cregit-Linux how code gets into the kernel

Release 4.15 scripts/kallsyms.c

Directory: scripts
/* Generate assembler source containing symbol information
 *
 * Copyright 2002       by Kai Germaschewski
 *
 * This software may be used and distributed according to the terms
 * of the GNU General Public License, incorporated herein by reference.
 *
 * Usage: nm -n vmlinux | scripts/kallsyms [--all-symbols] > symbols.S
 *
 *      Table compression uses all the unused char codes on the symbols and
 *  maps these to the most used substrings (tokens). For instance, it might
 *  map char code 0xF7 to represent "write_" and then in every symbol where
 *  "write_" appears it can be replaced by 0xF7, saving 5 bytes.
 *      The used codes themselves are also placed in the table so that the
 *  decompresion can work without "special cases".
 *      Applied to kernel symbols, this usually produces a compression ratio
 *  of about 50%.
 *
 */

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <limits.h>

#ifndef ARRAY_SIZE

#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
#endif


#define KSYM_NAME_LEN		128


struct sym_entry {
	
unsigned long long addr;
	
unsigned int len;
	
unsigned int start_pos;
	
unsigned char *sym;
	
unsigned int percpu_absolute;
};


struct addr_range {
	

const char *start_sym, *end_sym;
	

unsigned long long start, end;
};


static unsigned long long _text;

static unsigned long long relative_base;

static struct addr_range text_ranges[] = {
	{ "_stext",     "_etext"     },
	{ "_sinittext", "_einittext" },
	{ "_stext_l1",  "_etext_l1"  },	/* Blackfin on-chip L1 inst SRAM */
	{ "_stext_l2",  "_etext_l2"  },	/* Blackfin on-chip L2 SRAM */
};

#define text_range_text     (&text_ranges[0])

#define text_range_inittext (&text_ranges[1])


static struct addr_range percpu_range = {
	"__per_cpu_start", "__per_cpu_end", -1ULL, 0
};


static struct sym_entry *table;


static unsigned int table_size, table_cnt;

static int all_symbols = 0;

static int absolute_percpu = 0;

static char symbol_prefix_char = '\0';

static int base_relative = 0;


int token_profit[0x10000];

/* the table that holds the result of the compression */

unsigned char best_table[256][2];

unsigned char best_table_len[256];



static void usage(void) { fprintf(stderr, "Usage: kallsyms [--all-symbols] " "[--symbol-prefix=<prefix char>] " "[--base-relative] < in.map > out.S\n"); exit(1); }

Contributors

PersonTokensPropCommitsCommitProp
Kai Germaschewski1986.36%133.33%
Lei Ming29.09%133.33%
Ard Biesheuvel14.55%133.33%
Total22100.00%3100.00%

/* * This ignores the intensely annoying "mapping symbols" found * in ARM ELF files: $a, $t and $d. */
static inline int is_arm_mapping_symbol(const char *str) { return str[0] == '$' && strchr("axtd", str[1]) && (str[2] == '\0' || str[2] == '.'); }

Contributors

PersonTokensPropCommitsCommitProp
Russell King4597.83%150.00%
Kyle McMartin12.17%150.00%
Total46100.00%2100.00%


static int check_symbol_range(const char *sym, unsigned long long addr, struct addr_range *ranges, int entries) { size_t i; struct addr_range *ar; for (i = 0; i < entries; ++i) { ar = &ranges[i]; if (strcmp(sym, ar->start_sym) == 0) { ar->start = addr; return 0; } else if (strcmp(sym, ar->end_sym) == 0) { ar->end = addr; return 0; } } return 1; }

Contributors

PersonTokensPropCommitsCommitProp
Mike Frysinger8781.31%150.00%
Kees Cook2018.69%150.00%
Total107100.00%2100.00%


static int read_symbol(FILE *in, struct sym_entry *s) { char str[500]; char *sym, stype; int rc; rc = fscanf(in, "%llx %c %499s\n", &s->addr, &stype, str); if (rc != 3) { if (rc != EOF && fgets(str, 500, in) == NULL) fprintf(stderr, "Read error or end of file.\n"); return -1; } if (strlen(str) > KSYM_NAME_LEN) { fprintf(stderr, "Symbol %s too long for kallsyms (%zu vs %d).\n" "Please increase KSYM_NAME_LEN both in kernel and kallsyms.c\n", str, strlen(str), KSYM_NAME_LEN); return -1; } sym = str; /* skip prefix char */ if (symbol_prefix_char && str[0] == symbol_prefix_char) sym++; /* Ignore most absolute/undefined (?) symbols. */ if (strcmp(sym, "_text") == 0) _text = s->addr; else if (check_symbol_range(sym, s->addr, text_ranges, ARRAY_SIZE(text_ranges)) == 0) /* nothing to do */; else if (toupper(stype) == 'A') { /* Keep these useful absolute symbols */ if (strcmp(sym, "__kernel_syscall_via_break") && strcmp(sym, "__kernel_syscall_via_epc") && strcmp(sym, "__kernel_sigtramp") && strcmp(sym, "__gp")) return -1; } else if (toupper(stype) == 'U' || is_arm_mapping_symbol(sym)) return -1; /* exclude also MIPS ELF local symbols ($L123 instead of .L123) */ else if (str[0] == '$') return -1; /* exclude debugging symbols */ else if (stype == 'N' || stype == 'n') return -1; /* include the type field in the symbol name, so that it gets * compressed together */ s->len = strlen(str) + 1; s->sym = malloc(s->len + 1); if (!s->sym) { fprintf(stderr, "kallsyms failure: " "unable to allocate required amount of memory\n"); exit(EXIT_FAILURE); } strcpy((char *)s->sym + 1, str); s->sym[0] = stype; s->percpu_absolute = 0; /* Record if we've found __per_cpu_start/end. */ check_symbol_range(sym, s->addr, &percpu_range, 1); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Kai Germaschewski7921.41%15.00%
Paulo Marques4612.47%210.00%
Keith Owens3710.03%15.00%
Andi Kleen318.40%15.00%
Yoshinori Sato297.86%15.00%
Andrew Morton287.59%15.00%
Jesper Juhl225.96%15.00%
Eric W. Biedermann174.61%15.00%
Ralf Bächle154.07%15.00%
Rusty Russell154.07%15.00%
Sam Ravnborg123.25%15.00%
Jean Sacren102.71%15.00%
Kees Cook82.17%15.00%
Ard Biesheuvel61.63%15.00%
Russell King41.08%15.00%
Guenter Roeck41.08%15.00%
Robin Getz30.81%15.00%
Mike Frysinger20.54%15.00%
Fabio Estevam10.27%15.00%
Total369100.00%20100.00%


static int symbol_in_range(struct sym_entry *s, struct addr_range *ranges, int entries) { size_t i; struct addr_range *ar; for (i = 0; i < entries; ++i) { ar = &ranges[i]; if (s->addr >= ar->start && s->addr <= ar->end) return 1; } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Mike Frysinger5878.38%266.67%
Kees Cook1621.62%133.33%
Total74100.00%3100.00%


static int symbol_valid(struct sym_entry *s) { /* Symbols which vary between passes. Passes 1 and 2 must have * identical symbol lists. The kallsyms_* symbols below are only added * after pass 1, they would be included in pass 2 when --all-symbols is * specified so exclude them to get a stable symbol list. */ static char *special_symbols[] = { "kallsyms_addresses", "kallsyms_offsets", "kallsyms_relative_base", "kallsyms_num_syms", "kallsyms_names", "kallsyms_markers", "kallsyms_token_table", "kallsyms_token_index", /* Exclude linker generated symbols which vary between passes */ "_SDA_BASE_", /* ppc */ "_SDA2_BASE_", /* ppc */ NULL }; static char *special_prefixes[] = { "__crc_", /* modversions */ NULL }; static char *special_suffixes[] = { "_veneer", /* arm */ "_from_arm", /* arm */ "_from_thumb", /* arm */ NULL }; int i; char *sym_name = (char *)s->sym + 1; /* skip prefix char */ if (symbol_prefix_char && *sym_name == symbol_prefix_char) sym_name++; /* if --all-symbols is not specified, then symbols outside the text * and inittext sections are discarded */ if (!all_symbols) { if (symbol_in_range(s, text_ranges, ARRAY_SIZE(text_ranges)) == 0) return 0; /* Corner case. Discard any symbols with the same value as * _etext _einittext; they can move between pass 1 and 2 when * the kallsyms data are added. If these symbols move then * they may get dropped in pass 2, which breaks the kallsyms * rules. */ if ((s->addr == text_range_text->end && strcmp(sym_name, text_range_text->end_sym)) || (s->addr == text_range_inittext->end && strcmp(sym_name, text_range_inittext->end_sym))) return 0; } /* Exclude symbols which vary between passes. */ for (i = 0; special_symbols[i]; i++) if (strcmp(sym_name, special_symbols[i]) == 0) return 0; for (i = 0; special_prefixes[i]; i++) { int l = strlen(special_prefixes[i]); if (l <= strlen(sym_name) && strncmp(sym_name, special_prefixes[i], l) == 0) return 0; } for (i = 0; special_suffixes[i]; i++) { int l = strlen(sym_name) - strlen(special_suffixes[i]); if (l >= 0 && strcmp(sym_name + l, special_suffixes[i]) == 0) return 0; } return 1; }

Contributors

PersonTokensPropCommitsCommitProp
Ard Biesheuvel15247.35%426.67%
Keith Owens4112.77%213.33%
Paulo Marques3912.15%16.67%
Kai Germaschewski299.03%16.67%
Yoshinori Sato144.36%16.67%
Mike Frysinger144.36%16.67%
Sam Ravnborg134.05%16.67%
Kees Cook103.12%16.67%
Andrew Morton72.18%16.67%
Robin Getz20.62%213.33%
Total321100.00%15100.00%


static void read_map(FILE *in) { while (!feof(in)) { if (table_cnt >= table_size) { table_size += 10000; table = realloc(table, sizeof(*table) * table_size); if (!table) { fprintf(stderr, "out of memory\n"); exit (1); } } if (read_symbol(in, &table[table_cnt]) == 0) { table[table_cnt].start_pos = table_cnt; table_cnt++; } } }

Contributors

PersonTokensPropCommitsCommitProp
Kai Germaschewski7882.11%133.33%
Paulo Marques1717.89%266.67%
Total95100.00%3100.00%


static void output_label(char *label) { if (symbol_prefix_char) printf(".globl %c%s\n", symbol_prefix_char, label); else printf(".globl %s\n", label); printf("\tALGN\n"); if (symbol_prefix_char) printf("%c%s:\n", symbol_prefix_char, label); else printf("%s:\n", label); }

Contributors

PersonTokensPropCommitsCommitProp
Yoshinori Sato2849.12%120.00%
Kai Germaschewski1526.32%240.00%
Paulo Marques1221.05%120.00%
Andi Kleen23.51%120.00%
Total57100.00%5100.00%

/* uncompress a compressed symbol. When this function is called, the best table * might still be compressed itself, so the function needs to be recursive */
static int expand_symbol(unsigned char *data, int len, char *result) { int c, rlen, total=0; while (len) { c = *data; /* if the table holds a single char that is the same as the one * we are looking for, then end the search */ if (best_table[c][0]==c && best_table_len[c]==1) { *result++ = c; total++; } else { /* if not, recurse and expand */ rlen = expand_symbol(best_table[c], best_table_len[c], result); total += rlen; result += rlen; } data++; len--; } *result=0; return total; }

Contributors

PersonTokensPropCommitsCommitProp
Paulo Marques112100.00%1100.00%
Total112100.00%1100.00%


static int symbol_absolute(struct sym_entry *s) { return s->percpu_absolute; }

Contributors

PersonTokensPropCommitsCommitProp
Kees Cook1593.75%150.00%
Ard Biesheuvel16.25%150.00%
Total16100.00%2100.00%


static void write_src(void) { unsigned int i, k, off; unsigned int best_idx[256]; unsigned int *markers; char buf[KSYM_NAME_LEN]; printf("#include <asm/types.h>\n"); printf("#if BITS_PER_LONG == 64\n"); printf("#define PTR .quad\n"); printf("#define ALGN .align 8\n"); printf("#else\n"); printf("#define PTR .long\n"); printf("#define ALGN .align 4\n"); printf("#endif\n"); printf("\t.section .rodata, \"a\"\n"); /* Provide proper symbols relocatability by their relativeness * to a fixed anchor point in the runtime image, either '_text' * for absolute address tables, in which case the linker will * emit the final addresses at build time. Otherwise, use the * offset relative to the lowest value encountered of all relative * symbols, and emit non-relocatable fixed offsets that will be fixed * up at runtime. * * The symbol names cannot be used to construct normal symbol * references as the list of symbols contains symbols that are * declared static and are private to their .o files. This prevents * .tmp_kallsyms.o or any other object from referencing them. */ if (!base_relative) output_label("kallsyms_addresses"); else output_label("kallsyms_offsets"); for (i = 0; i < table_cnt; i++) { if (base_relative) { long long offset; int overflow; if (!absolute_percpu) { offset = table[i].addr - relative_base; overflow = (offset < 0 || offset > UINT_MAX); } else if (symbol_absolute(&table[i])) { offset = table[i].addr; overflow = (offset < 0 || offset > INT_MAX); } else { offset = relative_base - table[i].addr - 1; overflow = (offset < INT_MIN || offset >= 0); } if (overflow) { fprintf(stderr, "kallsyms failure: " "%s symbol value %#llx out of range in relative mode\n", symbol_absolute(&table[i]) ? "absolute" : "relative", table[i].addr); exit(EXIT_FAILURE); } printf("\t.long\t%#x\n", (int)offset); } else if (!symbol_absolute(&table[i])) { if (_text <= table[i].addr) printf("\tPTR\t_text + %#llx\n", table[i].addr - _text); else printf("\tPTR\t_text - %#llx\n", _text - table[i].addr); } else { printf("\tPTR\t%#llx\n", table[i].addr); } } printf("\n"); if (base_relative) { output_label("kallsyms_relative_base"); printf("\tPTR\t_text - %#llx\n", _text - relative_base); printf("\n"); } output_label("kallsyms_num_syms"); printf("\tPTR\t%d\n", table_cnt); printf("\n"); /* table of offset markers, that give the offset in the compressed stream * every 256 symbols */ markers = malloc(sizeof(unsigned int) * ((table_cnt + 255) / 256)); if (!markers) { fprintf(stderr, "kallsyms failure: " "unable to allocate required memory\n"); exit(EXIT_FAILURE); } output_label("kallsyms_names"); off = 0; for (i = 0; i < table_cnt; i++) { if ((i & 0xFF) == 0) markers[i >> 8] = off; printf("\t.byte 0x%02x", table[i].len); for (k = 0; k < table[i].len; k++) printf(", 0x%02x", table[i].sym[k]); printf("\n"); off += table[i].len + 1; } printf("\n"); output_label("kallsyms_markers"); for (i = 0; i < ((table_cnt + 255) >> 8); i++) printf("\tPTR\t%d\n", markers[i]); printf("\n"); free(markers); output_label("kallsyms_token_table"); off = 0; for (i = 0; i < 256; i++) { best_idx[i] = off; expand_symbol(best_table[i], best_table_len[i], buf); printf("\t.asciz\t\"%s\"\n", buf); off += strlen(buf) + 1; } printf("\n"); output_label("kallsyms_token_index"); for (i = 0; i < 256; i++) printf("\t.short\t%d\n", best_idx[i]); printf("\n"); }

Contributors

PersonTokensPropCommitsCommitProp
Paulo Marques38756.91%218.18%
Ard Biesheuvel19328.38%19.09%
Eric W. Biedermann284.12%19.09%
Vivek Goyal233.38%19.09%
Kai Germaschewski223.24%218.18%
Jesper Juhl202.94%19.09%
Andrew Morton30.44%19.09%
Kees Cook30.44%19.09%
Jan Beulich10.15%19.09%
Total680100.00%11100.00%

/* table lookup compression functions */ /* count all the possible tokens in a symbol */
static void learn_symbol(unsigned char *symbol, int len) { int i; for (i = 0; i < len - 1; i++) token_profit[ symbol[i] + (symbol[i + 1] << 8) ]++; }

Contributors

PersonTokensPropCommitsCommitProp
Paulo Marques52100.00%2100.00%
Total52100.00%2100.00%

/* decrease the count for all the possible tokens in a symbol */
static void forget_symbol(unsigned char *symbol, int len) { int i; for (i = 0; i < len - 1; i++) token_profit[ symbol[i] + (symbol[i + 1] << 8) ]--; }

Contributors

PersonTokensPropCommitsCommitProp
Paulo Marques52100.00%2100.00%
Total52100.00%2100.00%

/* remove all the invalid symbols from the table and do the initial token count */
static void build_initial_tok_table(void) { unsigned int i, pos; pos = 0; for (i = 0; i < table_cnt; i++) { if ( symbol_valid(&table[i]) ) { if (pos != i) table[pos] = table[i]; learn_symbol(table[pos].sym, table[pos].len); pos++; } } table_cnt = pos; }

Contributors

PersonTokensPropCommitsCommitProp
Paulo Marques86100.00%2100.00%
Total86100.00%2100.00%


static void *find_token(unsigned char *str, int len, unsigned char *token) { int i; for (i = 0; i < len - 1; i++) { if (str[i] == token[0] && str[i+1] == token[1]) return &str[i]; } return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Paulo Marques74100.00%1100.00%
Total74100.00%1100.00%

/* replace a given token in all the valid symbols. Use the sampled symbols * to update the counts */
static void compress_symbols(unsigned char *str, int idx) { unsigned int i, len, size; unsigned char *p1, *p2; for (i = 0; i < table_cnt; i++) { len = table[i].len; p1 = table[i].sym; /* find the token on the symbol */ p2 = find_token(p1, len, str); if (!p2) continue; /* decrease the counts for this symbol's tokens */ forget_symbol(table[i].sym, len); size = len; do { *p2 = idx; p2++; size -= (p2 - p1); memmove(p2, p2 + 1, size); p1 = p2; len--; if (size < 2) break; /* find the token on the symbol */ p2 = find_token(p1, size, str); } while (p2); table[i].len = len; /* increase the counts for this symbol's new tokens */ learn_symbol(table[i].sym, len); } }

Contributors

PersonTokensPropCommitsCommitProp
Paulo Marques181100.00%3100.00%
Total181100.00%3100.00%

/* search the token with the maximum profit */
static int find_best_token(void) { int i, best, bestprofit; bestprofit=-10000; best = 0; for (i = 0; i < 0x10000; i++) { if (token_profit[i] > bestprofit) { best = i; bestprofit = token_profit[i]; } } return best; }

Contributors

PersonTokensPropCommitsCommitProp
Paulo Marques6398.44%266.67%
Kai Germaschewski11.56%133.33%
Total64100.00%3100.00%

/* this is the core of the algorithm: calculate the "best" table */
static void optimize_result(void) { int i, best; /* using the '\0' symbol last allows compress_symbols to use standard * fast string functions */ for (i = 255; i >= 0; i--) { /* if this table slot is empty (it is not used by an actual * original char code */ if (!best_table_len[i]) { /* find the token with the breates profit value */ best = find_best_token(); if (token_profit[best] == 0) break; /* place it in the "best" table */ best_table_len[i] = 2; best_table[i][0] = best & 0xFF; best_table[i][1] = (best >> 8) & 0xFF; /* replace this token in all the valid symbols */ compress_symbols(best_table[i], i); } } }

Contributors

PersonTokensPropCommitsCommitProp
Paulo Marques6966.99%250.00%
Kai Germaschewski2423.30%125.00%
Xiaochen Wang109.71%125.00%
Total103100.00%4100.00%

/* start by placing the symbols that are actually used on the table */
static