summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Makefile3
-rw-r--r--arch/um/kernel/um_arch.c11
-rw-r--r--arch/x86/Kconfig9
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S2
-rw-r--r--arch/x86/crypto/camellia-aesni-avx-asm_64.S7
-rw-r--r--arch/x86/crypto/camellia-aesni-avx2-asm_64.S1
-rw-r--r--arch/x86/crypto/camellia-x86_64-asm_64.S9
-rw-r--r--arch/x86/crypto/serpent-avx-x86_64-asm_64.S7
-rw-r--r--arch/x86/crypto/twofish-x86_64-asm_64-3way.S5
-rw-r--r--arch/x86/crypto/twofish-x86_64-asm_64.S5
-rw-r--r--arch/x86/entry/calling.h1
-rw-r--r--arch/x86/entry/entry.S2
-rw-r--r--arch/x86/entry/entry_64.S3
-rw-r--r--arch/x86/entry/entry_64_fred.S1
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl2
-rw-r--r--arch/x86/entry/vdso/Makefile1
-rw-r--r--arch/x86/entry/vdso/vma.c3
-rw-r--r--arch/x86/events/core.c2
-rw-r--r--arch/x86/include/asm/alternative.h15
-rw-r--r--arch/x86/include/asm/bug.h8
-rw-r--r--arch/x86/include/asm/cfi.h26
-rw-r--r--arch/x86/include/asm/cpu.h1
-rw-r--r--arch/x86/include/asm/ftrace.h16
-rw-r--r--arch/x86/include/asm/ibt.h13
-rw-r--r--arch/x86/include/asm/linkage.h18
-rw-r--r--arch/x86/include/asm/nmi.h2
-rw-r--r--arch/x86/include/asm/page_64.h1
-rw-r--r--arch/x86/include/asm/paravirt_types.h14
-rw-r--r--arch/x86/include/asm/pgtable_types.h2
-rw-r--r--arch/x86/include/asm/processor.h5
-rw-r--r--arch/x86/include/asm/proto.h3
-rw-r--r--arch/x86/include/asm/setup.h1
-rw-r--r--arch/x86/include/asm/smp.h6
-rw-r--r--arch/x86/include/asm/special_insns.h4
-rw-r--r--arch/x86/include/asm/string_64.h2
-rw-r--r--arch/x86/include/asm/tlbflush.h2
-rw-r--r--arch/x86/include/asm/traps.h2
-rw-r--r--arch/x86/kernel/acpi/madt_playdead.S1
-rw-r--r--arch/x86/kernel/acpi/wakeup_64.S1
-rw-r--r--arch/x86/kernel/alternative.c645
-rw-r--r--arch/x86/kernel/apic/ipi.c30
-rw-r--r--arch/x86/kernel/callthunks.c13
-rw-r--r--arch/x86/kernel/cfi.c26
-rw-r--r--arch/x86/kernel/crash.c2
-rw-r--r--arch/x86/kernel/early_printk.c49
-rw-r--r--arch/x86/kernel/ftrace.c30
-rw-r--r--arch/x86/kernel/ftrace_64.S5
-rw-r--r--arch/x86/kernel/irqflags.S1
-rw-r--r--arch/x86/kernel/kprobes/core.c11
-rw-r--r--arch/x86/kernel/module.c66
-rw-r--r--arch/x86/kernel/nmi.c42
-rw-r--r--arch/x86/kernel/paravirt.c32
-rw-r--r--arch/x86/kernel/process.c5
-rw-r--r--arch/x86/kernel/process_32.c5
-rw-r--r--arch/x86/kernel/process_64.c25
-rw-r--r--arch/x86/kernel/reboot.c12
-rw-r--r--arch/x86/kernel/setup.c66
-rw-r--r--arch/x86/kernel/smpboot.c3
-rw-r--r--arch/x86/kernel/traps.c132
-rw-r--r--arch/x86/lib/Makefile3
-rw-r--r--arch/x86/lib/bhi.S147
-rw-r--r--arch/x86/lib/clear_page_64.S9
-rw-r--r--arch/x86/lib/copy_page_64.S3
-rw-r--r--arch/x86/lib/copy_user_64.S3
-rw-r--r--arch/x86/lib/copy_user_uncached_64.S2
-rw-r--r--arch/x86/lib/getuser.S9
-rw-r--r--arch/x86/lib/hweight.S3
-rw-r--r--arch/x86/lib/memmove_64.S3
-rw-r--r--arch/x86/lib/memset_64.S3
-rw-r--r--arch/x86/lib/msr-reg.S3
-rw-r--r--arch/x86/lib/putuser.S9
-rw-r--r--arch/x86/lib/retpoline.S1
-rw-r--r--arch/x86/mm/mem_encrypt_boot.S1
-rw-r--r--arch/x86/mm/pat/cpa-test.c2
-rw-r--r--arch/x86/mm/pat/set_memory.c220
-rw-r--r--arch/x86/mm/tlb.c2
-rw-r--r--arch/x86/net/bpf_jit_comp.c34
-rw-r--r--arch/x86/power/hibernate_asm_64.S2
-rw-r--r--arch/x86/xen/xen-asm.S5
-rw-r--r--arch/x86/xen/xen-head.S2
-rw-r--r--include/linux/acpi.h1
-rw-r--r--include/linux/cfi.h2
-rw-r--r--include/linux/compiler.h10
-rw-r--r--include/linux/execmem.h31
-rw-r--r--include/linux/module.h16
-rw-r--r--include/linux/moduleloader.h4
-rw-r--r--include/linux/objtool.h4
-rw-r--r--include/linux/vm_event_item.h2
-rw-r--r--kernel/cfi.c4
-rw-r--r--kernel/module/main.c81
-rw-r--r--kernel/module/strict_rwx.c9
-rw-r--r--kernel/sysctl.c56
-rw-r--r--kernel/trace/bpf_trace.c21
-rw-r--r--mm/execmem.c39
-rw-r--r--mm/vmstat.c2
-rw-r--r--tools/objtool/arch/x86/decode.c1
-rw-r--r--tools/objtool/check.c12
97 files changed, 1499 insertions, 679 deletions
diff --git a/Makefile b/Makefile
index 70bdbf2218fc..2ea14ff6c88a 100644
--- a/Makefile
+++ b/Makefile
@@ -1014,6 +1014,9 @@ CC_FLAGS_CFI := -fsanitize=kcfi
ifdef CONFIG_CFI_ICALL_NORMALIZE_INTEGERS
CC_FLAGS_CFI += -fsanitize-cfi-icall-experimental-normalize-integers
endif
+ifdef CONFIG_FINEIBT_BHI
+ CC_FLAGS_CFI += -fsanitize-kcfi-arity
+endif
ifdef CONFIG_RUST
# Always pass -Zsanitizer-cfi-normalize-integers as CONFIG_RUST selects
# CONFIG_CFI_ICALL_NORMALIZE_INTEGERS.
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 79ea97d4797e..8be91974e786 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -440,25 +440,24 @@ void __init arch_cpu_finalize_init(void)
os_check_bugs();
}
-void apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void apply_seal_endbr(s32 *start, s32 *end)
{
}
-void apply_retpolines(s32 *start, s32 *end, struct module *mod)
+void apply_retpolines(s32 *start, s32 *end)
{
}
-void apply_returns(s32 *start, s32 *end, struct module *mod)
+void apply_returns(s32 *start, s32 *end)
{
}
void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
- s32 *start_cfi, s32 *end_cfi, struct module *mod)
+ s32 *start_cfi, s32 *end_cfi)
{
}
-void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
- struct module *mod)
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
{
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index be2c311f5118..5c277261507e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -85,6 +85,7 @@ config X86
select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN
select ARCH_HAS_EARLY_DEBUG if KGDB
select ARCH_HAS_ELF_RANDOMIZE
+ select ARCH_HAS_EXECMEM_ROX if X86_64
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
@@ -2472,6 +2473,10 @@ config CC_HAS_RETURN_THUNK
config CC_HAS_ENTRY_PADDING
def_bool $(cc-option,-fpatchable-function-entry=16,16)
+config CC_HAS_KCFI_ARITY
+ def_bool $(cc-option,-fsanitize=kcfi -fsanitize-kcfi-arity)
+ depends on CC_IS_CLANG && !RUST
+
config FUNCTION_PADDING_CFI
int
default 59 if FUNCTION_ALIGNMENT_64B
@@ -2497,6 +2502,10 @@ config FINEIBT
depends on X86_KERNEL_IBT && CFI_CLANG && MITIGATION_RETPOLINE
select CALL_PADDING
+config FINEIBT_BHI
+ def_bool y
+ depends on FINEIBT && CC_HAS_KCFI_ARITY
+
config HAVE_CALL_THUNKS
def_bool y
depends on CC_HAS_ENTRY_PADDING && MITIGATION_RETHUNK && OBJTOOL
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index eb153eff9331..b37881bb9f15 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -17,6 +17,7 @@
*/
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/frame.h>
#define STATE1 %xmm0
@@ -1071,6 +1072,7 @@ SYM_FUNC_END(_aesni_inc)
* size_t len, u8 *iv)
*/
SYM_FUNC_START(aesni_ctr_enc)
+ ANNOTATE_NOENDBR
FRAME_BEGIN
cmp $16, LEN
jb .Lctr_enc_just_ret
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index 646477a13e11..1dfef28c1266 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -16,6 +16,7 @@
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/frame.h>
#define CAMELLIA_TABLE_BYTE_LEN 272
@@ -882,7 +883,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
jmp .Ldec_max24;
SYM_FUNC_END(__camellia_dec_blk16)
-SYM_FUNC_START(camellia_ecb_enc_16way)
+SYM_TYPED_FUNC_START(camellia_ecb_enc_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst (16 blocks)
@@ -907,7 +908,7 @@ SYM_FUNC_START(camellia_ecb_enc_16way)
RET;
SYM_FUNC_END(camellia_ecb_enc_16way)
-SYM_FUNC_START(camellia_ecb_dec_16way)
+SYM_TYPED_FUNC_START(camellia_ecb_dec_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst (16 blocks)
@@ -937,7 +938,7 @@ SYM_FUNC_START(camellia_ecb_dec_16way)
RET;
SYM_FUNC_END(camellia_ecb_dec_16way)
-SYM_FUNC_START(camellia_cbc_dec_16way)
+SYM_TYPED_FUNC_START(camellia_cbc_dec_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst (16 blocks)
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index a0eb94e53b1b..b1c9b9450555 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -6,6 +6,7 @@
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/frame.h>
#define CAMELLIA_TABLE_BYTE_LEN 272
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 816b6bb8bded..824cb94de6c2 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -6,6 +6,7 @@
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
.file "camellia-x86_64-asm_64.S"
.text
@@ -177,7 +178,7 @@
bswapq RAB0; \
movq RAB0, 4*2(RIO);
-SYM_FUNC_START(__camellia_enc_blk)
+SYM_TYPED_FUNC_START(__camellia_enc_blk)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -224,7 +225,7 @@ SYM_FUNC_START(__camellia_enc_blk)
RET;
SYM_FUNC_END(__camellia_enc_blk)
-SYM_FUNC_START(camellia_dec_blk)
+SYM_TYPED_FUNC_START(camellia_dec_blk)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -411,7 +412,7 @@ SYM_FUNC_END(camellia_dec_blk)
bswapq RAB1; \
movq RAB1, 12*2(RIO);
-SYM_FUNC_START(__camellia_enc_blk_2way)
+SYM_TYPED_FUNC_START(__camellia_enc_blk_2way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -460,7 +461,7 @@ SYM_FUNC_START(__camellia_enc_blk_2way)
RET;
SYM_FUNC_END(__camellia_enc_blk_2way)
-SYM_FUNC_START(camellia_dec_blk_2way)
+SYM_TYPED_FUNC_START(camellia_dec_blk_2way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index 97e283621851..84e47f7f6188 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/frame.h>
#include "glue_helper-asm-avx.S"
@@ -656,7 +657,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
RET;
SYM_FUNC_END(__serpent_dec_blk8_avx)
-SYM_FUNC_START(serpent_ecb_enc_8way_avx)
+SYM_TYPED_FUNC_START(serpent_ecb_enc_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -674,7 +675,7 @@ SYM_FUNC_START(serpent_ecb_enc_8way_avx)
RET;
SYM_FUNC_END(serpent_ecb_enc_8way_avx)
-SYM_FUNC_START(serpent_ecb_dec_8way_avx)
+SYM_TYPED_FUNC_START(serpent_ecb_dec_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -692,7 +693,7 @@ SYM_FUNC_START(serpent_ecb_dec_8way_avx)
RET;
SYM_FUNC_END(serpent_ecb_dec_8way_avx)
-SYM_FUNC_START(serpent_cbc_dec_8way_avx)
+SYM_TYPED_FUNC_START(serpent_cbc_dec_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index d2288bf38a8a..071e90e7f0d8 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -6,6 +6,7 @@
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
.file "twofish-x86_64-asm-3way.S"
.text
@@ -220,7 +221,7 @@
rorq $32, RAB2; \
outunpack3(mov, RIO, 2, RAB, 2);
-SYM_FUNC_START(__twofish_enc_blk_3way)
+SYM_TYPED_FUNC_START(__twofish_enc_blk_3way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -269,7 +270,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way)
RET;
SYM_FUNC_END(__twofish_enc_blk_3way)
-SYM_FUNC_START(twofish_dec_blk_3way)
+SYM_TYPED_FUNC_START(twofish_dec_blk_3way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S
index 775af290cd19..e08b4ba07b93 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64.S
@@ -8,6 +8,7 @@
.text
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/asm-offsets.h>
#define a_offset 0
@@ -202,7 +203,7 @@
xor %r8d, d ## D;\
ror $1, d ## D;
-SYM_FUNC_START(twofish_enc_blk)
+SYM_TYPED_FUNC_START(twofish_enc_blk)
pushq R1
/* %rdi contains the ctx address */
@@ -255,7 +256,7 @@ SYM_FUNC_START(twofish_enc_blk)
RET
SYM_FUNC_END(twofish_enc_blk)
-SYM_FUNC_START(twofish_dec_blk)
+SYM_TYPED_FUNC_START(twofish_dec_blk)
pushq R1
/* %rdi contains the ctx address */
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index ea81770629ee..cb0911c5dc5d 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -431,6 +431,7 @@ For 32-bit we have the following conventions - kernel is built with
/* rdi: arg1 ... normal C conventions. rax is saved/restored. */
.macro THUNK name, func
SYM_FUNC_START(\name)
+ ANNOTATE_NOENDBR
pushq %rbp
movq %rsp, %rbp
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index b7ea3e8e9ecc..e6d52c2fd088 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -5,6 +5,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/msr-index.h>
#include <asm/unwind_hints.h>
#include <asm/segment.h>
@@ -17,6 +18,7 @@
.pushsection .noinstr.text, "ax"
SYM_FUNC_START(entry_ibpb)
+ ANNOTATE_NOENDBR
movl $MSR_IA32_PRED_CMD, %ecx
movl $PRED_CMD_IBPB, %eax
xorl %edx, %edx
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f52dbe0ad93c..4e5260cdeb81 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -175,6 +175,7 @@ SYM_CODE_END(entry_SYSCALL_64)
*/
.pushsection .text, "ax"
SYM_FUNC_START(__switch_to_asm)
+ ANNOTATE_NOENDBR
/*
* Save callee-saved registers
* This must match the order in inactive_task_frame
@@ -742,6 +743,7 @@ _ASM_NOKPROBE(common_interrupt_return)
* Is in entry.text as it shouldn't be instrumented.
*/
SYM_FUNC_START(asm_load_gs_index)
+ ANNOTATE_NOENDBR
FRAME_BEGIN
swapgs
.Lgs_change:
@@ -1526,6 +1528,7 @@ SYM_CODE_END(rewind_stack_and_make_dead)
* refactored in the future if needed.
*/
SYM_FUNC_START(clear_bhb_loop)
+ ANNOTATE_NOENDBR
push %rbp
mov %rsp, %rbp
movl $5, %ecx
diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S
index a02bc6f3d2e6..29c5c32c16c3 100644
--- a/arch/x86/entry/entry_64_fred.S
+++ b/arch/x86/entry/entry_64_fred.S
@@ -58,6 +58,7 @@ SYM_CODE_END(asm_fred_entrypoint_kernel)
#if IS_ENABLED(CONFIG_KVM_INTEL)
SYM_FUNC_START(asm_fred_entry_from_kvm)
+ ANNOTATE_NOENDBR
push %rbp
mov %rsp, %rbp
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 4d0fb2fba7e2..62283097a7cc 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -396,7 +396,7 @@
381 i386 pkey_alloc sys_pkey_alloc
382 i386 pkey_free sys_pkey_free
383 i386 statx sys_statx
-384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl
+384 i386 arch_prctl sys_arch_prctl
385 i386 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents
386 i386 rseq sys_rseq
393 i386 semget sys_semget
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index c9216ac4fb1e..bf9f4f63e1b4 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -133,6 +133,7 @@ KBUILD_CFLAGS_32 += -fno-stack-protector
KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS_32 += -DBUILD_VDSO
ifdef CONFIG_MITIGATION_RETPOLINE
ifneq ($(RETPOLINE_VDSO_CFLAGS),)
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 39e6efc1a9ca..bfc7cabf4017 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -48,8 +48,7 @@ int __init init_vdso_image(const struct vdso_image *image)
apply_alternatives((struct alt_instr *)(image->data + image->alt),
(struct alt_instr *)(image->data + image->alt +
- image->alt_len),
- NULL);
+ image->alt_len));
return 0;
}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 2092d615333d..6da70d444815 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2844,7 +2844,7 @@ static bool is_uprobe_at_func_entry(struct pt_regs *regs)
return true;
/* endbr64 (64-bit only) */
- if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn))
+ if (user_64bit_mode(regs) && is_endbr((u32 *)auprobe->insn))
return true;
return false;
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index e3903b731305..853fbcf68719 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -87,20 +87,19 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
* instructions were patched in already:
*/
extern int alternatives_patched;
-struct module;
extern void alternative_instructions(void);
-extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
- struct module *mod);
-extern void apply_retpolines(s32 *start, s32 *end, struct module *mod);
-extern void apply_returns(s32 *start, s32 *end, struct module *mod);
-extern void apply_seal_endbr(s32 *start, s32 *end, struct module *mod);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
+extern void apply_returns(s32 *start, s32 *end);
+extern void apply_seal_endbr(s32 *start, s32 *end);
extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
- s32 *start_cfi, s32 *end_cfi, struct module *mod);
+ s32 *start_cfi, s32 *end_cfi);
+
+struct module;
struct callthunk_sites {
s32 *call_start, *call_end;
- struct alt_instr *alt_start, *alt_end;
};
#ifdef CONFIG_CALL_THUNKS
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index e85ac0c7c039..f0e9acf72547 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -17,13 +17,17 @@
* In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit.
*/
#define INSN_ASOP 0x67
+#define INSN_LOCK 0xf0
#define OPCODE_ESCAPE 0x0f
#define SECOND_BYTE_OPCODE_UD1 0xb9
#define SECOND_BYTE_OPCODE_UD2 0x0b
#define BUG_NONE 0xffff
-#define BUG_UD1 0xfffe
-#define BUG_UD2 0xfffd
+#define BUG_UD2 0xfffe
+#define BUG_UD1 0xfffd
+#define BUG_UD1_UBSAN 0xfffc
+#define BUG_EA 0xffea
+#define BUG_LOCK 0xfff0
#ifdef CONFIG_GENERIC_BUG
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 31d19c815f99..3e51ba459154 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -101,6 +101,16 @@ enum cfi_mode {
extern enum cfi_mode cfi_mode;
+#ifdef CONFIG_FINEIBT_BHI
+extern bool cfi_bhi;
+#else
+#define cfi_bhi (0)
+#endif
+
+typedef u8 bhi_thunk[32];
+extern bhi_thunk __bhi_args[];
+extern bhi_thunk __bhi_args_end[];
+
struct pt_regs;
#ifdef CONFIG_CFI_CLANG
@@ -125,6 +135,18 @@ static inline int cfi_get_offset(void)
#define cfi_get_offset cfi_get_offset
extern u32 cfi_get_func_hash(void *func);
+extern int cfi_get_func_arity(void *func);
+
+#ifdef CONFIG_FINEIBT
+extern bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type);
+#else
+static inline bool
+decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+ return false;
+}
+
+#endif
#else
static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
@@ -137,6 +159,10 @@ static inline u32 cfi_get_func_hash(void *func)
{
return 0;
}
+static inline int cfi_get_func_arity(void *func)
+{
+ return 0;
+}
#endif /* CONFIG_CFI_CLANG */
#if HAS_KERNEL_IBT == 1
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 98eced5084ca..f44bbce18859 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -12,7 +12,6 @@
#ifndef CONFIG_SMP
#define cpu_physical_id(cpu) boot_cpu_physical_apicid
#define cpu_acpi_id(cpu) 0
-#define safe_smp_processor_id() 0
#endif /* CONFIG_SMP */
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index f9cb4d07df58..f2265246249a 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -36,21 +36,9 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
{
-#ifdef CONFIG_X86_KERNEL_IBT
- u32 instr;
-
- /* We want to be extra safe in case entry ip is on the page edge,
- * but otherwise we need to avoid get_kernel_nofault()'s overhead.
- */
- if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
- if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
- return fentry_ip;
- } else {
- instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
- }
- if (is_endbr(instr))
+ if (is_endbr((void*)(fentry_ip - ENDBR_INSN_SIZE)))
fentry_ip -= ENDBR_INSN_SIZE;
-#endif
+
return fentry_ip;
}
#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip)
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index 1e59581d500c..9423a2967f50 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -41,7 +41,7 @@
_ASM_PTR fname "\n\t" \
".popsection\n\t"
-static inline __attribute_const__ u32 gen_endbr(void)
+static __always_inline __attribute_const__ u32 gen_endbr(void)
{
u32 endbr;
@@ -56,7 +56,7 @@ static inline __attribute_const__ u32 gen_endbr(void)
return endbr;
}
-static inline __attribute_const__ u32 gen_endbr_poison(void)
+static __always_inline __attribute_const__ u32 gen_endbr_poison(void)
{
/*
* 4 byte NOP that isn't NOP4 (in fact it is OSP NOP3), such that it
@@ -65,15 +65,20 @@ static inline __attribute_const__ u32 gen_endbr_poison(void)
return 0x001f0f66; /* osp nopl (%rax) */
}
-static inline bool is_endbr(u32 val)
+static inline bool __is_endbr(u32 val)
{
if (val == gen_endbr_poison())
return true;
+ /* See cfi_fineibt_bhi_preamble() */
+ if (IS_ENABLED(CONFIG_FINEIBT_BHI) && val == 0x001f0ff5)
+ return true;
+
val &= ~0x01000000U; /* ENDBR32 -> ENDBR64 */
return val == gen_endbr();
}
+extern __noendbr bool is_endbr(u32 *val);
extern __noendbr u64 ibt_save(bool disable);
extern __noendbr void ibt_restore(u64 save);
@@ -98,7 +103,7 @@ extern __noendbr void ibt_restore(u64 save);
#define __noendbr
-static inline bool is_endbr(u32 val) { return false; }
+static inline bool is_endbr(u32 *val) { return false; }
static inline u64 ibt_save(bool disable) { return 0; }
static inline void ibt_restore(u64 save) { }
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index dc31b13b87a0..4835c67bb5dd 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -119,33 +119,27 @@
/* SYM_FUNC_START -- use for global functions */
#define SYM_FUNC_START(name) \
- SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \
- ENDBR
+ SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)
/* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */
#define SYM_FUNC_START_NOALIGN(name) \
- SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE) \
- ENDBR
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)
/* SYM_FUNC_START_LOCAL -- use for local functions */
#define SYM_FUNC_START_LOCAL(name) \
- SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN) \
- ENDBR
+ SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)
/* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */
#define SYM_FUNC_START_LOCAL_NOALIGN(name) \
- SYM_START(name, SYM_L_LOCAL, SYM_A_NONE) \
- ENDBR
+ SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)
/* SYM_FUNC_START_WEAK -- use for weak functions */
#define SYM_FUNC_START_WEAK(name) \
- SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN) \
- ENDBR
+ SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)
/* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */
#define SYM_FUNC_START_WEAK_NOALIGN(name) \
- SYM_START(name, SYM_L_WEAK, SYM_A_NONE) \
- ENDBR
+ SYM_START(name, SYM_L_WEAK, SYM_A_NONE)
#endif /* _ASM_X86_LINKAGE_H */
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 41a0ebb699ec..f677382093f3 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -56,6 +56,8 @@ int __register_nmi_handler(unsigned int, struct nmiaction *);
void unregister_nmi_handler(unsigned int, const char *);
+void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler);
+
void stop_nmi(void);
void restart_nmi(void);
void local_touch_nmi(void);
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index d63576608ce7..5c5cfa076a27 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -60,6 +60,7 @@ static inline void clear_page(void *page)
}
void copy_page(void *to, void *from);
+KCFI_REFERENCE(copy_page);
#ifdef CONFIG_X86_5LEVEL
/*
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index fea56b04f436..8e21a1a85e74 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -242,9 +242,17 @@ extern struct paravirt_patch_template pv_ops;
#define paravirt_ptr(op) [paravirt_opptr] "m" (pv_ops.op)
-int paravirt_disable_iospace(void);
-
-/* This generates an indirect call based on the operation type number. */
+/*
+ * This generates an indirect call based on the operation type number.
+ *
+ * Since alternatives run after enabling CET/IBT -- the latter setting/clearing
+ * capabilities and the former requiring all capabilities being finalized --
+ * these indirect calls are subject to IBT and the paravirt stubs should have
+ * ENDBR on.
+ *
+ * OTOH since this is effectively a __nocfi indirect call, the paravirt stubs
+ * don't need to bother with CFI prefixes.
+ */
#define PARAVIRT_CALL \
ANNOTATE_RETPOLINE_SAFE \
"call *%[paravirt_opptr];"
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 4b804531b03c..c90e9c51edb7 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -33,6 +33,7 @@
#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1
#define _PAGE_BIT_UFFD_WP _PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */
+#define _PAGE_BIT_KERNEL_4K _PAGE_BIT_SOFTW3 /* page must not be converted to large */
#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4
#ifdef CONFIG_X86_64
@@ -64,6 +65,7 @@
#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
#define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
#define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define _PAGE_KERNEL_4K (_AT(pteval_t, 1) << _PAGE_BIT_KERNEL_4K)
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
#define _PAGE_PKEY_BIT0 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT0)
#define _PAGE_PKEY_BIT1 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT1)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0cd10182e90..0c911083fdd1 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -668,8 +668,6 @@ static __always_inline void prefetchw(const void *x)
.sysenter_cs = __KERNEL_CS, \
}
-#define KSTK_ESP(task) (task_pt_regs(task)->sp)
-
#else
extern unsigned long __top_init_kernel_stack[];
@@ -677,8 +675,6 @@ extern unsigned long __top_init_kernel_stack[];
.sp = (unsigned long)&__top_init_kernel_stack, \
}
-extern unsigned long KSTK_ESP(struct task_struct *task);
-
#endif /* CONFIG_X86_64 */
extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
@@ -692,6 +688,7 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE_LOW)
#define KSTK_EIP(task) (task_pt_regs(task)->ip)
+#define KSTK_ESP(task) (task_pt_regs(task)->sp)
/* Get/set a process' ability to use the timestamp counter instruction */
#define GET_TSC_CTL(adr) get_tsc_mode((adr))
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 484f4f0131a5..05224a695872 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -15,7 +15,6 @@ void entry_SYSCALL_64(void);
void entry_SYSCALL_64_safe_stack(void);
void entry_SYSRETQ_unsafe_stack(void);
void entry_SYSRETQ_end(void);
-long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
#endif
#ifdef CONFIG_X86_32
@@ -41,6 +40,6 @@ void x86_configure_nx(void);
extern int reboot_force;
-long do_arch_prctl_common(int option, unsigned long arg2);
+long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
#endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 85f4fde3515c..a8d676bba5de 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -46,6 +46,7 @@ void setup_bios_corruption_check(void);
void early_platform_quirks(void);
extern unsigned long saved_video_mode;
+extern unsigned long acpi_realmode_flags;
extern void reserve_standard_io_resources(void);
extern void i386_reserve_resources(void);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ca073f40698f..2419e5086c9e 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -136,12 +136,6 @@ __visible void smp_call_function_single_interrupt(struct pt_regs *r);
#define raw_smp_processor_id() this_cpu_read(pcpu_hot.cpu_number)
#define __smp_processor_id() __this_cpu_read(pcpu_hot.cpu_number)
-#ifdef CONFIG_X86_32
-extern int safe_smp_processor_id(void);
-#else
-# define safe_smp_processor_id() smp_processor_id()
-#endif
-
static inline struct cpumask *cpu_llc_shared_mask(int cpu)
{
return per_cpu(cpu_llc_shared_map, cpu);
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 03e7c2d49559..21ce480658b1 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -42,14 +42,14 @@ static __always_inline void native_write_cr2(unsigned long val)
asm volatile("mov %0,%%cr2": : "r" (val) : "memory");
}
-static inline unsigned long __native_read_cr3(void)
+static __always_inline unsigned long __native_read_cr3(void)
{
unsigned long val;
asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
return val;
}
-static inline void native_write_cr3(unsigned long val)
+static __always_inline void native_write_cr3(unsigned long val)
{
asm volatile("mov %0,%%cr3": : "r" (val) : "memory");
}
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 9d0b324eab21..79e9695dc13e 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -21,6 +21,7 @@ extern void *__memcpy(void *to, const void *from, size_t len);
#define __HAVE_ARCH_MEMSET
void *memset(void *s, int c, size_t n);
void *__memset(void *s, int c, size_t n);
+KCFI_REFERENCE(__memset);
/*
* KMSAN needs to instrument as much code as possible. Use C versions of
@@ -70,6 +71,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
#define __HAVE_ARCH_MEMMOVE
void *memmove(void *dest, const void *src, size_t count);
void *__memmove(void *dest, const void *src, size_t count);
+KCFI_REFERENCE(__memmove);
int memcmp(const void *cs, const void *ct, size_t count);
size_t strlen(const char *s);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 02fc2aa06e9e..3da645139748 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -242,7 +242,7 @@ void flush_tlb_multi(const struct cpumask *cpumask,
flush_tlb_mm_range((vma)->vm_mm, start, end, \
((vma)->vm_flags & VM_HUGETLB) \
? huge_page_shift(hstate_vma(vma)) \
- : PAGE_SHIFT, false)
+ : PAGE_SHIFT, true)
extern void flush_tlb_all(void);
extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 1f1deaecd364..869b88061801 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -35,8 +35,6 @@ static inline int get_si_code(unsigned long condition)
return TRAP_BRKPT;
}
-extern int panic_on_unrecovered_nmi;
-
void math_emulate(struct math_emu_info *);
bool fault_in_kernel_space(unsigned long address);
diff --git a/arch/x86/kernel/acpi/madt_playdead.S b/arch/x86/kernel/acpi/madt_playdead.S
index 4e498d28cdc8..aefb9cb583ad 100644
--- a/arch/x86/kernel/acpi/madt_playdead.S
+++ b/arch/x86/kernel/acpi/madt_playdead.S
@@ -14,6 +14,7 @@
* rsi: PGD of the identity mapping
*/
SYM_FUNC_START(asm_acpi_mp_play_dead)
+ ANNOTATE_NOENDBR
/* Turn off global entries. Following CR3 write will flush them. */
movq %cr4, %rdx
andq $~(X86_CR4_PGE), %rdx
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index b200a193beeb..04f561f75e99 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -17,6 +17,7 @@
* Hooray, we are in Long 64-bit mode (but still running in low memory)
*/
SYM_FUNC_START(wakeup_long64)
+ ANNOTATE_NOENDBR
movq saved_magic(%rip), %rax
movq $0x123456789abcdef0, %rdx
cmpq %rdx, %rax
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c71b575bf229..bf82c6f7d690 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -392,10 +392,8 @@ EXPORT_SYMBOL(BUG_func);
* Rewrite the "call BUG_func" replacement to point to the target of the
* indirect pv_ops call "call *disp(%ip)".
*/
-static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
- struct module *mod)
+static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
{
- u8 *wr_instr = module_writable_address(mod, instr);
void *target, *bug = &BUG_func;
s32 disp;
@@ -405,14 +403,14 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
}
if (a->instrlen != 6 ||
- wr_instr[0] != CALL_RIP_REL_OPCODE ||
- wr_instr[1] != CALL_RIP_REL_MODRM) {
+ instr[0] != CALL_RIP_REL_OPCODE ||
+ instr[1] != CALL_RIP_REL_MODRM) {
pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n");
BUG();
}
/* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */
- disp = *(s32 *)(wr_instr + 2);
+ disp = *(s32 *)(instr + 2);
#ifdef CONFIG_X86_64
/* ff 15 00 00 00 00 call *0x0(%rip) */
/* target address is stored at "next instruction + disp". */
@@ -450,8 +448,7 @@ static inline u8 * instr_va(struct alt_instr *i)
* to refetch changed I$ lines.
*/
void __init_or_module noinline apply_alternatives(struct alt_instr *start,
- struct alt_instr *end,
- struct module *mod)
+ struct alt_instr *end)
{
u8 insn_buff[MAX_PATCH_LEN];
u8 *instr, *replacement;
@@ -480,7 +477,6 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
*/
for (a = start; a < end; a++) {
int insn_buff_sz = 0;
- u8 *wr_instr, *wr_replacement;
/*
* In case of nested ALTERNATIVE()s the outer alternative might
@@ -494,11 +490,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
}
instr = instr_va(a);
- wr_instr = module_writable_address(mod, instr);
-
replacement = (u8 *)&a->repl_offset + a->repl_offset;
- wr_replacement = module_writable_address(mod, replacement);
-
BUG_ON(a->instrlen > sizeof(insn_buff));
BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
@@ -509,9 +501,9 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
* patch if feature is *NOT* present.
*/
if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
- memcpy(insn_buff, wr_instr, a->instrlen);
+ memcpy(insn_buff, instr, a->instrlen);
optimize_nops(instr, insn_buff, a->instrlen);
- text_poke_early(wr_instr, insn_buff, a->instrlen);
+ text_poke_early(instr, insn_buff, a->instrlen);
continue;
}
@@ -521,12 +513,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
instr, instr, a->instrlen,
replacement, a->replacementlen, a->flags);
- memcpy(insn_buff, wr_replacement, a->replacementlen);
+ memcpy(insn_buff, replacement, a->replacementlen);
insn_buff_sz = a->replacementlen;
if (a->flags & ALT_FLAG_DIRECT_CALL) {
- insn_buff_sz = alt_replace_call(instr, insn_buff, a,
- mod);
+ insn_buff_sz = alt_replace_call(instr, insn_buff, a);
if (insn_buff_sz < 0)
continue;
}
@@ -536,11 +527,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
- DUMP_BYTES(ALT, wr_instr, a->instrlen, "%px: old_insn: ", instr);
+ DUMP_BYTES(ALT, instr, a->instrlen, "%px: old_insn: ", instr);
DUMP_BYTES(ALT, replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
DUMP_BYTES(ALT, insn_buff, insn_buff_sz, "%px: final_insn: ", instr);
- text_poke_early(wr_instr, insn_buff, insn_buff_sz);
+ text_poke_early(instr, insn_buff, insn_buff_sz);
}
kasan_enable_current();
@@ -731,20 +722,18 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
/*
* Generated by 'objtool --retpoline'.
*/
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
- struct module *mod)
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
{
s32 *s;
for (s = start; s < end; s++) {
void *addr = (void *)s + *s;
- void *wr_addr = module_writable_address(mod, addr);
struct insn insn;
int len, ret;
u8 bytes[16];
u8 op1, op2;
- ret = insn_decode_kernel(&insn, wr_addr);
+ ret = insn_decode_kernel(&insn, addr);
if (WARN_ON_ONCE(ret < 0))
continue;
@@ -752,6 +741,11 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
op2 = insn.opcode.bytes[1];
switch (op1) {
+ case 0x70 ... 0x7f: /* Jcc.d8 */
+ /* See cfi_paranoid. */
+ WARN_ON_ONCE(cfi_mode != CFI_FINEIBT);
+ continue;
+
case CALL_INSN_OPCODE:
case JMP32_INSN_OPCODE:
break;
@@ -772,9 +766,9 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
len = patch_retpoline(addr, &insn, bytes);
if (len == insn.length) {
optimize_nops(addr, bytes, len);
- DUMP_BYTES(RETPOLINE, ((u8*)wr_addr), len, "%px: orig: ", addr);
+ DUMP_BYTES(RETPOLINE, ((u8*)addr), len, "%px: orig: ", addr);
DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr);
- text_poke_early(wr_addr, bytes, len);
+ text_poke_early(addr, bytes, len);
}
}
}
@@ -810,8 +804,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
return i;
}
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
- struct module *mod)
+void __init_or_module noinline apply_returns(s32 *start, s32 *end)
{
s32 *s;
@@ -820,13 +813,12 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end,
for (s = start; s < end; s++) {
void *dest = NULL, *addr = (void *)s + *s;
- void *wr_addr = module_writable_address(mod, addr);
struct insn insn;
int len, ret;
u8 bytes[16];
u8 op;
- ret = insn_decode_kernel(&insn, wr_addr);
+ ret = insn_decode_kernel(&insn, addr);
if (WARN_ON_ONCE(ret < 0))
continue;
@@ -846,41 +838,59 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end,
len = patch_return(addr, &insn, bytes);
if (len == insn.length) {
- DUMP_BYTES(RET, ((u8*)wr_addr), len, "%px: orig: ", addr);
+ DUMP_BYTES(RET, ((u8*)addr), len, "%px: orig: ", addr);
DUMP_BYTES(RET, ((u8*)bytes), len, "%px: repl: ", addr);
- text_poke_early(wr_addr, bytes, len);
+ text_poke_early(addr, bytes, len);
}
}
}
-#else
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
- struct module *mod) { }
-#endif /* CONFIG_MITIGATION_RETHUNK */
+#else /* !CONFIG_MITIGATION_RETHUNK: */
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
+#endif /* !CONFIG_MITIGATION_RETHUNK */
#else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
- struct module *mod) { }
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
- struct module *mod) { }
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
-#endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */
+#endif /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
#ifdef CONFIG_X86_KERNEL_IBT
-static void poison_cfi(void *addr, void *wr_addr);
+__noendbr bool is_endbr(u32 *val)
+{
+ u32 endbr;
+
+ __get_kernel_nofault(&endbr, val, u32, Efault);
+ return __is_endbr(endbr);
+
+Efault:
+ return false;
+}
-static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
+#ifdef CONFIG_FINEIBT
+
+static __noendbr bool exact_endbr(u32 *val)
{
- u32 endbr, poison = gen_endbr_poison();
+ u32 endbr;
- if (WARN_ON_ONCE(get_kernel_nofault(endbr, wr_addr)))
- return;
+ __get_kernel_nofault(&endbr, val, u32, Efault);
+ return endbr == gen_endbr();
+
+Efault:
+ return false;
+}
- if (!is_endbr(endbr)) {
- WARN_ON_ONCE(warn);
+#endif
+
+static void poison_cfi(void *addr);
+
+static void __init_or_module poison_endbr(void *addr)
+{
+ u32 poison = gen_endbr_poison();
+
+ if (WARN_ON_ONCE(!is_endbr(addr)))
return;
- }
DPRINTK(ENDBR, "ENDBR at: %pS (%px)", addr, addr);
@@ -889,7 +899,7 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
*/
DUMP_BYTES(ENDBR, ((u8*)addr), 4, "%px: orig: ", addr);
DUMP_BYTES(ENDBR, ((u8*)&poison), 4, "%px: repl: ", addr);
- text_poke_early(wr_addr, &poison, 4);
+ text_poke_early(addr, &poison, 4);
}
/*
@@ -898,36 +908,39 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
* Seal the functions for indirect calls by clobbering the ENDBR instructions
* and the kCFI hash value.
*/
-void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
{
s32 *s;
for (s = start; s < end; s++) {
void *addr = (void *)s + *s;
- void *wr_addr = module_writable_address(mod, addr);
- poison_endbr(addr, wr_addr, true);
+ poison_endbr(addr);
if (IS_ENABLED(CONFIG_FINEIBT))
- poison_cfi(addr - 16, wr_addr - 16);
+ poison_cfi(addr - 16);
}
}
-#else
+#else /* !CONFIG_X86_KERNEL_IBT: */
-void __init_or_module apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { }
+void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
-#endif /* CONFIG_X86_KERNEL_IBT */
+#endif /* !CONFIG_X86_KERNEL_IBT */
#ifdef CONFIG_CFI_AUTO_DEFAULT
-#define __CFI_DEFAULT CFI_AUTO
+# define __CFI_DEFAULT CFI_AUTO
#elif defined(CONFIG_CFI_CLANG)
-#define __CFI_DEFAULT CFI_KCFI
+# define __CFI_DEFAULT CFI_KCFI
#else
-#define __CFI_DEFAULT CFI_OFF
+# define __CFI_DEFAULT CFI_OFF
#endif
enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
+#ifdef CONFIG_FINEIBT_BHI
+bool cfi_bhi __ro_after_init = false;
+#endif
+
#ifdef CONFIG_CFI_CLANG
struct bpf_insn;
@@ -935,11 +948,7 @@ struct bpf_insn;
extern unsigned int __bpf_prog_runX(const void *ctx,
const struct bpf_insn *insn);
-/*
- * Force a reference to the external symbol so the compiler generates
- * __kcfi_typid.
- */
-__ADDRESSABLE(__bpf_prog_runX);
+KCFI_REFERENCE(__bpf_prog_runX);
/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
asm (
@@ -956,7 +965,7 @@ asm (
/* Must match bpf_callback_t */
extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
-__ADDRESSABLE(__bpf_callback_fn);
+KCFI_REFERENCE(__bpf_callback_fn);
/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
asm (
@@ -991,6 +1000,21 @@ u32 cfi_get_func_hash(void *func)
return hash;
}
+
+int cfi_get_func_arity(void *func)
+{
+ bhi_thunk *target;
+ s32 disp;
+
+ if (cfi_mode != CFI_FINEIBT && !cfi_bhi)
+ return 0;
+
+ if (get_kernel_nofault(disp, func - 4))
+ return 0;
+
+ target = func + disp;
+ return target - __bhi_args;
+}
#endif
#ifdef CONFIG_FINEIBT
@@ -998,6 +1022,8 @@ u32 cfi_get_func_hash(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.
@@ -1005,7 +1031,7 @@ static u32 cfi_seed __ro_after_init;
static u32 cfi_rehash(u32 hash)
{
hash ^= cfi_seed;
- while (unlikely(is_endbr(hash) || is_endbr(-hash))) {
+ while (unlikely(__is_endbr(hash) || __is_endbr(-hash))) {
bool lsb = hash & 1;
hash >>= 1;
if (lsb)
@@ -1037,6 +1063,25 @@ static __init int cfi_parse_cmdline(char *str)
cfi_mode = CFI_FINEIBT;
} else if (!strcmp(str, "norand")) {
cfi_rand = false;
+ } else if (!strcmp(str, "warn")) {
+ pr_alert("CFI mismatch non-fatal!\n");
+ cfi_warn = true;
+ } else if (!strcmp(str, "paranoid")) {
+ if (cfi_mode == CFI_FINEIBT) {
+ cfi_paranoid = true;
+ } else {
+ pr_err("Ignoring paranoid; depends on fineibt.\n");
+ }
+ } else if (!strcmp(str, "bhi")) {
+#ifdef CONFIG_FINEIBT_BHI
+ if (cfi_mode == CFI_FINEIBT) {
+ cfi_bhi = true;
+ } else {
+ pr_err("Ignoring bhi; depends on fineibt.\n");
+ }
+#else
+ pr_err("Ignoring bhi; depends on FINEIBT_BHI=y.\n");
+#endif
} else {
pr_err("Ignoring unknown cfi option (%s).", str);
}
@@ -1054,9 +1099,9 @@ early_param("cfi", cfi_parse_cmdline);
* __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 jne __cfi_\func+6 // 2
+ * nop nop3 // 3
+ * nop
* nop
* nop
* nop
@@ -1068,34 +1113,53 @@ early_param("cfi", cfi_parse_cmdline);
*
* caller: caller:
* movl $(-0x12345678),%r10d // 6 movl $0x12345678,%r10d // 6
- * addl $-15(%r11),%r10d // 4 sub $16,%r11 // 4
+ * addl $-15(%r11),%r10d // 4 lea -0x10(%r11),%r11 // 4
* je 1f // 2 nop4 // 4
* ud2 // 2
- * 1: call __x86_indirect_thunk_r11 // 5 call *%r11; nop2; // 5
+ * 1: cs call __x86_indirect_thunk_r11 // 6 call *%r11; nop3; // 6
*
*/
-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"
+/*
+ * <fineibt_preamble_start>:
+ * 0: f3 0f 1e fa endbr64
+ * 4: 41 81 <ea> 78 56 34 12 sub $0x12345678, %r10d
+ * b: 75 f9 jne 6 <fineibt_preamble_start+0x6>
+ * d: 0f 1f 00 nopl (%rax)
+ *
+ * Note that the JNE target is the 0xEA byte inside the SUB, this decodes as
+ * (bad) on x86_64 and raises #UD.
+ */
+asm( ".pushsection .rodata \n"
+ "fineibt_preamble_start: \n"
+ " endbr64 \n"
+ " subl $0x12345678, %r10d \n"
+ "fineibt_preamble_bhi: \n"
+ " jne fineibt_preamble_start+6 \n"
+ ASM_NOP3
+ "fineibt_preamble_end: \n"
".popsection\n"
);
extern u8 fineibt_preamble_start[];
+extern u8 fineibt_preamble_bhi[];
extern u8 fineibt_preamble_end[];
#define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
+#define fineibt_preamble_bhi (fineibt_preamble_bhi - fineibt_preamble_start)
+#define fineibt_preamble_ud 6
#define fineibt_preamble_hash 7
+/*
+ * <fineibt_caller_start>:
+ * 0: 41 ba 78 56 34 12 mov $0x12345678, %r10d
+ * 6: 4d 8d 5b f0 lea -0x10(%r11), %r11
+ * a: 0f 1f 40 00 nopl 0x0(%rax)
+ */
asm( ".pushsection .rodata \n"
"fineibt_caller_start: \n"
" movl $0x12345678, %r10d \n"
- " sub $16, %r11 \n"
+ " lea -0x10(%r11), %r11 \n"
ASM_NOP4
"fineibt_caller_end: \n"
".popsection \n"
@@ -1109,13 +1173,62 @@ extern u8 fineibt_caller_end[];
#define fineibt_caller_jmp (fineibt_caller_size - 2)
-static u32 decode_preamble_hash(void *addr)
+/*
+ * Since FineIBT does hash validation on the callee side it is prone to
+ * circumvention attacks where a 'naked' ENDBR instruction exists that
+ * is not part of the fineibt_preamble sequence.
+ *
+ * Notably the x86 entry points must be ENDBR and equally cannot be
+ * fineibt_preamble.
+ *
+ * The fineibt_paranoid caller sequence adds additional caller side
+ * hash validation. This stops such circumvention attacks dead, but at the cost
+ * of adding a load.
+ *
+ * <fineibt_paranoid_start>:
+ * 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: 75 fd jne d <fineibt_paranoid_start+0xd>
+ * 10: 41 ff d3 call *%r11
+ * 13: 90 nop
+ *
+ * Notably LEA does not modify flags and can be reordered with the CMP,
+ * avoiding a dependency. Again, using a non-taken (backwards) branch
+ * for the failure case, abusing LEA's immediate 0xf0 as LOCK prefix for the
+ * Jcc.d8, causing #UD.
+ */
+asm( ".pushsection .rodata \n"
+ "fineibt_paranoid_start: \n"
+ " movl $0x12345678, %r10d \n"
+ " cmpl -9(%r11), %r10d \n"
+ " lea -0x10(%r11), %r11 \n"
+ " jne fineibt_paranoid_start+0xd \n"
+ "fineibt_paranoid_ind: \n"
+ " call *%r11 \n"
+ " nop \n"
+ "fineibt_paranoid_end: \n"
+ ".popsection \n"
+);
+
+extern u8 fineibt_paranoid_start[];
+extern u8 fineibt_paranoid_ind[];
+extern u8 fineibt_paranoid_end[];
+
+#define fineibt_paranoid_size (fineibt_paranoid_end - fineibt_paranoid_start)
+#define fineibt_paranoid_ind (fineibt_paranoid_ind - fineibt_paranoid_start)
+#define fineibt_paranoid_ud 0xd
+
+static u32 decode_preamble_hash(void *addr, int *reg)
{
u8 *p = addr;
- /* b8 78 56 34 12 mov $0x12345678,%eax */
- if (p[0] == 0xb8)
+ /* b8+reg 78 56 34 12 movl $0x12345678,\reg */
+ if (p[0] >= 0xb8 && p[0] < 0xc0) {
+ if (reg)
+ *reg = p[0] - 0xb8;
return *(u32 *)(addr + 1);
+ }
return 0; /* invalid hash value */
}
@@ -1124,11 +1237,11 @@ static u32 decode_caller_hash(void *addr)
{
u8 *p = addr;
- /* 41 ba 78 56 34 12 mov $0x12345678,%r10d */
+ /* 41 ba 88 a9 cb ed mov $(-0x12345678),%r10d */
if (p[0] == 0x41 && p[1] == 0xba)
return -*(u32 *)(addr + 2);
- /* e8 0c 78 56 34 12 jmp.d8 +12 */
+ /* e8 0c 88 a9 cb ed jmp.d8 +12 */
if (p[0] == JMP8_INSN_OPCODE && p[1] == fineibt_caller_jmp)
return -*(u32 *)(addr + 2);
@@ -1136,7 +1249,7 @@ static u32 decode_caller_hash(void *addr)
}
/* .retpoline_sites */
-static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_disable_callers(s32 *start, s32 *end)
{
/*
* Disable kCFI by patching in a JMP.d8, this leaves the hash immediate
@@ -1148,23 +1261,20 @@ static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
for (s = start; s < end; s++) {
void *addr = (void *)s + *s;
- void *wr_addr;
u32 hash;
addr -= fineibt_caller_size;
- wr_addr = module_writable_address(mod, addr);
- hash = decode_caller_hash(wr_addr);
-
+ hash = decode_caller_hash(addr);
if (!hash) /* nocfi callers */
continue;
- text_poke_early(wr_addr, jmp, 2);
+ text_poke_early(addr, jmp, 2);
}
return 0;
}
-static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_enable_callers(s32 *start, s32 *end)
{
/*
* Re-enable kCFI, undo what cfi_disable_callers() did.
@@ -1174,126 +1284,212 @@ static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
for (s = start; s < end; s++) {
void *addr = (void *)s + *s;
- void *wr_addr;
u32 hash;
addr -= fineibt_caller_size;
- wr_addr = module_writable_address(mod, addr);
- hash = decode_caller_hash(wr_addr);
+ hash = decode_caller_hash(addr);
if (!hash) /* nocfi callers */
continue;
- text_poke_early(wr_addr, mov, 2);
+ text_poke_early(addr, mov, 2);
}
return 0;
}
/* .cfi_sites */
-static int cfi_rand_preamble(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_preamble(s32 *start, s32 *end)
{
s32 *s;
for (s = start; s < end; s++) {
void *addr = (void *)s + *s;
- void *wr_addr = module_writable_address(mod, addr);
u32 hash;
- hash = decode_preamble_hash(wr_addr);
+ hash = decode_preamble_hash(addr, NULL);
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(wr_addr + 1, &hash, 4);
+ text_poke_early(addr + 1, &hash, 4);
}
return 0;
}
-static int cfi_rewrite_preamble(s32 *start, s32 *end, struct module *mod)
+static void cfi_fineibt_bhi_preamble(void *addr, int arity)
+{
+ if (!arity)
+ return;
+
+ if (!cfi_warn && arity == 1) {
+ /*
+ * Crazy scheme to allow arity-1 inline:
+ *
+ * __cfi_foo:
+ * 0: f3 0f 1e fa endbr64
+ * 4: 41 81 <ea> 78 56 34 12 sub 0x12345678, %r10d
+ * b: 49 0f 45 fa cmovne %r10, %rdi
+ * f: 75 f5 jne __cfi_foo+6
+ * 11: 0f 1f 00 nopl (%rax)
+ *
+ * Code that direct calls to foo()+0, decodes the tail end as:
+ *
+ * foo:
+ * 0: f5 cmc
+ * 1: 0f 1f 00 nopl (%rax)
+ *
+ * which clobbers CF, but does not affect anything ABI
+ * wise.
+ *
+ * Notably, this scheme is incompatible with permissive CFI
+ * because the CMOVcc is unconditional and RDI will have been
+ * clobbered.
+ */
+ const u8 magic[9] = {
+ 0x49, 0x0f, 0x45, 0xfa,
+ 0x75, 0xf5,
+ BYTES_NOP3,
+ };
+
+ text_poke_early(addr + fineibt_preamble_bhi, magic, 9);
+
+ return;
+ }
+
+ text_poke_early(addr + fineibt_preamble_bhi,
+ text_gen_insn(CALL_INSN_OPCODE,
+ addr + fineibt_preamble_bhi,
+ __bhi_args[arity]),
+ CALL_INSN_SIZE);
+}
+
+static int cfi_rewrite_preamble(s32 *start, s32 *end)
{
s32 *s;
for (s = start; s < end; s++) {
void *addr = (void *)s + *s;
- void *wr_addr = module_writable_address(mod, addr);
+ int arity;
u32 hash;
- hash = decode_preamble_hash(wr_addr);
+ /*
+ * When the function doesn't start with ENDBR the compiler will
+ * have determined there are no indirect calls to it and we
+ * don't need no CFI either.
+ */
+ if (!is_endbr(addr + 16))
+ continue;
+
+ hash = decode_preamble_hash(addr, &arity);
if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
addr, addr, 5, addr))
return -EINVAL;
- text_poke_early(wr_addr, fineibt_preamble_start, fineibt_preamble_size);
- WARN_ON(*(u32 *)(wr_addr + fineibt_preamble_hash) != 0x12345678);
- text_poke_early(wr_addr + fineibt_preamble_hash, &hash, 4);
+ 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);
+
+ WARN_ONCE(!IS_ENABLED(CONFIG_FINEIBT_BHI) && arity,
+ "kCFI preamble has wrong register at: %pS %*ph\n",
+ addr, 5, addr);
+
+ if (cfi_bhi)
+ cfi_fineibt_bhi_preamble(addr, arity);
}
return 0;
}
-static void cfi_rewrite_endbr(s32 *start, s32 *end, struct module *mod)
+static void cfi_rewrite_endbr(s32 *start, s32 *end)
{
s32 *s;
for (s = start; s < end; s++) {
void *addr = (void *)s + *s;
- void *wr_addr = module_writable_address(mod, addr);
- poison_endbr(addr + 16, wr_addr + 16, false);
+ if (!exact_endbr(addr + 16))
+ continue;
+
+ poison_endbr(addr + 16);
}
}
/* .retpoline_sites */
-static int cfi_rand_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_callers(s32 *start, s32 *end)
{
s32 *s;
for (s = start; s < end; s++) {
void *addr = (void *)s + *s;
- void *wr_addr;
u32 hash;
addr -= fineibt_caller_size;
- wr_addr = module_writable_address(mod, addr);
- hash = decode_caller_hash(wr_addr);
+ hash = decode_caller_hash(addr);
if (hash) {
hash = -cfi_rehash(hash);
- text_poke_early(wr_addr + 2, &hash, 4);
+ text_poke_early(addr + 2, &hash, 4);
}
}
return 0;
}
-static int cfi_rewrite_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_rewrite_callers(s32 *start, s32 *end)
{
s32 *s;
+ BUG_ON(fineibt_paranoid_size != 20);
+
for (s = start; s < end; s++) {
void *addr = (void *)s + *s;
- void *wr_addr;
+ struct insn insn;
+ u8 bytes[20];
u32 hash;
+ int ret;
+ u8 op;
addr -= fineibt_caller_size;
- wr_addr = module_writable_address(mod, addr);
- hash = decode_caller_hash(wr_addr);
- if (hash) {
- text_poke_early(wr_addr, fineibt_caller_start, fineibt_caller_size);
- WARN_ON(*(u32 *)(wr_addr + fineibt_caller_hash) != 0x12345678);
- text_poke_early(wr_addr + fineibt_caller_hash, &hash, 4);
+ hash = decode_caller_hash(addr);
+ if (!hash)
+ continue;
+
+ if (!cfi_paranoid) {
+ 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() */
+ continue;
+ }
+
+ /* cfi_paranoid */
+ ret = insn_decode_kernel(&insn, addr + fineibt_caller_size);
+ if (WARN_ON_ONCE(ret < 0))
+ continue;
+
+ op = insn.opcode.bytes[0];
+ if (op != CALL_INSN_OPCODE && op != JMP32_INSN_OPCODE) {
+ WARN_ON_ONCE(1);
+ continue;
}
- /* rely on apply_retpolines() */
+
+ 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;
+
+ text_poke_early(addr, bytes, fineibt_paranoid_size);
}
return 0;
}
static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
- s32 *start_cfi, s32 *end_cfi, struct module *mod)
+ s32 *start_cfi, s32 *end_cfi, bool builtin)
{
- bool builtin = mod ? false : true;
int ret;
if (WARN_ONCE(fineibt_preamble_size != 16,
@@ -1302,8 +1498,15 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
if (cfi_mode == CFI_AUTO) {
cfi_mode = CFI_KCFI;
- if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
+ if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT)) {
+ /*
+ * FRED has much saner context on exception entry and
+ * is less easy to take advantage of.
+ */
+ if (!cpu_feature_enabled(X86_FEATURE_FRED))
+ cfi_paranoid = true;
cfi_mode = CFI_FINEIBT;
+ }
}
/*
@@ -1311,7 +1514,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
* 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, mod);
+ ret = cfi_disable_callers(start_retpoline, end_retpoline);
if (ret)
goto err;
@@ -1322,11 +1525,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash);
}
- ret = cfi_rand_preamble(start_cfi, end_cfi, mod);
+ ret = cfi_rand_preamble(start_cfi, end_cfi);
if (ret)
goto err;
- ret = cfi_rand_callers(start_retpoline, end_retpoline, mod);
+ ret = cfi_rand_callers(start_retpoline, end_retpoline);
if (ret)
goto err;
}
@@ -1338,7 +1541,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
return;
case CFI_KCFI:
- ret = cfi_enable_callers(start_retpoline, end_retpoline, mod);
+ ret = cfi_enable_callers(start_retpoline, end_retpoline);
if (ret)
goto err;
@@ -1348,20 +1551,23 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
case CFI_FINEIBT:
/* place the FineIBT preamble at func()-16 */
- ret = cfi_rewrite_preamble(start_cfi, end_cfi, mod);
+ ret = cfi_rewrite_preamble(start_cfi, end_cfi);
if (ret)
goto err;
/* rewrite the callers to target func()-16 */
- ret = cfi_rewrite_callers(start_retpoline, end_retpoline, mod);
+ ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
if (ret)
goto err;
/* now that nobody targets func()+0, remove ENDBR there */
- cfi_rewrite_endbr(start_cfi, end_cfi, mod);
+ cfi_rewrite_endbr(start_cfi, end_cfi);
- if (builtin)
- pr_info("Using FineIBT CFI\n");
+ if (builtin) {
+ pr_info("Using %sFineIBT%s CFI\n",
+ cfi_paranoid ? "paranoid " : "",
+ cfi_bhi ? "+BHI" : "");
+ }
return;
default:
@@ -1377,11 +1583,25 @@ static inline void poison_hash(void *addr)
*(u32 *)addr = 0;
}
-static void poison_cfi(void *addr, void *wr_addr)
+static void poison_cfi(void *addr)
{
+ /*
+ * Compilers manage to be inconsistent with ENDBR vs __cfi prefixes,
+ * some (static) functions for which they can determine the address
+ * is never taken do not get a __cfi prefix, but *DO* get an ENDBR.
+ *
+ * As such, these functions will get sealed, but we need to be careful
+ * to not unconditionally scribble the previous function.
+ */
switch (cfi_mode) {
case CFI_FINEIBT:
/*
+ * FineIBT prefix should start with an ENDBR.
+ */
+ if (!is_endbr(addr))
+ break;
+
+ /*
* __cfi_\func:
* osp nopl (%rax)
* subl $0, %r10d
@@ -1389,17 +1609,23 @@ static void poison_cfi(void *addr, void *wr_addr)
* ud2
* 1: nop
*/
- poison_endbr(addr, wr_addr, false);
- poison_hash(wr_addr + fineibt_preamble_hash);
+ poison_endbr(addr);
+ poison_hash(addr + fineibt_preamble_hash);
break;
case CFI_KCFI:
/*
+ * kCFI prefix should start with a valid hash.
+ */
+ if (!decode_preamble_hash(addr, NULL))
+ break;
+
+ /*
* __cfi_\func:
* movl $0, %eax
* .skip 11, 0x90
*/
- poison_hash(wr_addr + 1);
+ poison_hash(addr + 1);
break;
default:
@@ -1407,24 +1633,135 @@ static void poison_cfi(void *addr, void *wr_addr)
}
}
-#else
+/*
+ * When regs->ip points to a 0xEA byte in the FineIBT preamble,
+ * return true and fill out target and type.
+ *
+ * We check the preamble by checking for the ENDBR instruction relative to the
+ * 0xEA instruction.
+ */
+static bool decode_fineibt_preamble(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+ unsigned long addr = regs->ip - fineibt_preamble_ud;
+ u32 hash;
+
+ if (!exact_endbr((void *)addr))
+ return false;
+
+ *target = addr + fineibt_preamble_size;
+
+ __get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
+ *type = (u32)regs->r10 + hash;
+
+ /*
+ * Since regs->ip points to the middle of an instruction; it cannot
+ * continue with the normal fixup.
+ */
+ regs->ip = *target;
+
+ return true;
+
+Efault:
+ return false;
+}
+
+/*
+ * regs->ip points to one of the UD2 in __bhi_args[].
+ */
+static bool decode_fineibt_bhi(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+ unsigned long addr;
+ u32 hash;
+
+ if (!cfi_bhi)
+ return false;
+
+ if (regs->ip < (unsigned long)__bhi_args ||
+ regs->ip >= (unsigned long)__bhi_args_end)
+ return false;
+
+ /*
+ * Fetch the return address from the stack, this points to the
+ * FineIBT preamble. Since the CALL instruction is in the 5 last
+ * bytes of the preamble, the return address is in fact the target
+ * address.
+ */
+ __get_kernel_nofault(&addr, regs->sp, unsigned long, Efault);
+ *target = addr;
+
+ addr -= fineibt_preamble_size;
+ if (!exact_endbr((void *)addr))
+ return false;
+
+ __get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
+ *type = (u32)regs->r10 + hash;
+
+ /*
+ * The UD2 sites are constructed with a RET immediately following,
+ * as such the non-fatal case can use the regular fixup.
+ */
+ return true;
+
+Efault:
+ return false;
+}
+
+/*
+ * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[]
+ * sequence.
+ */
+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))
+ return false;
+
+ __get_kernel_nofault(&hash, addr + fineibt_caller_hash, u32, Efault);
+ *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;
+
+Efault:
+ return false;
+}
+
+bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+ if (decode_fineibt_paranoid(regs, target, type))
+ return true;
+
+ if (decode_fineibt_bhi(regs, target, type))
+ return true;
+
+ return decode_fineibt_preamble(regs, target, type);
+}
+
+#else /* !CONFIG_FINEIBT: */
static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
- s32 *start_cfi, s32 *end_cfi, struct module *mod)
+ s32 *start_cfi, s32 *end_cfi, bool builtin)
{
}
#ifdef CONFIG_X86_KERNEL_IBT
-static void poison_cfi(void *addr, void *wr_addr) { }
+static void poison_cfi(void *addr) { }
#endif
-#endif
+#endif /* !CONFIG_FINEIBT */
void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
- s32 *start_cfi, s32 *end_cfi, struct module *mod)
+ s32 *start_cfi, s32 *end_cfi)
{
return __apply_fineibt(start_retpoline, end_retpoline,
- start_cfi, end_cfi, mod);
+ start_cfi, end_cfi,
+ /* .builtin = */ false);
}
#ifdef CONFIG_SMP
@@ -1721,27 +2058,27 @@ void __init alternative_instructions(void)
paravirt_set_cap();
__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
- __cfi_sites, __cfi_sites_end, NULL);
+ __cfi_sites, __cfi_sites_end, true);
/*
* Rewrite the retpolines, must be done before alternatives since
* those can rewrite the retpoline thunks.
*/
- apply_retpolines(__retpoline_sites, __retpoline_sites_end, NULL);
- apply_returns(__return_sites, __return_sites_end, NULL);
-
- apply_alternatives(__alt_instructions, __alt_instructions_end, NULL);
+ apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+ apply_returns(__return_sites, __return_sites_end);
/*
- * Now all calls are established. Apply the call thunks if
- * required.
+ * Adjust all CALL instructions to point to func()-10, including
+ * those in .altinstr_replacement.
*/
callthunks_patch_builtin_calls();
+ apply_alternatives(__alt_instructions, __alt_instructions_end);
+
/*
* Seal all functions that do not have their address taken.
*/
- apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end, NULL);
+ apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
#ifdef CONFIG_SMP
/* Patch to UP if other cpus not imminent. */
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 5da693d633b7..23025a3a1db4 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -287,34 +287,4 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
__default_send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL);
local_irq_restore(flags);
}
-
-#ifdef CONFIG_SMP
-static int convert_apicid_to_cpu(u32 apic_id)
-{
- int i;
-
- for_each_possible_cpu(i) {
- if (per_cpu(x86_cpu_to_apicid, i) == apic_id)
- return i;
- }
- return -1;
-}
-
-int safe_smp_processor_id(void)
-{
- u32 apicid;
- int cpuid;
-
- if (!boot_cpu_has(X86_FEATURE_APIC))
- return 0;
-
- apicid = read_apic_id();
- if (apicid == BAD_APICID)
- return 0;
-
- cpuid = convert_apicid_to_cpu(apicid);
-
- return cpuid >= 0 ? cpuid : 0;
-}
-#endif
#endif
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 8418a892d195..25ae54250112 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -240,21 +240,10 @@ patch_call_sites(s32 *start, s32 *end, const struct core_text *ct)
}
static __init_or_module void
-patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end,
- const struct core_text *ct)
-{
- struct alt_instr *a;
-
- for (a = start; a < end; a++)
- patch_call((void *)&a->instr_offset + a->instr_offset, 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_alt_call_sites(cs->alt_start, cs->alt_end, ct);
prdbg("Patching call sites done%s\n", ct->name);
}
@@ -263,8 +252,6 @@ void __init callthunks_patch_builtin_calls(void)
struct callthunk_sites cs = {
.call_start = __call_sites,
.call_end = __call_sites_end,
- .alt_start = __alt_instructions,
- .alt_end = __alt_instructions_end
};
if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
index e6bf78fac146..77086cf565ec 100644
--- a/arch/x86/kernel/cfi.c
+++ b/arch/x86/kernel/cfi.c
@@ -67,16 +67,30 @@ static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target,
*/
enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
{
- unsigned long target;
+ unsigned long target, addr = regs->ip;
u32 type;
- if (!is_cfi_trap(regs->ip))
- return BUG_TRAP_TYPE_NONE;
+ switch (cfi_mode) {
+ case CFI_KCFI:
+ if (!is_cfi_trap(addr))
+ return BUG_TRAP_TYPE_NONE;
+
+ if (!decode_cfi_insn(regs, &target, &type))
+ return report_cfi_failure_noaddr(regs, addr);
+
+ break;
- if (!decode_cfi_insn(regs, &target, &type))
- return report_cfi_failure_noaddr(regs, regs->ip);
+ case CFI_FINEIBT:
+ if (!decode_fineibt_insn(regs, &target, &type))
+ return BUG_TRAP_TYPE_NONE;
+
+ break;
+
+ default:
+ return BUG_TRAP_TYPE_NONE;
+ }
- return report_cfi_failure(regs, regs->ip, &target, type);
+ return report_cfi_failure(regs, addr, &target, type);
}
/*
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 340af8155658..0be61c45400c 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -140,7 +140,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
x86_platform.guest.enc_kexec_begin();
x86_platform.guest.enc_kexec_finish();
- crash_save_cpu(regs, safe_smp_processor_id());
+ crash_save_cpu(regs, smp_processor_id());
}
#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG)
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 44f937015e1e..fc1714bad045 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -19,6 +19,7 @@
#include <linux/usb/ehci_def.h>
#include <linux/usb/xhci-dbgp.h>
#include <asm/pci_x86.h>
+#include <linux/static_call.h>
/* Simple VGA output */
#define VGABASE (__ISA_IO_base + 0xb8000)
@@ -94,26 +95,28 @@ static unsigned long early_serial_base = 0x3f8; /* ttyS0 */
#define DLL 0 /* Divisor Latch Low */
#define DLH 1 /* Divisor latch High */
-static unsigned int io_serial_in(unsigned long addr, int offset)
+static __noendbr unsigned int io_serial_in(unsigned long addr, int offset)
{
return inb(addr + offset);
}
+ANNOTATE_NOENDBR_SYM(io_serial_in);
-static void io_serial_out(unsigned long addr, int offset, int value)
+static __noendbr void io_serial_out(unsigned long addr, int offset, int value)
{
outb(value, addr + offset);
}
+ANNOTATE_NOENDBR_SYM(io_serial_out);
-static unsigned int (*serial_in)(unsigned long addr, int offset) = io_serial_in;
-static void (*serial_out)(unsigned long addr, int offset, int value) = io_serial_out;
+DEFINE_STATIC_CALL(serial_in, io_serial_in);
+DEFINE_STATIC_CALL(serial_out, io_serial_out);
static int early_serial_putc(unsigned char ch)
{
unsigned timeout = 0xffff;
- while ((serial_in(early_serial_base, LSR) & XMTRDY) == 0 && --timeout)
+ while ((static_call(serial_in)(early_serial_base, LSR) & XMTRDY) == 0 && --timeout)
cpu_relax();
- serial_out(early_serial_base, TXR, ch);
+ static_call(serial_out)(early_serial_base, TXR, ch);
return timeout ? 0 : -1;
}
@@ -131,16 +134,16 @@ static __init void early_serial_hw_init(unsigned divisor)
{
unsigned char c;
- serial_out(early_serial_base, LCR, 0x3); /* 8n1 */
- serial_out(early_serial_base, IER, 0); /* no interrupt */
- serial_out(early_serial_base, FCR, 0); /* no fifo */
- serial_out(early_serial_base, MCR, 0x3); /* DTR + RTS */
+ static_call(serial_out)(early_serial_base, LCR, 0x3); /* 8n1 */
+ static_call(serial_out)(early_serial_base, IER, 0); /* no interrupt */
+ static_call(serial_out)(early_serial_base, FCR, 0); /* no fifo */
+ static_call(serial_out)(early_serial_base, MCR, 0x3); /* DTR + RTS */
- c = serial_in(early_serial_base, LCR);
- serial_out(early_serial_base, LCR, c | DLAB);
- serial_out(early_serial_base, DLL, divisor & 0xff);
- serial_out(early_serial_base, DLH, (divisor >> 8) & 0xff);
- serial_out(early_serial_base, LCR, c & ~DLAB);
+ c = static_call(serial_in)(early_serial_base, LCR);
+ static_call(serial_out)(early_serial_base, LCR, c | DLAB);
+ static_call(serial_out)(early_serial_base, DLL, divisor & 0xff);
+ static_call(serial_out)(early_serial_base, DLH, (divisor >> 8) & 0xff);
+ static_call(serial_out)(early_serial_base, LCR, c & ~DLAB);
}
#define DEFAULT_BAUD 9600
@@ -183,28 +186,26 @@ static __init void early_serial_init(char *s)
/* Convert from baud to divisor value */
divisor = 115200 / baud;
- /* These will always be IO based ports */
- serial_in = io_serial_in;
- serial_out = io_serial_out;
-
/* Set up the HW */
early_serial_hw_init(divisor);
}
#ifdef CONFIG_PCI
-static void mem32_serial_out(unsigned long addr, int offset, int value)
+static __noendbr void mem32_serial_out(unsigned long addr, int offset, int value)
{
u32 __iomem *vaddr = (u32 __iomem *)addr;
/* shift implied by pointer type */
writel(value, vaddr + offset);
}
+ANNOTATE_NOENDBR_SYM(mem32_serial_out);
-static unsigned int mem32_serial_in(unsigned long addr, int offset)
+static __noendbr unsigned int mem32_serial_in(unsigned long addr, int offset)
{
u32 __iomem *vaddr = (u32 __iomem *)addr;
/* shift implied by pointer type */
return readl(vaddr + offset);
}
+ANNOTATE_NOENDBR_SYM(mem32_serial_in);
/*
* early_pci_serial_init()
@@ -278,15 +279,13 @@ static __init void early_pci_serial_init(char *s)
*/
if ((bar0 & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
/* it is IO mapped */
- serial_in = io_serial_in;
- serial_out = io_serial_out;
early_serial_base = bar0 & PCI_BASE_ADDRESS_IO_MASK;
write_pci_config(bus, slot, func, PCI_COMMAND,
cmdreg|PCI_COMMAND_IO);
} else {
/* It is memory mapped - assume 32-bit alignment */
- serial_in = mem32_serial_in;
- serial_out = mem32_serial_out;
+ static_call_update(serial_in, mem32_serial_in);
+ static_call_update(serial_out, mem32_serial_out);
/* WARNING! assuming the address is always in the first 4G */
early_serial_base =
(unsigned long)early_ioremap(bar0 & PCI_BASE_ADDRESS_MEM_MASK, 0x10);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 166bc0ea3bdf..cace6e8d7cc7 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -118,13 +118,10 @@ ftrace_modify_code_direct(unsigned long ip, const char *old_code,
return ret;
/* replace the text with the new text */
- if (ftrace_poke_late) {
+ if (ftrace_poke_late)
text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
- } else {
- mutex_lock(&text_mutex);
- text_poke((void *)ip, new_code, MCOUNT_INSN_SIZE);
- mutex_unlock(&text_mutex);
- }
+ else
+ text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
return 0;
}
@@ -321,7 +318,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
union ftrace_op_code_union op_ptr;
- void *ret;
+ int ret;
if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
start_offset = (unsigned long)ftrace_regs_caller;
@@ -352,15 +349,15 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
/* Copy ftrace_caller onto the trampoline memory */
- ret = text_poke_copy(trampoline, (void *)start_offset, size);
- if (WARN_ON(!ret))
+ ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
+ if (WARN_ON(ret < 0))
goto fail;
ip = trampoline + size;
if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
else
- text_poke_copy(ip, retq, sizeof(retq));
+ memcpy(ip, retq, sizeof(retq));
/* No need to test direct calls on created trampolines */
if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
@@ -368,7 +365,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
ip = trampoline + (jmp_offset - start_offset);
if (WARN_ON(*(char *)ip != 0x75))
goto fail;
- if (!text_poke_copy(ip, x86_nops[2], 2))
+ ret = copy_from_kernel_nofault(ip, x86_nops[2], 2);
+ if (ret < 0)
goto fail;
}
@@ -381,7 +379,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
*/
ptr = (unsigned long *)(trampoline + size + RET_SIZE);
- text_poke_copy(ptr, &ops, sizeof(unsigned long));
+ *ptr = (unsigned long)ops;
op_offset -= start_offset;
memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
@@ -397,7 +395,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
op_ptr.offset = offset;
/* put in the new offset to the ftrace_ops */
- text_poke_copy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
+ memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
/* put in the call to the function */
mutex_lock(&text_mutex);
@@ -407,9 +405,9 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
* the depth accounting before the call already.
*/
dest = ftrace_ops_get_func(ops);
- text_poke_copy_locked(trampoline + call_offset,
- text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
- CALL_INSN_SIZE, false);
+ memcpy(trampoline + call_offset,
+ 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 */
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index d51647228596..367da3638167 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -146,12 +146,14 @@ SYM_FUNC_END(ftrace_stub_graph)
#ifdef CONFIG_DYNAMIC_FTRACE
SYM_FUNC_START(__fentry__)
+ ANNOTATE_NOENDBR
CALL_DEPTH_ACCOUNT
RET
SYM_FUNC_END(__fentry__)
EXPORT_SYMBOL(__fentry__)
SYM_FUNC_START(ftrace_caller)
+ ANNOTATE_NOENDBR
/* save_mcount_regs fills in first two parameters */
save_mcount_regs
@@ -197,6 +199,7 @@ SYM_FUNC_END(ftrace_caller);
STACK_FRAME_NON_STANDARD_FP(ftrace_caller)
SYM_FUNC_START(ftrace_regs_caller)
+ ANNOTATE_NOENDBR
/* Save the current flags before any operations that can change them */
pushfq
@@ -310,6 +313,7 @@ SYM_FUNC_END(ftrace_regs_caller)
STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
SYM_FUNC_START(ftrace_stub_direct_tramp)
+ ANNOTATE_NOENDBR
CALL_DEPTH_ACCOUNT
RET
SYM_FUNC_END(ftrace_stub_direct_tramp)
@@ -317,6 +321,7 @@ SYM_FUNC_END(ftrace_stub_direct_tramp)
#else /* ! CONFIG_DYNAMIC_FTRACE */
SYM_FUNC_START(__fentry__)
+ ANNOTATE_NOENDBR
CALL_DEPTH_ACCOUNT
cmpq $ftrace_stub, ftrace_trace_function
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index 7f542a7799cb..fdabd5dda154 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -9,6 +9,7 @@
*/
.pushsection .noinstr.text, "ax"
SYM_FUNC_START(native_save_fl)
+ ENDBR
pushf
pop %_ASM_AX
RET
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 72e6a45e7ec2..09608fd93687 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -373,16 +373,7 @@ out:
kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
bool *on_func_entry)
{
- u32 insn;
-
- /*
- * Since 'addr' is not guaranteed to be safe to access, use
- * copy_from_kernel_nofault() to read the instruction:
- */
- if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32)))
- return NULL;
-
- if (is_endbr(insn)) {
+ if (is_endbr((u32 *)addr)) {
*on_func_entry = !offset || offset == 4;
if (*on_func_entry)
offset = 4;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 8984abd91c00..615f74c4bd6c 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -146,21 +146,18 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
}
if (apply) {
- void *wr_loc = module_writable_address(me, loc);
-
- if (memcmp(wr_loc, &zero, size)) {
+ if (memcmp(loc, &zero, size)) {
pr_err("x86/modules: Invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), loc, val);
return -ENOEXEC;
}
- write(wr_loc, &val, size);
+ write(loc, &val, size);
} else {
if (memcmp(loc, &val, size)) {
pr_warn("x86/modules: Invalid relocation target, existing value does not match expected value for type %d, loc %p, val %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), loc, val);
return -ENOEXEC;
}
- /* FIXME: needs care for ROX module allocations */
write(loc, &zero, size);
}
}
@@ -227,7 +224,7 @@ int module_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *me)
{
- const Elf_Shdr *s, *alt = NULL,
+ const Elf_Shdr *s, *alt = NULL, *locks = NULL,
*orc = NULL, *orc_ip = NULL,
*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
*calls = NULL, *cfi = NULL;
@@ -236,6 +233,8 @@ int module_finalize(const Elf_Ehdr *hdr,
for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
if (!strcmp(".altinstructions", secstrings + s->sh_name))
alt = s;
+ if (!strcmp(".smp_locks", secstrings + s->sh_name))
+ locks = s;
if (!strcmp(".orc_unwind", secstrings + s->sh_name))
orc = s;
if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
@@ -266,60 +265,33 @@ int module_finalize(const Elf_Ehdr *hdr,
csize = cfi->sh_size;
}
- apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize, me);
+ apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize);
}
if (retpolines) {
void *rseg = (void *)retpolines->sh_addr;
- apply_retpolines(rseg, rseg + retpolines->sh_size, me);
+ apply_retpolines(rseg, rseg + retpolines->sh_size);
}
if (returns) {
void *rseg = (void *)returns->sh_addr;
- apply_returns(rseg, rseg + returns->sh_size, me);
+ apply_returns(rseg, rseg + returns->sh_size);
}
- if (alt) {
- /* patch .altinstructions */
- void *aseg = (void *)alt->sh_addr;
- apply_alternatives(aseg, aseg + alt->sh_size, me);
- }
- if (calls || alt) {
+ if (calls) {
struct callthunk_sites cs = {};
- if (calls) {
- cs.call_start = (void *)calls->sh_addr;
- cs.call_end = (void *)calls->sh_addr + calls->sh_size;
- }
-
- if (alt) {
- cs.alt_start = (void *)alt->sh_addr;
- cs.alt_end = (void *)alt->sh_addr + alt->sh_size;
- }
+ cs.call_start = (void *)calls->sh_addr;
+ cs.call_end = (void *)calls->sh_addr + calls->sh_size;
callthunks_patch_module_calls(&cs, me);
}
+ if (alt) {
+ /* patch .altinstructions */
+ void *aseg = (void *)alt->sh_addr;
+ apply_alternatives(aseg, aseg + alt->sh_size);
+ }
if (ibt_endbr) {
void *iseg = (void *)ibt_endbr->sh_addr;
- apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size, me);
- }
-
- if (orc && orc_ip)
- unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
- (void *)orc->sh_addr, orc->sh_size);
-
- return 0;
-}
-
-int module_post_finalize(const Elf_Ehdr *hdr,
- const Elf_Shdr *sechdrs,
- struct module *me)
-{
- const Elf_Shdr *s, *locks = NULL;
- char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
-
- for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
- if (!strcmp(".smp_locks", secstrings + s->sh_name))
- locks = s;
+ apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size);
}
-
if (locks) {
void *lseg = (void *)locks->sh_addr;
void *text = me->mem[MOD_TEXT].base;
@@ -329,6 +301,10 @@ int module_post_finalize(const Elf_Ehdr *hdr,
text, text_end);
}
+ if (orc && orc_ip)
+ unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
+ (void *)orc->sh_addr, orc->sh_size);
+
return 0;
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index ed163c8c8604..9a95d00f1423 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -40,8 +40,12 @@
#define CREATE_TRACE_POINTS
#include <trace/events/nmi.h>
+/*
+ * An emergency handler can be set in any context including NMI
+ */
struct nmi_desc {
raw_spinlock_t lock;
+ nmi_handler_t emerg_handler;
struct list_head head;
};
@@ -132,9 +136,22 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration)
static int nmi_handle(unsigned int type, struct pt_regs *regs)
{
struct nmi_desc *desc = nmi_to_desc(type);
+ nmi_handler_t ehandler;
struct nmiaction *a;
int handled=0;
+ /*
+ * Call the emergency handler, if set
+ *
+ * In the case of crash_nmi_callback() emergency handler, it will
+ * return in the case of the crashing CPU to enable it to complete
+ * other necessary crashing actions ASAP. Other handlers in the
+ * linked list won't need to be run.
+ */
+ ehandler = desc->emerg_handler;
+ if (ehandler)
+ return ehandler(type, regs);
+
rcu_read_lock();
/*
@@ -224,6 +241,31 @@ void unregister_nmi_handler(unsigned int type, const char *name)
}
EXPORT_SYMBOL_GPL(unregister_nmi_handler);
+/**
+ * set_emergency_nmi_handler - Set emergency handler
+ * @type: NMI type
+ * @handler: the emergency handler to be stored
+ *
+ * Set an emergency NMI handler which, if set, will preempt all the other
+ * handlers in the linked list. If a NULL handler is passed in, it will clear
+ * it. It is expected that concurrent calls to this function will not happen
+ * or the system is screwed beyond repair.
+ */
+void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler)
+{
+ struct nmi_desc *desc = nmi_to_desc(type);
+
+ if (WARN_ON_ONCE(desc->emerg_handler == handler))
+ return;
+ desc->emerg_handler = handler;
+
+ /*
+ * Ensure the emergency handler is visible to other CPUs before
+ * function return
+ */
+ smp_wmb();
+}
+
static void
pci_serr_error(unsigned char reason, struct pt_regs *regs)
{
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1ccaa3397a67..d0b789d04245 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -90,30 +90,20 @@ void paravirt_set_sched_clock(u64 (*func)(void))
static_call_update(pv_sched_clock, func);
}
-/* These are in entry.S */
-static struct resource reserve_ioports = {
- .start = 0,
- .end = IO_SPACE_LIMIT,
- .name = "paravirt-ioport",
- .flags = IORESOURCE_IO | IORESOURCE_BUSY,
-};
+#ifdef CONFIG_PARAVIRT_XXL
+static noinstr void pv_native_write_cr2(unsigned long val)
+{
+ native_write_cr2(val);
+}
-/*
- * Reserve the whole legacy IO space to prevent any legacy drivers
- * from wasting time probing for their hardware. This is a fairly
- * brute-force approach to disabling all non-virtual drivers.
- *
- * Note that this must be called very early to have any effect.
- */
-int paravirt_disable_iospace(void)
+static noinstr unsigned long pv_native_read_cr3(void)
{
- return request_resource(&ioport_resource, &reserve_ioports);
+ return __native_read_cr3();
}
-#ifdef CONFIG_PARAVIRT_XXL
-static noinstr void pv_native_write_cr2(unsigned long val)
+static noinstr void pv_native_write_cr3(unsigned long cr3)
{
- native_write_cr2(val);
+ native_write_cr3(cr3);
}
static noinstr unsigned long pv_native_get_debugreg(int regno)
@@ -203,8 +193,8 @@ struct paravirt_patch_template pv_ops = {
#ifdef CONFIG_PARAVIRT_XXL
.mmu.read_cr2 = __PV_IS_CALLEE_SAVE(pv_native_read_cr2),
.mmu.write_cr2 = pv_native_write_cr2,
- .mmu.read_cr3 = __native_read_cr3,
- .mmu.write_cr3 = native_write_cr3,
+ .mmu.read_cr3 = pv_native_read_cr3,
+ .mmu.write_cr3 = pv_native_write_cr3,
.mmu.pgd_alloc = __paravirt_pgd_alloc,
.mmu.pgd_free = paravirt_nop,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6da6769d7254..0f398a42c1e2 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -1043,7 +1043,7 @@ unsigned long __get_wchan(struct task_struct *p)
return addr;
}
-long do_arch_prctl_common(int option, unsigned long arg2)
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
{
switch (option) {
case ARCH_GET_CPUID:
@@ -1058,5 +1058,8 @@ long do_arch_prctl_common(int option, unsigned long arg2)
return fpu_xstate_prctl(option, arg2);
}
+ if (!in_ia32_syscall())
+ return do_arch_prctl_64(current, option, arg2);
+
return -EINVAL;
}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0917c7f25720..2bdab416298c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -215,8 +215,3 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
return prev_p;
}
-
-SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
- return do_arch_prctl_common(option, arg2);
-}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 226472332a70..f983d2a57ac3 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -942,7 +942,7 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
case ARCH_MAP_VDSO_X32:
return prctl_map_vdso(&vdso_image_x32, arg2);
# endif
-# if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+# ifdef CONFIG_IA32_EMULATION
case ARCH_MAP_VDSO_32:
return prctl_map_vdso(&vdso_image_32, arg2);
# endif
@@ -979,26 +979,3 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
return ret;
}
-
-SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
- long ret;
-
- ret = do_arch_prctl_64(current, option, arg2);
- if (ret == -EINVAL)
- ret = do_arch_prctl_common(option, arg2);
-
- return ret;
-}
-
-#ifdef CONFIG_IA32_EMULATION
-COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
- return do_arch_prctl_common(option, arg2);
-}
-#endif
-
-unsigned long KSTK_ESP(struct task_struct *task)
-{
- return task_pt_regs(task)->sp;
-}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index dc1dd3f3e67f..964f6b0a3d68 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -921,20 +921,16 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
return;
/* Make a note of crashing cpu. Will be used in NMI callback. */
- crashing_cpu = safe_smp_processor_id();
+ crashing_cpu = smp_processor_id();
shootdown_callback = callback;
atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
- /* Would it be better to replace the trap vector here? */
- if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback,
- NMI_FLAG_FIRST, "crash"))
- return; /* Return what? */
+
/*
- * Ensure the new callback function is set before sending
- * out the NMI
+ * Set emergency handler to preempt other handlers.
*/
- wmb();
+ set_emergency_nmi_handler(NMI_LOCAL, crash_nmi_callback);
apic_send_IPI_allbutself(NMI_VECTOR);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cebee310e200..9f8ff3aad4f4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -56,6 +56,9 @@
#include <asm/unwind.h>
#include <asm/vsyscall.h>
#include <linux/vmalloc.h>
+#if defined(CONFIG_X86_LOCAL_APIC)
+#include <asm/nmi.h>
+#endif
/*
* max_low_pfn_mapped: highest directly mapped pfn < 4 GB
@@ -146,6 +149,69 @@ static size_t ima_kexec_buffer_size;
/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
int bootloader_type, bootloader_version;
+static const struct ctl_table x86_sysctl_table[] = {
+ {
+ .procname = "panic_on_unrecovered_nmi",
+ .data = &panic_on_unrecovered_nmi,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "panic_on_io_nmi",
+ .data = &panic_on_io_nmi,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "bootloader_type",
+ .data = &bootloader_type,
+ .maxlen = sizeof(int),
+ .mode = 0444,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "bootloader_version",
+ .data = &bootloader_version,
+ .maxlen = sizeof(int),
+ .mode = 0444,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "io_delay_type",
+ .data = &io_delay_type,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#if defined(CONFIG_X86_LOCAL_APIC)
+ {
+ .procname = "unknown_nmi_panic",
+ .data = &unknown_nmi_panic,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#endif
+#if defined(CONFIG_ACPI_SLEEP)
+ {
+ .procname = "acpi_video_flags",
+ .data = &acpi_realmode_flags,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ },
+#endif
+};
+
+static int __init init_x86_sysctl(void)
+{
+ register_sysctl_init("kernel", x86_sysctl_table);
+ return 0;
+}
+arch_initcall(init_x86_sysctl);
+
/*
* Setup options
*/
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c10850ae6f09..4be00831656c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -229,7 +229,7 @@ static void ap_calibrate_delay(void)
/*
* Activate a secondary processor.
*/
-static void notrace start_secondary(void *unused)
+static void notrace __noendbr start_secondary(void *unused)
{
/*
* Don't put *anything* except direct CPU state initialization
@@ -314,6 +314,7 @@ static void notrace start_secondary(void *unused)
wmb();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
+ANNOTATE_NOENDBR_SYM(start_secondary);
/*
* The bootstrap kernel entry code has set these up. Save them for
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 2dbadf347b5f..f4263cb3d21e 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -94,10 +94,20 @@ __always_inline int is_valid_bugaddr(unsigned long addr)
/*
* Check for UD1 or UD2, accounting for Address Size Override Prefixes.
- * If it's a UD1, get the ModRM byte to pass along to UBSan.
+ * If it's a UD1, further decode to determine its use:
+ *
+ * FineIBT: ea (bad)
+ * FineIBT: f0 75 f9 lock jne . - 6
+ * UBSan{0}: 67 0f b9 00 ud1 (%eax),%eax
+ * UBSan{10}: 67 0f b9 40 10 ud1 0x10(%eax),%eax
+ * static_call: 0f b9 cc ud1 %esp,%ecx
+ *
+ * Notably UBSAN uses EAX, static_call uses ECX.
*/
-__always_inline int decode_bug(unsigned long addr, u32 *imm)
+__always_inline int decode_bug(unsigned long addr, s32 *imm, int *len)
{
+ unsigned long start = addr;
+ bool lock = false;
u8 v;
if (addr < TASK_SIZE_MAX)
@@ -106,28 +116,67 @@ __always_inline int decode_bug(unsigned long addr, u32 *imm)
v = *(u8 *)(addr++);
if (v == INSN_ASOP)
v = *(u8 *)(addr++);
- if (v != OPCODE_ESCAPE)
+
+ if (v == INSN_LOCK) {
+ lock = true;
+ v = *(u8 *)(addr++);
+ }
+
+ switch (v) {
+ case 0x70 ... 0x7f: /* Jcc.d8 */
+ addr += 1; /* d8 */
+ *len = addr - start;
+ WARN_ON_ONCE(!lock);
+ return BUG_LOCK;
+
+ case 0xea:
+ *len = addr - start;
+ return BUG_EA;
+
+ case OPCODE_ESCAPE:
+ break;
+
+ default:
return BUG_NONE;
+ }
v = *(u8 *)(addr++);
- if (v == SECOND_BYTE_OPCODE_UD2)
+ if (v == SECOND_BYTE_OPCODE_UD2) {
+ *len = addr - start;
return BUG_UD2;
+ }
- if (!IS_ENABLED(CONFIG_UBSAN_TRAP) || v != SECOND_BYTE_OPCODE_UD1)
+ if (v != SECOND_BYTE_OPCODE_UD1)
return BUG_NONE;
- /* Retrieve the immediate (type value) for the UBSAN UD1 */
- v = *(u8 *)(addr++);
- if (X86_MODRM_RM(v) == 4)
- addr++;
-
*imm = 0;
- if (X86_MODRM_MOD(v) == 1)
- *imm = *(u8 *)addr;
- else if (X86_MODRM_MOD(v) == 2)
- *imm = *(u32 *)addr;
- else
- WARN_ONCE(1, "Unexpected MODRM_MOD: %u\n", X86_MODRM_MOD(v));
+ v = *(u8 *)(addr++); /* ModRM */
+
+ if (X86_MODRM_MOD(v) != 3 && X86_MODRM_RM(v) == 4)
+ addr++; /* SIB */
+
+ /* Decode immediate, if present */
+ switch (X86_MODRM_MOD(v)) {
+ case 0: if (X86_MODRM_RM(v) == 5)
+ addr += 4; /* RIP + disp32 */
+ break;
+
+ case 1: *imm = *(s8 *)addr;
+ addr += 1;
+ break;
+
+ case 2: *imm = *(s32 *)addr;
+ addr += 4;
+ break;
+
+ case 3: break;
+ }
+
+ /* record instruction length */
+ *len = addr - start;
+
+ if (X86_MODRM_REG(v) == 0) /* EAX */
+ return BUG_UD1_UBSAN;
return BUG_UD1;
}
@@ -257,11 +306,12 @@ static inline void handle_invalid_op(struct pt_regs *regs)
static noinstr bool handle_bug(struct pt_regs *regs)
{
+ unsigned long addr = regs->ip;
bool handled = false;
- int ud_type;
- u32 imm;
+ int ud_type, ud_len;
+ s32 ud_imm;
- ud_type = decode_bug(regs->ip, &imm);
+ ud_type = decode_bug(addr, &ud_imm, &ud_len);
if (ud_type == BUG_NONE)
return handled;
@@ -281,15 +331,47 @@ static noinstr bool handle_bug(struct pt_regs *regs)
*/
if (regs->flags & X86_EFLAGS_IF)
raw_local_irq_enable();
- if (ud_type == BUG_UD2) {
- if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
- handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
- regs->ip += LEN_UD2;
+
+ switch (ud_type) {
+ case BUG_UD2:
+ if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
handled = true;
+ break;
}
- } else if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
- pr_crit("%s at %pS\n", report_ubsan_failure(regs, imm), (void *)regs->ip);
+ fallthrough;
+
+ case BUG_EA:
+ case BUG_LOCK:
+ if (handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
+ handled = true;
+ break;
+ }
+ break;
+
+ case BUG_UD1_UBSAN:
+ if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
+ pr_crit("%s at %pS\n",
+ report_ubsan_failure(regs, ud_imm),
+ (void *)regs->ip);
+ }
+ break;
+
+ default:
+ break;
+ }
+
+ /*
+ * When continuing, and regs->ip hasn't changed, move it to the next
+ * instruction. When not continuing execution, restore the instruction
+ * pointer.
+ */
+ if (handled) {
+ if (regs->ip == addr)
+ regs->ip += ud_len;
+ } else {
+ regs->ip = addr;
}
+
if (regs->flags & X86_EFLAGS_IF)
raw_local_irq_disable();
instrumentation_end();
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 8a59c61624c2..f453507649d4 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -66,5 +66,6 @@ endif
lib-y += clear_page_64.o copy_page_64.o
lib-y += memmove_64.o memset_64.o
lib-y += copy_user_64.o copy_user_uncached_64.o
- lib-y += cmpxchg16b_emu.o
+ lib-y += cmpxchg16b_emu.o
+ lib-y += bhi.o
endif
diff --git a/arch/x86/lib/bhi.S b/arch/x86/lib/bhi.S
new file mode 100644
index 000000000000..58891681261b
--- /dev/null
+++ b/arch/x86/lib/bhi.S
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/unwind_hints.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * Notably, the FineIBT preamble calling these will have ZF set and r10 zero.
+ *
+ * The very last element is in fact larger than 32 bytes, but since its the
+ * last element, this does not matter,
+ *
+ * There are 2 #UD sites, located between 0,1-2,3 and 4,5-6,7 such that they
+ * can be reached using Jcc.d8, these elements (1 and 5) have sufficiently
+ * big alignment holes for this to not stagger the array.
+ */
+
+.pushsection .noinstr.text, "ax"
+
+ .align 32
+SYM_CODE_START(__bhi_args)
+
+#ifdef CONFIG_FINEIBT_BHI
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_0, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_1
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_1, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_1
+ cmovne %r10, %rdi
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 8
+ ANNOTATE_REACHABLE
+.Lud_1: ud2
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_2, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_1
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_3, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_1
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_4, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_2
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ cmovne %r10, %rcx
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_5, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_2
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ cmovne %r10, %rcx
+ cmovne %r10, %r8
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 8
+ ANNOTATE_REACHABLE
+.Lud_2: ud2
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_6, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_2
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ cmovne %r10, %rcx
+ cmovne %r10, %r8
+ cmovne %r10, %r9
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_7, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_2
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ cmovne %r10, %rcx
+ cmovne %r10, %r8
+ cmovne %r10, %r9
+ cmovne %r10, %rsp
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+#endif /* CONFIG_FINEIBT_BHI */
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_end, SYM_L_GLOBAL)
+ ANNOTATE_NOENDBR
+ nop /* Work around toolchain+objtool quirk */
+SYM_CODE_END(__bhi_args)
+
+.popsection
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 2760a15fbc00..a508e4a8c66a 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,6 +1,8 @@
/* SPDX-License-Identifier: GPL-2.0-only */
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <linux/objtool.h>
#include <asm/asm.h>
/*
@@ -14,7 +16,7 @@
* Zero a page.
* %rdi - page
*/
-SYM_FUNC_START(clear_page_rep)
+SYM_TYPED_FUNC_START(clear_page_rep)
movl $4096/8,%ecx
xorl %eax,%eax
rep stosq
@@ -22,7 +24,7 @@ SYM_FUNC_START(clear_page_rep)
SYM_FUNC_END(clear_page_rep)
EXPORT_SYMBOL_GPL(clear_page_rep)
-SYM_FUNC_START(clear_page_orig)
+SYM_TYPED_FUNC_START(clear_page_orig)
xorl %eax,%eax
movl $4096/64,%ecx
.p2align 4
@@ -44,7 +46,7 @@ SYM_FUNC_START(clear_page_orig)
SYM_FUNC_END(clear_page_orig)
EXPORT_SYMBOL_GPL(clear_page_orig)
-SYM_FUNC_START(clear_page_erms)
+SYM_TYPED_FUNC_START(clear_page_erms)
movl $4096,%ecx
xorl %eax,%eax
rep stosb
@@ -63,6 +65,7 @@ EXPORT_SYMBOL_GPL(clear_page_erms)
* rcx: uncleared bytes or 0 if successful.
*/
SYM_FUNC_START(rep_stos_alternative)
+ ANNOTATE_NOENDBR
cmpq $64,%rcx
jae .Lunrolled
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index d6ae793d08fa..d8e87fedc20d 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -3,6 +3,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
@@ -13,7 +14,7 @@
* prefetch distance based on SMP/UP.
*/
ALIGN
-SYM_FUNC_START(copy_page)
+SYM_TYPED_FUNC_START(copy_page)
ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
movl $4096/8, %ecx
rep movsq
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fc9fb5d06174..aa8c341b2441 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -8,6 +8,8 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <linux/objtool.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
#include <asm/asm.h>
@@ -30,6 +32,7 @@
* it simpler for us, we can clobber rsi/rdi and rax freely.
*/
SYM_FUNC_START(rep_movs_alternative)
+ ANNOTATE_NOENDBR
cmpq $64,%rcx
jae .Llarge
diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S
index 2918e36eece2..18350b343c2a 100644
--- a/arch/x86/lib/copy_user_uncached_64.S
+++ b/arch/x86/lib/copy_user_uncached_64.S
@@ -5,6 +5,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/asm.h>
/*
@@ -27,6 +28,7 @@
* rax uncopied bytes or 0 if successful.
*/
SYM_FUNC_START(__copy_user_nocache)
+ ANNOTATE_NOENDBR
/* If destination is not 7-byte aligned, we'll have to align it */
testb $7,%dil
jne .Lalign
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 89ecd57c9d42..71d8e7da4fc5 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -28,6 +28,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/page_types.h>
#include <asm/errno.h>
#include <asm/asm-offsets.h>
@@ -62,6 +63,7 @@
.text
SYM_FUNC_START(__get_user_1)
+ ANNOTATE_NOENDBR
check_range size=1
ASM_STAC
UACCESS movzbl (%_ASM_AX),%edx
@@ -72,6 +74,7 @@ SYM_FUNC_END(__get_user_1)
EXPORT_SYMBOL(__get_user_1)
SYM_FUNC_START(__get_user_2)
+ ANNOTATE_NOENDBR
check_range size=2
ASM_STAC
UACCESS movzwl (%_ASM_AX),%edx
@@ -82,6 +85,7 @@ SYM_FUNC_END(__get_user_2)
EXPORT_SYMBOL(__get_user_2)
SYM_FUNC_START(__get_user_4)
+ ANNOTATE_NOENDBR
check_range size=4
ASM_STAC
UACCESS movl (%_ASM_AX),%edx
@@ -92,6 +96,7 @@ SYM_FUNC_END(__get_user_4)
EXPORT_SYMBOL(__get_user_4)
SYM_FUNC_START(__get_user_8)
+ ANNOTATE_NOENDBR
#ifndef CONFIG_X86_64
xor %ecx,%ecx
#endif
@@ -111,6 +116,7 @@ EXPORT_SYMBOL(__get_user_8)
/* .. and the same for __get_user, just without the range checks */
SYM_FUNC_START(__get_user_nocheck_1)
+ ANNOTATE_NOENDBR
ASM_STAC
ASM_BARRIER_NOSPEC
UACCESS movzbl (%_ASM_AX),%edx
@@ -121,6 +127,7 @@ SYM_FUNC_END(__get_user_nocheck_1)
EXPORT_SYMBOL(__get_user_nocheck_1)
SYM_FUNC_START(__get_user_nocheck_2)
+ ANNOTATE_NOENDBR
ASM_STAC
ASM_BARRIER_NOSPEC
UACCESS movzwl (%_ASM_AX),%edx
@@ -131,6 +138,7 @@ SYM_FUNC_END(__get_user_nocheck_2)
EXPORT_SYMBOL(__get_user_nocheck_2)
SYM_FUNC_START(__get_user_nocheck_4)
+ ANNOTATE_NOENDBR
ASM_STAC
ASM_BARRIER_NOSPEC
UACCESS movl (%_ASM_AX),%edx
@@ -141,6 +149,7 @@ SYM_FUNC_END(__get_user_nocheck_4)
EXPORT_SYMBOL(__get_user_nocheck_4)
SYM_FUNC_START(__get_user_nocheck_8)
+ ANNOTATE_NOENDBR
ASM_STAC
ASM_BARRIER_NOSPEC
#ifdef CONFIG_X86_64
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 774bdf3e6f0a..edbeb3ecad38 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/asm.h>
@@ -9,6 +10,7 @@
* %rdi: w
*/
SYM_FUNC_START(__sw_hweight32)
+ ANNOTATE_NOENDBR
#ifdef CONFIG_X86_64
movl %edi, %eax # w
@@ -42,6 +44,7 @@ EXPORT_SYMBOL(__sw_hweight32)
*/
#ifdef CONFIG_X86_64
SYM_FUNC_START(__sw_hweight64)
+ ANNOTATE_NOENDBR
pushq %rdi
pushq %rdx
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 1b60ae81ecd8..aa1f92ee6b2e 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,6 +8,7 @@
*/
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
@@ -26,7 +27,7 @@
* Output:
* rax: dest
*/
-SYM_FUNC_START(__memmove)
+SYM_TYPED_FUNC_START(__memmove)
mov %rdi, %rax
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 0199d56cb479..d66b710d628f 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -3,6 +3,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
@@ -28,7 +29,7 @@
* only for the return value that is the same as the source input,
* which the compiler could/should do much better anyway.
*/
-SYM_FUNC_START(__memset)
+SYM_TYPED_FUNC_START(__memset)
ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
movq %rdi,%r9
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index ebd259f31496..5ef8494896e8 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/linkage.h>
#include <linux/errno.h>
+#include <linux/cfi_types.h>
#include <asm/asm.h>
#include <asm/msr.h>
@@ -12,7 +13,7 @@
*
*/
.macro op_safe_regs op
-SYM_FUNC_START(\op\()_safe_regs)
+SYM_TYPED_FUNC_START(\op\()_safe_regs)
pushq %rbx
pushq %r12
movq %rdi, %r10 /* Save pointer */
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 975c9c18263d..46d9e9b98a61 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -13,6 +13,7 @@
*/
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/thread_info.h>
#include <asm/errno.h>
#include <asm/asm.h>
@@ -45,6 +46,7 @@
.text
SYM_FUNC_START(__put_user_1)
+ ANNOTATE_NOENDBR
check_range size=1
ASM_STAC
1: movb %al,(%_ASM_CX)
@@ -55,6 +57,7 @@ SYM_FUNC_END(__put_user_1)
EXPORT_SYMBOL(__put_user_1)
SYM_FUNC_START(__put_user_nocheck_1)
+ ANNOTATE_NOENDBR
ASM_STAC
2: movb %al,(%_ASM_CX)
xor %ecx,%ecx
@@ -64,6 +67,7 @@ SYM_FUNC_END(__put_user_nocheck_1)
EXPORT_SYMBOL(__put_user_nocheck_1)
SYM_FUNC_START(__put_user_2)
+ ANNOTATE_NOENDBR
check_range size=2
ASM_STAC
3: movw %ax,(%_ASM_CX)
@@ -74,6 +78,7 @@ SYM_FUNC_END(__put_user_2)
EXPORT_SYMBOL(__put_user_2)
SYM_FUNC_START(__put_user_nocheck_2)
+ ANNOTATE_NOENDBR
ASM_STAC
4: movw %ax,(%_ASM_CX)
xor %ecx,%ecx
@@ -83,6 +88,7 @@ SYM_FUNC_END(__put_user_nocheck_2)
EXPORT_SYMBOL(__put_user_nocheck_2)
SYM_FUNC_START(__put_user_4)
+ ANNOTATE_NOENDBR
check_range size=4
ASM_STAC
5: movl %eax,(%_ASM_CX)
@@ -93,6 +99,7 @@ SYM_FUNC_END(__put_user_4)
EXPORT_SYMBOL(__put_user_4)
SYM_FUNC_START(__put_user_nocheck_4)
+ ANNOTATE_NOENDBR
ASM_STAC
6: movl %eax,(%_ASM_CX)
xor %ecx,%ecx
@@ -102,6 +109,7 @@ SYM_FUNC_END(__put_user_nocheck_4)
EXPORT_SYMBOL(__put_user_nocheck_4)
SYM_FUNC_START(__put_user_8)
+ ANNOTATE_NOENDBR
check_range size=8
ASM_STAC
7: mov %_ASM_AX,(%_ASM_CX)
@@ -115,6 +123,7 @@ SYM_FUNC_END(__put_user_8)
EXPORT_SYMBOL(__put_user_8)
SYM_FUNC_START(__put_user_nocheck_8)
+ ANNOTATE_NOENDBR
ASM_STAC
9: mov %_ASM_AX,(%_ASM_CX)
#ifdef CONFIG_X86_32
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 391059b2c6fb..038f49a43ab4 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -326,6 +326,7 @@ SYM_FUNC_END(retbleed_untrain_ret)
#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
SYM_FUNC_START(entry_untrain_ret)
+ ANNOTATE_NOENDBR
ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
SYM_FUNC_END(entry_untrain_ret)
__EXPORT_THUNK(entry_untrain_ret)
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index e25288ee33c2..f8a33b25ae86 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -72,6 +72,7 @@ SYM_FUNC_START(sme_encrypt_execute)
SYM_FUNC_END(sme_encrypt_execute)
SYM_FUNC_START(__enc_copy)
+ ANNOTATE_NOENDBR
/*
* Routine used to encrypt memory in place.
* This routine must be run outside of the kernel proper since
diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c
index 3d2f7f0a6ed1..ad3c1feec990 100644
--- a/arch/x86/mm/pat/cpa-test.c
+++ b/arch/x86/mm/pat/cpa-test.c
@@ -183,7 +183,7 @@ static int pageattr_test(void)
break;
case 1:
- err = change_page_attr_set(addrs, len[1], PAGE_CPA_TEST, 1);
+ err = change_page_attr_set(addrs, len[i], PAGE_CPA_TEST, 1);
break;
case 2:
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index ef4514d64c05..7bd0f62ba48f 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -73,6 +73,7 @@ static DEFINE_SPINLOCK(cpa_lock);
#define CPA_ARRAY 2
#define CPA_PAGES_ARRAY 4
#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
+#define CPA_COLLAPSE 16 /* try to collapse large pages */
static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
{
@@ -105,6 +106,18 @@ static void split_page_count(int level)
direct_pages_count[level - 1] += PTRS_PER_PTE;
}
+static void collapse_page_count(int level)
+{
+ direct_pages_count[level]++;
+ if (system_state == SYSTEM_RUNNING) {
+ if (level == PG_LEVEL_2M)
+ count_vm_event(DIRECT_MAP_LEVEL2_COLLAPSE);
+ else if (level == PG_LEVEL_1G)
+ count_vm_event(DIRECT_MAP_LEVEL3_COLLAPSE);
+ }
+ direct_pages_count[level - 1] -= PTRS_PER_PTE;
+}
+
void arch_report_meminfo(struct seq_file *m)
{
seq_printf(m, "DirectMap4k: %8lu kB\n",
@@ -122,6 +135,7 @@ void arch_report_meminfo(struct seq_file *m)
}
#else
static inline void split_page_count(int level) { }
+static inline void collapse_page_count(int level) { }
#endif
#ifdef CONFIG_X86_CPA_STATISTICS
@@ -394,16 +408,49 @@ static void __cpa_flush_tlb(void *data)
flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
}
-static void cpa_flush(struct cpa_data *data, int cache)
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables);
+
+static void cpa_collapse_large_pages(struct cpa_data *cpa)
+{
+ unsigned long start, addr, end;
+ struct ptdesc *ptdesc, *tmp;
+ LIST_HEAD(pgtables);
+ int collapsed = 0;
+ int i;
+
+ if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
+ for (i = 0; i < cpa->numpages; i++)
+ collapsed += collapse_large_pages(__cpa_addr(cpa, i),
+ &pgtables);
+ } else {
+ addr = __cpa_addr(cpa, 0);
+ start = addr & PMD_MASK;
+ end = addr + PAGE_SIZE * cpa->numpages;
+
+ for (addr = start; within(addr, start, end); addr += PMD_SIZE)
+ collapsed += collapse_large_pages(addr, &pgtables);
+ }
+
+ if (!collapsed)
+ return;
+
+ flush_tlb_all();
+
+ list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) {
+ list_del(&ptdesc->pt_list);
+ __free_page(ptdesc_page(ptdesc));
+ }
+}
+
+static void cpa_flush(struct cpa_data *cpa, int cache)
{
- struct cpa_data *cpa = data;
unsigned int i;
BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) {
cpa_flush_all(cache);
- return;
+ goto collapse_large_pages;
}
if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
@@ -412,7 +459,7 @@ static void cpa_flush(struct cpa_data *data, int cache)
on_each_cpu(__cpa_flush_tlb, cpa, 1);
if (!cache)
- return;
+ goto collapse_large_pages;
mb();
for (i = 0; i < cpa->numpages; i++) {
@@ -428,6 +475,10 @@ static void cpa_flush(struct cpa_data *data, int cache)
clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE);
}
mb();
+
+collapse_large_pages:
+ if (cpa->flags & CPA_COLLAPSE)
+ cpa_collapse_large_pages(cpa);
}
static bool overlaps(unsigned long r1_start, unsigned long r1_end,
@@ -1197,6 +1248,161 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
return 0;
}
+static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
+ struct list_head *pgtables)
+{
+ pmd_t _pmd, old_pmd;
+ pte_t *pte, first;
+ unsigned long pfn;
+ pgprot_t pgprot;
+ int i = 0;
+
+ addr &= PMD_MASK;
+ pte = pte_offset_kernel(pmd, addr);
+ first = *pte;
+ pfn = pte_pfn(first);
+
+ /* Make sure alignment is suitable */
+ if (PFN_PHYS(pfn) & ~PMD_MASK)
+ return 0;
+
+ /* The page is 4k intentionally */
+ if (pte_flags(first) & _PAGE_KERNEL_4K)
+ return 0;
+
+ /* Check that the rest of PTEs are compatible with the first one */
+ for (i = 1, pte++; i < PTRS_PER_PTE; i++, pte++) {
+ pte_t entry = *pte;
+
+ if (!pte_present(entry))
+ return 0;
+ if (pte_flags(entry) != pte_flags(first))
+ return 0;
+ if (pte_pfn(entry) != pte_pfn(first) + i)
+ return 0;
+ }
+
+ old_pmd = *pmd;
+
+ /* Success: set up a large page */
+ pgprot = pgprot_4k_2_large(pte_pgprot(first));
+ pgprot_val(pgprot) |= _PAGE_PSE;
+ _pmd = pfn_pmd(pfn, pgprot);
+ set_pmd(pmd, _pmd);
+
+ /* Queue the page table to be freed after TLB flush */
+ list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables);
+
+ if (IS_ENABLED(CONFIG_X86_32) && !SHARED_KERNEL_PMD) {
+ struct page *page;
+
+ /* Update all PGD tables to use the same large page */
+ list_for_each_entry(page, &pgd_list, lru) {
+ pgd_t *pgd = (pgd_t *)page_address(page) + pgd_index(addr);
+ p4d_t *p4d = p4d_offset(pgd, addr);
+ pud_t *pud = pud_offset(p4d, addr);
+ pmd_t *pmd = pmd_offset(pud, addr);
+ /* Something is wrong if entries doesn't match */
+ if (WARN_ON(pmd_val(old_pmd) != pmd_val(*pmd)))
+ continue;
+ set_pmd(pmd, _pmd);
+ }
+ }
+
+ if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+ collapse_page_count(PG_LEVEL_2M);
+
+ return 1;
+}
+
+static int collapse_pud_page(pud_t *pud, unsigned long addr,
+ struct list_head *pgtables)
+{
+ unsigned long pfn;
+ pmd_t *pmd, first;
+ int i;
+
+ if (!direct_gbpages)
+ return 0;
+
+ addr &= PUD_MASK;
+ pmd = pmd_offset(pud, addr);
+ first = *pmd;
+
+ /*
+ * To restore PUD page all PMD entries must be large and
+ * have suitable alignment
+ */
+ pfn = pmd_pfn(first);
+ if (!pmd_leaf(first) || (PFN_PHYS(pfn) & ~PUD_MASK))
+ return 0;
+
+ /*
+ * To restore PUD page, all following PMDs must be compatible with the
+ * first one.
+ */
+ for (i = 1, pmd++; i < PTRS_PER_PMD; i++, pmd++) {
+ pmd_t entry = *pmd;
+
+ if (!pmd_present(entry) || !pmd_leaf(entry))
+ return 0;
+ if (pmd_flags(entry) != pmd_flags(first))
+ return 0;
+ if (pmd_pfn(entry) != pmd_pfn(first) + i * PTRS_PER_PTE)
+ return 0;
+ }
+
+ /* Restore PUD page and queue page table to be freed after TLB flush */
+ list_add(&page_ptdesc(pud_page(*pud))->pt_list, pgtables);
+ set_pud(pud, pfn_pud(pfn, pmd_pgprot(first)));
+
+ if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+ collapse_page_count(PG_LEVEL_1G);
+
+ return 1;
+}
+
+/*
+ * Collapse PMD and PUD pages in the kernel mapping around the address where
+ * possible.
+ *
+ * Caller must flush TLB and free page tables queued on the list before
+ * touching the new entries. CPU must not see TLB entries of different size
+ * with different attributes.
+ */
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables)
+{
+ int collapsed = 0;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ addr &= PMD_MASK;
+
+ spin_lock(&pgd_lock);
+ pgd = pgd_offset_k(addr);
+ if (pgd_none(*pgd))
+ goto out;
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d))
+ goto out;
+ pud = pud_offset(p4d, addr);
+ if (!pud_present(*pud) || pud_leaf(*pud))
+ goto out;
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_present(*pmd) || pmd_leaf(*pmd))
+ goto out;
+
+ collapsed = collapse_pmd_page(pmd, addr, pgtables);
+ if (collapsed)
+ collapsed += collapse_pud_page(pud, addr, pgtables);
+
+out:
+ spin_unlock(&pgd_lock);
+ return collapsed;
+}
+
static bool try_to_free_pte_page(pte_t *pte)
{
int i;
@@ -2120,7 +2326,8 @@ int set_memory_rox(unsigned long addr, int numpages)
if (__supported_pte_mask & _PAGE_NX)
clr.pgprot |= _PAGE_NX;
- return change_page_attr_clear(&addr, numpages, clr, 0);
+ return change_page_attr_set_clr(&addr, numpages, __pgprot(0), clr, 0,
+ CPA_COLLAPSE, NULL);
}
int set_memory_rw(unsigned long addr, int numpages)
@@ -2147,7 +2354,8 @@ int set_memory_p(unsigned long addr, int numpages)
int set_memory_4k(unsigned long addr, int numpages)
{
- return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+ return change_page_attr_set_clr(&addr, numpages,
+ __pgprot(_PAGE_KERNEL_4K),
__pgprot(0), 1, 0, NULL);
}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6cf881a942bb..ffc25b348041 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1325,7 +1325,7 @@ bool nmi_uaccess_okay(void)
if (loaded_mm != current_mm)
return false;
- VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
+ VM_WARN_ON_ONCE(__pa(current_mm->pgd) != read_cr3_pa());
return true;
}
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a43fc5af973d..72776dcb75aa 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -410,16 +410,20 @@ static void emit_nops(u8 **pprog, int len)
* Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
* in arch/x86/kernel/alternative.c
*/
+static int emit_call(u8 **prog, void *func, void *ip);
-static void emit_fineibt(u8 **pprog, u32 hash)
+static void emit_fineibt(u8 **pprog, u8 *ip, u32 hash, int arity)
{
u8 *prog = *pprog;
EMIT_ENDBR();
EMIT3_off32(0x41, 0x81, 0xea, hash); /* subl $hash, %r10d */
- EMIT2(0x74, 0x07); /* jz.d8 +7 */
- EMIT2(0x0f, 0x0b); /* ud2 */
- EMIT1(0x90); /* nop */
+ if (cfi_bhi) {
+ emit_call(&prog, __bhi_args[arity], ip + 11);
+ } else {
+ EMIT2(0x75, 0xf9); /* jne.d8 .-7 */
+ EMIT3(0x0f, 0x1f, 0x00); /* nop3 */
+ }
EMIT_ENDBR_POISON();
*pprog = prog;
@@ -448,13 +452,13 @@ static void emit_kcfi(u8 **pprog, u32 hash)
*pprog = prog;
}
-static void emit_cfi(u8 **pprog, u32 hash)
+static void emit_cfi(u8 **pprog, u8 *ip, u32 hash, int arity)
{
u8 *prog = *pprog;
switch (cfi_mode) {
case CFI_FINEIBT:
- emit_fineibt(&prog, hash);
+ emit_fineibt(&prog, ip, hash, arity);
break;
case CFI_KCFI:
@@ -505,13 +509,17 @@ static void emit_prologue_tail_call(u8 **pprog, bool is_subprog)
* bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
* while jumping to another program
*/
-static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+static void emit_prologue(u8 **pprog, u8 *ip, u32 stack_depth, bool ebpf_from_cbpf,
bool tail_call_reachable, bool is_subprog,
bool is_exception_cb)
{
u8 *prog = *pprog;
- emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash);
+ if (is_subprog) {
+ emit_cfi(&prog, ip, cfi_bpf_subprog_hash, 5);
+ } else {
+ emit_cfi(&prog, ip, cfi_bpf_hash, 1);
+ }
/* BPF trampoline can be made to work without these nops,
* but let's waste 5 bytes for now and optimize later
*/
@@ -641,7 +649,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
* See emit_prologue(), for IBT builds the trampoline hook is preceded
* with an ENDBR instruction.
*/
- if (is_endbr(*(u32 *)ip))
+ if (is_endbr(ip))
ip += ENDBR_INSN_SIZE;
return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
@@ -1480,7 +1488,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
detect_reg_usage(insn, insn_cnt, callee_regs_used);
- emit_prologue(&prog, stack_depth,
+ emit_prologue(&prog, image, stack_depth,
bpf_prog_was_classic(bpf_prog), tail_call_reachable,
bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
/* Exception callback will clobber callee regs for its own use, and
@@ -3036,7 +3044,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
/* skip patched call instruction and point orig_call to actual
* body of the kernel function.
*/
- if (is_endbr(*(u32 *)orig_call))
+ if (is_endbr(orig_call))
orig_call += ENDBR_INSN_SIZE;
orig_call += X86_PATCH_SIZE;
}
@@ -3047,7 +3055,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
/*
* Indirect call for bpf_struct_ops
*/
- emit_cfi(&prog, cfi_get_func_hash(func_addr));
+ emit_cfi(&prog, image,
+ cfi_get_func_hash(func_addr),
+ cfi_get_func_arity(func_addr));
} else {
/*
* Direct-call fentry stub, as such it needs accounting for the
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 0a0539e1cc81..8c534c36adfa 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -26,6 +26,7 @@
/* code below belongs to the image kernel */
.align PAGE_SIZE
SYM_FUNC_START(restore_registers)
+ ANNOTATE_NOENDBR
/* go back to the original page tables */
movq %r9, %cr3
@@ -119,6 +120,7 @@ SYM_FUNC_END(restore_image)
/* code below has been relocated to a safe page */
SYM_FUNC_START(core_restore_code)
+ ANNOTATE_NOENDBR
/* switch to temporary page tables */
movq %rax, %cr3
/* flush TLB */
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index b518f36d1ca2..109af12f7647 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -51,6 +51,7 @@ SYM_FUNC_END(xen_hypercall_pv)
* non-zero.
*/
SYM_FUNC_START(xen_irq_disable_direct)
+ ENDBR
movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
RET
SYM_FUNC_END(xen_irq_disable_direct)
@@ -90,6 +91,7 @@ SYM_FUNC_END(check_events)
* then enter the hypervisor to get them handled.
*/
SYM_FUNC_START(xen_irq_enable_direct)
+ ENDBR
FRAME_BEGIN
/* Unmask events */
movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
@@ -120,6 +122,7 @@ SYM_FUNC_END(xen_irq_enable_direct)
* x86 use opposite senses (mask vs enable).
*/
SYM_FUNC_START(xen_save_fl_direct)
+ ENDBR
testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
setz %ah
addb %ah, %ah
@@ -127,6 +130,7 @@ SYM_FUNC_START(xen_save_fl_direct)
SYM_FUNC_END(xen_save_fl_direct)
SYM_FUNC_START(xen_read_cr2)
+ ENDBR
FRAME_BEGIN
_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
_ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX
@@ -135,6 +139,7 @@ SYM_FUNC_START(xen_read_cr2)
SYM_FUNC_END(xen_read_cr2);
SYM_FUNC_START(xen_read_cr2_direct)
+ ENDBR
FRAME_BEGIN
_ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX
FRAME_END
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 894edf8d6d62..8d6873edff36 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -133,11 +133,13 @@ SYM_FUNC_START(xen_hypercall_hvm)
SYM_FUNC_END(xen_hypercall_hvm)
SYM_FUNC_START(xen_hypercall_amd)
+ ANNOTATE_NOENDBR
vmmcall
RET
SYM_FUNC_END(xen_hypercall_amd)
SYM_FUNC_START(xen_hypercall_intel)
+ ANNOTATE_NOENDBR
vmcall
RET
SYM_FUNC_END(xen_hypercall_intel)
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4e495b29c640..a70e62d69dc7 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -330,7 +330,6 @@ static inline bool acpi_sci_irq_valid(void)
}
extern int sbf_port;
-extern unsigned long acpi_realmode_flags;
int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index f0df518e11dd..1db17ecbb86c 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -11,6 +11,8 @@
#include <linux/module.h>
#include <asm/cfi.h>
+extern bool cfi_warn;
+
#ifndef cfi_get_offset
static inline int cfi_get_offset(void)
{
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 155385754824..e80d0f04d78f 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -212,6 +212,16 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
#endif /* __KERNEL__ */
+#if defined(CONFIG_CFI_CLANG) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+/*
+ * Force a reference to the external symbol so the compiler generates
+ * __kcfi_typid.
+ */
+#define KCFI_REFERENCE(sym) __ADDRESSABLE(sym)
+#else
+#define KCFI_REFERENCE(sym)
+#endif
+
/**
* offset_to_ptr - convert a relative memory offset to an absolute pointer
* @off: the address of the 32-bit offset value
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 64130ae19690..65655a5d1be2 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -65,6 +65,37 @@ enum execmem_range_flags {
* Architectures that use EXECMEM_ROX_CACHE must implement this.
*/
void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable);
+
+/**
+ * execmem_make_temp_rw - temporarily remap region with read-write
+ * permissions
+ * @ptr: address of the region to remap
+ * @size: size of the region to remap
+ *
+ * Remaps a part of the cached large page in the ROX cache in the range
+ * [@ptr, @ptr + @size) as writable and not executable. The caller must
+ * have exclusive ownership of this range and ensure nothing will try to
+ * execute code in this range.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_make_temp_rw(void *ptr, size_t size);
+
+/**
+ * execmem_restore_rox - restore read-only-execute permissions
+ * @ptr: address of the region to remap
+ * @size: size of the region to remap
+ *
+ * Restores read-only-execute permissions on a range [@ptr, @ptr + @size)
+ * after it was temporarily remapped as writable. Relies on architecture
+ * implementation of set_memory_rox() to restore mapping using large pages.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_restore_rox(void *ptr, size_t size);
+#else
+static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
+static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
#endif
/**
diff --git a/include/linux/module.h b/include/linux/module.h
index 30e5b19bafa9..9937e71a3b5b 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -370,7 +370,6 @@ enum mod_mem_type {
struct module_memory {
void *base;
- void *rw_copy;
bool is_rox;
unsigned int size;
@@ -772,16 +771,6 @@ static inline bool is_livepatch_module(struct module *mod)
void set_module_sig_enforced(void);
-void *__module_writable_address(struct module *mod, void *loc);
-
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
- if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod ||
- mod->state != MODULE_STATE_UNFORMED)
- return loc;
- return __module_writable_address(mod, loc);
-}
-
#else /* !CONFIG_MODULES... */
static inline struct module *__module_address(unsigned long addr)
@@ -889,11 +878,6 @@ static inline bool module_is_coming(struct module *mod)
{
return false;
}
-
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
- return loc;
-}
#endif /* CONFIG_MODULES */
#ifdef CONFIG_SYSFS
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 1f5507ba5a12..e395461d59e5 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -108,10 +108,6 @@ int module_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *mod);
-int module_post_finalize(const Elf_Ehdr *hdr,
- const Elf_Shdr *sechdrs,
- struct module *mod);
-
#ifdef CONFIG_MODULES
void flush_module_init_free_work(void);
#else
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index c722a921165b..3ca965a2ddc8 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -128,7 +128,7 @@
#define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t"
#define STACK_FRAME_NON_STANDARD(func)
#define STACK_FRAME_NON_STANDARD_FP(func)
-#define __ASM_ANNOTATE(label, type)
+#define __ASM_ANNOTATE(label, type) ""
#define ASM_ANNOTATE(type)
#else
.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0
@@ -147,6 +147,8 @@
* these relocations will never be used for indirect calls.
*/
#define ANNOTATE_NOENDBR ASM_ANNOTATE(ANNOTYPE_NOENDBR)
+#define ANNOTATE_NOENDBR_SYM(sym) asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOENDBR))
+
/*
* This should be used immediately before an indirect jump/call. It tells
* objtool the subsequent indirect jump/call is vouched safe for retpoline
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index f70d0958095c..5a37cb2b6f93 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -151,6 +151,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
#ifdef CONFIG_X86
DIRECT_MAP_LEVEL2_SPLIT,
DIRECT_MAP_LEVEL3_SPLIT,
+ DIRECT_MAP_LEVEL2_COLLAPSE,
+ DIRECT_MAP_LEVEL3_COLLAPSE,
#endif
#ifdef CONFIG_PER_VMA_LOCK_STATS
VMA_LOCK_SUCCESS,
diff --git a/kernel/cfi.c b/kernel/cfi.c
index 08caad776717..19be79639542 100644
--- a/kernel/cfi.c
+++ b/kernel/cfi.c
@@ -7,6 +7,8 @@
#include <linux/cfi.h>
+bool cfi_warn __ro_after_init = IS_ENABLED(CONFIG_CFI_PERMISSIVE);
+
enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
unsigned long *target, u32 type)
{
@@ -17,7 +19,7 @@ enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
pr_err("CFI failure at %pS (no target information)\n",
(void *)addr);
- if (IS_ENABLED(CONFIG_CFI_PERMISSIVE)) {
+ if (cfi_warn) {
__warn(NULL, 0, (void *)addr, 0, regs, NULL);
return BUG_TRAP_TYPE_WARN;
}
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 1fb9ad289a6f..a256cc919ad7 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1221,18 +1221,6 @@ void __weak module_arch_freeing_init(struct module *mod)
{
}
-void *__module_writable_address(struct module *mod, void *loc)
-{
- for_class_mod_mem_type(type, text) {
- struct module_memory *mem = &mod->mem[type];
-
- if (loc >= mem->base && loc < mem->base + mem->size)
- return loc + (mem->rw_copy - mem->base);
- }
-
- return loc;
-}
-
static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
{
unsigned int size = PAGE_ALIGN(mod->mem[type].size);
@@ -1250,21 +1238,15 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
if (!ptr)
return -ENOMEM;
- mod->mem[type].base = ptr;
-
if (execmem_is_rox(execmem_type)) {
- ptr = vzalloc(size);
+ int err = execmem_make_temp_rw(ptr, size);
- if (!ptr) {
- execmem_free(mod->mem[type].base);
+ if (err) {
+ execmem_free(ptr);
return -ENOMEM;
}
- mod->mem[type].rw_copy = ptr;
mod->mem[type].is_rox = true;
- } else {
- mod->mem[type].rw_copy = mod->mem[type].base;
- memset(mod->mem[type].base, 0, size);
}
/*
@@ -1278,18 +1260,29 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
* *do* eventually get freed, but let's just keep things simple
* and avoid *any* false positives.
*/
- kmemleak_not_leak(ptr);
+ if (!mod->mem[type].is_rox)
+ kmemleak_not_leak(ptr);
+
+ memset(ptr, 0, size);
+ mod->mem[type].base = ptr;
return 0;
}
+static void module_memory_restore_rox(struct module *mod)
+{
+ for_class_mod_mem_type(type, text) {
+ struct module_memory *mem = &mod->mem[type];
+
+ if (mem->is_rox)
+ execmem_restore_rox(mem->base, mem->size);
+ }
+}
+
static void module_memory_free(struct module *mod, enum mod_mem_type type)
{
struct module_memory *mem = &mod->mem[type];
- if (mem->is_rox)
- vfree(mem->rw_copy);
-
execmem_free(mem->base);
}
@@ -2642,7 +2635,6 @@ static int move_module(struct module *mod, struct load_info *info)
for_each_mod_mem_type(type) {
if (!mod->mem[type].size) {
mod->mem[type].base = NULL;
- mod->mem[type].rw_copy = NULL;
continue;
}
@@ -2659,7 +2651,6 @@ static int move_module(struct module *mod, struct load_info *info)
void *dest;
Elf_Shdr *shdr = &info->sechdrs[i];
const char *sname;
- unsigned long addr;
if (!(shdr->sh_flags & SHF_ALLOC))
continue;
@@ -2680,14 +2671,12 @@ static int move_module(struct module *mod, struct load_info *info)
ret = PTR_ERR(dest);
goto out_err;
}
- addr = (unsigned long)dest;
codetag_section_found = true;
} else {
enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT;
unsigned long offset = shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK;
- addr = (unsigned long)mod->mem[type].base + offset;
- dest = mod->mem[type].rw_copy + offset;
+ dest = mod->mem[type].base + offset;
}
if (shdr->sh_type != SHT_NOBITS) {
@@ -2710,13 +2699,14 @@ static int move_module(struct module *mod, struct load_info *info)
* users of info can keep taking advantage and using the newly
* minted official memory area.
*/
- shdr->sh_addr = addr;
+ shdr->sh_addr = (unsigned long)dest;
pr_debug("\t0x%lx 0x%.8lx %s\n", (long)shdr->sh_addr,
(long)shdr->sh_size, info->secstrings + shdr->sh_name);
}
return 0;
out_err:
+ module_memory_restore_rox(mod);
for (t--; t >= 0; t--)
module_memory_free(mod, t);
if (codetag_section_found)
@@ -2863,17 +2853,8 @@ int __weak module_finalize(const Elf_Ehdr *hdr,
return 0;
}
-int __weak module_post_finalize(const Elf_Ehdr *hdr,
- const Elf_Shdr *sechdrs,
- struct module *me)
-{
- return 0;
-}
-
static int post_relocation(struct module *mod, const struct load_info *info)
{
- int ret;
-
/* Sort exception table now relocations are done. */
sort_extable(mod->extable, mod->extable + mod->num_exentries);
@@ -2885,24 +2866,7 @@ static int post_relocation(struct module *mod, const struct load_info *info)
add_kallsyms(mod, info);
/* Arch-specific module finalizing. */
- ret = module_finalize(info->hdr, info->sechdrs, mod);
- if (ret)
- return ret;
-
- for_each_mod_mem_type(type) {
- struct module_memory *mem = &mod->mem[type];
-
- if (mem->is_rox) {
- if (!execmem_update_copy(mem->base, mem->rw_copy,
- mem->size))
- return -ENOMEM;
-
- vfree(mem->rw_copy);
- mem->rw_copy = NULL;
- }
- }
-
- return module_post_finalize(info->hdr, info->sechdrs, mod);
+ return module_finalize(info->hdr, info->sechdrs, mod);
}
/* Call module constructors. */
@@ -3499,6 +3463,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
mod->mem[type].size);
}
+ module_memory_restore_rox(mod);
module_deallocate(mod, info);
free_copy:
/*
diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c
index 74834ba15615..03f4142cfbf4 100644
--- a/kernel/module/strict_rwx.c
+++ b/kernel/module/strict_rwx.c
@@ -9,6 +9,7 @@
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/set_memory.h>
+#include <linux/execmem.h>
#include "internal.h"
static int module_set_memory(const struct module *mod, enum mod_mem_type type,
@@ -32,12 +33,12 @@ static int module_set_memory(const struct module *mod, enum mod_mem_type type,
int module_enable_text_rox(const struct module *mod)
{
for_class_mod_mem_type(type, text) {
+ const struct module_memory *mem = &mod->mem[type];
int ret;
- if (mod->mem[type].is_rox)
- continue;
-
- if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+ if (mem->is_rox)
+ ret = execmem_restore_rox(mem->base, mem->size);
+ else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
ret = module_set_memory(mod, type, set_memory_rox);
else
ret = module_set_memory(mod, type, set_memory_x);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index cb57da499ebb..8a37d30f2aa6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1831,16 +1831,6 @@ static const struct ctl_table kern_table[] = {
.mode = 0444,
.proc_handler = proc_dointvec,
},
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
- {
- .procname = "unknown_nmi_panic",
- .data = &unknown_nmi_panic,
- .maxlen = sizeof (int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
-
#if (defined(CONFIG_X86_32) || defined(CONFIG_PARISC)) && \
defined(CONFIG_DEBUG_STACKOVERFLOW)
{
@@ -1851,43 +1841,6 @@ static const struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
-#if defined(CONFIG_X86)
- {
- .procname = "panic_on_unrecovered_nmi",
- .data = &panic_on_unrecovered_nmi,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "panic_on_io_nmi",
- .data = &panic_on_io_nmi,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "bootloader_type",
- .data = &bootloader_type,
- .maxlen = sizeof (int),
- .mode = 0444,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "bootloader_version",
- .data = &bootloader_version,
- .maxlen = sizeof (int),
- .mode = 0444,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "io_delay_type",
- .data = &io_delay_type,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
#if defined(CONFIG_MMU)
{
.procname = "randomize_va_space",
@@ -1906,15 +1859,6 @@ static const struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
-#if defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86)
- {
- .procname = "acpi_video_flags",
- .data = &acpi_realmode_flags,
- .maxlen = sizeof (unsigned long),
- .mode = 0644,
- .proc_handler = proc_doulongvec_minmax,
- },
-#endif
#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
{
.procname = "ignore-unaligned-usertrap",
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index adc947587eb8..997fb2a47c92 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1038,27 +1038,14 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
.arg1_type = ARG_PTR_TO_CTX,
};
-#ifdef CONFIG_X86_KERNEL_IBT
-static unsigned long get_entry_ip(unsigned long fentry_ip)
+static inline unsigned long get_entry_ip(unsigned long fentry_ip)
{
- u32 instr;
-
- /* We want to be extra safe in case entry ip is on the page edge,
- * but otherwise we need to avoid get_kernel_nofault()'s overhead.
- */
- if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
- if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
- return fentry_ip;
- } else {
- instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
- }
- if (is_endbr(instr))
+#ifdef CONFIG_X86_KERNEL_IBT
+ if (is_endbr((void *)(fentry_ip - ENDBR_INSN_SIZE)))
fentry_ip -= ENDBR_INSN_SIZE;
+#endif
return fentry_ip;
}
-#else
-#define get_entry_ip(fentry_ip) fentry_ip
-#endif
BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs)
{
diff --git a/mm/execmem.c b/mm/execmem.c
index 317b6a8d35be..e6c4f5076ca8 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -257,7 +257,6 @@ out_unlock:
static int execmem_cache_populate(struct execmem_range *range, size_t size)
{
unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
- unsigned long start, end;
struct vm_struct *vm;
size_t alloc_size;
int err = -ENOMEM;
@@ -275,26 +274,18 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
/* fill memory with instructions that will trap */
execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
- start = (unsigned long)p;
- end = start + alloc_size;
-
- vunmap_range(start, end);
-
- err = execmem_set_direct_map_valid(vm, false);
- if (err)
- goto err_free_mem;
-
- err = vmap_pages_range_noflush(start, end, range->pgprot, vm->pages,
- PMD_SHIFT);
+ err = set_memory_rox((unsigned long)p, vm->nr_pages);
if (err)
goto err_free_mem;
err = execmem_cache_add(p, alloc_size);
if (err)
- goto err_free_mem;
+ goto err_reset_direct_map;
return 0;
+err_reset_direct_map:
+ execmem_set_direct_map_valid(vm, true);
err_free_mem:
vfree(p);
return err;
@@ -344,6 +335,28 @@ static bool execmem_cache_free(void *ptr)
return true;
}
+
+int execmem_make_temp_rw(void *ptr, size_t size)
+{
+ unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long addr = (unsigned long)ptr;
+ int ret;
+
+ ret = set_memory_nx(addr, nr);
+ if (ret)
+ return ret;
+
+ return set_memory_rw(addr, nr);
+}
+
+int execmem_restore_rox(void *ptr, size_t size)
+{
+ unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long addr = (unsigned long)ptr;
+
+ return set_memory_rox(addr, nr);
+}
+
#else /* CONFIG_ARCH_HAS_EXECMEM_ROX */
static void *execmem_cache_alloc(struct execmem_range *range, size_t size)
{
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 16bfe1c694dd..88998725f1c5 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1435,6 +1435,8 @@ const char * const vmstat_text[] = {
#ifdef CONFIG_X86
"direct_map_level2_splits",
"direct_map_level3_splits",
+ "direct_map_level2_collapses",
+ "direct_map_level3_collapses",
#endif
#ifdef CONFIG_PER_VMA_LOCK_STATS
"vma_lock_success",
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index fe1362c34564..181aa604f8cd 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -850,5 +850,6 @@ bool arch_is_rethunk(struct symbol *sym)
bool arch_is_embedded_insn(struct symbol *sym)
{
return !strcmp(sym->name, "retbleed_return_thunk") ||
+ !strcmp(sym->name, "srso_alias_safe_ret") ||
!strcmp(sym->name, "srso_safe_ret");
}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index ce973d9d8e6d..814d40724069 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1284,15 +1284,6 @@ static void annotate_call_site(struct objtool_file *file,
if (!sym)
sym = reloc->sym;
- /*
- * Alternative replacement code is just template code which is
- * sometimes copied to the original instruction. For now, don't
- * annotate it. (In the future we might consider annotating the
- * original instruction if/when it ever makes sense to do so.)
- */
- if (!strcmp(insn->sec->name, ".altinstr_replacement"))
- return;
-
if (sym->static_call_tramp) {
list_add_tail(&insn->call_node, &file->static_call_list);
return;
@@ -1350,7 +1341,8 @@ static void annotate_call_site(struct objtool_file *file,
return;
}
- if (insn->type == INSN_CALL && !insn->sec->init)
+ if (insn->type == INSN_CALL && !insn->sec->init &&
+ !insn->_call_dest->embedded_insn)
list_add_tail(&insn->call_node, &file->call_list);
if (!sibling && dead_end_function(file, sym))