x86/module: prepare module loading for ROX allocations of text

When module text memory will be allocated with ROX permissions, the memory
at the actual address where the module will live will contain invalid
instructions and there will be a writable copy that contains the actual
module code.

Update relocations and alternatives patching to deal with it.

[rppt@kernel.org: fix writable address in cfi_rewrite_endbr()]
  Link: https://lkml.kernel.org/r/ZysRwR29Ji8CcbXc@kernel.org
Link: https://lkml.kernel.org/r/20241023162711.2579610-7-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Tested-by: kdevops <kdevops@lists.linux.dev>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Brian Cain <bcain@quicinc.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Helge Deller <deller@gmx.de>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.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: Oleg Nesterov <oleg@redhat.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Song Liu <song@kernel.org>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Vineet Gupta <vgupta@kernel.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Mike Rapoport (Microsoft)
2024-10-23 19:27:09 +03:00
committed by Andrew Morton
parent 0c6378a715
commit 9bfc4824fd
6 changed files with 171 additions and 121 deletions

View File

@@ -435,24 +435,25 @@ void __init arch_cpu_finalize_init(void)
os_check_bugs();
}
void apply_seal_endbr(s32 *start, s32 *end)
void apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
{
}
void apply_retpolines(s32 *start, s32 *end)
void apply_retpolines(s32 *start, s32 *end, struct module *mod)
{
}
void apply_returns(s32 *start, s32 *end)
void apply_returns(s32 *start, s32 *end, struct module *mod)
{
}
void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
s32 *start_cfi, s32 *end_cfi)
s32 *start_cfi, s32 *end_cfi, struct module *mod)
{
}
void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
struct module *mod)
{
}

View File

@@ -54,7 +54,8 @@ int __init init_vdso_image(const struct vdso_image *image)
apply_alternatives((struct alt_instr *)(image->data + image->alt),
(struct alt_instr *)(image->data + image->alt +
image->alt_len));
image->alt_len),
NULL);
return 0;
}

View File

@@ -96,16 +96,16 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
* instructions were patched in already:
*/
extern int alternatives_patched;
struct module;
extern void alternative_instructions(void);
extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
extern void apply_retpolines(s32 *start, s32 *end);
extern void apply_returns(s32 *start, s32 *end);
extern void apply_seal_endbr(s32 *start, s32 *end);
extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
struct module *mod);
extern void apply_retpolines(s32 *start, s32 *end, struct module *mod);
extern void apply_returns(s32 *start, s32 *end, struct module *mod);
extern void apply_seal_endbr(s32 *start, s32 *end, struct module *mod);
extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
s32 *start_cfi, s32 *end_cfi);
struct module;
s32 *start_cfi, s32 *end_cfi, struct module *mod);
struct callthunk_sites {
s32 *call_start, *call_end;

File diff suppressed because it is too large Load Diff

View File

@@ -118,10 +118,13 @@ ftrace_modify_code_direct(unsigned long ip, const char *old_code,
return ret;
/* replace the text with the new text */
if (ftrace_poke_late)
if (ftrace_poke_late) {
text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
else
text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
} else {
mutex_lock(&text_mutex);
text_poke((void *)ip, new_code, MCOUNT_INSN_SIZE);
mutex_unlock(&text_mutex);
}
return 0;
}
@@ -318,7 +321,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
union ftrace_op_code_union op_ptr;
int ret;
void *ret;
if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
start_offset = (unsigned long)ftrace_regs_caller;
@@ -349,15 +352,15 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
/* Copy ftrace_caller onto the trampoline memory */
ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
if (WARN_ON(ret < 0))
ret = text_poke_copy(trampoline, (void *)start_offset, size);
if (WARN_ON(!ret))
goto fail;
ip = trampoline + size;
if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
else
memcpy(ip, retq, sizeof(retq));
text_poke_copy(ip, retq, sizeof(retq));
/* No need to test direct calls on created trampolines */
if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
@@ -365,8 +368,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
ip = trampoline + (jmp_offset - start_offset);
if (WARN_ON(*(char *)ip != 0x75))
goto fail;
ret = copy_from_kernel_nofault(ip, x86_nops[2], 2);
if (ret < 0)
if (!text_poke_copy(ip, x86_nops[2], 2))
goto fail;
}
@@ -379,7 +381,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
*/
ptr = (unsigned long *)(trampoline + size + RET_SIZE);
*ptr = (unsigned long)ops;
text_poke_copy(ptr, &ops, sizeof(unsigned long));
op_offset -= start_offset;
memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
@@ -395,7 +397,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
op_ptr.offset = offset;
/* put in the new offset to the ftrace_ops */
memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
text_poke_copy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
/* put in the call to the function */
mutex_lock(&text_mutex);
@@ -405,9 +407,9 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
* the depth accounting before the call already.
*/
dest = ftrace_ops_get_func(ops);
memcpy(trampoline + call_offset,
text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
CALL_INSN_SIZE);
text_poke_copy_locked(trampoline + call_offset,
text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
CALL_INSN_SIZE, false);
mutex_unlock(&text_mutex);
/* ALLOC_TRAMP flags lets us know we created it */

View File

@@ -146,18 +146,21 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
}
if (apply) {
if (memcmp(loc, &zero, size)) {
void *wr_loc = module_writable_address(me, loc);
if (memcmp(wr_loc, &zero, size)) {
pr_err("x86/modules: 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;
}
write(loc, &val, size);
write(wr_loc, &val, size);
} else {
if (memcmp(loc, &val, size)) {
pr_warn("x86/modules: Invalid relocation target, existing value does not match expected value for type %d, loc %p, val %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), loc, val);
return -ENOEXEC;
}
/* FIXME: needs care for ROX module allocations */
write(loc, &zero, size);
}
}
@@ -224,7 +227,7 @@ int module_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *me)
{
const Elf_Shdr *s, *alt = NULL, *locks = NULL,
const Elf_Shdr *s, *alt = NULL,
*orc = NULL, *orc_ip = NULL,
*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
*calls = NULL, *cfi = NULL;
@@ -233,8 +236,6 @@ int module_finalize(const Elf_Ehdr *hdr,
for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
if (!strcmp(".altinstructions", secstrings + s->sh_name))
alt = s;
if (!strcmp(".smp_locks", secstrings + s->sh_name))
locks = s;
if (!strcmp(".orc_unwind", secstrings + s->sh_name))
orc = s;
if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
@@ -265,20 +266,20 @@ int module_finalize(const Elf_Ehdr *hdr,
csize = cfi->sh_size;
}
apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize);
apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize, me);
}
if (retpolines) {
void *rseg = (void *)retpolines->sh_addr;
apply_retpolines(rseg, rseg + retpolines->sh_size);
apply_retpolines(rseg, rseg + retpolines->sh_size, me);
}
if (returns) {
void *rseg = (void *)returns->sh_addr;
apply_returns(rseg, rseg + returns->sh_size);
apply_returns(rseg, rseg + returns->sh_size, me);
}
if (alt) {
/* patch .altinstructions */
void *aseg = (void *)alt->sh_addr;
apply_alternatives(aseg, aseg + alt->sh_size);
apply_alternatives(aseg, aseg + alt->sh_size, me);
}
if (calls || alt) {
struct callthunk_sites cs = {};
@@ -297,15 +298,7 @@ int module_finalize(const Elf_Ehdr *hdr,
}
if (ibt_endbr) {
void *iseg = (void *)ibt_endbr->sh_addr;
apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size);
}
if (locks) {
void *lseg = (void *)locks->sh_addr;
void *text = me->mem[MOD_TEXT].base;
void *text_end = text + me->mem[MOD_TEXT].size;
alternatives_smp_module_add(me, me->name,
lseg, lseg + locks->sh_size,
text, text_end);
apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size, me);
}
if (orc && orc_ip)
@@ -315,6 +308,30 @@ int module_finalize(const Elf_Ehdr *hdr,
return 0;
}
int module_post_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *me)
{
const Elf_Shdr *s, *locks = NULL;
char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
if (!strcmp(".smp_locks", secstrings + s->sh_name))
locks = s;
}
if (locks) {
void *lseg = (void *)locks->sh_addr;
void *text = me->mem[MOD_TEXT].base;
void *text_end = text + me->mem[MOD_TEXT].size;
alternatives_smp_module_add(me, me->name,
lseg, lseg + locks->sh_size,
text, text_end);
}
return 0;
}
void module_arch_cleanup(struct module *mod)
{
alternatives_smp_module_del(mod);