linux/kernel/module/kallsyms.c

522 lines
14 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Module kallsyms support
*
* Copyright (C) 2010 Rusty Russell
*/
#include <linux/module.h>
#include <linux/module_symbol.h>
#include <linux/kallsyms.h>
#include <linux/buildid.h>
#include <linux/bsearch.h>
#include "internal.h"
/* Lookup exported symbol in given range of kernel_symbols */
static const struct kernel_symbol *lookup_exported_symbol(const char *name,
const struct kernel_symbol *start,
const struct kernel_symbol *stop)
{
return bsearch(name, start, stop - start,
sizeof(struct kernel_symbol), cmp_name);
}
static int is_exported(const char *name, unsigned long value,
const struct module *mod)
{
const struct kernel_symbol *ks;
if (!mod)
ks = lookup_exported_symbol(name, __start___ksymtab, __stop___ksymtab);
else
ks = lookup_exported_symbol(name, mod->syms, mod->syms + mod->num_syms);
return ks && kernel_symbol_value(ks) == value;
}
/* As per nm */
static char elf_type(const Elf_Sym *sym, const struct load_info *info)
{
const Elf_Shdr *sechdrs = info->sechdrs;
if (ELF_ST_BIND(sym->st_info) == STB_WEAK) {
if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT)
return 'v';
else
return 'w';
}
if (sym->st_shndx == SHN_UNDEF)
return 'U';
if (sym->st_shndx == SHN_ABS || sym->st_shndx == info->index.pcpu)
return 'a';
if (sym->st_shndx >= SHN_LORESERVE)
return '?';
if (sechdrs[sym->st_shndx].sh_flags & SHF_EXECINSTR)
return 't';
if (sechdrs[sym->st_shndx].sh_flags & SHF_ALLOC &&
sechdrs[sym->st_shndx].sh_type != SHT_NOBITS) {
if (!(sechdrs[sym->st_shndx].sh_flags & SHF_WRITE))
return 'r';
else if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL)
return 'g';
else
return 'd';
}
if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) {
if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL)
return 's';
else
return 'b';
}
if (strstarts(info->secstrings + sechdrs[sym->st_shndx].sh_name,
".debug")) {
return 'n';
}
return '?';
}
static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
unsigned int shnum, unsigned int pcpundx)
{
const Elf_Shdr *sec;
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
enum mod_mem_type type;
if (src->st_shndx == SHN_UNDEF ||
src->st_shndx >= shnum ||
!src->st_name)
return false;
#ifdef CONFIG_KALLSYMS_ALL
if (src->st_shndx == pcpundx)
return true;
#endif
sec = sechdrs + src->st_shndx;
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
type = sec->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT;
if (!(sec->sh_flags & SHF_ALLOC)
#ifndef CONFIG_KALLSYMS_ALL
|| !(sec->sh_flags & SHF_EXECINSTR)
#endif
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
|| mod_mem_type_is_init(type))
return false;
return true;
}
/*
* We only allocate and copy the strings needed by the parts of symtab
* we keep. This is simple, but has the effect of making multiple
* copies of duplicates. We could be more sophisticated, see
* linux-kernel thread starting with
* <73defb5e4bca04a6431392cc341112b1@localhost>.
*/
void layout_symtab(struct module *mod, struct load_info *info)
{
Elf_Shdr *symsect = info->sechdrs + info->index.sym;
Elf_Shdr *strsect = info->sechdrs + info->index.str;
const Elf_Sym *src;
unsigned int i, nsrc, ndst, strtab_size = 0;
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
struct module_memory *mod_mem_data = &mod->mem[MOD_DATA];
struct module_memory *mod_mem_init_data = &mod->mem[MOD_INIT_DATA];
/* Put symbol section at end of init part of module. */
symsect->sh_flags |= SHF_ALLOC;
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
symsect->sh_entsize = module_get_offset_and_type(mod, MOD_INIT_DATA,
symsect, info->index.sym);
pr_debug("\t%s\n", info->secstrings + symsect->sh_name);
src = (void *)info->hdr + symsect->sh_offset;
nsrc = symsect->sh_size / sizeof(*src);
/* Compute total space required for the core symbols' strtab. */
for (ndst = i = 0; i < nsrc; i++) {
if (i == 0 || is_livepatch_module(mod) ||
is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum,
info->index.pcpu)) {
strtab_size += strlen(&info->strtab[src[i].st_name]) + 1;
ndst++;
}
}
/* Append room for core symbols at end of core part. */
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
info->symoffs = ALIGN(mod_mem_data->size, symsect->sh_addralign ?: 1);
info->stroffs = mod_mem_data->size = info->symoffs + ndst * sizeof(Elf_Sym);
mod_mem_data->size += strtab_size;
modules: Fix corruption of /proc/kallsyms The commit 91fb02f31505 ("module: Move kallsyms support into a separate file") changed from using strlcpy() to using strscpy() which created a buffer overflow. That happened because: 1) an incorrect value was passed as the buffer length 2) strscpy() (unlike strlcpy()) may copy beyond the length of the input string when copying word-by-word. The assumption was that because it was already known that the strings being copied would fit in the space available, it was not necessary to correctly set the buffer length. strscpy() breaks that assumption because although it will not touch bytes beyond the given buffer length it may write bytes beyond the input string length when writing word-by-word. The result of the buffer overflow is to corrupt the symbol type information that follows. e.g. $ sudo cat -v /proc/kallsyms | grep '\^' | head ffffffffc0615000 ^@ rfcomm_session_get [rfcomm] ffffffffc061c060 ^@ session_list [rfcomm] ffffffffc06150d0 ^@ rfcomm_send_frame [rfcomm] ffffffffc0615130 ^@ rfcomm_make_uih [rfcomm] ffffffffc07ed58d ^@ bnep_exit [bnep] ffffffffc07ec000 ^@ bnep_rx_control [bnep] ffffffffc07ec1a0 ^@ bnep_session [bnep] ffffffffc07e7000 ^@ input_leds_event [input_leds] ffffffffc07e9000 ^@ input_leds_handler [input_leds] ffffffffc07e7010 ^@ input_leds_disconnect [input_leds] Notably, the null bytes (represented above by ^@) can confuse tools. Fix by correcting the buffer length. Fixes: 91fb02f31505 ("module: Move kallsyms support into a separate file") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2022-07-01 09:44:03 +00:00
/* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
info->core_typeoffs = mod_mem_data->size;
mod_mem_data->size += ndst * sizeof(char);
/* Put string table section at end of init part of module. */
strsect->sh_flags |= SHF_ALLOC;
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
strsect->sh_entsize = module_get_offset_and_type(mod, MOD_INIT_DATA,
strsect, info->index.str);
pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
/* We'll tack temporary mod_kallsyms on the end. */
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
mod_mem_init_data->size = ALIGN(mod_mem_init_data->size,
__alignof__(struct mod_kallsyms));
info->mod_kallsyms_init_off = mod_mem_init_data->size;
mod_mem_init_data->size += sizeof(struct mod_kallsyms);
info->init_typeoffs = mod_mem_init_data->size;
mod_mem_init_data->size += nsrc * sizeof(char);
}
/*
* We use the full symtab and strtab which layout_symtab arranged to
* be appended to the init section. Later we switch to the cut-down
* core-only ones.
*/
void add_kallsyms(struct module *mod, const struct load_info *info)
{
unsigned int i, ndst;
const Elf_Sym *src;
Elf_Sym *dst;
char *s;
Elf_Shdr *symsec = &info->sechdrs[info->index.sym];
modules: Fix corruption of /proc/kallsyms The commit 91fb02f31505 ("module: Move kallsyms support into a separate file") changed from using strlcpy() to using strscpy() which created a buffer overflow. That happened because: 1) an incorrect value was passed as the buffer length 2) strscpy() (unlike strlcpy()) may copy beyond the length of the input string when copying word-by-word. The assumption was that because it was already known that the strings being copied would fit in the space available, it was not necessary to correctly set the buffer length. strscpy() breaks that assumption because although it will not touch bytes beyond the given buffer length it may write bytes beyond the input string length when writing word-by-word. The result of the buffer overflow is to corrupt the symbol type information that follows. e.g. $ sudo cat -v /proc/kallsyms | grep '\^' | head ffffffffc0615000 ^@ rfcomm_session_get [rfcomm] ffffffffc061c060 ^@ session_list [rfcomm] ffffffffc06150d0 ^@ rfcomm_send_frame [rfcomm] ffffffffc0615130 ^@ rfcomm_make_uih [rfcomm] ffffffffc07ed58d ^@ bnep_exit [bnep] ffffffffc07ec000 ^@ bnep_rx_control [bnep] ffffffffc07ec1a0 ^@ bnep_session [bnep] ffffffffc07e7000 ^@ input_leds_event [input_leds] ffffffffc07e9000 ^@ input_leds_handler [input_leds] ffffffffc07e7010 ^@ input_leds_disconnect [input_leds] Notably, the null bytes (represented above by ^@) can confuse tools. Fix by correcting the buffer length. Fixes: 91fb02f31505 ("module: Move kallsyms support into a separate file") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2022-07-01 09:44:03 +00:00
unsigned long strtab_size;
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
void *data_base = mod->mem[MOD_DATA].base;
void *init_data_base = mod->mem[MOD_INIT_DATA].base;
/* Set up to point into init section. */
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
mod->kallsyms = (void __rcu *)init_data_base +
info->mod_kallsyms_init_off;
rcu_read_lock();
/* The following is safe since this pointer cannot change */
rcu_dereference(mod->kallsyms)->symtab = (void *)symsec->sh_addr;
rcu_dereference(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
/* Make sure we get permanent strtab: don't use info->strtab. */
rcu_dereference(mod->kallsyms)->strtab =
(void *)info->sechdrs[info->index.str].sh_addr;
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
rcu_dereference(mod->kallsyms)->typetab = init_data_base + info->init_typeoffs;
/*
* Now populate the cut down core kallsyms for after init
* and set types up while we still have access to sections.
*/
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
mod->core_kallsyms.symtab = dst = data_base + info->symoffs;
mod->core_kallsyms.strtab = s = data_base + info->stroffs;
mod->core_kallsyms.typetab = data_base + info->core_typeoffs;
modules: Fix corruption of /proc/kallsyms The commit 91fb02f31505 ("module: Move kallsyms support into a separate file") changed from using strlcpy() to using strscpy() which created a buffer overflow. That happened because: 1) an incorrect value was passed as the buffer length 2) strscpy() (unlike strlcpy()) may copy beyond the length of the input string when copying word-by-word. The assumption was that because it was already known that the strings being copied would fit in the space available, it was not necessary to correctly set the buffer length. strscpy() breaks that assumption because although it will not touch bytes beyond the given buffer length it may write bytes beyond the input string length when writing word-by-word. The result of the buffer overflow is to corrupt the symbol type information that follows. e.g. $ sudo cat -v /proc/kallsyms | grep '\^' | head ffffffffc0615000 ^@ rfcomm_session_get [rfcomm] ffffffffc061c060 ^@ session_list [rfcomm] ffffffffc06150d0 ^@ rfcomm_send_frame [rfcomm] ffffffffc0615130 ^@ rfcomm_make_uih [rfcomm] ffffffffc07ed58d ^@ bnep_exit [bnep] ffffffffc07ec000 ^@ bnep_rx_control [bnep] ffffffffc07ec1a0 ^@ bnep_session [bnep] ffffffffc07e7000 ^@ input_leds_event [input_leds] ffffffffc07e9000 ^@ input_leds_handler [input_leds] ffffffffc07e7010 ^@ input_leds_disconnect [input_leds] Notably, the null bytes (represented above by ^@) can confuse tools. Fix by correcting the buffer length. Fixes: 91fb02f31505 ("module: Move kallsyms support into a separate file") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2022-07-01 09:44:03 +00:00
strtab_size = info->core_typeoffs - info->stroffs;
src = rcu_dereference(mod->kallsyms)->symtab;
for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) {
rcu_dereference(mod->kallsyms)->typetab[i] = elf_type(src + i, info);
if (i == 0 || is_livepatch_module(mod) ||
is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum,
info->index.pcpu)) {
modules: Fix corruption of /proc/kallsyms The commit 91fb02f31505 ("module: Move kallsyms support into a separate file") changed from using strlcpy() to using strscpy() which created a buffer overflow. That happened because: 1) an incorrect value was passed as the buffer length 2) strscpy() (unlike strlcpy()) may copy beyond the length of the input string when copying word-by-word. The assumption was that because it was already known that the strings being copied would fit in the space available, it was not necessary to correctly set the buffer length. strscpy() breaks that assumption because although it will not touch bytes beyond the given buffer length it may write bytes beyond the input string length when writing word-by-word. The result of the buffer overflow is to corrupt the symbol type information that follows. e.g. $ sudo cat -v /proc/kallsyms | grep '\^' | head ffffffffc0615000 ^@ rfcomm_session_get [rfcomm] ffffffffc061c060 ^@ session_list [rfcomm] ffffffffc06150d0 ^@ rfcomm_send_frame [rfcomm] ffffffffc0615130 ^@ rfcomm_make_uih [rfcomm] ffffffffc07ed58d ^@ bnep_exit [bnep] ffffffffc07ec000 ^@ bnep_rx_control [bnep] ffffffffc07ec1a0 ^@ bnep_session [bnep] ffffffffc07e7000 ^@ input_leds_event [input_leds] ffffffffc07e9000 ^@ input_leds_handler [input_leds] ffffffffc07e7010 ^@ input_leds_disconnect [input_leds] Notably, the null bytes (represented above by ^@) can confuse tools. Fix by correcting the buffer length. Fixes: 91fb02f31505 ("module: Move kallsyms support into a separate file") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2022-07-01 09:44:03 +00:00
ssize_t ret;
mod->core_kallsyms.typetab[ndst] =
rcu_dereference(mod->kallsyms)->typetab[i];
dst[ndst] = src[i];
dst[ndst++].st_name = s - mod->core_kallsyms.strtab;
modules: Fix corruption of /proc/kallsyms The commit 91fb02f31505 ("module: Move kallsyms support into a separate file") changed from using strlcpy() to using strscpy() which created a buffer overflow. That happened because: 1) an incorrect value was passed as the buffer length 2) strscpy() (unlike strlcpy()) may copy beyond the length of the input string when copying word-by-word. The assumption was that because it was already known that the strings being copied would fit in the space available, it was not necessary to correctly set the buffer length. strscpy() breaks that assumption because although it will not touch bytes beyond the given buffer length it may write bytes beyond the input string length when writing word-by-word. The result of the buffer overflow is to corrupt the symbol type information that follows. e.g. $ sudo cat -v /proc/kallsyms | grep '\^' | head ffffffffc0615000 ^@ rfcomm_session_get [rfcomm] ffffffffc061c060 ^@ session_list [rfcomm] ffffffffc06150d0 ^@ rfcomm_send_frame [rfcomm] ffffffffc0615130 ^@ rfcomm_make_uih [rfcomm] ffffffffc07ed58d ^@ bnep_exit [bnep] ffffffffc07ec000 ^@ bnep_rx_control [bnep] ffffffffc07ec1a0 ^@ bnep_session [bnep] ffffffffc07e7000 ^@ input_leds_event [input_leds] ffffffffc07e9000 ^@ input_leds_handler [input_leds] ffffffffc07e7010 ^@ input_leds_disconnect [input_leds] Notably, the null bytes (represented above by ^@) can confuse tools. Fix by correcting the buffer length. Fixes: 91fb02f31505 ("module: Move kallsyms support into a separate file") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2022-07-01 09:44:03 +00:00
ret = strscpy(s,
&rcu_dereference(mod->kallsyms)->strtab[src[i].st_name],
modules: Fix corruption of /proc/kallsyms The commit 91fb02f31505 ("module: Move kallsyms support into a separate file") changed from using strlcpy() to using strscpy() which created a buffer overflow. That happened because: 1) an incorrect value was passed as the buffer length 2) strscpy() (unlike strlcpy()) may copy beyond the length of the input string when copying word-by-word. The assumption was that because it was already known that the strings being copied would fit in the space available, it was not necessary to correctly set the buffer length. strscpy() breaks that assumption because although it will not touch bytes beyond the given buffer length it may write bytes beyond the input string length when writing word-by-word. The result of the buffer overflow is to corrupt the symbol type information that follows. e.g. $ sudo cat -v /proc/kallsyms | grep '\^' | head ffffffffc0615000 ^@ rfcomm_session_get [rfcomm] ffffffffc061c060 ^@ session_list [rfcomm] ffffffffc06150d0 ^@ rfcomm_send_frame [rfcomm] ffffffffc0615130 ^@ rfcomm_make_uih [rfcomm] ffffffffc07ed58d ^@ bnep_exit [bnep] ffffffffc07ec000 ^@ bnep_rx_control [bnep] ffffffffc07ec1a0 ^@ bnep_session [bnep] ffffffffc07e7000 ^@ input_leds_event [input_leds] ffffffffc07e9000 ^@ input_leds_handler [input_leds] ffffffffc07e7010 ^@ input_leds_disconnect [input_leds] Notably, the null bytes (represented above by ^@) can confuse tools. Fix by correcting the buffer length. Fixes: 91fb02f31505 ("module: Move kallsyms support into a separate file") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2022-07-01 09:44:03 +00:00
strtab_size);
if (ret < 0)
break;
s += ret + 1;
strtab_size -= ret + 1;
}
}
rcu_read_unlock();
mod->core_kallsyms.num_symtab = ndst;
}
#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
void init_build_id(struct module *mod, const struct load_info *info)
{
const Elf_Shdr *sechdr;
unsigned int i;
for (i = 0; i < info->hdr->e_shnum; i++) {
sechdr = &info->sechdrs[i];
if (!sect_empty(sechdr) && sechdr->sh_type == SHT_NOTE &&
!build_id_parse_buf((void *)sechdr->sh_addr, mod->build_id,
sechdr->sh_size))
break;
}
}
#else
void init_build_id(struct module *mod, const struct load_info *info)
{
}
#endif
static const char *kallsyms_symbol_name(struct mod_kallsyms *kallsyms, unsigned int symnum)
{
return kallsyms->strtab + kallsyms->symtab[symnum].st_name;
}
/*
* Given a module and address, find the corresponding symbol and return its name
* while providing its size and offset if needed.
*/
static const char *find_kallsyms_symbol(struct module *mod,
unsigned long addr,
unsigned long *size,
unsigned long *offset)
{
unsigned int i, best = 0;
unsigned long nextval, bestval;
struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
struct module_memory *mod_mem;
/* At worse, next value is at end of module */
if (within_module_init(addr, mod))
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
mod_mem = &mod->mem[MOD_INIT_TEXT];
else
module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu <song@kernel.org> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-02-07 00:28:02 +00:00
mod_mem = &mod->mem[MOD_TEXT];
nextval = (unsigned long)mod_mem->base + mod_mem->size;
bestval = kallsyms_symbol_value(&kallsyms->symtab[best]);
/*
* Scan for closest preceding symbol, and next symbol. (ELF
* starts real symbols at 1).
*/
for (i = 1; i < kallsyms->num_symtab; i++) {
const Elf_Sym *sym = &kallsyms->symtab[i];
unsigned long thisval = kallsyms_symbol_value(sym);
if (sym->st_shndx == SHN_UNDEF)
continue;
/*
* We ignore unnamed symbols: they're uninformative
* and inserted at a whim.
*/
if (*kallsyms_symbol_name(kallsyms, i) == '\0' ||
module: Ignore L0 and rename is_arm_mapping_symbol() The L0 symbol is generated when build module on LoongArch, ignore it in modpost and when looking at module symbols, otherwise we can not see the expected call trace. Now is_arm_mapping_symbol() is not only for ARM, in order to reflect the reality, rename is_arm_mapping_symbol() to is_mapping_symbol(). This is related with commit c17a2538704f ("mksysmap: Fix the mismatch of 'L0' symbols in System.map"). (1) Simple test case [loongson@linux hello]$ cat hello.c #include <linux/init.h> #include <linux/module.h> #include <linux/printk.h> static void test_func(void) { pr_info("This is a test\n"); dump_stack(); } static int __init hello_init(void) { pr_warn("Hello, world\n"); test_func(); return 0; } static void __exit hello_exit(void) { pr_warn("Goodbye\n"); } module_init(hello_init); module_exit(hello_exit); MODULE_LICENSE("GPL"); [loongson@linux hello]$ cat Makefile obj-m:=hello.o ccflags-y += -g -Og all: make -C /lib/modules/$(shell uname -r)/build/ M=$(PWD) modules clean: make -C /lib/modules/$(shell uname -r)/build/ M=$(PWD) clean (2) Test environment system: LoongArch CLFS 5.5 https://github.com/sunhaiyong1978/CLFS-for-LoongArch/releases/tag/5.0 It needs to update grub to avoid booting error "invalid magic number". kernel: 6.3-rc1 with loongson3_defconfig + CONFIG_DYNAMIC_FTRACE=y (3) Test result Without this patch: [root@linux hello]# insmod hello.ko [root@linux hello]# dmesg ... Hello, world This is a test ... Call Trace: [<9000000000223728>] show_stack+0x68/0x18c [<90000000013374cc>] dump_stack_lvl+0x60/0x88 [<ffff800002050028>] L0\x01+0x20/0x2c [hello] [<ffff800002058028>] L0\x01+0x20/0x30 [hello] [<900000000022097c>] do_one_initcall+0x88/0x288 [<90000000002df890>] do_init_module+0x54/0x200 [<90000000002e1e18>] __do_sys_finit_module+0xc4/0x114 [<90000000013382e8>] do_syscall+0x7c/0x94 [<9000000000221e3c>] handle_syscall+0xbc/0x158 With this patch: [root@linux hello]# insmod hello.ko [root@linux hello]# dmesg ... Hello, world This is a test ... Call Trace: [<9000000000223728>] show_stack+0x68/0x18c [<90000000013374cc>] dump_stack_lvl+0x60/0x88 [<ffff800002050028>] test_func+0x28/0x34 [hello] [<ffff800002058028>] hello_init+0x28/0x38 [hello] [<900000000022097c>] do_one_initcall+0x88/0x288 [<90000000002df890>] do_init_module+0x54/0x200 [<90000000002e1e18>] __do_sys_finit_module+0xc4/0x114 [<90000000013382e8>] do_syscall+0x7c/0x94 [<9000000000221e3c>] handle_syscall+0xbc/0x158 Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn> Tested-by: Youling Tang <tangyouling@loongson.cn> # for LoongArch Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-03-31 09:15:53 +00:00
is_mapping_symbol(kallsyms_symbol_name(kallsyms, i)))
continue;
if (thisval <= addr && thisval > bestval) {
best = i;
bestval = thisval;
}
if (thisval > addr && thisval < nextval)
nextval = thisval;
}
if (!best)
return NULL;
if (size)
*size = nextval - bestval;
if (offset)
*offset = addr - bestval;
return kallsyms_symbol_name(kallsyms, best);
}
void * __weak dereference_module_function_descriptor(struct module *mod,
void *ptr)
{
return ptr;
}
/*
* For kallsyms to ask for address resolution. NULL means not found. Careful
* not to lock to avoid deadlock on oopses, simply disable preemption.
*/
const char *module_address_lookup(unsigned long addr,
unsigned long *size,
unsigned long *offset,
char **modname,
const unsigned char **modbuildid,
char *namebuf)
{
const char *ret = NULL;
struct module *mod;
preempt_disable();
mod = __module_address(addr);
if (mod) {
if (modname)
*modname = mod->name;
if (modbuildid) {
#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
*modbuildid = mod->build_id;
#else
*modbuildid = NULL;
#endif
}
ret = find_kallsyms_symbol(mod, addr, size, offset);
}
/* Make a copy in here where it's safe */
if (ret) {
strscpy(namebuf, ret, KSYM_NAME_LEN);
ret = namebuf;
}
preempt_enable();
return ret;
}
int lookup_module_symbol_name(unsigned long addr, char *symname)
{
struct module *mod;
preempt_disable();
list_for_each_entry_rcu(mod, &modules, list) {
if (mod->state == MODULE_STATE_UNFORMED)
continue;
if (within_module(addr, mod)) {
const char *sym;
sym = find_kallsyms_symbol(mod, addr, NULL, NULL);
if (!sym)
goto out;
strscpy(symname, sym, KSYM_NAME_LEN);
preempt_enable();
return 0;
}
}
out:
preempt_enable();
return -ERANGE;
}
int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
char *name, char *module_name, int *exported)
{
struct module *mod;
preempt_disable();
list_for_each_entry_rcu(mod, &modules, list) {
struct mod_kallsyms *kallsyms;
if (mod->state == MODULE_STATE_UNFORMED)
continue;
kallsyms = rcu_dereference_sched(mod->kallsyms);
if (symnum < kallsyms->num_symtab) {
const Elf_Sym *sym = &kallsyms->symtab[symnum];
*value = kallsyms_symbol_value(sym);
*type = kallsyms->typetab[symnum];
strscpy(name, kallsyms_symbol_name(kallsyms, symnum), KSYM_NAME_LEN);
strscpy(module_name, mod->name, MODULE_NAME_LEN);
*exported = is_exported(name, *value, mod);
preempt_enable();
return 0;
}
symnum -= kallsyms->num_symtab;
}
preempt_enable();
return -ERANGE;
}
/* Given a module and name of symbol, find and return the symbol's value */
static unsigned long __find_kallsyms_symbol_value(struct module *mod, const char *name)
{
unsigned int i;
struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
for (i = 0; i < kallsyms->num_symtab; i++) {
const Elf_Sym *sym = &kallsyms->symtab[i];
if (strcmp(name, kallsyms_symbol_name(kallsyms, i)) == 0 &&
sym->st_shndx != SHN_UNDEF)
return kallsyms_symbol_value(sym);
}
return 0;
}
static unsigned long __module_kallsyms_lookup_name(const char *name)
{
struct module *mod;
char *colon;
colon = strnchr(name, MODULE_NAME_LEN, ':');
if (colon) {
mod = find_module_all(name, colon - name, false);
if (mod)
return __find_kallsyms_symbol_value(mod, colon + 1);
return 0;
}
list_for_each_entry_rcu(mod, &modules, list) {
unsigned long ret;
if (mod->state == MODULE_STATE_UNFORMED)
continue;
ret = __find_kallsyms_symbol_value(mod, name);
if (ret)
return ret;
}
return 0;
}
/* Look for this name: can be of form module:name. */
unsigned long module_kallsyms_lookup_name(const char *name)
{
unsigned long ret;
/* Don't lock: we're in enough trouble already. */
preempt_disable();
ret = __module_kallsyms_lookup_name(name);
preempt_enable();
return ret;
}
unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name)
{
unsigned long ret;
preempt_disable();
ret = __find_kallsyms_symbol_value(mod, name);
preempt_enable();
return ret;
}
int module_kallsyms_on_each_symbol(const char *modname,
int (*fn)(void *, const char *, unsigned long),
void *data)
{
struct module *mod;
unsigned int i;
int ret = 0;
mutex_lock(&module_mutex);
list_for_each_entry(mod, &modules, list) {
struct mod_kallsyms *kallsyms;
if (mod->state == MODULE_STATE_UNFORMED)
continue;
if (modname && strcmp(modname, mod->name))
continue;
/* Use rcu_dereference_sched() to remain compliant with the sparse tool */
preempt_disable();
kallsyms = rcu_dereference_sched(mod->kallsyms);
preempt_enable();
for (i = 0; i < kallsyms->num_symtab; i++) {
const Elf_Sym *sym = &kallsyms->symtab[i];
if (sym->st_shndx == SHN_UNDEF)
continue;
ret = fn(data, kallsyms_symbol_name(kallsyms, i),
kallsyms_symbol_value(sym));
if (ret != 0)
goto out;
}
/*
* The given module is found, the subsequent modules do not
* need to be compared.
*/
if (modname)
break;
}
out:
mutex_unlock(&module_mutex);
return ret;
}