linux-sg2042/arch/arm/kernel/module-plts.c

229 lines
6.0 KiB
C
Raw Normal View History

/*
* Copyright (C) 2014 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>
#include <asm/cache.h>
#include <asm/opcodes.h>
#define PLT_ENT_STRIDE L1_CACHE_BYTES
#define PLT_ENT_COUNT (PLT_ENT_STRIDE / sizeof(u32))
#define PLT_ENT_SIZE (sizeof(struct plt_entries) / PLT_ENT_COUNT)
#ifdef CONFIG_THUMB2_KERNEL
#define PLT_ENT_LDR __opcode_to_mem_thumb32(0xf8dff000 | \
(PLT_ENT_STRIDE - 4))
#else
#define PLT_ENT_LDR __opcode_to_mem_arm(0xe59ff000 | \
(PLT_ENT_STRIDE - 8))
#endif
struct plt_entries {
u32 ldr[PLT_ENT_COUNT];
u32 lit[PLT_ENT_COUNT];
};
u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
{
ARM: kernel: avoid brute force search on PLT generation Given that we now sort the relocation sections in a way that guarantees that entries that can share a single PLT entry end up adjacently, there is no a longer a need to go over the entire list to look for an existing entry that matches our jump target. If such a match exists, it was the last one to be emitted, so we can simply check the preceding slot. Note that this will still work correctly in the [theoretical] presence of call/jump relocations against SHN_UNDEF symbols with non-zero addends, although not optimally. Since the relocations are presented in the same order that we checked them for duplicates, any duplicates that we failed to spot the first time around will be accounted for in the PLT allocation so there is guaranteed to be sufficient space for them when actually emitting the PLT. For instance, the following sequence of relocations: 000004d8 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 000004fc 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 0000050e 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000520 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000532 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000544 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000556 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000568 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 0000057a 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 0000058c 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 0000059e 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 000005b0 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 000005c2 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 000005d4 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null may result in several PLT entries to be allocated, and also emitted, if any of the entries in the middle refer to a Place that contains a non-zero addend (i.e., one for all the preceding zero-addend relocations, one for all the following zero-addend relocations, and one for the non-zero addend relocation itself) Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-18 16:58:49 +08:00
struct plt_entries *plt = (struct plt_entries *)mod->arch.plt->sh_addr;
int idx = 0;
/*
* Look for an existing entry pointing to 'val'. Given that the
* relocations are sorted, this will be the last entry we allocated.
* (if one exists).
*/
if (mod->arch.plt_count > 0) {
plt += (mod->arch.plt_count - 1) / PLT_ENT_COUNT;
idx = (mod->arch.plt_count - 1) % PLT_ENT_COUNT;
if (plt->lit[idx] == val)
return (u32)&plt->ldr[idx];
idx = (idx + 1) % PLT_ENT_COUNT;
if (!idx)
plt++;
}
ARM: kernel: avoid brute force search on PLT generation Given that we now sort the relocation sections in a way that guarantees that entries that can share a single PLT entry end up adjacently, there is no a longer a need to go over the entire list to look for an existing entry that matches our jump target. If such a match exists, it was the last one to be emitted, so we can simply check the preceding slot. Note that this will still work correctly in the [theoretical] presence of call/jump relocations against SHN_UNDEF symbols with non-zero addends, although not optimally. Since the relocations are presented in the same order that we checked them for duplicates, any duplicates that we failed to spot the first time around will be accounted for in the PLT allocation so there is guaranteed to be sufficient space for them when actually emitting the PLT. For instance, the following sequence of relocations: 000004d8 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 000004fc 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 0000050e 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000520 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000532 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000544 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000556 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 00000568 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 0000057a 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 0000058c 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 0000059e 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 000005b0 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 000005c2 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null 000005d4 00058b0a R_ARM_THM_CALL 00000000 warn_slowpath_null may result in several PLT entries to be allocated, and also emitted, if any of the entries in the middle refer to a Place that contains a non-zero addend (i.e., one for all the preceding zero-addend relocations, one for all the following zero-addend relocations, and one for the non-zero addend relocation itself) Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-18 16:58:49 +08:00
mod->arch.plt_count++;
BUG_ON(mod->arch.plt_count * PLT_ENT_SIZE > mod->arch.plt->sh_size);
if (!idx)
/* Populate a new set of entries */
*plt = (struct plt_entries){
{ [0 ... PLT_ENT_COUNT - 1] = PLT_ENT_LDR, },
{ val, }
};
else
plt->lit[idx] = val;
return (u32)&plt->ldr[idx];
}
#define cmp_3way(a,b) ((a) < (b) ? -1 : (a) > (b))
static int cmp_rel(const void *a, const void *b)
{
const Elf32_Rel *x = a, *y = b;
int i;
/* sort by type and symbol index */
i = cmp_3way(ELF32_R_TYPE(x->r_info), ELF32_R_TYPE(y->r_info));
if (i == 0)
i = cmp_3way(ELF32_R_SYM(x->r_info), ELF32_R_SYM(y->r_info));
return i;
}
static bool is_zero_addend_relocation(Elf32_Addr base, const Elf32_Rel *rel)
{
u32 *tval = (u32 *)(base + rel->r_offset);
/*
* Do a bitwise compare on the raw addend rather than fully decoding
* the offset and doing an arithmetic comparison.
* Note that a zero-addend jump/call relocation is encoded taking the
* PC bias into account, i.e., -8 for ARM and -4 for Thumb2.
*/
switch (ELF32_R_TYPE(rel->r_info)) {
u16 upper, lower;
case R_ARM_THM_CALL:
case R_ARM_THM_JUMP24:
upper = __mem_to_opcode_thumb16(((u16 *)tval)[0]);
lower = __mem_to_opcode_thumb16(((u16 *)tval)[1]);
return (upper & 0x7ff) == 0x7ff && (lower & 0x2fff) == 0x2ffe;
case R_ARM_CALL:
case R_ARM_PC24:
case R_ARM_JUMP24:
return (__mem_to_opcode_arm(*tval) & 0xffffff) == 0xfffffe;
}
BUG();
}
static bool duplicate_rel(Elf32_Addr base, const Elf32_Rel *rel, int num)
{
const Elf32_Rel *prev;
/*
* Entries are sorted by type and symbol index. That means that,
* if a duplicate entry exists, it must be in the preceding
* slot.
*/
if (!num)
return false;
prev = rel + num - 1;
return cmp_rel(rel + num, prev) == 0 &&
is_zero_addend_relocation(base, prev);
}
/* Count how many PLT entries we may need */
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
static unsigned int count_plts(const Elf32_Sym *syms, Elf32_Addr base,
const Elf32_Rel *rel, int num)
{
unsigned int ret = 0;
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
const Elf32_Sym *s;
int i;
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
for (i = 0; i < num; i++) {
switch (ELF32_R_TYPE(rel[i].r_info)) {
case R_ARM_CALL:
case R_ARM_PC24:
case R_ARM_JUMP24:
case R_ARM_THM_CALL:
case R_ARM_THM_JUMP24:
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
/*
* We only have to consider branch targets that resolve
* to undefined symbols. This is not simply a heuristic,
* it is a fundamental limitation, since the PLT itself
* is part of the module, and needs to be within range
* as well, so modules can never grow beyond that limit.
*/
s = syms + ELF32_R_SYM(rel[i].r_info);
if (s->st_shndx != SHN_UNDEF)
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.
*/
if (!is_zero_addend_relocation(base, rel + i) ||
!duplicate_rel(base, rel, i))
ret++;
}
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
}
return ret;
}
int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
char *secstrings, struct module *mod)
{
unsigned long plts = 0;
Elf32_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum;
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
Elf32_Sym *syms = NULL;
/*
* To store the PLTs, we expand the .text section for core module code
* and for initialization code.
*/
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
for (s = sechdrs; s < sechdrs_end; ++s) {
if (strcmp(".plt", secstrings + s->sh_name) == 0)
mod->arch.plt = s;
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
else if (s->sh_type == SHT_SYMTAB)
syms = (Elf32_Sym *)s->sh_addr;
}
if (!mod->arch.plt) {
pr_err("%s: module PLT section missing\n", mod->name);
return -ENOEXEC;
}
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
if (!syms) {
pr_err("%s: module symtab section missing\n", mod->name);
return -ENOEXEC;
}
for (s = sechdrs + 1; s < sechdrs_end; ++s) {
Elf32_Rel *rels = (void *)ehdr + s->sh_offset;
int numrels = s->sh_size / sizeof(Elf32_Rel);
Elf32_Shdr *dstsec = sechdrs + s->sh_info;
if (s->sh_type != SHT_REL)
continue;
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
/* ignore relocations that operate on non-exec sections */
if (!(dstsec->sh_flags & SHF_EXECINSTR))
continue;
/* sort by type and symbol index */
sort(rels, numrels, sizeof(Elf32_Rel), cmp_rel, NULL);
ARM: kernel: allocate PLT entries only for external symbols When CONFIG_ARM_MODULE_PLTS is enabled, jump and call instructions in modules no longer need to be within 16 MB (8 MB for Thumb2) of their targets. If they are further away, a PLT entry will be generated on the fly for each of them, which extends the range to the entire 32-bit address space. However, since these PLT entries will become the branch targets of the original jump and call instructions, the PLT itself needs to be in range, or we end up in the same situation we started in. Since the PLT is in a separate section, this essentially means that all jumps and calls inside the same module must be resolvable without PLT entries. The PLT allocation code executes before the module itself is loaded in its final location, and so it has to use a worst-case estimate for which jumps and calls will require an entry in the PLT at relocation time. As an optimization, this code deduplicates entries pointing to the same symbol, using a O(n^2) algorithm. However, it does not take the above into account, i.e., that PLT entries will only be needed for jump and call relocations against symbols that are not defined in the module. So disregard relocations against symbols that are defined in the module itself. As an additional minor optimization, ignore input sections that lack the SHF_EXECINSTR flag. Since jump and call relocations operate on executable instructions only, there is no need to look in sections that do not contain executable code. Tested-by: Jongsung Kim <neidhard.kim@lge.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
2016-08-16 22:49:56 +08:00
plts += count_plts(syms, dstsec->sh_addr, rels, numrels);
}
mod->arch.plt->sh_type = SHT_NOBITS;
mod->arch.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
mod->arch.plt->sh_addralign = L1_CACHE_BYTES;
mod->arch.plt->sh_size = round_up(plts * PLT_ENT_SIZE,
sizeof(struct plt_entries));
mod->arch.plt_count = 0;
pr_debug("%s: plt=%x\n", __func__, mod->arch.plt->sh_size);
return 0;
}