mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-19 10:14:23 +08:00
e31cf2f4ca
Patch series "mm: consolidate definitions of page table accessors", v2. The low level page table accessors (pXY_index(), pXY_offset()) are duplicated across all architectures and sometimes more than once. For instance, we have 31 definition of pgd_offset() for 25 supported architectures. Most of these definitions are actually identical and typically it boils down to, e.g. static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); } These definitions can be shared among 90% of the arches provided XYZ_SHIFT, PTRS_PER_XYZ and xyz_page_vaddr() are defined. For architectures that really need a custom version there is always possibility to override the generic version with the usual ifdefs magic. These patches introduce include/linux/pgtable.h that replaces include/asm-generic/pgtable.h and add the definitions of the page table accessors to the new header. This patch (of 12): The linux/mm.h header includes <asm/pgtable.h> to allow inlining of the functions involving page table manipulations, e.g. pte_alloc() and pmd_alloc(). So, there is no point to explicitly include <asm/pgtable.h> in the files that include <linux/mm.h>. The include statements in such cases are remove with a simple loop: for f in $(git grep -l "include <linux/mm.h>") ; do sed -i -e '/include <asm\/pgtable.h>/ d' $f done Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Mike Rapoport <rppt@kernel.org> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200514170327.31389-1-rppt@kernel.org Link: http://lkml.kernel.org/r/20200514170327.31389-2-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
303 lines
7.3 KiB
C
303 lines
7.3 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/* Kernel module help for x86.
|
|
Copyright (C) 2001 Rusty Russell.
|
|
|
|
*/
|
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
#include <linux/moduleloader.h>
|
|
#include <linux/elf.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/string.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/kasan.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/jump_label.h>
|
|
#include <linux/random.h>
|
|
#include <linux/memory.h>
|
|
|
|
#include <asm/text-patching.h>
|
|
#include <asm/page.h>
|
|
#include <asm/setup.h>
|
|
#include <asm/unwind.h>
|
|
|
|
#if 0
|
|
#define DEBUGP(fmt, ...) \
|
|
printk(KERN_DEBUG fmt, ##__VA_ARGS__)
|
|
#else
|
|
#define DEBUGP(fmt, ...) \
|
|
do { \
|
|
if (0) \
|
|
printk(KERN_DEBUG fmt, ##__VA_ARGS__); \
|
|
} while (0)
|
|
#endif
|
|
|
|
#ifdef CONFIG_RANDOMIZE_BASE
|
|
static unsigned long module_load_offset;
|
|
|
|
/* Mutex protects the module_load_offset. */
|
|
static DEFINE_MUTEX(module_kaslr_mutex);
|
|
|
|
static unsigned long int get_module_load_offset(void)
|
|
{
|
|
if (kaslr_enabled()) {
|
|
mutex_lock(&module_kaslr_mutex);
|
|
/*
|
|
* Calculate the module_load_offset the first time this
|
|
* code is called. Once calculated it stays the same until
|
|
* reboot.
|
|
*/
|
|
if (module_load_offset == 0)
|
|
module_load_offset =
|
|
(get_random_int() % 1024 + 1) * PAGE_SIZE;
|
|
mutex_unlock(&module_kaslr_mutex);
|
|
}
|
|
return module_load_offset;
|
|
}
|
|
#else
|
|
static unsigned long int get_module_load_offset(void)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
void *module_alloc(unsigned long size)
|
|
{
|
|
void *p;
|
|
|
|
if (PAGE_ALIGN(size) > MODULES_LEN)
|
|
return NULL;
|
|
|
|
p = __vmalloc_node_range(size, MODULE_ALIGN,
|
|
MODULES_VADDR + get_module_load_offset(),
|
|
MODULES_END, GFP_KERNEL,
|
|
PAGE_KERNEL, 0, NUMA_NO_NODE,
|
|
__builtin_return_address(0));
|
|
if (p && (kasan_module_alloc(p, size) < 0)) {
|
|
vfree(p);
|
|
return NULL;
|
|
}
|
|
|
|
return p;
|
|
}
|
|
|
|
#ifdef CONFIG_X86_32
|
|
int apply_relocate(Elf32_Shdr *sechdrs,
|
|
const char *strtab,
|
|
unsigned int symindex,
|
|
unsigned int relsec,
|
|
struct module *me)
|
|
{
|
|
unsigned int i;
|
|
Elf32_Rel *rel = (void *)sechdrs[relsec].sh_addr;
|
|
Elf32_Sym *sym;
|
|
uint32_t *location;
|
|
|
|
DEBUGP("Applying relocate section %u to %u\n",
|
|
relsec, sechdrs[relsec].sh_info);
|
|
for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
|
|
/* This is where to make the change */
|
|
location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
|
|
+ rel[i].r_offset;
|
|
/* This is the symbol it is referring to. Note that all
|
|
undefined symbols have been resolved. */
|
|
sym = (Elf32_Sym *)sechdrs[symindex].sh_addr
|
|
+ ELF32_R_SYM(rel[i].r_info);
|
|
|
|
switch (ELF32_R_TYPE(rel[i].r_info)) {
|
|
case R_386_32:
|
|
/* We add the value into the location given */
|
|
*location += sym->st_value;
|
|
break;
|
|
case R_386_PC32:
|
|
/* Add the value, subtract its position */
|
|
*location += sym->st_value - (uint32_t)location;
|
|
break;
|
|
default:
|
|
pr_err("%s: Unknown relocation: %u\n",
|
|
me->name, ELF32_R_TYPE(rel[i].r_info));
|
|
return -ENOEXEC;
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
#else /*X86_64*/
|
|
static int __apply_relocate_add(Elf64_Shdr *sechdrs,
|
|
const char *strtab,
|
|
unsigned int symindex,
|
|
unsigned int relsec,
|
|
struct module *me,
|
|
void *(*write)(void *dest, const void *src, size_t len))
|
|
{
|
|
unsigned int i;
|
|
Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;
|
|
Elf64_Sym *sym;
|
|
void *loc;
|
|
u64 val;
|
|
|
|
DEBUGP("Applying relocate section %u to %u\n",
|
|
relsec, sechdrs[relsec].sh_info);
|
|
for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
|
|
/* This is where to make the change */
|
|
loc = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
|
|
+ rel[i].r_offset;
|
|
|
|
/* This is the symbol it is referring to. Note that all
|
|
undefined symbols have been resolved. */
|
|
sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
|
|
+ ELF64_R_SYM(rel[i].r_info);
|
|
|
|
DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n",
|
|
(int)ELF64_R_TYPE(rel[i].r_info),
|
|
sym->st_value, rel[i].r_addend, (u64)loc);
|
|
|
|
val = sym->st_value + rel[i].r_addend;
|
|
|
|
switch (ELF64_R_TYPE(rel[i].r_info)) {
|
|
case R_X86_64_NONE:
|
|
break;
|
|
case R_X86_64_64:
|
|
if (*(u64 *)loc != 0)
|
|
goto invalid_relocation;
|
|
write(loc, &val, 8);
|
|
break;
|
|
case R_X86_64_32:
|
|
if (*(u32 *)loc != 0)
|
|
goto invalid_relocation;
|
|
write(loc, &val, 4);
|
|
if (val != *(u32 *)loc)
|
|
goto overflow;
|
|
break;
|
|
case R_X86_64_32S:
|
|
if (*(s32 *)loc != 0)
|
|
goto invalid_relocation;
|
|
write(loc, &val, 4);
|
|
if ((s64)val != *(s32 *)loc)
|
|
goto overflow;
|
|
break;
|
|
case R_X86_64_PC32:
|
|
case R_X86_64_PLT32:
|
|
if (*(u32 *)loc != 0)
|
|
goto invalid_relocation;
|
|
val -= (u64)loc;
|
|
write(loc, &val, 4);
|
|
#if 0
|
|
if ((s64)val != *(s32 *)loc)
|
|
goto overflow;
|
|
#endif
|
|
break;
|
|
case R_X86_64_PC64:
|
|
if (*(u64 *)loc != 0)
|
|
goto invalid_relocation;
|
|
val -= (u64)loc;
|
|
write(loc, &val, 8);
|
|
break;
|
|
default:
|
|
pr_err("%s: Unknown rela relocation: %llu\n",
|
|
me->name, ELF64_R_TYPE(rel[i].r_info));
|
|
return -ENOEXEC;
|
|
}
|
|
}
|
|
return 0;
|
|
|
|
invalid_relocation:
|
|
pr_err("x86/modules: Skipping invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
|
|
(int)ELF64_R_TYPE(rel[i].r_info), loc, val);
|
|
return -ENOEXEC;
|
|
|
|
overflow:
|
|
pr_err("overflow in relocation type %d val %Lx\n",
|
|
(int)ELF64_R_TYPE(rel[i].r_info), val);
|
|
pr_err("`%s' likely not compiled with -mcmodel=kernel\n",
|
|
me->name);
|
|
return -ENOEXEC;
|
|
}
|
|
|
|
int apply_relocate_add(Elf64_Shdr *sechdrs,
|
|
const char *strtab,
|
|
unsigned int symindex,
|
|
unsigned int relsec,
|
|
struct module *me)
|
|
{
|
|
int ret;
|
|
bool early = me->state == MODULE_STATE_UNFORMED;
|
|
void *(*write)(void *, const void *, size_t) = memcpy;
|
|
|
|
if (!early) {
|
|
write = text_poke;
|
|
mutex_lock(&text_mutex);
|
|
}
|
|
|
|
ret = __apply_relocate_add(sechdrs, strtab, symindex, relsec, me,
|
|
write);
|
|
|
|
if (!early) {
|
|
text_poke_sync();
|
|
mutex_unlock(&text_mutex);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
#endif
|
|
|
|
int module_finalize(const Elf_Ehdr *hdr,
|
|
const Elf_Shdr *sechdrs,
|
|
struct module *me)
|
|
{
|
|
const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
|
|
*para = NULL, *orc = NULL, *orc_ip = NULL;
|
|
char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
|
|
|
|
for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
|
|
if (!strcmp(".text", secstrings + s->sh_name))
|
|
text = s;
|
|
if (!strcmp(".altinstructions", secstrings + s->sh_name))
|
|
alt = s;
|
|
if (!strcmp(".smp_locks", secstrings + s->sh_name))
|
|
locks = s;
|
|
if (!strcmp(".parainstructions", secstrings + s->sh_name))
|
|
para = s;
|
|
if (!strcmp(".orc_unwind", secstrings + s->sh_name))
|
|
orc = s;
|
|
if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
|
|
orc_ip = s;
|
|
}
|
|
|
|
if (alt) {
|
|
/* patch .altinstructions */
|
|
void *aseg = (void *)alt->sh_addr;
|
|
apply_alternatives(aseg, aseg + alt->sh_size);
|
|
}
|
|
if (locks && text) {
|
|
void *lseg = (void *)locks->sh_addr;
|
|
void *tseg = (void *)text->sh_addr;
|
|
alternatives_smp_module_add(me, me->name,
|
|
lseg, lseg + locks->sh_size,
|
|
tseg, tseg + text->sh_size);
|
|
}
|
|
|
|
if (para) {
|
|
void *pseg = (void *)para->sh_addr;
|
|
apply_paravirt(pseg, pseg + para->sh_size);
|
|
}
|
|
|
|
/* make jump label nops */
|
|
jump_label_apply_nops(me);
|
|
|
|
if (orc && orc_ip)
|
|
unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
|
|
(void *)orc->sh_addr, orc->sh_size);
|
|
|
|
return 0;
|
|
}
|
|
|
|
void module_arch_cleanup(struct module *mod)
|
|
{
|
|
alternatives_smp_module_del(mod);
|
|
}
|