- 19 Apr, 2024 9 commits
-
-
Arnaldo Carvalho de Melo authored
This reverts commit a672af91. By now it is not used for building tools/perf, but Stephen Rothwell reported that when building on a O= directory that had been built with torvalds/master and this perf build command line: $ make -C tools/perf -f Makefile.perf -s -O -j60 O=/home/sfr/next/perf NO_BPF_SKEL=1 If we then merge perf-tools-next, as he did for linux-next, then we end up with a build failure for libbpf: PERF_VERSION = 6.9.rc3.g42c4635c8dee make[3]: *** No rule to make target '/home/sfr/next/next/tools/include/uapi/linux/stat.h', needed by '/home/sfr/next/perf/libbpf/staticobjs/libbpf.o'. Stop. make[2]: *** [Makefile:157: /home/sfr/next/perf/libbpf/staticobjs/libbpf-in.o] Error 2 make[1]: *** [Makefile.perf:892: /home/sfr/next/perf/libbpf/libbpf.a] Error 2 make[1]: *** Waiting for unfinished jobs.... make: *** [Makefile.perf:264: sub-make] Error 2 This needs to be further investigated to figure out how to check if libbpf really needs something that is in that tools/include/uapi/linux/stat.h file and if not to remove that file in a way that we don't break the build in any situation, to avoid requiring doing a 'make clean'. Reported-by:
Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Stephen Rothwell <sfr@canb.auug.org.au> # PowerPC le incermental build Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/20240413124340.4d48c6d8@canb.auug.org.auSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Dima Kogan authored
This is a common failure mode when probing userspace C++ code (where the mangling adds significant length to the symbol names). Prior to this patch, only a very generic error message is produced, making the user guess at what the issue is. Signed-off-by:
Dima Kogan <dima@secretsauce.net> Acked-by:
Masami Hiramatsu <mhiramat@kernel.org> Link: https://lore.kernel.org/r/20240416045533.162692-3-dima@secretsauce.netSigned-off-by:
-
Dima Kogan authored
In several places we had char buf[64]; ... snprintf(buf, 64, ...); This patch changes it to char buf[64]; ... snprintf(buf, sizeof(buf), ...); so the "64" is only stated once. Signed-off-by:
-
Weilin Wang authored
Hardware counter and event information could be used to help creating event groups that better utilize hardware counters and improve multiplexing. Reviewed-by:
Ian Rogers <irogers@google.com> Signed-off-by:
Weilin Wang <weilin.wang@intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.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> Link: https://lore.kernel.org/r/20240412210756.309828-2-weilin.wang@intel.comSigned-off-by:
-
James Clark authored
These tests record in a mode that includes kernel trace but look for samples of a userspace process. This makes them sensitive to any kernel compilation options that increase the amount of time spent in the kernel. If the trace buffer is completely filled before userspace is reached then the test will fail. Double the buffer size to fix this. The other tests in the same file aren't sensitive to this for various reasons, for example the iterate devices test filters by userspace trace only. But in order to keep coverage of all the modes, increase the buffer size rather than filtering by userspace for the basic tests. Fixes: d1efa4a0 ("perf cs-etm: Add separate decode paths for timeless and per-thread modes") Reviewed-by:
Anshuman Khandual <anshuman.khandual@arm.com> Signed-off-by:
James Clark <james.clark@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Link: https://lore.kernel.org/r/20240326113749.257250-1-james.clark@arm.comSigned-off-by:
-
Chen Pei authored
When cross-compiling perf with libelf, the following error occurred: In file included from tests/genelf.c:14: tests/../util/genelf.h:50:2: error: #error "unsupported architecture" 50 | #error "unsupported architecture" | ^~~~~ tests/../util/genelf.h:59:5: warning: "GEN_ELF_CLASS" is not defined, evaluates to 0 [-Wundef] 59 | #if GEN_ELF_CLASS == ELFCLASS64 Fix this by adding GEN-ELF-ARCH and GEN-ELF-CLASS definitions for rv32. Reviewed-by:
Chen Pei <cp0613@linux.alibaba.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Link: https://lore.kernel.org/r/20240415095532.4930-1-cp0613@linux.alibaba.comSigned-off-by:
-
Ilkka Koskinen authored
L1D_CACHE_INVAL overcounts in certain situations. See AC03_CPU_41 and AC04_CPU_1 for more details. Mark the event impacted by the errata. Reviewed-by:
Ilkka Koskinen <ilkka@os.amperecomputing.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20240408214022.541839-1-ilkka@os.amperecomputing.comSigned-off-by:
-
Ian Rogers authored
Refactor test to better enable sharing of logic, to give an idea of progress and introduce test functions. Add test of measuring both cycles and cycles:b simultaneously. Signed-off-by:
-
Ian Rogers authored
Document that 'b' is used as a modifier to make an event use a BPF counter. Fixes: 01bd8efc ("perf stat: Introduce ':b' modifier") Signed-off-by:
-
- 17 Apr, 2024 4 commits
-
-
Chaitanya S Prakash authored
Test "perf probe of function from different CU" fails due to certain configs not being enabled. Building the kernel with CONFIG_KPROBE_EVENTS=y and CONFIG_UPROBE_EVENTS=y fixes the issue. As CONFIG_KPROBE_EVENTS is dependent on CONFIG_KPROBES, enable it as well. Some platforms enable these configs as a part of their defconfig, so this change is only required for the ones that don't do so. Reviewed-by:
Chaitanya S Prakash <chaitanyas.prakash@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: James Clark <james.clark@arm.com> Link: https://lore.kernel.org/r/20240408062230.1949882-1-ChaitanyaS.Prakash@arm.com Link: https://lore.kernel.org/r/20240408062230.1949882-7-ChaitanyaS.Prakash@arm.comSigned-off-by:
-
Namhyung Kim authored
Add weight1, weight2 and weight3 fields to -F/--fields and their aliases like 'ins_lat', 'p_stage_cyc' and 'retire_lat'. Note that they are in the sort keys too but the difference is that output fields will sum up the weight values and display the average. In the sort key, users can see the distribution of weight value and I think it's confusing we have local vs. global weight for the same weight. For example, I experiment with mem-loads events to get the weights. On my laptop, it seems only weight1 field is supported. $ perf mem record -- perf test -w noploop Let's look at the noploop function only. It has 7 samples. $ perf script -F event,ip,sym,weight | grep noploop # event weight ip sym cpu/mem-loads,ldlat=30/P: 43 55b3c122bffc noploop cpu/mem-loads,ldlat=30/P: 48 55b3c122bffc noploop cpu/mem-loads,ldlat=30/P: 38 55b3c122bffc noploop <--- same weight cpu/mem-loads,ldlat=30/P: 38 55b3c122bffc noploop <--- same weight cpu/mem-loads,ldlat=30/P: 59 55b3c122bffc noploop cpu/mem-loads,ldlat=30/P: 33 55b3c122bffc noploop cpu/mem-loads,ldlat=30/P: 38 55b3c122bffc noploop <--- same weight When you use the 'weight' sort key, it'd show entries with a separate weight value separately. Also note that the first entry has 3 samples with weight value 38, so they are displayed together and the weight value is the sum of 3 samples (114 = 38 * 3). $ perf report -n -s +weight | grep -e Weight -e noploop # Overhead Samples Command Shared Object Symbol Weight 0.53% 3 perf perf [.] noploop 114 0.18% 1 perf perf [.] noploop 59 0.18% 1 perf perf [.] noploop 48 0.18% 1 perf perf [.] noploop 43 0.18% 1 perf perf [.] noploop 33 If you use 'local_weight' sort key, you can see the actual weight. $ perf report -n -s +local_weight | grep -e Weight -e noploop # Overhead Samples Command Shared Object Symbol Local Weight 0.53% 3 perf perf [.] noploop 38 0.18% 1 perf perf [.] noploop 59 0.18% 1 perf perf [.] noploop 48 0.18% 1 perf perf [.] noploop 43 0.18% 1 perf perf [.] noploop 33 But when you use the -F/--field option instead, you can see the average weight for the while noploop function (as it won't group samples by weight value and use the default 'comm,dso,sym' sort keys). $ perf report -n -F +weight | grep -e Weight -e noploop Warning: --fields weight shows the average value unlike in the --sort key. # Overhead Samples Weight1 Command Shared Object Symbol 1.23% 7 42.4 perf perf [.] noploop The weight1 field shows the average value: (38 * 3 + 59 + 48 + 43 + 33) / 7 = 42.4 Also it'd show the warning that 'weight' field has the average value. Using 'weight1' can remove the warning. Signed-off-by:Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20240411181718.2367948-3-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
Like period and sample numbers, it'd be better to track weight values and display them in the output rather than having them as sort keys. This patch just adds a few more fields to save the weights in a hist entry. It'll be displayed as new output fields in the later patch. Signed-off-by:
-
Namhyung Kim authored
It's strange that sort.h has the definition of struct hist_entry. As sort.h already includes hist.h, let's move the data structure to hist.h. Signed-off-by:
-
- 16 Apr, 2024 4 commits
-
-
Namhyung Kim authored
In some cases, the stack pointer on x86 (rsp = reg7) is used to point variables on stack but it's not the frame base register. Then it should handle the register like normal registers (IOW not to access the other stack variables using offset calculation) but it should not assume it would have a pointer. Before: ----------------------------------------------------------- find data type for 0x7c(reg7) at tcp_getsockopt+0xb62 CU for net/ipv4/tcp.c (die:0x7b5f516) frame base: cfa=0 fbreg=6 no pointer or no type check variable "zc" failed (die: 0x7b9580a) variable location: base=reg7, offset=0x40 type='struct tcp_zerocopy_receive' size=0x40 (die:0x7b947f4) After: ----------------------------------------------------------- find data type for 0x7c(reg7) at tcp_getsockopt+0xb62 CU for net/ipv4/tcp.c (die:0x7b5f516) frame base: cfa=0 fbreg=6 found "zc" in scope=3/3 (die: 0x7b957fc) type_offset=0x3c variable location: base=reg7, offset=0x40 type='struct tcp_zerocopy_receive' size=0x40 (die:0x7b947f4) Note that the type-offset was properly calculated to 0x3c as the variable starts at 0x40. Signed-off-by:
-
Namhyung Kim authored
In match_var_offset(), it just checked the end address of the variable with the given offset because it assumed the register holds a pointer to the data type and the offset starts from the base. But I found some cases that the stack pointer (rsp = reg7) register is used to pointer a stack variable while the frame base is maintained by a different register (rbp = reg6). In that case, it cannot simply use the stack pointer as it cannot guarantee that it points to the frame base. So it needs to check both boundaries of the variable location. Before: ----------------------------------------------------------- find data type for 0x7c(reg7) at tcp_getsockopt+0xb62 CU for net/ipv4/tcp.c (die:0x7b5f516) frame base: cfa=0 fbreg=6 no pointer or no type check variable "tss" failed (die: 0x7b95801) variable location: base reg7, offset=0x110 type='struct scm_timestamping_internal' size=0x30 (die:0x7b8c126) So the current code just checks register number for the non-PC and non-FB registers and assuming it has offset 0. But this variable has offset 0x110 so it should not match to this. After: ----------------------------------------------------------- find data type for 0x7c(reg7) at tcp_getsockopt+0xb62 CU for net/ipv4/tcp.c (die:0x7b5f516) frame base: cfa=0 fbreg=6 no pointer or no type check variable "zc" failed (die: 0x7b9580a) variable location: base=reg7, offset=0x40 type='struct tcp_zerocopy_receive' size=0x40 (die:7b947f4) Now it find the correct variable "zc". It was located at reg7 + 0x40 and the size if 0x40 which means it should cover [0x40, 0x80). And the access was for reg7 + 0x7c so it found the right one. But it still failed to use the variable and it would be handled in the next patch. Signed-off-by:
-
Namhyung Kim authored
In match_var_offset(), it checks the offset range with the target type only for non-pointer types. But it also needs to check the pointer types with the target type. This is because there can be more than one pointer variable located in the same register. Let's look at the following example. It's looking up a variable for reg3 at tcp_get_info+0x62. It found "sk" variable but it wasn't the right one since it accesses beyond the target type (struct 'sock' in this case) size. ----------------------------------------------------------- find data type for 0x7bc(reg3) at tcp_get_info+0x62 CU for net/ipv4/tcp.c (die:0x7b5f516) frame base: cfa=0 fbreg=6 offset: 1980 is bigger than size: 760 check variable "sk" failed (die: 0x7b92b2c) variable location: reg3 type='struct sock' size=0x2f8 (die:0x7b63c3ab) Actually there was another variable "tp" in the function and it's located at the same (reg3) because it's just type-casted like below. void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); ... The 'struct tcp_sock' contains the 'struct sock' at offset 0 so it can just use the same address as a pointer to tcp_sock. That means it should match variables correctly by checking the offset and size. Actually it cannot distinguish if the offset was smaller than the size of the original struct sock. But I think it's fine as they are the same at that part. So let's check the target type size and retry if it doesn't match. Now it succeeded to find the correct variable. ----------------------------------------------------------- find data type for 0x7bc(reg3) at tcp_get_info+0x62 CU for net/ipv4/tcp.c (die:0x7b5f516) frame base: cfa=0 fbreg=6 found "tp" in scope=1/1 (die: 0x7b92b16) type_offset=0x7bc variable location: reg3 type='struct tcp_sock' size=0xa68 (die:0x7b81380) Fixes: bc10db8e ("perf annotate-data: Support stack variables") Signed-off-by:
-
Namhyung Kim authored
To verify it found the correct variable, let's add the location expression to the debug message. $ perf --debug type-profile annotate --data-type ... ----------------------------------------------------------- find data type for 0xaf0(reg15) at schedule+0xeb CU for kernel/sched/core.c (die:0x1180523) frame base: cfa=0 fbreg=6 found "rq" in scope=3/4 (die: 0x11b6a00) type_offset=0xaf0 variable location: reg15 type='struct rq' size=0xfc0 (die:0x11892e2) ----------------------------------------------------------- find data type for 0x7bc(reg3) at tcp_get_info+0x62 CU for net/ipv4/tcp.c (die:0x7b5f516) frame base: cfa=0 fbreg=6 offset: 1980 is bigger than size: 760 check variable "sk" failed (die: 0x7b92b2c) variable location: reg3 type='struct sock' size=0x2f8 (die:0x7b63c3ab) ----------------------------------------------------------- ... The first case is fine. It looked up a data type in r15 with offset of 0xaf0 at schedule+0xeb. It found the CU die and the frame base info and the variable "rq" was found in the scope 3/4. Its location is the r15 register and the type size is 0xfc0 which includes 0xaf0. But the second case is not good. It looked up a data type in rbx (reg3) with offset 0x7bc. It found a CU and the frame base which is good so far. And it also found a variable "sk" but the access offset is bigger than the type size (1980 vs. 760 or 0x7bc vs. 0x2f8). The variable has the right location (reg3) but I need to figure out why it accesses beyond what it's supposed to. Signed-off-by:
-
- 12 Apr, 2024 23 commits
-
-
Ian Rogers authored
Name benchmarks with _ret at the end to avoid creating a new set of benchmarks. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andrei Vagin <avagin@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kees Kook <keescook@chromium.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20240406040911.1603801-2-irogers@google.comSigned-off-by:
-
Ian Rogers authored
bpf_program__attach_uprobe_opts will search LD_LIBRARY_PATH and so specifying `/lib64` is unnecessary and causes failures for libc.so.6 paths like `/lib/x86_64-linux-gnu/libc.so.6`. Fixes: 7b47623b ("perf bench uprobe trace_printk: Add entry attaching an BPF program that does a trace_printk") Signed-off-by:
-
Ian Rogers authored
Add shell check to scripts generating perf trace lookup tables. Fix quoting issue in arch_errno_names.sh. Reviewed-by:
-
Ian Rogers authored
Add shellcheck to generate-cmdlist.sh to avoid basic shell script mistakes. Reviewed-by:
-
Ian Rogers authored
Add shellcheck for: tools/perf/arch/x86/tests/gen-insn-x86-dat.sh tools/perf/arch/x86/entry/syscalls/syscalltbl.sh Address a minor quoting issue. Reviewed-by:
-
Ian Rogers authored
Address shell check errors/warnings in perf-archive.sh and perf-completion.sh. Reviewed-by:
-
Ian Rogers authored
Events like for sapphirerapids have '\r' in the uncore descriptions. The non-escaped versions of this fail JSON validation the the 'perf list' test. Signed-off-by:
-
Ian Rogers authored
Switch loops within dsos.c, add a version that isn't locked. Switch some unlocked loops to hold the read lock. Signed-off-by:
-
Ian Rogers authored
Move dso and dso_id functions to dso.c to match the struct declarations. Signed-off-by:
-
Ian Rogers authored
To better abstract the dsos internals, introduce dsos__for_each_dso that does a callback on each dso. This also means the read lock can be correctly held. Signed-off-by:
-
Ian Rogers authored
Move more functionality into dsos.c generally from machine.c, renaming functions to match their new usage. The find function is made to always "get" before returning a dso. Reduce the scope of locks in vdso to match the locking paradigm. Signed-off-by:
-
Ian Rogers authored
Move functions from machine and build-id to dsos. Pass 'struct dsos' rather than internal state. Rename some functions to better represent which data structure they operate on. Signed-off-by:
-
Adrian Hunter authored
evlist__config() might mess up the debug output consumed by test "Test per-thread recording" in "Miscellaneous Intel PT testing". Move it out from between the debug prints: "perf record opening and mmapping events" and "perf record done opening and mmapping events" Fixes: da406202 ("perf tools: Add debug messages and comments for testing") Closes: https://lore.kernel.org/linux-perf-users/ZhVfc5jYLarnGzKa@x1/Reported-by:
Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by:
Adrian Hunter <adrian.hunter@intel.com> Tested-by:
-
Namhyung Kim authored
In some data file, I see the following messages repeated. It seems it doesn't have DSOs in the system and the dso->binary_type is set to DSO_BINARY_TYPE__NOT_FOUND. Let's skip them to avoid the followings. No output from objdump --start-address=0x0000000000000000 --stop-address=0x00000000000000d4 -d --no-show-raw-insn -C "$1" Error running objdump --start-address=0x0000000000000000 --stop-address=0x0000000000000631 -d --no-show-raw-insn -C "$1" ... Closes: https://lore.kernel.org/linux-perf-users/15e1a2847b8cebab4de57fc68e033086aa6980ce.camel@yandex.ru/Reported-by:
Konstantin Kharlamov <Hi-Angel@yandex.ru> Reviewed-by:
-
Namhyung Kim authored
The data type profiling alone doesn't need the sample histogram for functions. It only needs the histogram for the types. Let's remove the condition in the report_callback to check if data type profiling is selected and make sure the annotation has the 'struct annotated_source' instantiated before calling symbol__disassemble(). Reviewed-by:
-
Namhyung Kim authored
When the hist entry has the type info, it should be able to display the annotation browser for the type like in `perf annotate --data-type`. Reviewed-by:
-
Namhyung Kim authored
Like in stdio, it should print all events in a group together. Committer notes: Collect it: root@number:~# perf record -a -e '{cpu_core/mem-loads,ldlat=30/P,cpu_core/mem-stores/P}' ^C[ perf record: Woken up 8 times to write data ] [ perf record: Captured and wrote 4.980 MB perf.data (55825 samples) ] root@number:~# Then do it in stdio: root@number:~# perf annotate --stdio --data-type Annotate type: 'union ' in /usr/lib64/libc.so.6 (1131 samples): event[0] = cpu_core/mem-loads,ldlat=30/P event[1] = cpu_core/mem-stores/P ============================================================================ Percent offset size field 100.00 100.00 0 40 union { 100.00 100.00 0 40 struct __pthread_mutex_s __data { 48.61 23.46 0 4 int __lock; 0.00 0.48 4 4 unsigned int __count; 6.38 41.32 8 4 int __owner; 8.74 34.02 12 4 unsigned int __nusers; 35.66 0.26 16 4 int __kind; 0.61 0.45 20 2 short int __spins; 0.00 0.00 22 2 short int __elision; 0.00 0.00 24 16 __pthread_list_t __list { 0.00 0.00 24 8 struct __pthread_internal_list* __prev; 0.00 0.00 32 8 struct __pthread_internal_list* __next; }; }; 0.00 0.00 0 0 char* __size; 48.61 23.94 0 8 long int __align; }; Now with TUI before this patch: root@number:~# perf annotate --tui --data-type Annotate type: 'union ' (790 samples) Percent Offset Size Field 100.00 0 40 union { 100.00 0 40 struct __pthread_mutex_s __data { 48.61 0 4 int __lock; 0.00 4 4 unsigned int __count; 6.38 8 4 int __owner; 8.74 12 4 unsigned int __nusers; 35.66 16 4 int __kind; 0.61 20 2 short int __spins; 0.00 22 2 short int __elision; 0.00 24 16 __pthread_list_t __list { 0.00 24 8 struct __pthread_internal_list* __prev; 0.00 32 8 struct __pthread_internal_list* __next; 0.00 0 0 char* __size; 48.61 0 8 long int __align; }; And now after this patch: Annotate type: 'union ' (790 samples) Percent Offset Size Field 100.00 100.00 0 40 union { 100.00 100.00 0 40 struct __pthread_mutex_s __data { 48.61 23.46 0 4 int __lock; 0.00 0.48 4 4 unsigned int __count; 6.38 41.32 8 4 int __owner; 8.74 34.02 12 4 unsigned int __nusers; 35.66 0.26 16 4 int __kind; 0.61 0.45 20 2 short int __spins; 0.00 0.00 22 2 short int __elision; 0.00 0.00 24 16 __pthread_list_t __list { 0.00 0.00 24 8 struct __pthread_internal_list* __prev; 0.00 0.00 32 8 struct __pthread_internal_list* __next; }; }; 0.00 0.00 0 0 char* __size; 48.61 23.94 0 8 long int __align; }; On a followup patch the --tui output should have this that is present in --stdio: And the --stdio has all the missing info in TUI: Annotate type: 'union ' in /usr/lib64/libc.so.6 (1131 samples): event[0] = cpu_core/mem-loads,ldlat=30/P event[1] = cpu_core/mem-stores/P Reviewed-by: -
Namhyung Kim authored
Support data type profiling output on TUI. Testing from Arnaldo: First make sure that the debug information for your workload binaries in embedded in them by building it with '-g' or install the debuginfo packages, since our workload is 'find': root@number:~# type find find is hashed (/usr/bin/find) root@number:~# rpm -qf /usr/bin/find findutils-4.9.0-5.fc39.x86_64 root@number:~# dnf debuginfo-install findutils <SNIP> root@number:~# Then collect some data: root@number:~# echo 1 > /proc/sys/vm/drop_caches root@number:~# perf mem record find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.331 MB perf.data (3982 samples) ] root@number:~# Finally do data-type annotation with the following command, that will default, as 'perf report' to the --tui mode, with lines colored to highlight the hotspots, etc. root@number:~# perf annotate --data-type Annotate type: 'struct predicate' (58 samples) Percent Offset Size Field 100.00 0 312 struct predicate { 0.00 0 8 PRED_FUNC pred_func; 0.00 8 8 char* p_name; 0.00 16 4 enum predicate_type p_type; 0.00 20 4 enum predicate_precedence p_prec; 0.00 24 1 _Bool side_effects; 0.00 25 1 _Bool no_default_print; 0.00 26 1 _Bool need_stat; 0.00 27 1 _Bool need_type; 0.00 28 1 _Bool need_inum; 0.00 32 4 enum EvaluationCost p_cost; 0.00 36 4 float est_success_rate; 0.00 40 1 _Bool literal_control_chars; 0.00 41 1 _Bool artificial; 0.00 48 8 char* arg_text; <SNIP> Reviewed-by: -
Namhyung Kim authored
And move the related code into util/annotate-data.c file. Reviewed-by:
-
Namhyung Kim authored
Like 'perf report', it can take a while to process samples. Show a progress window to inform users how that it is not stuck. Reviewed-by:
-
Namhyung Kim authored
It's a pseudo data type and has no field. Fixes: b3c95109 ("perf annotate-data: Add stack canary type") Closes: https://lore.kernel.org/lkml/Zhb6jJneP36Z-or0@x1Reported-by:
-
James Clark authored
This check can be done with uname which is more portable. At the same time re-arrange it into a standard if statement so that it's more readable. Reviewed-by:
-
James Clark authored
In a debug build there is validation that mmap lists are sorted when taking a lock. In machine__update_kernel_mmap() the start and end addresses are updated resulting in an unsorted list before the map is removed from the list. When the map is removed, the lock is taken which triggers the validation and the failure: $ perf test "object code reading" --- start --- perf: util/maps.c:88: check_invariants: Assertion `map__start(prev) <= map__start(map)' failed. Aborted Fix it by updating the addresses after removal, but before insertion. The bug depends on the ordering and type of debug info on the system and doesn't reproduce everywhere. Fixes: 659ad349 ("perf maps: Switch from rbtree to lazily sorted array for addresses") Reviewed-by:
-
