kernel/linux.git/tools/perf/builtin-annotate.c, branch v6.12.80

perf annotate: Display the branch counter histogram

2024-08-14T13:20:40+00:00

Display the branch counter histogram in the annotation view. Press 'B' to display the branch counter's abbreviation list as well. Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }', 4000 Hz, Event count (approx.): f3 /home/sdp/test/tchain_edit [Percent: local period] Percent │ IPC Cycle Branch Counter (Average IPC: 1.39, IPC Coverage: 29.4%) │ 0000000000401755 : 0.00 0.00 │ endbr64 │ push %rbp │ mov %rsp,%rbp │ movl $0x0,-0x4(%rbp) 0.00 0.00 │1.33 3 |A |- | ↓ jmp 25 11.03 11.03 │ 11: mov -0x4(%rbp),%eax │ and $0x1,%eax │ test %eax,%eax 17.13 17.13 │2.41 1 |A |- | ↓ je 21 │ addl $0x1,-0x4(%rbp) 21.84 21.84 │2.22 2 |AA |- | ↓ jmp 25 17.13 17.13 │ 21: addl $0x1,-0x4(%rbp) 21.84 21.84 │ 25: cmpl $0x270f,-0x4(%rbp) 11.03 11.03 │0.61 3 |A |- | ↑ jle 11 │ nop │ pop %rbp 0.00 0.00 │0.24 20 |AA |B | ← ret Originally-by: Tinghao Zhang Reviewed-by: Andi Kleen Signed-off-by: Kan Liang Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/r/20240813160208.2493643-8-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Save branch counters for each block

2024-08-14T13:20:40+00:00

When annotating a basic block, it's useful to display the occurrences of other events in the block. The branch counter feature is only available for newer Intel platforms. So a dedicated option to display the branch counters is not introduced. Reuse the existing --total-cycles option, which triggers the annotation of a basic block and displays the cycle-related annotation. When the branch counters information is available, the branch counters are automatically appended after all the cycle-related annotation. Accounting the branch counters as well when accounting the cycles in hist__account_cycles(). In 'struct annotated_branch', introduce a br_cntr array to save the accumulation of each branch counter. In a sample, all the branch counters for a branch are saved in a u64 space. Because the saturation of a branch counter is small, e.g., for Intel Sierra Forest, the saturation is only 3. Add ANNOTATION__BR_CNTR_SATURATED_FLAG to indicate if a branch counter once saturated. That can be used to indicate a potential event lost because of the saturation. Reviewed-by: Andi Kleen Signed-off-by: Kan Liang Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/r/20240813160208.2493643-5-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Use perf_tool__init()

2024-08-12T21:11:10+00:00

Use perf_tool__init() so that more uses of 'struct perf_tool' can be const and not relying on perf_tool__fill_defaults(). Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Anshuman Khandual Cc: Athira Rajeev Cc: Huacai Chen Cc: Ilkka Koskinen Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Jonathan Cameron Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Nick Desaulniers Cc: Nick Terrell Cc: Oliver Upton Cc: Peter Zijlstra Cc: Song Liu Cc: Sun Haiyong Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yanteng Si Cc: Yicong Yang Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20240812204720.631678-18-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf tool: Constify tool pointers

2024-08-12T21:05:14+00:00

The tool pointer (to a struct largely of function pointers) is passed around but is unchanged except at initialization. Change parameter and variable types to be const to lower the possibilities of what could happen with a tool. Reviewed-by: Adrian Hunter Signed-off-by: Ian Rogers Tested-by: Adrian Hunter Tested-by: Leo Yan Cc: Alexander Shishkin Cc: Anshuman Khandual Cc: Athira Rajeev Cc: Huacai Chen Cc: Ilkka Koskinen Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Jonathan Cameron Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Nick Desaulniers Cc: Nick Terrell Cc: Oliver Upton Cc: Peter Zijlstra Cc: Song Liu Cc: Sun Haiyong Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yanteng Si Cc: Yicong Yang Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20240812204720.631678-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Fix --group behavior when leader has no samples

2024-08-09T21:12:29+00:00

When --group option is used, it should display all events together. But the current logic only checks if the first (leader) event has samples or not. Let's check the member events as well. Also it missed to put the linked samples from member evsels to the output RB-tree so that it can be displayed in the output. For example, take a look at this example. $ ./perf evlist cpu/mem-loads,ldlat=30/P cpu/mem-stores/P dummy:u It has three events but 'path_put' function has samples only for mem-stores (second) event. $ sudo ./perf annotate --stdio -f path_put Percent | Source code & Disassembly of kcore for cpu/mem-stores/P (2 samples, percent: local period) ---------------------------------------------------------------------------------------------------------- : 0 0xffffffffae600020 : 0.00 : ffffffffae600020: endbr64 0.00 : ffffffffae600024: nopl (%rax, %rax) 91.22 : ffffffffae600029: pushq %rbx 0.00 : ffffffffae60002a: movq %rdi, %rbx 0.00 : ffffffffae60002d: movq 8(%rdi), %rdi 8.78 : ffffffffae600031: callq 0xffffffffae614aa0 0.00 : ffffffffae600036: movq (%rbx), %rdi 0.00 : ffffffffae600039: popq %rbx 0.00 : ffffffffae60003a: jmp 0xffffffffae620670 0.00 : ffffffffae60003f: nop Therefore, it didn't show up when --group option is used since the leader ("mem-loads") event has no samples. But now it checks both events. Before: $ sudo ./perf annotate --stdio -f --group path_put (no output) After: $ sudo ./perf annotate --stdio -f --group path_put Percent | Source code & Disassembly of kcore for cpu/mem-loads,ldlat=30/P, cpu/mem-stores/P, dummy:u (0 samples, percent: local period) ------------------------------------------------------------------------------------------------------------------------------------------------------------- : 0 0xffffffffae600020 : 0.00 0.00 0.00 : ffffffffae600020: endbr64 0.00 0.00 0.00 : ffffffffae600024: nopl (%rax, %rax) 0.00 91.22 0.00 : ffffffffae600029: pushq %rbx 0.00 0.00 0.00 : ffffffffae60002a: movq %rdi, %rbx 0.00 0.00 0.00 : ffffffffae60002d: movq 8(%rdi), %rdi 0.00 8.78 0.00 : ffffffffae600031: callq 0xffffffffae614aa0 0.00 0.00 0.00 : ffffffffae600036: movq (%rbx), %rdi 0.00 0.00 0.00 : ffffffffae600039: popq %rbx 0.00 0.00 0.00 : ffffffffae60003a: jmp 0xffffffffae620670 0.00 0.00 0.00 : ffffffffae60003f: nop Committer testing: Before: root@number:~# perf annotate --group --stdio2 clear_page_erms root@number:~# After: root@number:~# perf annotate --group --stdio2 clear_page_erms Samples: 125 of events 'cpu_atom/mem-loads,ldlat=30/P, cpu_atom/mem-stores/P, dummy:u', 4000 Hz, Event count (approx.): 13198416, [percent: local period] clear_page_erms() /proc/kcore Percent 0xffffffff990c6cc0 : endbr64 movl $0x1000,%ecx xorl %eax,%eax 0.00 100.00 0.00 rep stosb %al, (%rdi) ← retq int3 int3 int3 int3 nop nop root@number:~# Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20240807061555.1642669-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Add --skip-empty option

2024-08-05T19:14:01+00:00

Like in 'perf report', we want to hide empty events in the 'perf annotate' output. This is consistent when the option is set in perf report. For example, the following command would use 3 events including dummy. $ perf mem record -a -- perf test -w noploop $ perf evlist cpu/mem-loads,ldlat=30/P cpu/mem-stores/P dummy:u Just using perf annotate with --group will show the all 3 events. $ perf annotate --group --stdio | head Percent | Source code & Disassembly of ... -------------------------------------------------------------- : 0 0xe060 <_dl_relocate_object>: 0.00 0.00 0.00 : e060: pushq %rbp 0.00 0.00 0.00 : e061: movq %rsp, %rbp 0.00 0.00 0.00 : e064: pushq %r15 0.00 0.00 0.00 : e066: movq %rdi, %r15 0.00 0.00 0.00 : e069: pushq %r14 0.00 0.00 0.00 : e06b: pushq %r13 0.00 0.00 0.00 : e06d: movl %edx, %r13d Now with --skip-empty, it'll hide the last dummy event. $ perf annotate --group --stdio --skip-empty | head Percent | Source code & Disassembly of ... ------------------------------------------------------ : 0 0xe060 <_dl_relocate_object>: 0.00 0.00 : e060: pushq %rbp 0.00 0.00 : e061: movq %rsp, %rbp 0.00 0.00 : e064: pushq %r15 0.00 0.00 : e066: movq %rdi, %r15 0.00 0.00 : e069: pushq %r14 0.00 0.00 : e06b: pushq %r13 0.00 0.00 : e06d: movl %edx, %r13d Committer testing: root@x1:~# perf evlist cpu_atom/mem-loads,ldlat=30/P cpu_atom/mem-stores/P dummy:u root@x1:~# Before: root@x1:~# perf annotate --group --stdio2 do_lookup_x | head -25 Samples: 20 of events 'cpu_atom/mem-loads,ldlat=30/P, cpu_atom/mem-stores/P, dummy:u', 4000 Hz, Event count (approx.): 769079, [percent: local period] do_lookup_x() /usr/lib64/ld-linux-x86-64.so.2 Percent 0x9900 : pushq %rbp movq %rsp,%rbp pushq %r15 pushq %r14 pushq %r13 pushq %r12 pushq %rbx subq $0x88,%rsp movq %rdi,-0x50(%rbp) movl 8(%r9),%edi movq 0x10(%rbp),%r12 movq 0x28(%rbp),%r10 movq %rdx,-0x70(%rbp) movq %rcx,-0x58(%rbp) movq %rdi,%r11 0.00 5.73 0.00 movq %r8,-0x68(%rbp) movq (%r9),%r8 movl %esi,%eax 8.30 0.00 0.00 movl 0x30(%rbp),%r9d movl %esi,%r15d shrl $6, %eax movq %r8,%r13 root@x1:~# After: root@x1:~# perf annotate --group --skip-empty --stdio2 do_lookup_x | head -25 Samples: 20 of events 'cpu_atom/mem-loads,ldlat=30/P, cpu_atom/mem-stores/P', 4000 Hz, Event count (approx.): 769079, [percent: local period] do_lookup_x() /usr/lib64/ld-linux-x86-64.so.2 Percent 0x9900 : pushq %rbp movq %rsp,%rbp pushq %r15 pushq %r14 pushq %r13 pushq %r12 pushq %rbx subq $0x88,%rsp movq %rdi,-0x50(%rbp) movl 8(%r9),%edi movq 0x10(%rbp),%r12 movq 0x28(%rbp),%r10 movq %rdx,-0x70(%rbp) movq %rcx,-0x58(%rbp) movq %rdi,%r11 0.00 5.73 movq %r8,-0x68(%rbp) movq (%r9),%r8 movl %esi,%eax 8.30 0.00 movl 0x30(%rbp),%r9d movl %esi,%r15d shrl $6, %eax movq %r8,%r13 root@x1:~# Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240803211332.1107222-6-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Set instruction name to be used with insn-stat when using raw instruction

2024-07-31T19:12:59+00:00

Since the "ins.name" is not set while using raw instruction, 'perf annotate' with insn-stat gives wrong data: Result from "./perf annotate --data-type --insn-stat": Annotate Instruction stats total 615, ok 419 (68.1%), bad 196 (31.9%) Name : Good Bad ----------------------------------------------------------- : 419 196 This patch sets "dl->ins.name" in arch specific function "check_ppc_insn" while initialising "struct disasm_line". Also update "ins_find" function to pass "struct disasm_line" as a parameter so as to set its name field in arch specific call. With the patch changes: Annotate Instruction stats total 609, ok 446 (73.2%), bad 163 (26.8%) Name/opcode : Good Bad ----------------------------------------------------------- 58 : 323 80 32 : 49 43 34 : 33 11 OP_31_XOP_LDX : 8 20 40 : 23 0 OP_31_XOP_LWARX : 5 1 OP_31_XOP_LWZX : 2 3 OP_31_XOP_LDARX : 3 0 33 : 0 2 OP_31_XOP_LBZX : 0 1 OP_31_XOP_LWAX : 0 1 OP_31_XOP_LHZX : 0 1 Reviewed-by: Kajol Jain Reviewed-by: Namhyung Kim Signed-off-by: Athira Rajeev Tested-by: Kajol Jain Cc: Adrian Hunter Cc: Akanksha J N Cc: Christophe Leroy Cc: Disha Goel Cc: Hari Bathini Cc: Ian Rogers Cc: Jiri Olsa Cc: Madhavan Srinivasan Cc: Segher Boessenkool Link: https://lore.kernel.org/lkml/20240718084358.72242-16-atrajeev@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo

perf hist: Add symbol_conf.skip_empty

2024-06-16T04:04:04+00:00

Add the skip_empty flag to symbol_conf and set the value from the report command to preserve the existing behavior. This makes the code simpler and will be needed other code which is hard to add a new argument. Tested-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Link: https://lore.kernel.org/r/20240607202918.2357459-4-namhyung@kernel.org

perf dso: Add reference count checking and accessor functions

2024-05-06T18:28:49+00:00

Add reference count checking to struct dso, this can help with implementing correct reference counting discipline. To avoid RC_CHK_ACCESS everywhere, add accessor functions for the variables in struct dso. The majority of the change is mechanical in nature and not easy to split up. Committer testing: 'perf test' up to this patch shows no regressions. But: util/symbol.c: In function ‘dso__load_bfd_symbols’: util/symbol.c:1683:9: error: too few arguments to function ‘dso__set_adjust_symbols’ 1683 | dso__set_adjust_symbols(dso); | ^~~~~~~~~~~~~~~~~~~~~~~ In file included from util/symbol.c:21: util/dso.h:268:20: note: declared here 268 | static inline void dso__set_adjust_symbols(struct dso *dso, bool val) | ^~~~~~~~~~~~~~~~~~~~~~~ make[6]: *** [/home/acme/git/perf-tools-next/tools/build/Makefile.build:106: /tmp/tmp.ZWHbQftdN6/util/symbol.o] Error 1 MKDIR /tmp/tmp.ZWHbQftdN6/tests/workloads/ make[6]: *** Waiting for unfinished jobs.... This was updated: - symbols__fixup_end(&dso->symbols, false); - symbols__fixup_duplicate(&dso->symbols); - dso->adjust_symbols = 1; + symbols__fixup_end(dso__symbols(dso), false); + symbols__fixup_duplicate(dso__symbols(dso)); + dso__set_adjust_symbols(dso); But not build tested with BUILD_NONDISTRO and libbfd devel files installed (binutils-devel on fedora). Add the missing argument: symbols__fixup_end(dso__symbols(dso), false); symbols__fixup_duplicate(dso__symbols(dso)); - dso__set_adjust_symbols(dso); + dso__set_adjust_symbols(dso, true); Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ahelenia Ziemiańska Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Ben Gainey Cc: Changbin Du Cc: Chengen Du Cc: Colin Ian King Cc: Dima Kogan Cc: Ilkka Koskinen Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: K Prateek Nayak Cc: Kan Liang Cc: Leo Yan Cc: Li Dong Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Paran Lee Cc: Peter Zijlstra Cc: Song Liu Cc: Sun Haiyong Cc: Thomas Richter Cc: Tiezhu Yang Cc: Yanteng Si Cc: zhaimingbing Link: https://lore.kernel.org/r/20240504213803.218974-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Fix data type profiling on stdio

2024-04-27T01:13:10+00:00

The loop in hists__find_annotations() never set the 'nd' pointer to NULL and it makes stdio output repeating the last element forever. I think it doesn't set to NULL for TUI to prevent it from exiting unexpectedly. But it should just set on stdio mode. Fixes: d001c7a7f4736743 ("perf annotate-data: Add hist_entry__annotate_data_tui()") Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240423020643.740029-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo