mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-22 16:08:58 +07:00
be0f272bfc
When building the arm64 kernel with both CONFIG_ARM64_MODULE_PLTS and CONFIG_DYNAMIC_FTRACE enabled, the ftrace-mod.o object file is built with the kernel and contains a trampoline that is linked into each module, so that modules can be loaded far away from the kernel and still reach the ftrace entry point in the core kernel with an ordinary relative branch, as is emitted by the compiler instrumentation code dynamic ftrace relies on. In order to be able to build out of tree modules, this object file needs to be included into the linux-headers or linux-devel packages, which is undesirable, as it makes arm64 a special case (although a precedent does exist for 32-bit PPC). Given that the trampoline essentially consists of a PLT entry, let's not bother with a source or object file for it, and simply patch it in whenever the trampoline is being populated, using the existing PLT support routines. Cc: <stable@vger.kernel.org> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
198 lines
5.9 KiB
C
198 lines
5.9 KiB
C
/*
|
|
* Copyright (C) 2014-2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
|
|
#include <linux/elf.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/sort.h>
|
|
|
|
static bool in_init(const struct module *mod, void *loc)
|
|
{
|
|
return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size;
|
|
}
|
|
|
|
u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
|
|
Elf64_Sym *sym)
|
|
{
|
|
struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
|
|
&mod->arch.init;
|
|
struct plt_entry *plt = (struct plt_entry *)pltsec->plt->sh_addr;
|
|
int i = pltsec->plt_num_entries;
|
|
u64 val = sym->st_value + rela->r_addend;
|
|
|
|
plt[i] = get_plt_entry(val);
|
|
|
|
/*
|
|
* Check if the entry we just created is a duplicate. Given that the
|
|
* relocations are sorted, this will be the last entry we allocated.
|
|
* (if one exists).
|
|
*/
|
|
if (i > 0 && plt_entries_equal(plt + i, plt + i - 1))
|
|
return (u64)&plt[i - 1];
|
|
|
|
pltsec->plt_num_entries++;
|
|
BUG_ON(pltsec->plt_num_entries > pltsec->plt_max_entries);
|
|
|
|
return (u64)&plt[i];
|
|
}
|
|
|
|
#define cmp_3way(a,b) ((a) < (b) ? -1 : (a) > (b))
|
|
|
|
static int cmp_rela(const void *a, const void *b)
|
|
{
|
|
const Elf64_Rela *x = a, *y = b;
|
|
int i;
|
|
|
|
/* sort by type, symbol index and addend */
|
|
i = cmp_3way(ELF64_R_TYPE(x->r_info), ELF64_R_TYPE(y->r_info));
|
|
if (i == 0)
|
|
i = cmp_3way(ELF64_R_SYM(x->r_info), ELF64_R_SYM(y->r_info));
|
|
if (i == 0)
|
|
i = cmp_3way(x->r_addend, y->r_addend);
|
|
return i;
|
|
}
|
|
|
|
static bool duplicate_rel(const Elf64_Rela *rela, int num)
|
|
{
|
|
/*
|
|
* Entries are sorted by type, symbol index and addend. That means
|
|
* that, if a duplicate entry exists, it must be in the preceding
|
|
* slot.
|
|
*/
|
|
return num > 0 && cmp_rela(rela + num, rela + num - 1) == 0;
|
|
}
|
|
|
|
static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num,
|
|
Elf64_Word dstidx)
|
|
{
|
|
unsigned int ret = 0;
|
|
Elf64_Sym *s;
|
|
int i;
|
|
|
|
for (i = 0; i < num; i++) {
|
|
switch (ELF64_R_TYPE(rela[i].r_info)) {
|
|
case R_AARCH64_JUMP26:
|
|
case R_AARCH64_CALL26:
|
|
/*
|
|
* We only have to consider branch targets that resolve
|
|
* to symbols that are defined in a different section.
|
|
* This is not simply a heuristic, it is a fundamental
|
|
* limitation, since there is no guaranteed way to emit
|
|
* PLT entries sufficiently close to the branch if the
|
|
* section size exceeds the range of a branch
|
|
* instruction. So ignore relocations against defined
|
|
* symbols if they live in the same section as the
|
|
* relocation target.
|
|
*/
|
|
s = syms + ELF64_R_SYM(rela[i].r_info);
|
|
if (s->st_shndx == dstidx)
|
|
break;
|
|
|
|
/*
|
|
* Jump relocations with non-zero addends against
|
|
* undefined symbols are supported by the ELF spec, but
|
|
* do not occur in practice (e.g., 'jump n bytes past
|
|
* the entry point of undefined function symbol f').
|
|
* So we need to support them, but there is no need to
|
|
* take them into consideration when trying to optimize
|
|
* this code. So let's only check for duplicates when
|
|
* the addend is zero: this allows us to record the PLT
|
|
* entry address in the symbol table itself, rather than
|
|
* having to search the list for duplicates each time we
|
|
* emit one.
|
|
*/
|
|
if (rela[i].r_addend != 0 || !duplicate_rel(rela, i))
|
|
ret++;
|
|
break;
|
|
}
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
|
|
char *secstrings, struct module *mod)
|
|
{
|
|
unsigned long core_plts = 0;
|
|
unsigned long init_plts = 0;
|
|
Elf64_Sym *syms = NULL;
|
|
Elf_Shdr *tramp = NULL;
|
|
int i;
|
|
|
|
/*
|
|
* Find the empty .plt section so we can expand it to store the PLT
|
|
* entries. Record the symtab address as well.
|
|
*/
|
|
for (i = 0; i < ehdr->e_shnum; i++) {
|
|
if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
|
|
mod->arch.core.plt = sechdrs + i;
|
|
else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
|
|
mod->arch.init.plt = sechdrs + i;
|
|
else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
|
|
!strcmp(secstrings + sechdrs[i].sh_name,
|
|
".text.ftrace_trampoline"))
|
|
tramp = sechdrs + i;
|
|
else if (sechdrs[i].sh_type == SHT_SYMTAB)
|
|
syms = (Elf64_Sym *)sechdrs[i].sh_addr;
|
|
}
|
|
|
|
if (!mod->arch.core.plt || !mod->arch.init.plt) {
|
|
pr_err("%s: module PLT section(s) missing\n", mod->name);
|
|
return -ENOEXEC;
|
|
}
|
|
if (!syms) {
|
|
pr_err("%s: module symtab section missing\n", mod->name);
|
|
return -ENOEXEC;
|
|
}
|
|
|
|
for (i = 0; i < ehdr->e_shnum; i++) {
|
|
Elf64_Rela *rels = (void *)ehdr + sechdrs[i].sh_offset;
|
|
int numrels = sechdrs[i].sh_size / sizeof(Elf64_Rela);
|
|
Elf64_Shdr *dstsec = sechdrs + sechdrs[i].sh_info;
|
|
|
|
if (sechdrs[i].sh_type != SHT_RELA)
|
|
continue;
|
|
|
|
/* ignore relocations that operate on non-exec sections */
|
|
if (!(dstsec->sh_flags & SHF_EXECINSTR))
|
|
continue;
|
|
|
|
/* sort by type, symbol index and addend */
|
|
sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL);
|
|
|
|
if (strncmp(secstrings + dstsec->sh_name, ".init", 5) != 0)
|
|
core_plts += count_plts(syms, rels, numrels,
|
|
sechdrs[i].sh_info);
|
|
else
|
|
init_plts += count_plts(syms, rels, numrels,
|
|
sechdrs[i].sh_info);
|
|
}
|
|
|
|
mod->arch.core.plt->sh_type = SHT_NOBITS;
|
|
mod->arch.core.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
|
|
mod->arch.core.plt->sh_addralign = L1_CACHE_BYTES;
|
|
mod->arch.core.plt->sh_size = (core_plts + 1) * sizeof(struct plt_entry);
|
|
mod->arch.core.plt_num_entries = 0;
|
|
mod->arch.core.plt_max_entries = core_plts;
|
|
|
|
mod->arch.init.plt->sh_type = SHT_NOBITS;
|
|
mod->arch.init.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
|
|
mod->arch.init.plt->sh_addralign = L1_CACHE_BYTES;
|
|
mod->arch.init.plt->sh_size = (init_plts + 1) * sizeof(struct plt_entry);
|
|
mod->arch.init.plt_num_entries = 0;
|
|
mod->arch.init.plt_max_entries = init_plts;
|
|
|
|
if (tramp) {
|
|
tramp->sh_type = SHT_NOBITS;
|
|
tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
|
|
tramp->sh_addralign = __alignof__(struct plt_entry);
|
|
tramp->sh_size = sizeof(struct plt_entry);
|
|
}
|
|
|
|
return 0;
|
|
}
|