@@ -1179,7 +1179,7 @@ cmd_link-vmlinux = \
$(CONFIG_SHELL) $< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)"; \
$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
-vmlinux: scripts/link-vmlinux.sh autoksyms_recursive $(vmlinux-deps) FORCE
+vmlinux: scripts/link-vmlinux.sh autoksyms_recursive $(vmlinux-deps) modules_thick.builtin FORCE
+$(call if_changed_dep,link-vmlinux)
targets := vmlinux
@@ -1526,6 +1526,14 @@ config POSIX_TIMERS
If unsure say y.
+config KALLMODSYMS
+ default y
+ bool "Enable support for /proc/kallmodsyms" if EXPERT
+ depends on KALLSYMS
+ help
+ This option enables the /proc/kallmodsyms file, which maps symbols
+ to addresses and their associated modules.
+
config PRINTK
default y
bool "Enable support for printk" if EXPERT
@@ -32,6 +32,12 @@ HOSTCFLAGS_sorttable.o += -DUNWINDER_ORC_ENABLED
HOSTLDLIBS_sorttable = -lpthread
endif
+kallsyms-objs := kallsyms.o
+
+ifdef CONFIG_KALLMODSYMS
+kallsyms-objs += modules_thick.o
+endif
+
# The following programs are only built on demand
hostprogs += unifdef
@@ -5,7 +5,10 @@
* 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: nm -n vmlinux
+ * | scripts/kallsyms [--all-symbols] [--absolute-percpu]
+ * [--base-relative] [--builtin=modules_thick.builtin]
+ * > 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
@@ -24,6 +27,10 @@
#include <string.h>
#include <ctype.h>
#include <limits.h>
+#include <assert.h>
+#include "modules_thick.h"
+
+#include "../include/generated/autoconf.h"
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
@@ -67,11 +74,116 @@ static int token_profit[0x10000];
static unsigned char best_table[256][2];
static unsigned char best_table_len[256];
+#ifdef CONFIG_KALLMODSYMS
+static unsigned int strhash(const char *s)
+{
+ /* fnv32 hash */
+ unsigned int hash = 2166136261U;
+
+ for (; *s; s++)
+ hash = (hash ^ *s) * 0x01000193;
+ return hash;
+}
+
+#define OBJ2MOD_BITS 10
+#define OBJ2MOD_N (1 << OBJ2MOD_BITS)
+#define OBJ2MOD_MASK (OBJ2MOD_N - 1)
+struct obj2mod_elem {
+ char *obj;
+ char *mods; /* sorted module name strtab */
+ size_t nmods; /* number of modules in "mods" */
+ size_t mods_size; /* size of all mods together */
+ int mod_offset; /* offset in .kallsyms_module_names */
+ struct obj2mod_elem *obj2mod_next;
+};
+
+/*
+ * Map from object files to obj2mod entries (a unique mapping).
+ */
+
+static struct obj2mod_elem *obj2mod[OBJ2MOD_N];
+static size_t num_objfiles;
+
+/*
+ * An ordered list of address ranges and the objfile that occupies that range.
+ */
+struct addrmap_entry {
+ unsigned long long addr;
+ struct obj2mod_elem *objfile;
+};
+static struct addrmap_entry *addrmap;
+static int addrmap_num, addrmap_alloced;
+
+static void obj2mod_init(void)
+{
+ memset(obj2mod, 0, sizeof(obj2mod));
+}
+
+static struct obj2mod_elem *obj2mod_get(const char *obj)
+{
+ int i = strhash(obj) & OBJ2MOD_MASK;
+ struct obj2mod_elem *elem;
+
+ for (elem = obj2mod[i]; elem; elem = elem->obj2mod_next) {
+ if (strcmp(elem->obj, obj) == 0)
+ return elem;
+ }
+ return NULL;
+}
+
+/*
+ * Note that a given object file is found in some module, interning it in the
+ * obj2mod hash. Should not be called more than once for any given (module,
+ * object) pair.
+ */
+static void obj2mod_add(char *obj, char *mod)
+{
+ int i = strhash(obj) & OBJ2MOD_MASK;
+ struct obj2mod_elem *elem;
+
+ elem = obj2mod_get(obj);
+ if (!elem) {
+ elem = malloc(sizeof(struct obj2mod_elem));
+ if (!elem)
+ goto oom;
+ memset(elem, 0, sizeof(struct obj2mod_elem));
+ elem->obj = strdup(obj);
+ if (!elem->obj)
+ goto oom;
+ elem->mods = strdup(mod);
+ if (!elem->mods)
+ goto oom;
+
+ elem->obj2mod_next = obj2mod[i];
+ obj2mod[i] = elem;
+ num_objfiles++;
+ } else {
+ elem->mods = realloc(elem->mods, elem->mods_size +
+ strlen(mod) + 1);
+ if (!elem->mods)
+ goto oom;
+ strcpy(elem->mods + elem->mods_size, mod);
+ }
+
+ elem->mods_size += strlen(mod) + 1;
+ elem->nmods++;
+ if (elem->nmods > 255) {
+ fprintf(stderr, "kallsyms: %s: too many modules associated with this object file\n",
+ obj);
+ exit(EXIT_FAILURE);
+ }
+ return;
+oom:
+ fprintf(stderr, "kallsyms: out of memory\n");
+ exit(1);
+}
+#endif /* CONFIG_KALLMODSYMS */
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] [--builtin=modules_thick.builtin] "
+ "< nm_vmlinux.out > symbols.S\n");
exit(1);
}
@@ -95,10 +207,16 @@ static bool is_ignored_symbol(const char *name, char type)
"kallsyms_offsets",
"kallsyms_relative_base",
"kallsyms_num_syms",
+ "kallsyms_num_modules",
"kallsyms_names",
"kallsyms_markers",
"kallsyms_token_table",
"kallsyms_token_index",
+ "kallsyms_module_offsets",
+ "kallsyms_module_addresses",
+ "kallsyms_modules",
+ "kallsyms_module_names",
+ "kallsyms_module_names_len",
/* Exclude linker generated symbols which vary between passes */
"_SDA_BASE_", /* ppc */
"_SDA2_BASE_", /* ppc */
@@ -246,8 +364,8 @@ static struct sym_entry *read_symbol(FILE *in)
return sym;
}
-static int symbol_in_range(const struct sym_entry *s,
- const struct addr_range *ranges, int entries)
+static int addr_in_range(unsigned long long addr,
+ const struct addr_range *ranges, int entries)
{
size_t i;
const struct addr_range *ar;
@@ -255,7 +373,7 @@ static int symbol_in_range(const struct sym_entry *s,
for (i = 0; i < entries; ++i) {
ar = &ranges[i];
- if (s->addr >= ar->start && s->addr <= ar->end)
+ if (addr >= ar->start && addr <= ar->end)
return 1;
}
@@ -269,8 +387,8 @@ static int symbol_valid(const struct sym_entry *s)
/* 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)
+ if (addr_in_range(s->addr, 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
@@ -352,6 +470,121 @@ static void output_address(unsigned long long addr)
printf("\tPTR\t_text - %#llx\n", _text - addr);
}
+#ifdef CONFIG_KALLMODSYMS
+/* Output the .kallmodsyms_modules symbol content. */
+static void output_kallmodsyms_modules(void)
+{
+ struct obj2mod_elem *elem;
+ size_t offset = 1;
+ size_t i;
+
+ /*
+ * Traverse and emit, updating mod_offset accordingly.
+ * Emit a single \0 at the start, to encode non-modular objfiles.
+ */
+ output_label("kallsyms_module_names");
+ printf("\t.byte\t0\n");
+ for (i = 0; i < OBJ2MOD_N; i++) {
+ for (elem = obj2mod[i]; elem;
+ elem = elem->obj2mod_next) {
+ const char *onemod;
+ size_t i;
+
+ elem->mod_offset = offset;
+ onemod = elem->mods;
+
+ /*
+ * Technically this is a waste of space: we could just
+ * as well implement multimodule entries by pointing one
+ * byte further back, to the trailing \0 of the previous
+ * entry, but doing it this way makes it more obvious
+ * when an entry is a multimodule entry.
+ */
+ if (elem->nmods != 1) {
+ printf("\t.byte\t0\n");
+ printf("\t.byte\t%zi\n", elem->nmods);
+ offset += 2;
+ }
+
+ for (i = elem->nmods; i > 0; i--) {
+ printf("\t.asciz\t\"%s\"\n", onemod);
+ offset += strlen(onemod) + 1;
+ onemod += strlen(onemod) + 1;
+ }
+ }
+ }
+ printf("\n");
+ output_label("kallsyms_module_names_len");
+ printf("\t.long\t%zi\n", offset);
+}
+
+static void output_kallmodsyms_objfiles(void)
+{
+ size_t i = 0;
+ size_t emitted_offsets = 0;
+ size_t emitted_objfiles = 0;
+
+ if (base_relative)
+ output_label("kallsyms_module_offsets");
+ else
+ output_label("kallsyms_module_addresses");
+
+ for (i = 0; i < addrmap_num; i++) {
+ long long offset;
+ int overflow;
+
+ if (base_relative) {
+ if (!absolute_percpu) {
+ offset = addrmap[i].addr - relative_base;
+ overflow = (offset < 0 || offset > UINT_MAX);
+ } else {
+ offset = relative_base - addrmap[i].addr - 1;
+ overflow = (offset < INT_MIN || offset >= 0);
+ }
+ if (overflow) {
+ fprintf(stderr, "kallsyms failure: "
+ "objfile %s at address %#llx out of range in relative mode\n",
+ addrmap[i].objfile ? addrmap[i].objfile->obj :
+ "in always-built-in object", table[i]->addr);
+ exit(EXIT_FAILURE);
+ }
+ printf("\t.long\t0x%x\n", (int)offset);
+ } else
+ printf("\tPTR\t%#llx\n", addrmap[i].addr);
+ emitted_offsets++;
+ }
+
+ output_label("kallsyms_modules");
+
+ for (i = 0; i < addrmap_num; i++) {
+ struct obj2mod_elem *elem = addrmap[i].objfile;
+ /*
+ * Address range cites no object file: point at 0, the built-in
+ * module.
+ */
+ if (addrmap[i].objfile == NULL) {
+ printf("\t.long\t0x0\n");
+ emitted_objfiles++;
+ continue;
+ }
+
+ /*
+ * Zero offset is the initial \0, there to catch uninitialized
+ * obj2mod entries, and is forbidden.
+ */
+ assert (elem->mod_offset != 0);
+
+ printf("\t.long\t0x%x\n", elem->mod_offset);
+ emitted_objfiles++;
+ }
+
+ assert (emitted_offsets == emitted_objfiles);
+ output_label("kallsyms_num_modules");
+ printf("\t.long\t%zi\n", emitted_objfiles);
+ printf("\n");
+}
+#endif /* CONFIG_KALLMODSYMS */
+
/* 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(const unsigned char *data, int len, char *result)
@@ -451,6 +684,11 @@ static void write_src(void)
printf("\n");
}
+#ifdef CONFIG_KALLMODSYMS
+ output_kallmodsyms_modules();
+ output_kallmodsyms_objfiles();
+#endif
+
output_label("kallsyms_num_syms");
printf("\t.long\t%u\n", table_cnt);
printf("\n");
@@ -735,7 +973,7 @@ static void make_percpus_absolute(void)
unsigned int i;
for (i = 0; i < table_cnt; i++)
- if (symbol_in_range(table[i], &percpu_range, 1)) {
+ if (addr_in_range(table[i]->addr, &percpu_range, 1)) {
/*
* Keep the 'A' override for percpu symbols to
* ensure consistent behavior compared to older
@@ -762,17 +1000,124 @@ static void record_relative_base(void)
}
}
+#ifdef CONFIG_KALLMODSYMS
+/*
+ * Read the linker map.
+ */
+static void read_linker_map(void)
+{
+ unsigned long long addr, size;
+ char obj[PATH_MAX+1];
+ FILE *f = fopen(".tmp_vmlinux.ranges", "r");
+
+ if (!f) {
+ fprintf(stderr, "Cannot open '.tmp_vmlinux.ranges'.\n");
+ exit(1);
+ }
+
+ addrmap_num = 0;
+ addrmap_alloced = 4096;
+ addrmap = malloc(sizeof(*addrmap) * addrmap_alloced);
+ if (!addrmap)
+ goto oom;
+
+ /*
+ * For each address range, add to addrmap the address and the objfile
+ * entry to which the range maps. Only add entries relating to text
+ * ranges. (We assume that the text ranges are tightly packed, because
+ * in any reasonable object file format they will be, so we can ignore
+ * the size.)
+ *
+ * Ranges that do not correspond to a built-in module, but to an
+ * always-built-in object file, have no obj2mod_elem and point at NULL
+ * instead.
+ */
+
+ while (fscanf(f, "%llx %llx %s\n", &addr, &size, obj) == 3) {
+ struct obj2mod_elem *elem = obj2mod_get(obj);
+
+ if (addr == 0 || size == 0 ||
+ !addr_in_range(addr, text_ranges, ARRAY_SIZE(text_ranges)))
+ continue;
+
+ if (addrmap_num >= addrmap_alloced) {
+ addrmap_alloced *= 2;
+ addrmap = realloc(addrmap,
+ sizeof(*addrmap) * addrmap_alloced);
+ if (!addrmap)
+ goto oom;
+ }
+
+ addrmap[addrmap_num].addr = addr;
+ addrmap[addrmap_num].objfile = elem;
+ addrmap_num++;
+ }
+ fclose(f);
+ return;
+
+oom:
+ fprintf(stderr, "kallsyms: out of memory\n");
+ exit(1);
+}
+
+/*
+ * Read "modules_thick.builtin" (the list of built-in modules). Construct the
+ * obj2mod hash to track objfile -> module mappings. Read ".tmp_vmlinux.ranges"
+ * (the linker map) and build addrmap[], which maps address ranges to built-in
+ * module names (using obj2mod).
+ */
+static void read_modules(const char *modules_builtin)
+{
+ struct modules_thick_iter *i;
+ char *module_name = NULL;
+ char **module_paths;
+
+ obj2mod_init();
+ /*
+ * Iterate over all modules in modules_thick.builtin and add each.
+ */
+ i = modules_thick_iter_new(modules_builtin);
+ if (i == NULL) {
+ fprintf(stderr, "Cannot iterate over builtin modules.\n");
+ exit(1);
+ }
+
+ while ((module_paths = modules_thick_iter_next(i, &module_name))) {
+ char **walk = module_paths;
+ while (*walk) {
+ obj2mod_add(*walk, module_name);
+ walk++;
+ }
+ free(module_paths);
+ }
+
+ free(module_name);
+ modules_thick_iter_free(i);
+
+ /*
+ * Read linker map.
+ */
+ read_linker_map();
+}
+#else
+static void read_modules(const char *unused) {}
+#endif /* CONFIG_KALLMODSYMS */
+
int main(int argc, char **argv)
{
+ const char *modules_builtin = "modules_thick.builtin";
+
if (argc >= 2) {
int i;
for (i = 1; i < argc; i++) {
- if(strcmp(argv[i], "--all-symbols") == 0)
+ 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 if (strncmp(argv[i], "--builtin=", 10) == 0)
+ modules_builtin = &argv[i][10];
else
usage();
}
@@ -780,6 +1125,7 @@ int main(int argc, char **argv)
usage();
read_map(stdin);
+ read_modules(modules_builtin);
shrink_table();
if (absolute_percpu)
make_percpus_absolute();
The mapping consists of three new symbols, computed by integrating the information in the (just-added) .tmp_vmlinux.ranges and modules_thick.builtin: taken together, they map address ranges (corresponding to object files on the input) to the names of zero or more modules containing those address ranges. - kallsyms_module_addresses/kallsyms_module_offsets encodes the address/offset of each object file (derived from the linker map), in exactly the same way as kallsyms_addresses/kallsyms_offsets does for symbols. There is no size: instead, the object files are assumed to tile the address space. (This is slightly more space-efficient than using a size). Non-text-section addresses are skipped: for now, all the users of this interface only need module/non-module information for instruction pointer addresses, not absolute-addressed symbols and the like. This restriction can easily be lifted in future. (Regarding the name: right now the entries correspond pretty closely to object files, so we could call the section kallsyms_objfiles or something, but the optimizer added in the next commit will change this.) - kallsyms_module_names encodes the name of each module in a modified form of strtab: notably, if an object file appears in *multiple* modules, all of which are built in, this is encoded via a zero byte, a one-byte module count, then a series of that many null-terminated strings. As a special case, the table starts with a single zero byte which does *not* represent the start of a multi-module list. - kallsyms_modules connects the two, encoding a table associated 1:1 with kallsyms_module_addresses / kallsyms_module_offsets, pointing at an offset in kallsyms_module_names describing which module (or modules, for a multi-module list) the code occupying this address range is part of. If an address range is part of no module (always built-in) it points at 0 (the null byte at the start of the kallsyms_module_names list). There is no optimization yet: kallsyms_modules and kallsyms_module_names will almost certainly contain many duplicate entries, and kallsyms_module_{addresses,offsets} may contain consecutive entries that point to the same place. The size hit is fairly substantial as a result, though still much less than a naive implementation mapping each symbol to a module name would be: 50KiB or so. Signed-off-by: Nick Alcock <nick.alcock@oracle.com> --- Makefile | 2 +- init/Kconfig | 8 + scripts/Makefile | 6 + scripts/kallsyms.c | 366 +++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 371 insertions(+), 11 deletions(-)