diff options
Diffstat (limited to 'scripts')
| -rw-r--r-- | scripts/Makefile.btf | 2 | ||||
| -rw-r--r-- | scripts/coccinelle/misc/newline_in_nl_msg.cocci | 13 | ||||
| -rwxr-xr-x | scripts/gen-crc-consts.py | 291 | ||||
| -rwxr-xr-x | scripts/link-vmlinux.sh | 4 | ||||
| -rwxr-xr-x | scripts/make_fit.py | 6 | ||||
| -rwxr-xr-x | scripts/selinux/install_policy.sh | 15 | ||||
| -rw-r--r-- | scripts/sorttable.c | 411 | ||||
| -rwxr-xr-x | scripts/tracing/draw_functrace.py | 129 |
8 files changed, 717 insertions, 154 deletions
diff --git a/scripts/Makefile.btf b/scripts/Makefile.btf index c3cbeb13de50..fbaaec2187e5 100644 --- a/scripts/Makefile.btf +++ b/scripts/Makefile.btf @@ -24,7 +24,7 @@ else pahole-flags-$(call test-ge, $(pahole-ver), 126) = -j$(JOBS) --btf_features=encode_force,var,float,enum64,decl_tag,type_tag,optimized_func,consistent_func,decl_tag_kfuncs ifneq ($(KBUILD_EXTMOD),) -module-pahole-flags-$(call test-ge, $(pahole-ver), 126) += --btf_features=distilled_base +module-pahole-flags-$(call test-ge, $(pahole-ver), 128) += --btf_features=distilled_base endif endif diff --git a/scripts/coccinelle/misc/newline_in_nl_msg.cocci b/scripts/coccinelle/misc/newline_in_nl_msg.cocci index 9baffe55d917..2814f6b205b9 100644 --- a/scripts/coccinelle/misc/newline_in_nl_msg.cocci +++ b/scripts/coccinelle/misc/newline_in_nl_msg.cocci @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /// -/// Catch strings ending in newline with GENL_SET_ERR_MSG, NL_SET_ERR_MSG, -/// NL_SET_ERR_MSG_MOD. +/// Catch strings ending in newline with (GE)NL_SET_ERR_MSG*. /// // Confidence: Very High // Copyright: (C) 2020 Intel Corporation @@ -17,7 +16,11 @@ expression e; constant m; position p; @@ - \(GENL_SET_ERR_MSG\|NL_SET_ERR_MSG\|NL_SET_ERR_MSG_MOD\)(e,m@p) + \(GENL_SET_ERR_MSG\|GENL_SET_ERR_MSG_FMT\|NL_SET_ERR_MSG\|NL_SET_ERR_MSG_MOD\| + NL_SET_ERR_MSG_FMT\|NL_SET_ERR_MSG_FMT_MOD\|NL_SET_ERR_MSG_WEAK\| + NL_SET_ERR_MSG_WEAK_MOD\|NL_SET_ERR_MSG_ATTR_POL\| + NL_SET_ERR_MSG_ATTR_POL_FMT\|NL_SET_ERR_MSG_ATTR\| + NL_SET_ERR_MSG_ATTR_FMT\)(e,m@p,...) @script:python@ m << r.m; @@ -32,7 +35,7 @@ expression r.e; constant r.m; position r.p; @@ - fname(e,m@p) + fname(e,m@p,...) //---------------------------------------------------------- // For context mode @@ -43,7 +46,7 @@ identifier r1.fname; expression r.e; constant r.m; @@ -* fname(e,m) +* fname(e,m,...) //---------------------------------------------------------- // For org mode diff --git a/scripts/gen-crc-consts.py b/scripts/gen-crc-consts.py new file mode 100755 index 000000000000..f9b44fc3a03f --- /dev/null +++ b/scripts/gen-crc-consts.py @@ -0,0 +1,291 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0-or-later +# +# Script that generates constants for computing the given CRC variant(s). +# +# Copyright 2025 Google LLC +# +# Author: Eric Biggers <ebiggers@google.com> + +import sys + +# XOR (add) an iterable of polynomials. +def xor(iterable): + res = 0 + for val in iterable: + res ^= val + return res + +# Multiply two polynomials. +def clmul(a, b): + return xor(a << i for i in range(b.bit_length()) if (b & (1 << i)) != 0) + +# Polynomial division floor(a / b). +def div(a, b): + q = 0 + while a.bit_length() >= b.bit_length(): + q ^= 1 << (a.bit_length() - b.bit_length()) + a ^= b << (a.bit_length() - b.bit_length()) + return q + +# Reduce the polynomial 'a' modulo the polynomial 'b'. +def reduce(a, b): + return a ^ clmul(div(a, b), b) + +# Reflect the bits of a polynomial. +def bitreflect(poly, num_bits): + assert poly.bit_length() <= num_bits + return xor(((poly >> i) & 1) << (num_bits - 1 - i) for i in range(num_bits)) + +# Format a polynomial as hex. Bit-reflect it if the CRC is lsb-first. +def fmt_poly(variant, poly, num_bits): + if variant.lsb: + poly = bitreflect(poly, num_bits) + return f'0x{poly:0{2*num_bits//8}x}' + +# Print a pair of 64-bit polynomial multipliers. They are always passed in the +# order [HI64_TERMS, LO64_TERMS] but will be printed in the appropriate order. +def print_mult_pair(variant, mults): + mults = list(mults if variant.lsb else reversed(mults)) + terms = ['HI64_TERMS', 'LO64_TERMS'] if variant.lsb else ['LO64_TERMS', 'HI64_TERMS'] + for i in range(2): + print(f'\t\t{fmt_poly(variant, mults[i]["val"], 64)},\t/* {terms[i]}: {mults[i]["desc"]} */') + +# Pretty-print a polynomial. +def pprint_poly(prefix, poly): + terms = [f'x^{i}' for i in reversed(range(poly.bit_length())) + if (poly & (1 << i)) != 0] + j = 0 + while j < len(terms): + s = prefix + terms[j] + (' +' if j < len(terms) - 1 else '') + j += 1 + while j < len(terms) and len(s) < 73: + s += ' ' + terms[j] + (' +' if j < len(terms) - 1 else '') + j += 1 + print(s) + prefix = ' * ' + (' ' * (len(prefix) - 3)) + +# Print a comment describing constants generated for the given CRC variant. +def print_header(variant, what): + print('/*') + s = f'{"least" if variant.lsb else "most"}-significant-bit-first CRC-{variant.bits}' + print(f' * {what} generated for {s} using') + pprint_poly(' * G(x) = ', variant.G) + print(' */') + +class CrcVariant: + def __init__(self, bits, generator_poly, bit_order): + self.bits = bits + if bit_order not in ['lsb', 'msb']: + raise ValueError('Invalid value for bit_order') + self.lsb = bit_order == 'lsb' + self.name = f'crc{bits}_{bit_order}_0x{generator_poly:0{(2*bits+7)//8}x}' + if self.lsb: + generator_poly = bitreflect(generator_poly, bits) + self.G = generator_poly ^ (1 << bits) + +# Generate tables for CRC computation using the "slice-by-N" method. +# N=1 corresponds to the traditional byte-at-a-time table. +def gen_slicebyN_tables(variants, n): + for v in variants: + print('') + print_header(v, f'Slice-by-{n} CRC table') + print(f'static const u{v.bits} __maybe_unused {v.name}_table[{256*n}] = {{') + s = '' + for i in range(256 * n): + # The i'th table entry is the CRC of the message consisting of byte + # i % 256 followed by i // 256 zero bytes. + poly = (bitreflect(i % 256, 8) if v.lsb else i % 256) << (v.bits + 8*(i//256)) + next_entry = fmt_poly(v, reduce(poly, v.G), v.bits) + ',' + if len(s + next_entry) > 71: + print(f'\t{s}') + s = '' + s += (' ' if s else '') + next_entry + if s: + print(f'\t{s}') + print('};') + +def print_riscv_const(v, bits_per_long, name, val, desc): + print(f'\t.{name} = {fmt_poly(v, val, bits_per_long)}, /* {desc} */') + +def do_gen_riscv_clmul_consts(v, bits_per_long): + (G, n, lsb) = (v.G, v.bits, v.lsb) + + pow_of_x = 3 * bits_per_long - (1 if lsb else 0) + print_riscv_const(v, bits_per_long, 'fold_across_2_longs_const_hi', + reduce(1 << pow_of_x, G), f'x^{pow_of_x} mod G') + pow_of_x = 2 * bits_per_long - (1 if lsb else 0) + print_riscv_const(v, bits_per_long, 'fold_across_2_longs_const_lo', + reduce(1 << pow_of_x, G), f'x^{pow_of_x} mod G') + + pow_of_x = bits_per_long - 1 + n + print_riscv_const(v, bits_per_long, 'barrett_reduction_const_1', + div(1 << pow_of_x, G), f'floor(x^{pow_of_x} / G)') + + val = G - (1 << n) + desc = f'G - x^{n}' + if lsb: + val <<= bits_per_long - n + desc = f'({desc}) * x^{bits_per_long - n}' + print_riscv_const(v, bits_per_long, 'barrett_reduction_const_2', val, desc) + +def gen_riscv_clmul_consts(variants): + print('') + print('struct crc_clmul_consts {'); + print('\tunsigned long fold_across_2_longs_const_hi;'); + print('\tunsigned long fold_across_2_longs_const_lo;'); + print('\tunsigned long barrett_reduction_const_1;'); + print('\tunsigned long barrett_reduction_const_2;'); + print('};'); + for v in variants: + print(''); + if v.bits > 32: + print_header(v, 'Constants') + print('#ifdef CONFIG_64BIT') + print(f'static const struct crc_clmul_consts {v.name}_consts __maybe_unused = {{') + do_gen_riscv_clmul_consts(v, 64) + print('};') + print('#endif') + else: + print_header(v, 'Constants') + print(f'static const struct crc_clmul_consts {v.name}_consts __maybe_unused = {{') + print('#ifdef CONFIG_64BIT') + do_gen_riscv_clmul_consts(v, 64) + print('#else') + do_gen_riscv_clmul_consts(v, 32) + print('#endif') + print('};') + +# Generate constants for carryless multiplication based CRC computation. +def gen_x86_pclmul_consts(variants): + # These are the distances, in bits, to generate folding constants for. + FOLD_DISTANCES = [2048, 1024, 512, 256, 128] + + for v in variants: + (G, n, lsb) = (v.G, v.bits, v.lsb) + print('') + print_header(v, 'CRC folding constants') + print('static const struct {') + if not lsb: + print('\tu8 bswap_mask[16];') + for i in FOLD_DISTANCES: + print(f'\tu64 fold_across_{i}_bits_consts[2];') + print('\tu8 shuf_table[48];') + print('\tu64 barrett_reduction_consts[2];') + print(f'}} {v.name}_consts ____cacheline_aligned __maybe_unused = {{') + + # Byte-reflection mask, needed for msb-first CRCs + if not lsb: + print('\t.bswap_mask = {' + ', '.join(str(i) for i in reversed(range(16))) + '},') + + # Fold constants for all distances down to 128 bits + for i in FOLD_DISTANCES: + print(f'\t.fold_across_{i}_bits_consts = {{') + # Given 64x64 => 128 bit carryless multiplication instructions, two + # 64-bit fold constants are needed per "fold distance" i: one for + # HI64_TERMS that is basically x^(i+64) mod G and one for LO64_TERMS + # that is basically x^i mod G. The exact values however undergo a + # couple adjustments, described below. + mults = [] + for j in [64, 0]: + pow_of_x = i + j + if lsb: + # Each 64x64 => 128 bit carryless multiplication instruction + # actually generates a 127-bit product in physical bits 0 + # through 126, which in the lsb-first case represent the + # coefficients of x^1 through x^127, not x^0 through x^126. + # Thus in the lsb-first case, each such instruction + # implicitly adds an extra factor of x. The below removes a + # factor of x from each constant to compensate for this. + # For n < 64 the x could be removed from either the reduced + # part or unreduced part, but for n == 64 the reduced part + # is the only option. Just always use the reduced part. + pow_of_x -= 1 + # Make a factor of x^(64-n) be applied unreduced rather than + # reduced, to cause the product to use only the x^(64-n) and + # higher terms and always be zero in the lower terms. Usually + # this makes no difference as it does not affect the product's + # congruence class mod G and the constant remains 64-bit, but + # part of the final reduction from 128 bits does rely on this + # property when it reuses one of the constants. + pow_of_x -= 64 - n + mults.append({ 'val': reduce(1 << pow_of_x, G) << (64 - n), + 'desc': f'(x^{pow_of_x} mod G) * x^{64-n}' }) + print_mult_pair(v, mults) + print('\t},') + + # Shuffle table for handling 1..15 bytes at end + print('\t.shuf_table = {') + print('\t\t' + (16*'-1, ').rstrip()) + print('\t\t' + ''.join(f'{i:2}, ' for i in range(16)).rstrip()) + print('\t\t' + (16*'-1, ').rstrip()) + print('\t},') + + # Barrett reduction constants for reducing 128 bits to the final CRC + print('\t.barrett_reduction_consts = {') + mults = [] + + val = div(1 << (63+n), G) + desc = f'floor(x^{63+n} / G)' + if not lsb: + val = (val << 1) - (1 << 64) + desc = f'({desc} * x) - x^64' + mults.append({ 'val': val, 'desc': desc }) + + val = G - (1 << n) + desc = f'G - x^{n}' + if lsb and n == 64: + assert (val & 1) != 0 # The x^0 term should always be nonzero. + val >>= 1 + desc = f'({desc} - x^0) / x' + else: + pow_of_x = 64 - n - (1 if lsb else 0) + val <<= pow_of_x + desc = f'({desc}) * x^{pow_of_x}' + mults.append({ 'val': val, 'desc': desc }) + + print_mult_pair(v, mults) + print('\t},') + + print('};') + +def parse_crc_variants(vars_string): + variants = [] + for var_string in vars_string.split(','): + bits, bit_order, generator_poly = var_string.split('_') + assert bits.startswith('crc') + bits = int(bits.removeprefix('crc')) + assert generator_poly.startswith('0x') + generator_poly = generator_poly.removeprefix('0x') + assert len(generator_poly) % 2 == 0 + generator_poly = int(generator_poly, 16) + variants.append(CrcVariant(bits, generator_poly, bit_order)) + return variants + +if len(sys.argv) != 3: + sys.stderr.write(f'Usage: {sys.argv[0]} CONSTS_TYPE[,CONSTS_TYPE]... CRC_VARIANT[,CRC_VARIANT]...\n') + sys.stderr.write(' CONSTS_TYPE can be sliceby[1-8], riscv_clmul, or x86_pclmul\n') + sys.stderr.write(' CRC_VARIANT is crc${num_bits}_${bit_order}_${generator_poly_as_hex}\n') + sys.stderr.write(' E.g. crc16_msb_0x8bb7 or crc32_lsb_0xedb88320\n') + sys.stderr.write(' Polynomial must use the given bit_order and exclude x^{num_bits}\n') + sys.exit(1) + +print('/* SPDX-License-Identifier: GPL-2.0-or-later */') +print('/*') +print(' * CRC constants generated by:') +print(' *') +print(f' *\t{sys.argv[0]} {" ".join(sys.argv[1:])}') +print(' *') +print(' * Do not edit manually.') +print(' */') +consts_types = sys.argv[1].split(',') +variants = parse_crc_variants(sys.argv[2]) +for consts_type in consts_types: + if consts_type.startswith('sliceby'): + gen_slicebyN_tables(variants, int(consts_type.removeprefix('sliceby'))) + elif consts_type == 'riscv_clmul': + gen_riscv_clmul_consts(variants) + elif consts_type == 'x86_pclmul': + gen_x86_pclmul_consts(variants) + else: + raise ValueError(f'Unknown consts_type: {consts_type}') diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 67e66333bd2a..94c78244a2b0 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -173,12 +173,14 @@ 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/make_fit.py b/scripts/make_fit.py index 4a1bb2f55861..1683e5ec6e67 100755 --- a/scripts/make_fit.py +++ b/scripts/make_fit.py @@ -279,7 +279,11 @@ def build_fit(args): if os.path.splitext(fname)[1] != '.dtb': continue - (model, compat, files) = process_dtb(fname, args) + try: + (model, compat, files) = process_dtb(fname, args) + except Exception as e: + sys.stderr.write(f"Error processing {fname}:\n") + raise e for fn in files: if fn not in fdts: diff --git a/scripts/selinux/install_policy.sh b/scripts/selinux/install_policy.sh index 24086793b0d8..db40237e60ce 100755 --- a/scripts/selinux/install_policy.sh +++ b/scripts/selinux/install_policy.sh @@ -6,27 +6,24 @@ if [ `id -u` -ne 0 ]; then exit 1 fi -SF=`which setfiles` -if [ $? -eq 1 ]; then +SF=`which setfiles` || { echo "Could not find setfiles" echo "Do you have policycoreutils installed?" exit 1 -fi +} -CP=`which checkpolicy` -if [ $? -eq 1 ]; then +CP=`which checkpolicy` || { echo "Could not find checkpolicy" echo "Do you have checkpolicy installed?" exit 1 -fi +} VERS=`$CP -V | awk '{print $1}'` -ENABLED=`which selinuxenabled` -if [ $? -eq 1 ]; then +ENABLED=`which selinuxenabled` || { echo "Could not find selinuxenabled" echo "Do you have libselinux-utils installed?" exit 1 -fi +} if selinuxenabled; then echo "SELinux is already enabled" diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 9f41575afd7a..7b4b3714b1af 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -28,6 +28,7 @@ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> +#include <stdbool.h> #include <string.h> #include <unistd.h> #include <errno.h> @@ -79,10 +80,16 @@ typedef union { Elf64_Sym e64; } Elf_Sym; +typedef union { + Elf32_Rela e32; + Elf64_Rela e64; +} Elf_Rela; + static uint32_t (*r)(const uint32_t *); static uint16_t (*r2)(const uint16_t *); static uint64_t (*r8)(const uint64_t *); static void (*w)(uint32_t, uint32_t *); +static void (*w8)(uint64_t, uint64_t *); typedef void (*table_sort_t)(char *, int); static struct elf_funcs { @@ -102,6 +109,10 @@ static struct elf_funcs { uint32_t (*sym_name)(Elf_Sym *sym); uint64_t (*sym_value)(Elf_Sym *sym); uint16_t (*sym_shndx)(Elf_Sym *sym); + uint64_t (*rela_offset)(Elf_Rela *rela); + uint64_t (*rela_info)(Elf_Rela *rela); + uint64_t (*rela_addend)(Elf_Rela *rela); + void (*rela_write_addend)(Elf_Rela *rela, uint64_t val); } e; static uint64_t ehdr64_shoff(Elf_Ehdr *ehdr) @@ -262,6 +273,38 @@ SYM_ADDR(value) SYM_WORD(name) SYM_HALF(shndx) +#define __maybe_unused __attribute__((__unused__)) + +#define RELA_ADDR(fn_name) \ +static uint64_t rela64_##fn_name(Elf_Rela *rela) \ +{ \ + return r8((uint64_t *)&rela->e64.r_##fn_name); \ +} \ + \ +static uint64_t rela32_##fn_name(Elf_Rela *rela) \ +{ \ + return r((uint32_t *)&rela->e32.r_##fn_name); \ +} \ + \ +static uint64_t __maybe_unused rela_##fn_name(Elf_Rela *rela) \ +{ \ + return e.rela_##fn_name(rela); \ +} + +RELA_ADDR(offset) +RELA_ADDR(info) +RELA_ADDR(addend) + +static void rela64_write_addend(Elf_Rela *rela, uint64_t val) +{ + w8(val, (uint64_t *)&rela->e64.r_addend); +} + +static void rela32_write_addend(Elf_Rela *rela, uint64_t val) +{ + w(val, (uint32_t *)&rela->e32.r_addend); +} + /* * Get the whole file as a programming convenience in order to avoid * malloc+lseek+read+free of many pieces. If successful, then mmap @@ -341,6 +384,16 @@ static void wle(uint32_t val, uint32_t *x) put_unaligned_le32(val, x); } +static void w8be(uint64_t val, uint64_t *x) +{ + put_unaligned_be64(val, x); +} + +static void w8le(uint64_t val, uint64_t *x) +{ + put_unaligned_le64(val, x); +} + /* * Move reserved section indices SHN_LORESERVE..SHN_HIRESERVE out of * the way to -256..-1, to avoid conflicting with real section @@ -398,13 +451,12 @@ static inline void *get_index(void *start, int entsize, int index) static int extable_ent_size; static int long_size; +#define ERRSTR_MAXSZ 256 #ifdef UNWINDER_ORC_ENABLED /* ORC unwinder only support X86_64 */ #include <asm/orc_types.h> -#define ERRSTR_MAXSZ 256 - static char g_err[ERRSTR_MAXSZ]; static int *g_orc_ip_table; static struct orc_entry *g_orc_table; @@ -499,7 +551,136 @@ static void *sort_orctable(void *arg) #endif #ifdef MCOUNT_SORT_ENABLED + +static int compare_values_64(const void *a, const void *b) +{ + uint64_t av = *(uint64_t *)a; + uint64_t bv = *(uint64_t *)b; + + if (av < bv) + return -1; + return av > bv; +} + +static int compare_values_32(const void *a, const void *b) +{ + uint32_t av = *(uint32_t *)a; + uint32_t bv = *(uint32_t *)b; + + if (av < bv) + return -1; + return av > bv; +} + +static int (*compare_values)(const void *a, const void *b); + +/* Only used for sorting mcount table */ +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; +} + +/* Used for when mcount/fentry is before the function entry */ +static int before_func; + +/* 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 + before_func < 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; + +static long rela_type; + +static char m_err[ERRSTR_MAXSZ]; struct elf_mcount_loc { Elf_Ehdr *ehdr; @@ -508,17 +689,197 @@ struct elf_mcount_loc { uint64_t stop_mcount_loc; }; +/* Fill the array with the content of the relocs */ +static int fill_relocs(void *ptr, uint64_t size, Elf_Ehdr *ehdr, uint64_t start_loc) +{ + Elf_Shdr *shdr_start; + Elf_Rela *rel; + unsigned int shnum; + unsigned int count = 0; + int shentsize; + void *array_end = ptr + size; + + shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr)); + shentsize = ehdr_shentsize(ehdr); + + shnum = ehdr_shnum(ehdr); + if (shnum == SHN_UNDEF) + shnum = shdr_size(shdr_start); + + for (int i = 0; i < shnum; i++) { + Elf_Shdr *shdr = get_index(shdr_start, shentsize, i); + void *end; + + if (shdr_type(shdr) != SHT_RELA) + continue; + + rel = (void *)ehdr + shdr_offset(shdr); + end = (void *)rel + shdr_size(shdr); + + for (; (void *)rel < end; rel = (void *)rel + shdr_entsize(shdr)) { + uint64_t offset = rela_offset(rel); + + if (offset >= start_loc && offset < start_loc + size) { + if (ptr + long_size > array_end) { + snprintf(m_err, ERRSTR_MAXSZ, + "Too many relocations"); + return -1; + } + + /* Make sure this has the correct type */ + if (rela_info(rel) != rela_type) { + snprintf(m_err, ERRSTR_MAXSZ, + "rela has type %lx but expected %lx\n", + (long)rela_info(rel), rela_type); + return -1; + } + + if (long_size == 4) + *(uint32_t *)ptr = rela_addend(rel); + else + *(uint64_t *)ptr = rela_addend(rel); + ptr += long_size; + count++; + } + } + } + return count; +} + +/* Put the sorted vals back into the relocation elements */ +static void replace_relocs(void *ptr, uint64_t size, Elf_Ehdr *ehdr, uint64_t start_loc) +{ + Elf_Shdr *shdr_start; + Elf_Rela *rel; + unsigned int shnum; + int shentsize; + + shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr)); + shentsize = ehdr_shentsize(ehdr); + + shnum = ehdr_shnum(ehdr); + if (shnum == SHN_UNDEF) + shnum = shdr_size(shdr_start); + + for (int i = 0; i < shnum; i++) { + Elf_Shdr *shdr = get_index(shdr_start, shentsize, i); + void *end; + + if (shdr_type(shdr) != SHT_RELA) + continue; + + rel = (void *)ehdr + shdr_offset(shdr); + end = (void *)rel + shdr_size(shdr); + + for (; (void *)rel < end; rel = (void *)rel + shdr_entsize(shdr)) { + uint64_t offset = rela_offset(rel); + + if (offset >= start_loc && offset < start_loc + size) { + if (long_size == 4) + rela_write_addend(rel, *(uint32_t *)ptr); + else + rela_write_addend(rel, *(uint64_t *)ptr); + ptr += long_size; + } + } + } +} + +static int fill_addrs(void *ptr, uint64_t size, void *addrs) +{ + void *end = ptr + size; + int count = 0; + + for (; ptr < end; ptr += long_size, addrs += long_size, count++) { + if (long_size == 4) + *(uint32_t *)ptr = r(addrs); + else + *(uint64_t *)ptr = r8(addrs); + } + return count; +} + +static void replace_addrs(void *ptr, uint64_t size, void *addrs) +{ + void *end = ptr + size; + + for (; ptr < end; ptr += long_size, addrs += long_size) { + if (long_size == 4) + w(*(uint32_t *)ptr, addrs); + else + w8(*(uint64_t *)ptr, addrs); + } +} + /* Sort the addresses stored between __start_mcount_loc to __stop_mcount_loc in vmlinux */ static void *sort_mcount_loc(void *arg) { struct elf_mcount_loc *emloc = (struct elf_mcount_loc *)arg; uint64_t offset = emloc->start_mcount_loc - shdr_addr(emloc->init_data_sec) + shdr_offset(emloc->init_data_sec); - uint64_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc; + uint64_t size = emloc->stop_mcount_loc - emloc->start_mcount_loc; unsigned char *start_loc = (void *)emloc->ehdr + offset; + Elf_Ehdr *ehdr = emloc->ehdr; + void *e_msg = NULL; + void *vals; + int count; + + vals = malloc(long_size * size); + if (!vals) { + snprintf(m_err, ERRSTR_MAXSZ, "Failed to allocate sort array"); + pthread_exit(m_err); + } + + if (sort_reloc) { + count = fill_relocs(vals, size, ehdr, emloc->start_mcount_loc); + /* gcc may use relocs to save the addresses, but clang does not. */ + if (!count) { + count = fill_addrs(vals, size, start_loc); + sort_reloc = 0; + } + } else + count = fill_addrs(vals, size, start_loc); - qsort(start_loc, count/long_size, long_size, compare_extable); - return NULL; + if (count < 0) { + e_msg = m_err; + goto out; + } + + if (count != size / long_size) { + snprintf(m_err, ERRSTR_MAXSZ, "Expected %u mcount elements but found %u\n", + (int)(size / long_size), count); + e_msg = m_err; + 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); + + if (sort_reloc) + replace_relocs(vals, size, ehdr, emloc->start_mcount_loc); + else + replace_addrs(vals, size, start_loc); + +out: + free(vals); + + pthread_exit(e_msg); } /* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */ @@ -555,6 +916,8 @@ 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, @@ -866,12 +1229,14 @@ static int do_file(char const *const fname, void *addr) r2 = r2le; r8 = r8le; w = wle; + w8 = w8le; break; case ELFDATA2MSB: r = rbe; r2 = r2be; r8 = r8be; w = wbe; + w8 = w8be; break; default: fprintf(stderr, "unrecognized ELF data encoding %d: %s\n", @@ -887,8 +1252,15 @@ static int do_file(char const *const fname, void *addr) } switch (r2(&ehdr->e32.e_machine)) { - case EM_386: case EM_AARCH64: +#ifdef MCOUNT_SORT_ENABLED + sort_reloc = true; + rela_type = 0x403; + /* arm64 uses patchable function entry placing before function */ + before_func = 8; +#endif + /* fallthrough */ + case EM_386: case EM_LOONGARCH: case EM_RISCV: case EM_S390: @@ -932,6 +1304,10 @@ static int do_file(char const *const fname, void *addr) .sym_name = sym32_name, .sym_value = sym32_value, .sym_shndx = sym32_shndx, + .rela_offset = rela32_offset, + .rela_info = rela32_info, + .rela_addend = rela32_addend, + .rela_write_addend = rela32_write_addend, }; e = efuncs; @@ -965,6 +1341,10 @@ static int do_file(char const *const fname, void *addr) .sym_name = sym64_name, .sym_value = sym64_value, .sym_shndx = sym64_shndx, + .rela_offset = rela64_offset, + .rela_info = rela64_info, + .rela_addend = rela64_addend, + .rela_write_addend = rela64_write_addend, }; e = efuncs; @@ -995,14 +1375,29 @@ 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; diff --git a/scripts/tracing/draw_functrace.py b/scripts/tracing/draw_functrace.py deleted file mode 100755 index 42fa87300941..000000000000 --- a/scripts/tracing/draw_functrace.py +++ /dev/null @@ -1,129 +0,0 @@ -#!/usr/bin/env python -# SPDX-License-Identifier: GPL-2.0-only - -""" -Copyright 2008 (c) Frederic Weisbecker <fweisbec@gmail.com> - -This script parses a trace provided by the function tracer in -kernel/trace/trace_functions.c -The resulted trace is processed into a tree to produce a more human -view of the call stack by drawing textual but hierarchical tree of -calls. Only the functions's names and the call time are provided. - -Usage: - Be sure that you have CONFIG_FUNCTION_TRACER - # mount -t tracefs nodev /sys/kernel/tracing - # echo function > /sys/kernel/tracing/current_tracer - $ cat /sys/kernel/tracing/trace_pipe > ~/raw_trace_func - Wait some times but not too much, the script is a bit slow. - Break the pipe (Ctrl + Z) - $ scripts/tracing/draw_functrace.py < ~/raw_trace_func > draw_functrace - Then you have your drawn trace in draw_functrace -""" - - -import sys, re - -class CallTree: - """ This class provides a tree representation of the functions - call stack. If a function has no parent in the kernel (interrupt, - syscall, kernel thread...) then it is attached to a virtual parent - called ROOT. - """ - ROOT = None - - def __init__(self, func, time = None, parent = None): - self._func = func - self._time = time - if parent is None: - self._parent = CallTree.ROOT - else: - self._parent = parent - self._children = [] - - def calls(self, func, calltime): - """ If a function calls another one, call this method to insert it - into the tree at the appropriate place. - @return: A reference to the newly created child node. - """ - child = CallTree(func, calltime, self) - self._children.append(child) - return child - - def getParent(self, func): - """ Retrieve the last parent of the current node that - has the name given by func. If this function is not - on a parent, then create it as new child of root - @return: A reference to the parent. - """ - tree = self - while tree != CallTree.ROOT and tree._func != func: - tree = tree._parent - if tree == CallTree.ROOT: - child = CallTree.ROOT.calls(func, None) - return child - return tree - - def __repr__(self): - return self.__toString("", True) - - def __toString(self, branch, lastChild): - if self._time is not None: - s = "%s----%s (%s)\n" % (branch, self._func, self._time) - else: - s = "%s----%s\n" % (branch, self._func) - - i = 0 - if lastChild: - branch = branch[:-1] + " " - while i < len(self._children): - if i != len(self._children) - 1: - s += "%s" % self._children[i].__toString(branch +\ - " |", False) - else: - s += "%s" % self._children[i].__toString(branch +\ - " |", True) - i += 1 - return s - -class BrokenLineException(Exception): - """If the last line is not complete because of the pipe breakage, - we want to stop the processing and ignore this line. - """ - pass - -class CommentLineException(Exception): - """ If the line is a comment (as in the beginning of the trace file), - just ignore it. - """ - pass - - -def parseLine(line): - line = line.strip() - if line.startswith("#"): - raise CommentLineException - m = re.match("[^]]+?\\] +([a-z.]+) +([0-9.]+): (\\w+) <-(\\w+)", line) - if m is None: - raise BrokenLineException - return (m.group(2), m.group(3), m.group(4)) - - -def main(): - CallTree.ROOT = CallTree("Root (Nowhere)", None, None) - tree = CallTree.ROOT - - for line in sys.stdin: - try: - calltime, callee, caller = parseLine(line) - except BrokenLineException: - break - except CommentLineException: - continue - tree = tree.getParent(caller) - tree = tree.calls(callee, calltime) - - print(CallTree.ROOT) - -if __name__ == "__main__": - main() |