On Thu, 1 Jun 2023 at 14:10, Masahiro Yamada <masahiroy@xxxxxxxxxx> wrote:
>
> When CONFIG_THUMB2_KERNEL is enabled, modpost fails to detect some
> types of section mismatches.
>
> [test code]
>
> #include <linux/init.h>
>
> int __initdata foo;
> int get_foo(void) { return foo; }
>
> It is apparently a bad reference, but modpost does not report anything.
>
> The test code above produces the following relocations.
>
> Relocation section '.rel.text' at offset 0x1e8 contains 2 entries:
> Offset Info Type Sym.Value Sym. Name
> 00000000 0000052f R_ARM_THM_MOVW_AB 00000000 .LANCHOR0
> 00000004 00000530 R_ARM_THM_MOVT_AB 00000000 .LANCHOR0
>
> Currently, R_ARM_THM_MOVW_ABS_NC and R_ARM_THM_MOVT_ABS are just skipped.
>
> Add code to handle them. I checked arch/arm/kernel/module.c to learn
> how the offset is encoded in the instruction.
>
> One more thing to note for Thumb instructions - the st_value is an odd
> value, so you need to mask the bit 0 to get the offset. Otherwise, you
> will get an off-by-one error in the nearest symbol look-up.
>
> It is documented in "ELF for the ARM Architecture" [1]:
>
> * If the symbol addresses a Thumb instruction, its value is the address
> of the instruction with bit zero set (in a relocatable object, the
> section offset with bit zero set).
>
> * For the purposes of relocation the value used shall be the address
> of the instruction (st_value & ~1).
>
> [1]: https://github.com/ARM-software/abi-aa/blob/main/aaelf32/aaelf32.rst
>
> Signed-off-by: Masahiro Yamada <masahiroy@xxxxxxxxxx>
> ---
>
> scripts/mod/modpost.c | 31 ++++++++++++++++++++++++++-----
> 1 file changed, 26 insertions(+), 5 deletions(-)
>
> diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
> index 32d56efe3f3b..528aa9175e84 100644
> --- a/scripts/mod/modpost.c
> +++ b/scripts/mod/modpost.c
> @@ -1082,7 +1082,8 @@ static Elf_Sym *find_nearest_sym(struct elf_info *elf, Elf_Addr addr,
> {
> Elf_Sym *sym;
> Elf_Sym *near = NULL;
> - Elf_Addr distance;
> + Elf_Addr sym_addr, distance;
> + bool is_arm = (elf->hdr->e_machine == EM_ARM);
>
> for (sym = elf->symtab_start; sym < elf->symtab_stop; sym++) {
> if (get_secindex(elf, sym) != secndx)
> @@ -1090,10 +1091,19 @@ static Elf_Sym *find_nearest_sym(struct elf_info *elf, Elf_Addr addr,
> if (!is_valid_name(elf, sym))
> continue;
>
> - if (addr >= sym->st_value)
> - distance = addr - sym->st_value;
> + sym_addr = sym->st_value;
> +
> + /*
> + * For ARM Thumb instruction, the bit 0 of st_value is set.
> + * Mask it to get the address.
> + */
> + if (is_arm)
> + sym_addr &= ~1;
> +
This is only appropriate for STT_FUNC symbols. If this is a data
reference, bit 0 could be a valid address bit.
> + if (addr >= sym_addr)
> + distance = addr - sym_addr;
> else if (allow_negative)
> - distance = sym->st_value - addr;
> + distance = sym_addr - addr;
> else
> continue;
>
> @@ -1266,7 +1276,7 @@ static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
> unsigned int r_typ = ELF_R_TYPE(r->r_info);
> Elf_Sym *sym = elf->symtab_start + ELF_R_SYM(r->r_info);
> void *loc = reloc_location(elf, sechdr, r);
> - uint32_t inst;
> + uint32_t inst, upper, lower;
> int32_t offset;
>
> switch (r_typ) {
> @@ -1288,6 +1298,17 @@ static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
> offset = sign_extend32((inst & 0x00ffffff) << 2, 25);
> r->r_addend = offset + sym->st_value + 8;
> break;
> + case R_ARM_THM_MOVW_ABS_NC:
> + case R_ARM_THM_MOVT_ABS:
> + upper = TO_NATIVE(*(uint16_t *)loc);
> + lower = TO_NATIVE(*((uint16_t *)loc + 1));
> + offset = sign_extend32(((upper & 0x000f) << 12) |
> + ((upper & 0x0400) << 1) |
> + ((lower & 0x7000) >> 4) |
> + (lower & 0x00ff),
> + 15);
> + r->r_addend = offset + sym->st_value;
> + break;
> case R_ARM_THM_CALL:
> case R_ARM_THM_JUMP24:
> case R_ARM_THM_JUMP19:
> --
> 2.39.2
>
