ea3752ba96
Contemporary kernels and modules can be relatively large, especially when common debug options are enabled. Using GCC 12.1.0, a v6.3-rc7 defconfig kernel is ~38M, and with PROVE_LOCKING + KASAN_INLINE enabled this expands to ~117M. Shanker reports [1] that the NVIDIA GPU driver alone can consume 110M of module space in some configurations. Both KASLR and ARM64_ERRATUM_843419 select MODULE_PLTS, so anyone wanting a kernel to have KASLR or run on Cortex-A53 will have MODULE_PLTS selected. This is the case in defconfig and distribution kernels (e.g. Debian, Android, etc). Practically speaking, this means we're very likely to need MODULE_PLTS and while it's almost guaranteed that MODULE_PLTS will be selected, it is possible to disable support, and we have to maintain some awkward special cases for such unusual configurations. This patch removes the MODULE_PLTS config option, with the support code always enabled if MODULES is selected. This results in a slight simplification, and will allow for further improvement in subsequent patches. For any config which currently selects MODULE_PLTS, there will be no functional change as a result of this patch. [1] https://lore.kernel.org/linux-arm-kernel/159ceeab-09af-3174-5058-445bc8dcf85b@nvidia.com/ Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Cc: Shanker Donthineni <sdonthineni@nvidia.com> Cc: Will Deacon <will@kernel.org> Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> Link: https://lore.kernel.org/r/20230530110328.2213762-6-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
70 lines
1.8 KiB
C
70 lines
1.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Copyright (C) 2012 ARM Ltd.
|
|
*/
|
|
#ifndef __ASM_MODULE_H
|
|
#define __ASM_MODULE_H
|
|
|
|
#include <asm-generic/module.h>
|
|
|
|
struct mod_plt_sec {
|
|
int plt_shndx;
|
|
int plt_num_entries;
|
|
int plt_max_entries;
|
|
};
|
|
|
|
struct mod_arch_specific {
|
|
struct mod_plt_sec core;
|
|
struct mod_plt_sec init;
|
|
|
|
/* for CONFIG_DYNAMIC_FTRACE */
|
|
struct plt_entry *ftrace_trampolines;
|
|
};
|
|
|
|
u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs,
|
|
void *loc, const Elf64_Rela *rela,
|
|
Elf64_Sym *sym);
|
|
|
|
u64 module_emit_veneer_for_adrp(struct module *mod, Elf64_Shdr *sechdrs,
|
|
void *loc, u64 val);
|
|
|
|
struct plt_entry {
|
|
/*
|
|
* A program that conforms to the AArch64 Procedure Call Standard
|
|
* (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
|
|
* IP1 (x17) may be inserted at any branch instruction that is
|
|
* exposed to a relocation that supports long branches. Since that
|
|
* is exactly what we are dealing with here, we are free to use x16
|
|
* as a scratch register in the PLT veneers.
|
|
*/
|
|
__le32 adrp; /* adrp x16, .... */
|
|
__le32 add; /* add x16, x16, #0x.... */
|
|
__le32 br; /* br x16 */
|
|
};
|
|
|
|
static inline bool is_forbidden_offset_for_adrp(void *place)
|
|
{
|
|
return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) &&
|
|
cpus_have_const_cap(ARM64_WORKAROUND_843419) &&
|
|
((u64)place & 0xfff) >= 0xff8;
|
|
}
|
|
|
|
struct plt_entry get_plt_entry(u64 dst, void *pc);
|
|
|
|
static inline const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
|
|
const Elf_Shdr *sechdrs,
|
|
const char *name)
|
|
{
|
|
const Elf_Shdr *s, *se;
|
|
const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
|
|
|
|
for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
|
|
if (strcmp(name, secstrs + s->sh_name) == 0)
|
|
return s;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
#endif /* __ASM_MODULE_H */
|