kernel/tools/perf/util/dso.c, branch master

perf thread: Add optional e_flags output argument to thread__e_machine

2026-01-26T21:21:20Z

The e_flags are needed to accurately compute complete perf register information for CSKY. Add the ability to read and have this value associated with a thread. This change doesn't wire up the use of the e_flags except in disasm where use already exists but just wasn't set up yet. Signed-off-by: Ian Rogers Cc: Aditya Bodkhe Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Chun-Tse Shao Cc: Guo Ren Cc: Howard Chu Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sergei Trofimovich Cc: Shimin Guo Cc: Stephen Brennan Cc: Swapnil Sapkal Cc: Tianyou Li Signed-off-by: Arnaldo Carvalho de Melo

perf dso: Factor out e_machine reading for use in thread

2026-01-26T21:21:20Z

Factor out the resilient e_machine reading code in dso so that it may be used in thread. As there is no dso in that case, make the dso optional. This makes some minor other changes as the swap type from the dso cannot be ascertained. Signed-off-by: Ian Rogers Cc: Aditya Bodkhe Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Chun-Tse Shao Cc: Guo Ren Cc: Howard Chu Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sergei Trofimovich Cc: Shimin Guo Cc: Stephen Brennan Cc: Swapnil Sapkal Cc: Tianyou Li Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Get debug info of DSO properly

2026-01-20T20:20:51Z

The dso__debuginfo() just used the path name to open the file but it may be outdated. It should check build-ID and use the file in the build-ID cache if available rather than just using the path name. Let's factor out dso__get_filename() to avoid code duplicate. Fixes: 53a61a6ca279165d ("perf annotate: Add dso__debuginfo() helper") Reviewed-by: Ian Rogers Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo

perf powerpc: Unify the skip-callchain-idx libdw with that for addr2line

2026-01-20T16:04:38Z

Rather than have 2 Dwfl unify the Dwfl in skip-callchain-idx with that is used by libdw__addr2line(). Rename that variable in 'struct dso' from 'a2l_libdw' to just 'libdw' as it is now used in more than addr2line. The Dwfl in skip-callchain-idx uses a map address when being read with dwfl_report_elf (rather than dwfl_report_offline that addr2line uses). skip-callchain-idx is wrong as the map address can vary between processes because of ASLR, ie it should need a different Dwfl per process. In the code after this patch the base address becomes 0 and the mapped PC is used with the dwfl functions. This should increase the accuracy of skip-callchain-idx, but the impact has only been build tested. Signed-off-by: Ian Rogers Cc: Aditya Bodkhe Cc: Adrian Hunter Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andi Kleen Cc: Athira Rajeev Cc: Chun-Tse Shao Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Guo Ren Cc: Haibo Xu Cc: Howard Chu Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Krzysztof Łopatowski Cc: Leo Yan Cc: Mark Wielaard Cc: Namhyung Kim Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Sergei Trofimovich Cc: Shimin Guo Cc: Stephen Brennan Cc: Thomas Falcon Cc: Will Deacon Signed-off-by: Arnaldo Carvalho de Melo

perf dso: Extra validity checks that e_machine is valid

2026-01-20T15:55:01Z

Better ensure a read e_machine is valid by checking the file appears like an ELF file and the read e_machine value is less than EM_NUM. This better avoids spurious e_machine values when looking for an e_machine in say a thread. Signed-off-by: Ian Rogers Cc: Aditya Bodkhe Cc: Adrian Hunter Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andi Kleen Cc: Athira Rajeev Cc: Chun-Tse Shao Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Guo Ren Cc: Haibo Xu Cc: Howard Chu Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Krzysztof Łopatowski Cc: Leo Yan Cc: Mark Wielaard Cc: Namhyung Kim Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Sergei Trofimovich Cc: Shimin Guo Cc: Stephen Brennan Cc: Thomas Falcon Cc: Will Deacon Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Switch printf("...%s", strerror(errno)) to printf("...%m")

2026-01-14T20:22:50Z

strerror() has thread safety issues, strerror_r() requires stack allocated buffers. Code in perf has already been using the "%m" formatting flag that is a widely support glibc extension to print the current errno's description. Expand the usage of this formatting flag and remove usage of strerror()/strerror_r(). Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Blake Jones Cc: Chun-Tse Shao Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Haibo Xu Cc: Howard Chu Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Peter Zijlstra Cc: Stephen Brennan Cc: Thomas Falcon Cc: Yunseong Kim Cc: Zhongqiu Han Signed-off-by: Arnaldo Carvalho de Melo

perf addr2line: Add a libdw implementation

2026-01-12T19:23:06Z

Add an implementation of addr2line that uses libdw. Other addr2line implementations are slow, particularly in the case of forking addr2line. Add an implementation that caches the libdw information in the dso and uses it to find the file and line number information. Inline information is supported but because cu_walk_functions_at visits the leaf function last add a inline_list__append_tail to reverse the lists order. Committer testing: # perf probe -x ~/bin/perf libdw__addr2line Added new event: probe_perf:libdw_addr2line (on libdw__addr2line in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:libdw_addr2line -aR sleep 1 # # perf stat -e probe_perf:libdw_addr2line perf report -f --dso perf --stdio -s srcfile,srcline # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 4K of event 'cpu/cycles/Pu' # Event count (approx.): 5535180842 # # Overhead Source File Source:Line # ........ ............ ............... # 99.04% inlineloop.c inlineloop.c:21 0.46% inlineloop.c inlineloop.c:20 # # (Tip: For tracepoint events, try: perf report -s trace_fields) # Performance counter stats for 'perf report -f --dso perf --stdio -s srcfile,srcline': 44 probe_perf:libdw_addr2line 0.037260744 seconds time elapsed 0.025299000 seconds user 0.011918000 seconds sys # Adding probes to the other addr2line implementations (llvm__addr2line, libbfd__addr2line and cmd__addr2line) I noticed some fallbacks to the llvm one: Performance counter stats for 'perf report -f --dso perf --stdio -s srcfile,srcline': 44 probe_perf:libdw_addr2line 23 probe_perf:llvm_addr2line 0 probe_perf:libbfd_addr2line 0 probe_perf:cmd_addr2line Something to investigate further, but at least we don't fallback to the cmd based one :-) Reviewed-by: James Clark Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Howard Chu Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephen Brennan Cc: Tony Jones Signed-off-by: Arnaldo Carvalho de Melo

perf dso: Clean up read_symbol() error handling

2025-10-06T19:35:28Z

Ensure errno is set and return to caller for error handling. Unusually for perf the value isn't negated as expected by symbol__strerror_disassemble(). Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Andi Kleen Cc: Athira Rajeev Cc: Bill Wendling Cc: Charlie Jenkins Cc: Collin Funk Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Eric Biggers Cc: Haibo Xu Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Justin Stitt Cc: Li Huafei Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Song Liu Cc: Stephen Brennan Signed-off-by: Arnaldo Carvalho de Melo

perf dso: Support BPF programs in dso__read_symbol()

2025-10-06T19:35:28Z

Set the buffer to the code in the BPF linear info. This enables BPF JIT code disassembly by LLVM and capstone. Move the common but minimal disassmble_bpf_image call to disassemble_objdump so that it is only called after falling back to the objdump option. Similarly move the disassmble_bpf function to disassemble_objdump and rename to disassmble_bpf_libbfd to make it clearer that this support relies on libbfd. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Andi Kleen Cc: Athira Rajeev Cc: Bill Wendling Cc: Charlie Jenkins Cc: Collin Funk Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Eric Biggers Cc: Haibo Xu Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Justin Stitt Cc: Li Huafei Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Song Liu Cc: Stephen Brennan Signed-off-by: Arnaldo Carvalho de Melo

perf dso: Move read_symbol() from llvm/capstone to dso

2025-10-06T19:35:25Z

Move the read_symbol function to dso.h, make the return type const and add a mutable out_buf out parameter. In future changes this will allow a code pointer to be returned without necessary allocating memory. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Andi Kleen Cc: Athira Rajeev Cc: Bill Wendling Cc: Charlie Jenkins Cc: Collin Funk Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Eric Biggers Cc: Haibo Xu Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Justin Stitt Cc: Li Huafei Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Song Liu Cc: Stephen Brennan Signed-off-by: Arnaldo Carvalho de Melo