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
  ...

16 files changed, 0 insertions, 35 deletions

diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index 2e1658ddbe1a..4a30618281ec 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/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
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index 0e4e9abbf4de..deaf62aa73a6 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/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
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index b258af420c92..0326a01503c3 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/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
diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S
index 721474abfb71..5286db5b8165 100644
--- a/arch/x86/crypto/crct10dif-pcl-asm_64.S
+++ b/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
diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
index 2077ce7a5647..b9abcd79c1f4 100644
--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
+++ b/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 {
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index 82f2313f512b..97e283621851 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/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
diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S
index 8ea34c9b9316..6d60c50593a9 100644
--- a/arch/x86/crypto/serpent-avx2-asm_64.S
+++ b/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
diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S
index 3cae5a1bb3d6..cade913d4882 100644
--- a/arch/x86/crypto/sha1_ni_asm.S
+++ b/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
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index 06ea30c20828..5555b5d5215a 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/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
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 2d2be531a11e..3eada9416852 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/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
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index 7db28839108d..959288eecc68 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/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
diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S
index 47f93937f798..537b6dcd7ed8 100644
--- a/arch/x86/crypto/sha256_ni_asm.S
+++ b/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 */
diff --git a/arch/x86/crypto/sm3-avx-asm_64.S b/arch/x86/crypto/sm3-avx-asm_64.S
index 8fc5ac681fd6..503bab450a91 100644
--- a/arch/x86/crypto/sm3-avx-asm_64.S
+++ b/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
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
index 22b6560eb9e1..e2668d2fe6ce 100644
--- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S
+++ b/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
diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
index 23ee39a8ada8..98ede9459287 100644
--- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
+++ b/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
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index 31f9b2ec3857..12fde271cd3f 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/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