1 files changed, 213 insertions, 163 deletions

diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 54ad86d13784..653b92f6d4c8 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -5,7 +5,8 @@
  * 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
+ * Usage: kallsyms [--all-symbols] [--absolute-percpu]
+ *                         [--base-relative] [--lto-clang] in.map > out.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
@@ -18,6 +19,8 @@
  *
  */
 
+#include <errno.h>
+#include <getopt.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -27,11 +30,12 @@
 
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
 
-#define KSYM_NAME_LEN		128
+#define KSYM_NAME_LEN		512
 
 struct sym_entry {
 	unsigned long long addr;
 	unsigned int len;
+	unsigned int seq;
 	unsigned int start_pos;
 	unsigned int percpu_absolute;
 	unsigned char sym[];
@@ -60,6 +64,7 @@ static unsigned int table_size, table_cnt;
 static int all_symbols;
 static int absolute_percpu;
 static int base_relative;
+static int lto_clang;
 
 static int token_profit[0x10000];
 
@@ -70,8 +75,8 @@ static unsigned char best_table_len[256];
 
 static void usage(void)
 {
-	fprintf(stderr, "Usage: kallsyms [--all-symbols] "
-			"[--base-relative] < in.map > out.S\n");
+	fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] "
+			"[--base-relative] [--lto-clang] in.map > out.S\n");
 	exit(1);
 }
 
@@ -82,86 +87,7 @@ static char *sym_name(const struct sym_entry *s)
 
 static bool is_ignored_symbol(const char *name, char type)
 {
-	/* Symbol names that exactly match to the following are ignored.*/
-	static const char * const ignored_symbols[] = {
-		/*
-		 * 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.
-		 */
-		"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
-	};
-
-	/* Symbol names that begin with the following are ignored.*/
-	static const char * const ignored_prefixes[] = {
-		"$",			/* local symbols for ARM, MIPS, etc. */
-		".LASANPC",		/* s390 kasan local symbols */
-		"__crc_",		/* modversions */
-		"__efistub_",		/* arm64 EFI stub namespace */
-		"__kvm_nvhe_",		/* arm64 non-VHE KVM namespace */
-		"__AArch64ADRPThunk_",	/* arm64 lld */
-		"__ARMV5PILongThunk_",	/* arm lld */
-		"__ARMV7PILongThunk_",
-		"__ThumbV7PILongThunk_",
-		"__LA25Thunk_",		/* mips lld */
-		"__microLA25Thunk_",
-		NULL
-	};
-
-	/* Symbol names that end with the following are ignored.*/
-	static const char * const ignored_suffixes[] = {
-		"_from_arm",		/* arm */
-		"_from_thumb",		/* arm */
-		"_veneer",		/* arm */
-		NULL
-	};
-
-	/* Symbol names that contain the following are ignored.*/
-	static const char * const ignored_matches[] = {
-		".long_branch.",	/* ppc stub */
-		".plt_branch.",		/* ppc stub */
-		NULL
-	};
-
-	const char * const *p;
-
-	for (p = ignored_symbols; *p; p++)
-		if (!strcmp(name, *p))
-			return true;
-
-	for (p = ignored_prefixes; *p; p++)
-		if (!strncmp(name, *p, strlen(*p)))
-			return true;
-
-	for (p = ignored_suffixes; *p; p++) {
-		int l = strlen(name) - strlen(*p);
-
-		if (l >= 0 && !strcmp(name + l, *p))
-			return true;
-	}
-
-	for (p = ignored_matches; *p; p++) {
-		if (strstr(name, *p))
-			return true;
-	}
-
-	if (type == 'U' || type == 'u')
-		return true;
-	/* exclude debugging symbols */
-	if (type == 'N' || type == 'n')
+	if (type == 'u' || type == 'n')
 		return true;
 
 	if (toupper(type) == 'A') {
@@ -195,24 +121,41 @@ static void check_symbol_range(const char *sym, unsigned long long addr,
 	}
 }
 
-static struct sym_entry *read_symbol(FILE *in)
+static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
 {
-	char name[500], type;
+	char *name, type, *p;
 	unsigned long long addr;
-	unsigned int len;
+	size_t len;
+	ssize_t readlen;
 	struct sym_entry *sym;
-	int rc;
 
-	rc = fscanf(in, "%llx %c %499s\n", &addr, &type, name);
-	if (rc != 3) {
-		if (rc != EOF && fgets(name, 500, in) == NULL)
-			fprintf(stderr, "Read error or end of file.\n");
+	errno = 0;
+	readlen = getline(buf, buf_len, in);
+	if (readlen < 0) {
+		if (errno) {
+			perror("read_symbol");
+			exit(EXIT_FAILURE);
+		}
 		return NULL;
 	}
-	if (strlen(name) >= KSYM_NAME_LEN) {
+
+	if ((*buf)[readlen - 1] == '\n')
+		(*buf)[readlen - 1] = 0;
+
+	addr = strtoull(*buf, &p, 16);
+
+	if (*buf == p || *p++ != ' ' || !isascii((type = *p++)) || *p++ != ' ') {
+		fprintf(stderr, "line format error\n");
+		exit(EXIT_FAILURE);
+	}
+
+	name = p;
+	len = strlen(name);
+
+	if (len >= KSYM_NAME_LEN) {
 		fprintf(stderr, "Symbol %s too long for kallsyms (%zu >= %d).\n"
 				"Please increase KSYM_NAME_LEN both in kernel and kallsyms.c\n",
-			name, strlen(name), KSYM_NAME_LEN);
+			name, len, KSYM_NAME_LEN);
 		return NULL;
 	}
 
@@ -228,8 +171,7 @@ static struct sym_entry *read_symbol(FILE *in)
 
 	/* include the type field in the symbol name, so that it gets
 	 * compressed together */
-
-	len = strlen(name) + 1;
+	len++;
 
 	sym = malloc(sizeof(*sym) + len + 1);
 	if (!sym) {
@@ -312,12 +254,21 @@ static void shrink_table(void)
 	}
 }
 
-static void read_map(FILE *in)
+static void read_map(const char *in)
 {
+	FILE *fp;
 	struct sym_entry *sym;
+	char *buf = NULL;
+	size_t buflen = 0;
 
-	while (!feof(in)) {
-		sym = read_symbol(in);
+	fp = fopen(in, "r");
+	if (!fp) {
+		perror(in);
+		exit(1);
+	}
+
+	while (!feof(fp)) {
+		sym = read_symbol(fp, &buf, &buflen);
 		if (!sym)
 			continue;
 
@@ -328,12 +279,16 @@ static void read_map(FILE *in)
 			table = realloc(table, sizeof(*table) * table_size);
 			if (!table) {
 				fprintf(stderr, "out of memory\n");
+				fclose(fp);
 				exit (1);
 			}
 		}
 
 		table[table_cnt++] = sym;
 	}
+
+	free(buf);
+	fclose(fp);
 }
 
 static void output_label(const char *label)
@@ -384,6 +339,50 @@ static int symbol_absolute(const struct sym_entry *s)
 	return s->percpu_absolute;
 }
 
+static void cleanup_symbol_name(char *s)
+{
+	char *p;
+
+	/*
+	 * ASCII[.]   = 2e
+	 * ASCII[0-9] = 30,39
+	 * ASCII[A-Z] = 41,5a
+	 * ASCII[_]   = 5f
+	 * ASCII[a-z] = 61,7a
+	 *
+	 * As above, replacing the first '.' in ".llvm." with '\0' does not
+	 * affect the main sorting, but it helps us with subsorting.
+	 */
+	p = strstr(s, ".llvm.");
+	if (p)
+		*p = '\0';
+}
+
+static int compare_names(const void *a, const void *b)
+{
+	int ret;
+	const struct sym_entry *sa = *(const struct sym_entry **)a;
+	const struct sym_entry *sb = *(const struct sym_entry **)b;
+
+	ret = strcmp(sym_name(sa), sym_name(sb));
+	if (!ret) {
+		if (sa->addr > sb->addr)
+			return 1;
+		else if (sa->addr < sb->addr)
+			return -1;
+
+		/* keep old order */
+		return (int)(sa->seq - sb->seq);
+	}
+
+	return ret;
+}
+
+static void sort_symbols_by_name(void)
+{
+	qsort(table, table_cnt, sizeof(table[0]), compare_names);
+}
+
 static void write_src(void)
 {
 	unsigned int i, k, off;
@@ -402,6 +401,89 @@ static void write_src(void)
 
 	printf("\t.section .rodata, \"a\"\n");
 
+	output_label("kallsyms_num_syms");
+	printf("\t.long\t%u\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;
+		table[i]->seq = i;
+
+		/* There cannot be any symbol of length zero. */
+		if (table[i]->len == 0) {
+			fprintf(stderr, "kallsyms failure: "
+				"unexpected zero symbol length\n");
+			exit(EXIT_FAILURE);
+		}
+
+		/* Only lengths that fit in up-to-two-byte ULEB128 are supported. */
+		if (table[i]->len > 0x3FFF) {
+			fprintf(stderr, "kallsyms failure: "
+				"unexpected huge symbol length\n");
+			exit(EXIT_FAILURE);
+		}
+
+		/* Encode length with ULEB128. */
+		if (table[i]->len <= 0x7F) {
+			/* Most symbols use a single byte for the length. */
+			printf("\t.byte 0x%02x", table[i]->len);
+			off += table[i]->len + 1;
+		} else {
+			/* "Big" symbols use two bytes. */
+			printf("\t.byte 0x%02x, 0x%02x",
+				(table[i]->len & 0x7F) | 0x80,
+				(table[i]->len >> 7) & 0x7F);
+			off += table[i]->len + 2;
+		}
+		for (k = 0; k < table[i]->len; k++)
+			printf(", 0x%02x", table[i]->sym[k]);
+		printf("\n");
+	}
+	printf("\n");
+
+	/*
+	 * Now that we wrote out the compressed symbol names, restore the
+	 * original names, which are needed in some of the later steps.
+	 */
+	for (i = 0; i < table_cnt; i++) {
+		expand_symbol(table[i]->sym, table[i]->len, buf);
+		strcpy((char *)table[i]->sym, buf);
+	}
+
+	output_label("kallsyms_markers");
+	for (i = 0; i < ((table_cnt + 255) >> 8); i++)
+		printf("\t.long\t%u\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");
+
 	if (!base_relative)
 		output_label("kallsyms_addresses");
 	else
@@ -436,7 +518,7 @@ static void write_src(void)
 					table[i]->addr);
 				exit(EXIT_FAILURE);
 			}
-			printf("\t.long\t%#x\n", (int)offset);
+			printf("\t.long\t%#x	/* %s */\n", (int)offset, table[i]->sym);
 		} else if (!symbol_absolute(table[i])) {
 			output_address(table[i]->addr);
 		} else {
@@ -451,54 +533,17 @@ static void write_src(void)
 		printf("\n");
 	}
 
-	output_label("kallsyms_num_syms");
-	printf("\t.long\t%u\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("\t.long\t%u\n", markers[i]);
-	printf("\n");
+	if (lto_clang)
+		for (i = 0; i < table_cnt; i++)
+			cleanup_symbol_name((char *)table[i]->sym);
 
-	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]);
+	sort_symbols_by_name();
+	output_label("kallsyms_seqs_of_names");
+	for (i = 0; i < table_cnt; i++)
+		printf("\t.byte 0x%02x, 0x%02x, 0x%02x\n",
+			(unsigned char)(table[i]->seq >> 16),
+			(unsigned char)(table[i]->seq >> 8),
+			(unsigned char)(table[i]->seq >> 0));
 	printf("\n");
 }
 
@@ -524,7 +569,7 @@ static void forget_symbol(const unsigned char *symbol, int len)
 }
 
 /* do the initial token count */
-static void build_initial_tok_table(void)
+static void build_initial_token_table(void)
 {
 	unsigned int i;
 
@@ -649,7 +694,7 @@ static void insert_real_symbols_in_table(void)
 
 static void optimize_token_table(void)
 {
-	build_initial_tok_table();
+	build_initial_token_table();
 
 	insert_real_symbols_in_table();
 
@@ -764,22 +809,27 @@ static void record_relative_base(void)
 
 int main(int argc, char **argv)
 {
-	if (argc >= 2) {
-		int i;
-		for (i = 1; i < argc; i++) {
-			if(strcmp(argv[i], "--all-symbols") == 0)
-				all_symbols = 1;
-			else if (strcmp(argv[i], "--absolute-percpu") == 0)
-				absolute_percpu = 1;
-			else if (strcmp(argv[i], "--base-relative") == 0)
-				base_relative = 1;
-			else
-				usage();
-		}
-	} else if (argc != 1)
+	while (1) {
+		static const struct option long_options[] = {
+			{"all-symbols",     no_argument, &all_symbols,     1},
+			{"absolute-percpu", no_argument, &absolute_percpu, 1},
+			{"base-relative",   no_argument, &base_relative,   1},
+			{"lto-clang",       no_argument, &lto_clang,       1},
+			{},
+		};
+
+		int c = getopt_long(argc, argv, "", long_options, NULL);
+
+		if (c == -1)
+			break;
+		if (c != 0)
+			usage();
+	}
+
+	if (optind >= argc)
 		usage();
 
-	read_map(stdin);
+	read_map(argv[optind]);
 	shrink_table();
 	if (absolute_percpu)
 		make_percpus_absolute();