- 21 Mar, 2024 40 commits
-
-
Ian Rogers authored
Update events from 1.17 to 1.20 as released in: https://github.com/intel/perfmon/commit/6f674057745acf0125395638ca6be36458a59bda Various description updates. Adds uncore events UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL, UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE, UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL, UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE, UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL, UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE, UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_LOCAL, UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_REMOTE, UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_LOCAL, UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_REMOTE, UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_LOCAL, UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_REMOTE and removes core events AMX_OPS_RETIRED.BF16 and AMX_OPS_RETIRED.INT8. Reviewed-by:
Kan Liang <kan.liang@linux.intel.com> Signed-off-by:
Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Edward Baker <edward.baker@intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Samantha Alt <samantha.alt@intel.com> Cc: Weilin Wang <weilin.wang@intel.com> Link: https://lore.kernel.org/r/20240321060016.1464787-8-irogers@google.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Ian Rogers authored
Update events from 1.07 to 1.08 as released in: https://github.com/intel/perfmon/commit/f0f8f3e163d9eb84e6ce8e2108a22cb43b2527e5 Various description updates. Adds topdown, offcore and uncore events OCR.DEMAND_DATA_RD.L3_HIT, OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD, OCR.DEMAND_RFO.L3_HIT, OCR.DEMAND_DATA_RD.L3_MISS, OCR.DEMAND_RFO.L3_MISS, OCR.DEMAND_DATA_RD.ANY_RESPONSE, OCR.DEMAND_DATA_RD.DRAM, OCR.DEMAND_RFO.ANY_RESPONSE, OCR.DEMAND_RFO.DRAM, TOPDOWN_BAD_SPECULATION.ALL_P, TOPDOWN_BE_BOUND.ALL_P, TOPDOWN_FE_BOUND.ALL_P, TOPDOWN_RETIRING.ALL_P, UNC_ARB_DAT_OCCUPANCY.RD and UNC_HAC_ARB_COH_TRK_REQUESTS.ALL. Reviewed-by:
-
Ian Rogers authored
Update events from 1.00 to 1.01 as released in: https://github.com/intel/perfmon/commit/56ab8d837ac566d51a4d8748b6b4b817a22c9b84 Various encoding and description updates. Adds the events CPU_CLK_UNHALTED.CORE, CPU_CLK_UNHALTED.CORE_P, CPU_CLK_UNHALTED.REF_TSC_P, CPU_CLK_UNHALTED.THREAD, MISC_RETIRED.LBR_INSERTS, TOPDOWN_BAD_SPECULATION.ALL_P, TOPDOWN_BE_BOUND.ALL_P, TOPDOWN_FE_BOUND.ALL_P, TOPDOWN_RETIRING.ALL_P. Reviewed-by:
-
Ian Rogers authored
Update events from 1.23 to 1.24 as released in: https://github.com/intel/perfmon/commit/d883888ae60882028e387b6fe1ebf683beb693fa Fixes spelling and descriptions. Adds the uncore events UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL and UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE, while removing UNC_IIO_NUM_REQ_FROM_CPU.IRP. Reviewed-by:
-
Ian Rogers authored
Update events from 1.01 to 1.02 as released in: https://github.com/intel/perfmon/commit/b2a81e803add1ba0af68a442c975683d226d868c Fixes spelling and descriptions. Adds topdown events and uncore cache UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT, UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT, UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT. Reviewed-by:
-
Ian Rogers authored
Update events from 1.03 to 1.96 as released in: https://github.com/intel/perfmon/commit/21a8be3ea7918749141db4036fb65a2343cd865d Fixes spelling and descriptions. Adds cache miss latency events UNC_CHA_TOR_(INSERTS|OCCUPANCY).IO_(PCIRDCUR|ITOM|ITOMCACHENEAR)_(LOCAL|REMOTE). Reviewed-by:
-
Ian Rogers authored
Update events from 1.20 to 1.21 as released in: https://github.com/intel/perfmon/commit/fcfdba3be8f3be81ad6b509fdebf953ead92dc2c Largely fixes spelling and descriptions. Reviewed-by:
-
Arnaldo Carvalho de Melo authored
This prototype is obtained indirectly, by luck, from some other header in probe-event.c in most systems, but recently exploded on alpine:edge: 8 13.39 alpine:edge : FAIL gcc version 13.2.1 20240309 (Alpine 13.2.1_git20240309) util/probe-event.c: In function 'convert_exec_to_group': util/probe-event.c:225:16: error: implicit declaration of function 'basename' [-Werror=implicit-function-declaration] 225 | ptr1 = basename(exec_copy); | ^~~~~~~~ util/probe-event.c:225:14: error: assignment to 'char *' from 'int' makes pointer from integer without a cast [-Werror=int-conversion] 225 | ptr1 = basename(exec_copy); | ^ cc1: all warnings being treated as errors make[3]: *** [/git/perf-6.8.0/tools/build/Makefile.build:158: util] Error 2 Fix it by adding the libgen.h header where basename() is prototyped. Fixes: fb7345bb ("perf probe: Support basic dwarf-based operations on uprobe events") Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/Signed-off-by: -
Arnaldo Carvalho de Melo authored
There were needless two entries, one for 'newfstatat' and another for 'fstatat', keep just one and pretty print its 'flags' argument using the fs_at_flags scnprintf that is also used by other FS syscalls such as 'stat', now: root@number:~# perf trace -e newfstatat --max-events=5 0.000 ( 0.010 ms): abrt-dump-jour/1400 newfstatat(dfd: 7, filename: "", statbuf: 0x7fff0d127000, flag: EMPTY_PATH) = 0 0.020 ( 0.003 ms): abrt-dump-jour/1400 newfstatat(dfd: 9, filename: "", statbuf: 0x55752507b0e8, flag: EMPTY_PATH) = 0 0.039 ( 0.004 ms): abrt-dump-jour/1400 newfstatat(dfd: 19, filename: "", statbuf: 0x557525061378, flag: EMPTY_PATH) = 0 0.047 ( 0.003 ms): abrt-dump-jour/1400 newfstatat(dfd: 20, filename: "", statbuf: 0x5575250b8cc8, flag: EMPTY_PATH) = 0 0.053 ( 0.003 ms): abrt-dump-jour/1400 newfstatat(dfd: 22, filename: "", statbuf: 0x5575250535d8, flag: EMPTY_PATH) = 0 root@number:~# Reviewed-by: -
Arnaldo Carvalho de Melo authored
Reusing the fs_at_flags array done for the 'stat' syscall. Reviewed-by:
-
Arnaldo Carvalho de Melo authored
The fsaccessat and fsaccessat2 now have beautifiers for its arguments. Reviewed-by:
-
Arnaldo Carvalho de Melo authored
It was using the first variation on producing a string representation for a binary flag, one that used the system's stat.h and preprocessor tricks that had to be updated everytime a new flag was introduced. Use the more recent scrape script + strarray + strarray__scnprintf_flags() combo. $ tools/perf/trace/beauty/statx_mask.sh static const char *statx_mask[] = { [ilog2(0x00000001) + 1] = "TYPE", [ilog2(0x00000002) + 1] = "MODE", [ilog2(0x00000004) + 1] = "NLINK", [ilog2(0x00000008) + 1] = "UID", [ilog2(0x00000010) + 1] = "GID", [ilog2(0x00000020) + 1] = "ATIME", [ilog2(0x00000040) + 1] = "MTIME", [ilog2(0x00000080) + 1] = "CTIME", [ilog2(0x00000100) + 1] = "INO", [ilog2(0x00000200) + 1] = "SIZE", [ilog2(0x00000400) + 1] = "BLOCKS", [ilog2(0x00000800) + 1] = "BTIME", [ilog2(0x00001000) + 1] = "MNT_ID", [ilog2(0x00002000) + 1] = "DIOALIGN", [ilog2(0x00004000) + 1] = "MNT_ID_UNIQUE", }; $ Now we need a copy of uapi/linux/stat.h from tools/include/ in the scrape only directory tools/perf/trace/beauty/include. Reviewed-by: -
Arnaldo Carvalho de Melo authored
It was using the first variation on producing a string representation for a binary flag, one that used the system's fcntl.h and preprocessor tricks that had to be updated everytime a new flag was introduced. Use the more recent scrape script + strarray + strarray__scnprintf_flags() combo. $ tools/perf/trace/beauty/fs_at_flags.sh static const char *fs_at_flags[] = { [ilog2(0x100) + 1] = "SYMLINK_NOFOLLOW", [ilog2(0x200) + 1] = "REMOVEDIR", [ilog2(0x400) + 1] = "SYMLINK_FOLLOW", [ilog2(0x800) + 1] = "NO_AUTOMOUNT", [ilog2(0x1000) + 1] = "EMPTY_PATH", [ilog2(0x0000) + 1] = "STATX_SYNC_AS_STAT", [ilog2(0x2000) + 1] = "STATX_FORCE_SYNC", [ilog2(0x4000) + 1] = "STATX_DONT_SYNC", [ilog2(0x8000) + 1] = "RECURSIVE", [ilog2(0x80000000) + 1] = "GETATTR_NOSEC", }; $ Now we need a copy of uapi/linux/fcntl.h from tools/include/ in the scrape only directory tools/perf/trace/beauty/include and will use that fs_at_flags array for other fs syscalls. Reviewed-by: -
Ian Rogers authored
Switch from running tests sequentially to running in parallel by default. Change the opt-in '-p' or '--parallel' flag to '-S' or '--sequential'. On an 8 core tigerlake an address sanitizer run time changes from: 326.54user 622.73system 6:59.91elapsed 226%CPU to: 973.02user 583.98system 3:01.17elapsed 859%CPU So over twice as fast, saving 4 minutes. Signed-off-by:
-
Ian Rogers authored
The levenshtein penalty for deleting a character was far higher than subsituting or inserting a character. Lower the penalty to match that of inserting a character. Before: $ perf recccord perf: 'recccord' is not a perf-command. See 'perf --help'. $ After: $ perf recccord perf: 'recccord' is not a perf-command. See 'perf --help'. Did you mean this? record $ Signed-off-by: -
Ian Rogers authored
The existing unknown command code looks for perf scripts like perf-archive.sh and perf-iostat.sh, however, inbuilt commands aren't suggested. Add the inbuilt commands so they may be suggested too. Before: $ perf reccord perf: 'reccord' is not a perf-command. See 'perf --help'. $ After: $ perf reccord perf: 'reccord' is not a perf-command. See 'perf --help'. Did you mean this? record $ Signed-off-by: -
Ian Rogers authored
Make the perf test output smoother by timing out the poll of the child process after 100ms rather than 1s. Signed-off-by:
-
Ian Rogers authored
Switch from dumping err then out, to a single file descriptor for both of them. This allows the err and output to be correctly interleaved in verbose output. Fixes: b482f5f8 ("perf tests: Add option to run tests in parallel") Signed-off-by:
-
Ian Rogers authored
Per-thread mode requires either system-wide (-a), a pid (-p) or a tid (-t). The stat output tests were using system-wide mode but this is racy when threads are starting and exiting - something that happens a lot when running the tests in parallel (perf test -p). Avoid the race conditions by using pid mode with the pid of the parent process. Signed-off-by:
-
Ian Rogers authored
The session has a header in it which contains a perf env with bpf_progs. The bpf_progs are accessed by the sideband thread and so the sideband thread must be stopped before the session is deleted, to avoid a use after free. This error was detected by AddressSanitizer in the following: ==2054673==ERROR: AddressSanitizer: heap-use-after-free on address 0x61d000161e00 at pc 0x55769289de54 bp 0x7f9df36d4ab0 sp 0x7f9df36d4aa8 READ of size 8 at 0x61d000161e00 thread T1 #0 0x55769289de53 in __perf_env__insert_bpf_prog_info util/env.c:42 #1 0x55769289dbb1 in perf_env__insert_bpf_prog_info util/env.c:29 #2 0x557692bbae29 in perf_env__add_bpf_info util/bpf-event.c:483 #3 0x557692bbb01a in bpf_event__sb_cb util/bpf-event.c:512 #4 0x5576928b75f4 in perf_evlist__poll_thread util/sideband_evlist.c:68 #5 0x7f9df96a63eb in start_thread nptl/pthread_create.c:444 #6 0x7f9df9726a4b in clone3 ../sysdeps/unix/sysv/linux/x86_64/clone3.S:81 0x61d000161e00 is located 384 bytes inside of 2136-byte region [0x61d000161c80,0x61d0001624d8) freed by thread T0 here: #0 0x7f9dfa6d7288 in __interceptor_free libsanitizer/asan/asan_malloc_linux.cpp:52 #1 0x557692978d50 in perf_session__delete util/session.c:319 #2 0x557692673959 in __cmd_record tools/perf/builtin-record.c:2884 #3 0x55769267a9f0 in cmd_record tools/perf/builtin-record.c:4259 #4 0x55769286710c in run_builtin tools/perf/perf.c:349 #5 0x557692867678 in handle_internal_command tools/perf/perf.c:402 #6 0x557692867a40 in run_argv tools/perf/perf.c:446 #7 0x557692867fae in main tools/perf/perf.c:562 #8 0x7f9df96456c9 in __libc_start_call_main ../sysdeps/nptl/libc_start_call_main.h:58 Fixes: 657ee553 ("perf evlist: Introduce side band thread") Signed-off-by: -
Ian Rogers authored
Add perf_pmu__name_from_config that does a reverse lookup from a config number to an alias name. The lookup is expensive as the config is computed for every alias by filling in a perf_event_attr, but this is only done when verbose output is enabled. The lookup also only considers config, and not config1, config2 or config3. An example of the output: $ perf stat -vv -e data_read true ... perf_event_attr: type 24 (uncore_imc_free_running_0) size 136 config 0x20ff (data_read) sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 exclude_guest 1 ... Committer notes: Fix the python binding build by adding dummies for not strictly needed perf_pmu__name_from_config() and perf_pmus__find_by_type(). Signed-off-by: -
Ian Rogers authored
When dumping a perf_event_attr, use pmus to find the PMU and its name by the type number. This allows dynamically added PMUs to be described. Before: $ perf stat -vv -e data_read true ... perf_event_attr: type 24 size 136 config 0x20ff sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 exclude_guest 1 ... After: $ perf stat -vv -e data_read true ... perf_event_attr: type 24 (uncore_imc_free_running_0) size 136 config 0x20ff sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 exclude_guest 1 ... However, it also means that when we have a PMU name we prefer it to a hard coded name: Before: $ perf stat -vv -e faults true ... perf_event_attr: type 1 (PERF_TYPE_SOFTWARE) size 136 config 0x2 (PERF_COUNT_SW_PAGE_FAULTS) sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ... After: $ perf stat -vv -e faults true ... perf_event_attr: type 1 (software) size 136 config 0x2 (PERF_COUNT_SW_PAGE_FAULTS) sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ... It feels more consistent to do this, rather than only prefer a PMU name when a hard coded name isn't available. Signed-off-by: -
Ian Rogers authored
List all the PMUs, not just the first core one, and list real format specifiers with value ranges. Before: $ perf list ... rNNN [Raw hardware event descriptor] cpu/t1=v1[,t2=v2,t3 ...]/modifier [Raw hardware event descriptor] [(see 'man perf-list' on how to encode it)] mem:<addr>[/len][:access] [Hardware breakpoint] ... After: $ perf list ... rNNN [Raw event descriptor] cpu/event=0..255,pc,edge,.../modifier [Raw event descriptor] [(see 'man perf-list' or 'man perf-record' on how to encode it)] breakpoint//modifier [Raw event descriptor] cstate_core/event=0..0xffffffffffffffff/modifier [Raw event descriptor] cstate_pkg/event=0..0xffffffffffffffff/modifier [Raw event descriptor] i915/i915_eventid=0..0x1fffff/modifier [Raw event descriptor] intel_bts//modifier [Raw event descriptor] intel_pt/ptw,event,cyc_thresh=0..15,.../modifier [Raw event descriptor] kprobe/retprobe/modifier [Raw event descriptor] msr/event=0..0xffffffffffffffff/modifier [Raw event descriptor] power/event=0..255/modifier [Raw event descriptor] software//modifier [Raw event descriptor] tracepoint//modifier [Raw event descriptor] uncore_arb/event=0..255,edge,inv,.../modifier [Raw event descriptor] uncore_cbox/event=0..255,edge,inv,.../modifier [Raw event descriptor] uncore_clock/event=0..255/modifier [Raw event descriptor] uncore_imc_free_running/event=0..255,umask=0..255/modifier[Raw event descriptor] uprobe/ref_ctr_offset=0..0xffffffff,retprobe/modifier[Raw event descriptor] mem:<addr>[/len][:access] [Hardware breakpoint] ... With '--details' provide more details on the formats encoding: cpu/event=0..255,pc,edge,.../modifier [Raw event descriptor] [(see 'man perf-list' or 'man perf-record' on how to encode it)] cpu/event=0..255,pc,edge,offcore_rsp=0..0xffffffffffffffff,ldlat=0..0xffff,inv, umask=0..255,frontend=0..0xffffff,cmask=0..255,config=0..0xffffffffffffffff, config1=0..0xffffffffffffffff,config2=0..0xffffffffffffffff,config3=0..0xffffffffffffffff, name=string,period=number,freq=number,branch_type=(u|k|hv|any|...),time, call-graph=(fp|dwarf|lbr),stack-size=number,max-stack=number,nr=number,inherit,no-inherit, overwrite,no-overwrite,percore,aux-output,aux-sample-size=number/modifier breakpoint//modifier [Raw event descriptor] breakpoint//modifier cstate_core/event=0..0xffffffffffffffff/modifier [Raw event descriptor] cstate_core/event=0..0xffffffffffffffff/modifier cstate_pkg/event=0..0xffffffffffffffff/modifier [Raw event descriptor] cstate_pkg/event=0..0xffffffffffffffff/modifier i915/i915_eventid=0..0x1fffff/modifier [Raw event descriptor] i915/i915_eventid=0..0x1fffff/modifier intel_bts//modifier [Raw event descriptor] intel_bts//modifier intel_pt/ptw,event,cyc_thresh=0..15,.../modifier [Raw event descriptor] intel_pt/ptw,event,cyc_thresh=0..15,pt,notnt,branch,tsc,pwr_evt,fup_on_ptw,cyc,noretcomp, mtc,psb_period=0..15,mtc_period=0..15/modifier kprobe/retprobe/modifier [Raw event descriptor] kprobe/retprobe/modifier msr/event=0..0xffffffffffffffff/modifier [Raw event descriptor] msr/event=0..0xffffffffffffffff/modifier power/event=0..255/modifier [Raw event descriptor] power/event=0..255/modifier software//modifier [Raw event descriptor] software//modifier tracepoint//modifier [Raw event descriptor] tracepoint//modifier uncore_arb/event=0..255,edge,inv,.../modifier [Raw event descriptor] uncore_arb/event=0..255,edge,inv,umask=0..255,cmask=0..31/modifier uncore_cbox/event=0..255,edge,inv,.../modifier [Raw event descriptor] uncore_cbox/event=0..255,edge,inv,umask=0..255,cmask=0..31/modifier uncore_clock/event=0..255/modifier [Raw event descriptor] uncore_clock/event=0..255/modifier uncore_imc_free_running/event=0..255,umask=0..255/modifier[Raw event descriptor] uncore_imc_free_running/event=0..255,umask=0..255/modifier uprobe/ref_ctr_offset=0..0xffffffff,retprobe/modifier[Raw event descriptor] uprobe/ref_ctr_offset=0..0xffffffff,retprobe/modifier Committer notes: Address this build error in various distros: 55 58.44 ubuntu:24.04 : FAIL gcc version 13.2.0 (Ubuntu 13.2.0-17ubuntu2) util/pmu.c:1638:70: error: '_Static_assert' with no message is a C2x extension [-Werror,-Wc2x-extensions] 1638 | _Static_assert(ARRAY_SIZE(terms) == __PARSE_EVENTS__TERM_TYPE_NR - 6); | ^ | , "" 1 error generated. Signed-off-by: -
Ian Rogers authored
A raw event encoding may be a block with terms separated by commas. If wrapping such a string it would be useful to break at the commas, so add this ability to wordwrap. Signed-off-by:
-
Ian Rogers authored
"default_core" is used by jevents.py for json events' PMU name when none is specified. On x86 the "default_core" is typically the PMU "cpu". When creating an alias see if the event's PMU name is "default_core" in which case don't record it. This means in places like "perf list" the PMU's name will be used in its place. Before: $ perf list --details ... cache: l1d.replacement [Counts the number of cache lines replaced in L1 data cache] default_core/event=0x51,period=0x186a3,umask=0x1/ ... After: $ perf list --details ... cache: l1d.replacement [Counts the number of cache lines replaced in L1 data cache. Unit: cpu] cpu/event=0x51,period=0x186a3,umask=0x1/ ... Signed-off-by: -
Ian Rogers authored
The tracepoint id holds the config value and is probed in determining what an event is. Add reading of the id so that we can display the event encoding as: $ perf list --details ... alarmtimer:alarmtimer_cancel [Tracepoint event] tracepoint/config=0x18c/ ... Signed-off-by: -
Arnaldo Carvalho de Melo authored
It was using the first variation on producing a string representation for a binary flag, one that used the copy of uapi/linux/sched.h with preprocessor tricks that had to be updated everytime a new flag was introduced. Use the more recent scrape script + strarray + strarray__scnprintf_flags() combo. $ tools/perf/trace/beauty/clone.sh | head -5 static const char *clone_flags[] = { [ilog2(0x00000100) + 1] = "VM", [ilog2(0x00000200) + 1] = "FS", [ilog2(0x00000400) + 1] = "FILES", [ilog2(0x00000800) + 1] = "SIGHAND", $ Now we can move uapi/linux/sched.h from tools/include/, that is used for building perf to the scrape only directory tools/perf/trace/beauty/include. Reviewed-by: -
Namhyung Kim authored
In some cases, it was able to find a type or location info (for per-cpu variable) but cannot match because of invalid offset or missing global information. In those cases, it's meaningless to go to the outer scope and retry because there will be no additional information. Let's change the return type of find_matching_type() and bail out if it returns -1 for the cases. Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20240319055115.4063940-24-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
They are often searched by many different places. Let's add a cache for them to reduce the duplicate DWARF access. Signed-off-by:
-
Namhyung Kim authored
When the stack protector is enabled, compiler would generate code to check stack overflow with a special value called 'stack carary' at runtime. On x86_64, GCC hard-codes the stack canary as %gs:40. While there's a definition of fixed_percpu_data in asm/processor.h, it seems that the header is not included everywhere and many places it cannot find the type info. As it's in the well-known location (at %gs:40), let's add a pseudo stack canary type to handle it specially. Signed-off-by:
-
Namhyung Kim authored
There are different patterns for percpu variable access using a constant value added to the base. 2aeb: mov -0x7da0f7e0(,%rax,8),%r14 # r14 = __per_cpu_offset[cpu] 2af3: mov $0x34740,%rax # rax = address of runqueues * 2afa: add %rax,%r14 # r14 = &per_cpu(runqueues, cpu) 2bfd: cmpl $0x0,0x10(%r14) # cpu_rq(cpu)->has_blocked_load 2b03: je 0x2b36 At the first instruction, r14 has the __per_cpu_offset. And then rax has an immediate value and then added to r14 to calculate the address of a per-cpu variable. So it needs to track the immediate values and ADD instructions. Similar but a little different case is to use "this_cpu_off" instead of "__per_cpu_offset" for the current CPU. This time the variable address comes with PC-rel addressing. 89: mov $0x34740,%rax # rax = address of runqueues * 90: add %gs:0x7f015f60(%rip),%rax # 19a78 <this_cpu_off> 98: incl 0xd8c(%rax) # cpu_rq(cpu)->sched_count Signed-off-by:
-
Namhyung Kim authored
This is to support per-cpu variable access often without a matching DWARF entry. For some reason, I cannot find debug info of per-cpu variables sometimes. They have more complex pattern to calculate the address of per-cpu variables like below. 2b7d: mov -0x1e0(%rbp),%rax ; rax = cpu 2b84: mov -0x7da0f7e0(,%rax,8),%rcx ; rcx = __per_cpu_offset[cpu] * 2b8c: mov 0x34870(%rcx),%rax ; *(__per_cpu_offset[cpu] + 0x34870) Let's assume the rax register has a number for a CPU at 2b7d. The next instruction is to get the per-cpu offset' for that cpu. The offset -0x7da0f7e0 is 0xffffffff825f0820 in u64 which is the address of the '__per_cpu_offset' array in my system. So it'd get the actual offset of that CPU's per-cpu region and save it to the rcx register. Then, at 2b8c, accesses using rcx can be handled same as the global variable access. To handle this case, it should check if the offset of the instruction matches to the address of '__per_cpu_offset'. Signed-off-by:
-
Namhyung Kim authored
Like global variables, this per-cpu variables should be tracked correctly. Factor our get_global_var_type() to handle both global and per-cpu (for this cpu) variables in the same manner. Signed-off-by:
-
Namhyung Kim authored
On x86, the kernel gets the current task using the current macro like below: #define current get_current() static __always_inline struct task_struct *get_current(void) { return this_cpu_read_stable(pcpu_hot.current_task); } So it returns the current_task field of struct pcpu_hot which is the first member. On my build, it's located at 0x32940. $ nm vmlinux | grep pcpu_hot 0000000000032940 D pcpu_hot And the current macro generates the instructions like below: mov %gs:0x32940, %rcx So the %gs segment register points to the beginning of the per-cpu region of this cpu and it points the variable with a constant. Let's update the instruction location info to have a segment register and handle %gs in kernel to look up a global variable. Pretend it as a global variable by changing the register number to DWARF_REG_PC. Signed-off-by: -
Namhyung Kim authored
Add a segment field in the struct annotated_insn_loc and save it for the segment based addressing like %gs:0x28. For simplicity it now handles %gs register only. Signed-off-by:
-
Namhyung Kim authored
As instruction tracking updates the type state for each register, check the final type info for the target register at the given instruction. Signed-off-by:
-
Namhyung Kim authored
If it failed to find a variable for the location directly, it might be due to a missing variable in the source code. For example, accessing pointer variables in a chain can result in the case like below: struct foo *foo = ...; int i = foo->bar->baz; The DWARF debug information is created for each variable so it'd have one for 'foo'. But there's no variable for 'foo->bar' and then it cannot know the type of 'bar' and 'baz'. The above source code can be compiled to the follow x86 instructions: mov 0x8(%rax), %rcx mov 0x4(%rcx), %rdx <=== PMU sample mov %rdx, -4(%rbp) Let's say 'foo' is located in the %rax and it has a pointer to struct foo. But perf sample is captured in the second instruction and there is no variable or type info for the %rcx. It'd be great if compiler could generate debug info for %rcx, but we should handle it on our side. So this patch implements the logic to iterate instructions and update the type table for each location. As it already collected a list of scopes including the target instruction, we can use it to construct the type table smartly. +---------------- scope[0] subprogram | | +-------------- scope[1] lexical_block | | | | +------------ scope[2] inlined_subroutine | | | | | | +---------- scope[3] inlined_subroutine | | | | | | | | +-------- scope[4] lexical_block | | | | | | | | | | *** target instruction ... Image the target instruction has 5 scopes, each scope will have its own variables and parameters. Then it can start with the innermost scope (4). So it'd search the shortest path from the start of scope[4] to the target address and build a list of basic blocks. Then it iterates the basic blocks with the variables in the scope and update the table. If it finds a type at the target instruction, then returns it. Otherwise, it moves to the upper scope[3]. Now it'd search the shortest path from the start of scope[3] to the start of scope[4]. Then connect it to the existing basic block list. Then it'd iterate the blocks with variables for both scopes. It can repeat this until it finds a type at the target instruction or reaches to the top scope[0]. As the basic blocks contain the shortest path, it won't worry about branches and can update the table simply. The final check will be done by find_matching_type() in the next patch. Signed-off-by:
-
Namhyung Kim authored
When updating instruction states, the call instruction should play a role since it changes the register states. For simplicity, mark some registers as caller-saved registers (should be arch-dependent), and invalidate them all after a function call. If the function returns something, the designated register (ret_reg) will have the type info. Signed-off-by:
-
Namhyung Kim authored
When updating the instruction states, it also needs to handle global variable accesses. Same as it does for PC-relative addressing, it can look up the type by address (if it's defined in the same file), or by name after finding the symbol by address (for declarations). Signed-off-by:
-
Namhyung Kim authored
Accessing global variable is common when it tracks execution later. Factor out the common code into a function for later use. It adds thread and cpumode to struct data_loc_info to find (global) symbols if needed. Also remove var_name as it's retrieved in the helper function. Signed-off-by:
-
