pm24.git/tools/perf, branch rust-6.13

move asm/unaligned.h to linux/unaligned.h

2024-10-02T21:23:23Z

asm/unaligned.h is always an include of asm-generic/unaligned.h; might as well move that thing to linux/unaligned.h and include that - there's nothing arch-specific in that header. auto-generated by the following: for i in `git grep -l -w asm/unaligned.h`; do sed -i -e "s/asm\/unaligned.h/linux\/unaligned.h/" $i done for i in `git grep -l -w asm-generic/unaligned.h`; do sed -i -e "s/asm-generic\/unaligned.h/linux\/unaligned.h/" $i done git mv include/asm-generic/unaligned.h include/linux/unaligned.h git mv tools/include/asm-generic/unaligned.h tools/include/linux/unaligned.h sed -i -e "/unaligned.h/d" include/asm-generic/Kbuild sed -i -e "s/__ASM_GENERIC/__LINUX/" include/linux/unaligned.h tools/include/linux/unaligned.h

perf trace: Mark the 'head' arg in the set_robust_list syscall as coming from user space

2024-09-11T20:25:45Z

With that it uses the generic BTF based pretty printer: This one we need to think about, not being acquainted with this syscall, should we _traverse_ that list somehow? Would that be useful? root@number:~# perf trace -e set_robust_list sleep 1 0.000 ( 0.004 ms): sleep/1206493 set_robust_list(head: (struct robust_list_head){.list = (struct robust_list){.next = (struct robust_list *)0x7f48a9a02a20,},.futex_offset = (long int)-32,}, len: 24) = root@number:~# strace prints the default integer args: root@number:~# strace -e set_robust_list sleep 1 set_robust_list(0x7efd99559a20, 24) = 0 +++ exited with 0 +++ root@number:~# Cc: Adrian Hunter Cc: Alan Maguire Cc: Howard Chu Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim

perf trace: Mark the 'rseq' arg in the rseq syscall as coming from user space

2024-09-11T20:05:23Z

With that it uses the generic BTF based pretty printer: root@number:~# grep -w rseq /sys/kernel/tracing/events/syscalls/sys_enter_rseq/format field:struct rseq * rseq; offset:16; size:8; signed:0; print fmt: "rseq: 0x%08lx, rseq_len: 0x%08lx, flags: 0x%08lx, sig: 0x%08lx", ((unsigned long)(REC->rseq)), ((unsigned long)(REC->rseq_len)), ((unsigned long)(REC->flags)), ((unsigned long)(REC->sig)) root@number:~# Before: root@number:~# perf trace -e rseq 0.000 ( 0.017 ms): Isolated Web C/1195452 rseq(rseq: 0x7ff0ecfe6fe0, rseq_len: 32, sig: 1392848979) = 0 74.018 ( 0.006 ms): :1195453/1195453 rseq(rseq: 0x7f2af20fffe0, rseq_len: 32, sig: 1392848979) = 0 1817.220 ( 0.009 ms): Isolated Web C/1195454 rseq(rseq: 0x7f5c9ec7dfe0, rseq_len: 32, sig: 1392848979) = 0 2515.526 ( 0.034 ms): :1195455/1195455 rseq(rseq: 0x7f61503fffe0, rseq_len: 32, sig: 1392848979) = 0 ^Croot@number:~# After: root@number:~# perf trace -e rseq 0.000 ( 0.019 ms): Isolated Web C/1197258 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)4,.cpu_id = (__u32)4,.mm_cid = (__u32)5,}, rseq_len: 32, sig: 1392848979) = 0 1663.835 ( 0.019 ms): Isolated Web C/1197259 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)24,.cpu_id = (__u32)24,.mm_cid = (__u32)2,}, rseq_len: 32, sig: 1392848979) = 0 4750.444 ( 0.018 ms): Isolated Web C/1197260 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)8,.cpu_id = (__u32)8,.mm_cid = (__u32)4,}, rseq_len: 32, sig: 1392848979) = 0 4994.132 ( 0.018 ms): Isolated Web C/1197261 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)10,.cpu_id = (__u32)10,.mm_cid = (__u32)1,}, rseq_len: 32, sig: 1392848979) = 0 4997.578 ( 0.011 ms): Isolated Web C/1197263 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)16,.cpu_id = (__u32)16,.mm_cid = (__u32)4,}, rseq_len: 32, sig: 1392848979) = 0 4997.462 ( 0.014 ms): Isolated Web C/1197262 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)17,.cpu_id = (__u32)17,.mm_cid = (__u32)3,}, rseq_len: 32, sig: 1392848979) = 0 ^Croot@number:~# We'll probably need to come up with some way for using the BTF info to synthesize a test that then gets used and captures the output of the 'perf trace' output to check if the arguments are the ones synthesized, randomically, for now, lets make do manually: root@number:~# cat ~acme/c/rseq.c #include /* Definition of SYS_* constants */ #include #include #include #include #include #include /* Provide own rseq stub because glibc doesn't */ __attribute__((weak)) int sys_rseq(struct rseq *rseq, __u32 rseq_len, int flags, __u32 sig) { return syscall(SYS_rseq, rseq, rseq_len, flags, sig); } int main(int argc, char *argv[]) { struct rseq rseq = { .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }; int err = sys_rseq(&rseq, sizeof(rseq), 98765, 0xdeadbeaf); printf("sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, %d, 0) = %d (%s)\n", sizeof(rseq), err, strerror(errno)); return err; } root@number:~# perf trace -e rseq ~acme/c/rseq sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, 32, 0) = -1 (Invalid argument) 0.000 ( 0.003 ms): rseq/1200640 rseq(rseq: (struct rseq){}, rseq_len: 32, sig: 1392848979) = 0.064 ( 0.001 ms): rseq/1200640 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)12,.cpu_id = (__u32)34,.rseq_cs = (__u64)56,.flags = (__u32)78,.node_id = (__u32)90,.mm_cid = (__u32)12,}, rseq_len: 32, flags: 98765, sig: 3735928495) = -1 EINVAL (Invalid argument) root@number:~#root@number:~# cat ~acme/c/rseq.c #include /* Definition of SYS_* constants */ #include #include #include #include #include #include /* Provide own rseq stub because glibc doesn't */ __attribute__((weak)) int sys_rseq(struct rseq *rseq, __u32 rseq_len, int flags, __u32 sig) { return syscall(SYS_rseq, rseq, rseq_len, flags, sig); } int main(int argc, char *argv[]) { struct rseq rseq = { .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }; int err = sys_rseq(&rseq, sizeof(rseq), 98765, 0xdeadbeaf); printf("sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, %d, 0) = %d (%s)\n", sizeof(rseq), err, strerror(errno)); return err; } root@number:~# perf trace -e rseq ~acme/c/rseq sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, 32, 0) = -1 (Invalid argument) 0.000 ( 0.003 ms): rseq/1200640 rseq(rseq: (struct rseq){}, rseq_len: 32, sig: 1392848979) = 0.064 ( 0.001 ms): rseq/1200640 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)12,.cpu_id = (__u32)34,.rseq_cs = (__u64)56,.flags = (__u32)78,.node_id = (__u32)90,.mm_cid = (__u32)12,}, rseq_len: 32, flags: 98765, sig: 3735928495) = -1 EINVAL (Invalid argument) root@number:~# Interesting, glibc seems to be using rseq here, as in addition to the totally fake one this test case uses, we have this one, around these other syscalls: 0.175 ( 0.001 ms): rseq/1201095 set_tid_address(tidptr: 0x7f6def759a10) = 1201095 (rseq) 0.177 ( 0.001 ms): rseq/1201095 set_robust_list(head: 0x7f6def759a20, len: 24) = 0 0.178 ( 0.001 ms): rseq/1201095 rseq(rseq: (struct rseq){}, rseq_len: 32, sig: 1392848979) = 0.231 ( 0.005 ms): rseq/1201095 mprotect(start: 0x7f6def93f000, len: 16384, prot: READ) = 0 0.238 ( 0.003 ms): rseq/1201095 mprotect(start: 0x403000, len: 4096, prot: READ) = 0 0.244 ( 0.004 ms): rseq/1201095 mprotect(start: 0x7f6def99c000, len: 8192, prot: READ) Matches strace (well, not really as the strace in fedora:40 doesn't know about rseq, printing just integer values in hex): set_robust_list(0x7fbc6acc7a20, 24) = 0 rseq(0x7fbc6acc8060, 0x20, 0, 0x53053053) = 0 mprotect(0x7fbc6aead000, 16384, PROT_READ) = 0 mprotect(0x403000, 4096, PROT_READ) = 0 mprotect(0x7fbc6af0a000, 8192, PROT_READ) = 0 prlimit64(0, RLIMIT_STACK, NULL, {rlim_cur=8192*1024, rlim_max=RLIM64_INFINITY}) = 0 munmap(0x7fbc6aebd000, 81563) = 0 rseq(0x7fff15bb9920, 0x20, 0x181cd, 0xdeadbeaf) = -1 EINVAL (Invalid argument) fstat(1, {st_mode=S_IFCHR|0620, st_rdev=makedev(0x88, 0x9), ...}) = 0 getrandom("\xd0\x34\x97\x17\x61\xc2\x2b\x10", 8, GRND_NONBLOCK) = 8 brk(NULL) = 0x18ff4000 brk(0x19015000) = 0x19015000 write(1, "sys_rseq({ .cpu_id_start = 12, ."..., 136sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, 32, 0) = -1 (Invalid argument) ) = 136 exit_group(-1) = ? +++ exited with 255 +++ root@number:~# And also the focus for the v6.13 should be to have a better, strace like BTF pretty printer as one of the outputs we can get from the libbpf BTF dumper. Cc: Adrian Hunter Cc: Alan Maguire Cc: Howard Chu Cc: Jiri Olsa Cc: Kan Liang Cc: Mathieu Desnoyers Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZuH2K1LLt1pIDkbd@x1 Signed-off-by: Arnaldo Carvalho de Melo

perf env: Find correct branch counter info on hybrid

2024-09-11T16:08:46Z

No event is printed in the "Branch Counter" column on hybrid machines. For example, $ perf record -e "{cpu_core/branch-instructions/pp,cpu_core/branches/}:S" -j any,counter $ perf report --total-cycles # Branch counter abbr list: # cpu_core/branch-instructions/pp = A # cpu_core/branches/ = B # '-' No event occurs # '+' Event occurrences may be lost due to branch counter saturated # # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter # ............... .............. ........... .......... .............. 44.54% 727.1K 0.00% 1 |+ |+ | 36.31% 592.7K 0.00% 2 |+ |+ | 17.83% 291.1K 0.00% 1 |+ |+ | The branch counter information (br_cntr_width and br_cntr_nr) in the perf_env is retrieved from the CPU_PMU_CAPS. However, the CPU_PMU_CAPS is not available on hybrid machines. Without the width information, the number of occurrences of an event cannot be calculated. For a hybrid machine, the caps information should be retrieved from the PMU_CAPS, and stored in the perf_env->pmu_caps. Add a perf_env__find_br_cntr_info() to return the correct branch counter information from the corresponding fields. Committer notes: While testing I couldn't s ee those "Branch counter" columns enabled by pressing 'B' on the TUI, after reporting it to the list Kan explained the situation: For a hybrid client, the "Branch Counter" feature is only supported starting from the just released Lunar Lake. Perf falls back to only "ANY" on your Raptor Lake. The "The branch counter is not available" message is expected. Here is the 'perf evlist' result from my Lunar Lake machine, # perf evlist -v cpu_core/branch-instructions/pp: type: 4 (cpu_core), size: 136, config: 0xc4 (branch-instructions), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|READ|PERIOD|BRANCH_STACK|IDENTIFIER, read_format: ID|GROUP|LOST, disabled: 1, freq: 1, enable_on_exec: 1, precise_ip: 2, sample_id_all: 1, exclude_guest: 1, branch_sample_type: ANY|COUNTERS # Fixes: 6f9d8d1de2c61288 ("perf script: Add branch counters") Reviewed-by: Ian Rogers Signed-off-by: Kan Liang Cc: Adrian Hunter Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Link: https://lore.kernel.org/r/20240909184201.553519-1-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf evlist: Print hint for group

2024-09-11T16:08:45Z

An event group is a critical relationship. There is a -g option that can display the relationship. But it's hard for a user to know when should this option be applied. If there is an event group in the perf record, print a hint to suggest the user apply the -g to display the group information. With the patch, $ perf record -e "{cycles,instructions},instructions" sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.024 MB perf.data (4 samples) ] $ $ perf evlist cycles instructions instructions # Tip: use 'perf evlist -g' to show group information $ perf evlist -g {cycles,instructions} instructions $ Committer testing: So for a perf.data file _with_ a group: root@number:~# perf evlist -g {cpu_core/branch-instructions/pp,cpu_core/branches/} dummy:u root@number:~# perf evlist cpu_core/branch-instructions/pp cpu_core/branches/ dummy:u # Tip: use 'perf evlist -g' to show group information root@number:~# Then for something _without_ a group, no hint: root@number:~# perf record ls [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.035 MB perf.data (7 samples) ] root@number:~# perf evlist cpu_atom/cycles/P cpu_core/cycles/P dummy:u root@number:~# No suggestion, good. Suggested-by: Arnaldo Carvalho de Melo Reviewed-by: Ian Rogers Signed-off-by: Kan Liang Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Closes: https://lore.kernel.org/lkml/ZttgvduaKsVn1r4p@x1/ Link: https://lore.kernel.org/r/20240908202847.176280-1-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

tools: Drop nonsensical -O6

2024-09-11T16:08:36Z

-O6 is very much not-a-thing. Really, this should've been dropped entirely in 49b3cd306e60b9d8 ("tools: Set the maximum optimization level according to the compiler being used") instead of just passing it for not-Clang. Just collapse it down to -O3, instead of "-O6 unless Clang, in which case -O3". GCC interprets > -O3 as -O3. It doesn't even interpret > -O3 as -Ofast, which is a good thing, given -Ofast has specific (non-)requirements for code built using it. So, this does nothing except look a bit daft. Remove the silliness and also save a few lines in the Makefiles accordingly. Reviewed-by: Ian Rogers Reviewed-by: Jesper Juhl Signed-off-by: Sam James Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Bill Wendling Cc: Ingo Molnar Cc: Jiri Olsa Cc: Justin Stitt Cc: Kan Liang Cc: Mark Rutland Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/4f01524fa4ea91c7146a41e26ceaf9dae4c127e4.1725821201.git.sam@gentoo.org Signed-off-by: Arnaldo Carvalho de Melo

perf pmu: To info add event_type_desc

2024-09-11T14:29:20Z

All PMU events are assumed to be "Kernel PMU event", however, this isn't true for fake PMUs and won't be true with the addition of more software PMUs. Make the PMU's type description name configurable - largely for printing callbacks. Signed-off-by: Ian Rogers Link: https://lore.kernel.org/r/20240907050830.6752-5-irogers@google.com Cc: Ravi Bangoria Cc: Sandipan Das Cc: Mark Rutland Cc: Yang Jihong Cc: Dominique Martinet Cc: Clément Le Goffic Cc: Colin Ian King Cc: Howard Chu Cc: Ze Gao Cc: Yicong Yang Cc: Changbin Du Cc: Junhao He Cc: Peter Zijlstra Cc: Adrian Hunter Cc: Weilin Wang Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Namhyung Kim Cc: Will Deacon Cc: James Clark Cc: Mike Leach Cc: Jing Zhang Cc: Leo Yan Cc: Oliver Upton Cc: Benjamin Gray Cc: Andi Kleen Cc: Alexander Shishkin Cc: Kan Liang Cc: Athira Jajeev Cc: linux-arm-kernel@lists.infradead.org Cc: Sun Haiyong Cc: Tiezhu Yang Cc: Xu Yang Cc: John Garry Cc: Ingo Molnar Cc: Veronika Molnarova Cc: Dr. David Alan Gilbert Cc: linux-kernel@vger.kernel.org Cc: linux-perf-users@vger.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf evsel: Add accessor for tool_event

2024-09-11T14:28:27Z

Currently tool events use a dedicated variable within the evsel. Later changes will move this to the unused struct perf_event_attr config for these events. Add an accessor to allow the later change to be well typed and avoid changing all uses. Signed-off-by: Ian Rogers Link: https://lore.kernel.org/r/20240907050830.6752-4-irogers@google.com Cc: Ravi Bangoria Cc: Sandipan Das Cc: Mark Rutland Cc: Yang Jihong Cc: Dominique Martinet Cc: Clément Le Goffic Cc: Colin Ian King Cc: Howard Chu Cc: Ze Gao Cc: Yicong Yang Cc: Changbin Du Cc: Junhao He Cc: Peter Zijlstra Cc: Adrian Hunter Cc: Weilin Wang Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Namhyung Kim Cc: Will Deacon Cc: James Clark Cc: Mike Leach Cc: Jing Zhang Cc: Leo Yan Cc: Oliver Upton Cc: Benjamin Gray Cc: Andi Kleen Cc: Alexander Shishkin Cc: Kan Liang Cc: Athira Jajeev Cc: linux-arm-kernel@lists.infradead.org Cc: Sun Haiyong Cc: Tiezhu Yang Cc: Xu Yang Cc: John Garry Cc: Ingo Molnar Cc: Veronika Molnarova Cc: Dr. David Alan Gilbert Cc: linux-kernel@vger.kernel.org Cc: linux-perf-users@vger.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf pmus: Fake PMU clean up

2024-09-11T14:27:42Z

Rather than passing a fake PMU around, just pass that the fake PMU should be used - true when doing testing. Move the fake PMU into pmus.[ch] and try to abstract the PMU's properties in pmu.c, ie so there is less "if fake_pmu" in non-PMU code. Give the fake PMU a made up type number. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Benjamin Gray Cc: Changbin Du Cc: Clément Le Goffic Cc: Colin Ian King Cc: Dominique Martinet Cc: Dr. David Alan Gilbert Cc: Howard Chu Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Junhao He Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Oliver Upton Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sun Haiyong Cc: Tiezhu Yang Cc: Veronika Molnarova Cc: Weilin Wang Cc: Will Deacon Cc: Xu Yang Cc: Yang Jihong Cc: Yicong Yang Cc: Ze Gao Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20240907050830.6752-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf list: Avoid potential out of bounds memory read

2024-09-11T14:26:27Z

If a desc string is 0 length then -1 will be out of bounds, add a check. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Benjamin Gray Cc: Changbin Du Cc: Clément Le Goffic Cc: Colin Ian King Cc: Dominique Martinet Cc: Dr. David Alan Gilbert Cc: Howard Chu Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Junhao He Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Oliver Upton Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sun Haiyong Cc: Tiezhu Yang Cc: Veronika Molnarova Cc: Weilin Wang Cc: Will Deacon Cc: Xu Yang Cc: Yang Jihong Cc: Yicong Yang Cc: Ze Gao Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20240907050830.6752-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo