git/linux-net
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git/ synced 2026-04-17 22:23:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

module: replace module_layout with module_memory

Browse Source 
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>
This commit is contained in:
Song Liu
2023-02-06 16:28:02 -08:00
committed by Luis Chamberlain
parent fe15c26ee2
commit ac3b432839
18 changed files with 437 additions and 477 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
kernel/module/internal.h
View File

@@ -17,28 +17,20 @@
#define ARCH_SHF_SMALL 0
#endif
/* If this is set, the section belongs in the init part of the module */
#define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG - 1))
/*
* Use highest 4 bits of sh_entsize to store the mod_mem_type of this
* section. This leaves 28 bits for offset on 32-bit systems, which is
* about 256 MiB (WARN_ON_ONCE if we exceed that).
*/
#define SH_ENTSIZE_TYPE_BITS 4
#define SH_ENTSIZE_TYPE_SHIFT (BITS_PER_LONG - SH_ENTSIZE_TYPE_BITS)
#define SH_ENTSIZE_TYPE_MASK ((1UL << SH_ENTSIZE_TYPE_BITS) - 1)
#define SH_ENTSIZE_OFFSET_MASK ((1UL << (BITS_PER_LONG - SH_ENTSIZE_TYPE_BITS)) - 1)
/* Maximum number of characters written by module_flags() */
#define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4)
#ifndef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
#define data_layout core_layout
#endif
/*
* Modules' sections will be aligned on page boundaries
* to ensure complete separation of code and data, but
* only when CONFIG_STRICT_MODULE_RWX=y
*/
static inline unsigned int strict_align(unsigned int size)
{
if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
return PAGE_ALIGN(size);
else
return size;
}
extern struct mutex module_mutex;
extern struct list_head modules;
@@ -101,8 +93,8 @@ int try_to_force_load(struct module *mod, const char *reason);
bool find_symbol(struct find_symbol_arg *fsa);
struct module *find_module_all(const char *name, size_t len, bool even_unformed);
int cmp_name(const void *name, const void *sym);
long module_get_offset(struct module *mod, unsigned int *size, Elf_Shdr *sechdr,
unsigned int section);
long module_get_offset_and_type(struct module *mod, enum mod_mem_type type,
Elf_Shdr *sechdr, unsigned int section);
char *module_flags(struct module *mod, char *buf, bool show_state);
size_t module_flags_taint(unsigned long taints, char *buf);
@@ -190,10 +182,13 @@ struct mod_tree_root {
#endif
unsigned long addr_min;
unsigned long addr_max;
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
unsigned long data_addr_min;
unsigned long data_addr_max;
#endif
};
extern struct mod_tree_root mod_tree;
extern struct mod_tree_root mod_data_tree;
#ifdef CONFIG_MODULES_TREE_LOOKUP
void mod_tree_insert(struct module *mod);
@@ -224,7 +219,6 @@ void module_enable_nx(const struct module *mod);
void module_enable_x(const struct module *mod);
int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
char *secstrings, struct module *mod);
bool module_check_misalignment(const struct module *mod);
#ifdef CONFIG_MODULE_SIG
int module_sig_check(struct load_info *info, int flags);

58
kernel/module/kallsyms.c
View File

@@ -78,6 +78,7 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
unsigned int shnum, unsigned int pcpundx)
{
const Elf_Shdr *sec;
enum mod_mem_type type;
if (src->st_shndx == SHN_UNDEF ||
src->st_shndx >= shnum ||
@@ -90,11 +91,12 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
#endif
sec = sechdrs + src->st_shndx;
type = sec->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT;
if (!(sec->sh_flags & SHF_ALLOC)
#ifndef CONFIG_KALLSYMS_ALL
|| !(sec->sh_flags & SHF_EXECINSTR)
#endif
|| (sec->sh_entsize & INIT_OFFSET_MASK))
|| mod_mem_type_is_init(type))
return false;
return true;
@@ -113,11 +115,13 @@ void layout_symtab(struct module *mod, struct load_info *info)
Elf_Shdr *strsect = info->sechdrs + info->index.str;
const Elf_Sym *src;
unsigned int i, nsrc, ndst, strtab_size = 0;
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;
symsect->sh_entsize = module_get_offset(mod, &mod->init_layout.size, symsect,
info->index.sym) | INIT_OFFSET_MASK;
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;
@@ -134,28 +138,27 @@ void layout_symtab(struct module *mod, struct load_info *info)
}
/* Append room for core symbols at end of core part. */
info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1);
info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym);
mod->data_layout.size += strtab_size;
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;
/* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */
info->core_typeoffs = mod->data_layout.size;
mod->data_layout.size += ndst * sizeof(char);
mod->data_layout.size = strict_align(mod->data_layout.size);
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;
strsect->sh_entsize = module_get_offset(mod, &mod->init_layout.size, strsect,
info->index.str) | INIT_OFFSET_MASK;
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. */
mod->init_layout.size = ALIGN(mod->init_layout.size,
__alignof__(struct mod_kallsyms));
info->mod_kallsyms_init_off = mod->init_layout.size;
mod->init_layout.size += sizeof(struct mod_kallsyms);
info->init_typeoffs = mod->init_layout.size;
mod->init_layout.size += nsrc * sizeof(char);
mod->init_layout.size = strict_align(mod->init_layout.size);
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);
}
/*
@@ -171,9 +174,11 @@ void add_kallsyms(struct module *mod, const struct load_info *info)
char *s;
Elf_Shdr *symsec = &info->sechdrs[info->index.sym];
unsigned long strtab_size;
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. */
mod->kallsyms = (void __rcu *)mod->init_layout.base +
mod->kallsyms = (void __rcu *)init_data_base +
info->mod_kallsyms_init_off;
rcu_read_lock();
@@ -183,15 +188,15 @@ void add_kallsyms(struct module *mod, const struct load_info *info)
/* Make sure we get permanent strtab: don't use info->strtab. */
rcu_dereference(mod->kallsyms)->strtab =
(void *)info->sechdrs[info->index.str].sh_addr;
rcu_dereference(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs;
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.
*/
mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs;
mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs;
mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs;
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;
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++) {
@@ -267,12 +272,15 @@ static const char *find_kallsyms_symbol(struct module *mod,
unsigned int i, best = 0;
unsigned long nextval, bestval;
struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
struct module_memory *mod_mem;
/* At worse, next value is at end of module */
if (within_module_init(addr, mod))
nextval = (unsigned long)mod->init_layout.base + mod->init_layout.text_size;
mod_mem = &mod->mem[MOD_INIT_TEXT];
else
nextval = (unsigned long)mod->core_layout.base + mod->core_layout.text_size;
mod_mem = &mod->mem[MOD_TEXT];
nextval = (unsigned long)mod_mem->base + mod_mem->size;
bestval = kallsyms_symbol_value(&kallsyms->symtab[best]);

17
kernel/module/kdb.c
View File

@@ -26,10 +26,11 @@ int kdb_lsmod(int argc, const char **argv)
if (mod->state == MODULE_STATE_UNFORMED)
continue;
kdb_printf("%-20s%8u", mod->name, mod->core_layout.size);
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
kdb_printf("/%8u", mod->data_layout.size);
#endif
kdb_printf("%-20s%8u", mod->name, mod->mem[MOD_TEXT].size);
kdb_printf("/%8u", mod->mem[MOD_RODATA].size);
kdb_printf("/%8u", mod->mem[MOD_RO_AFTER_INIT].size);
kdb_printf("/%8u", mod->mem[MOD_DATA].size);
kdb_printf(" 0x%px ", (void *)mod);
#ifdef CONFIG_MODULE_UNLOAD
kdb_printf("%4d ", module_refcount(mod));
@@ -40,10 +41,10 @@ int kdb_lsmod(int argc, const char **argv)
kdb_printf(" (Loading)");
else
kdb_printf(" (Live)");
kdb_printf(" 0x%px", mod->core_layout.base);
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
kdb_printf("/0x%px", mod->data_layout.base);
#endif
kdb_printf(" 0x%px", mod->mem[MOD_TEXT].base);
kdb_printf("/0x%px", mod->mem[MOD_RODATA].base);
kdb_printf("/0x%px", mod->mem[MOD_RO_AFTER_INIT].base);
kdb_printf("/0x%px", mod->mem[MOD_DATA].base);
#ifdef CONFIG_MODULE_UNLOAD
{

395
kernel/module/main.c
View File

@@ -80,12 +80,6 @@ struct mod_tree_root mod_tree __cacheline_aligned = {
.addr_min = -1UL,
};
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
struct mod_tree_root mod_data_tree __cacheline_aligned = {
.addr_min = -1UL,
};
#endif
struct symsearch {
const struct kernel_symbol *start, *stop;
const s32 *crcs;
@@ -93,14 +87,24 @@ struct symsearch {
};
/*
* Bounds of module text, for speeding up __module_address.
* Bounds of module memory, for speeding up __module_address.
* Protected by module_mutex.
*/
static void __mod_update_bounds(void *base, unsigned int size, struct mod_tree_root *tree)
static void __mod_update_bounds(enum mod_mem_type type __maybe_unused, void *base,
unsigned int size, struct mod_tree_root *tree)
{
unsigned long min = (unsigned long)base;
unsigned long max = min + size;
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
if (mod_mem_type_is_core_data(type)) {
if (min < tree->data_addr_min)
tree->data_addr_min = min;
if (max > tree->data_addr_max)
tree->data_addr_max = max;
return;
}
#endif
if (min < tree->addr_min)
tree->addr_min = min;
if (max > tree->addr_max)
@@ -109,12 +113,12 @@ static void __mod_update_bounds(void *base, unsigned int size, struct mod_tree_r
static void mod_update_bounds(struct module *mod)
{
__mod_update_bounds(mod->core_layout.base, mod->core_layout.size, &mod_tree);
if (mod->init_layout.size)
__mod_update_bounds(mod->init_layout.base, mod->init_layout.size, &mod_tree);
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
__mod_update_bounds(mod->data_layout.base, mod->data_layout.size, &mod_data_tree);
#endif
for_each_mod_mem_type(type) {
struct module_memory *mod_mem = &mod->mem[type];
if (mod_mem->size)
__mod_update_bounds(type, mod_mem->base, mod_mem->size, &mod_tree);
}
}
/* Block module loading/unloading? */
@@ -926,7 +930,13 @@ struct module_attribute module_uevent =
static ssize_t show_coresize(struct module_attribute *mattr,
struct module_kobject *mk, char *buffer)
{
return sprintf(buffer, "%u\n", mk->mod->core_layout.size);
unsigned int size = mk->mod->mem[MOD_TEXT].size;
if (!IS_ENABLED(CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC)) {
for_class_mod_mem_type(type, core_data)
size += mk->mod->mem[type].size;
}
return sprintf(buffer, "%u\n", size);
}
static struct module_attribute modinfo_coresize =
@@ -936,7 +946,11 @@ static struct module_attribute modinfo_coresize =
static ssize_t show_datasize(struct module_attribute *mattr,
struct module_kobject *mk, char *buffer)
{
return sprintf(buffer, "%u\n", mk->mod->data_layout.size);
unsigned int size = 0;
for_class_mod_mem_type(type, core_data)
size += mk->mod->mem[type].size;
return sprintf(buffer, "%u\n", size);
}
static struct module_attribute modinfo_datasize =
@@ -946,7 +960,11 @@ static struct module_attribute modinfo_datasize =
static ssize_t show_initsize(struct module_attribute *mattr,
struct module_kobject *mk, char *buffer)
{
return sprintf(buffer, "%u\n", mk->mod->init_layout.size);
unsigned int size = 0;
for_class_mod_mem_type(type, init)
size += mk->mod->mem[type].size;
return sprintf(buffer, "%u\n", size);
}
static struct module_attribute modinfo_initsize =
@@ -1143,6 +1161,46 @@ void __weak module_arch_freeing_init(struct module *mod)
{
}
static bool mod_mem_use_vmalloc(enum mod_mem_type type)
{
return IS_ENABLED(CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC) &&
mod_mem_type_is_core_data(type);
}
static void *module_memory_alloc(unsigned int size, enum mod_mem_type type)
{
if (mod_mem_use_vmalloc(type))
return vzalloc(size);
return module_alloc(size);
}
static void module_memory_free(void *ptr, enum mod_mem_type type)
{
if (mod_mem_use_vmalloc(type))
vfree(ptr);
else
module_memfree(ptr);
}
static void free_mod_mem(struct module *mod)
{
for_each_mod_mem_type(type) {
struct module_memory *mod_mem = &mod->mem[type];
if (type == MOD_DATA)
continue;
/* Free lock-classes; relies on the preceding sync_rcu(). */
lockdep_free_key_range(mod_mem->base, mod_mem->size);
if (mod_mem->size)
module_memory_free(mod_mem->base, type);
}
/* MOD_DATA hosts mod, so free it at last */
lockdep_free_key_range(mod->mem[MOD_DATA].base, mod->mem[MOD_DATA].size);
module_memory_free(mod->mem[MOD_DATA].base, MOD_DATA);
}
/* Free a module, remove from lists, etc. */
static void free_module(struct module *mod)
{
@@ -1189,18 +1247,10 @@ static void free_module(struct module *mod)
/* This may be empty, but that's OK */
module_arch_freeing_init(mod);
module_memfree(mod->init_layout.base);
kfree(mod->args);
percpu_modfree(mod);
/* Free lock-classes; relies on the preceding sync_rcu(). */
lockdep_free_key_range(mod->data_layout.base, mod->data_layout.size);
/* Finally, free the core (containing the module structure) */
module_memfree(mod->core_layout.base);
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
vfree(mod->data_layout.base);
#endif
free_mod_mem(mod);
}
void *__symbol_get(const char *symbol)
@@ -1387,16 +1437,18 @@ unsigned int __weak arch_mod_section_prepend(struct module *mod,
return 0;
}
/* Update size with this section: return offset. */
long module_get_offset(struct module *mod, unsigned int *size,
Elf_Shdr *sechdr, unsigned int section)
long module_get_offset_and_type(struct module *mod, enum mod_mem_type type,
Elf_Shdr *sechdr, unsigned int section)
{
long ret;
long offset;
long mask = ((unsigned long)(type) & SH_ENTSIZE_TYPE_MASK) << SH_ENTSIZE_TYPE_SHIFT;
*size += arch_mod_section_prepend(mod, section);
ret = ALIGN(*size, sechdr->sh_addralign ?: 1);
*size = ret + sechdr->sh_size;
return ret;
mod->mem[type].size += arch_mod_section_prepend(mod, section);
offset = ALIGN(mod->mem[type].size, sechdr->sh_addralign ?: 1);
mod->mem[type].size = offset + sechdr->sh_size;
WARN_ON_ONCE(offset & mask);
return offset | mask;
}
static bool module_init_layout_section(const char *sname)
@@ -1408,15 +1460,11 @@ static bool module_init_layout_section(const char *sname)
return module_init_section(sname);
}
/*
* Lay out the SHF_ALLOC sections in a way not dissimilar to how ld
* might -- code, read-only data, read-write data, small data. Tally
* sizes, and place the offsets into sh_entsize fields: high bit means it
* belongs in init.
*/
static void layout_sections(struct module *mod, struct load_info *info)
static void __layout_sections(struct module *mod, struct load_info *info, bool is_init)
{
static unsigned long const masks[][2] = {
unsigned int m, i;
static const unsigned long masks[][2] = {
/*
* NOTE: all executable code must be the first section
* in this array; otherwise modify the text_size
@@ -1428,82 +1476,61 @@ static void layout_sections(struct module *mod, struct load_info *info)
{ SHF_WRITE | SHF_ALLOC, ARCH_SHF_SMALL },
{ ARCH_SHF_SMALL | SHF_ALLOC, 0 }
};
unsigned int m, i;
static const int core_m_to_mem_type[] = {
MOD_TEXT,
MOD_RODATA,
MOD_RO_AFTER_INIT,
MOD_DATA,
MOD_INVALID, /* This is needed to match the masks array */
};
static const int init_m_to_mem_type[] = {
MOD_INIT_TEXT,
MOD_INIT_RODATA,
MOD_INVALID,
MOD_INIT_DATA,
MOD_INVALID, /* This is needed to match the masks array */
};
for (m = 0; m < ARRAY_SIZE(masks); ++m) {
enum mod_mem_type type = is_init ? init_m_to_mem_type[m] : core_m_to_mem_type[m];
for (i = 0; i < info->hdr->e_shnum; ++i) {
Elf_Shdr *s = &info->sechdrs[i];
const char *sname = info->secstrings + s->sh_name;
if ((s->sh_flags & masks[m][0]) != masks[m][0]
|| (s->sh_flags & masks[m][1])
|| s->sh_entsize != ~0UL
|| is_init != module_init_layout_section(sname))
continue;
if (WARN_ON_ONCE(type == MOD_INVALID))
continue;
s->sh_entsize = module_get_offset_and_type(mod, type, s, i);
pr_debug("\t%s\n", sname);
}
}
}
/*
* Lay out the SHF_ALLOC sections in a way not dissimilar to how ld
* might -- code, read-only data, read-write data, small data. Tally
* sizes, and place the offsets into sh_entsize fields: high bit means it
* belongs in init.
*/
static void layout_sections(struct module *mod, struct load_info *info)
{
unsigned int i;
for (i = 0; i < info->hdr->e_shnum; i++)
info->sechdrs[i].sh_entsize = ~0UL;
pr_debug("Core section allocation order:\n");
for (m = 0; m < ARRAY_SIZE(masks); ++m) {
for (i = 0; i < info->hdr->e_shnum; ++i) {
Elf_Shdr *s = &info->sechdrs[i];
const char *sname = info->secstrings + s->sh_name;
unsigned int *sizep;
if ((s->sh_flags & masks[m][0]) != masks[m][0]
|| (s->sh_flags & masks[m][1])
|| s->sh_entsize != ~0UL
|| module_init_layout_section(sname))
continue;
sizep = m ? &mod->data_layout.size : &mod->core_layout.size;
s->sh_entsize = module_get_offset(mod, sizep, s, i);
pr_debug("\t%s\n", sname);
}
switch (m) {
case 0: /* executable */
mod->core_layout.size = strict_align(mod->core_layout.size);
mod->core_layout.text_size = mod->core_layout.size;
break;
case 1: /* RO: text and ro-data */
mod->data_layout.size = strict_align(mod->data_layout.size);
mod->data_layout.ro_size = mod->data_layout.size;
break;
case 2: /* RO after init */
mod->data_layout.size = strict_align(mod->data_layout.size);
mod->data_layout.ro_after_init_size = mod->data_layout.size;
break;
case 4: /* whole core */
mod->data_layout.size = strict_align(mod->data_layout.size);
break;
}
}
__layout_sections(mod, info, false);
pr_debug("Init section allocation order:\n");
for (m = 0; m < ARRAY_SIZE(masks); ++m) {
for (i = 0; i < info->hdr->e_shnum; ++i) {
Elf_Shdr *s = &info->sechdrs[i];
const char *sname = info->secstrings + s->sh_name;
if ((s->sh_flags & masks[m][0]) != masks[m][0]
|| (s->sh_flags & masks[m][1])
|| s->sh_entsize != ~0UL
|| !module_init_layout_section(sname))
continue;
s->sh_entsize = (module_get_offset(mod, &mod->init_layout.size, s, i)
| INIT_OFFSET_MASK);
pr_debug("\t%s\n", sname);
}
switch (m) {
case 0: /* executable */
mod->init_layout.size = strict_align(mod->init_layout.size);
mod->init_layout.text_size = mod->init_layout.size;
break;
case 1: /* RO: text and ro-data */
mod->init_layout.size = strict_align(mod->init_layout.size);
mod->init_layout.ro_size = mod->init_layout.size;
break;
case 2:
/*
* RO after init doesn't apply to init_layout (only
* core_layout), so it just takes the value of ro_size.
*/
mod->init_layout.ro_after_init_size = mod->init_layout.ro_size;
break;
case 4: /* whole init */
mod->init_layout.size = strict_align(mod->init_layout.size);
break;
}
}
__layout_sections(mod, info, true);
}
static void set_license(struct module *mod, const char *license)
@@ -2122,72 +2149,41 @@ static int move_module(struct module *mod, struct load_info *info)
{
int i;
void *ptr;
enum mod_mem_type t;
/* Do the allocs. */
ptr = module_alloc(mod->core_layout.size);
/*
* The pointer to this block is stored in the module structure
* which is inside the block. Just mark it as not being a
* leak.
*/
kmemleak_not_leak(ptr);
if (!ptr)
return -ENOMEM;
for_each_mod_mem_type(type) {
if (!mod->mem[type].size) {
mod->mem[type].base = NULL;
continue;
}
mod->mem[type].size = PAGE_ALIGN(mod->mem[type].size);
ptr = module_memory_alloc(mod->mem[type].size, type);
memset(ptr, 0, mod->core_layout.size);
mod->core_layout.base = ptr;
if (mod->init_layout.size) {
ptr = module_alloc(mod->init_layout.size);
/*
* The pointer to this block is stored in the module structure
* which is inside the block. This block doesn't need to be
* scanned as it contains data and code that will be freed
* after the module is initialized.
* which is inside the block. Just mark it as not being a
* leak.
*/
kmemleak_ignore(ptr);
if (!ptr) {
module_memfree(mod->core_layout.base);
return -ENOMEM;
t = type;
goto out_enomem;
}
memset(ptr, 0, mod->init_layout.size);
mod->init_layout.base = ptr;
} else
mod->init_layout.base = NULL;
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
/* Do the allocs. */
ptr = vzalloc(mod->data_layout.size);
/*
* The pointer to this block is stored in the module structure
* which is inside the block. Just mark it as not being a
* leak.
*/
kmemleak_not_leak(ptr);
if (!ptr) {
module_memfree(mod->core_layout.base);
module_memfree(mod->init_layout.base);
return -ENOMEM;
memset(ptr, 0, mod->mem[type].size);
mod->mem[type].base = ptr;
}
mod->data_layout.base = ptr;
#endif
/* Transfer each section which specifies SHF_ALLOC */
pr_debug("final section addresses:\n");
for (i = 0; i < info->hdr->e_shnum; i++) {
void *dest;
Elf_Shdr *shdr = &info->sechdrs[i];
enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT;
if (!(shdr->sh_flags & SHF_ALLOC))
continue;
if (shdr->sh_entsize & INIT_OFFSET_MASK)
dest = mod->init_layout.base
+ (shdr->sh_entsize & ~INIT_OFFSET_MASK);
else if (!(shdr->sh_flags & SHF_EXECINSTR))
dest = mod->data_layout.base + shdr->sh_entsize;
else
dest = mod->core_layout.base + shdr->sh_entsize;
dest = mod->mem[type].base + (shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK);
if (shdr->sh_type != SHT_NOBITS)
memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size);
@@ -2198,6 +2194,10 @@ static int move_module(struct module *mod, struct load_info *info)
}
return 0;
out_enomem:
for (t--; t >= 0; t--)
module_memory_free(mod->mem[t].base, t);
return -ENOMEM;
}
static int check_module_license_and_versions(struct module *mod)
@@ -2242,12 +2242,14 @@ static void flush_module_icache(const struct module *mod)
* Do it before processing of module parameters, so the module
* can provide parameter accessor functions of its own.
*/
if (mod->init_layout.base)
flush_icache_range((unsigned long)mod->init_layout.base,
(unsigned long)mod->init_layout.base
+ mod->init_layout.size);
flush_icache_range((unsigned long)mod->core_layout.base,
(unsigned long)mod->core_layout.base + mod->core_layout.size);
for_each_mod_mem_type(type) {
const struct module_memory *mod_mem = &mod->mem[type];
if (mod_mem->size) {
flush_icache_range((unsigned long)mod_mem->base,
(unsigned long)mod_mem->base + mod_mem->size);
}
}
}
bool __weak module_elf_check_arch(Elf_Ehdr *hdr)
@@ -2350,11 +2352,8 @@ static void module_deallocate(struct module *mod, struct load_info *info)
{
percpu_modfree(mod);
module_arch_freeing_init(mod);
module_memfree(mod->init_layout.base);
module_memfree(mod->core_layout.base);
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
vfree(mod->data_layout.base);
#endif
free_mod_mem(mod);
}
int __weak module_finalize(const Elf_Ehdr *hdr,
@@ -2415,7 +2414,9 @@ static void do_mod_ctors(struct module *mod)
/* For freeing module_init on success, in case kallsyms traversing */
struct mod_initfree {
struct llist_node node;
void *module_init;
void *init_text;
void *init_data;
void *init_rodata;
};
static void do_free_init(struct work_struct *w)
@@ -2429,7 +2430,9 @@ static void do_free_init(struct work_struct *w)
llist_for_each_safe(pos, n, list) {
initfree = container_of(pos, struct mod_initfree, node);
module_memfree(initfree->module_init);
module_memfree(initfree->init_text);
module_memfree(initfree->init_data);
module_memfree(initfree->init_rodata);
kfree(initfree);
}
}
@@ -2456,7 +2459,9 @@ static noinline int do_init_module(struct module *mod)
ret = -ENOMEM;
goto fail;
}
freeinit->module_init = mod->init_layout.base;
freeinit->init_text = mod->mem[MOD_INIT_TEXT].base;
freeinit->init_data = mod->mem[MOD_INIT_DATA].base;
freeinit->init_rodata = mod->mem[MOD_INIT_RODATA].base;
do_mod_ctors(mod);
/* Start the module */
@@ -2492,8 +2497,8 @@ static noinline int do_init_module(struct module *mod)
if (!mod->async_probe_requested)
async_synchronize_full();
ftrace_free_mem(mod, mod->init_layout.base, mod->init_layout.base +
mod->init_layout.size);
ftrace_free_mem(mod, mod->mem[MOD_INIT_TEXT].base,
mod->mem[MOD_INIT_TEXT].base + mod->mem[MOD_INIT_TEXT].size);
mutex_lock(&module_mutex);
/* Drop initial reference. */
module_put(mod);
@@ -2505,11 +2510,10 @@ static noinline int do_init_module(struct module *mod)
module_enable_ro(mod, true);
mod_tree_remove_init(mod);
module_arch_freeing_init(mod);
mod->init_layout.base = NULL;
mod->init_layout.size = 0;
mod->init_layout.ro_size = 0;
mod->init_layout.ro_after_init_size = 0;
mod->init_layout.text_size = 0;
for_class_mod_mem_type(type, init) {
mod->mem[type].base = NULL;
mod->mem[type].size = 0;
}
#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
/* .BTF is not SHF_ALLOC and will get removed, so sanitize pointer */
mod->btf_data = NULL;
@@ -2628,9 +2632,6 @@ static int complete_formation(struct module *mod, struct load_info *info)
module_bug_finalize(info->hdr, info->sechdrs, mod);
module_cfi_finalize(info->hdr, info->sechdrs, mod);
if (module_check_misalignment(mod))
goto out_misaligned;
module_enable_ro(mod, false);
module_enable_nx(mod);
module_enable_x(mod);
@@ -2644,8 +2645,6 @@ static int complete_formation(struct module *mod, struct load_info *info)
return 0;
out_misaligned:
err = -EINVAL;
out:
mutex_unlock(&module_mutex);
return err;
@@ -2909,7 +2908,10 @@ static int load_module(struct load_info *info, const char __user *uargs,
mutex_unlock(&module_mutex);
free_module:
/* Free lock-classes; relies on the preceding sync_rcu() */
lockdep_free_key_range(mod->data_layout.base, mod->data_layout.size);
for_class_mod_mem_type(type, core_data) {
lockdep_free_key_range(mod->mem[type].base,
mod->mem[type].size);
}
module_deallocate(mod, info);
free_copy:
@@ -3060,20 +3062,21 @@ bool is_module_address(unsigned long addr)
struct module *__module_address(unsigned long addr)
{
struct module *mod;
struct mod_tree_root *tree;
if (addr >= mod_tree.addr_min && addr <= mod_tree.addr_max)
tree = &mod_tree;
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
else if (addr >= mod_data_tree.addr_min && addr <= mod_data_tree.addr_max)
tree = &mod_data_tree;
#endif
else
return NULL;
goto lookup;
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
if (addr >= mod_tree.data_addr_min && addr <= mod_tree.data_addr_max)
goto lookup;
#endif
return NULL;
lookup:
module_assert_mutex_or_preempt();
mod = mod_find(addr, tree);
mod = mod_find(addr, &mod_tree);
if (mod) {
BUG_ON(!within_module(addr, mod));
if (mod->state == MODULE_STATE_UNFORMED)
@@ -3113,8 +3116,8 @@ struct module *__module_text_address(unsigned long addr)
struct module *mod = __module_address(addr);
if (mod) {
/* Make sure it's within the text section. */
if (!within(addr, mod->init_layout.base, mod->init_layout.text_size)
&& !within(addr, mod->core_layout.base, mod->core_layout.text_size))
if (!within_module_mem_type(addr, mod, MOD_TEXT) &&
!within_module_mem_type(addr, mod, MOD_INIT_TEXT))
mod = NULL;
}
return mod;

16
kernel/module/procfs.c
View File

@@ -62,6 +62,15 @@ static void m_stop(struct seq_file *m, void *p)
mutex_unlock(&module_mutex);
}
static unsigned int module_total_size(struct module *mod)
{
int size = 0;
for_each_mod_mem_type(type)
size += mod->mem[type].size;
return size;
}
static int m_show(struct seq_file *m, void *p)
{
struct module *mod = list_entry(p, struct module, list);
@@ -73,10 +82,7 @@ static int m_show(struct seq_file *m, void *p)
if (mod->state == MODULE_STATE_UNFORMED)
return 0;
size = mod->init_layout.size + mod->core_layout.size;
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
size += mod->data_layout.size;
#endif
size = module_total_size(mod);
seq_printf(m, "%s %u", mod->name, size);
print_unload_info(m, mod);
@@ -86,7 +92,7 @@ static int m_show(struct seq_file *m, void *p)
mod->state == MODULE_STATE_COMING ? "Loading" :
"Live");
/* Used by oprofile and other similar tools. */
value = m->private ? NULL : mod->core_layout.base;
value = m->private ? NULL : mod->mem[MOD_TEXT].base;
seq_printf(m, " 0x%px", value);
/* Taints info */

99
kernel/module/strict_rwx.c
View File

@@ -11,82 +11,25 @@
#include <linux/set_memory.h>
#include "internal.h"
/*
* LKM RO/NX protection: protect module's text/ro-data
* from modification and any data from execution.
*
* General layout of module is:
* [text] [read-only-data] [ro-after-init] [writable data]
* text_size -----^ ^ ^ ^
* ro_size ------------------------| | |
* ro_after_init_size -----------------------------| |
* size -----------------------------------------------------------|
*
* These values are always page-aligned (as is base) when
* CONFIG_STRICT_MODULE_RWX is set.
*/
static void module_set_memory(const struct module *mod, enum mod_mem_type type,
int (*set_memory)(unsigned long start, int num_pages))
{
const struct module_memory *mod_mem = &mod->mem[type];
set_vm_flush_reset_perms(mod_mem->base);
set_memory((unsigned long)mod_mem->base, mod_mem->size >> PAGE_SHIFT);
}
/*
* Since some arches are moving towards PAGE_KERNEL module allocations instead
* of PAGE_KERNEL_EXEC, keep frob_text() and module_enable_x() independent of
* of PAGE_KERNEL_EXEC, keep module_enable_x() independent of
* CONFIG_STRICT_MODULE_RWX because they are needed regardless of whether we
* are strict.
*/
static void frob_text(const struct module_layout *layout,
int (*set_memory)(unsigned long start, int num_pages))
{
set_memory((unsigned long)layout->base,
PAGE_ALIGN(layout->text_size) >> PAGE_SHIFT);
}
static void frob_rodata(const struct module_layout *layout,
int (*set_memory)(unsigned long start, int num_pages))
{
set_memory((unsigned long)layout->base + layout->text_size,
(layout->ro_size - layout->text_size) >> PAGE_SHIFT);
}
static void frob_ro_after_init(const struct module_layout *layout,
int (*set_memory)(unsigned long start, int num_pages))
{
set_memory((unsigned long)layout->base + layout->ro_size,
(layout->ro_after_init_size - layout->ro_size) >> PAGE_SHIFT);
}
static void frob_writable_data(const struct module_layout *layout,
int (*set_memory)(unsigned long start, int num_pages))
{
set_memory((unsigned long)layout->base + layout->ro_after_init_size,
(layout->size - layout->ro_after_init_size) >> PAGE_SHIFT);
}
static bool layout_check_misalignment(const struct module_layout *layout)
{
return WARN_ON(!PAGE_ALIGNED(layout->base)) ||
WARN_ON(!PAGE_ALIGNED(layout->text_size)) ||
WARN_ON(!PAGE_ALIGNED(layout->ro_size)) ||
WARN_ON(!PAGE_ALIGNED(layout->ro_after_init_size)) ||
WARN_ON(!PAGE_ALIGNED(layout->size));
}
bool module_check_misalignment(const struct module *mod)
{
if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
return false;
return layout_check_misalignment(&mod->core_layout) ||
layout_check_misalignment(&mod->data_layout) ||
layout_check_misalignment(&mod->init_layout);
}
void module_enable_x(const struct module *mod)
{
if (!PAGE_ALIGNED(mod->core_layout.base) ||
!PAGE_ALIGNED(mod->init_layout.base))
return;
frob_text(&mod->core_layout, set_memory_x);
frob_text(&mod->init_layout, set_memory_x);
for_class_mod_mem_type(type, text)
module_set_memory(mod, type, set_memory_x);
}
void module_enable_ro(const struct module *mod, bool after_init)
@@ -98,16 +41,13 @@ void module_enable_ro(const struct module *mod, bool after_init)
return;
#endif
set_vm_flush_reset_perms(mod->core_layout.base);
set_vm_flush_reset_perms(mod->init_layout.base);
frob_text(&mod->core_layout, set_memory_ro);
frob_rodata(&mod->data_layout, set_memory_ro);
frob_text(&mod->init_layout, set_memory_ro);
frob_rodata(&mod->init_layout, set_memory_ro);
module_set_memory(mod, MOD_TEXT, set_memory_ro);
module_set_memory(mod, MOD_INIT_TEXT, set_memory_ro);
module_set_memory(mod, MOD_RODATA, set_memory_ro);
module_set_memory(mod, MOD_INIT_RODATA, set_memory_ro);
if (after_init)
frob_ro_after_init(&mod->data_layout, set_memory_ro);
module_set_memory(mod, MOD_RO_AFTER_INIT, set_memory_ro);
}
void module_enable_nx(const struct module *mod)
@@ -115,11 +55,8 @@ void module_enable_nx(const struct module *mod)
if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
return;
frob_rodata(&mod->data_layout, set_memory_nx);
frob_ro_after_init(&mod->data_layout, set_memory_nx);
frob_writable_data(&mod->data_layout, set_memory_nx);
frob_rodata(&mod->init_layout, set_memory_nx);
frob_writable_data(&mod->init_layout, set_memory_nx);
for_class_mod_mem_type(type, data)
module_set_memory(mod, type, set_memory_nx);
}
int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,

39
kernel/module/tree_lookup.c
View File

@@ -21,16 +21,16 @@
static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n)
{
struct module_layout *layout = container_of(n, struct module_layout, mtn.node);
struct module_memory *mod_mem = container_of(n, struct module_memory, mtn.node);
return (unsigned long)layout->base;
return (unsigned long)mod_mem->base;
}
static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n)
{
struct module_layout *layout = container_of(n, struct module_layout, mtn.node);
struct module_memory *mod_mem = container_of(n, struct module_memory, mtn.node);
return (unsigned long)layout->size;
return (unsigned long)mod_mem->size;
}
static __always_inline bool
@@ -77,32 +77,27 @@ static void __mod_tree_remove(struct mod_tree_node *node, struct mod_tree_root *
*/
void mod_tree_insert(struct module *mod)
{
mod->core_layout.mtn.mod = mod;
mod->init_layout.mtn.mod = mod;
__mod_tree_insert(&mod->core_layout.mtn, &mod_tree);
if (mod->init_layout.size)
__mod_tree_insert(&mod->init_layout.mtn, &mod_tree);
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
mod->data_layout.mtn.mod = mod;
__mod_tree_insert(&mod->data_layout.mtn, &mod_data_tree);
#endif
for_each_mod_mem_type(type) {
mod->mem[type].mtn.mod = mod;
if (mod->mem[type].size)
__mod_tree_insert(&mod->mem[type].mtn, &mod_tree);
}
}
void mod_tree_remove_init(struct module *mod)
{
if (mod->init_layout.size)
__mod_tree_remove(&mod->init_layout.mtn, &mod_tree);
for_class_mod_mem_type(type, init) {
if (mod->mem[type].size)
__mod_tree_remove(&mod->mem[type].mtn, &mod_tree);
}
}
void mod_tree_remove(struct module *mod)
{
__mod_tree_remove(&mod->core_layout.mtn, &mod_tree);
mod_tree_remove_init(mod);
#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
__mod_tree_remove(&mod->data_layout.mtn, &mod_data_tree);
#endif
for_each_mod_mem_type(type) {
if (mod->mem[type].size)
__mod_tree_remove(&mod->mem[type].mtn, &mod_tree);
}
}
struct module *mod_find(unsigned long addr, struct mod_tree_root *tree)