summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/alternative.c529
-rw-r--r--arch/x86/kernel/asm-offsets.c5
-rw-r--r--arch/x86/kernel/asm-offsets_64.c2
-rw-r--r--arch/x86/kernel/callthunks.c388
-rw-r--r--arch/x86/kernel/cpu/Makefile3
-rw-r--r--arch/x86/kernel/cpu/bugs.c34
-rw-r--r--arch/x86/kernel/cpu/common.c97
-rw-r--r--arch/x86/kernel/dumpstack_32.c4
-rw-r--r--arch/x86/kernel/dumpstack_64.c2
-rw-r--r--arch/x86/kernel/ftrace.c20
-rw-r--r--arch/x86/kernel/ftrace_64.S37
-rw-r--r--arch/x86/kernel/head_64.S1
-rw-r--r--arch/x86/kernel/irq_32.c13
-rw-r--r--arch/x86/kernel/irq_64.c6
-rw-r--r--arch/x86/kernel/kprobes/core.c1
-rw-r--r--arch/x86/kernel/kvm.c18
-rw-r--r--arch/x86/kernel/module.c47
-rw-r--r--arch/x86/kernel/paravirt.c21
-rw-r--r--arch/x86/kernel/process_32.c6
-rw-r--r--arch/x86/kernel/process_64.c6
-rw-r--r--arch/x86/kernel/relocate_kernel_64.S5
-rw-r--r--arch/x86/kernel/setup_percpu.c7
-rw-r--r--arch/x86/kernel/smpboot.c10
-rw-r--r--arch/x86/kernel/static_call.c3
-rw-r--r--arch/x86/kernel/traps.c4
-rw-r--r--arch/x86/kernel/unwind_orc.c21
-rw-r--r--arch/x86/kernel/vmlinux.lds.S37
28 files changed, 1141 insertions, 188 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index cceaafdd2d84..96d51bbc2bd4 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -143,6 +143,8 @@ obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o
obj-$(CONFIG_CFI_CLANG) += cfi.o
+obj-$(CONFIG_CALL_THUNKS) += callthunks.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a9bea860e22a..23cbfa8d34c5 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -116,6 +116,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
extern s32 __retpoline_sites[], __retpoline_sites_end[];
extern s32 __return_sites[], __return_sites_end[];
+extern s32 __cfi_sites[], __cfi_sites_end[];
extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[];
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
extern s32 __smp_locks[], __smp_locks_end[];
@@ -377,6 +378,56 @@ static int emit_indirect(int op, int reg, u8 *bytes)
return i;
}
+static inline bool is_jcc32(struct insn *insn)
+{
+ /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
+ return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80;
+}
+
+static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+ u8 op = insn->opcode.bytes[0];
+ int i = 0;
+
+ /*
+ * Clang does 'weird' Jcc __x86_indirect_thunk_r11 conditional
+ * tail-calls. Deal with them.
+ */
+ if (is_jcc32(insn)) {
+ bytes[i++] = op;
+ op = insn->opcode.bytes[1];
+ goto clang_jcc;
+ }
+
+ if (insn->length == 6)
+ bytes[i++] = 0x2e; /* CS-prefix */
+
+ switch (op) {
+ case CALL_INSN_OPCODE:
+ __text_gen_insn(bytes+i, op, addr+i,
+ __x86_indirect_call_thunk_array[reg],
+ CALL_INSN_SIZE);
+ i += CALL_INSN_SIZE;
+ break;
+
+ case JMP32_INSN_OPCODE:
+clang_jcc:
+ __text_gen_insn(bytes+i, op, addr+i,
+ __x86_indirect_jump_thunk_array[reg],
+ JMP32_INSN_SIZE);
+ i += JMP32_INSN_SIZE;
+ break;
+
+ default:
+ WARN(1, "%pS %px %*ph\n", addr, addr, 6, addr);
+ return -1;
+ }
+
+ WARN_ON_ONCE(i != insn->length);
+
+ return i;
+}
+
/*
* Rewrite the compiler generated retpoline thunk calls.
*
@@ -409,8 +460,12 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
BUG_ON(reg == 4);
if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
- !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE))
+ !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
+ if (cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
+ return emit_call_track_retpoline(addr, insn, reg, bytes);
+
return -1;
+ }
op = insn->opcode.bytes[0];
@@ -427,8 +482,7 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
* [ NOP ]
* 1:
*/
- /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
- if (op == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80) {
+ if (is_jcc32(insn)) {
cc = insn->opcode.bytes[1] & 0xf;
cc ^= 1; /* invert condition */
@@ -518,6 +572,11 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
}
#ifdef CONFIG_RETHUNK
+
+#ifdef CONFIG_CALL_THUNKS
+void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk;
+#endif
+
/*
* Rewrite the compiler generated return thunk tail-calls.
*
@@ -533,14 +592,18 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
{
int i = 0;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
- return -1;
+ if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+ if (x86_return_thunk == __x86_return_thunk)
+ return -1;
- bytes[i++] = RET_INSN_OPCODE;
+ i = JMP32_INSN_SIZE;
+ __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i);
+ } else {
+ bytes[i++] = RET_INSN_OPCODE;
+ }
for (; i < insn->length;)
bytes[i++] = INT3_INSN_OPCODE;
-
return i;
}
@@ -594,6 +657,28 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
#ifdef CONFIG_X86_KERNEL_IBT
+static void poison_endbr(void *addr, bool warn)
+{
+ u32 endbr, poison = gen_endbr_poison();
+
+ if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
+ return;
+
+ if (!is_endbr(endbr)) {
+ WARN_ON_ONCE(warn);
+ return;
+ }
+
+ DPRINTK("ENDBR at: %pS (%px)", addr, addr);
+
+ /*
+ * When we have IBT, the lack of ENDBR will trigger #CP
+ */
+ DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr);
+ DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr);
+ text_poke_early(addr, &poison, 4);
+}
+
/*
* Generated by: objtool --ibt
*/
@@ -602,31 +687,391 @@ void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end)
s32 *s;
for (s = start; s < end; s++) {
- u32 endbr, poison = gen_endbr_poison();
void *addr = (void *)s + *s;
- if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
+ poison_endbr(addr, true);
+ if (IS_ENABLED(CONFIG_FINEIBT))
+ poison_endbr(addr - 16, false);
+ }
+}
+
+#else
+
+void __init_or_module apply_ibt_endbr(s32 *start, s32 *end) { }
+
+#endif /* CONFIG_X86_KERNEL_IBT */
+
+#ifdef CONFIG_FINEIBT
+
+enum cfi_mode {
+ CFI_DEFAULT,
+ CFI_OFF,
+ CFI_KCFI,
+ CFI_FINEIBT,
+};
+
+static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT;
+static bool cfi_rand __ro_after_init = true;
+static u32 cfi_seed __ro_after_init;
+
+/*
+ * Re-hash the CFI hash with a boot-time seed while making sure the result is
+ * not a valid ENDBR instruction.
+ */
+static u32 cfi_rehash(u32 hash)
+{
+ hash ^= cfi_seed;
+ while (unlikely(is_endbr(hash) || is_endbr(-hash))) {
+ bool lsb = hash & 1;
+ hash >>= 1;
+ if (lsb)
+ hash ^= 0x80200003;
+ }
+ return hash;
+}
+
+static __init int cfi_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ while (str) {
+ char *next = strchr(str, ',');
+ if (next) {
+ *next = 0;
+ next++;
+ }
+
+ if (!strcmp(str, "auto")) {
+ cfi_mode = CFI_DEFAULT;
+ } else if (!strcmp(str, "off")) {
+ cfi_mode = CFI_OFF;
+ cfi_rand = false;
+ } else if (!strcmp(str, "kcfi")) {
+ cfi_mode = CFI_KCFI;
+ } else if (!strcmp(str, "fineibt")) {
+ cfi_mode = CFI_FINEIBT;
+ } else if (!strcmp(str, "norand")) {
+ cfi_rand = false;
+ } else {
+ pr_err("Ignoring unknown cfi option (%s).", str);
+ }
+
+ str = next;
+ }
+
+ return 0;
+}
+early_param("cfi", cfi_parse_cmdline);
+
+/*
+ * kCFI FineIBT
+ *
+ * __cfi_\func: __cfi_\func:
+ * movl $0x12345678,%eax // 5 endbr64 // 4
+ * nop subl $0x12345678,%r10d // 7
+ * nop jz 1f // 2
+ * nop ud2 // 2
+ * nop 1: nop // 1
+ * nop
+ * nop
+ * nop
+ * nop
+ * nop
+ * nop
+ * nop
+ *
+ *
+ * caller: caller:
+ * movl $(-0x12345678),%r10d // 6 movl $0x12345678,%r10d // 6
+ * addl $-15(%r11),%r10d // 4 sub $16,%r11 // 4
+ * je 1f // 2 nop4 // 4
+ * ud2 // 2
+ * 1: call __x86_indirect_thunk_r11 // 5 call *%r11; nop2; // 5
+ *
+ */
+
+asm( ".pushsection .rodata \n"
+ "fineibt_preamble_start: \n"
+ " endbr64 \n"
+ " subl $0x12345678, %r10d \n"
+ " je fineibt_preamble_end \n"
+ " ud2 \n"
+ " nop \n"
+ "fineibt_preamble_end: \n"
+ ".popsection\n"
+);
+
+extern u8 fineibt_preamble_start[];
+extern u8 fineibt_preamble_end[];
+
+#define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
+#define fineibt_preamble_hash 7
+
+asm( ".pushsection .rodata \n"
+ "fineibt_caller_start: \n"
+ " movl $0x12345678, %r10d \n"
+ " sub $16, %r11 \n"
+ ASM_NOP4
+ "fineibt_caller_end: \n"
+ ".popsection \n"
+);
+
+extern u8 fineibt_caller_start[];
+extern u8 fineibt_caller_end[];
+
+#define fineibt_caller_size (fineibt_caller_end - fineibt_caller_start)
+#define fineibt_caller_hash 2
+
+#define fineibt_caller_jmp (fineibt_caller_size - 2)
+
+static u32 decode_preamble_hash(void *addr)
+{
+ u8 *p = addr;
+
+ /* b8 78 56 34 12 mov $0x12345678,%eax */
+ if (p[0] == 0xb8)
+ return *(u32 *)(addr + 1);
+
+ return 0; /* invalid hash value */
+}
+
+static u32 decode_caller_hash(void *addr)
+{
+ u8 *p = addr;
+
+ /* 41 ba 78 56 34 12 mov $0x12345678,%r10d */
+ if (p[0] == 0x41 && p[1] == 0xba)
+ return -*(u32 *)(addr + 2);
+
+ /* e8 0c 78 56 34 12 jmp.d8 +12 */
+ if (p[0] == JMP8_INSN_OPCODE && p[1] == fineibt_caller_jmp)
+ return -*(u32 *)(addr + 2);
+
+ return 0; /* invalid hash value */
+}
+
+/* .retpoline_sites */
+static int cfi_disable_callers(s32 *start, s32 *end)
+{
+ /*
+ * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate
+ * in tact for later usage. Also see decode_caller_hash() and
+ * cfi_rewrite_callers().
+ */
+ const u8 jmp[] = { JMP8_INSN_OPCODE, fineibt_caller_jmp };
+ s32 *s;
+
+ for (s = start; s < end; s++) {
+ void *addr = (void *)s + *s;
+ u32 hash;
+
+ addr -= fineibt_caller_size;
+ hash = decode_caller_hash(addr);
+ if (!hash) /* nocfi callers */
continue;
- if (WARN_ON_ONCE(!is_endbr(endbr)))
+ text_poke_early(addr, jmp, 2);
+ }
+
+ return 0;
+}
+
+static int cfi_enable_callers(s32 *start, s32 *end)
+{
+ /*
+ * Re-enable kCFI, undo what cfi_disable_callers() did.
+ */
+ const u8 mov[] = { 0x41, 0xba };
+ s32 *s;
+
+ for (s = start; s < end; s++) {
+ void *addr = (void *)s + *s;
+ u32 hash;
+
+ addr -= fineibt_caller_size;
+ hash = decode_caller_hash(addr);
+ if (!hash) /* nocfi callers */
continue;
- DPRINTK("ENDBR at: %pS (%px)", addr, addr);
+ text_poke_early(addr, mov, 2);
+ }
- /*
- * When we have IBT, the lack of ENDBR will trigger #CP
- */
- DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr);
- DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr);
- text_poke_early(addr, &poison, 4);
+ return 0;
+}
+
+/* .cfi_sites */
+static int cfi_rand_preamble(s32 *start, s32 *end)
+{
+ s32 *s;
+
+ for (s = start; s < end; s++) {
+ void *addr = (void *)s + *s;
+ u32 hash;
+
+ hash = decode_preamble_hash(addr);
+ if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
+ addr, addr, 5, addr))
+ return -EINVAL;
+
+ hash = cfi_rehash(hash);
+ text_poke_early(addr + 1, &hash, 4);
+ }
+
+ return 0;
+}
+
+static int cfi_rewrite_preamble(s32 *start, s32 *end)
+{
+ s32 *s;
+
+ for (s = start; s < end; s++) {
+ void *addr = (void *)s + *s;
+ u32 hash;
+
+ hash = decode_preamble_hash(addr);
+ if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
+ addr, addr, 5, addr))
+ return -EINVAL;
+
+ text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
+ WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
+ text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
+ }
+
+ return 0;
+}
+
+/* .retpoline_sites */
+static int cfi_rand_callers(s32 *start, s32 *end)
+{
+ s32 *s;
+
+ for (s = start; s < end; s++) {
+ void *addr = (void *)s + *s;
+ u32 hash;
+
+ addr -= fineibt_caller_size;
+ hash = decode_caller_hash(addr);
+ if (hash) {
+ hash = -cfi_rehash(hash);
+ text_poke_early(addr + 2, &hash, 4);
+ }
+ }
+
+ return 0;
+}
+
+static int cfi_rewrite_callers(s32 *start, s32 *end)
+{
+ s32 *s;
+
+ for (s = start; s < end; s++) {
+ void *addr = (void *)s + *s;
+ u32 hash;
+
+ addr -= fineibt_caller_size;
+ hash = decode_caller_hash(addr);
+ if (hash) {
+ text_poke_early(addr, fineibt_caller_start, fineibt_caller_size);
+ WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678);
+ text_poke_early(addr + fineibt_caller_hash, &hash, 4);
+ }
+ /* rely on apply_retpolines() */
+ }
+
+ return 0;
+}
+
+static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+ s32 *start_cfi, s32 *end_cfi, bool builtin)
+{
+ int ret;
+
+ if (WARN_ONCE(fineibt_preamble_size != 16,
+ "FineIBT preamble wrong size: %ld", fineibt_preamble_size))
+ return;
+
+ if (cfi_mode == CFI_DEFAULT) {
+ cfi_mode = CFI_KCFI;
+ if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
+ cfi_mode = CFI_FINEIBT;
+ }
+
+ /*
+ * Rewrite the callers to not use the __cfi_ stubs, such that we might
+ * rewrite them. This disables all CFI. If this succeeds but any of the
+ * later stages fails, we're without CFI.
+ */
+ ret = cfi_disable_callers(start_retpoline, end_retpoline);
+ if (ret)
+ goto err;
+
+ if (cfi_rand) {
+ if (builtin)
+ cfi_seed = get_random_u32();
+
+ ret = cfi_rand_preamble(start_cfi, end_cfi);
+ if (ret)
+ goto err;
+
+ ret = cfi_rand_callers(start_retpoline, end_retpoline);
+ if (ret)
+ goto err;
+ }
+
+ switch (cfi_mode) {
+ case CFI_OFF:
+ if (builtin)
+ pr_info("Disabling CFI\n");
+ return;
+
+ case CFI_KCFI:
+ ret = cfi_enable_callers(start_retpoline, end_retpoline);
+ if (ret)
+ goto err;
+
+ if (builtin)
+ pr_info("Using kCFI\n");
+ return;
+
+ case CFI_FINEIBT:
+ ret = cfi_rewrite_preamble(start_cfi, end_cfi);
+ if (ret)
+ goto err;
+
+ ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
+ if (ret)
+ goto err;
+
+ if (builtin)
+ pr_info("Using FineIBT CFI\n");
+ return;
+
+ default:
+ break;
}
+
+err:
+ pr_err("Something went horribly wrong trying to rewrite the CFI implementation.\n");
}
#else
-void __init_or_module apply_ibt_endbr(s32 *start, s32 *end) { }
+static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+ s32 *start_cfi, s32 *end_cfi, bool builtin)
+{
+}
-#endif /* CONFIG_X86_KERNEL_IBT */
+#endif
+
+void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+ s32 *start_cfi, s32 *end_cfi)
+{
+ return __apply_fineibt(start_retpoline, end_retpoline,
+ start_cfi, end_cfi,
+ /* .builtin = */ false);
+}
#ifdef CONFIG_SMP
static void alternatives_smp_lock(const s32 *start, const s32 *end,
@@ -934,6 +1379,9 @@ void __init alternative_instructions(void)
*/
apply_paravirt(__parainstructions, __parainstructions_end);
+ __apply_fineibt(__retpoline_sites, __retpoline_sites_end,
+ __cfi_sites, __cfi_sites_end, true);
+
/*
* Rewrite the retpolines, must be done before alternatives since
* those can rewrite the retpoline thunks.
@@ -947,6 +1395,12 @@ void __init alternative_instructions(void)
*/
apply_alternatives(__alt_instructions, __alt_instructions_end);
+ /*
+ * Now all calls are established. Apply the call thunks if
+ * required.
+ */
+ callthunks_patch_builtin_calls();
+
apply_ibt_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
#ifdef CONFIG_SMP
@@ -1236,27 +1690,15 @@ void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
return __text_poke(text_poke_memcpy, addr, opcode, len);
}
-/**
- * text_poke_copy - Copy instructions into (an unused part of) RX memory
- * @addr: address to modify
- * @opcode: source of the copy
- * @len: length to copy, could be more than 2x PAGE_SIZE
- *
- * Not safe against concurrent execution; useful for JITs to dump
- * new code blocks into unused regions of RX memory. Can be used in
- * conjunction with synchronize_rcu_tasks() to wait for existing
- * execution to quiesce after having made sure no existing functions
- * pointers are live.
- */
-void *text_poke_copy(void *addr, const void *opcode, size_t len)
+void *text_poke_copy_locked(void *addr, const void *opcode, size_t len,
+ bool core_ok)
{
unsigned long start = (unsigned long)addr;
size_t patched = 0;
- if (WARN_ON_ONCE(core_kernel_text(start)))
+ if (WARN_ON_ONCE(!core_ok && core_kernel_text(start)))
return NULL;
- mutex_lock(&text_mutex);
while (patched < len) {
unsigned long ptr = start + patched;
size_t s;
@@ -1266,6 +1708,25 @@ void *text_poke_copy(void *addr, const void *opcode, size_t len)
__text_poke(text_poke_memcpy, (void *)ptr, opcode + patched, s);
patched += s;
}
+ return addr;
+}
+
+/**
+ * text_poke_copy - Copy instructions into (an unused part of) RX memory
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy, could be more than 2x PAGE_SIZE
+ *
+ * Not safe against concurrent execution; useful for JITs to dump
+ * new code blocks into unused regions of RX memory. Can be used in
+ * conjunction with synchronize_rcu_tasks() to wait for existing
+ * execution to quiesce after having made sure no existing functions
+ * pointers are live.
+ */
+void *text_poke_copy(void *addr, const void *opcode, size_t len)
+{
+ mutex_lock(&text_mutex);
+ addr = text_poke_copy_locked(addr, opcode, len, false);
mutex_unlock(&text_mutex);
return addr;
}
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 437308004ef2..82c783da16a8 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -107,4 +107,9 @@ static void __used common(void)
OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
+ OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack);
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+ OFFSET(X86_call_depth, pcpu_hot, call_depth);
+#endif
+
}
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 9b698215d261..bb65371ea9df 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -57,7 +57,7 @@ int main(void)
BLANK();
#ifdef CONFIG_STACKPROTECTOR
- DEFINE(stack_canary_offset, offsetof(struct fixed_percpu_data, stack_canary));
+ OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary);
BLANK();
#endif
return 0;
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
new file mode 100644
index 000000000000..7d2c75ec9a8c
--- /dev/null
+++ b/arch/x86/kernel/callthunks.c
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "callthunks: " fmt
+
+#include <linux/debugfs.h>
+#include <linux/kallsyms.h>
+#include <linux/memory.h>
+#include <linux/moduleloader.h>
+#include <linux/static_call.h>
+
+#include <asm/alternative.h>
+#include <asm/asm-offsets.h>
+#include <asm/cpu.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+#include <asm/kexec.h>
+#include <asm/nospec-branch.h>
+#include <asm/paravirt.h>
+#include <asm/sections.h>
+#include <asm/switch_to.h>
+#include <asm/sync_core.h>
+#include <asm/text-patching.h>
+#include <asm/xen/hypercall.h>
+
+static int __initdata_or_module debug_callthunks;
+
+#define prdbg(fmt, args...) \
+do { \
+ if (debug_callthunks) \
+ printk(KERN_DEBUG pr_fmt(fmt), ##args); \
+} while(0)
+
+static int __init debug_thunks(char *str)
+{
+ debug_callthunks = 1;
+ return 1;
+}
+__setup("debug-callthunks", debug_thunks);
+
+#ifdef CONFIG_CALL_THUNKS_DEBUG
+DEFINE_PER_CPU(u64, __x86_call_count);
+DEFINE_PER_CPU(u64, __x86_ret_count);
+DEFINE_PER_CPU(u64, __x86_stuffs_count);
+DEFINE_PER_CPU(u64, __x86_ctxsw_count);
+EXPORT_SYMBOL_GPL(__x86_ctxsw_count);
+EXPORT_SYMBOL_GPL(__x86_call_count);
+#endif
+
+extern s32 __call_sites[], __call_sites_end[];
+
+struct thunk_desc {
+ void *template;
+ unsigned int template_size;
+};
+
+struct core_text {
+ unsigned long base;
+ unsigned long end;
+ const char *name;
+};
+
+static bool thunks_initialized __ro_after_init;
+
+static const struct core_text builtin_coretext = {
+ .base = (unsigned long)_text,
+ .end = (unsigned long)_etext,
+ .name = "builtin",
+};
+
+asm (
+ ".pushsection .rodata \n"
+ ".global skl_call_thunk_template \n"
+ "skl_call_thunk_template: \n"
+ __stringify(INCREMENT_CALL_DEPTH)" \n"
+ ".global skl_call_thunk_tail \n"
+ "skl_call_thunk_tail: \n"
+ ".popsection \n"
+);
+
+extern u8 skl_call_thunk_template[];
+extern u8 skl_call_thunk_tail[];
+
+#define SKL_TMPL_SIZE \
+ ((unsigned int)(skl_call_thunk_tail - skl_call_thunk_template))
+
+extern void error_entry(void);
+extern void xen_error_entry(void);
+extern void paranoid_entry(void);
+
+static inline bool within_coretext(const struct core_text *ct, void *addr)
+{
+ unsigned long p = (unsigned long)addr;
+
+ return ct->base <= p && p < ct->end;
+}
+
+static inline bool within_module_coretext(void *addr)
+{
+ bool ret = false;
+
+#ifdef CONFIG_MODULES
+ struct module *mod;
+
+ preempt_disable();
+ mod = __module_address((unsigned long)addr);
+ if (mod && within_module_core((unsigned long)addr, mod))
+ ret = true;
+ preempt_enable();
+#endif
+ return ret;
+}
+
+static bool is_coretext(const struct core_text *ct, void *addr)
+{
+ if (ct && within_coretext(ct, addr))
+ return true;
+ if (within_coretext(&builtin_coretext, addr))
+ return true;
+ return within_module_coretext(addr);
+}
+
+static __init_or_module bool skip_addr(void *dest)
+{
+ if (dest == error_entry)
+ return true;
+ if (dest == paranoid_entry)
+ return true;
+ if (dest == xen_error_entry)
+ return true;
+ /* Does FILL_RSB... */
+ if (dest == __switch_to_asm)
+ return true;
+ /* Accounts directly */
+ if (dest == ret_from_fork)
+ return true;
+#ifdef CONFIG_HOTPLUG_CPU
+ if (dest == start_cpu0)
+ return true;
+#endif
+#ifdef CONFIG_FUNCTION_TRACER
+ if (dest == __fentry__)
+ return true;
+#endif
+#ifdef CONFIG_KEXEC_CORE
+ if (dest >= (void *)relocate_kernel &&
+ dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE)
+ return true;
+#endif
+#ifdef CONFIG_XEN
+ if (dest >= (void *)hypercall_page &&
+ dest < (void*)hypercall_page + PAGE_SIZE)
+ return true;
+#endif
+ return false;
+}
+
+static __init_or_module void *call_get_dest(void *addr)
+{
+ struct insn insn;
+ void *dest;
+ int ret;
+
+ ret = insn_decode_kernel(&insn, addr);
+ if (ret)
+ return ERR_PTR(ret);
+
+ /* Patched out call? */
+ if (insn.opcode.bytes[0] != CALL_INSN_OPCODE)
+ return NULL;
+
+ dest = addr + insn.length + insn.immediate.value;
+ if (skip_addr(dest))
+ return NULL;
+ return dest;
+}
+
+static const u8 nops[] = {
+ 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
+ 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
+ 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
+ 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
+};
+
+static __init_or_module void *patch_dest(void *dest, bool direct)
+{
+ unsigned int tsize = SKL_TMPL_SIZE;
+ u8 *pad = dest - tsize;
+
+ /* Already patched? */
+ if (!bcmp(pad, skl_call_thunk_template, tsize))
+ return pad;
+
+ /* Ensure there are nops */
+ if (bcmp(pad, nops, tsize)) {
+ pr_warn_once("Invalid padding area for %pS\n", dest);
+ return NULL;
+ }
+
+ if (direct)
+ memcpy(pad, skl_call_thunk_template, tsize);
+ else
+ text_poke_copy_locked(pad, skl_call_thunk_template, tsize, true);
+ return pad;
+}
+
+static __init_or_module void patch_call(void *addr, const struct core_text *ct)
+{
+ void *pad, *dest;
+ u8 bytes[8];
+
+ if (!within_coretext(ct, addr))
+ return;
+
+ dest = call_get_dest(addr);
+ if (!dest || WARN_ON_ONCE(IS_ERR(dest)))
+ return;
+
+ if (!is_coretext(ct, dest))
+ return;
+
+ pad = patch_dest(dest, within_coretext(ct, dest));
+ if (!pad)
+ return;
+
+ prdbg("Patch call at: %pS %px to %pS %px -> %px \n", addr, addr,
+ dest, dest, pad);
+ __text_gen_insn(bytes, CALL_INSN_OPCODE, addr, pad, CALL_INSN_SIZE);
+ text_poke_early(addr, bytes, CALL_INSN_SIZE);
+}
+
+static __init_or_module void
+patch_call_sites(s32 *start, s32 *end, const struct core_text *ct)
+{
+ s32 *s;
+
+ for (s = start; s < end; s++)
+ patch_call((void *)s + *s, ct);
+}
+
+static __init_or_module void
+patch_paravirt_call_sites(struct paravirt_patch_site *start,
+ struct paravirt_patch_site *end,
+ const struct core_text *ct)
+{
+ struct paravirt_patch_site *p;
+
+ for (p = start; p < end; p++)
+ patch_call(p->instr, ct);
+}
+
+static __init_or_module void
+callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct)
+{
+ prdbg("Patching call sites %s\n", ct->name);
+ patch_call_sites(cs->call_start, cs->call_end, ct);
+ patch_paravirt_call_sites(cs->pv_start, cs->pv_end, ct);
+ prdbg("Patching call sites done%s\n", ct->name);
+}
+
+void __init callthunks_patch_builtin_calls(void)
+{
+ struct callthunk_sites cs = {
+ .call_start = __call_sites,
+ .call_end = __call_sites_end,
+ .pv_start = __parainstructions,
+ .pv_end = __parainstructions_end
+ };
+
+ if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
+ return;
+
+ pr_info("Setting up call depth tracking\n");
+ mutex_lock(&text_mutex);
+ callthunks_setup(&cs, &builtin_coretext);
+ static_call_force_reinit();
+ thunks_initialized = true;
+ mutex_unlock(&text_mutex);
+}
+
+void *callthunks_translate_call_dest(void *dest)
+{
+ void *target;
+
+ lockdep_assert_held(&text_mutex);
+
+ if (!thunks_initialized || skip_addr(dest))
+ return dest;
+
+ if (!is_coretext(NULL, dest))
+ return dest;
+
+ target = patch_dest(dest, false);
+ return target ? : dest;
+}
+
+bool is_callthunk(void *addr)
+{
+ unsigned int tmpl_size = SKL_TMPL_SIZE;
+ void *tmpl = skl_call_thunk_template;
+ unsigned long dest;
+
+ dest = roundup((unsigned long)addr, CONFIG_FUNCTION_ALIGNMENT);
+ if (!thunks_initialized || skip_addr((void *)dest))
+ return false;
+
+ return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size);
+}
+
+#ifdef CONFIG_BPF_JIT
+int x86_call_depth_emit_accounting(u8 **pprog, void *func)
+{
+ unsigned int tmpl_size = SKL_TMPL_SIZE;
+ void *tmpl = skl_call_thunk_template;
+
+ if (!thunks_initialized)
+ return 0;
+
+ /* Is function call target a thunk? */
+ if (func && is_callthunk(func))
+ return 0;
+
+ memcpy(*pprog, tmpl, tmpl_size);
+ *pprog += tmpl_size;
+ return tmpl_size;
+}
+#endif
+
+#ifdef CONFIG_MODULES
+void noinline callthunks_patch_module_calls(struct callthunk_sites *cs,
+ struct module *mod)
+{
+ struct core_text ct = {
+ .base = (unsigned long)mod->core_layout.base,
+ .end = (unsigned long)mod->core_layout.base + mod->core_layout.size,
+ .name = mod->name,
+ };
+
+ if (!thunks_initialized)
+ return;
+
+ mutex_lock(&text_mutex);
+ callthunks_setup(cs, &ct);
+ mutex_unlock(&text_mutex);
+}
+#endif /* CONFIG_MODULES */
+
+#if defined(CONFIG_CALL_THUNKS_DEBUG) && defined(CONFIG_DEBUG_FS)
+static int callthunks_debug_show(struct seq_file *m, void *p)
+{
+ unsigned long cpu = (unsigned long)m->private;
+
+ seq_printf(m, "C: %16llu R: %16llu S: %16llu X: %16llu\n,",
+ per_cpu(__x86_call_count, cpu),
+ per_cpu(__x86_ret_count, cpu),
+ per_cpu(__x86_stuffs_count, cpu),
+ per_cpu(__x86_ctxsw_count, cpu));
+ return 0;
+}
+
+static int callthunks_debug_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, callthunks_debug_show, inode->i_private);
+}
+
+static const struct file_operations dfs_ops = {
+ .open = callthunks_debug_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int __init callthunks_debugfs_init(void)
+{
+ struct dentry *dir;
+ unsigned long cpu;
+
+ dir = debugfs_create_dir("callthunks", NULL);
+ for_each_possible_cpu(cpu) {
+ void *arg = (void *)cpu;
+ char name [10];
+
+ sprintf(name, "cpu%lu", cpu);
+ debugfs_create_file(name, 0644, dir, arg, &dfs_ops);
+ }
+ return 0;
+}
+__initcall(callthunks_debugfs_init);
+#endif
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index f10a921ee756..d7e3ceaf75c1 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -17,9 +17,6 @@ KMSAN_SANITIZE_common.o := n
# As above, instrumenting secondary CPU boot code causes boot hangs.
KCSAN_SANITIZE_common.o := n
-# Make sure load_percpu_segment has no stackprotector
-CFLAGS_common.o := -fno-stack-protector
-
obj-y := cacheinfo.o scattered.o topology.o
obj-y += common.o
obj-y += rdrand.o
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index a8a5033a804d..d970ddb0cc65 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -787,6 +787,7 @@ enum retbleed_mitigation {
RETBLEED_MITIGATION_IBPB,
RETBLEED_MITIGATION_IBRS,
RETBLEED_MITIGATION_EIBRS,
+ RETBLEED_MITIGATION_STUFF,
};
enum retbleed_mitigation_cmd {
@@ -794,6 +795,7 @@ enum retbleed_mitigation_cmd {
RETBLEED_CMD_AUTO,
RETBLEED_CMD_UNRET,
RETBLEED_CMD_IBPB,
+ RETBLEED_CMD_STUFF,
};
static const char * const retbleed_strings[] = {
@@ -802,6 +804,7 @@ static const char * const retbleed_strings[] = {
[RETBLEED_MITIGATION_IBPB] = "Mitigation: IBPB",
[RETBLEED_MITIGATION_IBRS] = "Mitigation: IBRS",
[RETBLEED_MITIGATION_EIBRS] = "Mitigation: Enhanced IBRS",
+ [RETBLEED_MITIGATION_STUFF] = "Mitigation: Stuffing",
};
static enum retbleed_mitigation retbleed_mitigation __ro_after_init =
@@ -831,8 +834,12 @@ static int __init retbleed_parse_cmdline(char *str)
retbleed_cmd = RETBLEED_CMD_UNRET;
} else if (!strcmp(str, "ibpb")) {
retbleed_cmd = RETBLEED_CMD_IBPB;
+ } else if (!strcmp(str, "stuff")) {
+ retbleed_cmd = RETBLEED_CMD_STUFF;
} else if (!strcmp(str, "nosmt")) {
retbleed_nosmt = true;
+ } else if (!strcmp(str, "force")) {
+ setup_force_cpu_bug(X86_BUG_RETBLEED);
} else {
pr_err("Ignoring unknown retbleed option (%s).", str);
}
@@ -879,6 +886,21 @@ static void __init retbleed_select_mitigation(void)
}
break;
+ case RETBLEED_CMD_STUFF:
+ if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING) &&
+ spectre_v2_enabled == SPECTRE_V2_RETPOLINE) {
+ retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
+
+ } else {
+ if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING))
+ pr_err("WARNING: retbleed=stuff depends on spectre_v2=retpoline\n");
+ else
+ pr_err("WARNING: kernel not compiled with CALL_DEPTH_TRACKING.\n");
+
+ goto do_cmd_auto;
+ }
+ break;
+
do_cmd_auto:
case RETBLEED_CMD_AUTO:
default:
@@ -916,6 +938,12 @@ do_cmd_auto:
mitigate_smt = true;
break;
+ case RETBLEED_MITIGATION_STUFF:
+ setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+ setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
+ x86_set_skl_return_thunk();
+ break;
+
default:
break;
}
@@ -926,7 +954,7 @@ do_cmd_auto:
/*
* Let IBRS trump all on Intel without affecting the effects of the
- * retbleed= cmdline option.
+ * retbleed= cmdline option except for call depth based stuffing
*/
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
switch (spectre_v2_enabled) {
@@ -939,7 +967,8 @@ do_cmd_auto:
retbleed_mitigation = RETBLEED_MITIGATION_EIBRS;
break;
default:
- pr_err(RETBLEED_INTEL_MSG);
+ if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF)
+ pr_err(RETBLEED_INTEL_MSG);
}
}
@@ -1413,6 +1442,7 @@ static void __init spectre_v2_select_mitigation(void)
if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) &&
boot_cpu_has_bug(X86_BUG_RETBLEED) &&
retbleed_cmd != RETBLEED_CMD_OFF &&
+ retbleed_cmd != RETBLEED_CMD_STUFF &&
boot_cpu_has(X86_FEATURE_IBRS) &&
boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
mode = SPECTRE_V2_IBRS;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 62b83bc5b4b9..9cfca3d7d0e2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -610,6 +610,7 @@ static __always_inline void setup_cet(struct cpuinfo_x86 *c)
if (!ibt_selftest()) {
pr_err("IBT selftest: Failed!\n");
+ wrmsrl(MSR_IA32_S_CET, 0);
setup_clear_cpu_cap(X86_FEATURE_IBT);
return;
}
@@ -702,16 +703,6 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
__u32 cpu_caps_set[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
-void load_percpu_segment(int cpu)
-{
-#ifdef CONFIG_X86_32
- loadsegment(fs, __KERNEL_PERCPU);
-#else
- __loadsegment_simple(gs, 0);
- wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
-#endif
-}
-
#ifdef CONFIG_X86_32
/* The 32-bit entry code needs to find cpu_entry_area. */
DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
@@ -739,16 +730,45 @@ void load_fixmap_gdt(int cpu)
}
EXPORT_SYMBOL_GPL(load_fixmap_gdt);
-/*
- * Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one.
+/**
+ * switch_gdt_and_percpu_base - Switch to direct GDT and runtime per CPU base
+ * @cpu: The CPU number for which this is invoked
+ *
+ * Invoked during early boot to switch from early GDT and early per CPU to
+ * the direct GDT and the runtime per CPU area. On 32-bit the percpu base
+ * switch is implicit by loading the direct GDT. On 64bit this requires
+ * to update GSBASE.
*/
-void switch_to_new_gdt(int cpu)
+void __init switch_gdt_and_percpu_base(int cpu)
{
- /* Load the original GDT */
load_direct_gdt(cpu);
- /* Reload the per-cpu base */
- load_percpu_segment(cpu);
+
+#ifdef CONFIG_X86_64
+ /*
+ * No need to load %gs. It is already correct.
+ *
+ * Writing %gs on 64bit would zero GSBASE which would make any per
+ * CPU operation up to the point of the wrmsrl() fault.
+ *
+ * Set GSBASE to the new offset. Until the wrmsrl() happens the
+ * early mapping is still valid. That means the GSBASE update will
+ * lose any prior per CPU data which was not copied over in
+ * setup_per_cpu_areas().
+ *
+ * This works even with stackprotector enabled because the
+ * per CPU stack canary is 0 in both per CPU areas.
+ */
+ wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
+#else
+ /*
+ * %fs is already set to __KERNEL_PERCPU, but after switching GDT
+ * it is required to load FS again so that the 'hidden' part is
+ * updated from the new GDT. Up to this point the early per CPU
+ * translation is active. Any content of the early per CPU data
+ * which was not copied over in setup_per_cpu_areas() is lost.
+ */
+ loadsegment(fs, __KERNEL_PERCPU);
+#endif
}
static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
@@ -1993,27 +2013,18 @@ static __init int setup_clearcpuid(char *arg)
}
__setup("clearcpuid=", setup_clearcpuid);
+DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
+ .current_task = &init_task,
+ .preempt_count = INIT_PREEMPT_COUNT,
+ .top_of_stack = TOP_OF_INIT_STACK,
+};
+EXPORT_PER_CPU_SYMBOL(pcpu_hot);
+
#ifdef CONFIG_X86_64
DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
-/*
- * The following percpu variables are hot. Align current_task to
- * cacheline size such that they fall in the same cacheline.
- */
-DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
- &init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
-
-DEFINE_PER_CPU(void *, hardirq_stack_ptr);
-DEFINE_PER_CPU(bool, hardirq_stack_inuse);
-
-DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
-EXPORT_PER_CPU_SYMBOL(__preempt_count);
-
-DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK;
-
static void wrmsrl_cstar(unsigned long val)
{
/*
@@ -2064,20 +2075,6 @@ void syscall_init(void)
#else /* CONFIG_X86_64 */
-DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
-DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
-EXPORT_PER_CPU_SYMBOL(__preempt_count);
-
-/*
- * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
- * the top of the kernel stack. Use an extra percpu variable to track the
- * top of the kernel stack directly.
- */
-DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) =
- (unsigned long)&init_thread_union + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
-
#ifdef CONFIG_STACKPROTECTOR
DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
@@ -2248,12 +2245,6 @@ void cpu_init(void)
boot_cpu_has(X86_FEATURE_TSC) || boot_cpu_has(X86_FEATURE_DE))
cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
- /*
- * Initialize the per-CPU GDT with the boot GDT,
- * and set up the GDT descriptor:
- */
- switch_to_new_gdt(cpu);
-
if (IS_ENABLED(CONFIG_X86_64)) {
loadsegment(fs, 0);
memset(cur->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 722fd712e1cf..b4905d5173fd 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -37,7 +37,7 @@ const char *stack_type_name(enum stack_type type)
static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
{
- unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
+ unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
unsigned long *end = begin + (THREAD_SIZE / sizeof(long));
/*
@@ -62,7 +62,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
{
- unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack_ptr);
+ unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.softirq_stack_ptr);
unsigned long *end = begin + (THREAD_SIZE / sizeof(long));
/*
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6c5defd6569a..f05339fee778 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -134,7 +134,7 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info)
{
- unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
+ unsigned long *end = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
unsigned long *begin;
/*
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index bd165004776d..cf15ef5aecff 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -69,6 +69,10 @@ static const char *ftrace_nop_replace(void)
static const char *ftrace_call_replace(unsigned long ip, unsigned long addr)
{
+ /*
+ * No need to translate into a callthunk. The trampoline does
+ * the depth accounting itself.
+ */
return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
}
@@ -317,7 +321,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
unsigned long size;
unsigned long *ptr;
void *trampoline;
- void *ip;
+ void *ip, *dest;
/* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
@@ -359,7 +363,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
ip = trampoline + size;
if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
- __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, &__x86_return_thunk, JMP32_INSN_SIZE);
+ __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
else
memcpy(ip, retq, sizeof(retq));
@@ -404,17 +408,19 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
/* put in the call to the function */
mutex_lock(&text_mutex);
call_offset -= start_offset;
+ /*
+ * No need to translate into a callthunk. The trampoline does
+ * 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,
- ftrace_ops_get_func(ops)), CALL_INSN_SIZE);
+ text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
+ CALL_INSN_SIZE);
mutex_unlock(&text_mutex);
/* ALLOC_TRAMP flags lets us know we created it */
ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
- set_vm_flush_reset_perms(trampoline);
-
if (likely(system_state != SYSTEM_BOOTING))
set_memory_ro((unsigned long)trampoline, npages);
set_memory_x((unsigned long)trampoline, npages);
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 2a4be92fd144..1265ad519249 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -3,8 +3,9 @@
* Copyright (C) 2014 Steven Rostedt, Red Hat Inc
*/
-#include <linux/linkage.h>
#include <linux/cfi_types.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
#include <asm/ftrace.h>
#include <asm/export.h>
@@ -131,16 +132,19 @@
.endm
SYM_TYPED_FUNC_START(ftrace_stub)
+ CALL_DEPTH_ACCOUNT
RET
SYM_FUNC_END(ftrace_stub)
SYM_TYPED_FUNC_START(ftrace_stub_graph)
+ CALL_DEPTH_ACCOUNT
RET
SYM_FUNC_END(ftrace_stub_graph)
#ifdef CONFIG_DYNAMIC_FTRACE
SYM_FUNC_START(__fentry__)
+ CALL_DEPTH_ACCOUNT
RET
SYM_FUNC_END(__fentry__)
EXPORT_SYMBOL(__fentry__)
@@ -149,6 +153,8 @@ SYM_FUNC_START(ftrace_caller)
/* save_mcount_regs fills in first two parameters */
save_mcount_regs
+ CALL_DEPTH_ACCOUNT
+
/* Stack - skipping return address of ftrace_caller */
leaq MCOUNT_REG_SIZE+8(%rsp), %rcx
movq %rcx, RSP(%rsp)
@@ -164,6 +170,9 @@ SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL)
/* Only ops with REGS flag set should have CS register set */
movq $0, CS(%rsp)
+ /* Account for the function call below */
+ CALL_DEPTH_ACCOUNT
+
SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
call ftrace_stub
@@ -193,6 +202,8 @@ SYM_FUNC_START(ftrace_regs_caller)
save_mcount_regs 8
/* save_mcount_regs fills in first two parameters */
+ CALL_DEPTH_ACCOUNT
+
SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
/* Load the ftrace_ops into the 3rd parameter */
@@ -223,6 +234,9 @@ SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL)
/* regs go into 4th parameter */
leaq (%rsp), %rcx
+ /* Account for the function call below */
+ CALL_DEPTH_ACCOUNT
+
SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
call ftrace_stub
@@ -275,7 +289,20 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
/* Restore flags */
popfq
UNWIND_HINT_FUNC
- RET
+
+ /*
+ * The above left an extra return value on the stack; effectively
+ * doing a tail-call without using a register. This PUSH;RET
+ * pattern unbalances the RSB, inject a pointless CALL to rebalance.
+ */
+ ANNOTATE_INTRA_FUNCTION_CALL
+ CALL .Ldo_rebalance
+ int3
+.Ldo_rebalance:
+ add $8, %rsp
+ ALTERNATIVE __stringify(RET), \
+ __stringify(ANNOTATE_UNRET_SAFE; ret; int3), \
+ X86_FEATURE_CALL_DEPTH
SYM_FUNC_END(ftrace_regs_caller)
STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
@@ -284,6 +311,8 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
#else /* ! CONFIG_DYNAMIC_FTRACE */
SYM_FUNC_START(__fentry__)
+ CALL_DEPTH_ACCOUNT
+
cmpq $ftrace_stub, ftrace_trace_function
jnz trace
RET
@@ -337,6 +366,8 @@ SYM_CODE_START(return_to_handler)
int3
.Ldo_rop:
mov %rdi, (%rsp)
- RET
+ ALTERNATIVE __stringify(RET), \
+ __stringify(ANNOTATE_UNRET_SAFE; ret; int3), \
+ X86_FEATURE_CALL_DEPTH
SYM_CODE_END(return_to_handler)
#endif
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d860d437631b..222efd4a09bc 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -370,6 +370,7 @@ SYM_CODE_END(secondary_startup_64)
* start_secondary() via .Ljump_to_C_code.
*/
SYM_CODE_START(start_cpu0)
+ ANNOTATE_NOENDBR
UNWIND_HINT_EMPTY
movq initial_stack(%rip), %rsp
jmp .Ljump_to_C_code
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 01833ebf5e8e..dc1049c01f9b 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -52,9 +52,6 @@ static inline int check_stack_overflow(void) { return 0; }
static inline void print_stack_overflow(void) { }
#endif
-DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
-DEFINE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
-
static void call_on_stack(void *func, void *stack)
{
asm volatile("xchgl %%ebx,%%esp \n"
@@ -77,7 +74,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
u32 *isp, *prev_esp, arg1;
curstk = (struct irq_stack *) current_stack();
- irqstk = __this_cpu_read(hardirq_stack_ptr);
+ irqstk = __this_cpu_read(pcpu_hot.hardirq_stack_ptr);
/*
* this is where we switch to the IRQ stack. However, if we are
@@ -115,7 +112,7 @@ int irq_init_percpu_irqstack(unsigned int cpu)
int node = cpu_to_node(cpu);
struct page *ph, *ps;
- if (per_cpu(hardirq_stack_ptr, cpu))
+ if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
return 0;
ph = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
@@ -127,8 +124,8 @@ int irq_init_percpu_irqstack(unsigned int cpu)
return -ENOMEM;
}
- per_cpu(hardirq_stack_ptr, cpu) = page_address(ph);
- per_cpu(softirq_stack_ptr, cpu) = page_address(ps);
+ per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = page_address(ph);
+ per_cpu(pcpu_hot.softirq_stack_ptr, cpu) = page_address(ps);
return 0;
}
@@ -138,7 +135,7 @@ void do_softirq_own_stack(void)
struct irq_stack *irqstk;
u32 *isp, *prev_esp;
- irqstk = __this_cpu_read(softirq_stack_ptr);
+ irqstk = __this_cpu_read(pcpu_hot.softirq_stack_ptr);
/* build the stack frame on the softirq stack */
isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 1c0fb96b9e39..fe0c859873d1 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -50,7 +50,7 @@ static int map_irq_stack(unsigned int cpu)
return -ENOMEM;
/* Store actual TOS to avoid adjustment in the hotpath */
- per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+ per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
return 0;
}
#else
@@ -63,14 +63,14 @@ static int map_irq_stack(unsigned int cpu)
void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
/* Store actual TOS to avoid adjustment in the hotpath */
- per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+ per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
return 0;
}
#endif
int irq_init_percpu_irqstack(unsigned int cpu)
{
- if (per_cpu(hardirq_stack_ptr, cpu))
+ if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
return 0;
return map_irq_stack(cpu);
}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index eb8bc82846b9..01b8d956aa76 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -414,7 +414,6 @@ void *alloc_insn_page(void)
if (!page)
return NULL;
- set_vm_flush_reset_perms(page);
/*
* First make the page read-only, and only then make it executable to
* prevent it from being W+X in between.
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d4e48b4a438b..4d053cb2c48a 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -798,19 +798,13 @@ extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
* Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
* restoring to/from the stack.
*/
-asm(
-".pushsection .text;"
-".global __raw_callee_save___kvm_vcpu_is_preempted;"
-".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
-"__raw_callee_save___kvm_vcpu_is_preempted:"
-ASM_ENDBR
-"movq __per_cpu_offset(,%rdi,8), %rax;"
-"cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
-"setne %al;"
-ASM_RET
-".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
-".popsection");
+#define PV_VCPU_PREEMPTED_ASM \
+ "movq __per_cpu_offset(,%rdi,8), %rax\n\t" \
+ "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax)\n\t" \
+ "setne %al\n\t"
+DEFINE_PARAVIRT_ASM(__raw_callee_save___kvm_vcpu_is_preempted,
+ PV_VCPU_PREEMPTED_ASM, .text);
#endif
static void __init kvm_guest_init(void)
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);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 7ca2d46c08cc..327757afb027 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -37,27 +37,10 @@
* nop stub, which must not clobber anything *including the stack* to
* avoid confusing the entry prologues.
*/
-extern void _paravirt_nop(void);
-asm (".pushsection .entry.text, \"ax\"\n"
- ".global _paravirt_nop\n"
- "_paravirt_nop:\n\t"
- ASM_ENDBR
- ASM_RET
- ".size _paravirt_nop, . - _paravirt_nop\n\t"
- ".type _paravirt_nop, @function\n\t"
- ".popsection");
+DEFINE_PARAVIRT_ASM(_paravirt_nop, "", .entry.text);
/* stub always returning 0. */
-asm (".pushsection .entry.text, \"ax\"\n"
- ".global paravirt_ret0\n"
- "paravirt_ret0:\n\t"
- ASM_ENDBR
- "xor %" _ASM_AX ", %" _ASM_AX ";\n\t"
- ASM_RET
- ".size paravirt_ret0, . - paravirt_ret0\n\t"
- ".type paravirt_ret0, @function\n\t"
- ".popsection");
-
+DEFINE_PARAVIRT_ASM(paravirt_ret0, "xor %eax,%eax", .entry.text);
void __init default_banner(void)
{
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 2f314b170c9f..470c128759ea 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -191,13 +191,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
arch_end_context_switch(next_p);
/*
- * Reload esp0 and cpu_current_top_of_stack. This changes
+ * Reload esp0 and pcpu_hot.top_of_stack. This changes
* current_thread_info(). Refresh the SYSENTER configuration in
* case prev or next is vm86.
*/
update_task_stack(next_p);
refresh_sysenter_cs(next);
- this_cpu_write(cpu_current_top_of_stack,
+ this_cpu_write(pcpu_hot.top_of_stack,
(unsigned long)task_stack_page(next_p) +
THREAD_SIZE);
@@ -207,7 +207,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
if (prev->gs | next->gs)
loadsegment(gs, next->gs);
- this_cpu_write(current_task, next_p);
+ raw_cpu_write(pcpu_hot.current_task, next_p);
switch_fpu_finish();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e2f469175be8..4e34b3b68ebd 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -563,7 +563,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
int cpu = smp_processor_id();
WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
- this_cpu_read(hardirq_stack_inuse));
+ this_cpu_read(pcpu_hot.hardirq_stack_inuse));
if (!test_thread_flag(TIF_NEED_FPU_LOAD))
switch_fpu_prepare(prev_fpu, cpu);
@@ -617,8 +617,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
/*
* Switch the PDA and FPU contexts.
*/
- this_cpu_write(current_task, next_p);
- this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
+ raw_cpu_write(pcpu_hot.current_task, next_p);
+ raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p));
switch_fpu_finish();
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 4809c0dc4eb0..4a73351f87f8 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -41,6 +41,7 @@
.text
.align PAGE_SIZE
.code64
+SYM_CODE_START_NOALIGN(relocate_range)
SYM_CODE_START_NOALIGN(relocate_kernel)
UNWIND_HINT_EMPTY
ANNOTATE_NOENDBR
@@ -312,5 +313,5 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
int3
SYM_CODE_END(swap_pages)
- .globl kexec_control_code_size
-.set kexec_control_code_size, . - relocate_kernel
+ .skip KEXEC_CONTROL_CODE_MAX_SIZE - (. - relocate_kernel), 0xcc
+SYM_CODE_END(relocate_range);
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index b26123c90b4f..c242dc47e9cb 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -23,9 +23,6 @@
#include <asm/cpumask.h>
#include <asm/cpu.h>
-DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
-EXPORT_PER_CPU_SYMBOL(cpu_number);
-
#ifdef CONFIG_X86_64
#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
#else
@@ -172,7 +169,7 @@ void __init setup_per_cpu_areas(void)
for_each_possible_cpu(cpu) {
per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
- per_cpu(cpu_number, cpu) = cpu;
+ per_cpu(pcpu_hot.cpu_number, cpu) = cpu;
setup_percpu_segment(cpu);
/*
* Copy data used in early init routines from the
@@ -211,7 +208,7 @@ void __init setup_per_cpu_areas(void)
* area. Reload any changed state for the boot CPU.
*/
if (!cpu)
- switch_to_new_gdt(cpu);
+ switch_gdt_and_percpu_base(cpu);
}
/* indicate the early static arrays will soon be gone */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c295f0e008a3..55cad72715d9 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1048,7 +1048,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
/* Just in case we booted with a single CPU. */
alternatives_enable_smp();
- per_cpu(current_task, cpu) = idle;
+ per_cpu(pcpu_hot.current_task, cpu) = idle;
cpu_init_stack_canary(cpu, idle);
/* Initialize the interrupt stack(s) */
@@ -1058,7 +1058,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
#ifdef CONFIG_X86_32
/* Stack for startup_32 can be just as for start_secondary onwards */
- per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
+ per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
#else
initial_gs = per_cpu_offset(cpu);
#endif
@@ -1453,7 +1453,11 @@ void arch_thaw_secondary_cpus_end(void)
void __init native_smp_prepare_boot_cpu(void)
{
int me = smp_processor_id();
- switch_to_new_gdt(me);
+
+ /* SMP handles this from setup_per_cpu_areas() */
+ if (!IS_ENABLED(CONFIG_SMP))
+ switch_gdt_and_percpu_base(me);
+
/* already set me in cpu_online_mask in boot_cpu_init() */
cpumask_set_cpu(me, cpu_callout_mask);
cpu_set_state_online(me);
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index aaaba85d6d7f..2ebc338980bc 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -34,6 +34,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
switch (type) {
case CALL:
+ func = callthunks_translate_call_dest(func);
code = text_gen_insn(CALL_INSN_OPCODE, insn, func);
if (func == &__static_call_return0) {
emulate = code;
@@ -52,7 +53,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
case RET:
if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
- code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk);
+ code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk);
else
code = &retinsn;
break;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d1e1679f32cf..d317dc3d06a3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -858,7 +858,7 @@ DEFINE_IDTENTRY_RAW(exc_int3)
*/
asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs)
{
- struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1;
+ struct pt_regs *regs = (struct pt_regs *)this_cpu_read(pcpu_hot.top_of_stack) - 1;
if (regs != eregs)
*regs = *eregs;
return regs;
@@ -876,7 +876,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
* trust it and switch to the current kernel stack
*/
if (ip_within_syscall_gap(regs)) {
- sp = this_cpu_read(cpu_current_top_of_stack);
+ sp = this_cpu_read(pcpu_hot.top_of_stack);
goto sync;
}
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index c059820dfaea..cdf6c6060170 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -136,6 +136,21 @@ static struct orc_entry null_orc_entry = {
.type = UNWIND_HINT_TYPE_CALL
};
+#ifdef CONFIG_CALL_THUNKS
+static struct orc_entry *orc_callthunk_find(unsigned long ip)
+{
+ if (!is_callthunk((void *)ip))
+ return NULL;
+
+ return &null_orc_entry;
+}
+#else
+static struct orc_entry *orc_callthunk_find(unsigned long ip)
+{
+ return NULL;
+}
+#endif
+
/* Fake frame pointer entry -- used as a fallback for generated code */
static struct orc_entry orc_fp_entry = {
.type = UNWIND_HINT_TYPE_CALL,
@@ -189,7 +204,11 @@ static struct orc_entry *orc_find(unsigned long ip)
if (orc)
return orc;
- return orc_ftrace_find(ip);
+ orc = orc_ftrace_find(ip);
+ if (orc)
+ return orc;
+
+ return orc_callthunk_find(ip);
}
#ifdef CONFIG_MODULES
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 15f29053cec4..2e0ee14229bf 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -132,18 +132,19 @@ SECTIONS
CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
- ALIGN_ENTRY_TEXT_BEGIN
- ENTRY_TEXT
- ALIGN_ENTRY_TEXT_END
SOFTIRQENTRY_TEXT
- STATIC_CALL_TEXT
- *(.gnu.warning)
-
#ifdef CONFIG_RETPOLINE
__indirect_thunk_start = .;
*(.text.__x86.*)
__indirect_thunk_end = .;
#endif
+ STATIC_CALL_TEXT
+
+ ALIGN_ENTRY_TEXT_BEGIN
+ ENTRY_TEXT
+ ALIGN_ENTRY_TEXT_END
+ *(.gnu.warning)
+
} :text =0xcccc
/* End of text section, which should occupy whole number of pages */
@@ -290,6 +291,13 @@ SECTIONS
*(.return_sites)
__return_sites_end = .;
}
+
+ . = ALIGN(8);
+ .call_sites : AT(ADDR(.call_sites) - LOAD_OFFSET) {
+ __call_sites = .;
+ *(.call_sites)
+ __call_sites_end = .;
+ }
#endif
#ifdef CONFIG_X86_KERNEL_IBT
@@ -301,6 +309,15 @@ SECTIONS
}
#endif
+#ifdef CONFIG_FINEIBT
+ . = ALIGN(8);
+ .cfi_sites : AT(ADDR(.cfi_sites) - LOAD_OFFSET) {
+ __cfi_sites = .;
+ *(.cfi_sites)
+ __cfi_sites_end = .;
+ }
+#endif
+
/*
* struct alt_inst entries. From the header (alternative.h):
* "Alternative instructions for different CPU types or capabilities"
@@ -493,11 +510,3 @@ INIT_PER_CPU(irq_stack_backing_store);
#endif
#endif /* CONFIG_X86_64 */
-
-#ifdef CONFIG_KEXEC_CORE
-#include <asm/kexec.h>
-
-. = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
- "kexec control code size is too big");
-#endif
-