summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/module.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-12-14 15:03:00 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2022-12-14 15:03:00 -0800
commit94a855111ed9106971ca2617c5d075269e6aefde (patch)
tree330c762a403cf70c2cdbf12e7394e5e7c2a69a79 /arch/x86/kernel/module.c
parent93761c93e9da28d8a020777cee2a84133082b477 (diff)
parentf1a033cc6b9eb6d80322008422df3c87aa5d47a0 (diff)
Merge tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 core updates from Borislav Petkov: - Add the call depth tracking mitigation for Retbleed which has been long in the making. It is a lighterweight software-only fix for Skylake-based cores where enabling IBRS is a big hammer and causes a significant performance impact. What it basically does is, it aligns all kernel functions to 16 bytes boundary and adds a 16-byte padding before the function, objtool collects all functions' locations and when the mitigation gets applied, it patches a call accounting thunk which is used to track the call depth of the stack at any time. When that call depth reaches a magical, microarchitecture-specific value for the Return Stack Buffer, the code stuffs that RSB and avoids its underflow which could otherwise lead to the Intel variant of Retbleed. This software-only solution brings a lot of the lost performance back, as benchmarks suggest: https://lore.kernel.org/all/20220915111039.092790446@infradead.org/ That page above also contains a lot more detailed explanation of the whole mechanism - Implement a new control flow integrity scheme called FineIBT which is based on the software kCFI implementation and uses hardware IBT support where present to annotate and track indirect branches using a hash to validate them - Other misc fixes and cleanups * tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (80 commits) x86/paravirt: Use common macro for creating simple asm paravirt functions x86/paravirt: Remove clobber bitmask from .parainstructions x86/debug: Include percpu.h in debugreg.h to get DECLARE_PER_CPU() et al x86/cpufeatures: Move X86_FEATURE_CALL_DEPTH from bit 18 to bit 19 of word 11, to leave space for WIP X86_FEATURE_SGX_EDECCSSA bit x86/Kconfig: Enable kernel IBT by default x86,pm: Force out-of-line memcpy() objtool: Fix weak hole vs prefix symbol objtool: Optimize elf_dirty_reloc_sym() x86/cfi: Add boot time hash randomization x86/cfi: Boot time selection of CFI scheme x86/ibt: Implement FineIBT objtool: Add --cfi to generate the .cfi_sites section x86: Add prefix symbols for function padding objtool: Add option to generate prefix symbols objtool: Avoid O(bloody terrible) behaviour -- an ode to libelf objtool: Slice up elf_create_section_symbol() kallsyms: Revert "Take callthunks into account" x86: Unconfuse CONFIG_ and X86_FEATURE_ namespaces x86/retpoline: Fix crash printing warning x86/paravirt: Fix a !PARAVIRT build warning ...
Diffstat (limited to 'arch/x86/kernel/module.c')
-rw-r--r--arch/x86/kernel/module.c47
1 files changed, 42 insertions, 5 deletions
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index d85a6980e263..705fb2a41d7d 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -74,10 +74,11 @@ void *module_alloc(unsigned long size)
return NULL;
p = __vmalloc_node_range(size, MODULE_ALIGN,
- MODULES_VADDR + get_module_load_offset(),
- MODULES_END, gfp_mask,
- PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE,
- __builtin_return_address(0));
+ MODULES_VADDR + get_module_load_offset(),
+ MODULES_END, gfp_mask, PAGE_KERNEL,
+ VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK,
+ NUMA_NO_NODE, __builtin_return_address(0));
+
if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
vfree(p);
return NULL;
@@ -253,7 +254,8 @@ int module_finalize(const Elf_Ehdr *hdr,
{
const Elf_Shdr *s, *alt = NULL, *locks = NULL,
*para = NULL, *orc = NULL, *orc_ip = NULL,
- *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL;
+ *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
+ *calls = NULL, *cfi = NULL;
char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
@@ -271,6 +273,10 @@ int module_finalize(const Elf_Ehdr *hdr,
retpolines = s;
if (!strcmp(".return_sites", secstrings + s->sh_name))
returns = s;
+ if (!strcmp(".call_sites", secstrings + s->sh_name))
+ calls = s;
+ if (!strcmp(".cfi_sites", secstrings + s->sh_name))
+ cfi = s;
if (!strcmp(".ibt_endbr_seal", secstrings + s->sh_name))
ibt_endbr = s;
}
@@ -283,6 +289,22 @@ int module_finalize(const Elf_Ehdr *hdr,
void *pseg = (void *)para->sh_addr;
apply_paravirt(pseg, pseg + para->sh_size);
}
+ if (retpolines || cfi) {
+ void *rseg = NULL, *cseg = NULL;
+ unsigned int rsize = 0, csize = 0;
+
+ if (retpolines) {
+ rseg = (void *)retpolines->sh_addr;
+ rsize = retpolines->sh_size;
+ }
+
+ if (cfi) {
+ cseg = (void *)cfi->sh_addr;
+ csize = cfi->sh_size;
+ }
+
+ apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize);
+ }
if (retpolines) {
void *rseg = (void *)retpolines->sh_addr;
apply_retpolines(rseg, rseg + retpolines->sh_size);
@@ -296,6 +318,21 @@ int module_finalize(const Elf_Ehdr *hdr,
void *aseg = (void *)alt->sh_addr;
apply_alternatives(aseg, aseg + alt->sh_size);
}
+ if (calls || para) {
+ struct callthunk_sites cs = {};
+
+ if (calls) {
+ cs.call_start = (void *)calls->sh_addr;
+ cs.call_end = (void *)calls->sh_addr + calls->sh_size;
+ }
+
+ if (para) {
+ cs.pv_start = (void *)para->sh_addr;
+ cs.pv_end = (void *)para->sh_addr + para->sh_size;
+ }
+
+ callthunks_patch_module_calls(&cs, me);
+ }
if (ibt_endbr) {
void *iseg = (void *)ibt_endbr->sh_addr;
apply_ibt_endbr(iseg, iseg + ibt_endbr->sh_size);