoked, like: $ make BUILD: Doing 'make -j8' parallel build DESCEND plugins make[3]: Nothing to be done for 'plugins/libtraceevent-dynamic-list'. Changing the make descend directly to plugins directory, which quiets those messages down. Reported-by: -
Masami Hiramatsu authored
When a probe point is expanded to several places (like inlined) and if some of them are skipped because of blacklisted or __init function, those trace_events has no event name. It must be skipped while showing results. Without this fix, you can see "(null):(null)" on the list, # ./perf probe request_resource reserve_setup is out of .text, skip it. Added new events: (null):(null) (on request_resource) probe:request_resource (on request_resource) You can now use it in all perf tools, such as: perf record -e probe:request_resource -aR sleep 1 # With this fix, it is ignored: # ./perf probe request_resource reserve_setup is out of .text, skip it. Added new events: probe:request_resource (on request_resource) You can now use it in all perf tools, such as: perf record -e probe:request_resource -aR sleep 1 # Fixes: 5a51fcd1 ("perf probe: Skip kernel symbols which is out of .text") Signed-off-by:Masami Hiramatsu <mhiramat@kernel.org> Tested-by:
-
Masami Hiramatsu authored
Since commit 03db8b58 ("perf tools: Fix maps__find_symbol_by_name()") introduced map address range check in maps__find_symbol_by_name(), we can not get "_etext" from kernel map because _etext is placed on the edge of the kernel .text section (= kernel map in perf.) To fix this issue, this checks the address correctness by map address range information (map->start and map->end) instead of using _etext address. This can cause an error if the target inlined function is embedded in both __init function and normal function. For exaample, request_resource() is a normal function but also embedded in __init reserve_setup(). In this case, the probe point in reserve_setup() must be skipped. However, without this fix, it failes to setup all probe points: # ./perf probe -v request_resource probe-definition(0): request_resource symbol:request_resource file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (8 entries long) Using /usr/lib/debug/lib/modules/5.5.17-200.fc31.x86_64/vmlinux for symbols Open Debuginfo file: /usr/lib/debug/lib/modules/5.5.17-200.fc31.x86_64/vmlinux Try to find probe point from debuginfo. Matched function: request_resource [15e29ad] found inline addr: 0xffffffff82fbf892 Probe point found: reserve_setup+204 found inline addr: 0xffffffff810e9790 Probe point found: request_resource+0 Found 2 probe_trace_events. Opening /sys/kernel/debug/tracing//kprobe_events write=1 Opening /sys/kernel/debug/tracing//README write=0 Writing event: p:probe/request_resource _text+33290386 Failed to write event: Invalid argument Error: Failed to add events. Reason: Invalid argument (Code: -22) # With this fix, # ./perf probe request_resource reserve_setup is out of .text, skip it. Added new events: (null):(null) (on request_resource) probe:request_resource (on request_resource) You can now use it in all perf tools, such as: perf record -e probe:request_resource -aR sleep 1 # Fixes: 03db8b58 ("perf tools: Fix maps__find_symbol_by_name()") Reported-by:
Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by:
-
Masami Hiramatsu authored
Fix to check kprobe blacklist address correctly with relocated address by adjusting debuginfo address. Since the address in the debuginfo is same as objdump, it is different from relocated kernel address with KASLR. Thus, 'perf probe' always misses to catch the blacklisted addresses. Without this patch, 'perf probe' can not detect the blacklist addresses on a KASLR enabled kernel. # perf probe kprobe_dispatcher Failed to write event: Invalid argument Error: Failed to add events. # With this patch, it correctly shows the error message. # perf probe kprobe_dispatcher kprobe_dispatcher is blacklisted function, skip it. Probe point 'kprobe_dispatcher' not found. Error: Failed to add events. # Fixes: 9aaf5a5f ("perf probe: Check kprobes blacklist when adding new events") Signed-off-by: -
Masami Hiramatsu authored
Since the commit 6a13a0d7 ("ftrace/kprobe: Show the maxactive number on kprobe_events") introduced to show the instance number of kretprobe events, the length of the 1st format of the kprobe event will not 1, but it can be longer. This caused a parser error in perf-probe. Skip the length check the 1st format of the kprobe event to accept this instance number. Without this fix: # perf probe -a vfs_read%return Added new event: probe:vfs_read__return (on vfs_read%return) You can now use it in all perf tools, such as: perf record -e probe:vfs_read__return -aR sleep 1 # perf probe -l Semantic error :Failed to parse event name: r16:probe/vfs_read__return Error: Failed to show event list. And with this fixes: # perf probe -a vfs_read%return ... # perf probe -l probe:vfs_read__return (on vfs_read%return) Fixes: 6a13a0d7 ("ftrace/kprobe: Show the maxactive number on kprobe_events") Reported-by:
Yuxuan Shui <yshuiv7@gmail.com> Signed-off-by:
-
Arnaldo Carvalho de Melo authored
As these are 'struct evsel' methods, not part of tools/lib/perf/, aka libperf, to whom the perf_ prefix belongs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: -
Arnaldo Carvalho de Melo authored
As those are 'struct evsel' methods, not part of tools/lib/perf/, aka libperf, to whom the perf_ prefix belongs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: -
Arnaldo Carvalho de Melo authored
As these are 'struct evsel' methods, not part of tools/lib/perf/, aka libperf, to whom the perf_ prefix belongs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: -
Arnaldo Carvalho de Melo authored
As it is a 'struct evsel' method, not part of tools/lib/perf/, aka libperf, to whom the perf_ prefix belongs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: -
Arnaldo Carvalho de Melo authored
As it is a 'struct evsel' method, not part of tools/lib/perf/, aka libperf, to whom the perf_ prefix belongs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: -
Arnaldo Carvalho de Melo authored
As it is a 'struct evsel' method, not part of tools/lib/perf/, aka libperf, to whom the perf_ prefix belongs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: -
Arnaldo Carvalho de Melo authored
As it is a 'struct evsel' method, not part of tools/lib/perf/, aka libperf, to whom the perf_ prefix belongs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: -
Stephane Eranian authored
This patch enables AMD Fam17h RAPL support for the Package level metric. The support is as per AMD Fam17h Model31h (Zen2) and model 00-ffh (Zen1) PPR. The same output is available via the energy-pkg pseudo event: $ perf stat -a -I 1000 --per-socket -e power/energy-pkg/ Signed-off-by:
Ingo Molnar <mingo@kernel.org> Link: https://lore.kernel.org/r/20200527224659.206129-6-eranian@google.com
-
Stephane Eranian authored
This patch modifies perf_probe_msr() by allowing passing of struct perf_msr array where some entries are not populated, i.e., they have either an msr address of 0 or no attribute_group pointer. This helps with certain call paths, e.g., RAPL. In case the grp is NULL, the default sysfs visibility rule applies which is to make the group visible. Without the patch, you would get a kernel crash with a NULL group. Signed-off-by:
-
Stephane Eranian authored
This patch modifies the default visibility of the attribute_group for each RAPL event. By default if the grp.is_visible field is NULL, sysfs considers that it must display the attribute group. If the field is not NULL (callback function), then the return value of the callback determines the visibility (0 = not visible). The RAPL attribute groups had the field set to NULL, meaning that unless they failed the probing from perf_msr_probe(), they would be visible. We want to avoid having to specify attribute groups that are not supported by the HW in the rapl_msrs[] array, they don't have an MSR address to begin with. Therefore, we intialize the visible field of all RAPL attribute groups to a callback that returns 0. If the RAPL msr goes through probing and succeeds the is_visible field will be set back to NULL (visible). If the probing fails the field is set to a callback that return 0 (not visible). Signed-off-by:
-
Stephane Eranian authored
This patch modifies the rapl_model struct to include architecture specific knowledge in this previously Intel specific structure, and in particular it adds the MSR for POWER_UNIT and the rapl_msrs array. No functional changes. Signed-off-by:
-
Stephane Eranian authored
To prepare for support of both Intel and AMD RAPL. As per the AMD PPR, Fam17h support Package RAPL counters to monitor power usage. The RAPL counter operates as with Intel RAPL, and as such it is beneficial to share the code. No change in functionality. Signed-off-by:
-
