summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig12
-rw-r--r--arch/x86/entry/entry_64.S20
-rw-r--r--arch/x86/include/asm/alternative.h32
-rw-r--r--arch/x86/include/asm/cpufeatures.h3
-rw-r--r--arch/x86/include/asm/microcode.h2
-rw-r--r--arch/x86/include/asm/msr-index.h8
-rw-r--r--arch/x86/include/asm/nospec-branch.h10
-rw-r--r--arch/x86/kernel/alternative.c336
-rw-r--r--arch/x86/kernel/cpu/bugs.c176
-rw-r--r--arch/x86/kernel/cpu/common.c72
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c6
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c58
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c2
-rw-r--r--arch/x86/kernel/cpu/microcode/internal.h1
-rw-r--r--arch/x86/kernel/ftrace.c2
-rw-r--r--arch/x86/kernel/head32.c4
-rw-r--r--arch/x86/kernel/module.c6
-rw-r--r--arch/x86/kernel/static_call.c4
-rw-r--r--arch/x86/kernel/vmlinux.lds.S20
-rw-r--r--arch/x86/kvm/mmu.h3
-rw-r--r--arch/x86/kvm/mmu/mmu.c70
-rw-r--r--arch/x86/kvm/smm.c1
-rw-r--r--arch/x86/kvm/svm/sev.c32
-rw-r--r--arch/x86/kvm/svm/svm.c75
-rw-r--r--arch/x86/kvm/svm/svm.h2
-rw-r--r--arch/x86/kvm/x86.c8
-rw-r--r--arch/x86/lib/retpoline.S48
-rw-r--r--arch/x86/mm/init_32.c3
-rw-r--r--arch/x86/mm/init_64.c3
-rw-r--r--arch/x86/mm/tlb.c22
-rw-r--r--arch/x86/net/bpf_jit_comp.c58
-rw-r--r--arch/x86/um/shared/sysdep/faultinfo_32.h2
-rw-r--r--arch/x86/um/shared/sysdep/faultinfo_64.h2
33 files changed, 977 insertions, 126 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5873c9e39919..e21cca404943 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2711,6 +2711,18 @@ config MITIGATION_SSB
of speculative execution in a similar way to the Meltdown and Spectre
security vulnerabilities.
+config MITIGATION_ITS
+ bool "Enable Indirect Target Selection mitigation"
+ depends on CPU_SUP_INTEL && X86_64
+ depends on MITIGATION_RETPOLINE && MITIGATION_RETHUNK
+ select EXECMEM
+ default y
+ help
+ Enable Indirect Target Selection (ITS) mitigation. ITS is a bug in
+ BPU on some Intel CPUs that may allow Spectre V2 style attacks. If
+ disabled, mitigation cannot be enabled via cmdline.
+ See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
+
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f40bdf97d390..ed04a968cc7d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1525,7 +1525,9 @@ SYM_CODE_END(rewind_stack_and_make_dead)
* ORC to unwind properly.
*
* The alignment is for performance and not for safety, and may be safely
- * refactored in the future if needed.
+ * refactored in the future if needed. The .skips are for safety, to ensure
+ * that all RETs are in the second half of a cacheline to mitigate Indirect
+ * Target Selection, rather than taking the slowpath via its_return_thunk.
*/
SYM_FUNC_START(clear_bhb_loop)
ANNOTATE_NOENDBR
@@ -1536,10 +1538,22 @@ SYM_FUNC_START(clear_bhb_loop)
call 1f
jmp 5f
.align 64, 0xcc
+ /*
+ * Shift instructions so that the RET is in the upper half of the
+ * cacheline and don't take the slowpath to its_return_thunk.
+ */
+ .skip 32 - (.Lret1 - 1f), 0xcc
ANNOTATE_INTRA_FUNCTION_CALL
1: call 2f
- RET
+.Lret1: RET
.align 64, 0xcc
+ /*
+ * As above shift instructions for RET at .Lret2 as well.
+ *
+ * This should be ideally be: .skip 32 - (.Lret2 - 2f), 0xcc
+ * but some Clang versions (e.g. 18) don't like this.
+ */
+ .skip 32 - 18, 0xcc
2: movl $5, %eax
3: jmp 4f
nop
@@ -1547,7 +1561,7 @@ SYM_FUNC_START(clear_bhb_loop)
jnz 3b
sub $1, %ecx
jnz 1b
- RET
+.Lret2: RET
5: lfence
pop %rbp
RET
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4a37a8bd87fd..f2294784babc 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -6,6 +6,7 @@
#include <linux/stringify.h>
#include <linux/objtool.h>
#include <asm/asm.h>
+#include <asm/bug.h>
#define ALT_FLAGS_SHIFT 16
@@ -124,6 +125,37 @@ static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
}
#endif
+#ifdef CONFIG_MITIGATION_ITS
+extern void its_init_mod(struct module *mod);
+extern void its_fini_mod(struct module *mod);
+extern void its_free_mod(struct module *mod);
+extern u8 *its_static_thunk(int reg);
+#else /* CONFIG_MITIGATION_ITS */
+static inline void its_init_mod(struct module *mod) { }
+static inline void its_fini_mod(struct module *mod) { }
+static inline void its_free_mod(struct module *mod) { }
+static inline u8 *its_static_thunk(int reg)
+{
+ WARN_ONCE(1, "ITS not compiled in");
+
+ return NULL;
+}
+#endif
+
+#if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL)
+extern bool cpu_wants_rethunk(void);
+extern bool cpu_wants_rethunk_at(void *addr);
+#else
+static __always_inline bool cpu_wants_rethunk(void)
+{
+ return false;
+}
+static __always_inline bool cpu_wants_rethunk_at(void *addr)
+{
+ return false;
+}
+#endif
+
#ifdef CONFIG_SMP
extern void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6c2c152d8a67..39e61212ac9a 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -481,6 +481,7 @@
#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */
#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */
#define X86_FEATURE_PREFER_YMM (21*32 + 8) /* Avoid ZMM registers due to downclocking */
+#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32 + 9) /* Use thunk for indirect branches in lower half of cacheline */
/*
* BUG word(s)
@@ -533,4 +534,6 @@
#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
#define X86_BUG_SPECTRE_V2_USER X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
+#define X86_BUG_ITS X86_BUG(1*32 + 6) /* "its" CPU is affected by Indirect Target Selection */
+#define X86_BUG_ITS_NATIVE_ONLY X86_BUG(1*32 + 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 695e569159c1..be7cddc414e4 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -17,10 +17,12 @@ struct ucode_cpu_info {
void load_ucode_bsp(void);
void load_ucode_ap(void);
void microcode_bsp_resume(void);
+bool __init microcode_loader_disabled(void);
#else
static inline void load_ucode_bsp(void) { }
static inline void load_ucode_ap(void) { }
static inline void microcode_bsp_resume(void) { }
+static inline bool __init microcode_loader_disabled(void) { return false; }
#endif
extern unsigned long initrd_start_early;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e6134ef2263d..e7d2f460fcc6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -211,6 +211,14 @@
* VERW clears CPU Register
* File.
*/
+#define ARCH_CAP_ITS_NO BIT_ULL(62) /*
+ * Not susceptible to
+ * Indirect Target Selection.
+ * This bit is not set by
+ * HW, but is synthesized by
+ * VMMs for guests to know
+ * their affected status.
+ */
#define MSR_IA32_FLUSH_CMD 0x0000010b
#define L1D_FLUSH BIT(0) /*
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 5c43f145454d..7d04ade33541 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -336,10 +336,14 @@
#else /* __ASSEMBLER__ */
+#define ITS_THUNK_SIZE 64
+
typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
+typedef u8 its_thunk_t[ITS_THUNK_SIZE];
extern retpoline_thunk_t __x86_indirect_thunk_array[];
extern retpoline_thunk_t __x86_indirect_call_thunk_array[];
extern retpoline_thunk_t __x86_indirect_jump_thunk_array[];
+extern its_thunk_t __x86_indirect_its_thunk_array[];
#ifdef CONFIG_MITIGATION_RETHUNK
extern void __x86_return_thunk(void);
@@ -363,6 +367,12 @@ static inline void srso_return_thunk(void) {}
static inline void srso_alias_return_thunk(void) {}
#endif
+#ifdef CONFIG_MITIGATION_ITS
+extern void its_return_thunk(void);
+#else
+static inline void its_return_thunk(void) {}
+#endif
+
extern void retbleed_return_thunk(void);
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index bf82c6f7d690..48fd04e90114 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -18,6 +18,7 @@
#include <linux/mmu_context.h>
#include <linux/bsearch.h>
#include <linux/sync_core.h>
+#include <linux/execmem.h>
#include <asm/text-patching.h>
#include <asm/alternative.h>
#include <asm/sections.h>
@@ -31,6 +32,8 @@
#include <asm/paravirt.h>
#include <asm/asm-prototypes.h>
#include <asm/cfi.h>
+#include <asm/ibt.h>
+#include <asm/set_memory.h>
int __read_mostly alternatives_patched;
@@ -124,6 +127,165 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
#endif
};
+#ifdef CONFIG_FINEIBT
+static bool cfi_paranoid __ro_after_init;
+#endif
+
+#ifdef CONFIG_MITIGATION_ITS
+
+static struct module *its_mod;
+static void *its_page;
+static unsigned int its_offset;
+
+/* Initialize a thunk with the "jmp *reg; int3" instructions. */
+static void *its_init_thunk(void *thunk, int reg)
+{
+ u8 *bytes = thunk;
+ int offset = 0;
+ int i = 0;
+
+#ifdef CONFIG_FINEIBT
+ if (cfi_paranoid) {
+ /*
+ * When ITS uses indirect branch thunk the fineibt_paranoid
+ * caller sequence doesn't fit in the caller site. So put the
+ * remaining part of the sequence (<ea> + JNE) into the ITS
+ * thunk.
+ */
+ bytes[i++] = 0xea; /* invalid instruction */
+ bytes[i++] = 0x75; /* JNE */
+ bytes[i++] = 0xfd;
+
+ offset = 1;
+ }
+#endif
+
+ if (reg >= 8) {
+ bytes[i++] = 0x41; /* REX.B prefix */
+ reg -= 8;
+ }
+ bytes[i++] = 0xff;
+ bytes[i++] = 0xe0 + reg; /* jmp *reg */
+ bytes[i++] = 0xcc;
+
+ return thunk + offset;
+}
+
+void its_init_mod(struct module *mod)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+ return;
+
+ mutex_lock(&text_mutex);
+ its_mod = mod;
+ its_page = NULL;
+}
+
+void its_fini_mod(struct module *mod)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+ return;
+
+ WARN_ON_ONCE(its_mod != mod);
+
+ its_mod = NULL;
+ its_page = NULL;
+ mutex_unlock(&text_mutex);
+
+ for (int i = 0; i < mod->its_num_pages; i++) {
+ void *page = mod->its_page_array[i];
+ execmem_restore_rox(page, PAGE_SIZE);
+ }
+}
+
+void its_free_mod(struct module *mod)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+ return;
+
+ for (int i = 0; i < mod->its_num_pages; i++) {
+ void *page = mod->its_page_array[i];
+ execmem_free(page);
+ }
+ kfree(mod->its_page_array);
+}
+
+static void *its_alloc(void)
+{
+ void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+
+ if (!page)
+ return NULL;
+
+ if (its_mod) {
+ void *tmp = krealloc(its_mod->its_page_array,
+ (its_mod->its_num_pages+1) * sizeof(void *),
+ GFP_KERNEL);
+ if (!tmp)
+ return NULL;
+
+ its_mod->its_page_array = tmp;
+ its_mod->its_page_array[its_mod->its_num_pages++] = page;
+
+ execmem_make_temp_rw(page, PAGE_SIZE);
+ }
+
+ return no_free_ptr(page);
+}
+
+static void *its_allocate_thunk(int reg)
+{
+ int size = 3 + (reg / 8);
+ void *thunk;
+
+#ifdef CONFIG_FINEIBT
+ /*
+ * The ITS thunk contains an indirect jump and an int3 instruction so
+ * its size is 3 or 4 bytes depending on the register used. If CFI
+ * paranoid is used then 3 extra bytes are added in the ITS thunk to
+ * complete the fineibt_paranoid caller sequence.
+ */
+ if (cfi_paranoid)
+ size += 3;
+#endif
+
+ if (!its_page || (its_offset + size - 1) >= PAGE_SIZE) {
+ its_page = its_alloc();
+ if (!its_page) {
+ pr_err("ITS page allocation failed\n");
+ return NULL;
+ }
+ memset(its_page, INT3_INSN_OPCODE, PAGE_SIZE);
+ its_offset = 32;
+ }
+
+ /*
+ * If the indirect branch instruction will be in the lower half
+ * of a cacheline, then update the offset to reach the upper half.
+ */
+ if ((its_offset + size - 1) % 64 < 32)
+ its_offset = ((its_offset - 1) | 0x3F) + 33;
+
+ thunk = its_page + its_offset;
+ its_offset += size;
+
+ return its_init_thunk(thunk, reg);
+}
+
+u8 *its_static_thunk(int reg)
+{
+ u8 *thunk = __x86_indirect_its_thunk_array[reg];
+
+#ifdef CONFIG_FINEIBT
+ /* Paranoid thunk starts 2 bytes before */
+ if (cfi_paranoid)
+ return thunk - 2;
+#endif
+ return thunk;
+}
+
+#endif
+
/*
* Nomenclature for variable names to simplify and clarify this code and ease
* any potential staring at it:
@@ -581,7 +743,8 @@ static int emit_indirect(int op, int reg, u8 *bytes)
return i;
}
-static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+static int __emit_trampoline(void *addr, struct insn *insn, u8 *bytes,
+ void *call_dest, void *jmp_dest)
{
u8 op = insn->opcode.bytes[0];
int i = 0;
@@ -602,7 +765,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8
switch (op) {
case CALL_INSN_OPCODE:
__text_gen_insn(bytes+i, op, addr+i,
- __x86_indirect_call_thunk_array[reg],
+ call_dest,
CALL_INSN_SIZE);
i += CALL_INSN_SIZE;
break;
@@ -610,7 +773,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8
case JMP32_INSN_OPCODE:
clang_jcc:
__text_gen_insn(bytes+i, op, addr+i,
- __x86_indirect_jump_thunk_array[reg],
+ jmp_dest,
JMP32_INSN_SIZE);
i += JMP32_INSN_SIZE;
break;
@@ -625,6 +788,48 @@ clang_jcc:
return i;
}
+static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+ return __emit_trampoline(addr, insn, bytes,
+ __x86_indirect_call_thunk_array[reg],
+ __x86_indirect_jump_thunk_array[reg]);
+}
+
+#ifdef CONFIG_MITIGATION_ITS
+static int emit_its_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+ u8 *thunk = __x86_indirect_its_thunk_array[reg];
+ u8 *tmp = its_allocate_thunk(reg);
+
+ if (tmp)
+ thunk = tmp;
+
+ return __emit_trampoline(addr, insn, bytes, thunk, thunk);
+}
+
+/* Check if an indirect branch is at ITS-unsafe address */
+static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+ return false;
+
+ /* Indirect branch opcode is 2 or 3 bytes depending on reg */
+ addr += 1 + reg / 8;
+
+ /* Lower-half of the cacheline? */
+ return !(addr & 0x20);
+}
+#else /* CONFIG_MITIGATION_ITS */
+
+#ifdef CONFIG_FINEIBT
+static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg)
+{
+ return false;
+}
+#endif
+
+#endif /* CONFIG_MITIGATION_ITS */
+
/*
* Rewrite the compiler generated retpoline thunk calls.
*
@@ -699,6 +904,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
bytes[i++] = 0xe8; /* LFENCE */
}
+#ifdef CONFIG_MITIGATION_ITS
+ /*
+ * Check if the address of last byte of emitted-indirect is in
+ * lower-half of the cacheline. Such branches need ITS mitigation.
+ */
+ if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + i, reg))
+ return emit_its_trampoline(addr, insn, reg, bytes);
+#endif
+
ret = emit_indirect(op, reg, bytes + i);
if (ret < 0)
return ret;
@@ -732,6 +946,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
int len, ret;
u8 bytes[16];
u8 op1, op2;
+ u8 *dest;
ret = insn_decode_kernel(&insn, addr);
if (WARN_ON_ONCE(ret < 0))
@@ -748,6 +963,12 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
case CALL_INSN_OPCODE:
case JMP32_INSN_OPCODE:
+ /* Check for cfi_paranoid + ITS */
+ dest = addr + insn.length + insn.immediate.value;
+ if (dest[-1] == 0xea && (dest[0] & 0xf0) == 0x70) {
+ WARN_ON_ONCE(cfi_mode != CFI_FINEIBT);
+ continue;
+ }
break;
case 0x0f: /* escape */
@@ -775,6 +996,21 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
#ifdef CONFIG_MITIGATION_RETHUNK
+bool cpu_wants_rethunk(void)
+{
+ return cpu_feature_enabled(X86_FEATURE_RETHUNK);
+}
+
+bool cpu_wants_rethunk_at(void *addr)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ return false;
+ if (x86_return_thunk != its_return_thunk)
+ return true;
+
+ return !((unsigned long)addr & 0x20);
+}
+
/*
* Rewrite the compiler generated return thunk tail-calls.
*
@@ -791,7 +1027,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
int i = 0;
/* Patch the custom return thunks... */
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+ if (cpu_wants_rethunk_at(addr)) {
i = JMP32_INSN_SIZE;
__text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i);
} else {
@@ -808,7 +1044,7 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
{
s32 *s;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ if (cpu_wants_rethunk())
static_call_force_reinit();
for (s = start; s < end; s++) {
@@ -1022,8 +1258,6 @@ int cfi_get_func_arity(void *func)
static bool cfi_rand __ro_after_init = true;
static u32 cfi_seed __ro_after_init;
-static bool cfi_paranoid __ro_after_init = false;
-
/*
* Re-hash the CFI hash with a boot-time seed while making sure the result is
* not a valid ENDBR instruction.
@@ -1436,6 +1670,19 @@ static int cfi_rand_callers(s32 *start, s32 *end)
return 0;
}
+static int emit_paranoid_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+ u8 *thunk = (void *)__x86_indirect_its_thunk_array[reg] - 2;
+
+#ifdef CONFIG_MITIGATION_ITS
+ u8 *tmp = its_allocate_thunk(reg);
+ if (tmp)
+ thunk = tmp;
+#endif
+
+ return __emit_trampoline(addr, insn, bytes, thunk, thunk);
+}
+
static int cfi_rewrite_callers(s32 *start, s32 *end)
{
s32 *s;
@@ -1477,9 +1724,14 @@ static int cfi_rewrite_callers(s32 *start, s32 *end)
memcpy(bytes, fineibt_paranoid_start, fineibt_paranoid_size);
memcpy(bytes + fineibt_caller_hash, &hash, 4);
- ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
- if (WARN_ON_ONCE(ret != 3))
- continue;
+ if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + fineibt_paranoid_ind, 11)) {
+ emit_paranoid_trampoline(addr + fineibt_caller_size,
+ &insn, 11, bytes + fineibt_caller_size);
+ } else {
+ ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
+ if (WARN_ON_ONCE(ret != 3))
+ continue;
+ }
text_poke_early(addr, bytes, fineibt_paranoid_size);
}
@@ -1706,29 +1958,66 @@ Efault:
return false;
}
+static bool is_paranoid_thunk(unsigned long addr)
+{
+ u32 thunk;
+
+ __get_kernel_nofault(&thunk, (u32 *)addr, u32, Efault);
+ return (thunk & 0x00FFFFFF) == 0xfd75ea;
+
+Efault:
+ return false;
+}
+
/*
* regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[]
- * sequence.
+ * sequence, or to an invalid instruction (0xea) + Jcc.d8 for cfi_paranoid + ITS
+ * thunk.
*/
static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type)
{
unsigned long addr = regs->ip - fineibt_paranoid_ud;
- u32 hash;
- if (!cfi_paranoid || !is_cfi_trap(addr + fineibt_caller_size - LEN_UD2))
+ if (!cfi_paranoid)
return false;
- __get_kernel_nofault(&hash, addr + fineibt_caller_hash, u32, Efault);
- *target = regs->r11 + fineibt_preamble_size;
- *type = regs->r10;
+ if (is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) {
+ *target = regs->r11 + fineibt_preamble_size;
+ *type = regs->r10;
+
+ /*
+ * Since the trapping instruction is the exact, but LOCK prefixed,
+ * Jcc.d8 that got us here, the normal fixup will work.
+ */
+ return true;
+ }
/*
- * Since the trapping instruction is the exact, but LOCK prefixed,
- * Jcc.d8 that got us here, the normal fixup will work.
+ * The cfi_paranoid + ITS thunk combination results in:
+ *
+ * 0: 41 ba 78 56 34 12 mov $0x12345678, %r10d
+ * 6: 45 3b 53 f7 cmp -0x9(%r11), %r10d
+ * a: 4d 8d 5b f0 lea -0x10(%r11), %r11
+ * e: 2e e8 XX XX XX XX cs call __x86_indirect_paranoid_thunk_r11
+ *
+ * Where the paranoid_thunk looks like:
+ *
+ * 1d: <ea> (bad)
+ * __x86_indirect_paranoid_thunk_r11:
+ * 1e: 75 fd jne 1d
+ * __x86_indirect_its_thunk_r11:
+ * 20: 41 ff eb jmp *%r11
+ * 23: cc int3
+ *
*/
- return true;
+ if (is_paranoid_thunk(regs->ip)) {
+ *target = regs->r11 + fineibt_preamble_size;
+ *type = regs->r10;
+
+ regs->ip = *target;
+ return true;
+ }
-Efault:
return false;
}
@@ -2031,6 +2320,8 @@ static noinline void __init alt_reloc_selftest(void)
void __init alternative_instructions(void)
{
+ u64 ibt;
+
int3_selftest();
/*
@@ -2057,6 +2348,9 @@ void __init alternative_instructions(void)
*/
paravirt_set_cap();
+ /* Keep CET-IBT disabled until caller/callee are patched */
+ ibt = ibt_save(/*disable*/ true);
+
__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
__cfi_sites, __cfi_sites_end, true);
@@ -2080,6 +2374,8 @@ void __init alternative_instructions(void)
*/
apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
+ ibt_restore(ibt);
+
#ifdef CONFIG_SMP
/* Patch to UP if other cpus not imminent. */
if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) {
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 362602b705cc..8596ce85026c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -49,6 +49,7 @@ static void __init srbds_select_mitigation(void);
static void __init l1d_flush_select_mitigation(void);
static void __init srso_select_mitigation(void);
static void __init gds_select_mitigation(void);
+static void __init its_select_mitigation(void);
/* The base value of the SPEC_CTRL MSR without task-specific bits set */
u64 x86_spec_ctrl_base;
@@ -66,6 +67,14 @@ static DEFINE_MUTEX(spec_ctrl_mutex);
void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
+static void __init set_return_thunk(void *thunk)
+{
+ if (x86_return_thunk != __x86_return_thunk)
+ pr_warn("x86/bugs: return thunk changed\n");
+
+ x86_return_thunk = thunk;
+}
+
/* Update SPEC_CTRL MSR and its cached copy unconditionally */
static void update_spec_ctrl(u64 val)
{
@@ -178,6 +187,7 @@ void __init cpu_select_mitigations(void)
*/
srso_select_mitigation();
gds_select_mitigation();
+ its_select_mitigation();
}
/*
@@ -1118,7 +1128,7 @@ do_cmd_auto:
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_UNRET);
- x86_return_thunk = retbleed_return_thunk;
+ set_return_thunk(retbleed_return_thunk);
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -1153,7 +1163,7 @@ do_cmd_auto:
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
- x86_return_thunk = call_depth_return_thunk;
+ set_return_thunk(call_depth_return_thunk);
break;
default:
@@ -1188,6 +1198,145 @@ do_cmd_auto:
}
#undef pr_fmt
+#define pr_fmt(fmt) "ITS: " fmt
+
+enum its_mitigation_cmd {
+ ITS_CMD_OFF,
+ ITS_CMD_ON,
+ ITS_CMD_VMEXIT,
+ ITS_CMD_RSB_STUFF,
+};
+
+enum its_mitigation {
+ ITS_MITIGATION_OFF,
+ ITS_MITIGATION_VMEXIT_ONLY,
+ ITS_MITIGATION_ALIGNED_THUNKS,
+ ITS_MITIGATION_RETPOLINE_STUFF,
+};
+
+static const char * const its_strings[] = {
+ [ITS_MITIGATION_OFF] = "Vulnerable",
+ [ITS_MITIGATION_VMEXIT_ONLY] = "Mitigation: Vulnerable, KVM: Not affected",
+ [ITS_MITIGATION_ALIGNED_THUNKS] = "Mitigation: Aligned branch/return thunks",
+ [ITS_MITIGATION_RETPOLINE_STUFF] = "Mitigation: Retpolines, Stuffing RSB",
+};
+
+static enum its_mitigation its_mitigation __ro_after_init = ITS_MITIGATION_ALIGNED_THUNKS;
+
+static enum its_mitigation_cmd its_cmd __ro_after_init =
+ IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_CMD_ON : ITS_CMD_OFF;
+
+static int __init its_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!IS_ENABLED(CONFIG_MITIGATION_ITS)) {
+ pr_err("Mitigation disabled at compile time, ignoring option (%s)", str);
+ return 0;
+ }
+
+ if (!strcmp(str, "off")) {
+ its_cmd = ITS_CMD_OFF;
+ } else if (!strcmp(str, "on")) {
+ its_cmd = ITS_CMD_ON;
+ } else if (!strcmp(str, "force")) {
+ its_cmd = ITS_CMD_ON;
+ setup_force_cpu_bug(X86_BUG_ITS);
+ } else if (!strcmp(str, "vmexit")) {
+ its_cmd = ITS_CMD_VMEXIT;
+ } else if (!strcmp(str, "stuff")) {
+ its_cmd = ITS_CMD_RSB_STUFF;
+ } else {
+ pr_err("Ignoring unknown indirect_target_selection option (%s).", str);
+ }
+
+ return 0;
+}
+early_param("indirect_target_selection", its_parse_cmdline);
+
+static void __init its_select_mitigation(void)
+{
+ enum its_mitigation_cmd cmd = its_cmd;
+
+ if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) {
+ its_mitigation = ITS_MITIGATION_OFF;
+ return;
+ }
+
+ /* Retpoline+CDT mitigates ITS, bail out */
+ if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+ boot_cpu_has(X86_FEATURE_CALL_DEPTH)) {
+ its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+ goto out;
+ }
+
+ /* Exit early to avoid irrelevant warnings */
+ if (cmd == ITS_CMD_OFF) {
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+ if (spectre_v2_enabled == SPECTRE_V2_NONE) {
+ pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n");
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+ if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) ||
+ !IS_ENABLED(CONFIG_MITIGATION_RETHUNK)) {
+ pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n");
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+ if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) {
+ pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n");
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+ if (boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) {
+ pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n");
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+
+ if (cmd == ITS_CMD_RSB_STUFF &&
+ (!boot_cpu_has(X86_FEATURE_RETPOLINE) || !IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))) {
+ pr_err("RSB stuff mitigation not supported, using default\n");
+ cmd = ITS_CMD_ON;
+ }
+
+ switch (cmd) {
+ case ITS_CMD_OFF:
+ its_mitigation = ITS_MITIGATION_OFF;
+ break;
+ case ITS_CMD_VMEXIT:
+ if (boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY)) {
+ its_mitigation = ITS_MITIGATION_VMEXIT_ONLY;
+ goto out;
+ }
+ fallthrough;
+ case ITS_CMD_ON:
+ its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+ if (!boot_cpu_has(X86_FEATURE_RETPOLINE))
+ setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS);
+ setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+ set_return_thunk(its_return_thunk);
+ break;
+ case ITS_CMD_RSB_STUFF:
+ its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+ setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+ setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
+ set_return_thunk(call_depth_return_thunk);
+ if (retbleed_mitigation == RETBLEED_MITIGATION_NONE) {
+ retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
+ pr_info("Retbleed mitigation updated to stuffing\n");
+ }
+ break;
+ }
+out:
+ pr_info("%s\n", its_strings[its_mitigation]);
+}
+
+#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
@@ -1697,11 +1846,11 @@ static void __init bhi_select_mitigation(void)
return;
}
- /* Mitigate in hardware if supported */
- if (spec_ctrl_bhi_dis())
+ if (!IS_ENABLED(CONFIG_X86_64))
return;
- if (!IS_ENABLED(CONFIG_X86_64))
+ /* Mitigate in hardware if supported */
+ if (spec_ctrl_bhi_dis())
return;
if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) {
@@ -2607,10 +2756,10 @@ static void __init srso_select_mitigation(void)
if (boot_cpu_data.x86 == 0x19) {
setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS);
- x86_return_thunk = srso_alias_return_thunk;
+ set_return_thunk(srso_alias_return_thunk);
} else {
setup_force_cpu_cap(X86_FEATURE_SRSO);
- x86_return_thunk = srso_return_thunk;
+ set_return_thunk(srso_return_thunk);
}
if (has_microcode)
srso_mitigation = SRSO_MITIGATION_SAFE_RET;
@@ -2800,6 +2949,11 @@ static ssize_t rfds_show_state(char *buf)
return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]);
}
+static ssize_t its_show_state(char *buf)
+{
+ return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]);
+}
+
static char *stibp_state(void)
{
if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
@@ -2982,6 +3136,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_RFDS:
return rfds_show_state(buf);
+ case X86_BUG_ITS:
+ return its_show_state(buf);
+
default:
break;
}
@@ -3061,6 +3218,11 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib
{
return cpu_show_common(dev, attr, buf, X86_BUG_RFDS);
}
+
+ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
+}
#endif
void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 12126adbc3a9..0ff057ff11ce 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1227,6 +1227,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define GDS BIT(6)
/* CPU is affected by Register File Data Sampling */
#define RFDS BIT(7)
+/* CPU is affected by Indirect Target Selection */
+#define ITS BIT(8)
+/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
+#define ITS_NATIVE_ONLY BIT(9)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS),
@@ -1238,22 +1242,25 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS),
VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO),
VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS),
- VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS),
VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS),
VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED),
- VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS),
- VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS),
- VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED),
- VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS),
- VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS),
+ VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
+ VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY),
+ VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+ VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY),
+ VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY),
VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED),
- VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS),
VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS),
VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS),
@@ -1318,6 +1325,32 @@ static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr)
return cpu_matches(cpu_vuln_blacklist, RFDS);
}
+static bool __init vulnerable_to_its(u64 x86_arch_cap_msr)
+{
+ /* The "immunity" bit trumps everything else: */
+ if (x86_arch_cap_msr & ARCH_CAP_ITS_NO)
+ return false;
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return false;
+
+ /* None of the affected CPUs have BHI_CTRL */
+ if (boot_cpu_has(X86_FEATURE_BHI_CTRL))
+ return false;
+
+ /*
+ * If a VMM did not expose ITS_NO, assume that a guest could
+ * be running on a vulnerable hardware or may migrate to such
+ * hardware.
+ */
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return true;
+
+ if (cpu_matches(cpu_vuln_blacklist, ITS))
+ return true;
+
+ return false;
+}
+
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 x86_arch_cap_msr = x86_read_arch_cap_msr();
@@ -1439,9 +1472,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
if (vulnerable_to_rfds(x86_arch_cap_msr))
setup_force_cpu_bug(X86_BUG_RFDS);
- /* When virtualized, eIBRS could be hidden, assume vulnerable */
- if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) &&
- !cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
+ /*
+ * Intel parts with eIBRS are vulnerable to BHI attacks. Parts with
+ * BHI_NO still need to use the BHI mitigation to prevent Intra-mode
+ * attacks. When virtualized, eIBRS could be hidden, assume vulnerable.
+ */
+ if (!cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
(boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
boot_cpu_has(X86_FEATURE_HYPERVISOR)))
setup_force_cpu_bug(X86_BUG_BHI);
@@ -1449,6 +1485,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET))
setup_force_cpu_bug(X86_BUG_IBPB_NO_RET);
+ if (vulnerable_to_its(x86_arch_cap_msr)) {
+ setup_force_cpu_bug(X86_BUG_ITS);
+ if (cpu_matches(cpu_vuln_blacklist, ITS_NATIVE_ONLY))
+ setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
+ }
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 4a10d35e70aa..96cb992d50ef 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -1098,15 +1098,17 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
static int __init save_microcode_in_initrd(void)
{
- unsigned int cpuid_1_eax = native_cpuid_eax(1);
struct cpuinfo_x86 *c = &boot_cpu_data;
struct cont_desc desc = { 0 };
+ unsigned int cpuid_1_eax;
enum ucode_state ret;
struct cpio_data cp;
- if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+ if (microcode_loader_disabled() || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
return 0;
+ cpuid_1_eax = native_cpuid_eax(1);
+
if (!find_blobs_in_containers(&cp))
return -EINVAL;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index b3658d11e7b6..079f046ee26d 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -41,8 +41,8 @@
#include "internal.h"
-static struct microcode_ops *microcode_ops;
-bool dis_ucode_ldr = true;
+static struct microcode_ops *microcode_ops;
+static bool dis_ucode_ldr = false;
bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
@@ -84,6 +84,9 @@ static bool amd_check_current_patch_level(void)
u32 lvl, dummy, i;
u32 *levels;
+ if (x86_cpuid_vendor() != X86_VENDOR_AMD)
+ return false;
+
native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
levels = final_levels;
@@ -95,27 +98,29 @@ static bool amd_check_current_patch_level(void)
return false;
}
-static bool __init check_loader_disabled_bsp(void)
+bool __init microcode_loader_disabled(void)
{
- static const char *__dis_opt_str = "dis_ucode_ldr";
- const char *cmdline = boot_command_line;
- const char *option = __dis_opt_str;
+ if (dis_ucode_ldr)
+ return true;
/*
- * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
- * completely accurate as xen pv guests don't see that CPUID bit set but
- * that's good enough as they don't land on the BSP path anyway.
+ * Disable when:
+ *
+ * 1) The CPU does not support CPUID.
+ *
+ * 2) Bit 31 in CPUID[1]:ECX is clear
+ * The bit is reserved for hypervisor use. This is still not
+ * completely accurate as XEN PV guests don't see that CPUID bit
+ * set, but that's good enough as they don't land on the BSP
+ * path anyway.
+ *
+ * 3) Certain AMD patch levels are not allowed to be
+ * overwritten.
*/
- if (native_cpuid_ecx(1) & BIT(31))
- return true;
-
- if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
- if (amd_check_current_patch_level())
- return true;
- }
-
- if (cmdline_find_option_bool(cmdline, option) <= 0)
- dis_ucode_ldr = false;
+ if (!have_cpuid_p() ||
+ native_cpuid_ecx(1) & BIT(31) ||
+ amd_check_current_patch_level())
+ dis_ucode_ldr = true;
return dis_ucode_ldr;
}
@@ -125,7 +130,10 @@ void __init load_ucode_bsp(void)
unsigned int cpuid_1_eax;
bool intel = true;
- if (!have_cpuid_p())
+ if (cmdline_find_option_bool(boot_command_line, "dis_ucode_ldr") > 0)
+ dis_ucode_ldr = true;
+
+ if (microcode_loader_disabled())
return;
cpuid_1_eax = native_cpuid_eax(1);
@@ -146,9 +154,6 @@ void __init load_ucode_bsp(void)
return;
}
- if (check_loader_disabled_bsp())
- return;
-
if (intel)
load_ucode_intel_bsp(&early_data);
else
@@ -159,6 +164,11 @@ void load_ucode_ap(void)
{
unsigned int cpuid_1_eax;
+ /*
+ * Can't use microcode_loader_disabled() here - .init section
+ * hell. It doesn't have to either - the BSP variant must've
+ * parsed cmdline already anyway.
+ */
if (dis_ucode_ldr)
return;
@@ -810,7 +820,7 @@ static int __init microcode_init(void)
struct cpuinfo_x86 *c = &boot_cpu_data;
int error;
- if (dis_ucode_ldr)
+ if (microcode_loader_disabled())
return -EINVAL;
if (c->x86_vendor == X86_VENDOR_INTEL)
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 819199bc0119..2a397da43923 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -389,7 +389,7 @@ static int __init save_builtin_microcode(void)
if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED)
return 0;
- if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ if (microcode_loader_disabled() || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return 0;
uci.mc = get_microcode_blob(&uci, true);
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 5df621752fef..50a9702ae4e2 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -94,7 +94,6 @@ static inline unsigned int x86_cpuid_family(void)
return x86_family(eax);
}
-extern bool dis_ucode_ldr;
extern bool force_minrev;
#ifdef CONFIG_CPU_SUP_AMD
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index cace6e8d7cc7..5eb1514af559 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -354,7 +354,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
goto fail;
ip = trampoline + size;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ if (cpu_wants_rethunk_at(ip))
__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
else
memcpy(ip, retq, sizeof(retq));
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index de001b2146ab..375f2d7f1762 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -145,10 +145,6 @@ void __init __no_stack_protector mk_early_pgtbl_32(void)
*ptr = (unsigned long)ptep + PAGE_OFFSET;
#ifdef CONFIG_MICROCODE_INITRD32
- /* Running on a hypervisor? */
- if (native_cpuid_ecx(1) & BIT(31))
- return;
-
params = (struct boot_params *)__pa_nodebug(&boot_params);
if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image)
return;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index a7998f351701..ff07558b7ebc 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -266,6 +266,8 @@ int module_finalize(const Elf_Ehdr *hdr,
ibt_endbr = s;
}
+ its_init_mod(me);
+
if (retpolines || cfi) {
void *rseg = NULL, *cseg = NULL;
unsigned int rsize = 0, csize = 0;
@@ -286,6 +288,9 @@ int module_finalize(const Elf_Ehdr *hdr,
void *rseg = (void *)retpolines->sh_addr;
apply_retpolines(rseg, rseg + retpolines->sh_size);
}
+
+ its_fini_mod(me);
+
if (returns) {
void *rseg = (void *)returns->sh_addr;
apply_returns(rseg, rseg + returns->sh_size);
@@ -326,4 +331,5 @@ int module_finalize(const Elf_Ehdr *hdr,
void module_arch_cleanup(struct module *mod)
{
alternatives_smp_module_del(mod);
+ its_free_mod(mod);
}
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index a59c72e77645..c3d7ff44b29a 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -81,7 +81,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
break;
case RET:
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ if (cpu_wants_rethunk_at(insn))
code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk);
else
code = &retinsn;
@@ -90,7 +90,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
case JCC:
if (!func) {
func = __static_call_return;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ if (cpu_wants_rethunk())
func = x86_return_thunk;
}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index ccdc45e5b759..cda5f8362e9d 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -466,10 +466,18 @@ SECTIONS
}
/*
- * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause
+ * this. Let's assume that nobody will be running a COMPILE_TEST kernel and
+ * let's assert that fuller build coverage is more valuable than being able to
+ * run a COMPILE_TEST kernel.
+ */
+#ifndef CONFIG_COMPILE_TEST
+/*
+ * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility:
*/
. = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
"kernel image bigger than KERNEL_IMAGE_SIZE");
+#endif
/* needed for Clang - see arch/x86/entry/entry.S */
PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
@@ -497,6 +505,16 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
"SRSO function pair won't alias");
#endif
+#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)
+. = ASSERT(__x86_indirect_its_thunk_rax & 0x20, "__x86_indirect_thunk_rax not in second half of cacheline");
+. = ASSERT(((__x86_indirect_its_thunk_rcx - __x86_indirect_its_thunk_rax) % 64) == 0, "Indirect thunks are not cacheline apart");
+. = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array");
+#endif
+
+#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)
+. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline");
+#endif
+
#endif /* CONFIG_X86_64 */
/*
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 050a0e229a4d..f2b36d32ef40 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -104,6 +104,9 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
{
+ if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
+ kvm_mmu_free_obsolete_roots(vcpu);
+
/*
* Checking root.hpa is sufficient even when KVM has mirror root.
* We can have either:
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 63bb77ee1bb1..8d1b632e33d2 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5974,6 +5974,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu)
__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu);
__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu);
}
+EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots);
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
int *bytes)
@@ -7669,9 +7670,30 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
}
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+}
+
bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
struct kvm_gfn_range *range)
{
+ struct kvm_memory_slot *slot = range->slot;
+ int level;
+
/*
* Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only
* supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
@@ -7686,6 +7708,38 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
return false;
+ if (WARN_ON_ONCE(range->end <= range->start))
+ return false;
+
+ /*
+ * If the head and tail pages of the range currently allow a hugepage,
+ * i.e. reside fully in the slot and don't have mixed attributes, then
+ * add each corresponding hugepage range to the ongoing invalidation,
+ * e.g. to prevent KVM from creating a hugepage in response to a fault
+ * for a gfn whose attributes aren't changing. Note, only the range
+ * of gfns whose attributes are being modified needs to be explicitly
+ * unmapped, as that will unmap any existing hugepages.
+ */
+ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+ gfn_t start = gfn_round_for_level(range->start, level);
+ gfn_t end = gfn_round_for_level(range->end - 1, level);
+ gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+
+ if ((start != range->start || start + nr_pages > range->end) &&
+ start >= slot->base_gfn &&
+ start + nr_pages <= slot->base_gfn + slot->npages &&
+ !hugepage_test_mixed(slot, start, level))
+ kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages);
+
+ if (end == start)
+ continue;
+
+ if ((end + nr_pages) > range->end &&
+ (end + nr_pages) <= (slot->base_gfn + slot->npages) &&
+ !hugepage_test_mixed(slot, end, level))
+ kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages);
+ }
+
/* Unmap the old attribute page. */
if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE)
range->attr_filter = KVM_FILTER_SHARED;
@@ -7695,23 +7749,7 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
return kvm_unmap_gfn_range(kvm, range);
}
-static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
- int level)
-{
- return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
-}
-
-static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
- int level)
-{
- lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
-}
-static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
- int level)
-{
- lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
-}
static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
gfn_t gfn, int level, unsigned long attrs)
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
index 699e551ec93b..9864c057187d 100644
--- a/arch/x86/kvm/smm.c
+++ b/arch/x86/kvm/smm.c
@@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
kvm_mmu_reset_context(vcpu);
}
+EXPORT_SYMBOL_GPL(kvm_smm_changed);
void process_smi(struct kvm_vcpu *vcpu)
{
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0bc708ee2788..a7a7dc507336 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3173,9 +3173,14 @@ skip_vmsa_free:
kvfree(svm->sev_es.ghcb_sa);
}
+static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
+{
+ return (((u64)control->exit_code_hi) << 32) | control->exit_code;
+}
+
static void dump_ghcb(struct vcpu_svm *svm)
{
- struct ghcb *ghcb = svm->sev_es.ghcb;
+ struct vmcb_control_area *control = &svm->vmcb->control;
unsigned int nbits;
/* Re-use the dump_invalid_vmcb module parameter */
@@ -3184,18 +3189,24 @@ static void dump_ghcb(struct vcpu_svm *svm)
return;
}
- nbits = sizeof(ghcb->save.valid_bitmap) * 8;
+ nbits = sizeof(svm->sev_es.valid_bitmap) * 8;
- pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa);
+ /*
+ * Print KVM's snapshot of the GHCB values that were (unsuccessfully)
+ * used to handle the exit. If the guest has since modified the GHCB
+ * itself, dumping the raw GHCB won't help debug why KVM was unable to
+ * handle the VMGEXIT that KVM observed.
+ */
+ pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa);
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
- ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb));
+ kvm_ghcb_get_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
- ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb));
+ control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
- ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb));
+ control->exit_info_2, kvm_ghcb_sw_exit_info_2_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch",
- ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb));
- pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap);
+ svm->sev_es.sw_scratch, kvm_ghcb_sw_scratch_is_valid(svm));
+ pr_err("%-20s%*pb\n", "valid_bitmap", nbits, svm->sev_es.valid_bitmap);
}
static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
@@ -3266,11 +3277,6 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
}
-static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
-{
- return (((u64)control->exit_code_hi) << 32) | control->exit_code;
-}
-
static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d5d0c5c3300b..a89c271a1951 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -607,9 +607,6 @@ static void svm_disable_virtualization_cpu(void)
kvm_cpu_svm_disable();
amd_pmu_disable_virt();
-
- if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
- msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
}
static int svm_enable_virtualization_cpu(void)
@@ -687,9 +684,6 @@ static int svm_enable_virtualization_cpu(void)
rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
}
- if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
- msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
-
return 0;
}
@@ -1518,6 +1512,63 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
}
+#ifdef CONFIG_CPU_MITIGATIONS
+static DEFINE_SPINLOCK(srso_lock);
+static atomic_t srso_nr_vms;
+
+static void svm_srso_clear_bp_spec_reduce(void *ign)
+{
+ struct svm_cpu_data *sd = this_cpu_ptr(&svm_data);
+
+ if (!sd->bp_spec_reduce_set)
+ return;
+
+ msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+ sd->bp_spec_reduce_set = false;
+}
+
+static void svm_srso_vm_destroy(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+ return;
+
+ if (atomic_dec_return(&srso_nr_vms))
+ return;
+
+ guard(spinlock)(&srso_lock);
+
+ /*
+ * Verify a new VM didn't come along, acquire the lock, and increment
+ * the count before this task acquired the lock.
+ */
+ if (atomic_read(&srso_nr_vms))
+ return;
+
+ on_each_cpu(svm_srso_clear_bp_spec_reduce, NULL, 1);
+}
+
+static void svm_srso_vm_init(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+ return;
+
+ /*
+ * Acquire the lock on 0 => 1 transitions to ensure a potential 1 => 0
+ * transition, i.e. destroying the last VM, is fully complete, e.g. so
+ * that a delayed IPI doesn't clear BP_SPEC_REDUCE after a vCPU runs.
+ */
+ if (atomic_inc_not_zero(&srso_nr_vms))
+ return;
+
+ guard(spinlock)(&srso_lock);
+
+ atomic_inc(&srso_nr_vms);
+}
+#else
+static void svm_srso_vm_init(void) { }
+static void svm_srso_vm_destroy(void) { }
+#endif
+
static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1550,6 +1601,11 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
(!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
+ if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE) &&
+ !sd->bp_spec_reduce_set) {
+ sd->bp_spec_reduce_set = true;
+ msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+ }
svm->guest_state_loaded = true;
}
@@ -2231,6 +2287,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
*/
if (!sev_es_guest(vcpu->kvm)) {
clear_page(svm->vmcb);
+#ifdef CONFIG_KVM_SMM
+ if (is_smm(vcpu))
+ kvm_smm_changed(vcpu, false);
+#endif
kvm_vcpu_reset(vcpu, true);
}
@@ -5036,6 +5096,8 @@ static void svm_vm_destroy(struct kvm *kvm)
{
avic_vm_destroy(kvm);
sev_vm_destroy(kvm);
+
+ svm_srso_vm_destroy();
}
static int svm_vm_init(struct kvm *kvm)
@@ -5061,6 +5123,7 @@ static int svm_vm_init(struct kvm *kvm)
return ret;
}
+ svm_srso_vm_init();
return 0;
}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index d4490eaed55d..f16b068c4228 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -335,6 +335,8 @@ struct svm_cpu_data {
u32 next_asid;
u32 min_asid;
+ bool bp_spec_reduce_set;
+
struct vmcb *save_area;
unsigned long save_area_pa;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index df5b99ea1f18..be7bb6d20129 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1584,7 +1584,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc);
ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
- ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
+ ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO)
static u64 kvm_get_arch_capabilities(void)
{
@@ -1618,6 +1618,8 @@ static u64 kvm_get_arch_capabilities(void)
data |= ARCH_CAP_MDS_NO;
if (!boot_cpu_has_bug(X86_BUG_RFDS))
data |= ARCH_CAP_RFDS_NO;
+ if (!boot_cpu_has_bug(X86_BUG_ITS))
+ data |= ARCH_CAP_ITS_NO;
if (!boot_cpu_has(X86_FEATURE_RTM)) {
/*
@@ -4597,7 +4599,7 @@ static bool kvm_is_vm_type_supported(unsigned long type)
return type < 32 && (kvm_caps.supported_vm_types & BIT(type));
}
-static inline u32 kvm_sync_valid_fields(struct kvm *kvm)
+static inline u64 kvm_sync_valid_fields(struct kvm *kvm)
{
return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS;
}
@@ -11493,7 +11495,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_queued_exception *ex = &vcpu->arch.exception;
struct kvm_run *kvm_run = vcpu->run;
- u32 sync_valid_fields;
+ u64 sync_valid_fields;
int r;
r = kvm_mmu_post_init_vm(vcpu->kvm);
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index a26c43abd47d..39374949daa2 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -367,6 +367,54 @@ SYM_FUNC_END(call_depth_return_thunk)
#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
+#ifdef CONFIG_MITIGATION_ITS
+
+.macro ITS_THUNK reg
+
+/*
+ * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b)
+ * that complete the fineibt_paranoid caller sequence.
+ */
+1: .byte 0xea
+SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+ jne 1b
+SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+ ANNOTATE_RETPOLINE_SAFE
+ jmp *%\reg
+ int3
+ .align 32, 0xcc /* fill to the end of the line */
+ .skip 32 - (__x86_indirect_its_thunk_\reg - 1b), 0xcc /* skip to the next upper half */
+.endm
+
+/* ITS mitigation requires thunks be aligned to upper half of cacheline */
+.align 64, 0xcc
+.skip 29, 0xcc
+
+#define GEN(reg) ITS_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+ .align 64, 0xcc
+SYM_FUNC_ALIAS(__x86_indirect_its_thunk_array, __x86_indirect_its_thunk_rax)
+SYM_CODE_END(__x86_indirect_its_thunk_array)
+
+.align 64, 0xcc
+.skip 32, 0xcc
+SYM_CODE_START(its_return_thunk)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_CODE_END(its_return_thunk)
+EXPORT_SYMBOL(its_return_thunk)
+
+#endif /* CONFIG_MITIGATION_ITS */
+
/*
* This function name is magical and is used by -mfunction-return=thunk-extern
* for the compiler to generate JMPs to it.
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ad662cc4605c..7fa3965dcef1 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -30,6 +30,7 @@
#include <linux/initrd.h>
#include <linux/cpumask.h>
#include <linux/gfp.h>
+#include <linux/execmem.h>
#include <asm/asm.h>
#include <asm/bios_ebda.h>
@@ -755,6 +756,8 @@ void mark_rodata_ro(void)
pr_info("Write protecting kernel text and read-only data: %luk\n",
size >> 10);
+ execmem_cache_make_ro();
+
kernel_set_to_readonly = 1;
#ifdef CONFIG_CPA_DEBUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 7c4f6f591f2b..949a447f75ec 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,6 +34,7 @@
#include <linux/gfp.h>
#include <linux/kcore.h>
#include <linux/bootmem_info.h>
+#include <linux/execmem.h>
#include <asm/processor.h>
#include <asm/bios_ebda.h>
@@ -1391,6 +1392,8 @@ void mark_rodata_ro(void)
(end - start) >> 10);
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+ execmem_cache_make_ro();
+
kernel_set_to_readonly = 1;
/*
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index eb83348f9305..b6d6750e4bd1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -899,8 +899,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
cond_mitigation(tsk);
/*
- * Let nmi_uaccess_okay() and finish_asid_transition()
- * know that CR3 is changing.
+ * Indicate that CR3 is about to change. nmi_uaccess_okay()
+ * and others are sensitive to the window where mm_cpumask(),
+ * CR3 and cpu_tlbstate.loaded_mm are not all in sync.
*/
this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
barrier();
@@ -1204,8 +1205,16 @@ done:
static bool should_flush_tlb(int cpu, void *data)
{
+ struct mm_struct *loaded_mm = per_cpu(cpu_tlbstate.loaded_mm, cpu);
struct flush_tlb_info *info = data;
+ /*
+ * Order the 'loaded_mm' and 'is_lazy' against their
+ * write ordering in switch_mm_irqs_off(). Ensure
+ * 'is_lazy' is at least as new as 'loaded_mm'.
+ */
+ smp_rmb();
+
/* Lazy TLB will get flushed at the next context switch. */
if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
return false;
@@ -1214,8 +1223,15 @@ static bool should_flush_tlb(int cpu, void *data)
if (!info->mm)
return true;
+ /*
+ * While switching, the remote CPU could have state from
+ * either the prev or next mm. Assume the worst and flush.
+ */
+ if (loaded_mm == LOADED_MM_SWITCHING)
+ return true;
+
/* The target mm is loaded, and the CPU is not lazy. */
- if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm)
+ if (loaded_mm == info->mm)
return true;
/* In cpumask, but not the loaded mm? Periodically remove by flushing. */
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 9e5fe2ba858f..ea4dd5b393aa 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -41,6 +41,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2)
#define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
#define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+#define EMIT5(b1, b2, b3, b4, b5) \
+ do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0)
#define EMIT1_off32(b1, off) \
do { EMIT1(b1); EMIT(off, 4); } while (0)
@@ -661,7 +663,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
{
u8 *prog = *pprog;
- if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
+ if (cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) {
+ OPTIMIZER_HIDE_VAR(reg);
+ emit_jump(&prog, its_static_thunk(reg), ip);
+ } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
EMIT_LFENCE();
EMIT2(0xFF, 0xE0 + reg);
} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
@@ -683,7 +688,7 @@ static void emit_return(u8 **pprog, u8 *ip)
{
u8 *prog = *pprog;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+ if (cpu_wants_rethunk()) {
emit_jump(&prog, x86_return_thunk, ip);
} else {
EMIT1(0xC3); /* ret */
@@ -1502,6 +1507,48 @@ static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr)
#define PRIV_STACK_GUARD_SZ 8
#define PRIV_STACK_GUARD_VAL 0xEB9F12345678eb9fULL
+static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip,
+ struct bpf_prog *bpf_prog)
+{
+ u8 *prog = *pprog;
+ u8 *func;
+
+ if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) {
+ /* The clearing sequence clobbers eax and ecx. */
+ EMIT1(0x50); /* push rax */
+ EMIT1(0x51); /* push rcx */
+ ip += 2;
+
+ func = (u8 *)clear_bhb_loop;
+ ip += x86_call_depth_emit_accounting(&prog, func, ip);
+
+ if (emit_call(&prog, func, ip))
+ return -EINVAL;
+ EMIT1(0x59); /* pop rcx */
+ EMIT1(0x58); /* pop rax */
+ }
+ /* Insert IBHF instruction */
+ if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) &&
+ cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) ||
+ cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) {
+ /*
+ * Add an Indirect Branch History Fence (IBHF). IBHF acts as a
+ * fence preventing branch history from before the fence from
+ * affecting indirect branches after the fence. This is
+ * specifically used in cBPF jitted code to prevent Intra-mode
+ * BHI attacks. The IBHF instruction is designed to be a NOP on
+ * hardware that doesn't need or support it. The REP and REX.W
+ * prefixes are required by the microcode, and they also ensure
+ * that the NOP is unlikely to be used in existing code.
+ *
+ * IBHF is not a valid instruction in 32-bit mode.
+ */
+ EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */
+ }
+ *pprog = prog;
+ return 0;
+}
+
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
int oldproglen, struct jit_context *ctx, bool jmp_padding)
{
@@ -2544,6 +2591,13 @@ emit_jmp:
seen_exit = true;
/* Update cleanup_addr */
ctx->cleanup_addr = proglen;
+ if (bpf_prog_was_classic(bpf_prog) &&
+ !capable(CAP_SYS_ADMIN)) {
+ u8 *ip = image + addrs[i - 1];
+
+ if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog))
+ return -EINVAL;
+ }
if (bpf_prog->aux->exception_boundary) {
pop_callee_regs(&prog, all_callee_regs_used);
pop_r12(&prog);
diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h
index ab5c8e47049c..9193a7790a71 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_32.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_32.h
@@ -31,8 +31,8 @@ struct faultinfo {
#define ___backtrack_faulted(_faulted) \
asm volatile ( \
- "mov $0, %0\n" \
"movl $__get_kernel_nofault_faulted_%=,%1\n" \
+ "mov $0, %0\n" \
"jmp _end_%=\n" \
"__get_kernel_nofault_faulted_%=:\n" \
"mov $1, %0;" \
diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h
index 26fb4835d3e9..61e4ca1e0ab5 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_64.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_64.h
@@ -31,8 +31,8 @@ struct faultinfo {
#define ___backtrack_faulted(_faulted) \
asm volatile ( \
- "mov $0, %0\n" \
"movq $__get_kernel_nofault_faulted_%=,%1\n" \
+ "mov $0, %0\n" \
"jmp _end_%=\n" \
"__get_kernel_nofault_faulted_%=:\n" \
"mov $1, %0;" \