From 897dd75c10a2c3b9ff016cde1b82ad5626a7c486 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Sun, 24 Jul 2022 14:00:12 +0800 Subject: perf symbol: Correct address for bss symbols [ Upstream commit 2d86612aacb7805f72873691a2644d7279ed0630 ] When using 'perf mem' and 'perf c2c', an issue is observed that tool reports the wrong offset for global data symbols. This is a common issue on both x86 and Arm64 platforms. Let's see an example, for a test program, below is the disassembly for its .bss section which is dumped with objdump: ... Disassembly of section .bss: 0000000000004040 : ... 0000000000004080 : ... 00000000000040c0 : ... 0000000000004100 : ... First we used 'perf mem record' to run the test program and then used 'perf --debug verbose=4 mem report' to observe what's the symbol info for 'buf1' and 'buf2' structures. # ./perf mem record -e ldlat-loads,ldlat-stores -- false_sharing.exe 8 # ./perf --debug verbose=4 mem report ... dso__load_sym_internal: adjusting symbol: st_value: 0x40c0 sh_addr: 0x4040 sh_offset: 0x3028 symbol__new: buf2 0x30a8-0x30e8 ... dso__load_sym_internal: adjusting symbol: st_value: 0x4080 sh_addr: 0x4040 sh_offset: 0x3028 symbol__new: buf1 0x3068-0x30a8 ... The perf tool relies on libelf to parse symbols, in executable and shared object files, 'st_value' holds a virtual address; 'sh_addr' is the address at which section's first byte should reside in memory, and 'sh_offset' is the byte offset from the beginning of the file to the first byte in the section. The perf tool uses below formula to convert a symbol's memory address to a file address: file_address = st_value - sh_addr + sh_offset ^ ` Memory address We can see the final adjusted address ranges for buf1 and buf2 are [0x30a8-0x30e8) and [0x3068-0x30a8) respectively, apparently this is incorrect, in the code, the structure for 'buf1' and 'buf2' specifies compiler attribute with 64-byte alignment. The problem happens for 'sh_offset', libelf returns it as 0x3028 which is not 64-byte aligned, combining with disassembly, it's likely libelf doesn't respect the alignment for .bss section, therefore, it doesn't return the aligned value for 'sh_offset'. Suggested by Fangrui Song, ELF file contains program header which contains PT_LOAD segments, the fields p_vaddr and p_offset in PT_LOAD segments contain the execution info. A better choice for converting memory address to file address is using the formula: file_address = st_value - p_vaddr + p_offset This patch introduces elf_read_program_header() which returns the program header based on the passed 'st_value', then it uses the formula above to calculate the symbol file address; and the debugging log is updated respectively. After applying the change: # ./perf --debug verbose=4 mem report ... dso__load_sym_internal: adjusting symbol: st_value: 0x40c0 p_vaddr: 0x3d28 p_offset: 0x2d28 symbol__new: buf2 0x30c0-0x3100 ... dso__load_sym_internal: adjusting symbol: st_value: 0x4080 p_vaddr: 0x3d28 p_offset: 0x2d28 symbol__new: buf1 0x3080-0x30c0 ... Fixes: f17e04afaff84b5c ("perf report: Fix ELF symbol parsing") Reported-by: Chang Rui Suggested-by: Fangrui Song Signed-off-by: Leo Yan Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220724060013.171050-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/symbol-elf.c | 45 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 41 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 166c621e0223..bd33d6613929 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -201,6 +201,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, return NULL; } +static int elf_read_program_header(Elf *elf, u64 vaddr, GElf_Phdr *phdr) +{ + size_t i, phdrnum; + u64 sz; + + if (elf_getphdrnum(elf, &phdrnum)) + return -1; + + for (i = 0; i < phdrnum; i++) { + if (gelf_getphdr(elf, i, phdr) == NULL) + return -1; + + if (phdr->p_type != PT_LOAD) + continue; + + sz = max(phdr->p_memsz, phdr->p_filesz); + if (!sz) + continue; + + if (vaddr >= phdr->p_vaddr && (vaddr < phdr->p_vaddr + sz)) + return 0; + } + + /* Not found any valid program header */ + return -1; +} + static bool want_demangle(bool is_kernel_sym) { return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; @@ -1063,6 +1090,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, sym.st_value); used_opd = true; } + /* * When loading symbols in a data mapping, ABS symbols (which * has a value of SHN_ABS in its st_shndx) failed at @@ -1099,11 +1127,20 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, goto out_elf_end; } else if ((used_opd && runtime_ss->adjust_symbols) || (!used_opd && syms_ss->adjust_symbols)) { + GElf_Phdr phdr; + + if (elf_read_program_header(syms_ss->elf, + (u64)sym.st_value, &phdr)) { + pr_warning("%s: failed to find program header for " + "symbol: %s st_value: %#" PRIx64 "\n", + __func__, elf_name, (u64)sym.st_value); + continue; + } pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " " - "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__, - (u64)sym.st_value, (u64)shdr.sh_addr, - (u64)shdr.sh_offset); - sym.st_value -= shdr.sh_addr - shdr.sh_offset; + "p_vaddr: %#" PRIx64 " p_offset: %#" PRIx64 "\n", + __func__, (u64)sym.st_value, (u64)phdr.p_vaddr, + (u64)phdr.p_offset); + sym.st_value -= phdr.p_vaddr - phdr.p_offset; } demangled = demangle_sym(dso, kmodule, elf_name); -- cgit v1.2.3