From 01157ddc58dc2fe428ec17dd5a18cc13f134639f Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Thu, 23 Jan 2025 14:07:47 -0500 Subject: kallsyms: Remove KALLSYMS_ABSOLUTE_PERCPU x86-64 was the only user. Signed-off-by: Brian Gerst Signed-off-by: Ingo Molnar Reviewed-by: Ard Biesheuvel Cc: Linus Torvalds Link: https://lore.kernel.org/r/20250123190747.745588-16-brgerst@gmail.com --- scripts/link-vmlinux.sh | 4 ---- 1 file changed, 4 deletions(-) (limited to 'scripts/link-vmlinux.sh') diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 56a077d204cf..67e66333bd2a 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -144,10 +144,6 @@ kallsyms() kallsymopt="${kallsymopt} --all-symbols" fi - if is_enabled CONFIG_KALLSYMS_ABSOLUTE_PERCPU; then - kallsymopt="${kallsymopt} --absolute-percpu" - fi - info KSYMS "${2}.S" scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S" -- cgit v1.2.3 From ef378c3b8233855497a414b9d67bf22592c928a4 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 18 Feb 2025 14:59:22 -0500 Subject: scripts/sorttable: Zero out weak functions in mcount_loc table When a function is annotated as "weak" and is overridden, the code is not removed. If it is traced, the fentry/mcount location in the weak function will be referenced by the "__mcount_loc" section. This will then be added to the available_filter_functions list. Since only the address of the functions are listed, to find the name to show, a search of kallsyms is used. Since kallsyms will return the function by simply finding the function that the address is after but before the next function, an address of a weak function will show up as the function before it. This is because kallsyms does not save names of weak functions. This has caused issues in the past, as now the traced weak function will be listed in available_filter_functions with the name of the function before it. At best, this will cause the previous function's name to be listed twice. At worse, if the previous function was marked notrace, it will now show up as a function that can be traced. Note that it only shows up that it can be traced but will not be if enabled, which causes confusion. https://lore.kernel.org/all/20220412094923.0abe90955e5db486b7bca279@kernel.org/ The commit b39181f7c6907 ("ftrace: Add FTRACE_MCOUNT_MAX_OFFSET to avoid adding weak function") was a workaround to this by checking the function address before printing its name. If the address was too far from the function given by the name then instead of printing the name it would print: __ftrace_invalid_address___ The real issue is that these invalid addresses are listed in the ftrace table look up which available_filter_functions is derived from. A place holder must be listed in that file because set_ftrace_filter may take a series of indexes into that file instead of names to be able to do O(1) lookups to enable filtering (many tools use this method). Even if kallsyms saved the size of the function, it does not remove the need of having these place holders. The real solution is to not add a weak function into the ftrace table in the first place. To solve this, the sorttable.c code that sorts the mcount regions during the build is modified to take a "nm -S vmlinux" input, sort it, and any function listed in the mcount_loc section that is not within a boundary of the function list given by nm is considered a weak function and is zeroed out. Note, this does not mean they will remain zero when booting as KASLR will still shift those addresses. To handle this, the entries in the mcount_loc section will be ignored if they are zero or match the kaslr_offset() value. Before: ~# grep __ftrace_invalid_address___ /sys/kernel/tracing/available_filter_functions | wc -l 551 After: ~# grep __ftrace_invalid_address___ /sys/kernel/tracing/available_filter_functions | wc -l 0 Cc: bpf Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Masahiro Yamada Cc: Nathan Chancellor Cc: Nicolas Schier Cc: Zheng Yejian Cc: Martin Kelly Cc: Christophe Leroy Cc: Josh Poimboeuf Cc: Heiko Carstens Cc: Catalin Marinas Cc: Will Deacon Cc: Vasily Gorbik Cc: Alexander Gordeev Link: https://lore.kernel.org/20250218200022.883095980@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 6 ++- scripts/link-vmlinux.sh | 4 +- scripts/sorttable.c | 128 +++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 134 insertions(+), 4 deletions(-) (limited to 'scripts/link-vmlinux.sh') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 728ecda6e8d4..e3f89924f603 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7004,6 +7004,7 @@ static int ftrace_process_locs(struct module *mod, unsigned long count; unsigned long *p; unsigned long addr; + unsigned long kaslr; unsigned long flags = 0; /* Shut up gcc */ int ret = -ENOMEM; @@ -7052,6 +7053,9 @@ static int ftrace_process_locs(struct module *mod, ftrace_pages->next = start_pg; } + /* For zeroed locations that were shifted for core kernel */ + kaslr = !mod ? kaslr_offset() : 0; + p = start; pg = start_pg; while (p < end) { @@ -7063,7 +7067,7 @@ static int ftrace_process_locs(struct module *mod, * object files to satisfy alignments. * Skip any NULL pointers. */ - if (!addr) { + if (!addr || addr == kaslr) { skipped++; continue; } diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 56a077d204cf..59b07fe6fd00 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -177,12 +177,14 @@ mksysmap() sorttable() { - ${objtree}/scripts/sorttable ${1} + ${NM} -S ${1} > .tmp_vmlinux.nm-sort + ${objtree}/scripts/sorttable -s .tmp_vmlinux.nm-sort ${1} } cleanup() { rm -f .btf.* + rm -f .tmp_vmlinux.nm-sort rm -f System.map rm -f vmlinux rm -f vmlinux.map diff --git a/scripts/sorttable.c b/scripts/sorttable.c index ec02a2852efb..23c7e0e6c024 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -580,6 +580,98 @@ static void rela_write_addend(Elf_Rela *rela, uint64_t val) e.rela_write_addend(rela, val); } +struct func_info { + uint64_t addr; + uint64_t size; +}; + +/* List of functions created by: nm -S vmlinux */ +static struct func_info *function_list; +static int function_list_size; + +/* Allocate functions in 1k blocks */ +#define FUNC_BLK_SIZE 1024 +#define FUNC_BLK_MASK (FUNC_BLK_SIZE - 1) + +static int add_field(uint64_t addr, uint64_t size) +{ + struct func_info *fi; + int fsize = function_list_size; + + if (!(fsize & FUNC_BLK_MASK)) { + fsize += FUNC_BLK_SIZE; + fi = realloc(function_list, fsize * sizeof(struct func_info)); + if (!fi) + return -1; + function_list = fi; + } + fi = &function_list[function_list_size++]; + fi->addr = addr; + fi->size = size; + return 0; +} + +/* Only return match if the address lies inside the function size */ +static int cmp_func_addr(const void *K, const void *A) +{ + uint64_t key = *(const uint64_t *)K; + const struct func_info *a = A; + + if (key < a->addr) + return -1; + return key >= a->addr + a->size; +} + +/* Find the function in function list that is bounded by the function size */ +static int find_func(uint64_t key) +{ + return bsearch(&key, function_list, function_list_size, + sizeof(struct func_info), cmp_func_addr) != NULL; +} + +static int cmp_funcs(const void *A, const void *B) +{ + const struct func_info *a = A; + const struct func_info *b = B; + + if (a->addr < b->addr) + return -1; + return a->addr > b->addr; +} + +static int parse_symbols(const char *fname) +{ + FILE *fp; + char addr_str[20]; /* Only need 17, but round up to next int size */ + char size_str[20]; + char type; + + fp = fopen(fname, "r"); + if (!fp) { + perror(fname); + return -1; + } + + while (fscanf(fp, "%16s %16s %c %*s\n", addr_str, size_str, &type) == 3) { + uint64_t addr; + uint64_t size; + + /* Only care about functions */ + if (type != 't' && type != 'T' && type != 'W') + continue; + + addr = strtoull(addr_str, NULL, 16); + size = strtoull(size_str, NULL, 16); + if (add_field(addr, size) < 0) + return -1; + } + fclose(fp); + + qsort(function_list, function_list_size, sizeof(struct func_info), cmp_funcs); + + return 0; +} + static pthread_t mcount_sort_thread; static bool sort_reloc; @@ -752,6 +844,21 @@ static void *sort_mcount_loc(void *arg) goto out; } + /* zero out any locations not found by function list */ + if (function_list_size) { + for (void *ptr = vals; ptr < vals + size; ptr += long_size) { + uint64_t key; + + key = long_size == 4 ? r((uint32_t *)ptr) : r8((uint64_t *)ptr); + if (!find_func(key)) { + if (long_size == 4) + *(uint32_t *)ptr = 0; + else + *(uint64_t *)ptr = 0; + } + } + } + compare_values = long_size == 4 ? compare_values_32 : compare_values_64; qsort(vals, count, long_size, compare_values); @@ -801,6 +908,8 @@ static void get_mcount_loc(struct elf_mcount_loc *emloc, Elf_Shdr *symtab_sec, return; } } +#else /* MCOUNT_SORT_ENABLED */ +static inline int parse_symbols(const char *fname) { return 0; } #endif static int do_sort(Elf_Ehdr *ehdr, @@ -1256,14 +1365,29 @@ int main(int argc, char *argv[]) int i, n_error = 0; /* gcc-4.3.0 false positive complaint */ size_t size = 0; void *addr = NULL; + int c; + + while ((c = getopt(argc, argv, "s:")) >= 0) { + switch (c) { + case 's': + if (parse_symbols(optarg) < 0) { + fprintf(stderr, "Could not parse %s\n", optarg); + return -1; + } + break; + default: + fprintf(stderr, "usage: sorttable [-s nm-file] vmlinux...\n"); + return 0; + } + } - if (argc < 2) { + if ((argc - optind) < 1) { fprintf(stderr, "usage: sorttable vmlinux...\n"); return 0; } /* Process each file in turn, allowing deep failure. */ - for (i = 1; i < argc; i++) { + for (i = optind; i < argc; i++) { addr = mmap_file(argv[i], &size); if (!addr) { ++n_error; -- cgit v1.2.3 From ba4d705046fb568bad4aeffeb79db78d4e835a1f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 13 Mar 2025 19:26:03 +0900 Subject: kbuild: do not generate .tmp_vmlinux*.map when CONFIG_VMLINUX_MAP=y Commit 5cc124720461 ("kbuild: add CONFIG_VMLINUX_MAP expert option") mentioned that "the .map file can be rather large (several MB), and that's a waste of space when one isn't interested in these things." If that is the case, generating map files for the intermediate tmp_vmlinux* files is also a waste of space. It is unlikely that anyone would be interested in the .tmp_vmlinux*.map files. This commit stops passing the -Map= option when linking the .tmp_vmlinux* intermediates. I also hard-coded the file name 'vmlinux.map' instead of ${output}.map because a later commit will introduce vmlinux.unstripped but I want to keep the current name of the map file. Signed-off-by: Masahiro Yamada Acked-by: Ard Biesheuvel --- scripts/link-vmlinux.sh | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'scripts/link-vmlinux.sh') diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 56a077d204cf..96ae0bb65308 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -97,8 +97,8 @@ vmlinux_link() ldflags="${ldflags} ${wl}--strip-debug" fi - if is_enabled CONFIG_VMLINUX_MAP; then - ldflags="${ldflags} ${wl}-Map=${output}.map" + if [ -n "${generate_map}" ]; then + ldflags="${ldflags} ${wl}-Map=vmlinux.map" fi ${ld} ${ldflags} -o ${output} \ @@ -210,6 +210,7 @@ fi btf_vmlinux_bin_o= kallsymso= strip_debug= +generate_map= if is_enabled CONFIG_KALLSYMS; then true > .tmp_vmlinux0.syms @@ -278,6 +279,10 @@ fi strip_debug= +if is_enabled CONFIG_VMLINUX_MAP; then + generate_map=1 +fi + vmlinux_link vmlinux # fill in BTF IDs -- cgit v1.2.3 From e22bbb8e97846bfb5a6942a2322f0237ff13df0f Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 11 Mar 2025 12:06:18 +0100 Subject: kbuild: link-vmlinux.sh: Make output file name configurable In order to introduce an intermediate, non-stripped vmlinux build that can be used by other build steps as an input, pass the output file name to link-vmlinux.sh via its command line. Signed-off-by: Ard Biesheuvel Signed-off-by: Masahiro Yamada --- scripts/Makefile.vmlinux | 2 +- scripts/link-vmlinux.sh | 15 ++++++++------- 2 files changed, 9 insertions(+), 8 deletions(-) (limited to 'scripts/link-vmlinux.sh') diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index fb79fd6b2465..487f0bf716ad 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -69,7 +69,7 @@ ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink) # Final link of vmlinux with optional arch pass after final link cmd_link_vmlinux = \ - $< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)"; \ + $< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)" "$@"; \ $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true) targets += vmlinux diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 96ae0bb65308..b3d928925598 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -31,6 +31,7 @@ set -e LD="$1" KBUILD_LDFLAGS="$2" LDFLAGS_vmlinux="$3" +VMLINUX="$4" is_enabled() { grep -q "^$1=y" include/config/auto.conf @@ -283,23 +284,23 @@ if is_enabled CONFIG_VMLINUX_MAP; then generate_map=1 fi -vmlinux_link vmlinux +vmlinux_link "${VMLINUX}" # fill in BTF IDs if is_enabled CONFIG_DEBUG_INFO_BTF; then - info BTFIDS vmlinux + info BTFIDS "${VMLINUX}" RESOLVE_BTFIDS_ARGS="" if is_enabled CONFIG_WERROR; then RESOLVE_BTFIDS_ARGS=" --fatal_warnings " fi - ${RESOLVE_BTFIDS} ${RESOLVE_BTFIDS_ARGS} vmlinux + ${RESOLVE_BTFIDS} ${RESOLVE_BTFIDS_ARGS} "${VMLINUX}" fi -mksysmap vmlinux System.map +mksysmap "${VMLINUX}" System.map if is_enabled CONFIG_BUILDTIME_TABLE_SORT; then - info SORTTAB vmlinux - if ! sorttable vmlinux; then + info SORTTAB "${VMLINUX}" + if ! sorttable "${VMLINUX}"; then echo >&2 Failed to sort kernel tables exit 1 fi @@ -315,4 +316,4 @@ if is_enabled CONFIG_KALLSYMS; then fi # For fixdep -echo "vmlinux: $0" > .vmlinux.d +echo "${VMLINUX}: $0" > ".${VMLINUX}.d" -- cgit v1.2.3