- Add the call depth tracking mitigation for Retbleed which has

been long in the making. It is a lighterweight software-only fix for
 Skylake-based cores where enabling IBRS is a big hammer and causes a
 significant performance impact.
 
 What it basically does is, it aligns all kernel functions to 16 bytes
 boundary and adds a 16-byte padding before the function, objtool
 collects all functions' locations and when the mitigation gets applied,
 it patches a call accounting thunk which is used to track the call depth
 of the stack at any time.
 
 When that call depth reaches a magical, microarchitecture-specific value
 for the Return Stack Buffer, the code stuffs that RSB and avoids its
 underflow which could otherwise lead to the Intel variant of Retbleed.
 
 This software-only solution brings a lot of the lost performance back,
 as benchmarks suggest:
 
   https://lore.kernel.org/all/20220915111039.092790446@infradead.org/
 
 That page above also contains a lot more detailed explanation of the
 whole mechanism
 
 - Implement a new control flow integrity scheme called FineIBT which is
 based on the software kCFI implementation and uses hardware IBT support
 where present to annotate and track indirect branches using a hash to
 validate them
 
 - Other misc fixes and cleanups
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmOZp5EACgkQEsHwGGHe
 VUrZFxAAvi/+8L0IYSK4mKJvixGbTFjxN/Swo2JVOfs34LqGUT6JaBc+VUMwZxdb
 VMTFIZ3ttkKEodjhxGI7oGev6V8UfhI37SmO2lYKXpQVjXXnMlv/M+Vw3teE38CN
 gopi+xtGnT1IeWQ3tc/Tv18pleJ0mh5HKWiW+9KoqgXj0wgF9x4eRYDz1TDCDA/A
 iaBzs56j8m/FSykZHnrWZ/MvjKNPdGlfJASUCPeTM2dcrXQGJ93+X2hJctzDte0y
 Nuiw6Y0htfFBE7xoJn+sqm5Okr+McoUM18/CCprbgSKYk18iMYm3ZtAi6FUQZS1A
 ua4wQCf49loGp15PO61AS5d3OBf5D3q/WihQRbCaJvTVgPp9sWYnWwtcVUuhMllh
 ZQtBU9REcVJ/22bH09Q9CjBW0VpKpXHveqQdqRDViLJ6v/iI6EFGmD24SW/VxyRd
 73k9MBGrL/dOf1SbEzdsnvcSB3LGzp0Om8o/KzJWOomrVKjBCJy16bwTEsCZEJmP
 i406m92GPXeaN1GhTko7vmF0GnkEdJs1GVCZPluCAxxbhHukyxHnrjlQjI4vC80n
 Ylc0B3Kvitw7LGJsPqu+/jfNHADC/zhx1qz/30wb5cFmFbN1aRdp3pm8JYUkn+l/
 zri2Y6+O89gvE/9/xUhMohzHsWUO7xITiBavewKeTP9GSWybWUs=
 =cRy1
 -----END PGP SIGNATURE-----

Merge tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 core updates from Borislav Petkov:

 - Add the call depth tracking mitigation for Retbleed which has been
   long in the making. It is a lighterweight software-only fix for
   Skylake-based cores where enabling IBRS is a big hammer and causes a
   significant performance impact.

   What it basically does is, it aligns all kernel functions to 16 bytes
   boundary and adds a 16-byte padding before the function, objtool
   collects all functions' locations and when the mitigation gets
   applied, it patches a call accounting thunk which is used to track
   the call depth of the stack at any time.

   When that call depth reaches a magical, microarchitecture-specific
   value for the Return Stack Buffer, the code stuffs that RSB and
   avoids its underflow which could otherwise lead to the Intel variant
   of Retbleed.

   This software-only solution brings a lot of the lost performance
   back, as benchmarks suggest:

       https://lore.kernel.org/all/20220915111039.092790446@infradead.org/

   That page above also contains a lot more detailed explanation of the
   whole mechanism

 - Implement a new control flow integrity scheme called FineIBT which is
   based on the software kCFI implementation and uses hardware IBT
   support where present to annotate and track indirect branches using a
   hash to validate them

 - Other misc fixes and cleanups

* tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (80 commits)
  x86/paravirt: Use common macro for creating simple asm paravirt functions
  x86/paravirt: Remove clobber bitmask from .parainstructions
  x86/debug: Include percpu.h in debugreg.h to get DECLARE_PER_CPU() et al
  x86/cpufeatures: Move X86_FEATURE_CALL_DEPTH from bit 18 to bit 19 of word 11, to leave space for WIP X86_FEATURE_SGX_EDECCSSA bit
  x86/Kconfig: Enable kernel IBT by default
  x86,pm: Force out-of-line memcpy()
  objtool: Fix weak hole vs prefix symbol
  objtool: Optimize elf_dirty_reloc_sym()
  x86/cfi: Add boot time hash randomization
  x86/cfi: Boot time selection of CFI scheme
  x86/ibt: Implement FineIBT
  objtool: Add --cfi to generate the .cfi_sites section
  x86: Add prefix symbols for function padding
  objtool: Add option to generate prefix symbols
  objtool: Avoid O(bloody terrible) behaviour -- an ode to libelf
  objtool: Slice up elf_create_section_symbol()
  kallsyms: Revert "Take callthunks into account"
  x86: Unconfuse CONFIG_ and X86_FEATURE_ namespaces
  x86/retpoline: Fix crash printing warning
  x86/paravirt: Fix a !PARAVIRT build warning
  ...

Makefile

@@ -1006,8 +1006,8 @@ KBUILD_CFLAGS	+= $(CC_FLAGS_CFI)
 export CC_FLAGS_CFI
 endif
 
-ifdef CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B
-KBUILD_CFLAGS += -falign-functions=64
+ifneq ($(CONFIG_FUNCTION_ALIGNMENT),0)
+KBUILD_CFLAGS += -falign-functions=$(CONFIG_FUNCTION_ALIGNMENT)
 endif
 
 # arch Makefile may override CC so keep this after arch Makefile is included

arch/Kconfig

@@ -1438,4 +1438,28 @@ source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
 
+config FUNCTION_ALIGNMENT_4B
+	bool
+
+config FUNCTION_ALIGNMENT_8B
+	bool
+
+config FUNCTION_ALIGNMENT_16B
+	bool
+
+config FUNCTION_ALIGNMENT_32B
+	bool
+
+config FUNCTION_ALIGNMENT_64B
+	bool
+
+config FUNCTION_ALIGNMENT
+	int
+	default 64 if FUNCTION_ALIGNMENT_64B
+	default 32 if FUNCTION_ALIGNMENT_32B
+	default 16 if FUNCTION_ALIGNMENT_16B
+	default 8 if FUNCTION_ALIGNMENT_8B
+	default 4 if FUNCTION_ALIGNMENT_4B
+	default 0
+
 endmenu

arch/ia64/Kconfig

@@ -63,6 +63,7 @@ config IA64
 	select NUMA if !FLATMEM
 	select PCI_MSI_ARCH_FALLBACKS if PCI_MSI
 	select ZONE_DMA32
+	select FUNCTION_ALIGNMENT_32B
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to

arch/ia64/Makefile

@@ -23,7 +23,7 @@ KBUILD_AFLAGS_KERNEL := -mconstant-gp
 EXTRA		:=
 
 cflags-y	:= -pipe $(EXTRA) -ffixed-r13 -mfixed-range=f12-f15,f32-f127 \
-		   -falign-functions=32 -frename-registers -fno-optimize-sibling-calls
+		   -frename-registers -fno-optimize-sibling-calls
 KBUILD_CFLAGS_KERNEL := -mconstant-gp
 
 GAS_STATUS	= $(shell $(srctree)/arch/ia64/scripts/check-gas "$(CC)" "$(OBJDUMP)")

arch/um/kernel/um_arch.c

@@ -444,6 +444,11 @@ void apply_returns(s32 *start, s32 *end)
 {
 }
 
+void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+		   s32 *start_cfi, s32 *end_cfi)
+{
+}
+
 void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }

arch/x86/Kconfig

@@ -292,6 +292,8 @@ config X86
 	select X86_FEATURE_NAMES		if PROC_FS
 	select PROC_PID_ARCH_STATUS		if PROC_FS
 	select HAVE_ARCH_NODE_DEV_GROUP		if X86_SGX
+	select FUNCTION_ALIGNMENT_16B		if X86_64 || X86_ALIGNMENT_16
+	select FUNCTION_ALIGNMENT_4B
 	imply IMA_SECURE_AND_OR_TRUSTED_BOOT    if EFI
 	select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
 
@@ -1855,7 +1857,7 @@ config CC_HAS_IBT
 
 config X86_KERNEL_IBT
 	prompt "Indirect Branch Tracking"
-	bool
+	def_bool y
 	depends on X86_64 && CC_HAS_IBT && HAVE_OBJTOOL
 	# https://github.com/llvm/llvm-project/commit/9d7001eba9c4cb311e03cd8cdc231f9e579f2d0f
 	depends on !LD_IS_LLD || LLD_VERSION >= 140000
@@ -2492,6 +2494,46 @@ config CC_HAS_SLS
 config CC_HAS_RETURN_THUNK
 	def_bool $(cc-option,-mfunction-return=thunk-extern)
 
+config CC_HAS_ENTRY_PADDING
+	def_bool $(cc-option,-fpatchable-function-entry=16,16)
+
+config FUNCTION_PADDING_CFI
+	int
+	default 59 if FUNCTION_ALIGNMENT_64B
+	default 27 if FUNCTION_ALIGNMENT_32B
+	default 11 if FUNCTION_ALIGNMENT_16B
+	default  3 if FUNCTION_ALIGNMENT_8B
+	default  0
+
+# Basically: FUNCTION_ALIGNMENT - 5*CFI_CLANG
+# except Kconfig can't do arithmetic :/
+config FUNCTION_PADDING_BYTES
+	int
+	default FUNCTION_PADDING_CFI if CFI_CLANG
+	default FUNCTION_ALIGNMENT
+
+config CALL_PADDING
+	def_bool n
+	depends on CC_HAS_ENTRY_PADDING && OBJTOOL
+	select FUNCTION_ALIGNMENT_16B
+
+config FINEIBT
+	def_bool y
+	depends on X86_KERNEL_IBT && CFI_CLANG && RETPOLINE
+	select CALL_PADDING
+
+config HAVE_CALL_THUNKS
+	def_bool y
+	depends on CC_HAS_ENTRY_PADDING && RETHUNK && OBJTOOL
+
+config CALL_THUNKS
+	def_bool n
+	select CALL_PADDING
+
+config PREFIX_SYMBOLS
+	def_bool y
+	depends on CALL_PADDING && !CFI_CLANG
+
 menuconfig SPECULATION_MITIGATIONS
 	bool "Mitigations for speculative execution vulnerabilities"
 	default y
@@ -2543,6 +2585,37 @@ config CPU_UNRET_ENTRY
 	help
 	  Compile the kernel with support for the retbleed=unret mitigation.
 
+config CALL_DEPTH_TRACKING
+	bool "Mitigate RSB underflow with call depth tracking"
+	depends on CPU_SUP_INTEL && HAVE_CALL_THUNKS
+	select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
+	select CALL_THUNKS
+	default y
+	help
+	  Compile the kernel with call depth tracking to mitigate the Intel
+	  SKL Return-Speculation-Buffer (RSB) underflow issue. The
+	  mitigation is off by default and needs to be enabled on the
+	  kernel command line via the retbleed=stuff option. For
+	  non-affected systems the overhead of this option is marginal as
+	  the call depth tracking is using run-time generated call thunks
+	  in a compiler generated padding area and call patching. This
+	  increases text size by ~5%. For non affected systems this space
+	  is unused. On affected SKL systems this results in a significant
+	  performance gain over the IBRS mitigation.
+
+config CALL_THUNKS_DEBUG
+	bool "Enable call thunks and call depth tracking debugging"
+	depends on CALL_DEPTH_TRACKING
+	select FUNCTION_ALIGNMENT_32B
+	default n
+	help
+	  Enable call/ret counters for imbalance detection and build in
+	  a noisy dmesg about callthunks generation and call patching for
+	  trouble shooting. The debug prints need to be enabled on the
+	  kernel command line with 'debug-callthunks'.
+	  Only enable this, when you are debugging call thunks as this
+	  creates a noticable runtime overhead. If unsure say N.
+
 config CPU_IBPB_ENTRY
 	bool "Enable IBPB on kernel entry"
 	depends on CPU_SUP_AMD && X86_64

arch/x86/Makefile

@@ -208,6 +208,12 @@ ifdef CONFIG_SLS
   KBUILD_CFLAGS += -mharden-sls=all
 endif
 
+ifdef CONFIG_CALL_PADDING
+PADDING_CFLAGS := -fpatchable-function-entry=$(CONFIG_FUNCTION_PADDING_BYTES),$(CONFIG_FUNCTION_PADDING_BYTES)
+KBUILD_CFLAGS += $(PADDING_CFLAGS)
+export PADDING_CFLAGS
+endif
+
 KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE)
 
 ifdef CONFIG_LTO_CLANG

arch/x86/boot/compressed/head_64.S

@@ -37,6 +37,14 @@
 #include <asm/trapnr.h>
 #include "pgtable.h"
 
+/*
+ * Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result
+ * in assembly errors due to trying to move .org backward due to the excessive
+ * alignment.
+ */
+#undef __ALIGN
+#define __ALIGN		.balign	16, 0x90
+
 /*
  * Locally defined symbols should be marked hidden:
  */

arch/x86/crypto/camellia-aesni-avx-asm_64.S

@@ -712,7 +712,6 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 .text
 
-.align 8
 SYM_FUNC_START_LOCAL(__camellia_enc_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -799,7 +798,6 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk16)
 	jmp .Lenc_done;
 SYM_FUNC_END(__camellia_enc_blk16)
 
-.align 8
 SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX

arch/x86/crypto/camellia-aesni-avx2-asm_64.S

@@ -221,7 +221,6 @@
  * Size optimization... with inlined roundsm32 binary would be over 5 times
  * larger and would only marginally faster.
  */
-.align 8
 SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 	roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7,
 		  %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15,
@@ -229,7 +228,6 @@ SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_c
 	RET;
 SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
-.align 8
 SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3,
 		  %ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11,
@@ -748,7 +746,6 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 .text
 
-.align 8
 SYM_FUNC_START_LOCAL(__camellia_enc_blk32)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -835,7 +832,6 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk32)
 	jmp .Lenc_done;
 SYM_FUNC_END(__camellia_enc_blk32)
 
-.align 8
 SYM_FUNC_START_LOCAL(__camellia_dec_blk32)
 	/* input:
 	 *	%rdi: ctx, CTX

arch/x86/crypto/cast5-avx-x86_64-asm_64.S

@@ -208,7 +208,6 @@
 
 .text
 
-.align 16
 SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 	/* input:
 	 *	%rdi: ctx
@@ -282,7 +281,6 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 	RET;
 SYM_FUNC_END(__cast5_enc_blk16)
 
-.align 16
 SYM_FUNC_START_LOCAL(__cast5_dec_blk16)
 	/* input:
 	 *	%rdi: ctx

arch/x86/crypto/crct10dif-pcl-asm_64.S

@@ -94,7 +94,6 @@
 #
 # Assumes len >= 16.
 #
-.align 16
 SYM_FUNC_START(crc_t10dif_pcl)
 
 	movdqa	.Lbswap_mask(%rip), BSWAP_MASK

arch/x86/crypto/poly1305-x86_64-cryptogams.pl

@@ -108,7 +108,6 @@ if (!$kernel) {
 sub declare_function() {
 	my ($name, $align, $nargs) = @_;
 	if($kernel) {
-		$code .= ".align $align\n";
 		$code .= "SYM_FUNC_START($name)\n";
 		$code .= ".L$name:\n";
 	} else {

arch/x86/crypto/serpent-avx-x86_64-asm_64.S

@@ -550,7 +550,6 @@
 #define write_blocks(x0, x1, x2, x3, t0, t1, t2) \
 	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
 
-.align 8
 SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -604,7 +603,6 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx)
 	RET;
 SYM_FUNC_END(__serpent_enc_blk8_avx)
 
-.align 8
 SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
 	/* input:
 	 *	%rdi: ctx, CTX

arch/x86/crypto/serpent-avx2-asm_64.S

@@ -550,7 +550,6 @@
 #define write_blocks(x0, x1, x2, x3, t0, t1, t2) \
 	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
 
-.align 8
 SYM_FUNC_START_LOCAL(__serpent_enc_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -604,7 +603,6 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk16)
 	RET;
 SYM_FUNC_END(__serpent_enc_blk16)
 
-.align 8
 SYM_FUNC_START_LOCAL(__serpent_dec_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX

arch/x86/crypto/sha1_ni_asm.S

@@ -93,7 +93,6 @@
  * numBlocks: Number of blocks to process
  */
 .text
-.align 32
 SYM_TYPED_FUNC_START(sha1_ni_transform)
 	push		%rbp
 	mov		%rsp, %rbp

arch/x86/crypto/sha256-avx-asm.S

@@ -348,7 +348,6 @@ a = TMP_
 ########################################################################
 .text
 SYM_TYPED_FUNC_START(sha256_transform_avx)
-.align 32
 	pushq   %rbx
 	pushq   %r12
 	pushq   %r13

arch/x86/crypto/sha256-avx2-asm.S

@@ -525,7 +525,6 @@ STACK_SIZE	= _CTX      + _CTX_SIZE
 ########################################################################
 .text
 SYM_TYPED_FUNC_START(sha256_transform_rorx)
-.align 32
 	pushq	%rbx
 	pushq	%r12
 	pushq	%r13

arch/x86/crypto/sha256-ssse3-asm.S

@@ -357,7 +357,6 @@ a = TMP_
 ########################################################################
 .text
 SYM_TYPED_FUNC_START(sha256_transform_ssse3)
-.align 32
 	pushq   %rbx
 	pushq   %r12
 	pushq   %r13

arch/x86/crypto/sha256_ni_asm.S

@@ -97,7 +97,6 @@
  */
 
 .text
-.align 32
 SYM_TYPED_FUNC_START(sha256_ni_transform)
 
 	shl		$6, NUM_BLKS		/*  convert to bytes */

arch/x86/crypto/sm3-avx-asm_64.S

@@ -328,7 +328,6 @@
  * void sm3_transform_avx(struct sm3_state *state,
  *                        const u8 *data, int nblocks);
  */
-.align 16
 SYM_TYPED_FUNC_START(sm3_transform_avx)
 	/* input:
 	 *	%rdi: ctx, CTX

arch/x86/crypto/sm4-aesni-avx-asm_64.S

@@ -140,13 +140,11 @@
 
 
 .text
-.align 16
 
 /*
  * void sm4_aesni_avx_crypt4(const u32 *rk, u8 *dst,
  *                           const u8 *src, int nblocks)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx_crypt4)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -250,7 +248,6 @@ SYM_FUNC_START(sm4_aesni_avx_crypt4)
 	RET;
 SYM_FUNC_END(sm4_aesni_avx_crypt4)
 
-.align 8
 SYM_FUNC_START_LOCAL(__sm4_crypt_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -364,7 +361,6 @@ SYM_FUNC_END(__sm4_crypt_blk8)
  * void sm4_aesni_avx_crypt8(const u32 *rk, u8 *dst,
  *                           const u8 *src, int nblocks)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx_crypt8)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -420,7 +416,6 @@ SYM_FUNC_END(sm4_aesni_avx_crypt8)
  * void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst,
  *                                 const u8 *src, u8 *iv)
  */
-.align 8
 SYM_TYPED_FUNC_START(sm4_aesni_avx_ctr_enc_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -495,7 +490,6 @@ SYM_FUNC_END(sm4_aesni_avx_ctr_enc_blk8)
  * void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst,
  *                                 const u8 *src, u8 *iv)
  */
-.align 8
 SYM_TYPED_FUNC_START(sm4_aesni_avx_cbc_dec_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -545,7 +539,6 @@ SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8)
  * void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst,
  *                                 const u8 *src, u8 *iv)
  */
-.align 8
 SYM_TYPED_FUNC_START(sm4_aesni_avx_cfb_dec_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX

arch/x86/crypto/sm4-aesni-avx2-asm_64.S

@@ -154,9 +154,6 @@
 	.long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
 
 .text
-.align 16
-
-.align 8
 SYM_FUNC_START_LOCAL(__sm4_crypt_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -282,7 +279,6 @@ SYM_FUNC_END(__sm4_crypt_blk16)
  * void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst,
  *                                   const u8 *src, u8 *iv)
  */
-.align 8
 SYM_TYPED_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -395,7 +391,6 @@ SYM_FUNC_END(sm4_aesni_avx2_ctr_enc_blk16)
  * void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst,
  *                                   const u8 *src, u8 *iv)
  */
-.align 8
 SYM_TYPED_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -449,7 +444,6 @@ SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16)
  * void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst,
  *                                   const u8 *src, u8 *iv)
  */
-.align 8
 SYM_TYPED_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX

arch/x86/crypto/twofish-avx-x86_64-asm_64.S

@@ -228,7 +228,6 @@
 	vpxor		x2, wkey, x2; \
 	vpxor		x3, wkey, x3;
 
-.align 8
 SYM_FUNC_START_LOCAL(__twofish_enc_blk8)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -270,7 +269,6 @@ SYM_FUNC_START_LOCAL(__twofish_enc_blk8)
 	RET;
 SYM_FUNC_END(__twofish_enc_blk8)
 
-.align 8
 SYM_FUNC_START_LOCAL(__twofish_dec_blk8)
 	/* input:
 	 *	%rdi: ctx, CTX

arch/x86/entry/entry_32.S

@@ -1181,7 +1181,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 * is using the thread stack right now, so it's safe for us to use it.
 	 */
 	movl	%esp, %ebx
-	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
+	movl	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esp
 	call	exc_nmi
 	movl	%ebx, %esp
 
@@ -1243,7 +1243,7 @@ SYM_CODE_START(rewind_stack_and_make_dead)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
-	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esi
+	movl	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esi
 	leal	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
 
 	call	make_task_dead

arch/x86/entry/entry_64.S

@@ -92,7 +92,7 @@ SYM_CODE_START(entry_SYSCALL_64)
 	/* tss.sp2 is scratch space. */
 	movq	%rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
 
 SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
@@ -252,7 +252,7 @@ SYM_FUNC_START(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movq	TASK_stack_canary(%rsi), %rbx
-	movq	%rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset
+	movq	%rbx, PER_CPU_VAR(fixed_percpu_data) + FIXED_stack_canary
 #endif
 
 	/*
@@ -284,9 +284,11 @@ SYM_FUNC_END(__switch_to_asm)
  * r12: kernel thread arg
  */
 .pushsection .text, "ax"
-SYM_CODE_START(ret_from_fork)
+	__FUNC_ALIGN
+SYM_CODE_START_NOALIGN(ret_from_fork)
 	UNWIND_HINT_EMPTY
 	ANNOTATE_NOENDBR // copy_thread
+	CALL_DEPTH_ACCOUNT
 	movq	%rax, %rdi
 	call	schedule_tail			/* rdi: 'prev' task parameter */
 
@@ -326,11 +328,12 @@ SYM_CODE_END(ret_from_fork)
 #endif
 .endm
 
-SYM_CODE_START_LOCAL(xen_error_entry)
+SYM_CODE_START(xen_error_entry)
+	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
-	UNTRAIN_RET
+	UNTRAIN_RET_FROM_CALL
 	RET
 SYM_CODE_END(xen_error_entry)
 
@@ -600,13 +603,13 @@ SYM_CODE_END(\asmsym)
  * shared between 32 and 64 bit and emit the __irqentry_text_* markers
  * so the stacktrace boundary checks work.
  */
-	.align 16
+	__ALIGN
 	.globl __irqentry_text_start
 __irqentry_text_start:
 
 #include <asm/idtentry.h>
 
-	.align 16
+	__ALIGN
 	.globl __irqentry_text_end
 __irqentry_text_end:
 	ANNOTATE_NOENDBR
@@ -828,7 +831,8 @@ EXPORT_SYMBOL(asm_load_gs_index)
  *
  * C calling convention: exc_xen_hypervisor_callback(struct *pt_regs)
  */
-SYM_CODE_START_LOCAL(exc_xen_hypervisor_callback)
+	__FUNC_ALIGN
+SYM_CODE_START_LOCAL_NOALIGN(exc_xen_hypervisor_callback)
 
 /*
  * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
@@ -856,7 +860,8 @@ SYM_CODE_END(exc_xen_hypervisor_callback)
  * We distinguish between categories by comparing each saved segment register
  * with its current contents: any discrepancy means we in category 1.
  */
-SYM_CODE_START(xen_failsafe_callback)
+	__FUNC_ALIGN
+SYM_CODE_START_NOALIGN(xen_failsafe_callback)
 	UNWIND_HINT_EMPTY
 	ENDBR
 	movl	%ds, %ecx
@@ -903,7 +908,8 @@ SYM_CODE_END(xen_failsafe_callback)
  * R14 - old CR3
  * R15 - old SPEC_CTRL
  */
-SYM_CODE_START_LOCAL(paranoid_entry)
+SYM_CODE_START(paranoid_entry)
+	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
@@ -972,7 +978,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	 * CR3 above, keep the old value in a callee saved register.
 	 */
 	IBRS_ENTER save_reg=%r15
-	UNTRAIN_RET
+	UNTRAIN_RET_FROM_CALL
 
 	RET
 SYM_CODE_END(paranoid_entry)
@@ -1038,7 +1044,8 @@ SYM_CODE_END(paranoid_exit)
 /*
  * Switch GS and CR3 if needed.
  */
-SYM_CODE_START_LOCAL(error_entry)
+SYM_CODE_START(error_entry)
+	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 
 	PUSH_AND_CLEAR_REGS save_ret=1
@@ -1056,14 +1063,11 @@ SYM_CODE_START_LOCAL(error_entry)
 	/* We have user CR3.  Change to kernel CR3. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	IBRS_ENTER
-	UNTRAIN_RET
+	UNTRAIN_RET_FROM_CALL
 
 	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
-.Lerror_entry_from_usermode_after_swapgs:
-
 	/* Put us onto the real thread stack. */
-	call	sync_regs
-	RET
+	jmp	sync_regs
 
 	/*
 	 * There are two places in the kernel that can potentially fault with
@@ -1094,6 +1098,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 */
 .Lerror_entry_done_lfence:
 	FENCE_SWAPGS_KERNEL_ENTRY
+	CALL_DEPTH_ACCOUNT
 	leaq	8(%rsp), %rax			/* return pt_regs pointer */
 	ANNOTATE_UNRET_END
 	RET
@@ -1112,7 +1117,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	IBRS_ENTER
-	UNTRAIN_RET
+	UNTRAIN_RET_FROM_CALL
 
 	/*
 	 * Pretend that the exception came from user mode: set up pt_regs
@@ -1121,7 +1126,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
 	call	fixup_bad_iret
 	mov	%rax, %rdi
-	jmp	.Lerror_entry_from_usermode_after_swapgs
+	jmp	sync_regs
 SYM_CODE_END(error_entry)
 
 SYM_CODE_START_LOCAL(error_return)
@@ -1206,7 +1211,7 @@ SYM_CODE_START(asm_exc_nmi)
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
 	UNWIND_HINT_IRET_REGS base=%rdx offset=8
 	pushq	5*8(%rdx)	/* pt_regs->ss */
 	pushq	4*8(%rdx)	/* pt_regs->rsp */
@@ -1516,12 +1521,13 @@ SYM_CODE_END(ignore_sysret)
 #endif
 
 .pushsection .text, "ax"
-SYM_CODE_START(rewind_stack_and_make_dead)
+	__FUNC_ALIGN
+SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead)
 	UNWIND_HINT_FUNC
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
+	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rax
 	leaq	-PTREGS_SIZE(%rax), %rsp
 	UNWIND_HINT_REGS
 

arch/x86/entry/entry_64_compat.S

@@ -58,7 +58,7 @@ SYM_CODE_START(entry_SYSENTER_compat)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	popq	%rax
 
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
 
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER_DS		/* pt_regs->ss */
@@ -128,7 +128,6 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
 	popfq
 	jmp	.Lsysenter_flags_fixed
 SYM_INNER_LABEL(__end_entry_SYSENTER_compat, SYM_L_GLOBAL)
-	ANNOTATE_NOENDBR // is_sysenter_singlestep
 SYM_CODE_END(entry_SYSENTER_compat)
 
 /*
@@ -191,7 +190,7 @@ SYM_CODE_START(entry_SYSCALL_compat)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
 
 	/* Switch to the kernel stack */
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
 
 SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
@@ -332,7 +331,7 @@ SYM_CODE_START(entry_INT80_compat)
 	ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
 
 	movq	%rsp, %rax
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
 
 	pushq	5*8(%rax)		/* regs->ss */
 	pushq	4*8(%rax)		/* regs->rsp */

arch/x86/entry/thunk_64.S

@@ -11,7 +11,7 @@
 
 	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 	.macro THUNK name, func
-SYM_FUNC_START_NOALIGN(\name)
+SYM_FUNC_START(\name)
 	pushq %rbp
 	movq %rsp, %rbp
 
@@ -36,7 +36,7 @@ SYM_FUNC_END(\name)
 	EXPORT_SYMBOL(preempt_schedule_thunk)
 	EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
 
-SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore)
+SYM_CODE_START_LOCAL(__thunk_restore)
 	popq %r11
 	popq %r10
 	popq %r9

arch/x86/entry/vdso/Makefile

@@ -33,11 +33,12 @@ vobjs32-y += vdso32/vclock_gettime.o
 vobjs-$(CONFIG_X86_SGX)	+= vsgx.o
 
 # files to link into kernel
-obj-y				+= vma.o extable.o
-KASAN_SANITIZE_vma.o		:= y
-UBSAN_SANITIZE_vma.o		:= y
-KCSAN_SANITIZE_vma.o		:= y
-OBJECT_FILES_NON_STANDARD_vma.o	:= n
+obj-y					+= vma.o extable.o
+KASAN_SANITIZE_vma.o			:= y
+UBSAN_SANITIZE_vma.o			:= y
+KCSAN_SANITIZE_vma.o			:= y
+OBJECT_FILES_NON_STANDARD_vma.o		:= n
+OBJECT_FILES_NON_STANDARD_extable.o	:= n
 
 # vDSO images to build
 vdso_img-$(VDSO64-y)		+= 64
@@ -94,7 +95,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),)
 endif
 endif
 
-$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(PADDING_CFLAGS) $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 $(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO
 
 #
@@ -157,6 +158,7 @@ KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_CFI),$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(PADDING_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
 KBUILD_CFLAGS_32 += -fno-stack-protector
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)

arch/x86/include/asm/alternative.h

@@ -78,8 +78,43 @@ 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_ibt_endbr(s32 *start, s32 *end);
+extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
+			  s32 *start_cfi, s32 *end_cfi);
 
 struct module;
+struct paravirt_patch_site;
+
+struct callthunk_sites {
+	s32				*call_start, *call_end;
+	struct paravirt_patch_site	*pv_start, *pv_end;
+};
+
+#ifdef CONFIG_CALL_THUNKS
+extern void callthunks_patch_builtin_calls(void);
+extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
+					  struct module *mod);
+extern void *callthunks_translate_call_dest(void *dest);
+extern bool is_callthunk(void *addr);
+extern int x86_call_depth_emit_accounting(u8 **pprog, void *func);
+#else
+static __always_inline void callthunks_patch_builtin_calls(void) {}
+static __always_inline void
+callthunks_patch_module_calls(struct callthunk_sites *sites,
+			      struct module *mod) {}
+static __always_inline void *callthunks_translate_call_dest(void *dest)
+{
+	return dest;
+}
+static __always_inline bool is_callthunk(void *addr)
+{
+	return false;
+}
+static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
+							  void *func)
+{
+	return 0;
+}
+#endif
 
 #ifdef CONFIG_SMP
 extern void alternatives_smp_module_add(struct module *mod, char *name,
@@ -347,6 +382,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 #define old_len			141b-140b
 #define new_len1		144f-143f
 #define new_len2		145f-144f
+#define new_len3		146f-145f
 
 /*
  * gas compatible max based on the idea from:
@@ -354,7 +390,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
  *
  * The additional "-" is needed because gas uses a "true" value of -1.
  */
-#define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+#define alt_max_2(a, b)		((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+#define alt_max_3(a, b, c)	(alt_max_2(alt_max_2(a, b), c))
 
 
 /*
@@ -366,8 +403,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
 140:
 	\oldinstr
 141:
-	.skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
-		(alt_max_short(new_len1, new_len2) - (old_len)),0x90
+	.skip -((alt_max_2(new_len1, new_len2) - (old_len)) > 0) * \
+		(alt_max_2(new_len1, new_len2) - (old_len)),0x90
 142:
 
 	.pushsection .altinstructions,"a"
@@ -384,6 +421,31 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	.popsection
 .endm
 
+.macro ALTERNATIVE_3 oldinstr, newinstr1, feature1, newinstr2, feature2, newinstr3, feature3
+140:
+	\oldinstr
+141:
+	.skip -((alt_max_3(new_len1, new_len2, new_len3) - (old_len)) > 0) * \
+		(alt_max_3(new_len1, new_len2, new_len3) - (old_len)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f
+	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f
+	altinstruction_entry 140b,145f,\feature3,142b-140b,146f-145f
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr1
+144:
+	\newinstr2
+145:
+	\newinstr3
+146:
+	.popsection
+.endm
+
 /* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
 #define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
 	ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\

arch/x86/include/asm/cpufeatures.h

@@ -305,8 +305,7 @@
 #define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
 #define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
 #define X86_FEATURE_SGX_EDECCSSA	(11*32+18) /* "" SGX EDECCSSA user leaf function */
-
-
+#define X86_FEATURE_CALL_DEPTH		(11*32+19) /* "" Call depth tracking for RSB stuffing */
 #define X86_FEATURE_MSR_TSX_CTRL	(11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */

arch/x86/include/asm/current.h

@@ -3,16 +3,42 @@
 #define _ASM_X86_CURRENT_H
 
 #include <linux/compiler.h>
-#include <asm/percpu.h>
 
 #ifndef __ASSEMBLY__
+
+#include <linux/cache.h>
+#include <asm/percpu.h>
+
 struct task_struct;
 
-DECLARE_PER_CPU(struct task_struct *, current_task);
+struct pcpu_hot {
+	union {
+		struct {
+			struct task_struct	*current_task;
+			int			preempt_count;
+			int			cpu_number;
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+			u64			call_depth;
+#endif
+			unsigned long		top_of_stack;
+			void			*hardirq_stack_ptr;
+			u16			softirq_pending;
+#ifdef CONFIG_X86_64
+			bool			hardirq_stack_inuse;
+#else
+			void			*softirq_stack_ptr;
+#endif
+		};
+		u8	pad[64];
+	};
+};
+static_assert(sizeof(struct pcpu_hot) == 64);
+
+DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot);
 
 static __always_inline struct task_struct *get_current(void)
 {
-	return this_cpu_read_stable(current_task);
+	return this_cpu_read_stable(pcpu_hot.current_task);
 }
 
 #define current get_current()

arch/x86/include/asm/debugreg.h

@@ -2,8 +2,8 @@
 #ifndef _ASM_X86_DEBUGREG_H
 #define _ASM_X86_DEBUGREG_H
 
-
 #include <linux/bug.h>
+#include <linux/percpu.h>
 #include <uapi/asm/debugreg.h>
 
 DECLARE_PER_CPU(unsigned long, cpu_dr7);

arch/x86/include/asm/disabled-features.h

@@ -69,6 +69,12 @@
 # define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
 #endif
 
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+# define DISABLE_CALL_DEPTH_TRACKING	0
+#else
+# define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
+#endif
+
 #ifdef CONFIG_INTEL_IOMMU_SVM
 # define DISABLE_ENQCMD		0
 #else
@@ -107,7 +113,8 @@
 #define DISABLED_MASK8	(DISABLE_XENPV|DISABLE_TDX_GUEST)
 #define DISABLED_MASK9	(DISABLE_SGX)
 #define DISABLED_MASK10	0
-#define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET)
+#define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
+			 DISABLE_CALL_DEPTH_TRACKING)
 #define DISABLED_MASK12	0
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0

arch/x86/include/asm/hardirq.h

@@ -3,9 +3,9 @@
 #define _ASM_X86_HARDIRQ_H
 
 #include <linux/threads.h>
+#include <asm/current.h>
 
 typedef struct {
-	u16	     __softirq_pending;
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 	u8	     kvm_cpu_l1tf_flush_l1d;
 #endif
@@ -60,6 +60,7 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu);
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat		arch_irq_stat
 
+#define local_softirq_pending_ref       pcpu_hot.softirq_pending
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 static inline void kvm_set_cpu_l1tf_flush_l1d(void)

arch/x86/include/asm/irq_stack.h

@@ -116,7 +116,7 @@
 	ASM_CALL_ARG2
 
 #define call_on_irqstack(func, asm_call, argconstr...)			\
-	call_on_stack(__this_cpu_read(hardirq_stack_ptr),		\
+	call_on_stack(__this_cpu_read(pcpu_hot.hardirq_stack_ptr),	\
 		      func, asm_call, argconstr)
 
 /* Macros to assert type correctness for run_*_on_irqstack macros */
@@ -135,7 +135,7 @@
 	 * User mode entry and interrupt on the irq stack do not	\
 	 * switch stacks. If from user mode the task stack is empty.	\
 	 */								\
-	if (user_mode(regs) || __this_cpu_read(hardirq_stack_inuse)) {	\
+	if (user_mode(regs) || __this_cpu_read(pcpu_hot.hardirq_stack_inuse)) { \
 		irq_enter_rcu();					\
 		func(c_args);						\
 		irq_exit_rcu();						\
@@ -146,9 +146,9 @@
 		 * places. Invoke the stack switch macro with the call	\
 		 * sequence which matches the above direct invocation.	\
 		 */							\
-		__this_cpu_write(hardirq_stack_inuse, true);		\
+		__this_cpu_write(pcpu_hot.hardirq_stack_inuse, true);	\
 		call_on_irqstack(func, asm_call, constr);		\
-		__this_cpu_write(hardirq_stack_inuse, false);		\
+		__this_cpu_write(pcpu_hot.hardirq_stack_inuse, false);	\
 	}								\
 }
 
@@ -212,9 +212,9 @@
  */
 #define do_softirq_own_stack()						\
 {									\
-	__this_cpu_write(hardirq_stack_inuse, true);			\
+	__this_cpu_write(pcpu_hot.hardirq_stack_inuse, true);		\
 	call_on_irqstack(__do_softirq, ASM_CALL_ARG0);			\
-	__this_cpu_write(hardirq_stack_inuse, false);			\
+	__this_cpu_write(pcpu_hot.hardirq_stack_inuse, false);		\
 }
 
 #endif

arch/x86/include/asm/linkage.h

@@ -12,13 +12,26 @@
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
 #endif /* CONFIG_X86_32 */
 
-#ifdef __ASSEMBLY__
-
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16)
-#define __ALIGN		.p2align 4, 0x90
+#define __ALIGN		.balign CONFIG_FUNCTION_ALIGNMENT, 0x90;
 #define __ALIGN_STR	__stringify(__ALIGN)
+
+#if defined(CONFIG_CALL_PADDING) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#define FUNCTION_PADDING	.skip CONFIG_FUNCTION_ALIGNMENT, 0x90;
+#else
+#define FUNCTION_PADDING
 #endif
 
+#if (CONFIG_FUNCTION_ALIGNMENT > 8) && !defined(__DISABLE_EXPORTS) && !defined(BULID_VDSO)
+# define __FUNC_ALIGN		__ALIGN; FUNCTION_PADDING
+#else
+# define __FUNC_ALIGN		__ALIGN
+#endif
+
+#define ASM_FUNC_ALIGN		__stringify(__FUNC_ALIGN)
+#define SYM_F_ALIGN		__FUNC_ALIGN
+
+#ifdef __ASSEMBLY__
+
 #if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
 #define RET	jmp __x86_return_thunk
 #else /* CONFIG_RETPOLINE */
@@ -43,11 +56,45 @@
 
 #endif /* __ASSEMBLY__ */
 
+/*
+ * Depending on -fpatchable-function-entry=N,N usage (CONFIG_CALL_PADDING) the
+ * CFI symbol layout changes.
+ *
+ * Without CALL_THUNKS:
+ *
+ * 	.align	FUNCTION_ALIGNMENT
+ * __cfi_##name:
+ * 	.skip	FUNCTION_PADDING, 0x90
+ * 	.byte   0xb8
+ * 	.long	__kcfi_typeid_##name
+ * name:
+ *
+ * With CALL_THUNKS:
+ *
+ * 	.align FUNCTION_ALIGNMENT
+ * __cfi_##name:
+ * 	.byte	0xb8
+ * 	.long	__kcfi_typeid_##name
+ * 	.skip	FUNCTION_PADDING, 0x90
+ * name:
+ *
+ * In both cases the whole thing is FUNCTION_ALIGNMENT aligned and sized.
+ */
+
+#ifdef CONFIG_CALL_PADDING
+#define CFI_PRE_PADDING
+#define CFI_POST_PADDING	.skip	CONFIG_FUNCTION_PADDING_BYTES, 0x90;
+#else
+#define CFI_PRE_PADDING		.skip	CONFIG_FUNCTION_PADDING_BYTES, 0x90;
+#define CFI_POST_PADDING
+#endif
+
 #define __CFI_TYPE(name)					\
 	SYM_START(__cfi_##name, SYM_L_LOCAL, SYM_A_NONE)	\
-	.fill 11, 1, 0x90 ASM_NL				\
+	CFI_PRE_PADDING						\
 	.byte 0xb8 ASM_NL					\
 	.long __kcfi_typeid_##name ASM_NL			\
+	CFI_POST_PADDING					\
 	SYM_FUNC_END(__cfi_##name)
 
 /* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */
@@ -57,7 +104,7 @@
 
 /* SYM_FUNC_START -- use for global functions */
 #define SYM_FUNC_START(name)				\
-	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
+	SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)	\
 	ENDBR
 
 /* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */
@@ -67,7 +114,7 @@
 
 /* SYM_FUNC_START_LOCAL -- use for local functions */
 #define SYM_FUNC_START_LOCAL(name)			\
-	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)	\
+	SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)	\
 	ENDBR
 
 /* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */
@@ -77,7 +124,7 @@
 
 /* SYM_FUNC_START_WEAK -- use for weak functions */
 #define SYM_FUNC_START_WEAK(name)			\
-	SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)	\
+	SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)	\
 	ENDBR
 
 /* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */

arch/x86/include/asm/nospec-branch.h

@@ -12,8 +12,104 @@
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 #include <asm/percpu.h>
+#include <asm/current.h>
 
-#define RETPOLINE_THUNK_SIZE	32
+/*
+ * Call depth tracking for Intel SKL CPUs to address the RSB underflow
+ * issue in software.
+ *
+ * The tracking does not use a counter. It uses uses arithmetic shift
+ * right on call entry and logical shift left on return.
+ *
+ * The depth tracking variable is initialized to 0x8000.... when the call
+ * depth is zero. The arithmetic shift right sign extends the MSB and
+ * saturates after the 12th call. The shift count is 5 for both directions
+ * so the tracking covers 12 nested calls.
+ *
+ *  Call
+ *  0: 0x8000000000000000	0x0000000000000000
+ *  1: 0xfc00000000000000	0xf000000000000000
+ * ...
+ * 11: 0xfffffffffffffff8	0xfffffffffffffc00
+ * 12: 0xffffffffffffffff	0xffffffffffffffe0
+ *
+ * After a return buffer fill the depth is credited 12 calls before the
+ * next stuffing has to take place.
+ *
+ * There is a inaccuracy for situations like this:
+ *
+ *  10 calls
+ *   5 returns
+ *   3 calls
+ *   4 returns
+ *   3 calls
+ *   ....
+ *
+ * The shift count might cause this to be off by one in either direction,
+ * but there is still a cushion vs. the RSB depth. The algorithm does not
+ * claim to be perfect and it can be speculated around by the CPU, but it
+ * is considered that it obfuscates the problem enough to make exploitation
+ * extremly difficult.
+ */
+#define RET_DEPTH_SHIFT			5
+#define RSB_RET_STUFF_LOOPS		16
+#define RET_DEPTH_INIT			0x8000000000000000ULL
+#define RET_DEPTH_INIT_FROM_CALL	0xfc00000000000000ULL
+#define RET_DEPTH_CREDIT		0xffffffffffffffffULL
+
+#ifdef CONFIG_CALL_THUNKS_DEBUG
+# define CALL_THUNKS_DEBUG_INC_CALLS				\
+	incq	%gs:__x86_call_count;
+# define CALL_THUNKS_DEBUG_INC_RETS				\
+	incq	%gs:__x86_ret_count;
+# define CALL_THUNKS_DEBUG_INC_STUFFS				\
+	incq	%gs:__x86_stuffs_count;
+# define CALL_THUNKS_DEBUG_INC_CTXSW				\
+	incq	%gs:__x86_ctxsw_count;
+#else
+# define CALL_THUNKS_DEBUG_INC_CALLS
+# define CALL_THUNKS_DEBUG_INC_RETS
+# define CALL_THUNKS_DEBUG_INC_STUFFS
+# define CALL_THUNKS_DEBUG_INC_CTXSW
+#endif
+
+#if defined(CONFIG_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS)
+
+#include <asm/asm-offsets.h>
+
+#define CREDIT_CALL_DEPTH					\
+	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+
+#define ASM_CREDIT_CALL_DEPTH					\
+	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+
+#define RESET_CALL_DEPTH					\
+	mov	$0x80, %rax;					\
+	shl	$56, %rax;					\
+	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+
+#define RESET_CALL_DEPTH_FROM_CALL				\
+	mov	$0xfc, %rax;					\
+	shl	$56, %rax;					\
+	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	CALL_THUNKS_DEBUG_INC_CALLS
+
+#define INCREMENT_CALL_DEPTH					\
+	sarq	$5, %gs:pcpu_hot + X86_call_depth;		\
+	CALL_THUNKS_DEBUG_INC_CALLS
+
+#define ASM_INCREMENT_CALL_DEPTH				\
+	sarq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	CALL_THUNKS_DEBUG_INC_CALLS
+
+#else
+#define CREDIT_CALL_DEPTH
+#define ASM_CREDIT_CALL_DEPTH
+#define RESET_CALL_DEPTH
+#define INCREMENT_CALL_DEPTH
+#define ASM_INCREMENT_CALL_DEPTH
+#define RESET_CALL_DEPTH_FROM_CALL
+#endif
 
 /*
  * Fill the CPU return stack buffer.
@@ -32,6 +128,7 @@
  * from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
  */
 
+#define RETPOLINE_THUNK_SIZE	32
 #define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
 
 /*
@@ -60,7 +157,9 @@
 	dec	reg;					\
 	jnz	771b;					\
 	/* barrier for jnz misprediction */		\
-	lfence;
+	lfence;						\
+	ASM_CREDIT_CALL_DEPTH				\
+	CALL_THUNKS_DEBUG_INC_CTXSW
 #else
 /*
  * i386 doesn't unconditionally have LFENCE, as such it can't
@@ -185,11 +284,32 @@
  * where we have a stack but before any RET instruction.
  */
 .macro UNTRAIN_RET
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY)
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
+	defined(CONFIG_CALL_DEPTH_TRACKING)
 	ANNOTATE_UNRET_END
-	ALTERNATIVE_2 "",						\
-	              CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET,		\
-		      "call entry_ibpb", X86_FEATURE_ENTRY_IBPB
+	ALTERNATIVE_3 "",						\
+		      CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET,		\
+		      "call entry_ibpb", X86_FEATURE_ENTRY_IBPB,	\
+		      __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+#endif
+.endm
+
+.macro UNTRAIN_RET_FROM_CALL
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
+	defined(CONFIG_CALL_DEPTH_TRACKING)
+	ANNOTATE_UNRET_END
+	ALTERNATIVE_3 "",						\
+		      CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET,		\
+		      "call entry_ibpb", X86_FEATURE_ENTRY_IBPB,	\
+		      __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH
+#endif
+.endm
+
+
+.macro CALL_DEPTH_ACCOUNT
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+	ALTERNATIVE "",							\
+		    __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
 #endif
 .endm
 
@@ -203,11 +323,45 @@
 
 typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
 extern retpoline_thunk_t __x86_indirect_thunk_array[];
+extern retpoline_thunk_t __x86_indirect_call_thunk_array[];
+extern retpoline_thunk_t __x86_indirect_jump_thunk_array[];
 
 extern void __x86_return_thunk(void);
 extern void zen_untrain_ret(void);
 extern void entry_ibpb(void);
 
+#ifdef CONFIG_CALL_THUNKS
+extern void (*x86_return_thunk)(void);
+#else
+#define x86_return_thunk	(&__x86_return_thunk)
+#endif
+
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+extern void __x86_return_skl(void);
+
+static inline void x86_set_skl_return_thunk(void)
+{
+	x86_return_thunk = &__x86_return_skl;
+}
+
+#define CALL_DEPTH_ACCOUNT					\
+	ALTERNATIVE("",						\
+		    __stringify(INCREMENT_CALL_DEPTH),		\
+		    X86_FEATURE_CALL_DEPTH)
+
+#ifdef CONFIG_CALL_THUNKS_DEBUG
+DECLARE_PER_CPU(u64, __x86_call_count);
+DECLARE_PER_CPU(u64, __x86_ret_count);
+DECLARE_PER_CPU(u64, __x86_stuffs_count);
+DECLARE_PER_CPU(u64, __x86_ctxsw_count);
+#endif
+#else
+static inline void x86_set_skl_return_thunk(void) {}
+
+#define CALL_DEPTH_ACCOUNT ""
+
+#endif
+
 #ifdef CONFIG_RETPOLINE
 
 #define GEN(reg) \
@@ -215,6 +369,16 @@ extern void entry_ibpb(void);
 #include <asm/GEN-for-each-reg.h>
 #undef GEN
 
+#define GEN(reg)						\
+	extern retpoline_thunk_t __x86_indirect_call_thunk_ ## reg;
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+#define GEN(reg)						\
+	extern retpoline_thunk_t __x86_indirect_jump_thunk_ ## reg;
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
 #ifdef CONFIG_X86_64
 
 /*

arch/x86/include/asm/paravirt.h

@@ -4,13 +4,13 @@
 /* Various instructions on x86 need to be replaced for
  * para-virtualization: those hooks are defined here. */
 
+#include <asm/paravirt_types.h>
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/pgtable_types.h>
 #include <asm/asm.h>
 #include <asm/nospec-branch.h>
 
-#include <asm/paravirt_types.h>
-
 #ifndef __ASSEMBLY__
 #include <linux/bug.h>
 #include <linux/types.h>
@@ -665,6 +665,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	asm(".pushsection " section ", \"ax\";"				\
 	    ".globl " PV_THUNK_NAME(func) ";"				\
 	    ".type " PV_THUNK_NAME(func) ", @function;"			\
+	    ASM_FUNC_ALIGN						\
 	    PV_THUNK_NAME(func) ":"					\
 	    ASM_ENDBR							\
 	    FRAME_BEGIN							\
@@ -730,6 +731,18 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #undef PVOP_VCALL4
 #undef PVOP_CALL4
 
+#define DEFINE_PARAVIRT_ASM(func, instr, sec)		\
+	asm (".pushsection " #sec ", \"ax\"\n"		\
+	     ".global " #func "\n\t"			\
+	     ".type " #func ", @function\n\t"		\
+	     ASM_FUNC_ALIGN "\n"			\
+	     #func ":\n\t"				\
+	     ASM_ENDBR					\
+	     instr "\n\t"				\
+	     ASM_RET					\
+	     ".size " #func ", . - " #func "\n\t"	\
+	     ".popsection")
+
 extern void default_banner(void);
 
 #else  /* __ASSEMBLY__ */

arch/x86/include/asm/paravirt_types.h

@@ -2,6 +2,24 @@
 #ifndef _ASM_X86_PARAVIRT_TYPES_H
 #define _ASM_X86_PARAVIRT_TYPES_H
 
+#ifndef __ASSEMBLY__
+/* These all sit in the .parainstructions section to tell us what to patch. */
+struct paravirt_patch_site {
+	u8 *instr;		/* original instructions */
+	u8 type;		/* type of this instruction */
+	u8 len;			/* length of original instruction */
+};
+
+/* Lazy mode for batching updates / context switch */
+enum paravirt_lazy_mode {
+	PARAVIRT_LAZY_NONE,
+	PARAVIRT_LAZY_MMU,
+	PARAVIRT_LAZY_CPU,
+};
+#endif
+
+#ifdef CONFIG_PARAVIRT
+
 #ifndef __ASSEMBLY__
 
 #include <asm/desc_defs.h>
@@ -534,13 +552,6 @@ int paravirt_disable_iospace(void);
 	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
 		     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 
-/* Lazy mode for batching updates / context switch */
-enum paravirt_lazy_mode {
-	PARAVIRT_LAZY_NONE,
-	PARAVIRT_LAZY_MMU,
-	PARAVIRT_LAZY_CPU,
-};
-
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
 void paravirt_start_context_switch(struct task_struct *prev);
 void paravirt_end_context_switch(struct task_struct *next);
@@ -556,16 +567,9 @@ unsigned long paravirt_ret0(void);
 
 #define paravirt_nop	((void *)_paravirt_nop)
 
-/* These all sit in the .parainstructions section to tell us what to patch. */
-struct paravirt_patch_site {
-	u8 *instr;		/* original instructions */
-	u8 type;		/* type of this instruction */
-	u8 len;			/* length of original instruction */
-};
-
 extern struct paravirt_patch_site __parainstructions[],
 	__parainstructions_end[];
 
 #endif	/* __ASSEMBLY__ */
-
+#endif  /* CONFIG_PARAVIRT */
 #endif	/* _ASM_X86_PARAVIRT_TYPES_H */

arch/x86/include/asm/preempt.h

@@ -4,11 +4,11 @@
 
 #include <asm/rmwcc.h>
 #include <asm/percpu.h>
+#include <asm/current.h>
+
 #include <linux/thread_info.h>
 #include <linux/static_call_types.h>
 
-DECLARE_PER_CPU(int, __preempt_count);
-
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
@@ -24,7 +24,7 @@ DECLARE_PER_CPU(int, __preempt_count);
  */
 static __always_inline int preempt_count(void)
 {
-	return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
+	return raw_cpu_read_4(pcpu_hot.preempt_count) & ~PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline void preempt_count_set(int pc)
@@ -32,10 +32,10 @@ static __always_inline void preempt_count_set(int pc)
 	int old, new;
 
 	do {
-		old = raw_cpu_read_4(__preempt_count);
+		old = raw_cpu_read_4(pcpu_hot.preempt_count);
 		new = (old & PREEMPT_NEED_RESCHED) |
 			(pc & ~PREEMPT_NEED_RESCHED);
-	} while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old);
+	} while (raw_cpu_cmpxchg_4(pcpu_hot.preempt_count, old, new) != old);
 }
 
 /*
@@ -44,7 +44,7 @@ static __always_inline void preempt_count_set(int pc)
 #define init_task_preempt_count(p) do { } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
-	per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
+	per_cpu(pcpu_hot.preempt_count, (cpu)) = PREEMPT_DISABLED; \
 } while (0)
 
 /*
@@ -58,17 +58,17 @@ static __always_inline void preempt_count_set(int pc)
 
 static __always_inline void set_preempt_need_resched(void)
 {
-	raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
+	raw_cpu_and_4(pcpu_hot.preempt_count, ~PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline void clear_preempt_need_resched(void)
 {
-	raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
+	raw_cpu_or_4(pcpu_hot.preempt_count, PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline bool test_preempt_need_resched(void)
 {
-	return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
+	return !(raw_cpu_read_4(pcpu_hot.preempt_count) & PREEMPT_NEED_RESCHED);
 }
 
 /*
@@ -77,12 +77,12 @@ static __always_inline bool test_preempt_need_resched(void)
 
 static __always_inline void __preempt_count_add(int val)
 {
-	raw_cpu_add_4(__preempt_count, val);
+	raw_cpu_add_4(pcpu_hot.preempt_count, val);
 }
 
 static __always_inline void __preempt_count_sub(int val)
 {
-	raw_cpu_add_4(__preempt_count, -val);
+	raw_cpu_add_4(pcpu_hot.preempt_count, -val);
 }
 
 /*
@@ -92,7 +92,8 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var]));
+	return GEN_UNARY_RMWcc("decl", pcpu_hot.preempt_count, e,
+			       __percpu_arg([var]));
 }
 
 /*
@@ -100,7 +101,7 @@ static __always_inline bool __preempt_count_dec_and_test(void)
  */
 static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
+	return unlikely(raw_cpu_read_4(pcpu_hot.preempt_count) == preempt_offset);
 }
 
 #ifdef CONFIG_PREEMPTION

arch/x86/include/asm/processor.h

@@ -377,8 +377,6 @@ struct irq_stack {
 	char		stack[IRQ_STACK_SIZE];
 } __aligned(IRQ_STACK_SIZE);
 
-DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
-
 #ifdef CONFIG_X86_64
 struct fixed_percpu_data {
 	/*
@@ -401,8 +399,6 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
 }
 
-DECLARE_PER_CPU(void *, hardirq_stack_ptr);
-DECLARE_PER_CPU(bool, hardirq_stack_inuse);
 extern asmlinkage void ignore_sysret(void);
 
 /* Save actual FS/GS selectors and bases to current->thread */
@@ -411,8 +407,6 @@ void current_save_fsgs(void);
 #ifdef CONFIG_STACKPROTECTOR
 DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
 #endif
-DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
-DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
 #endif	/* !X86_64 */
 
 struct perf_event;
@@ -517,7 +511,7 @@ static __always_inline unsigned long current_top_of_stack(void)
 	 *  and around vm86 mode and sp0 on x86_64 is special because of the
 	 *  entry trampoline.
 	 */
-	return this_cpu_read_stable(cpu_current_top_of_stack);
+	return this_cpu_read_stable(pcpu_hot.top_of_stack);
 }
 
 static __always_inline bool on_thread_stack(void)
@@ -554,10 +548,9 @@ extern int sysenter_setup(void);
 /* Defined in head.S */
 extern struct desc_ptr		early_gdt_descr;
 
-extern void switch_to_new_gdt(int);
+extern void switch_gdt_and_percpu_base(int);
 extern void load_direct_gdt(int);
 extern void load_fixmap_gdt(int);
-extern void load_percpu_segment(int);
 extern void cpu_init(void);
 extern void cpu_init_secondary(void);
 extern void cpu_init_exception_handling(void);

arch/x86/include/asm/qspinlock_paravirt.h

@@ -14,8 +14,6 @@
 
 __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
 #define __pv_queued_spin_unlock	__pv_queued_spin_unlock
-#define PV_UNLOCK		"__raw_callee_save___pv_queued_spin_unlock"
-#define PV_UNLOCK_SLOWPATH	"__raw_callee_save___pv_queued_spin_unlock_slowpath"
 
 /*
  * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock
@@ -37,32 +35,27 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
  *   rsi = lockval           (second argument)
  *   rdx = internal variable (set to 0)
  */
-asm    (".pushsection .spinlock.text, \"ax\";"
-	".globl " PV_UNLOCK ";"
-	".type " PV_UNLOCK ", @function;"
-	".align 4,0x90;"
-	PV_UNLOCK ": "
-	ASM_ENDBR
-	FRAME_BEGIN
-	"push  %rdx;"
-	"mov   $0x1,%eax;"
-	"xor   %edx,%edx;"
-	LOCK_PREFIX "cmpxchg %dl,(%rdi);"
-	"cmp   $0x1,%al;"
-	"jne   .slowpath;"
-	"pop   %rdx;"
+#define PV_UNLOCK_ASM							\
+	FRAME_BEGIN							\
+	"push  %rdx\n\t"						\
+	"mov   $0x1,%eax\n\t"						\
+	"xor   %edx,%edx\n\t"						\
+	LOCK_PREFIX "cmpxchg %dl,(%rdi)\n\t"				\
+	"cmp   $0x1,%al\n\t"						\
+	"jne   .slowpath\n\t"						\
+	"pop   %rdx\n\t"						\
+	FRAME_END							\
+	ASM_RET								\
+	".slowpath:\n\t"						\
+	"push   %rsi\n\t"						\
+	"movzbl %al,%esi\n\t"						\
+	"call __raw_callee_save___pv_queued_spin_unlock_slowpath\n\t"	\
+	"pop    %rsi\n\t"						\
+	"pop    %rdx\n\t"						\
 	FRAME_END
-	ASM_RET
-	".slowpath: "
-	"push   %rsi;"
-	"movzbl %al,%esi;"
-	"call " PV_UNLOCK_SLOWPATH ";"
-	"pop    %rsi;"
-	"pop    %rdx;"
-	FRAME_END
-	ASM_RET
-	".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
-	".popsection");
+
+DEFINE_PARAVIRT_ASM(__raw_callee_save___pv_queued_spin_unlock,
+		    PV_UNLOCK_ASM, .spinlock.text);
 
 #else /* CONFIG_64BIT */
 

arch/x86/include/asm/smp.h

@@ -3,10 +3,10 @@
 #define _ASM_X86_SMP_H
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
-#include <asm/percpu.h>
 
-#include <asm/thread_info.h>
 #include <asm/cpumask.h>
+#include <asm/current.h>
+#include <asm/thread_info.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
@@ -19,7 +19,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map);
 DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
 DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id);
-DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
@@ -150,11 +149,10 @@ __visible void smp_call_function_single_interrupt(struct pt_regs *r);
 
 /*
  * This function is needed by all SMP systems. It must _always_ be valid
- * from the initial startup. We map APIC_BASE very early in page_setup(),
- * so this is correct in the x86 case.
+ * from the initial startup.
  */
-#define raw_smp_processor_id()  this_cpu_read(cpu_number)
-#define __smp_processor_id() __this_cpu_read(cpu_number)
+#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);

arch/x86/include/asm/text-patching.h

@@ -45,6 +45,7 @@ extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void text_poke_sync(void);
 extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern void *text_poke_copy(void *addr, const void *opcode, size_t len);
+extern void *text_poke_copy_locked(void *addr, const void *opcode, size_t len, bool core_ok);
 extern void *text_poke_set(void *addr, int c, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate);

arch/x86/kernel/Makefile

@@ -143,6 +143,8 @@ obj-$(CONFIG_AMD_MEM_ENCRYPT)		+= sev.o
 
 obj-$(CONFIG_CFI_CLANG)			+= cfi.o
 
+obj-$(CONFIG_CALL_THUNKS)		+= callthunks.o
+
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)

arch/x86/kernel/alternative.c

@@ -116,6 +116,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 
 extern s32 __retpoline_sites[], __retpoline_sites_end[];
 extern s32 __return_sites[], __return_sites_end[];
+extern s32 __cfi_sites[], __cfi_sites_end[];
 extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[];
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
@@ -377,6 +378,56 @@ static int emit_indirect(int op, int reg, u8 *bytes)
 	return i;
 }
 
+static inline bool is_jcc32(struct insn *insn)
+{
+	/* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
+	return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80;
+}
+
+static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+	u8 op = insn->opcode.bytes[0];
+	int i = 0;
+
+	/*
+	 * Clang does 'weird' Jcc __x86_indirect_thunk_r11 conditional
+	 * tail-calls. Deal with them.
+	 */
+	if (is_jcc32(insn)) {
+		bytes[i++] = op;
+		op = insn->opcode.bytes[1];
+		goto clang_jcc;
+	}
+
+	if (insn->length == 6)
+		bytes[i++] = 0x2e; /* CS-prefix */
+
+	switch (op) {
+	case CALL_INSN_OPCODE:
+		__text_gen_insn(bytes+i, op, addr+i,
+				__x86_indirect_call_thunk_array[reg],
+				CALL_INSN_SIZE);
+		i += CALL_INSN_SIZE;
+		break;
+
+	case JMP32_INSN_OPCODE:
+clang_jcc:
+		__text_gen_insn(bytes+i, op, addr+i,
+				__x86_indirect_jump_thunk_array[reg],
+				JMP32_INSN_SIZE);
+		i += JMP32_INSN_SIZE;
+		break;
+
+	default:
+		WARN(1, "%pS %px %*ph\n", addr, addr, 6, addr);
+		return -1;
+	}
+
+	WARN_ON_ONCE(i != insn->length);
+
+	return i;
+}
+
 /*
  * Rewrite the compiler generated retpoline thunk calls.
  *
@@ -409,8 +460,12 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 	BUG_ON(reg == 4);
 
 	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
-	    !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE))
+	    !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
+		if (cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
+			return emit_call_track_retpoline(addr, insn, reg, bytes);
+
 		return -1;
+	}
 
 	op = insn->opcode.bytes[0];
 
@@ -427,8 +482,7 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 	 *   [ NOP ]
 	 * 1:
 	 */
-	/* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
-	if (op == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80) {
+	if (is_jcc32(insn)) {
 		cc = insn->opcode.bytes[1] & 0xf;
 		cc ^= 1; /* invert condition */
 
@@ -518,6 +572,11 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 }
 
 #ifdef CONFIG_RETHUNK
+
+#ifdef CONFIG_CALL_THUNKS
+void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk;
+#endif
+
 /*
  * Rewrite the compiler generated return thunk tail-calls.
  *
@@ -533,14 +592,18 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 {
 	int i = 0;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
-		return -1;
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+		if (x86_return_thunk == __x86_return_thunk)
+			return -1;
 
-	bytes[i++] = RET_INSN_OPCODE;
+		i = JMP32_INSN_SIZE;
+		__text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i);
+	} else {
+		bytes[i++] = RET_INSN_OPCODE;
+	}
 
 	for (; i < insn->length;)
 		bytes[i++] = INT3_INSN_OPCODE;
-
 	return i;
 }
 
@@ -594,6 +657,28 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
+static void poison_endbr(void *addr, bool warn)
+{
+	u32 endbr, poison = gen_endbr_poison();
+
+	if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
+		return;
+
+	if (!is_endbr(endbr)) {
+		WARN_ON_ONCE(warn);
+		return;
+	}
+
+	DPRINTK("ENDBR at: %pS (%px)", addr, addr);
+
+	/*
+	 * When we have IBT, the lack of ENDBR will trigger #CP
+	 */
+	DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr);
+	DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr);
+	text_poke_early(addr, &poison, 4);
+}
+
 /*
  * Generated by: objtool --ibt
  */
@@ -602,23 +687,11 @@ void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end)
 	s32 *s;
 
 	for (s = start; s < end; s++) {
-		u32 endbr, poison = gen_endbr_poison();
 		void *addr = (void *)s + *s;
 
-		if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
-			continue;
-
-		if (WARN_ON_ONCE(!is_endbr(endbr)))
-			continue;
-
-		DPRINTK("ENDBR at: %pS (%px)", addr, addr);
-
-		/*
-		 * When we have IBT, the lack of ENDBR will trigger #CP
-		 */
-		DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr);
-		DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr);
-		text_poke_early(addr, &poison, 4);
+		poison_endbr(addr, true);
+		if (IS_ENABLED(CONFIG_FINEIBT))
+			poison_endbr(addr - 16, false);
 	}
 }
 
@@ -628,6 +701,378 @@ void __init_or_module apply_ibt_endbr(s32 *start, s32 *end) { }
 
 #endif /* CONFIG_X86_KERNEL_IBT */
 
+#ifdef CONFIG_FINEIBT
+
+enum cfi_mode {
+	CFI_DEFAULT,
+	CFI_OFF,
+	CFI_KCFI,
+	CFI_FINEIBT,
+};
+
+static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT;
+static bool cfi_rand __ro_after_init = true;
+static u32  cfi_seed __ro_after_init;
+
+/*
+ * Re-hash the CFI hash with a boot-time seed while making sure the result is
+ * not a valid ENDBR instruction.
+ */
+static u32 cfi_rehash(u32 hash)
+{
+	hash ^= cfi_seed;
+	while (unlikely(is_endbr(hash) || is_endbr(-hash))) {
+		bool lsb = hash & 1;
+		hash >>= 1;
+		if (lsb)
+			hash ^= 0x80200003;
+	}
+	return hash;
+}
+
+static __init int cfi_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	while (str) {
+		char *next = strchr(str, ',');
+		if (next) {
+			*next = 0;
+			next++;
+		}
+
+		if (!strcmp(str, "auto")) {
+			cfi_mode = CFI_DEFAULT;
+		} else if (!strcmp(str, "off")) {
+			cfi_mode = CFI_OFF;
+			cfi_rand = false;
+		} else if (!strcmp(str, "kcfi")) {
+			cfi_mode = CFI_KCFI;
+		} else if (!strcmp(str, "fineibt")) {
+			cfi_mode = CFI_FINEIBT;
+		} else if (!strcmp(str, "norand")) {
+			cfi_rand = false;
+		} else {
+			pr_err("Ignoring unknown cfi option (%s).", str);
+		}
+
+		str = next;
+	}
+
+	return 0;
+}
+early_param("cfi", cfi_parse_cmdline);
+
+/*
+ * kCFI						FineIBT
+ *
+ * __cfi_\func:					__cfi_\func:
+ *	movl   $0x12345678,%eax		// 5	     endbr64			// 4
+ *	nop					     subl   $0x12345678,%r10d   // 7
+ *	nop					     jz     1f			// 2
+ *	nop					     ud2			// 2
+ *	nop					1:   nop			// 1
+ *	nop
+ *	nop
+ *	nop
+ *	nop
+ *	nop
+ *	nop
+ *	nop
+ *
+ *
+ * caller:					caller:
+ *	movl	$(-0x12345678),%r10d	 // 6	     movl   $0x12345678,%r10d	// 6
+ *	addl	$-15(%r11),%r10d	 // 4	     sub    $16,%r11		// 4
+ *	je	1f			 // 2	     nop4			// 4
+ *	ud2				 // 2
+ * 1:	call	__x86_indirect_thunk_r11 // 5	     call   *%r11; nop2;	// 5
+ *
+ */
+
+asm(	".pushsection .rodata			\n"
+	"fineibt_preamble_start:		\n"
+	"	endbr64				\n"
+	"	subl	$0x12345678, %r10d	\n"
+	"	je	fineibt_preamble_end	\n"
+	"	ud2				\n"
+	"	nop				\n"
+	"fineibt_preamble_end:			\n"
+	".popsection\n"
+);
+
+extern u8 fineibt_preamble_start[];
+extern u8 fineibt_preamble_end[];
+
+#define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
+#define fineibt_preamble_hash 7
+
+asm(	".pushsection .rodata			\n"
+	"fineibt_caller_start:			\n"
+	"	movl	$0x12345678, %r10d	\n"
+	"	sub	$16, %r11		\n"
+	ASM_NOP4
+	"fineibt_caller_end:			\n"
+	".popsection				\n"
+);
+
+extern u8 fineibt_caller_start[];
+extern u8 fineibt_caller_end[];
+
+#define fineibt_caller_size (fineibt_caller_end - fineibt_caller_start)
+#define fineibt_caller_hash 2
+
+#define fineibt_caller_jmp (fineibt_caller_size - 2)
+
+static u32 decode_preamble_hash(void *addr)
+{
+	u8 *p = addr;
+
+	/* b8 78 56 34 12          mov    $0x12345678,%eax */
+	if (p[0] == 0xb8)
+		return *(u32 *)(addr + 1);
+
+	return 0; /* invalid hash value */
+}
+
+static u32 decode_caller_hash(void *addr)
+{
+	u8 *p = addr;
+
+	/* 41 ba 78 56 34 12       mov    $0x12345678,%r10d */
+	if (p[0] == 0x41 && p[1] == 0xba)
+		return -*(u32 *)(addr + 2);
+
+	/* e8 0c 78 56 34 12	   jmp.d8  +12 */
+	if (p[0] == JMP8_INSN_OPCODE && p[1] == fineibt_caller_jmp)
+		return -*(u32 *)(addr + 2);
+
+	return 0; /* invalid hash value */
+}
+
+/* .retpoline_sites */
+static int cfi_disable_callers(s32 *start, s32 *end)
+{
+	/*
+	 * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate
+	 * in tact for later usage. Also see decode_caller_hash() and
+	 * cfi_rewrite_callers().
+	 */
+	const u8 jmp[] = { JMP8_INSN_OPCODE, fineibt_caller_jmp };
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		u32 hash;
+
+		addr -= fineibt_caller_size;
+		hash = decode_caller_hash(addr);
+		if (!hash) /* nocfi callers */
+			continue;
+
+		text_poke_early(addr, jmp, 2);
+	}
+
+	return 0;
+}
+
+static int cfi_enable_callers(s32 *start, s32 *end)
+{
+	/*
+	 * Re-enable kCFI, undo what cfi_disable_callers() did.
+	 */
+	const u8 mov[] = { 0x41, 0xba };
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		u32 hash;
+
+		addr -= fineibt_caller_size;
+		hash = decode_caller_hash(addr);
+		if (!hash) /* nocfi callers */
+			continue;
+
+		text_poke_early(addr, mov, 2);
+	}
+
+	return 0;
+}
+
+/* .cfi_sites */
+static int cfi_rand_preamble(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		u32 hash;
+
+		hash = decode_preamble_hash(addr);
+		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
+			 addr, addr, 5, addr))
+			return -EINVAL;
+
+		hash = cfi_rehash(hash);
+		text_poke_early(addr + 1, &hash, 4);
+	}
+
+	return 0;
+}
+
+static int cfi_rewrite_preamble(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		u32 hash;
+
+		hash = decode_preamble_hash(addr);
+		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
+			 addr, addr, 5, addr))
+			return -EINVAL;
+
+		text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
+		WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
+		text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
+	}
+
+	return 0;
+}
+
+/* .retpoline_sites */
+static int cfi_rand_callers(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		u32 hash;
+
+		addr -= fineibt_caller_size;
+		hash = decode_caller_hash(addr);
+		if (hash) {
+			hash = -cfi_rehash(hash);
+			text_poke_early(addr + 2, &hash, 4);
+		}
+	}
+
+	return 0;
+}
+
+static int cfi_rewrite_callers(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		u32 hash;
+
+		addr -= fineibt_caller_size;
+		hash = decode_caller_hash(addr);
+		if (hash) {
+			text_poke_early(addr, fineibt_caller_start, fineibt_caller_size);
+			WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678);
+			text_poke_early(addr + fineibt_caller_hash, &hash, 4);
+		}
+		/* rely on apply_retpolines() */
+	}
+
+	return 0;
+}
+
+static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
+{
+	int ret;
+
+	if (WARN_ONCE(fineibt_preamble_size != 16,
+		      "FineIBT preamble wrong size: %ld", fineibt_preamble_size))
+		return;
+
+	if (cfi_mode == CFI_DEFAULT) {
+		cfi_mode = CFI_KCFI;
+		if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
+			cfi_mode = CFI_FINEIBT;
+	}
+
+	/*
+	 * Rewrite the callers to not use the __cfi_ stubs, such that we might
+	 * rewrite them. This disables all CFI. If this succeeds but any of the
+	 * later stages fails, we're without CFI.
+	 */
+	ret = cfi_disable_callers(start_retpoline, end_retpoline);
+	if (ret)
+		goto err;
+
+	if (cfi_rand) {
+		if (builtin)
+			cfi_seed = get_random_u32();
+
+		ret = cfi_rand_preamble(start_cfi, end_cfi);
+		if (ret)
+			goto err;
+
+		ret = cfi_rand_callers(start_retpoline, end_retpoline);
+		if (ret)
+			goto err;
+	}
+
+	switch (cfi_mode) {
+	case CFI_OFF:
+		if (builtin)
+			pr_info("Disabling CFI\n");
+		return;
+
+	case CFI_KCFI:
+		ret = cfi_enable_callers(start_retpoline, end_retpoline);
+		if (ret)
+			goto err;
+
+		if (builtin)
+			pr_info("Using kCFI\n");
+		return;
+
+	case CFI_FINEIBT:
+		ret = cfi_rewrite_preamble(start_cfi, end_cfi);
+		if (ret)
+			goto err;
+
+		ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
+		if (ret)
+			goto err;
+
+		if (builtin)
+			pr_info("Using FineIBT CFI\n");
+		return;
+
+	default:
+		break;
+	}
+
+err:
+	pr_err("Something went horribly wrong trying to rewrite the CFI implementation.\n");
+}
+
+#else
+
+static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
+{
+}
+
+#endif
+
+void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+		   s32 *start_cfi, s32 *end_cfi)
+{
+	return __apply_fineibt(start_retpoline, end_retpoline,
+			       start_cfi, end_cfi,
+			       /* .builtin = */ false);
+}
+
 #ifdef CONFIG_SMP
 static void alternatives_smp_lock(const s32 *start, const s32 *end,
 				  u8 *text, u8 *text_end)
@@ -934,6 +1379,9 @@ void __init alternative_instructions(void)
 	 */
 	apply_paravirt(__parainstructions, __parainstructions_end);
 
+	__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
+			__cfi_sites, __cfi_sites_end, true);
+
 	/*
 	 * Rewrite the retpolines, must be done before alternatives since
 	 * those can rewrite the retpoline thunks.
@@ -947,6 +1395,12 @@ void __init alternative_instructions(void)
 	 */
 	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
+	/*
+	 * Now all calls are established. Apply the call thunks if
+	 * required.
+	 */
+	callthunks_patch_builtin_calls();
+
 	apply_ibt_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
 
 #ifdef CONFIG_SMP
@@ -1236,6 +1690,27 @@ void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
 	return __text_poke(text_poke_memcpy, addr, opcode, len);
 }
 
+void *text_poke_copy_locked(void *addr, const void *opcode, size_t len,
+			    bool core_ok)
+{
+	unsigned long start = (unsigned long)addr;
+	size_t patched = 0;
+
+	if (WARN_ON_ONCE(!core_ok && core_kernel_text(start)))
+		return NULL;
+
+	while (patched < len) {
+		unsigned long ptr = start + patched;
+		size_t s;
+
+		s = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(ptr), len - patched);
+
+		__text_poke(text_poke_memcpy, (void *)ptr, opcode + patched, s);
+		patched += s;
+	}
+	return addr;
+}
+
 /**
  * text_poke_copy - Copy instructions into (an unused part of) RX memory
  * @addr: address to modify
@@ -1250,22 +1725,8 @@ void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
  */
 void *text_poke_copy(void *addr, const void *opcode, size_t len)
 {
-	unsigned long start = (unsigned long)addr;
-	size_t patched = 0;
-
-	if (WARN_ON_ONCE(core_kernel_text(start)))
-		return NULL;
-
 	mutex_lock(&text_mutex);
-	while (patched < len) {
-		unsigned long ptr = start + patched;
-		size_t s;
-
-		s = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(ptr), len - patched);
-
-		__text_poke(text_poke_memcpy, (void *)ptr, opcode + patched, s);
-		patched += s;
-	}
+	addr = text_poke_copy_locked(addr, opcode, len, false);
 	mutex_unlock(&text_mutex);
 	return addr;
 }

arch/x86/kernel/asm-offsets.c

@@ -107,4 +107,9 @@ static void __used common(void)
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
 	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
+	OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack);
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+	OFFSET(X86_call_depth, pcpu_hot, call_depth);
+#endif
+
 }

arch/x86/kernel/asm-offsets_64.c

@@ -57,7 +57,7 @@ int main(void)
 	BLANK();
 
 #ifdef CONFIG_STACKPROTECTOR
-	DEFINE(stack_canary_offset, offsetof(struct fixed_percpu_data, stack_canary));
+	OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary);
 	BLANK();
 #endif
 	return 0;

arch/x86/kernel/callthunks.c

@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "callthunks: " fmt
+
+#include <linux/debugfs.h>
+#include <linux/kallsyms.h>
+#include <linux/memory.h>
+#include <linux/moduleloader.h>
+#include <linux/static_call.h>
+
+#include <asm/alternative.h>
+#include <asm/asm-offsets.h>
+#include <asm/cpu.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+#include <asm/kexec.h>
+#include <asm/nospec-branch.h>
+#include <asm/paravirt.h>
+#include <asm/sections.h>
+#include <asm/switch_to.h>
+#include <asm/sync_core.h>
+#include <asm/text-patching.h>
+#include <asm/xen/hypercall.h>
+
+static int __initdata_or_module debug_callthunks;
+
+#define prdbg(fmt, args...)					\
+do {								\
+	if (debug_callthunks)					\
+		printk(KERN_DEBUG pr_fmt(fmt), ##args);		\
+} while(0)
+
+static int __init debug_thunks(char *str)
+{
+	debug_callthunks = 1;
+	return 1;
+}
+__setup("debug-callthunks", debug_thunks);
+
+#ifdef CONFIG_CALL_THUNKS_DEBUG
+DEFINE_PER_CPU(u64, __x86_call_count);
+DEFINE_PER_CPU(u64, __x86_ret_count);
+DEFINE_PER_CPU(u64, __x86_stuffs_count);
+DEFINE_PER_CPU(u64, __x86_ctxsw_count);
+EXPORT_SYMBOL_GPL(__x86_ctxsw_count);
+EXPORT_SYMBOL_GPL(__x86_call_count);
+#endif
+
+extern s32 __call_sites[], __call_sites_end[];
+
+struct thunk_desc {
+	void		*template;
+	unsigned int	template_size;
+};
+
+struct core_text {
+	unsigned long	base;
+	unsigned long	end;
+	const char	*name;
+};
+
+static bool thunks_initialized __ro_after_init;
+
+static const struct core_text builtin_coretext = {
+	.base = (unsigned long)_text,
+	.end  = (unsigned long)_etext,
+	.name = "builtin",
+};
+
+asm (
+	".pushsection .rodata				\n"
+	".global skl_call_thunk_template		\n"
+	"skl_call_thunk_template:			\n"
+		__stringify(INCREMENT_CALL_DEPTH)"	\n"
+	".global skl_call_thunk_tail			\n"
+	"skl_call_thunk_tail:				\n"
+	".popsection					\n"
+);
+
+extern u8 skl_call_thunk_template[];
+extern u8 skl_call_thunk_tail[];
+
+#define SKL_TMPL_SIZE \
+	((unsigned int)(skl_call_thunk_tail - skl_call_thunk_template))
+
+extern void error_entry(void);
+extern void xen_error_entry(void);
+extern void paranoid_entry(void);
+
+static inline bool within_coretext(const struct core_text *ct, void *addr)
+{
+	unsigned long p = (unsigned long)addr;
+
+	return ct->base <= p && p < ct->end;
+}
+
+static inline bool within_module_coretext(void *addr)
+{
+	bool ret = false;
+
+#ifdef CONFIG_MODULES
+	struct module *mod;
+
+	preempt_disable();
+	mod = __module_address((unsigned long)addr);
+	if (mod && within_module_core((unsigned long)addr, mod))
+		ret = true;
+	preempt_enable();
+#endif
+	return ret;
+}
+
+static bool is_coretext(const struct core_text *ct, void *addr)
+{
+	if (ct && within_coretext(ct, addr))
+		return true;
+	if (within_coretext(&builtin_coretext, addr))
+		return true;
+	return within_module_coretext(addr);
+}
+
+static __init_or_module bool skip_addr(void *dest)
+{
+	if (dest == error_entry)
+		return true;
+	if (dest == paranoid_entry)
+		return true;
+	if (dest == xen_error_entry)
+		return true;
+	/* Does FILL_RSB... */
+	if (dest == __switch_to_asm)
+		return true;
+	/* Accounts directly */
+	if (dest == ret_from_fork)
+		return true;
+#ifdef CONFIG_HOTPLUG_CPU
+	if (dest == start_cpu0)
+		return true;
+#endif
+#ifdef CONFIG_FUNCTION_TRACER
+	if (dest == __fentry__)
+		return true;
+#endif
+#ifdef CONFIG_KEXEC_CORE
+	if (dest >= (void *)relocate_kernel &&
+	    dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE)
+		return true;
+#endif
+#ifdef CONFIG_XEN
+	if (dest >= (void *)hypercall_page &&
+	    dest < (void*)hypercall_page + PAGE_SIZE)
+		return true;
+#endif
+	return false;
+}
+
+static __init_or_module void *call_get_dest(void *addr)
+{
+	struct insn insn;
+	void *dest;
+	int ret;
+
+	ret = insn_decode_kernel(&insn, addr);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* Patched out call? */
+	if (insn.opcode.bytes[0] != CALL_INSN_OPCODE)
+		return NULL;
+
+	dest = addr + insn.length + insn.immediate.value;
+	if (skip_addr(dest))
+		return NULL;
+	return dest;
+}
+
+static const u8 nops[] = {
+	0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
+	0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
+	0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
+	0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
+};
+
+static __init_or_module void *patch_dest(void *dest, bool direct)
+{
+	unsigned int tsize = SKL_TMPL_SIZE;
+	u8 *pad = dest - tsize;
+
+	/* Already patched? */
+	if (!bcmp(pad, skl_call_thunk_template, tsize))
+		return pad;
+
+	/* Ensure there are nops */
+	if (bcmp(pad, nops, tsize)) {
+		pr_warn_once("Invalid padding area for %pS\n", dest);
+		return NULL;
+	}
+
+	if (direct)
+		memcpy(pad, skl_call_thunk_template, tsize);
+	else
+		text_poke_copy_locked(pad, skl_call_thunk_template, tsize, true);
+	return pad;
+}
+
+static __init_or_module void patch_call(void *addr, const struct core_text *ct)
+{
+	void *pad, *dest;
+	u8 bytes[8];
+
+	if (!within_coretext(ct, addr))
+		return;
+
+	dest = call_get_dest(addr);
+	if (!dest || WARN_ON_ONCE(IS_ERR(dest)))
+		return;
+
+	if (!is_coretext(ct, dest))
+		return;
+
+	pad = patch_dest(dest, within_coretext(ct, dest));
+	if (!pad)
+		return;
+
+	prdbg("Patch call at: %pS %px to %pS %px -> %px \n", addr, addr,
+		dest, dest, pad);
+	__text_gen_insn(bytes, CALL_INSN_OPCODE, addr, pad, CALL_INSN_SIZE);
+	text_poke_early(addr, bytes, CALL_INSN_SIZE);
+}
+
+static __init_or_module void
+patch_call_sites(s32 *start, s32 *end, const struct core_text *ct)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++)
+		patch_call((void *)s + *s, ct);
+}
+
+static __init_or_module void
+patch_paravirt_call_sites(struct paravirt_patch_site *start,
+			  struct paravirt_patch_site *end,
+			  const struct core_text *ct)
+{
+	struct paravirt_patch_site *p;
+
+	for (p = start; p < end; p++)
+		patch_call(p->instr, ct);
+}
+
+static __init_or_module void
+callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct)
+{
+	prdbg("Patching call sites %s\n", ct->name);
+	patch_call_sites(cs->call_start, cs->call_end, ct);
+	patch_paravirt_call_sites(cs->pv_start, cs->pv_end, ct);
+	prdbg("Patching call sites done%s\n", ct->name);
+}
+
+void __init callthunks_patch_builtin_calls(void)
+{
+	struct callthunk_sites cs = {
+		.call_start	= __call_sites,
+		.call_end	= __call_sites_end,
+		.pv_start	= __parainstructions,
+		.pv_end		= __parainstructions_end
+	};
+
+	if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
+		return;
+
+	pr_info("Setting up call depth tracking\n");
+	mutex_lock(&text_mutex);
+	callthunks_setup(&cs, &builtin_coretext);
+	static_call_force_reinit();
+	thunks_initialized = true;
+	mutex_unlock(&text_mutex);
+}
+
+void *callthunks_translate_call_dest(void *dest)
+{
+	void *target;
+
+	lockdep_assert_held(&text_mutex);
+
+	if (!thunks_initialized || skip_addr(dest))
+		return dest;
+
+	if (!is_coretext(NULL, dest))
+		return dest;
+
+	target = patch_dest(dest, false);
+	return target ? : dest;
+}
+
+bool is_callthunk(void *addr)
+{
+	unsigned int tmpl_size = SKL_TMPL_SIZE;
+	void *tmpl = skl_call_thunk_template;
+	unsigned long dest;
+
+	dest = roundup((unsigned long)addr, CONFIG_FUNCTION_ALIGNMENT);
+	if (!thunks_initialized || skip_addr((void *)dest))
+		return false;
+
+	return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size);
+}
+
+#ifdef CONFIG_BPF_JIT
+int x86_call_depth_emit_accounting(u8 **pprog, void *func)
+{
+	unsigned int tmpl_size = SKL_TMPL_SIZE;
+	void *tmpl = skl_call_thunk_template;
+
+	if (!thunks_initialized)
+		return 0;
+
+	/* Is function call target a thunk? */
+	if (func && is_callthunk(func))
+		return 0;
+
+	memcpy(*pprog, tmpl, tmpl_size);
+	*pprog += tmpl_size;
+	return tmpl_size;
+}
+#endif
+
+#ifdef CONFIG_MODULES
+void noinline callthunks_patch_module_calls(struct callthunk_sites *cs,
+					    struct module *mod)
+{
+	struct core_text ct = {
+		.base = (unsigned long)mod->core_layout.base,
+		.end  = (unsigned long)mod->core_layout.base + mod->core_layout.size,
+		.name = mod->name,
+	};
+
+	if (!thunks_initialized)
+		return;
+
+	mutex_lock(&text_mutex);
+	callthunks_setup(cs, &ct);
+	mutex_unlock(&text_mutex);
+}
+#endif /* CONFIG_MODULES */
+
+#if defined(CONFIG_CALL_THUNKS_DEBUG) && defined(CONFIG_DEBUG_FS)
+static int callthunks_debug_show(struct seq_file *m, void *p)
+{
+	unsigned long cpu = (unsigned long)m->private;
+
+	seq_printf(m, "C: %16llu R: %16llu S: %16llu X: %16llu\n,",
+		   per_cpu(__x86_call_count, cpu),
+		   per_cpu(__x86_ret_count, cpu),
+		   per_cpu(__x86_stuffs_count, cpu),
+		   per_cpu(__x86_ctxsw_count, cpu));
+	return 0;
+}
+
+static int callthunks_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, callthunks_debug_show, inode->i_private);
+}
+
+static const struct file_operations dfs_ops = {
+	.open		= callthunks_debug_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init callthunks_debugfs_init(void)
+{
+	struct dentry *dir;
+	unsigned long cpu;
+
+	dir = debugfs_create_dir("callthunks", NULL);
+	for_each_possible_cpu(cpu) {
+		void *arg = (void *)cpu;
+		char name [10];
+
+		sprintf(name, "cpu%lu", cpu);
+		debugfs_create_file(name, 0644, dir, arg, &dfs_ops);
+	}
+	return 0;
+}
+__initcall(callthunks_debugfs_init);
+#endif

arch/x86/kernel/cpu/Makefile

@@ -17,9 +17,6 @@ KMSAN_SANITIZE_common.o := n
 # As above, instrumenting secondary CPU boot code causes boot hangs.
 KCSAN_SANITIZE_common.o := n
 
-# Make sure load_percpu_segment has no stackprotector
-CFLAGS_common.o		:= -fno-stack-protector
-
 obj-y			:= cacheinfo.o scattered.o topology.o
 obj-y			+= common.o
 obj-y			+= rdrand.o

arch/x86/kernel/cpu/bugs.c

@@ -787,6 +787,7 @@ enum retbleed_mitigation {
 	RETBLEED_MITIGATION_IBPB,
 	RETBLEED_MITIGATION_IBRS,
 	RETBLEED_MITIGATION_EIBRS,
+	RETBLEED_MITIGATION_STUFF,
 };
 
 enum retbleed_mitigation_cmd {
@@ -794,6 +795,7 @@ enum retbleed_mitigation_cmd {
 	RETBLEED_CMD_AUTO,
 	RETBLEED_CMD_UNRET,
 	RETBLEED_CMD_IBPB,
+	RETBLEED_CMD_STUFF,
 };
 
 static const char * const retbleed_strings[] = {
@@ -802,6 +804,7 @@ static const char * const retbleed_strings[] = {
 	[RETBLEED_MITIGATION_IBPB]	= "Mitigation: IBPB",
 	[RETBLEED_MITIGATION_IBRS]	= "Mitigation: IBRS",
 	[RETBLEED_MITIGATION_EIBRS]	= "Mitigation: Enhanced IBRS",
+	[RETBLEED_MITIGATION_STUFF]	= "Mitigation: Stuffing",
 };
 
 static enum retbleed_mitigation retbleed_mitigation __ro_after_init =
@@ -831,8 +834,12 @@ static int __init retbleed_parse_cmdline(char *str)
 			retbleed_cmd = RETBLEED_CMD_UNRET;
 		} else if (!strcmp(str, "ibpb")) {
 			retbleed_cmd = RETBLEED_CMD_IBPB;
+		} else if (!strcmp(str, "stuff")) {
+			retbleed_cmd = RETBLEED_CMD_STUFF;
 		} else if (!strcmp(str, "nosmt")) {
 			retbleed_nosmt = true;
+		} else if (!strcmp(str, "force")) {
+			setup_force_cpu_bug(X86_BUG_RETBLEED);
 		} else {
 			pr_err("Ignoring unknown retbleed option (%s).", str);
 		}
@@ -879,6 +886,21 @@ static void __init retbleed_select_mitigation(void)
 		}
 		break;
 
+	case RETBLEED_CMD_STUFF:
+		if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING) &&
+		    spectre_v2_enabled == SPECTRE_V2_RETPOLINE) {
+			retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
+
+		} else {
+			if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING))
+				pr_err("WARNING: retbleed=stuff depends on spectre_v2=retpoline\n");
+			else
+				pr_err("WARNING: kernel not compiled with CALL_DEPTH_TRACKING.\n");
+
+			goto do_cmd_auto;
+		}
+		break;
+
 do_cmd_auto:
 	case RETBLEED_CMD_AUTO:
 	default:
@@ -916,6 +938,12 @@ static void __init retbleed_select_mitigation(void)
 		mitigate_smt = true;
 		break;
 
+	case RETBLEED_MITIGATION_STUFF:
+		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+		setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
+		x86_set_skl_return_thunk();
+		break;
+
 	default:
 		break;
 	}
@@ -926,7 +954,7 @@ static void __init retbleed_select_mitigation(void)
 
 	/*
 	 * Let IBRS trump all on Intel without affecting the effects of the
-	 * retbleed= cmdline option.
+	 * retbleed= cmdline option except for call depth based stuffing
 	 */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
 		switch (spectre_v2_enabled) {
@@ -939,7 +967,8 @@ static void __init retbleed_select_mitigation(void)
 			retbleed_mitigation = RETBLEED_MITIGATION_EIBRS;
 			break;
 		default:
-			pr_err(RETBLEED_INTEL_MSG);
+			if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF)
+				pr_err(RETBLEED_INTEL_MSG);
 		}
 	}
 
@@ -1413,6 +1442,7 @@ static void __init spectre_v2_select_mitigation(void)
 		if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) &&
 		    boot_cpu_has_bug(X86_BUG_RETBLEED) &&
 		    retbleed_cmd != RETBLEED_CMD_OFF &&
+		    retbleed_cmd != RETBLEED_CMD_STUFF &&
 		    boot_cpu_has(X86_FEATURE_IBRS) &&
 		    boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
 			mode = SPECTRE_V2_IBRS;

arch/x86/kernel/cpu/common.c

@@ -610,6 +610,7 @@ static __always_inline void setup_cet(struct cpuinfo_x86 *c)
 
 	if (!ibt_selftest()) {
 		pr_err("IBT selftest: Failed!\n");
+		wrmsrl(MSR_IA32_S_CET, 0);
 		setup_clear_cpu_cap(X86_FEATURE_IBT);
 		return;
 	}
@@ -702,16 +703,6 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
 __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
 __u32 cpu_caps_set[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
 
-void load_percpu_segment(int cpu)
-{
-#ifdef CONFIG_X86_32
-	loadsegment(fs, __KERNEL_PERCPU);
-#else
-	__loadsegment_simple(gs, 0);
-	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
-#endif
-}
-
 #ifdef CONFIG_X86_32
 /* The 32-bit entry code needs to find cpu_entry_area. */
 DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
@@ -739,16 +730,45 @@ void load_fixmap_gdt(int cpu)
 }
 EXPORT_SYMBOL_GPL(load_fixmap_gdt);
 
-/*
- * Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one.
+/**
+ * switch_gdt_and_percpu_base - Switch to direct GDT and runtime per CPU base
+ * @cpu:	The CPU number for which this is invoked
+ *
+ * Invoked during early boot to switch from early GDT and early per CPU to
+ * the direct GDT and the runtime per CPU area. On 32-bit the percpu base
+ * switch is implicit by loading the direct GDT. On 64bit this requires
+ * to update GSBASE.
  */
-void switch_to_new_gdt(int cpu)
+void __init switch_gdt_and_percpu_base(int cpu)
 {
-	/* Load the original GDT */
 	load_direct_gdt(cpu);
-	/* Reload the per-cpu base */
-	load_percpu_segment(cpu);
+
+#ifdef CONFIG_X86_64
+	/*
+	 * No need to load %gs. It is already correct.
+	 *
+	 * Writing %gs on 64bit would zero GSBASE which would make any per
+	 * CPU operation up to the point of the wrmsrl() fault.
+	 *
+	 * Set GSBASE to the new offset. Until the wrmsrl() happens the
+	 * early mapping is still valid. That means the GSBASE update will
+	 * lose any prior per CPU data which was not copied over in
+	 * setup_per_cpu_areas().
+	 *
+	 * This works even with stackprotector enabled because the
+	 * per CPU stack canary is 0 in both per CPU areas.
+	 */
+	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
+#else
+	/*
+	 * %fs is already set to __KERNEL_PERCPU, but after switching GDT
+	 * it is required to load FS again so that the 'hidden' part is
+	 * updated from the new GDT. Up to this point the early per CPU
+	 * translation is active. Any content of the early per CPU data
+	 * which was not copied over in setup_per_cpu_areas() is lost.
+	 */
+	loadsegment(fs, __KERNEL_PERCPU);
+#endif
 }
 
 static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
@@ -1993,27 +2013,18 @@ static __init int setup_clearcpuid(char *arg)
 }
 __setup("clearcpuid=", setup_clearcpuid);
 
+DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
+	.current_task	= &init_task,
+	.preempt_count	= INIT_PREEMPT_COUNT,
+	.top_of_stack	= TOP_OF_INIT_STACK,
+};
+EXPORT_PER_CPU_SYMBOL(pcpu_hot);
+
 #ifdef CONFIG_X86_64
 DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
 		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
 EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
 
-/*
- * The following percpu variables are hot.  Align current_task to
- * cacheline size such that they fall in the same cacheline.
- */
-DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
-	&init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
-
-DEFINE_PER_CPU(void *, hardirq_stack_ptr);
-DEFINE_PER_CPU(bool, hardirq_stack_inuse);
-
-DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
-EXPORT_PER_CPU_SYMBOL(__preempt_count);
-
-DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK;
-
 static void wrmsrl_cstar(unsigned long val)
 {
 	/*
@@ -2064,20 +2075,6 @@ void syscall_init(void)
 
 #else	/* CONFIG_X86_64 */
 
-DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
-DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
-EXPORT_PER_CPU_SYMBOL(__preempt_count);
-
-/*
- * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
- * the top of the kernel stack.  Use an extra percpu variable to track the
- * top of the kernel stack directly.
- */
-DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) =
-	(unsigned long)&init_thread_union + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
-
 #ifdef CONFIG_STACKPROTECTOR
 DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
 EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
@@ -2248,12 +2245,6 @@ void cpu_init(void)
 	    boot_cpu_has(X86_FEATURE_TSC) || boot_cpu_has(X86_FEATURE_DE))
 		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
-	/*
-	 * Initialize the per-CPU GDT with the boot GDT,
-	 * and set up the GDT descriptor:
-	 */
-	switch_to_new_gdt(cpu);
-
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		loadsegment(fs, 0);
 		memset(cur->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);

arch/x86/kernel/dumpstack_32.c

@@ -37,7 +37,7 @@ const char *stack_type_name(enum stack_type type)
 
 static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
+	unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
@@ -62,7 +62,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 
 static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack_ptr);
+	unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.softirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*

arch/x86/kernel/dumpstack_64.c

@@ -134,7 +134,7 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
 
 static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
+	unsigned long *end = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
 	unsigned long *begin;
 
 	/*

arch/x86/kernel/ftrace.c

@@ -69,6 +69,10 @@ static const char *ftrace_nop_replace(void)
 
 static const char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
+	/*
+	 * No need to translate into a callthunk. The trampoline does
+	 * the depth accounting itself.
+	 */
 	return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
 }
 
@@ -317,7 +321,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned long size;
 	unsigned long *ptr;
 	void *trampoline;
-	void *ip;
+	void *ip, *dest;
 	/* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
 	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
 	unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
@@ -359,7 +363,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	ip = trampoline + size;
 	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
-		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, &__x86_return_thunk, JMP32_INSN_SIZE);
+		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
 	else
 		memcpy(ip, retq, sizeof(retq));
 
@@ -404,17 +408,19 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	/* put in the call to the function */
 	mutex_lock(&text_mutex);
 	call_offset -= start_offset;
+	/*
+	 * No need to translate into a callthunk. The trampoline does
+	 * the depth accounting before the call already.
+	 */
+	dest = ftrace_ops_get_func(ops);
 	memcpy(trampoline + call_offset,
-	       text_gen_insn(CALL_INSN_OPCODE,
-			     trampoline + call_offset,
-			     ftrace_ops_get_func(ops)), CALL_INSN_SIZE);
+	       text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
+	       CALL_INSN_SIZE);
 	mutex_unlock(&text_mutex);
 
 	/* ALLOC_TRAMP flags lets us know we created it */
 	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
 
-	set_vm_flush_reset_perms(trampoline);
-
 	if (likely(system_state != SYSTEM_BOOTING))
 		set_memory_ro((unsigned long)trampoline, npages);
 	set_memory_x((unsigned long)trampoline, npages);

arch/x86/kernel/ftrace_64.S

@@ -3,8 +3,9 @@
  *  Copyright (C) 2014  Steven Rostedt, Red Hat Inc
  */
 
-#include <linux/linkage.h>
 #include <linux/cfi_types.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 #include <asm/ftrace.h>
 #include <asm/export.h>
@@ -131,16 +132,19 @@
 	.endm
 
 SYM_TYPED_FUNC_START(ftrace_stub)
+	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(ftrace_stub)
 
 SYM_TYPED_FUNC_START(ftrace_stub_graph)
+	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(ftrace_stub_graph)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
+	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
@@ -149,6 +153,8 @@ SYM_FUNC_START(ftrace_caller)
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
+	CALL_DEPTH_ACCOUNT
+
 	/* Stack - skipping return address of ftrace_caller */
 	leaq MCOUNT_REG_SIZE+8(%rsp), %rcx
 	movq %rcx, RSP(%rsp)
@@ -164,6 +170,9 @@ SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL)
 	/* Only ops with REGS flag set should have CS register set */
 	movq $0, CS(%rsp)
 
+	/* Account for the function call below */
+	CALL_DEPTH_ACCOUNT
+
 SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	call ftrace_stub
@@ -193,6 +202,8 @@ SYM_FUNC_START(ftrace_regs_caller)
 	save_mcount_regs 8
 	/* save_mcount_regs fills in first two parameters */
 
+	CALL_DEPTH_ACCOUNT
+
 SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	/* Load the ftrace_ops into the 3rd parameter */
@@ -223,6 +234,9 @@ SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL)
 	/* regs go into 4th parameter */
 	leaq (%rsp), %rcx
 
+	/* Account for the function call below */
+	CALL_DEPTH_ACCOUNT
+
 SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	call ftrace_stub
@@ -275,7 +289,20 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	/* Restore flags */
 	popfq
 	UNWIND_HINT_FUNC
-	RET
+
+	/*
+	 * The above left an extra return value on the stack; effectively
+	 * doing a tail-call without using a register. This PUSH;RET
+	 * pattern unbalances the RSB, inject a pointless CALL to rebalance.
+	 */
+	ANNOTATE_INTRA_FUNCTION_CALL
+	CALL .Ldo_rebalance
+	int3
+.Ldo_rebalance:
+	add $8, %rsp
+	ALTERNATIVE __stringify(RET), \
+		    __stringify(ANNOTATE_UNRET_SAFE; ret; int3), \
+		    X86_FEATURE_CALL_DEPTH
 
 SYM_FUNC_END(ftrace_regs_caller)
 STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
@@ -284,6 +311,8 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 SYM_FUNC_START(__fentry__)
+	CALL_DEPTH_ACCOUNT
+
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
 	RET
@@ -337,6 +366,8 @@ SYM_CODE_START(return_to_handler)
 	int3
 .Ldo_rop:
 	mov %rdi, (%rsp)
-	RET
+	ALTERNATIVE __stringify(RET), \
+		    __stringify(ANNOTATE_UNRET_SAFE; ret; int3), \
+		    X86_FEATURE_CALL_DEPTH
 SYM_CODE_END(return_to_handler)
 #endif

arch/x86/kernel/head_64.S

@@ -370,6 +370,7 @@ SYM_CODE_END(secondary_startup_64)
  * start_secondary() via .Ljump_to_C_code.
  */
 SYM_CODE_START(start_cpu0)
+	ANNOTATE_NOENDBR
 	UNWIND_HINT_EMPTY
 	movq	initial_stack(%rip), %rsp
 	jmp	.Ljump_to_C_code

arch/x86/kernel/irq_32.c

@@ -52,9 +52,6 @@ static inline int check_stack_overflow(void) { return 0; }
 static inline void print_stack_overflow(void) { }
 #endif
 
-DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
-DEFINE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
-
 static void call_on_stack(void *func, void *stack)
 {
 	asm volatile("xchgl	%%ebx,%%esp	\n"
@@ -77,7 +74,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	u32 *isp, *prev_esp, arg1;
 
 	curstk = (struct irq_stack *) current_stack();
-	irqstk = __this_cpu_read(hardirq_stack_ptr);
+	irqstk = __this_cpu_read(pcpu_hot.hardirq_stack_ptr);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -115,7 +112,7 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 	int node = cpu_to_node(cpu);
 	struct page *ph, *ps;
 
-	if (per_cpu(hardirq_stack_ptr, cpu))
+	if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
 		return 0;
 
 	ph = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
@@ -127,8 +124,8 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 		return -ENOMEM;
 	}
 
-	per_cpu(hardirq_stack_ptr, cpu) = page_address(ph);
-	per_cpu(softirq_stack_ptr, cpu) = page_address(ps);
+	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = page_address(ph);
+	per_cpu(pcpu_hot.softirq_stack_ptr, cpu) = page_address(ps);
 	return 0;
 }
 
@@ -138,7 +135,7 @@ void do_softirq_own_stack(void)
 	struct irq_stack *irqstk;
 	u32 *isp, *prev_esp;
 
-	irqstk = __this_cpu_read(softirq_stack_ptr);
+	irqstk = __this_cpu_read(pcpu_hot.softirq_stack_ptr);
 
 	/* build the stack frame on the softirq stack */
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));

arch/x86/kernel/irq_64.c

@@ -50,7 +50,7 @@ static int map_irq_stack(unsigned int cpu)
 		return -ENOMEM;
 
 	/* Store actual TOS to avoid adjustment in the hotpath */
-	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #else
@@ -63,14 +63,14 @@ static int map_irq_stack(unsigned int cpu)
 	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
 	/* Store actual TOS to avoid adjustment in the hotpath */
-	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #endif
 
 int irq_init_percpu_irqstack(unsigned int cpu)
 {
-	if (per_cpu(hardirq_stack_ptr, cpu))
+	if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
 		return 0;
 	return map_irq_stack(cpu);
 }

arch/x86/kernel/kprobes/core.c

@@ -414,7 +414,6 @@ void *alloc_insn_page(void)
 	if (!page)
 		return NULL;
 
-	set_vm_flush_reset_perms(page);
 	/*
 	 * First make the page read-only, and only then make it executable to
 	 * prevent it from being W+X in between.

arch/x86/kernel/kvm.c

@@ -798,19 +798,13 @@ extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
  * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
  * restoring to/from the stack.
  */
-asm(
-".pushsection .text;"
-".global __raw_callee_save___kvm_vcpu_is_preempted;"
-".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
-"__raw_callee_save___kvm_vcpu_is_preempted:"
-ASM_ENDBR
-"movq	__per_cpu_offset(,%rdi,8), %rax;"
-"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
-"setne	%al;"
-ASM_RET
-".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
-".popsection");
+#define PV_VCPU_PREEMPTED_ASM						     \
+ "movq   __per_cpu_offset(,%rdi,8), %rax\n\t"				     \
+ "cmpb   $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax)\n\t" \
+ "setne  %al\n\t"
 
+DEFINE_PARAVIRT_ASM(__raw_callee_save___kvm_vcpu_is_preempted,
+		    PV_VCPU_PREEMPTED_ASM, .text);
 #endif
 
 static void __init kvm_guest_init(void)

arch/x86/kernel/module.c

@@ -74,10 +74,11 @@ void *module_alloc(unsigned long size)
 		return NULL;
 
 	p = __vmalloc_node_range(size, MODULE_ALIGN,
-				    MODULES_VADDR + get_module_load_offset(),
-				    MODULES_END, gfp_mask,
-				    PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE,
-				    __builtin_return_address(0));
+				 MODULES_VADDR + get_module_load_offset(),
+				 MODULES_END, gfp_mask, PAGE_KERNEL,
+				 VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK,
+				 NUMA_NO_NODE, __builtin_return_address(0));
+
 	if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
 		vfree(p);
 		return NULL;
@@ -253,7 +254,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 {
 	const Elf_Shdr *s, *alt = NULL, *locks = NULL,
 		*para = NULL, *orc = NULL, *orc_ip = NULL,
-		*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL;
+		*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
+		*calls = NULL, *cfi = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
@@ -271,6 +273,10 @@ int module_finalize(const Elf_Ehdr *hdr,
 			retpolines = s;
 		if (!strcmp(".return_sites", secstrings + s->sh_name))
 			returns = s;
+		if (!strcmp(".call_sites", secstrings + s->sh_name))
+			calls = s;
+		if (!strcmp(".cfi_sites", secstrings + s->sh_name))
+			cfi = s;
 		if (!strcmp(".ibt_endbr_seal", secstrings + s->sh_name))
 			ibt_endbr = s;
 	}
@@ -283,6 +289,22 @@ int module_finalize(const Elf_Ehdr *hdr,
 		void *pseg = (void *)para->sh_addr;
 		apply_paravirt(pseg, pseg + para->sh_size);
 	}
+	if (retpolines || cfi) {
+		void *rseg = NULL, *cseg = NULL;
+		unsigned int rsize = 0, csize = 0;
+
+		if (retpolines) {
+			rseg = (void *)retpolines->sh_addr;
+			rsize = retpolines->sh_size;
+		}
+
+		if (cfi) {
+			cseg = (void *)cfi->sh_addr;
+			csize = cfi->sh_size;
+		}
+
+		apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize);
+	}
 	if (retpolines) {
 		void *rseg = (void *)retpolines->sh_addr;
 		apply_retpolines(rseg, rseg + retpolines->sh_size);
@@ -296,6 +318,21 @@ int module_finalize(const Elf_Ehdr *hdr,
 		void *aseg = (void *)alt->sh_addr;
 		apply_alternatives(aseg, aseg + alt->sh_size);
 	}
+	if (calls || para) {
+		struct callthunk_sites cs = {};
+
+		if (calls) {
+			cs.call_start = (void *)calls->sh_addr;
+			cs.call_end = (void *)calls->sh_addr + calls->sh_size;
+		}
+
+		if (para) {
+			cs.pv_start = (void *)para->sh_addr;
+			cs.pv_end = (void *)para->sh_addr + para->sh_size;
+		}
+
+		callthunks_patch_module_calls(&cs, me);
+	}
 	if (ibt_endbr) {
 		void *iseg = (void *)ibt_endbr->sh_addr;
 		apply_ibt_endbr(iseg, iseg + ibt_endbr->sh_size);

arch/x86/kernel/paravirt.c

@@ -37,27 +37,10 @@
  * nop stub, which must not clobber anything *including the stack* to
  * avoid confusing the entry prologues.
  */
-extern void _paravirt_nop(void);
-asm (".pushsection .entry.text, \"ax\"\n"
-     ".global _paravirt_nop\n"
-     "_paravirt_nop:\n\t"
-     ASM_ENDBR
-     ASM_RET
-     ".size _paravirt_nop, . - _paravirt_nop\n\t"
-     ".type _paravirt_nop, @function\n\t"
-     ".popsection");
+DEFINE_PARAVIRT_ASM(_paravirt_nop, "", .entry.text);
 
 /* stub always returning 0. */
-asm (".pushsection .entry.text, \"ax\"\n"
-     ".global paravirt_ret0\n"
-     "paravirt_ret0:\n\t"
-     ASM_ENDBR
-     "xor %" _ASM_AX ", %" _ASM_AX ";\n\t"
-     ASM_RET
-     ".size paravirt_ret0, . - paravirt_ret0\n\t"
-     ".type paravirt_ret0, @function\n\t"
-     ".popsection");
-
+DEFINE_PARAVIRT_ASM(paravirt_ret0, "xor %eax,%eax", .entry.text);
 
 void __init default_banner(void)
 {

arch/x86/kernel/process_32.c

@@ -191,13 +191,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	arch_end_context_switch(next_p);
 
 	/*
-	 * Reload esp0 and cpu_current_top_of_stack.  This changes
+	 * Reload esp0 and pcpu_hot.top_of_stack.  This changes
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
 	update_task_stack(next_p);
 	refresh_sysenter_cs(next);
-	this_cpu_write(cpu_current_top_of_stack,
+	this_cpu_write(pcpu_hot.top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
 		       THREAD_SIZE);
 
@@ -207,7 +207,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		loadsegment(gs, next->gs);
 
-	this_cpu_write(current_task, next_p);
+	raw_cpu_write(pcpu_hot.current_task, next_p);
 
 	switch_fpu_finish();
 

arch/x86/kernel/process_64.c

@@ -563,7 +563,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
-		     this_cpu_read(hardirq_stack_inuse));
+		     this_cpu_read(pcpu_hot.hardirq_stack_inuse));
 
 	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
 		switch_fpu_prepare(prev_fpu, cpu);
@@ -617,8 +617,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
-	this_cpu_write(current_task, next_p);
-	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
+	raw_cpu_write(pcpu_hot.current_task, next_p);
+	raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p));
 
 	switch_fpu_finish();
 

arch/x86/kernel/relocate_kernel_64.S

@@ -41,6 +41,7 @@
 	.text
 	.align PAGE_SIZE
 	.code64
+SYM_CODE_START_NOALIGN(relocate_range)
 SYM_CODE_START_NOALIGN(relocate_kernel)
 	UNWIND_HINT_EMPTY
 	ANNOTATE_NOENDBR
@@ -312,5 +313,5 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 	int3
 SYM_CODE_END(swap_pages)
 
-	.globl kexec_control_code_size
-.set kexec_control_code_size, . - relocate_kernel
+	.skip KEXEC_CONTROL_CODE_MAX_SIZE - (. - relocate_kernel), 0xcc
+SYM_CODE_END(relocate_range);

arch/x86/kernel/setup_percpu.c

@@ -23,9 +23,6 @@
 #include <asm/cpumask.h>
 #include <asm/cpu.h>
 
-DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
-EXPORT_PER_CPU_SYMBOL(cpu_number);
-
 #ifdef CONFIG_X86_64
 #define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
 #else
@@ -172,7 +169,7 @@ void __init setup_per_cpu_areas(void)
 	for_each_possible_cpu(cpu) {
 		per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
-		per_cpu(cpu_number, cpu) = cpu;
+		per_cpu(pcpu_hot.cpu_number, cpu) = cpu;
 		setup_percpu_segment(cpu);
 		/*
 		 * Copy data used in early init routines from the
@@ -211,7 +208,7 @@ void __init setup_per_cpu_areas(void)
 		 * area.  Reload any changed state for the boot CPU.
 		 */
 		if (!cpu)
-			switch_to_new_gdt(cpu);
+			switch_gdt_and_percpu_base(cpu);
 	}
 
 	/* indicate the early static arrays will soon be gone */

arch/x86/kernel/smpboot.c

@@ -1048,7 +1048,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
-	per_cpu(current_task, cpu) = idle;
+	per_cpu(pcpu_hot.current_task, cpu) = idle;
 	cpu_init_stack_canary(cpu, idle);
 
 	/* Initialize the interrupt stack(s) */
@@ -1058,7 +1058,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
-	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
+	per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
 #else
 	initial_gs = per_cpu_offset(cpu);
 #endif
@@ -1453,7 +1453,11 @@ void arch_thaw_secondary_cpus_end(void)
 void __init native_smp_prepare_boot_cpu(void)
 {
 	int me = smp_processor_id();
-	switch_to_new_gdt(me);
+
+	/* SMP handles this from setup_per_cpu_areas() */
+	if (!IS_ENABLED(CONFIG_SMP))
+		switch_gdt_and_percpu_base(me);
+
 	/* already set me in cpu_online_mask in boot_cpu_init() */
 	cpumask_set_cpu(me, cpu_callout_mask);
 	cpu_set_state_online(me);

arch/x86/kernel/static_call.c

@@ -34,6 +34,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 
 	switch (type) {
 	case CALL:
+		func = callthunks_translate_call_dest(func);
 		code = text_gen_insn(CALL_INSN_OPCODE, insn, func);
 		if (func == &__static_call_return0) {
 			emulate = code;
@@ -52,7 +53,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 
 	case RET:
 		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
-			code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk);
+			code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk);
 		else
 			code = &retinsn;
 		break;

arch/x86/kernel/traps.c

@@ -858,7 +858,7 @@ DEFINE_IDTENTRY_RAW(exc_int3)
  */
 asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
-	struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1;
+	struct pt_regs *regs = (struct pt_regs *)this_cpu_read(pcpu_hot.top_of_stack) - 1;
 	if (regs != eregs)
 		*regs = *eregs;
 	return regs;
@@ -876,7 +876,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
 	 * trust it and switch to the current kernel stack
 	 */
 	if (ip_within_syscall_gap(regs)) {
-		sp = this_cpu_read(cpu_current_top_of_stack);
+		sp = this_cpu_read(pcpu_hot.top_of_stack);
 		goto sync;
 	}
 

arch/x86/kernel/unwind_orc.c

@@ -136,6 +136,21 @@ static struct orc_entry null_orc_entry = {
 	.type = UNWIND_HINT_TYPE_CALL
 };
 
+#ifdef CONFIG_CALL_THUNKS
+static struct orc_entry *orc_callthunk_find(unsigned long ip)
+{
+	if (!is_callthunk((void *)ip))
+		return NULL;
+
+	return &null_orc_entry;
+}
+#else
+static struct orc_entry *orc_callthunk_find(unsigned long ip)
+{
+	return NULL;
+}
+#endif
+
 /* Fake frame pointer entry -- used as a fallback for generated code */
 static struct orc_entry orc_fp_entry = {
 	.type		= UNWIND_HINT_TYPE_CALL,
@@ -189,7 +204,11 @@ static struct orc_entry *orc_find(unsigned long ip)
 	if (orc)
 		return orc;
 
-	return orc_ftrace_find(ip);
+	orc =  orc_ftrace_find(ip);
+	if (orc)
+		return orc;
+
+	return orc_callthunk_find(ip);
 }
 
 #ifdef CONFIG_MODULES

arch/x86/kernel/vmlinux.lds.S

@@ -132,18 +132,19 @@ SECTIONS
 		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
-		ALIGN_ENTRY_TEXT_BEGIN
-		ENTRY_TEXT
-		ALIGN_ENTRY_TEXT_END
 		SOFTIRQENTRY_TEXT
-		STATIC_CALL_TEXT
-		*(.gnu.warning)
-
 #ifdef CONFIG_RETPOLINE
 		__indirect_thunk_start = .;
 		*(.text.__x86.*)
 		__indirect_thunk_end = .;
 #endif
+		STATIC_CALL_TEXT
+
+		ALIGN_ENTRY_TEXT_BEGIN
+		ENTRY_TEXT
+		ALIGN_ENTRY_TEXT_END
+		*(.gnu.warning)
+
 	} :text =0xcccc
 
 	/* End of text section, which should occupy whole number of pages */
@@ -290,6 +291,13 @@ SECTIONS
 		*(.return_sites)
 		__return_sites_end = .;
 	}
+
+	. = ALIGN(8);
+	.call_sites : AT(ADDR(.call_sites) - LOAD_OFFSET) {
+		__call_sites = .;
+		*(.call_sites)
+		__call_sites_end = .;
+	}
 #endif
 
 #ifdef CONFIG_X86_KERNEL_IBT
@@ -301,6 +309,15 @@ SECTIONS
 	}
 #endif
 
+#ifdef CONFIG_FINEIBT
+	. = ALIGN(8);
+	.cfi_sites : AT(ADDR(.cfi_sites) - LOAD_OFFSET) {
+		__cfi_sites = .;
+		*(.cfi_sites)
+		__cfi_sites_end = .;
+	}
+#endif
+
 	/*
 	 * struct alt_inst entries. From the header (alternative.h):
 	 * "Alternative instructions for different CPU types or capabilities"
@@ -493,11 +510,3 @@ INIT_PER_CPU(irq_stack_backing_store);
 #endif
 
 #endif /* CONFIG_X86_64 */
-
-#ifdef CONFIG_KEXEC_CORE
-#include <asm/kexec.h>
-
-. = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
-           "kexec control code size is too big");
-#endif
-

arch/x86/kvm/svm/vmenter.S

@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
 #include <asm/asm.h>
+#include <asm/asm-offsets.h>
 #include <asm/bitsperlong.h>
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/nospec-branch.h>

arch/x86/lib/error-inject.c

@@ -11,6 +11,7 @@ asm(
 	".text\n"
 	".type just_return_func, @function\n"
 	".globl just_return_func\n"
+	ASM_FUNC_ALIGN
 	"just_return_func:\n"
 		ANNOTATE_NOENDBR
 		ASM_RET

arch/x86/lib/putuser.S

@@ -47,8 +47,6 @@ SYM_FUNC_START(__put_user_1)
 	LOAD_TASK_SIZE_MINUS_N(0)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
-SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL)
-	ENDBR
 	ASM_STAC
 1:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -56,54 +54,87 @@ SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL)
 	RET
 SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
+
+SYM_FUNC_START(__put_user_nocheck_1)
+	ENDBR
+	ASM_STAC
+2:	movb %al,(%_ASM_CX)
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_nocheck_1)
 EXPORT_SYMBOL(__put_user_nocheck_1)
 
 SYM_FUNC_START(__put_user_2)
 	LOAD_TASK_SIZE_MINUS_N(1)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
-SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL)
-	ENDBR
 	ASM_STAC
-2:	movw %ax,(%_ASM_CX)
+3:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
 	ASM_CLAC
 	RET
 SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
+
+SYM_FUNC_START(__put_user_nocheck_2)
+	ENDBR
+	ASM_STAC
+4:	movw %ax,(%_ASM_CX)
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_nocheck_2)
 EXPORT_SYMBOL(__put_user_nocheck_2)
 
 SYM_FUNC_START(__put_user_4)
 	LOAD_TASK_SIZE_MINUS_N(3)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
-SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL)
-	ENDBR
 	ASM_STAC
-3:	movl %eax,(%_ASM_CX)
+5:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
 	ASM_CLAC
 	RET
 SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
+
+SYM_FUNC_START(__put_user_nocheck_4)
+	ENDBR
+	ASM_STAC
+6:	movl %eax,(%_ASM_CX)
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_nocheck_4)
 EXPORT_SYMBOL(__put_user_nocheck_4)
 
 SYM_FUNC_START(__put_user_8)
 	LOAD_TASK_SIZE_MINUS_N(7)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
-SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL)
-	ENDBR
 	ASM_STAC
-4:	mov %_ASM_AX,(%_ASM_CX)
+7:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32
-5:	movl %edx,4(%_ASM_CX)
+8:	movl %edx,4(%_ASM_CX)
 #endif
 	xor %ecx,%ecx
 	ASM_CLAC
 	RET
 SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
+
+SYM_FUNC_START(__put_user_nocheck_8)
+	ENDBR
+	ASM_STAC
+9:	mov %_ASM_AX,(%_ASM_CX)
+#ifdef CONFIG_X86_32
+10:	movl %edx,4(%_ASM_CX)
+#endif
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_nocheck_8)
 EXPORT_SYMBOL(__put_user_nocheck_8)
 
 SYM_CODE_START_LOCAL(.Lbad_put_user_clac)
@@ -117,6 +148,11 @@ SYM_CODE_END(.Lbad_put_user_clac)
 	_ASM_EXTABLE_UA(2b, .Lbad_put_user_clac)
 	_ASM_EXTABLE_UA(3b, .Lbad_put_user_clac)
 	_ASM_EXTABLE_UA(4b, .Lbad_put_user_clac)
-#ifdef CONFIG_X86_32
 	_ASM_EXTABLE_UA(5b, .Lbad_put_user_clac)
+	_ASM_EXTABLE_UA(6b, .Lbad_put_user_clac)
+	_ASM_EXTABLE_UA(7b, .Lbad_put_user_clac)
+	_ASM_EXTABLE_UA(9b, .Lbad_put_user_clac)
+#ifdef CONFIG_X86_32
+	_ASM_EXTABLE_UA(8b, .Lbad_put_user_clac)
+	_ASM_EXTABLE_UA(10b, .Lbad_put_user_clac)
 #endif

arch/x86/lib/retpoline.S

@@ -5,24 +5,27 @@
 #include <asm/dwarf2.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
+#include <asm/asm-offsets.h>
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
 #include <asm/unwind_hints.h>
+#include <asm/percpu.h>
 #include <asm/frame.h>
 
 	.section .text.__x86.indirect_thunk
 
-.macro RETPOLINE reg
+
+.macro POLINE reg
 	ANNOTATE_INTRA_FUNCTION_CALL
 	call    .Ldo_rop_\@
-.Lspec_trap_\@:
-	UNWIND_HINT_EMPTY
-	pause
-	lfence
-	jmp .Lspec_trap_\@
+	int3
 .Ldo_rop_\@:
 	mov     %\reg, (%_ASM_SP)
 	UNWIND_HINT_FUNC
+.endm
+
+.macro RETPOLINE reg
+	POLINE \reg
 	RET
 .endm
 
@@ -52,7 +55,6 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
  */
 
 #define __EXPORT_THUNK(sym)	_ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
-#define EXPORT_THUNK(reg)	__EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
 
 	.align RETPOLINE_THUNK_SIZE
 SYM_CODE_START(__x86_indirect_thunk_array)
@@ -64,10 +66,65 @@ SYM_CODE_START(__x86_indirect_thunk_array)
 	.align RETPOLINE_THUNK_SIZE
 SYM_CODE_END(__x86_indirect_thunk_array)
 
-#define GEN(reg) EXPORT_THUNK(reg)
+#define GEN(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
 #include <asm/GEN-for-each-reg.h>
 #undef GEN
 
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+.macro CALL_THUNK reg
+	.align RETPOLINE_THUNK_SIZE
+
+SYM_INNER_LABEL(__x86_indirect_call_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_EMPTY
+	ANNOTATE_NOENDBR
+
+	CALL_DEPTH_ACCOUNT
+	POLINE \reg
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+.endm
+
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_START(__x86_indirect_call_thunk_array)
+
+#define GEN(reg) CALL_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_END(__x86_indirect_call_thunk_array)
+
+#define GEN(reg) __EXPORT_THUNK(__x86_indirect_call_thunk_ ## reg)
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+.macro JUMP_THUNK reg
+	.align RETPOLINE_THUNK_SIZE
+
+SYM_INNER_LABEL(__x86_indirect_jump_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_EMPTY
+	ANNOTATE_NOENDBR
+	POLINE \reg
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+.endm
+
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_START(__x86_indirect_jump_thunk_array)
+
+#define GEN(reg) JUMP_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_END(__x86_indirect_jump_thunk_array)
+
+#define GEN(reg) __EXPORT_THUNK(__x86_indirect_jump_thunk_ ## reg)
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+#endif
 /*
  * This function name is magical and is used by -mfunction-return=thunk-extern
  * for the compiler to generate JMPs to it.
@@ -140,3 +197,37 @@ __EXPORT_THUNK(zen_untrain_ret)
 EXPORT_SYMBOL(__x86_return_thunk)
 
 #endif /* CONFIG_RETHUNK */
+
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+
+	.align 64
+SYM_FUNC_START(__x86_return_skl)
+	ANNOTATE_NOENDBR
+	/*
+	 * Keep the hotpath in a 16byte I-fetch for the non-debug
+	 * case.
+	 */
+	CALL_THUNKS_DEBUG_INC_RETS
+	shlq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth)
+	jz	1f
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+1:
+	CALL_THUNKS_DEBUG_INC_STUFFS
+	.rept	16
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call	2f
+	int3
+2:
+	.endr
+	add	$(8*16), %rsp
+
+	CREDIT_CALL_DEPTH
+
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+SYM_FUNC_END(__x86_return_skl)
+
+#endif /* CONFIG_CALL_DEPTH_TRACKING */

arch/x86/net/bpf_jit_comp.c

@@ -12,6 +12,7 @@
 #include <linux/memory.h>
 #include <linux/sort.h>
 #include <asm/extable.h>
+#include <asm/ftrace.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 #include <asm/text-patching.h>
@@ -340,6 +341,13 @@ static int emit_call(u8 **pprog, void *func, void *ip)
 	return emit_patch(pprog, func, ip, 0xE8);
 }
 
+static int emit_rsb_call(u8 **pprog, void *func, void *ip)
+{
+	OPTIMIZER_HIDE_VAR(func);
+	x86_call_depth_emit_accounting(pprog, func);
+	return emit_patch(pprog, func, ip, 0xE8);
+}
+
 static int emit_jump(u8 **pprog, void *func, void *ip)
 {
 	return emit_patch(pprog, func, ip, 0xE9);
@@ -417,7 +425,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 		EMIT2(0xFF, 0xE0 + reg);
 	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
 		OPTIMIZER_HIDE_VAR(reg);
-		emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
+		if (cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
+			emit_jump(&prog, &__x86_indirect_jump_thunk_array[reg], ip);
+		else
+			emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
 	} else {
 		EMIT2(0xFF, 0xE0 + reg);	/* jmp *%\reg */
 		if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS))
@@ -432,7 +443,7 @@ static void emit_return(u8 **pprog, u8 *ip)
 	u8 *prog = *pprog;
 
 	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
-		emit_jump(&prog, &__x86_return_thunk, ip);
+		emit_jump(&prog, x86_return_thunk, ip);
 	} else {
 		EMIT1(0xC3);		/* ret */
 		if (IS_ENABLED(CONFIG_SLS))
@@ -1514,19 +1525,26 @@ st:			if (is_imm8(insn->off))
 			break;
 
 			/* call */
-		case BPF_JMP | BPF_CALL:
+		case BPF_JMP | BPF_CALL: {
+			int offs;
+
 			func = (u8 *) __bpf_call_base + imm32;
 			if (tail_call_reachable) {
 				/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
 				EMIT3_off32(0x48, 0x8B, 0x85,
 					    -round_up(bpf_prog->aux->stack_depth, 8) - 8);
-				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7))
+				if (!imm32)
 					return -EINVAL;
+				offs = 7 + x86_call_depth_emit_accounting(&prog, func);
 			} else {
-				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
+				if (!imm32)
 					return -EINVAL;
+				offs = x86_call_depth_emit_accounting(&prog, func);
 			}
+			if (emit_call(&prog, func, image + addrs[i - 1] + offs))
+				return -EINVAL;
 			break;
+		}
 
 		case BPF_JMP | BPF_TAIL_CALL:
 			if (imm32)
@@ -1917,7 +1935,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	/* arg2: lea rsi, [rbp - ctx_cookie_off] */
 	EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
 
-	if (emit_call(&prog, bpf_trampoline_enter(p), prog))
+	if (emit_rsb_call(&prog, bpf_trampoline_enter(p), prog))
 		return -EINVAL;
 	/* remember prog start time returned by __bpf_prog_enter */
 	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
@@ -1938,7 +1956,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			       (long) p->insnsi >> 32,
 			       (u32) (long) p->insnsi);
 	/* call JITed bpf program or interpreter */
-	if (emit_call(&prog, p->bpf_func, prog))
+	if (emit_rsb_call(&prog, p->bpf_func, prog))
 		return -EINVAL;
 
 	/*
@@ -1962,7 +1980,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
 	/* arg3: lea rdx, [rbp - run_ctx_off] */
 	EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
-	if (emit_call(&prog, bpf_trampoline_exit(p), prog))
+	if (emit_rsb_call(&prog, bpf_trampoline_exit(p), prog))
 		return -EINVAL;
 
 	*pprog = prog;
@@ -2184,6 +2202,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	prog = image;
 
 	EMIT_ENDBR();
+	/*
+	 * This is the direct-call trampoline, as such it needs accounting
+	 * for the __fentry__ call.
+	 */
+	x86_call_depth_emit_accounting(&prog, NULL);
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
@@ -2210,7 +2233,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		/* arg1: mov rdi, im */
 		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
-		if (emit_call(&prog, __bpf_tramp_enter, prog)) {
+		if (emit_rsb_call(&prog, __bpf_tramp_enter, prog)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
@@ -2242,7 +2265,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 			EMIT2(0xff, 0xd0); /* call *rax */
 		} else {
 			/* call original function */
-			if (emit_call(&prog, orig_call, prog)) {
+			if (emit_rsb_call(&prog, orig_call, prog)) {
 				ret = -EINVAL;
 				goto cleanup;
 			}
@@ -2286,7 +2309,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		im->ip_epilogue = prog;
 		/* arg1: mov rdi, im */
 		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
-		if (emit_call(&prog, __bpf_tramp_exit, prog)) {
+		if (emit_rsb_call(&prog, __bpf_tramp_exit, prog)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}

arch/x86/power/hibernate.c

@@ -159,7 +159,7 @@ int relocate_restore_code(void)
 	if (!relocated_restore_code)
 		return -ENOMEM;
 
-	memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE);
+	__memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE);
 
 	/* Make the page containing the relocated code executable */
 	pgd = (pgd_t *)__va(read_cr3_pa()) +

arch/x86/xen/enlighten_pv.c

@@ -1210,7 +1210,7 @@ static void __init xen_setup_gdt(int cpu)
 	pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry_boot;
 	pv_ops.cpu.load_gdt = xen_load_gdt_boot;
 
-	switch_to_new_gdt(cpu);
+	switch_gdt_and_percpu_base(cpu);
 
 	pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry;
 	pv_ops.cpu.load_gdt = xen_load_gdt;

include/asm-generic/vmlinux.lds.h

@@ -81,8 +81,8 @@
 #define RO_EXCEPTION_TABLE
 #endif
 
-/* Align . to a 8 byte boundary equals to maximum function alignment. */
-#define ALIGN_FUNCTION()  . = ALIGN(8)
+/* Align . function alignment. */
+#define ALIGN_FUNCTION()  . = ALIGN(CONFIG_FUNCTION_ALIGNMENT)
 
 /*
  * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which

include/linux/linkage.h

@@ -69,8 +69,8 @@
 #endif
 
 #ifndef __ALIGN
-#define __ALIGN		.align 4,0x90
-#define __ALIGN_STR	".align 4,0x90"
+#define __ALIGN			.balign CONFIG_FUNCTION_ALIGNMENT
+#define __ALIGN_STR		__stringify(__ALIGN)
 #endif
 
 #ifdef __ASSEMBLY__

include/linux/static_call.h

@@ -162,6 +162,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 
 extern int __init static_call_init(void);
 
+extern void static_call_force_reinit(void);
+
 struct static_call_mod {
 	struct static_call_mod *next;
 	struct module *mod; /* for vmlinux, mod == NULL */

kernel/static_call_inline.c

@@ -15,7 +15,18 @@ extern struct static_call_site __start_static_call_sites[],
 extern struct static_call_tramp_key __start_static_call_tramp_key[],
 				    __stop_static_call_tramp_key[];
 
-static bool static_call_initialized;
+static int static_call_initialized;
+
+/*
+ * Must be called before early_initcall() to be effective.
+ */
+void static_call_force_reinit(void)
+{
+	if (WARN_ON_ONCE(!static_call_initialized))
+		return;
+
+	static_call_initialized++;
+}
 
 /* mutex to protect key modules/sites */
 static DEFINE_MUTEX(static_call_mutex);
@@ -475,7 +486,8 @@ int __init static_call_init(void)
 {
 	int ret;
 
-	if (static_call_initialized)
+	/* See static_call_force_reinit(). */
+	if (static_call_initialized == 1)
 		return 0;
 
 	cpus_read_lock();
@@ -490,11 +502,12 @@ int __init static_call_init(void)
 		BUG();
 	}
 
-	static_call_initialized = true;
-
 #ifdef CONFIG_MODULES
-	register_module_notifier(&static_call_module_nb);
+	if (!static_call_initialized)
+		register_module_notifier(&static_call_module_nb);
 #endif
+
+	static_call_initialized = 1;
 	return 0;
 }
 early_initcall(static_call_init);

kernel/trace/trace_selftest.c

@@ -785,7 +785,14 @@ static struct fgraph_ops fgraph_ops __initdata  = {
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
-noinline __noclone static void trace_direct_tramp(void) { }
+#ifndef CALL_DEPTH_ACCOUNT
+#define CALL_DEPTH_ACCOUNT ""
+#endif
+
+noinline __noclone static void trace_direct_tramp(void)
+{
+	asm(CALL_DEPTH_ACCOUNT);
+}
 #endif
 
 /*

lib/Kconfig.debug

@@ -469,6 +469,7 @@ config SECTION_MISMATCH_WARN_ONLY
 config DEBUG_FORCE_FUNCTION_ALIGN_64B
 	bool "Force all function address 64B aligned"
 	depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC)
+	select FUNCTION_ALIGNMENT_64B
 	help
 	  There are cases that a commit from one domain changes the function
 	  address alignment of other domains, and cause magic performance

samples/ftrace/ftrace-direct-modify.c

@@ -3,6 +3,7 @@
 #include <linux/kthread.h>
 #include <linux/ftrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func1(void);
 extern void my_direct_func2(void);
@@ -34,6 +35,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	call my_direct_func1\n"
 "	leave\n"
 "	.size		my_tramp1, .-my_tramp1\n"
@@ -45,6 +47,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	call my_direct_func2\n"
 "	leave\n"
 	ASM_RET

samples/ftrace/ftrace-direct-multi-modify.c

@@ -3,6 +3,7 @@
 #include <linux/kthread.h>
 #include <linux/ftrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func1(unsigned long ip);
 extern void my_direct_func2(unsigned long ip);
@@ -32,6 +33,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	movq 8(%rbp), %rdi\n"
 "	call my_direct_func1\n"
@@ -46,6 +48,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	movq 8(%rbp), %rdi\n"
 "	call my_direct_func2\n"

samples/ftrace/ftrace-direct-multi.c

@@ -5,6 +5,7 @@
 #include <linux/ftrace.h>
 #include <linux/sched/stat.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func(unsigned long ip);
 
@@ -27,6 +28,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	movq 8(%rbp), %rdi\n"
 "	call my_direct_func\n"

samples/ftrace/ftrace-direct-too.c

@@ -4,6 +4,7 @@
 #include <linux/mm.h> /* for handle_mm_fault() */
 #include <linux/ftrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func(struct vm_area_struct *vma,
 			   unsigned long address, unsigned int flags);
@@ -29,6 +30,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	pushq %rsi\n"
 "	pushq %rdx\n"

samples/ftrace/ftrace-direct.c

@@ -4,6 +4,7 @@
 #include <linux/sched.h> /* for wake_up_process() */
 #include <linux/ftrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func(struct task_struct *p);
 
@@ -26,6 +27,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	call my_direct_func\n"
 "	popq %rdi\n"

scripts/Makefile.lib

@@ -254,7 +254,9 @@ objtool := $(objtree)/tools/objtool/objtool
 
 objtool-args-$(CONFIG_HAVE_JUMP_LABEL_HACK)		+= --hacks=jump_label
 objtool-args-$(CONFIG_HAVE_NOINSTR_HACK)		+= --hacks=noinstr
+objtool-args-$(CONFIG_CALL_DEPTH_TRACKING)		+= --hacks=skylake
 objtool-args-$(CONFIG_X86_KERNEL_IBT)			+= --ibt
+objtool-args-$(CONFIG_FINEIBT)				+= --cfi
 objtool-args-$(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL)	+= --mcount
 objtool-args-$(CONFIG_UNWINDER_ORC)			+= --orc
 objtool-args-$(CONFIG_RETPOLINE)			+= --retpoline
@@ -264,6 +266,7 @@ objtool-args-$(CONFIG_STACK_VALIDATION)			+= --stackval
 objtool-args-$(CONFIG_HAVE_STATIC_CALL_INLINE)		+= --static-call
 objtool-args-$(CONFIG_HAVE_UACCESS_VALIDATION)		+= --uaccess
 objtool-args-$(CONFIG_GCOV_KERNEL)			+= --no-unreachable
+objtool-args-$(CONFIG_PREFIX_SYMBOLS)			+= --prefix=$(CONFIG_FUNCTION_PADDING_BYTES)
 
 objtool-args = $(objtool-args-y)					\
 	$(if $(delay-objtool), --link)					\

tools/include/linux/interval_tree_generic.h

@@ -0,0 +1,187 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+  Interval Trees
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+
+  include/linux/interval_tree_generic.h
+*/
+
+#include <linux/rbtree_augmented.h>
+
+/*
+ * Template for implementing interval trees
+ *
+ * ITSTRUCT:   struct type of the interval tree nodes
+ * ITRB:       name of struct rb_node field within ITSTRUCT
+ * ITTYPE:     type of the interval endpoints
+ * ITSUBTREE:  name of ITTYPE field within ITSTRUCT holding last-in-subtree
+ * ITSTART(n): start endpoint of ITSTRUCT node n
+ * ITLAST(n):  last endpoint of ITSTRUCT node n
+ * ITSTATIC:   'static' or empty
+ * ITPREFIX:   prefix to use for the inline tree definitions
+ *
+ * Note - before using this, please consider if generic version
+ * (interval_tree.h) would work for you...
+ */
+
+#define INTERVAL_TREE_DEFINE(ITSTRUCT, ITRB, ITTYPE, ITSUBTREE,		      \
+			     ITSTART, ITLAST, ITSTATIC, ITPREFIX)	      \
+									      \
+/* Callbacks for augmented rbtree insert and remove */			      \
+									      \
+RB_DECLARE_CALLBACKS_MAX(static, ITPREFIX ## _augment,			      \
+			 ITSTRUCT, ITRB, ITTYPE, ITSUBTREE, ITLAST)	      \
+									      \
+/* Insert / remove interval nodes from the tree */			      \
+									      \
+ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node,			      \
+				  struct rb_root_cached *root)	 	      \
+{									      \
+	struct rb_node **link = &root->rb_root.rb_node, *rb_parent = NULL;    \
+	ITTYPE start = ITSTART(node), last = ITLAST(node);		      \
+	ITSTRUCT *parent;						      \
+	bool leftmost = true;						      \
+									      \
+	while (*link) {							      \
+		rb_parent = *link;					      \
+		parent = rb_entry(rb_parent, ITSTRUCT, ITRB);		      \
+		if (parent->ITSUBTREE < last)				      \
+			parent->ITSUBTREE = last;			      \
+		if (start < ITSTART(parent))				      \
+			link = &parent->ITRB.rb_left;			      \
+		else {							      \
+			link = &parent->ITRB.rb_right;			      \
+			leftmost = false;				      \
+		}							      \
+	}								      \
+									      \
+	node->ITSUBTREE = last;						      \
+	rb_link_node(&node->ITRB, rb_parent, link);			      \
+	rb_insert_augmented_cached(&node->ITRB, root,			      \
+				   leftmost, &ITPREFIX ## _augment);	      \
+}									      \
+									      \
+ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node,			      \
+				  struct rb_root_cached *root)		      \
+{									      \
+	rb_erase_augmented_cached(&node->ITRB, root, &ITPREFIX ## _augment);  \
+}									      \
+									      \
+/*									      \
+ * Iterate over intervals intersecting [start;last]			      \
+ *									      \
+ * Note that a node's interval intersects [start;last] iff:		      \
+ *   Cond1: ITSTART(node) <= last					      \
+ * and									      \
+ *   Cond2: start <= ITLAST(node)					      \
+ */									      \
+									      \
+static ITSTRUCT *							      \
+ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last)	      \
+{									      \
+	while (true) {							      \
+		/*							      \
+		 * Loop invariant: start <= node->ITSUBTREE		      \
+		 * (Cond2 is satisfied by one of the subtree nodes)	      \
+		 */							      \
+		if (node->ITRB.rb_left) {				      \
+			ITSTRUCT *left = rb_entry(node->ITRB.rb_left,	      \
+						  ITSTRUCT, ITRB);	      \
+			if (start <= left->ITSUBTREE) {			      \
+				/*					      \
+				 * Some nodes in left subtree satisfy Cond2.  \
+				 * Iterate to find the leftmost such node N.  \
+				 * If it also satisfies Cond1, that's the     \
+				 * match we are looking for. Otherwise, there \
+				 * is no matching interval as nodes to the    \
+				 * right of N can't satisfy Cond1 either.     \
+				 */					      \
+				node = left;				      \
+				continue;				      \
+			}						      \
+		}							      \
+		if (ITSTART(node) <= last) {		/* Cond1 */	      \
+			if (start <= ITLAST(node))	/* Cond2 */	      \
+				return node;	/* node is leftmost match */  \
+			if (node->ITRB.rb_right) {			      \
+				node = rb_entry(node->ITRB.rb_right,	      \
+						ITSTRUCT, ITRB);	      \
+				if (start <= node->ITSUBTREE)		      \
+					continue;			      \
+			}						      \
+		}							      \
+		return NULL;	/* No match */				      \
+	}								      \
+}									      \
+									      \
+ITSTATIC ITSTRUCT *							      \
+ITPREFIX ## _iter_first(struct rb_root_cached *root,			      \
+			ITTYPE start, ITTYPE last)			      \
+{									      \
+	ITSTRUCT *node, *leftmost;					      \
+									      \
+	if (!root->rb_root.rb_node)					      \
+		return NULL;						      \
+									      \
+	/*								      \
+	 * Fastpath range intersection/overlap between A: [a0, a1] and	      \
+	 * B: [b0, b1] is given by:					      \
+	 *								      \
+	 *         a0 <= b1 && b0 <= a1					      \
+	 *								      \
+	 *  ... where A holds the lock range and B holds the smallest	      \
+	 * 'start' and largest 'last' in the tree. For the later, we	      \
+	 * rely on the root node, which by augmented interval tree	      \
+	 * property, holds the largest value in its last-in-subtree.	      \
+	 * This allows mitigating some of the tree walk overhead for	      \
+	 * for non-intersecting ranges, maintained and consulted in O(1).     \
+	 */								      \
+	node = rb_entry(root->rb_root.rb_node, ITSTRUCT, ITRB);		      \
+	if (node->ITSUBTREE < start)					      \
+		return NULL;						      \
+									      \
+	leftmost = rb_entry(root->rb_leftmost, ITSTRUCT, ITRB);		      \
+	if (ITSTART(leftmost) > last)					      \
+		return NULL;						      \
+									      \
+	return ITPREFIX ## _subtree_search(node, start, last);		      \
+}									      \
+									      \
+ITSTATIC ITSTRUCT *							      \
+ITPREFIX ## _iter_next(ITSTRUCT *node, ITTYPE start, ITTYPE last)	      \
+{									      \
+	struct rb_node *rb = node->ITRB.rb_right, *prev;		      \
+									      \
+	while (true) {							      \
+		/*							      \
+		 * Loop invariants:					      \
+		 *   Cond1: ITSTART(node) <= last			      \
+		 *   rb == node->ITRB.rb_right				      \
+		 *							      \
+		 * First, search right subtree if suitable		      \
+		 */							      \
+		if (rb) {						      \
+			ITSTRUCT *right = rb_entry(rb, ITSTRUCT, ITRB);	      \
+			if (start <= right->ITSUBTREE)			      \
+				return ITPREFIX ## _subtree_search(right,     \
+								start, last); \
+		}							      \
+									      \
+		/* Move up the tree until we come from a node's left child */ \
+		do {							      \
+			rb = rb_parent(&node->ITRB);			      \
+			if (!rb)					      \
+				return NULL;				      \
+			prev = &node->ITRB;				      \
+			node = rb_entry(rb, ITSTRUCT, ITRB);		      \
+			rb = node->ITRB.rb_right;			      \
+		} while (prev == rb);					      \
+									      \
+		/* Check if the node intersects [start;last] */		      \
+		if (last < ITSTART(node))		/* !Cond1 */	      \
+			return NULL;					      \
+		else if (start <= ITLAST(node))		/* Cond2 */	      \
+			return node;					      \
+	}								      \
+}

tools/objtool/arch/x86/decode.c

@@ -73,6 +73,30 @@ unsigned long arch_jump_destination(struct instruction *insn)
 	return insn->offset + insn->len + insn->immediate;
 }
 
+bool arch_pc_relative_reloc(struct reloc *reloc)
+{
+	/*
+	 * All relocation types where P (the address of the target)
+	 * is included in the computation.
+	 */
+	switch (reloc->type) {
+	case R_X86_64_PC8:
+	case R_X86_64_PC16:
+	case R_X86_64_PC32:
+	case R_X86_64_PC64:
+
+	case R_X86_64_PLT32:
+	case R_X86_64_GOTPC32:
+	case R_X86_64_GOTPCREL:
+		return true;
+
+	default:
+		break;
+	}
+
+	return false;
+}
+
 #define ADD_OP(op) \
 	if (!(op = calloc(1, sizeof(*op)))) \
 		return -1; \

tools/objtool/builtin-check.c

@@ -57,12 +57,17 @@ static int parse_hacks(const struct option *opt, const char *str, int unset)
 		found = true;
 	}
 
+	if (!str || strstr(str, "skylake")) {
+		opts.hack_skylake = true;
+		found = true;
+	}
+
 	return found ? 0 : -1;
 }
 
 const struct option check_options[] = {
 	OPT_GROUP("Actions:"),
-	OPT_CALLBACK_OPTARG('h', "hacks", NULL, NULL, "jump_label,noinstr", "patch toolchain bugs/limitations", parse_hacks),
+	OPT_CALLBACK_OPTARG('h', "hacks", NULL, NULL, "jump_label,noinstr,skylake", "patch toolchain bugs/limitations", parse_hacks),
 	OPT_BOOLEAN('i', "ibt", &opts.ibt, "validate and annotate IBT"),
 	OPT_BOOLEAN('m', "mcount", &opts.mcount, "annotate mcount/fentry calls for ftrace"),
 	OPT_BOOLEAN('n', "noinstr", &opts.noinstr, "validate noinstr rules"),
@@ -70,10 +75,12 @@ const struct option check_options[] = {
 	OPT_BOOLEAN('r', "retpoline", &opts.retpoline, "validate and annotate retpoline usage"),
 	OPT_BOOLEAN(0,   "rethunk", &opts.rethunk, "validate and annotate rethunk usage"),
 	OPT_BOOLEAN(0,   "unret", &opts.unret, "validate entry unret placement"),
+	OPT_INTEGER(0,   "prefix", &opts.prefix, "generate prefix symbols"),
 	OPT_BOOLEAN('l', "sls", &opts.sls, "validate straight-line-speculation mitigations"),
 	OPT_BOOLEAN('s', "stackval", &opts.stackval, "validate frame pointer rules"),
 	OPT_BOOLEAN('t', "static-call", &opts.static_call, "annotate static calls"),
 	OPT_BOOLEAN('u', "uaccess", &opts.uaccess, "validate uaccess rules for SMAP"),
+	OPT_BOOLEAN(0  , "cfi", &opts.cfi, "annotate kernel control flow integrity (kCFI) function preambles"),
 	OPT_CALLBACK_OPTARG(0, "dump", NULL, NULL, "orc", "dump metadata", parse_dump),
 
 	OPT_GROUP("Options:"),

tools/objtool/check.c

@@ -62,12 +62,12 @@ static struct instruction *next_insn_same_func(struct objtool_file *file,
 					       struct instruction *insn)
 {
 	struct instruction *next = list_next_entry(insn, list);
-	struct symbol *func = insn->func;
+	struct symbol *func = insn_func(insn);
 
 	if (!func)
 		return NULL;
 
-	if (&next->list != &file->insn_list && next->func == func)
+	if (&next->list != &file->insn_list && insn_func(next) == func)
 		return next;
 
 	/* Check if we're already in the subfunction: */
@@ -83,7 +83,7 @@ static struct instruction *prev_insn_same_sym(struct objtool_file *file,
 {
 	struct instruction *prev = list_prev_entry(insn, list);
 
-	if (&prev->list != &file->insn_list && prev->func == insn->func)
+	if (&prev->list != &file->insn_list && insn_func(prev) == insn_func(insn))
 		return prev;
 
 	return NULL;
@@ -129,16 +129,13 @@ static bool is_jump_table_jump(struct instruction *insn)
 static bool is_sibling_call(struct instruction *insn)
 {
 	/*
-	 * Assume only ELF functions can make sibling calls.  This ensures
-	 * sibling call detection consistency between vmlinux.o and individual
-	 * objects.
+	 * Assume only STT_FUNC calls have jump-tables.
 	 */
-	if (!insn->func)
-		return false;
-
-	/* An indirect jump is either a sibling call or a jump to a table. */
-	if (insn->type == INSN_JUMP_DYNAMIC)
-		return !is_jump_table_jump(insn);
+	if (insn_func(insn)) {
+		/* An indirect jump is either a sibling call or a jump to a table. */
+		if (insn->type == INSN_JUMP_DYNAMIC)
+			return !is_jump_table_jump(insn);
+	}
 
 	/* add_jump_destinations() sets insn->call_dest for sibling calls. */
 	return (is_static_jump(insn) && insn->call_dest);
@@ -207,7 +204,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
 		return false;
 
 	insn = find_insn(file, func->sec, func->offset);
-	if (!insn->func)
+	if (!insn_func(insn))
 		return false;
 
 	func_for_each_insn(file, func, insn) {
@@ -243,7 +240,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
 				return false;
 			}
 
-			return __dead_end_function(file, dest->func, recursion+1);
+			return __dead_end_function(file, insn_func(dest), recursion+1);
 		}
 	}
 
@@ -382,6 +379,15 @@ static int decode_instructions(struct objtool_file *file)
 		    !strncmp(sec->name, ".text.__x86.", 12))
 			sec->noinstr = true;
 
+		/*
+		 * .init.text code is ran before userspace and thus doesn't
+		 * strictly need retpolines, except for modules which are
+		 * loaded late, they very much do need retpoline in their
+		 * .init.text
+		 */
+		if (!strcmp(sec->name, ".init.text") && !opts.module)
+			sec->init = true;
+
 		for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) {
 			insn = malloc(sizeof(*insn));
 			if (!insn) {
@@ -418,7 +424,10 @@ static int decode_instructions(struct objtool_file *file)
 		}
 
 		list_for_each_entry(func, &sec->symbol_list, list) {
-			if (func->type != STT_FUNC || func->alias != func)
+			if (func->type != STT_NOTYPE && func->type != STT_FUNC)
+				continue;
+
+			if (func->return_thunk || func->alias != func)
 				continue;
 
 			if (!find_insn(file, sec, func->offset)) {
@@ -428,9 +437,11 @@ static int decode_instructions(struct objtool_file *file)
 			}
 
 			sym_for_each_insn(file, func, insn) {
-				insn->func = func;
-				if (insn->type == INSN_ENDBR && list_empty(&insn->call_node)) {
-					if (insn->offset == insn->func->offset) {
+				insn->sym = func;
+				if (func->type == STT_FUNC &&
+				    insn->type == INSN_ENDBR &&
+				    list_empty(&insn->call_node)) {
+					if (insn->offset == func->offset) {
 						list_add_tail(&insn->call_node, &file->endbr_list);
 						file->nr_endbr++;
 					} else {
@@ -850,6 +861,68 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file)
 	return 0;
 }
 
+static int create_cfi_sections(struct objtool_file *file)
+{
+	struct section *sec, *s;
+	struct symbol *sym;
+	unsigned int *loc;
+	int idx;
+
+	sec = find_section_by_name(file->elf, ".cfi_sites");
+	if (sec) {
+		INIT_LIST_HEAD(&file->call_list);
+		WARN("file already has .cfi_sites section, skipping");
+		return 0;
+	}
+
+	idx = 0;
+	for_each_sec(file, s) {
+		if (!s->text)
+			continue;
+
+		list_for_each_entry(sym, &s->symbol_list, list) {
+			if (sym->type != STT_FUNC)
+				continue;
+
+			if (strncmp(sym->name, "__cfi_", 6))
+				continue;
+
+			idx++;
+		}
+	}
+
+	sec = elf_create_section(file->elf, ".cfi_sites", 0, sizeof(unsigned int), idx);
+	if (!sec)
+		return -1;
+
+	idx = 0;
+	for_each_sec(file, s) {
+		if (!s->text)
+			continue;
+
+		list_for_each_entry(sym, &s->symbol_list, list) {
+			if (sym->type != STT_FUNC)
+				continue;
+
+			if (strncmp(sym->name, "__cfi_", 6))
+				continue;
+
+			loc = (unsigned int *)sec->data->d_buf + idx;
+			memset(loc, 0, sizeof(unsigned int));
+
+			if (elf_add_reloc_to_insn(file->elf, sec,
+						  idx * sizeof(unsigned int),
+						  R_X86_64_PC32,
+						  s, sym->offset))
+				return -1;
+
+			idx++;
+		}
+	}
+
+	return 0;
+}
+
 static int create_mcount_loc_sections(struct objtool_file *file)
 {
 	struct section *sec;
@@ -893,6 +966,49 @@ static int create_mcount_loc_sections(struct objtool_file *file)
 	return 0;
 }
 
+static int create_direct_call_sections(struct objtool_file *file)
+{
+	struct instruction *insn;
+	struct section *sec;
+	unsigned int *loc;
+	int idx;
+
+	sec = find_section_by_name(file->elf, ".call_sites");
+	if (sec) {
+		INIT_LIST_HEAD(&file->call_list);
+		WARN("file already has .call_sites section, skipping");
+		return 0;
+	}
+
+	if (list_empty(&file->call_list))
+		return 0;
+
+	idx = 0;
+	list_for_each_entry(insn, &file->call_list, call_node)
+		idx++;
+
+	sec = elf_create_section(file->elf, ".call_sites", 0, sizeof(unsigned int), idx);
+	if (!sec)
+		return -1;
+
+	idx = 0;
+	list_for_each_entry(insn, &file->call_list, call_node) {
+
+		loc = (unsigned int *)sec->data->d_buf + idx;
+		memset(loc, 0, sizeof(unsigned int));
+
+		if (elf_add_reloc_to_insn(file->elf, sec,
+					  idx * sizeof(unsigned int),
+					  R_X86_64_PC32,
+					  insn->sec, insn->offset))
+			return -1;
+
+		idx++;
+	}
+
+	return 0;
+}
+
 /*
  * Warnings shouldn't be reported for ignored functions.
  */
@@ -1280,6 +1396,9 @@ static void annotate_call_site(struct objtool_file *file,
 		return;
 	}
 
+	if (insn->type == INSN_CALL && !insn->sec->init)
+		list_add_tail(&insn->call_node, &file->call_list);
+
 	if (!sibling && dead_end_function(file, sym))
 		insn->dead_end = true;
 }
@@ -1350,27 +1469,50 @@ static void add_return_call(struct objtool_file *file, struct instruction *insn,
 		list_add_tail(&insn->call_node, &file->return_thunk_list);
 }
 
-static bool same_function(struct instruction *insn1, struct instruction *insn2)
+static bool is_first_func_insn(struct objtool_file *file,
+			       struct instruction *insn, struct symbol *sym)
 {
-	return insn1->func->pfunc == insn2->func->pfunc;
-}
-
-static bool is_first_func_insn(struct objtool_file *file, struct instruction *insn)
-{
-	if (insn->offset == insn->func->offset)
+	if (insn->offset == sym->offset)
 		return true;
 
+	/* Allow direct CALL/JMP past ENDBR */
 	if (opts.ibt) {
 		struct instruction *prev = prev_insn_same_sym(file, insn);
 
 		if (prev && prev->type == INSN_ENDBR &&
-		    insn->offset == insn->func->offset + prev->len)
+		    insn->offset == sym->offset + prev->len)
 			return true;
 	}
 
 	return false;
 }
 
+/*
+ * A sibling call is a tail-call to another symbol -- to differentiate from a
+ * recursive tail-call which is to the same symbol.
+ */
+static bool jump_is_sibling_call(struct objtool_file *file,
+				 struct instruction *from, struct instruction *to)
+{
+	struct symbol *fs = from->sym;
+	struct symbol *ts = to->sym;
+
+	/* Not a sibling call if from/to a symbol hole */
+	if (!fs || !ts)
+		return false;
+
+	/* Not a sibling call if not targeting the start of a symbol. */
+	if (!is_first_func_insn(file, to, ts))
+		return false;
+
+	/* Disallow sibling calls into STT_NOTYPE */
+	if (ts->type == STT_NOTYPE)
+		return false;
+
+	/* Must not be self to be a sibling */
+	return fs->pfunc != ts->pfunc;
+}
+
 /*
  * Find the destination instructions for all jumps.
  */
@@ -1405,7 +1547,7 @@ static int add_jump_destinations(struct objtool_file *file)
 		} else if (reloc->sym->return_thunk) {
 			add_return_call(file, insn, true);
 			continue;
-		} else if (insn->func) {
+		} else if (insn_func(insn)) {
 			/*
 			 * External sibling call or internal sibling call with
 			 * STT_FUNC reloc.
@@ -1447,8 +1589,8 @@ static int add_jump_destinations(struct objtool_file *file)
 		/*
 		 * Cross-function jump.
 		 */
-		if (insn->func && jump_dest->func &&
-		    insn->func != jump_dest->func) {
+		if (insn_func(insn) && insn_func(jump_dest) &&
+		    insn_func(insn) != insn_func(jump_dest)) {
 
 			/*
 			 * For GCC 8+, create parent/child links for any cold
@@ -1465,22 +1607,22 @@ static int add_jump_destinations(struct objtool_file *file)
 			 * case where the parent function's only reference to a
 			 * subfunction is through a jump table.
 			 */
-			if (!strstr(insn->func->name, ".cold") &&
-			    strstr(jump_dest->func->name, ".cold")) {
-				insn->func->cfunc = jump_dest->func;
-				jump_dest->func->pfunc = insn->func;
-
-			} else if (!same_function(insn, jump_dest) &&
-				   is_first_func_insn(file, jump_dest)) {
-				/*
-				 * Internal sibling call without reloc or with
-				 * STT_SECTION reloc.
-				 */
-				add_call_dest(file, insn, jump_dest->func, true);
-				continue;
+			if (!strstr(insn_func(insn)->name, ".cold") &&
+			    strstr(insn_func(jump_dest)->name, ".cold")) {
+				insn_func(insn)->cfunc = insn_func(jump_dest);
+				insn_func(jump_dest)->pfunc = insn_func(insn);
 			}
 		}
 
+		if (jump_is_sibling_call(file, insn, jump_dest)) {
+			/*
+			 * Internal sibling call without reloc or with
+			 * STT_SECTION reloc.
+			 */
+			add_call_dest(file, insn, insn_func(jump_dest), true);
+			continue;
+		}
+
 		insn->jump_dest = jump_dest;
 	}
 
@@ -1527,7 +1669,7 @@ static int add_call_destinations(struct objtool_file *file)
 				return -1;
 			}
 
-			if (insn->func && insn->call_dest->type != STT_FUNC) {
+			if (insn_func(insn) && insn->call_dest->type != STT_FUNC) {
 				WARN_FUNC("unsupported call to non-function",
 					  insn->sec, insn->offset);
 				return -1;
@@ -1623,7 +1765,7 @@ static int handle_group_alt(struct objtool_file *file,
 		nop->offset = special_alt->new_off + special_alt->new_len;
 		nop->len = special_alt->orig_len - special_alt->new_len;
 		nop->type = INSN_NOP;
-		nop->func = orig_insn->func;
+		nop->sym = orig_insn->sym;
 		nop->alt_group = new_alt_group;
 		nop->ignore = orig_insn->ignore_alts;
 	}
@@ -1643,7 +1785,7 @@ static int handle_group_alt(struct objtool_file *file,
 		last_new_insn = insn;
 
 		insn->ignore = orig_insn->ignore_alts;
-		insn->func = orig_insn->func;
+		insn->sym = orig_insn->sym;
 		insn->alt_group = new_alt_group;
 
 		/*
@@ -1655,7 +1797,7 @@ static int handle_group_alt(struct objtool_file *file,
 		 * accordingly.
 		 */
 		alt_reloc = insn_reloc(file, insn);
-		if (alt_reloc &&
+		if (alt_reloc && arch_pc_relative_reloc(alt_reloc) &&
 		    !arch_support_alt_relocation(special_alt, insn, alt_reloc)) {
 
 			WARN_FUNC("unsupported relocation in alternatives section",
@@ -1837,7 +1979,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn,
 	struct reloc *reloc = table;
 	struct instruction *dest_insn;
 	struct alternative *alt;
-	struct symbol *pfunc = insn->func->pfunc;
+	struct symbol *pfunc = insn_func(insn)->pfunc;
 	unsigned int prev_offset = 0;
 
 	/*
@@ -1864,7 +2006,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn,
 			break;
 
 		/* Make sure the destination is in the same function: */
-		if (!dest_insn->func || dest_insn->func->pfunc != pfunc)
+		if (!insn_func(dest_insn) || insn_func(dest_insn)->pfunc != pfunc)
 			break;
 
 		alt = malloc(sizeof(*alt));
@@ -1904,7 +2046,7 @@ static struct reloc *find_jump_table(struct objtool_file *file,
 	 * it.
 	 */
 	for (;
-	     insn && insn->func && insn->func->pfunc == func;
+	     insn && insn_func(insn) && insn_func(insn)->pfunc == func;
 	     insn = insn->first_jump_src ?: prev_insn_same_sym(file, insn)) {
 
 		if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC)
@@ -1921,7 +2063,7 @@ static struct reloc *find_jump_table(struct objtool_file *file,
 		if (!table_reloc)
 			continue;
 		dest_insn = find_insn(file, table_reloc->sym->sec, table_reloc->addend);
-		if (!dest_insn || !dest_insn->func || dest_insn->func->pfunc != func)
+		if (!dest_insn || !insn_func(dest_insn) || insn_func(dest_insn)->pfunc != func)
 			continue;
 
 		return table_reloc;
@@ -2370,6 +2512,13 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
+	/*
+	 * Must be before add_{jump_call}_destination.
+	 */
+	ret = classify_symbols(file);
+	if (ret)
+		return ret;
+
 	ret = decode_instructions(file);
 	if (ret)
 		return ret;
@@ -2388,13 +2537,6 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
-	/*
-	 * Must be before add_{jump_call}_destination.
-	 */
-	ret = classify_symbols(file);
-	if (ret)
-		return ret;
-
 	/*
 	 * Must be before add_jump_destinations(), which depends on 'func'
 	 * being set for alternatives, to enable proper sibling call detection.
@@ -2603,7 +2745,7 @@ static int update_cfi_state(struct instruction *insn,
 
 	/* stack operations don't make sense with an undefined CFA */
 	if (cfa->base == CFI_UNDEFINED) {
-		if (insn->func) {
+		if (insn_func(insn)) {
 			WARN_FUNC("undefined stack state", insn->sec, insn->offset);
 			return -1;
 		}
@@ -2949,7 +3091,7 @@ static int update_cfi_state(struct instruction *insn,
 		}
 
 		/* detect when asm code uses rbp as a scratch register */
-		if (opts.stackval && insn->func && op->src.reg == CFI_BP &&
+		if (opts.stackval && insn_func(insn) && op->src.reg == CFI_BP &&
 		    cfa->base != CFI_BP)
 			cfi->bp_scratch = true;
 		break;
@@ -3259,7 +3401,7 @@ static int validate_sibling_call(struct objtool_file *file,
 				 struct instruction *insn,
 				 struct insn_state *state)
 {
-	if (has_modified_stack_frame(insn, state)) {
+	if (insn_func(insn) && has_modified_stack_frame(insn, state)) {
 		WARN_FUNC("sibling call from callable instruction with modified stack frame",
 				insn->sec, insn->offset);
 		return 1;
@@ -3345,13 +3487,14 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 	while (1) {
 		next_insn = next_insn_to_validate(file, insn);
 
-		if (func && insn->func && func != insn->func->pfunc) {
+		if (func && insn_func(insn) && func != insn_func(insn)->pfunc) {
 			/* Ignore KCFI type preambles, which always fall through */
-			if (!strncmp(func->name, "__cfi_", 6))
+			if (!strncmp(func->name, "__cfi_", 6) ||
+			    !strncmp(func->name, "__pfx_", 6))
 				return 0;
 
 			WARN("%s() falls through to next function %s()",
-			     func->name, insn->func->name);
+			     func->name, insn_func(insn)->name);
 			return 1;
 		}
 
@@ -3593,7 +3736,7 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec)
 
 	while (&insn->list != &file->insn_list && (!sec || insn->sec == sec)) {
 		if (insn->hint && !insn->visited && !insn->ignore) {
-			ret = validate_branch(file, insn->func, insn, state);
+			ret = validate_branch(file, insn_func(insn), insn, state);
 			if (ret && opts.backtrace)
 				BT_FUNC("<=== (hint)", insn);
 			warnings += ret;
@@ -3758,13 +3901,7 @@ static int validate_retpoline(struct objtool_file *file)
 		if (insn->retpoline_safe)
 			continue;
 
-		/*
-		 * .init.text code is ran before userspace and thus doesn't
-		 * strictly need retpolines, except for modules which are
-		 * loaded late, they very much do need retpoline in their
-		 * .init.text
-		 */
-		if (!strcmp(insn->sec->name, ".init.text") && !opts.module)
+		if (insn->sec->init)
 			continue;
 
 		if (insn->type == INSN_RETURN) {
@@ -3822,7 +3959,7 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
 	 * In this case we'll find a piece of code (whole function) that is not
 	 * covered by a !section symbol. Ignore them.
 	 */
-	if (opts.link && !insn->func) {
+	if (opts.link && !insn_func(insn)) {
 		int size = find_symbol_hole_containing(insn->sec, insn->offset);
 		unsigned long end = insn->offset + size;
 
@@ -3846,10 +3983,10 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
 			/*
 			 * If this hole jumps to a .cold function, mark it ignore too.
 			 */
-			if (insn->jump_dest && insn->jump_dest->func &&
-			    strstr(insn->jump_dest->func->name, ".cold")) {
+			if (insn->jump_dest && insn_func(insn->jump_dest) &&
+			    strstr(insn_func(insn->jump_dest)->name, ".cold")) {
 				struct instruction *dest = insn->jump_dest;
-				func_for_each_insn(file, dest->func, dest)
+				func_for_each_insn(file, insn_func(dest), dest)
 					dest->ignore = true;
 			}
 		}
@@ -3857,10 +3994,10 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
 		return false;
 	}
 
-	if (!insn->func)
+	if (!insn_func(insn))
 		return false;
 
-	if (insn->func->static_call_tramp)
+	if (insn_func(insn)->static_call_tramp)
 		return true;
 
 	/*
@@ -3891,7 +4028,7 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
 
 		if (insn->type == INSN_JUMP_UNCONDITIONAL) {
 			if (insn->jump_dest &&
-			    insn->jump_dest->func == insn->func) {
+			    insn_func(insn->jump_dest) == insn_func(insn)) {
 				insn = insn->jump_dest;
 				continue;
 			}
@@ -3899,7 +4036,7 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
 			break;
 		}
 
-		if (insn->offset + insn->len >= insn->func->offset + insn->func->len)
+		if (insn->offset + insn->len >= insn_func(insn)->offset + insn_func(insn)->len)
 			break;
 
 		insn = list_next_entry(insn, list);
@@ -3908,6 +4045,54 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
 	return false;
 }
 
+static int add_prefix_symbol(struct objtool_file *file, struct symbol *func,
+			     struct instruction *insn)
+{
+	if (!opts.prefix)
+		return 0;
+
+	for (;;) {
+		struct instruction *prev = list_prev_entry(insn, list);
+		u64 offset;
+
+		if (&prev->list == &file->insn_list)
+			break;
+
+		if (prev->type != INSN_NOP)
+			break;
+
+		offset = func->offset - prev->offset;
+		if (offset >= opts.prefix) {
+			if (offset == opts.prefix) {
+				/*
+				 * Since the sec->symbol_list is ordered by
+				 * offset (see elf_add_symbol()) the added
+				 * symbol will not be seen by the iteration in
+				 * validate_section().
+				 *
+				 * Hence the lack of list_for_each_entry_safe()
+				 * there.
+				 *
+				 * The direct concequence is that prefix symbols
+				 * don't get visited (because pointless), except
+				 * for the logic in ignore_unreachable_insn()
+				 * that needs the terminating insn to be visited
+				 * otherwise it will report the hole.
+				 *
+				 * Hence mark the first instruction of the
+				 * prefix symbol as visisted.
+				 */
+				prev->visited |= VISITED_BRANCH;
+				elf_create_prefix_symbol(file->elf, func, opts.prefix);
+			}
+			break;
+		}
+		insn = prev;
+	}
+
+	return 0;
+}
+
 static int validate_symbol(struct objtool_file *file, struct section *sec,
 			   struct symbol *sym, struct insn_state *state)
 {
@@ -3926,9 +4111,11 @@ static int validate_symbol(struct objtool_file *file, struct section *sec,
 	if (!insn || insn->ignore || insn->visited)
 		return 0;
 
+	add_prefix_symbol(file, sym, insn);
+
 	state->uaccess = sym->uaccess_safe;
 
-	ret = validate_branch(file, insn->func, insn, *state);
+	ret = validate_branch(file, insn_func(insn), insn, *state);
 	if (ret && opts.backtrace)
 		BT_FUNC("<=== (sym)", insn);
 	return ret;
@@ -3994,6 +4181,24 @@ static void mark_endbr_used(struct instruction *insn)
 		list_del_init(&insn->call_node);
 }
 
+static bool noendbr_range(struct objtool_file *file, struct instruction *insn)
+{
+	struct symbol *sym = find_symbol_containing(insn->sec, insn->offset-1);
+	struct instruction *first;
+
+	if (!sym)
+		return false;
+
+	first = find_insn(file, sym->sec, sym->offset);
+	if (!first)
+		return false;
+
+	if (first->type != INSN_ENDBR && !first->noendbr)
+		return false;
+
+	return insn->offset == sym->offset + sym->len;
+}
+
 static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn)
 {
 	struct instruction *dest;
@@ -4047,7 +4252,7 @@ static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn
 			continue;
 		}
 
-		if (dest->func && dest->func == insn->func) {
+		if (insn_func(dest) && insn_func(dest) == insn_func(insn)) {
 			/*
 			 * Anything from->to self is either _THIS_IP_ or
 			 * IRET-to-self.
@@ -4066,9 +4271,19 @@ static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn
 			continue;
 		}
 
+		/*
+		 * Accept anything ANNOTATE_NOENDBR.
+		 */
 		if (dest->noendbr)
 			continue;
 
+		/*
+		 * Accept if this is the instruction after a symbol
+		 * that is (no)endbr -- typical code-range usage.
+		 */
+		if (noendbr_range(file, dest))
+			continue;
+
 		WARN_FUNC("relocation to !ENDBR: %s",
 			  insn->sec, insn->offset,
 			  offstr(dest->sec, dest->offset));
@@ -4307,11 +4522,25 @@ int check(struct objtool_file *file)
 		warnings += ret;
 	}
 
+	if (opts.cfi) {
+		ret = create_cfi_sections(file);
+		if (ret < 0)
+			goto out;
+		warnings += ret;
+	}
+
 	if (opts.rethunk) {
 		ret = create_return_sites_sections(file);
 		if (ret < 0)
 			goto out;
 		warnings += ret;
+
+		if (opts.hack_skylake) {
+			ret = create_direct_call_sections(file);
+			if (ret < 0)
+				goto out;
+			warnings += ret;
+		}
 	}
 
 	if (opts.mcount) {

tools/objtool/elf.c

@@ -16,6 +16,7 @@
 #include <string.h>
 #include <unistd.h>
 #include <errno.h>
+#include <linux/interval_tree_generic.h>
 #include <objtool/builtin.h>
 
 #include <objtool/elf.h>
@@ -50,39 +51,23 @@ static inline u32 str_hash(const char *str)
 	__elf_table(name); \
 })
 
-static bool symbol_to_offset(struct rb_node *a, const struct rb_node *b)
+static inline unsigned long __sym_start(struct symbol *s)
 {
-	struct symbol *sa = rb_entry(a, struct symbol, node);
-	struct symbol *sb = rb_entry(b, struct symbol, node);
-
-	if (sa->offset < sb->offset)
-		return true;
-	if (sa->offset > sb->offset)
-		return false;
-
-	if (sa->len < sb->len)
-		return true;
-	if (sa->len > sb->len)
-		return false;
-
-	sa->alias = sb;
-
-	return false;
+	return s->offset;
 }
 
-static int symbol_by_offset(const void *key, const struct rb_node *node)
+static inline unsigned long __sym_last(struct symbol *s)
 {
-	const struct symbol *s = rb_entry(node, struct symbol, node);
-	const unsigned long *o = key;
-
-	if (*o < s->offset)
-		return -1;
-	if (*o >= s->offset + s->len)
-		return 1;
-
-	return 0;
+	return s->offset + s->len - 1;
 }
 
+INTERVAL_TREE_DEFINE(struct symbol, node, unsigned long, __subtree_last,
+		     __sym_start, __sym_last, static, __sym)
+
+#define __sym_for_each(_iter, _tree, _start, _end)			\
+	for (_iter = __sym_iter_first((_tree), (_start), (_end));	\
+	     _iter; _iter = __sym_iter_next(_iter, (_start), (_end)))
+
 struct symbol_hole {
 	unsigned long key;
 	const struct symbol *sym;
@@ -147,13 +132,12 @@ static struct symbol *find_symbol_by_index(struct elf *elf, unsigned int idx)
 
 struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
 {
-	struct rb_node *node;
+	struct rb_root_cached *tree = (struct rb_root_cached *)&sec->symbol_tree;
+	struct symbol *iter;
 
-	rb_for_each(node, &offset, &sec->symbol_tree, symbol_by_offset) {
-		struct symbol *s = rb_entry(node, struct symbol, node);
-
-		if (s->offset == offset && s->type != STT_SECTION)
-			return s;
+	__sym_for_each(iter, tree, offset, offset) {
+		if (iter->offset == offset && iter->type != STT_SECTION)
+			return iter;
 	}
 
 	return NULL;
@@ -161,13 +145,12 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
 
 struct symbol *find_func_by_offset(struct section *sec, unsigned long offset)
 {
-	struct rb_node *node;
+	struct rb_root_cached *tree = (struct rb_root_cached *)&sec->symbol_tree;
+	struct symbol *iter;
 
-	rb_for_each(node, &offset, &sec->symbol_tree, symbol_by_offset) {
-		struct symbol *s = rb_entry(node, struct symbol, node);
-
-		if (s->offset == offset && s->type == STT_FUNC)
-			return s;
+	__sym_for_each(iter, tree, offset, offset) {
+		if (iter->offset == offset && iter->type == STT_FUNC)
+			return iter;
 	}
 
 	return NULL;
@@ -175,13 +158,12 @@ struct symbol *find_func_by_offset(struct section *sec, unsigned long offset)
 
 struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset)
 {
-	struct rb_node *node;
+	struct rb_root_cached *tree = (struct rb_root_cached *)&sec->symbol_tree;
+	struct symbol *iter;
 
-	rb_for_each(node, &offset, &sec->symbol_tree, symbol_by_offset) {
-		struct symbol *s = rb_entry(node, struct symbol, node);
-
-		if (s->type != STT_SECTION)
-			return s;
+	__sym_for_each(iter, tree, offset, offset) {
+		if (iter->type != STT_SECTION)
+			return iter;
 	}
 
 	return NULL;
@@ -202,7 +184,7 @@ int find_symbol_hole_containing(const struct section *sec, unsigned long offset)
 	/*
 	 * Find the rightmost symbol for which @offset is after it.
 	 */
-	n = rb_find(&hole, &sec->symbol_tree, symbol_hole_by_offset);
+	n = rb_find(&hole, &sec->symbol_tree.rb_root, symbol_hole_by_offset);
 
 	/* found a symbol that contains @offset */
 	if (n)
@@ -224,13 +206,12 @@ int find_symbol_hole_containing(const struct section *sec, unsigned long offset)
 
 struct symbol *find_func_containing(struct section *sec, unsigned long offset)
 {
-	struct rb_node *node;
+	struct rb_root_cached *tree = (struct rb_root_cached *)&sec->symbol_tree;
+	struct symbol *iter;
 
-	rb_for_each(node, &offset, &sec->symbol_tree, symbol_by_offset) {
-		struct symbol *s = rb_entry(node, struct symbol, node);
-
-		if (s->type == STT_FUNC)
-			return s;
+	__sym_for_each(iter, tree, offset, offset) {
+		if (iter->type == STT_FUNC)
+			return iter;
 	}
 
 	return NULL;
@@ -373,7 +354,9 @@ static void elf_add_symbol(struct elf *elf, struct symbol *sym)
 {
 	struct list_head *entry;
 	struct rb_node *pnode;
+	struct symbol *iter;
 
+	INIT_LIST_HEAD(&sym->reloc_list);
 	INIT_LIST_HEAD(&sym->pv_target);
 	sym->alias = sym;
 
@@ -386,7 +369,12 @@ static void elf_add_symbol(struct elf *elf, struct symbol *sym)
 	sym->offset = sym->sym.st_value;
 	sym->len = sym->sym.st_size;
 
-	rb_add(&sym->node, &sym->sec->symbol_tree, symbol_to_offset);
+	__sym_for_each(iter, &sym->sec->symbol_tree, sym->offset, sym->offset) {
+		if (iter->offset == sym->offset && iter->type == sym->type)
+			iter->alias = sym;
+	}
+
+	__sym_insert(sym, &sym->sec->symbol_tree);
 	pnode = rb_prev(&sym->node);
 	if (pnode)
 		entry = &rb_entry(pnode, struct symbol, node)->list;
@@ -401,7 +389,7 @@ static void elf_add_symbol(struct elf *elf, struct symbol *sym)
 	 * can exist within a function, confusing the sorting.
 	 */
 	if (!sym->len)
-		rb_erase(&sym->node, &sym->sec->symbol_tree);
+		__sym_remove(sym, &sym->sec->symbol_tree);
 }
 
 static int read_symbols(struct elf *elf)
@@ -570,6 +558,7 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
 	reloc->sym = sym;
 	reloc->addend = addend;
 
+	list_add_tail(&reloc->sym_reloc_entry, &sym->reloc_list);
 	list_add_tail(&reloc->list, &sec->reloc->reloc_list);
 	elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc));
 
@@ -586,21 +575,10 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
  */
 static void elf_dirty_reloc_sym(struct elf *elf, struct symbol *sym)
 {
-	struct section *sec;
+	struct reloc *reloc;
 
-	list_for_each_entry(sec, &elf->sections, list) {
-		struct reloc *reloc;
-
-		if (sec->changed)
-			continue;
-
-		list_for_each_entry(reloc, &sec->reloc_list, list) {
-			if (reloc->sym == sym) {
-				sec->changed = true;
-				break;
-			}
-		}
-	}
+	list_for_each_entry(reloc, &sym->reloc_list, sym_reloc_entry)
+		reloc->sec->changed = true;
 }
 
 /*
@@ -647,6 +625,12 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab,
 
 		/* end-of-list */
 		if (!symtab_data) {
+			/*
+			 * Over-allocate to avoid O(n^2) symbol creation
+			 * behaviour.  The down side is that libelf doesn't
+			 * like this; see elf_truncate_section() for the fixup.
+			 */
+			int num = max(1U, sym->idx/3);
 			void *buf;
 
 			if (idx) {
@@ -660,28 +644,34 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab,
 			if (t)
 				shndx_data = elf_newdata(t);
 
-			buf = calloc(1, entsize);
+			buf = calloc(num, entsize);
 			if (!buf) {
 				WARN("malloc");
 				return -1;
 			}
 
 			symtab_data->d_buf = buf;
-			symtab_data->d_size = entsize;
+			symtab_data->d_size = num * entsize;
 			symtab_data->d_align = 1;
 			symtab_data->d_type = ELF_T_SYM;
 
-			symtab->sh.sh_size += entsize;
 			symtab->changed = true;
+			symtab->truncate = true;
 
 			if (t) {
-				shndx_data->d_buf = &sym->sec->idx;
-				shndx_data->d_size = sizeof(Elf32_Word);
+				buf = calloc(num, sizeof(Elf32_Word));
+				if (!buf) {
+					WARN("malloc");
+					return -1;
+				}
+
+				shndx_data->d_buf = buf;
+				shndx_data->d_size = num * sizeof(Elf32_Word);
 				shndx_data->d_align = sizeof(Elf32_Word);
 				shndx_data->d_type = ELF_T_WORD;
 
-				symtab_shndx->sh.sh_size += sizeof(Elf32_Word);
 				symtab_shndx->changed = true;
+				symtab_shndx->truncate = true;
 			}
 
 			break;
@@ -730,11 +720,11 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab,
 }
 
 static struct symbol *
-elf_create_section_symbol(struct elf *elf, struct section *sec)
+__elf_create_symbol(struct elf *elf, struct symbol *sym)
 {
 	struct section *symtab, *symtab_shndx;
 	Elf32_Word first_non_local, new_idx;
-	struct symbol *sym, *old;
+	struct symbol *old;
 
 	symtab = find_section_by_name(elf, ".symtab");
 	if (symtab) {
@@ -744,27 +734,16 @@ elf_create_section_symbol(struct elf *elf, struct section *sec)
 		return NULL;
 	}
 
-	sym = calloc(1, sizeof(*sym));
-	if (!sym) {
-		perror("malloc");
-		return NULL;
-	}
+	new_idx = symtab->sh.sh_size / symtab->sh.sh_entsize;
 
-	sym->name = sec->name;
-	sym->sec = sec;
-
-	// st_name 0
-	sym->sym.st_info = GELF_ST_INFO(STB_LOCAL, STT_SECTION);
-	// st_other 0
-	// st_value 0
-	// st_size 0
+	if (GELF_ST_BIND(sym->sym.st_info) != STB_LOCAL)
+		goto non_local;
 
 	/*
 	 * Move the first global symbol, as per sh_info, into a new, higher
 	 * symbol index. This fees up a spot for a new local symbol.
 	 */
 	first_non_local = symtab->sh.sh_info;
-	new_idx = symtab->sh.sh_size / symtab->sh.sh_entsize;
 	old = find_symbol_by_index(elf, first_non_local);
 	if (old) {
 		old->idx = new_idx;
@@ -782,18 +761,82 @@ elf_create_section_symbol(struct elf *elf, struct section *sec)
 		new_idx = first_non_local;
 	}
 
+	/*
+	 * Either way, we will add a LOCAL symbol.
+	 */
+	symtab->sh.sh_info += 1;
+
+non_local:
 	sym->idx = new_idx;
 	if (elf_update_symbol(elf, symtab, symtab_shndx, sym)) {
 		WARN("elf_update_symbol");
 		return NULL;
 	}
 
-	/*
-	 * Either way, we added a LOCAL symbol.
-	 */
-	symtab->sh.sh_info += 1;
+	symtab->sh.sh_size += symtab->sh.sh_entsize;
+	symtab->changed = true;
 
-	elf_add_symbol(elf, sym);
+	if (symtab_shndx) {
+		symtab_shndx->sh.sh_size += sizeof(Elf32_Word);
+		symtab_shndx->changed = true;
+	}
+
+	return sym;
+}
+
+static struct symbol *
+elf_create_section_symbol(struct elf *elf, struct section *sec)
+{
+	struct symbol *sym = calloc(1, sizeof(*sym));
+
+	if (!sym) {
+		perror("malloc");
+		return NULL;
+	}
+
+	sym->name = sec->name;
+	sym->sec = sec;
+
+	// st_name 0
+	sym->sym.st_info = GELF_ST_INFO(STB_LOCAL, STT_SECTION);
+	// st_other 0
+	// st_value 0
+	// st_size 0
+
+	sym = __elf_create_symbol(elf, sym);
+	if (sym)
+		elf_add_symbol(elf, sym);
+
+	return sym;
+}
+
+static int elf_add_string(struct elf *elf, struct section *strtab, char *str);
+
+struct symbol *
+elf_create_prefix_symbol(struct elf *elf, struct symbol *orig, long size)
+{
+	struct symbol *sym = calloc(1, sizeof(*sym));
+	size_t namelen = strlen(orig->name) + sizeof("__pfx_");
+	char *name = malloc(namelen);
+
+	if (!sym || !name) {
+		perror("malloc");
+		return NULL;
+	}
+
+	snprintf(name, namelen, "__pfx_%s", orig->name);
+
+	sym->name = name;
+	sym->sec = orig->sec;
+
+	sym->sym.st_name = elf_add_string(elf, NULL, name);
+	sym->sym.st_info = orig->sym.st_info;
+	sym->sym.st_value = orig->sym.st_value - size;
+	sym->sym.st_size = size;
+
+	sym = __elf_create_symbol(elf, sym);
+	if (sym)
+		elf_add_symbol(elf, sym);
 
 	return sym;
 }
@@ -850,11 +893,12 @@ static int read_rela_reloc(struct section *sec, int i, struct reloc *reloc, unsi
 
 static int read_relocs(struct elf *elf)
 {
+	unsigned long nr_reloc, max_reloc = 0, tot_reloc = 0;
 	struct section *sec;
 	struct reloc *reloc;
-	int i;
 	unsigned int symndx;
-	unsigned long nr_reloc, max_reloc = 0, tot_reloc = 0;
+	struct symbol *sym;
+	int i;
 
 	if (!elf_alloc_hash(reloc, elf->text_size / 16))
 		return -1;
@@ -895,13 +939,14 @@ static int read_relocs(struct elf *elf)
 
 			reloc->sec = sec;
 			reloc->idx = i;
-			reloc->sym = find_symbol_by_index(elf, symndx);
+			reloc->sym = sym = find_symbol_by_index(elf, symndx);
 			if (!reloc->sym) {
 				WARN("can't find reloc entry symbol %d for %s",
 				     symndx, sec->name);
 				return -1;
 			}
 
+			list_add_tail(&reloc->sym_reloc_entry, &sym->reloc_list);
 			list_add_tail(&reloc->list, &sec->reloc_list);
 			elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc));
 
@@ -1285,6 +1330,60 @@ int elf_write_reloc(struct elf *elf, struct reloc *reloc)
 	return 0;
 }
 
+/*
+ * When Elf_Scn::sh_size is smaller than the combined Elf_Data::d_size
+ * do you:
+ *
+ *   A) adhere to the section header and truncate the data, or
+ *   B) ignore the section header and write out all the data you've got?
+ *
+ * Yes, libelf sucks and we need to manually truncate if we over-allocate data.
+ */
+static int elf_truncate_section(struct elf *elf, struct section *sec)
+{
+	u64 size = sec->sh.sh_size;
+	bool truncated = false;
+	Elf_Data *data = NULL;
+	Elf_Scn *s;
+
+	s = elf_getscn(elf->elf, sec->idx);
+	if (!s) {
+		WARN_ELF("elf_getscn");
+		return -1;
+	}
+
+	for (;;) {
+		/* get next data descriptor for the relevant section */
+		data = elf_getdata(s, data);
+
+		if (!data) {
+			if (size) {
+				WARN("end of section data but non-zero size left\n");
+				return -1;
+			}
+			return 0;
+		}
+
+		if (truncated) {
+			/* when we remove symbols */
+			WARN("truncated; but more data\n");
+			return -1;
+		}
+
+		if (!data->d_size) {
+			WARN("zero size data");
+			return -1;
+		}
+
+		if (data->d_size > size) {
+			truncated = true;
+			data->d_size = size;
+		}
+
+		size -= data->d_size;
+	}
+}
+
 int elf_write(struct elf *elf)
 {
 	struct section *sec;
@@ -1295,6 +1394,9 @@ int elf_write(struct elf *elf)
 
 	/* Update changed relocation sections and section headers: */
 	list_for_each_entry(sec, &elf->sections, list) {
+		if (sec->truncate)
+			elf_truncate_section(elf, sec);
+
 		if (sec->changed) {
 			s = elf_getscn(elf->elf, sec->idx);
 			if (!s) {

tools/objtool/include/objtool/arch.h

@@ -93,4 +93,6 @@ bool arch_is_rethunk(struct symbol *sym);
 
 int arch_rewrite_retpolines(struct objtool_file *file);
 
+bool arch_pc_relative_reloc(struct reloc *reloc);
+
 #endif /* _ARCH_H */

tools/objtool/include/objtool/builtin.h

@@ -14,6 +14,7 @@ struct opts {
 	bool dump_orc;
 	bool hack_jump_label;
 	bool hack_noinstr;
+	bool hack_skylake;
 	bool ibt;
 	bool mcount;
 	bool noinstr;
@@ -25,6 +26,8 @@ struct opts {
 	bool stackval;
 	bool static_call;
 	bool uaccess;
+	int prefix;
+	bool cfi;
 
 	/* options: */
 	bool backtrace;

tools/objtool/include/objtool/check.h

@@ -67,11 +67,21 @@ struct instruction {
 	struct reloc *jump_table;
 	struct reloc *reloc;
 	struct list_head alts;
-	struct symbol *func;
+	struct symbol *sym;
 	struct list_head stack_ops;
 	struct cfi_state *cfi;
 };
 
+static inline struct symbol *insn_func(struct instruction *insn)
+{
+	struct symbol *sym = insn->sym;
+
+	if (sym && sym->type != STT_FUNC)
+		sym = NULL;
+
+	return sym;
+}
+
 #define VISITED_BRANCH		0x01
 #define VISITED_BRANCH_UACCESS	0x02
 #define VISITED_BRANCH_MASK	0x03