Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up BPF changes we'll need. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
author: Arnaldo Carvalho de Melo <acme@redhat.com> 2019-11-26 15:06:19 +0100
committer: Arnaldo Carvalho de Melo <acme@redhat.com> 2019-11-26 15:06:19 +0100
commit: 2ea352d5960ad469f5712cf3e293db97beac4e01 (patch)
tree: c24ae19073f2884867b310ee193d36a82075b60f /arch/x86
parent: Merge branch 'x86/core' into perf/core, to resolve conflicts and to pick up c... (diff)
parent: Merge tag 'for-linus-5.5-1' of git://github.com/cminyard/linux-ipmi (diff)
download: linux-2ea352d5960ad469f5712cf3e293db97beac4e01.tar.xz
linux-2ea352d5960ad469f5712cf3e293db97beac4e01.zip
63 files changed, 5365 insertions, 857 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ef85139553f..f2aed8012e9c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,7 +24,7 @@ config X86_64
 	depends on 64BIT
 	# Options that are inherently 64-bit kernel only:
 	select ARCH_HAS_GIGANTIC_PAGE
-	select ARCH_SUPPORTS_INT128
+	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_SOFT_DIRTY
 	select MODULES_USE_ELF_RELA
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index bf9cd83de777..409c00f74e60 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -316,10 +316,6 @@ config UNWINDER_FRAME_POINTER
 	  unwinder, but the kernel text size will grow by ~3% and the kernel's
 	  overall performance will degrade by roughly 5-10%.
 
-	  This option is recommended if you want to use the livepatch
-	  consistency model, as this is currently the only way to get a
-	  reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE).
-
 config UNWINDER_GUESS
 	bool "Guess unwinder"
 	depends on EXPERT
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 759b1a927826..958440eae27e 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
 
 obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
+obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o
 
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
@@ -48,6 +49,7 @@ ifeq ($(avx_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o
 	obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
 	obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o
 endif
 
 # These modules require assembler to support AVX2.
@@ -70,6 +72,7 @@ serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
 aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
 
 nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
+blake2s-x86_64-y := blake2s-core.o blake2s-glue.o
 
 ifeq ($(avx_supported),yes)
 	camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S
new file mode 100644
index 000000000000..8591938eee26
--- /dev/null
+++ b/arch/x86/crypto/blake2s-core.S
@@ -0,0 +1,258 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2017-2019 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved.
+ */
+
+#include <linux/linkage.h>
+
+.section .rodata.cst32.BLAKE2S_IV, "aM", @progbits, 32
+.align 32
+IV:	.octa 0xA54FF53A3C6EF372BB67AE856A09E667
+	.octa 0x5BE0CD191F83D9AB9B05688C510E527F
+.section .rodata.cst16.ROT16, "aM", @progbits, 16
+.align 16
+ROT16:	.octa 0x0D0C0F0E09080B0A0504070601000302
+.section .rodata.cst16.ROR328, "aM", @progbits, 16
+.align 16
+ROR328:	.octa 0x0C0F0E0D080B0A090407060500030201
+.section .rodata.cst64.BLAKE2S_SIGMA, "aM", @progbits, 160
+.align 64
+SIGMA:
+.byte  0,  2,  4,  6,  1,  3,  5,  7, 14,  8, 10, 12, 15,  9, 11, 13
+.byte 14,  4,  9, 13, 10,  8, 15,  6,  5,  1,  0, 11,  3, 12,  2,  7
+.byte 11, 12,  5, 15,  8,  0,  2, 13,  9, 10,  3,  7,  4, 14,  6,  1
+.byte  7,  3, 13, 11,  9,  1, 12, 14, 15,  2,  5,  4,  8,  6, 10,  0
+.byte  9,  5,  2, 10,  0,  7,  4, 15,  3, 14, 11,  6, 13,  1, 12,  8
+.byte  2,  6,  0,  8, 12, 10, 11,  3,  1,  4,  7, 15,  9, 13,  5, 14
+.byte 12,  1, 14,  4,  5, 15, 13, 10,  8,  0,  6,  9, 11,  7,  3,  2
+.byte 13,  7, 12,  3, 11, 14,  1,  9,  2,  5, 15,  8, 10,  0,  4,  6
+.byte  6, 14, 11,  0, 15,  9,  3,  8, 10, 12, 13,  1,  5,  2,  7,  4
+.byte 10,  8,  7,  1,  2,  4,  6,  5, 13, 15,  9,  3,  0, 11, 14, 12
+#ifdef CONFIG_AS_AVX512
+.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 640
+.align 64
+SIGMA2:
+.long  0,  2,  4,  6,  1,  3,  5,  7, 14,  8, 10, 12, 15,  9, 11, 13
+.long  8,  2, 13, 15, 10,  9, 12,  3,  6,  4,  0, 14,  5, 11,  1,  7
+.long 11, 13,  8,  6,  5, 10, 14,  3,  2,  4, 12, 15,  1,  0,  7,  9
+.long 11, 10,  7,  0,  8, 15,  1, 13,  3,  6,  2, 12,  4, 14,  9,  5
+.long  4, 10,  9, 14, 15,  0, 11,  8,  1,  7,  3, 13,  2,  5,  6, 12
+.long  2, 11,  4, 15, 14,  3, 10,  8, 13,  6,  5,  7,  0, 12,  1,  9
+.long  4,  8, 15,  9, 14, 11, 13,  5,  3,  2,  1, 12,  6, 10,  7,  0
+.long  6, 13,  0, 14, 12,  2,  1, 11, 15,  4,  5,  8,  7,  9,  3, 10
+.long 15,  5,  4, 13, 10,  7,  3, 11, 12,  2,  0,  6,  9,  8,  1, 14
+.long  8,  7, 14, 11, 13, 15,  0, 12, 10,  4,  5,  6,  3,  2,  1,  9
+#endif /* CONFIG_AS_AVX512 */
+
+.text
+#ifdef CONFIG_AS_SSSE3
+ENTRY(blake2s_compress_ssse3)
+	testq		%rdx,%rdx
+	je		.Lendofloop
+	movdqu		(%rdi),%xmm0
+	movdqu		0x10(%rdi),%xmm1
+	movdqa		ROT16(%rip),%xmm12
+	movdqa		ROR328(%rip),%xmm13
+	movdqu		0x20(%rdi),%xmm14
+	movq		%rcx,%xmm15
+	leaq		SIGMA+0xa0(%rip),%r8
+	jmp		.Lbeginofloop
+	.align		32
+.Lbeginofloop:
+	movdqa		%xmm0,%xmm10
+	movdqa		%xmm1,%xmm11
+	paddq		%xmm15,%xmm14
+	movdqa		IV(%rip),%xmm2
+	movdqa		%xmm14,%xmm3
+	pxor		IV+0x10(%rip),%xmm3
+	leaq		SIGMA(%rip),%rcx
+.Lroundloop:
+	movzbl		(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm4
+	movzbl		0x1(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm5
+	movzbl		0x2(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm6
+	movzbl		0x3(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm7
+	punpckldq	%xmm5,%xmm4
+	punpckldq	%xmm7,%xmm6
+	punpcklqdq	%xmm6,%xmm4
+	paddd		%xmm4,%xmm0
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm12,%xmm3
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm8
+	psrld		$0xc,%xmm1
+	pslld		$0x14,%xmm8
+	por		%xmm8,%xmm1
+	movzbl		0x4(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm5
+	movzbl		0x5(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm6
+	movzbl		0x6(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm7
+	movzbl		0x7(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm4
+	punpckldq	%xmm6,%xmm5
+	punpckldq	%xmm4,%xmm7
+	punpcklqdq	%xmm7,%xmm5
+	paddd		%xmm5,%xmm0
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm13,%xmm3
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm8
+	psrld		$0x7,%xmm1
+	pslld		$0x19,%xmm8
+	por		%xmm8,%xmm1
+	pshufd		$0x93,%xmm0,%xmm0
+	pshufd		$0x4e,%xmm3,%xmm3
+	pshufd		$0x39,%xmm2,%xmm2
+	movzbl		0x8(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm6
+	movzbl		0x9(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm7
+	movzbl		0xa(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm4
+	movzbl		0xb(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm5
+	punpckldq	%xmm7,%xmm6
+	punpckldq	%xmm5,%xmm4
+	punpcklqdq	%xmm4,%xmm6
+	paddd		%xmm6,%xmm0
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm12,%xmm3
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm8
+	psrld		$0xc,%xmm1
+	pslld		$0x14,%xmm8
+	por		%xmm8,%xmm1
+	movzbl		0xc(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm7
+	movzbl		0xd(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm4
+	movzbl		0xe(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm5
+	movzbl		0xf(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm6
+	punpckldq	%xmm4,%xmm7
+	punpckldq	%xmm6,%xmm5
+	punpcklqdq	%xmm5,%xmm7
+	paddd		%xmm7,%xmm0
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm13,%xmm3
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm8
+	psrld		$0x7,%xmm1
+	pslld		$0x19,%xmm8
+	por		%xmm8,%xmm1
+	pshufd		$0x39,%xmm0,%xmm0
+	pshufd		$0x4e,%xmm3,%xmm3
+	pshufd		$0x93,%xmm2,%xmm2
+	addq		$0x10,%rcx
+	cmpq		%r8,%rcx
+	jnz		.Lroundloop
+	pxor		%xmm2,%xmm0
+	pxor		%xmm3,%xmm1
+	pxor		%xmm10,%xmm0
+	pxor		%xmm11,%xmm1
+	addq		$0x40,%rsi
+	decq		%rdx
+	jnz		.Lbeginofloop
+	movdqu		%xmm0,(%rdi)
+	movdqu		%xmm1,0x10(%rdi)
+	movdqu		%xmm14,0x20(%rdi)
+.Lendofloop:
+	ret
+ENDPROC(blake2s_compress_ssse3)
+#endif /* CONFIG_AS_SSSE3 */
+
+#ifdef CONFIG_AS_AVX512
+ENTRY(blake2s_compress_avx512)
+	vmovdqu		(%rdi),%xmm0
+	vmovdqu		0x10(%rdi),%xmm1
+	vmovdqu		0x20(%rdi),%xmm4
+	vmovq		%rcx,%xmm5
+	vmovdqa		IV(%rip),%xmm14
+	vmovdqa		IV+16(%rip),%xmm15
+	jmp		.Lblake2s_compress_avx512_mainloop
+.align 32
+.Lblake2s_compress_avx512_mainloop:
+	vmovdqa		%xmm0,%xmm10
+	vmovdqa		%xmm1,%xmm11
+	vpaddq		%xmm5,%xmm4,%xmm4
+	vmovdqa		%xmm14,%xmm2
+	vpxor		%xmm15,%xmm4,%xmm3
+	vmovdqu		(%rsi),%ymm6
+	vmovdqu		0x20(%rsi),%ymm7
+	addq		$0x40,%rsi
+	leaq		SIGMA2(%rip),%rax
+	movb		$0xa,%cl
+.Lblake2s_compress_avx512_roundloop:
+	addq		$0x40,%rax
+	vmovdqa		-0x40(%rax),%ymm8
+	vmovdqa		-0x20(%rax),%ymm9
+	vpermi2d	%ymm7,%ymm6,%ymm8
+	vpermi2d	%ymm7,%ymm6,%ymm9
+	vmovdqa		%ymm8,%ymm6
+	vmovdqa		%ymm9,%ymm7
+	vpaddd		%xmm8,%xmm0,%xmm0
+	vpaddd		%xmm1,%xmm0,%xmm0
+	vpxor		%xmm0,%xmm3,%xmm3
+	vprord		$0x10,%xmm3,%xmm3
+	vpaddd		%xmm3,%xmm2,%xmm2
+	vpxor		%xmm2,%xmm1,%xmm1
+	vprord		$0xc,%xmm1,%xmm1
+	vextracti128	$0x1,%ymm8,%xmm8
+	vpaddd		%xmm8,%xmm0,%xmm0
+	vpaddd		%xmm1,%xmm0,%xmm0
+	vpxor		%xmm0,%xmm3,%xmm3
+	vprord		$0x8,%xmm3,%xmm3
+	vpaddd		%xmm3,%xmm2,%xmm2
+	vpxor		%xmm2,%xmm1,%xmm1
+	vprord		$0x7,%xmm1,%xmm1
+	vpshufd		$0x93,%xmm0,%xmm0
+	vpshufd		$0x4e,%xmm3,%xmm3
+	vpshufd		$0x39,%xmm2,%xmm2
+	vpaddd		%xmm9,%xmm0,%xmm0
+	vpaddd		%xmm1,%xmm0,%xmm0
+	vpxor		%xmm0,%xmm3,%xmm3
+	vprord		$0x10,%xmm3,%xmm3
+	vpaddd		%xmm3,%xmm2,%xmm2
+	vpxor		%xmm2,%xmm1,%xmm1
+	vprord		$0xc,%xmm1,%xmm1
+	vextracti128	$0x1,%ymm9,%xmm9
+	vpaddd		%xmm9,%xmm0,%xmm0
+	vpaddd		%xmm1,%xmm0,%xmm0
+	vpxor		%xmm0,%xmm3,%xmm3
+	vprord		$0x8,%xmm3,%xmm3
+	vpaddd		%xmm3,%xmm2,%xmm2
+	vpxor		%xmm2,%xmm1,%xmm1
+	vprord		$0x7,%xmm1,%xmm1
+	vpshufd		$0x39,%xmm0,%xmm0
+	vpshufd		$0x4e,%xmm3,%xmm3
+	vpshufd		$0x93,%xmm2,%xmm2
+	decb		%cl
+	jne		.Lblake2s_compress_avx512_roundloop
+	vpxor		%xmm10,%xmm0,%xmm0
+	vpxor		%xmm11,%xmm1,%xmm1
+	vpxor		%xmm2,%xmm0,%xmm0
+	vpxor		%xmm3,%xmm1,%xmm1
+	decq		%rdx
+	jne		.Lblake2s_compress_avx512_mainloop
+	vmovdqu		%xmm0,(%rdi)
+	vmovdqu		%xmm1,0x10(%rdi)
+	vmovdqu		%xmm4,0x20(%rdi)
+	vzeroupper
+	retq
+ENDPROC(blake2s_compress_avx512)
+#endif /* CONFIG_AS_AVX512 */
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
new file mode 100644
index 000000000000..4a37ba7cdbe5
--- /dev/null
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <crypto/internal/blake2s.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/hash.h>
+
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/api.h>
+#include <asm/processor.h>
+#include <asm/simd.h>
+
+asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state,
+				       const u8 *block, const size_t nblocks,
+				       const u32 inc);
+asmlinkage void blake2s_compress_avx512(struct blake2s_state *state,
+					const u8 *block, const size_t nblocks,
+					const u32 inc);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512);
+
+void blake2s_compress_arch(struct blake2s_state *state,
+			   const u8 *block, size_t nblocks,
+			   const u32 inc)
+{
+	/* SIMD disables preemption, so relax after processing each page. */
+	BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8);
+
+	if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) {
+		blake2s_compress_generic(state, block, nblocks, inc);
+		return;
+	}
+
+	for (;;) {
+		const size_t blocks = min_t(size_t, nblocks,
+					    PAGE_SIZE / BLAKE2S_BLOCK_SIZE);
+
+		kernel_fpu_begin();
+		if (IS_ENABLED(CONFIG_AS_AVX512) &&
+		    static_branch_likely(&blake2s_use_avx512))
+			blake2s_compress_avx512(state, block, blocks, inc);
+		else
+			blake2s_compress_ssse3(state, block, blocks, inc);
+		kernel_fpu_end();
+
+		nblocks -= blocks;
+		if (!nblocks)
+			break;
+		block += blocks * BLAKE2S_BLOCK_SIZE;
+	}
+}
+EXPORT_SYMBOL(blake2s_compress_arch);
+
+static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+
+	if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(tctx->key, key, keylen);
+	tctx->keylen = keylen;
+
+	return 0;
+}
+
+static int crypto_blake2s_init(struct shash_desc *desc)
+{
+	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct blake2s_state *state = shash_desc_ctx(desc);
+	const int outlen = crypto_shash_digestsize(desc->tfm);
+
+	if (tctx->keylen)
+		blake2s_init_key(state, outlen, tctx->key, tctx->keylen);
+	else
+		blake2s_init(state, outlen);
+
+	return 0;
+}
+
+static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in,
+				 unsigned int inlen)
+{
+	struct blake2s_state *state = shash_desc_ctx(desc);
+	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
+
+	if (unlikely(!inlen))
+		return 0;
+	if (inlen > fill) {
+		memcpy(state->buf + state->buflen, in, fill);
+		blake2s_compress_arch(state, state->buf, 1, BLAKE2S_BLOCK_SIZE);
+		state->buflen = 0;
+		in += fill;
+		inlen -= fill;
+	}
+	if (inlen > BLAKE2S_BLOCK_SIZE) {
+		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
+		/* Hash one less (full) block than strictly possible */
+		blake2s_compress_arch(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE);
+		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+	}
+	memcpy(state->buf + state->buflen, in, inlen);
+	state->buflen += inlen;
+
+	return 0;
+}
+
+static int crypto_blake2s_final(struct shash_desc *desc, u8 *out)
+{
+	struct blake2s_state *state = shash_desc_ctx(desc);
+
+	blake2s_set_lastblock(state);
+	memset(state->buf + state->buflen, 0,
+	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
+	blake2s_compress_arch(state, state->buf, 1, state->buflen);
+	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
+	memcpy(out, state->h, state->outlen);
+	memzero_explicit(state, sizeof(*state));
+
+	return 0;
+}
+
+static struct shash_alg blake2s_algs[] = {{
+	.base.cra_name		= "blake2s-128",
+	.base.cra_driver_name	= "blake2s-128-x86",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_128_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}, {
+	.base.cra_name		= "blake2s-160",
+	.base.cra_driver_name	= "blake2s-160-x86",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_160_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}, {
+	.base.cra_name		= "blake2s-224",
+	.base.cra_driver_name	= "blake2s-224-x86",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_224_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}, {
+	.base.cra_name		= "blake2s-256",
+	.base.cra_driver_name	= "blake2s-256-x86",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_256_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}};
+
+static int __init blake2s_mod_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_SSSE3))
+		return 0;
+
+	static_branch_enable(&blake2s_use_ssse3);
+
+	if (IS_ENABLED(CONFIG_AS_AVX512) &&
+	    boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_AVX2) &&
+	    boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512VL) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM |
+			      XFEATURE_MASK_AVX512, NULL))
+		static_branch_enable(&blake2s_use_avx512);
+
+	return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
+}
+
+static void __exit blake2s_mod_exit(void)
+{
+	if (boot_cpu_has(X86_FEATURE_SSSE3))
+		crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
+}
+
+module_init(blake2s_mod_init);
+module_exit(blake2s_mod_exit);
+
+MODULE_ALIAS_CRYPTO("blake2s-128");
+MODULE_ALIAS_CRYPTO("blake2s-128-x86");
+MODULE_ALIAS_CRYPTO("blake2s-160");
+MODULE_ALIAS_CRYPTO("blake2s-160-x86");
+MODULE_ALIAS_CRYPTO("blake2s-224");
+MODULE_ALIAS_CRYPTO("blake2s-224-x86");
+MODULE_ALIAS_CRYPTO("blake2s-256");
+MODULE_ALIAS_CRYPTO("blake2s-256-x86");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 388f95a4ec24..a94e30b6f941 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -7,7 +7,7 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
@@ -21,24 +21,24 @@ asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
 asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
 					unsigned int len, int nrounds);
 asmlinkage void hchacha_block_ssse3(const u32 *state, u32 *out, int nrounds);
-#ifdef CONFIG_AS_AVX2
+
 asmlinkage void chacha_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
 asmlinkage void chacha_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
 asmlinkage void chacha_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
-static bool chacha_use_avx2;
-#ifdef CONFIG_AS_AVX512
+
 asmlinkage void chacha_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
 					   unsigned int len, int nrounds);
 asmlinkage void chacha_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
 					   unsigned int len, int nrounds);
 asmlinkage void chacha_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
 					   unsigned int len, int nrounds);
-static bool chacha_use_avx512vl;
-#endif
-#endif
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl);
 
 static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
 {
@@ -49,9 +49,8 @@ static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
 static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 			  unsigned int bytes, int nrounds)
 {
-#ifdef CONFIG_AS_AVX2
-#ifdef CONFIG_AS_AVX512
-	if (chacha_use_avx512vl) {
+	if (IS_ENABLED(CONFIG_AS_AVX512) &&
+	    static_branch_likely(&chacha_use_avx512vl)) {
 		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
 			chacha_8block_xor_avx512vl(state, dst, src, bytes,
 						   nrounds);
@@ -79,8 +78,9 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 			return;
 		}
 	}
-#endif
-	if (chacha_use_avx2) {
+
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    static_branch_likely(&chacha_use_avx2)) {
 		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
 			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
 			bytes -= CHACHA_BLOCK_SIZE * 8;
@@ -104,7 +104,7 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 			return;
 		}
 	}
-#endif
+
 	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
 		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
 		bytes -= CHACHA_BLOCK_SIZE * 4;
@@ -123,37 +123,76 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 	}
 }
 
-static int chacha_simd_stream_xor(struct skcipher_walk *walk,
+void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+{
+	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) {
+		hchacha_block_generic(state, stream, nrounds);
+	} else {
+		kernel_fpu_begin();
+		hchacha_block_ssse3(state, stream, nrounds);
+		kernel_fpu_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+	chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+		       int nrounds)
+{
+	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() ||
+	    bytes <= CHACHA_BLOCK_SIZE)
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	kernel_fpu_begin();
+	chacha_dosimd(state, dst, src, bytes, nrounds);
+	kernel_fpu_end();
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+static int chacha_simd_stream_xor(struct skcipher_request *req,
 				  const struct chacha_ctx *ctx, const u8 *iv)
 {
 	u32 *state, state_buf[16 + 2] __aligned(8);
-	int next_yield = 4096; /* bytes until next FPU yield */
-	int err = 0;
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
 
 	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
 	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
 
-	crypto_chacha_init(state, ctx, iv);
-
-	while (walk->nbytes > 0) {
-		unsigned int nbytes = walk->nbytes;
+	chacha_init_generic(state, ctx->key, iv);
 
-		if (nbytes < walk->total) {
-			nbytes = round_down(nbytes, walk->stride);
-			next_yield -= nbytes;
-		}
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
 
-		chacha_dosimd(state, walk->dst.virt.addr, walk->src.virt.addr,
-			      nbytes, ctx->nrounds);
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
 
-		if (next_yield <= 0) {
-			/* temporarily allow preemption */
-			kernel_fpu_end();
+		if (!static_branch_likely(&chacha_use_simd) ||
+		    !crypto_simd_usable()) {
+			chacha_crypt_generic(state, walk.dst.virt.addr,
+					     walk.src.virt.addr, nbytes,
+					     ctx->nrounds);
+		} else {
 			kernel_fpu_begin();
-			next_yield = 4096;
+			chacha_dosimd(state, walk.dst.virt.addr,
+				      walk.src.virt.addr, nbytes,
+				      ctx->nrounds);
+			kernel_fpu_end();
 		}
-
-		err = skcipher_walk_done(walk, walk->nbytes - nbytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
@@ -163,55 +202,34 @@ static int chacha_simd(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	int err;
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_chacha_crypt(req);
 
-	err = skcipher_walk_virt(&walk, req, true);
-	if (err)
-		return err;
-
-	kernel_fpu_begin();
-	err = chacha_simd_stream_xor(&walk, ctx, req->iv);
-	kernel_fpu_end();
-	return err;
+	return chacha_simd_stream_xor(req, ctx, req->iv);
 }
 
 static int xchacha_simd(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	struct chacha_ctx subctx;
 	u32 *state, state_buf[16 + 2] __aligned(8);
+	struct chacha_ctx subctx;
 	u8 real_iv[16];
-	int err;
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_xchacha_crypt(req);
-
-	err = skcipher_walk_virt(&walk, req, true);
-	if (err)
-		return err;
 
 	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
 	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
-	crypto_chacha_init(state, ctx, req->iv);
-
-	kernel_fpu_begin();
-
-	hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
+	chacha_init_generic(state, ctx->key, req->iv);
+
+	if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {
+		kernel_fpu_begin();
+		hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
+		kernel_fpu_end();
+	} else {
+		hchacha_block_generic(state, subctx.key, ctx->nrounds);
+	}
 	subctx.nrounds = ctx->nrounds;
 
 	memcpy(&real_iv[0], req->iv + 24, 8);
 	memcpy(&real_iv[8], req->iv + 16, 8);
-	err = chacha_simd_stream_xor(&walk, &subctx, real_iv);
-
-	kernel_fpu_end();
-
-	return err;
+	return chacha_simd_stream_xor(req, &subctx, real_iv);
 }
 
 static struct skcipher_alg algs[] = {
@@ -227,7 +245,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= CHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= chacha_simd,
 		.decrypt		= chacha_simd,
 	}, {
@@ -242,7 +260,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= xchacha_simd,
 		.decrypt		= xchacha_simd,
 	}, {
@@ -257,7 +275,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha12_setkey,
+		.setkey			= chacha12_setkey,
 		.encrypt		= xchacha_simd,
 		.decrypt		= xchacha_simd,
 	},
@@ -266,24 +284,28 @@ static struct skcipher_alg algs[] = {
 static int __init chacha_simd_mod_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_SSSE3))
-		return -ENODEV;
-
-#ifdef CONFIG_AS_AVX2
-	chacha_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) &&
-			  boot_cpu_has(X86_FEATURE_AVX2) &&
-			  cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
-#ifdef CONFIG_AS_AVX512
-	chacha_use_avx512vl = chacha_use_avx2 &&
-			      boot_cpu_has(X86_FEATURE_AVX512VL) &&
-			      boot_cpu_has(X86_FEATURE_AVX512BW); /* kmovq */
-#endif
-#endif
+		return 0;
+
+	static_branch_enable(&chacha_use_simd);
+
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_AVX2) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
+		static_branch_enable(&chacha_use_avx2);
+
+		if (IS_ENABLED(CONFIG_AS_AVX512) &&
+		    boot_cpu_has(X86_FEATURE_AVX512VL) &&
+		    boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
+			static_branch_enable(&chacha_use_avx512vl);
+	}
 	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 static void __exit chacha_simd_mod_fini(void)
 {
-	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+	if (boot_cpu_has(X86_FEATURE_SSSE3))
+		crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 module_init(chacha_simd_mod_init);
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
new file mode 100644
index 000000000000..a52a3fb15727
--- /dev/null
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -0,0 +1,2475 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (c) 2017 Armando Faz <armfazh@ic.unicamp.br>. All Rights Reserved.
+ * Copyright (C) 2018-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2018 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved.
+ */
+
+#include <crypto/curve25519.h>
+#include <crypto/internal/kpp.h>
+
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_adx);
+
+enum { NUM_WORDS_ELTFP25519 = 4 };
+typedef __aligned(32) u64 eltfp25519_1w[NUM_WORDS_ELTFP25519];
+typedef __aligned(32) u64 eltfp25519_1w_buffer[2 * NUM_WORDS_ELTFP25519];
+
+#define mul_eltfp25519_1w_adx(c, a, b) do { \
+	mul_256x256_integer_adx(m.buffer, a, b); \
+	red_eltfp25519_1w_adx(c, m.buffer); \
+} while (0)
+
+#define mul_eltfp25519_1w_bmi2(c, a, b) do { \
+	mul_256x256_integer_bmi2(m.buffer, a, b); \
+	red_eltfp25519_1w_bmi2(c, m.buffer); \
+} while (0)
+
+#define sqr_eltfp25519_1w_adx(a) do { \
+	sqr_256x256_integer_adx(m.buffer, a); \
+	red_eltfp25519_1w_adx(a, m.buffer); \
+} while (0)
+
+#define sqr_eltfp25519_1w_bmi2(a) do { \
+	sqr_256x256_integer_bmi2(m.buffer, a); \
+	red_eltfp25519_1w_bmi2(a, m.buffer); \
+} while (0)
+
+#define mul_eltfp25519_2w_adx(c, a, b) do { \
+	mul2_256x256_integer_adx(m.buffer, a, b); \
+	red_eltfp25519_2w_adx(c, m.buffer); \
+} while (0)
+
+#define mul_eltfp25519_2w_bmi2(c, a, b) do { \
+	mul2_256x256_integer_bmi2(m.buffer, a, b); \
+	red_eltfp25519_2w_bmi2(c, m.buffer); \
+} while (0)
+
+#define sqr_eltfp25519_2w_adx(a) do { \
+	sqr2_256x256_integer_adx(m.buffer, a); \
+	red_eltfp25519_2w_adx(a, m.buffer); \
+} while (0)
+
+#define sqr_eltfp25519_2w_bmi2(a) do { \
+	sqr2_256x256_integer_bmi2(m.buffer, a); \
+	red_eltfp25519_2w_bmi2(a, m.buffer); \
+} while (0)
+
+#define sqrn_eltfp25519_1w_adx(a, times) do { \
+	int ____counter = (times); \
+	while (____counter-- > 0) \
+		sqr_eltfp25519_1w_adx(a); \
+} while (0)
+
+#define sqrn_eltfp25519_1w_bmi2(a, times) do { \
+	int ____counter = (times); \
+	while (____counter-- > 0) \
+		sqr_eltfp25519_1w_bmi2(a); \
+} while (0)
+
+#define copy_eltfp25519_1w(C, A) do { \
+	(C)[0] = (A)[0]; \
+	(C)[1] = (A)[1]; \
+	(C)[2] = (A)[2]; \
+	(C)[3] = (A)[3]; \
+} while (0)
+
+#define setzero_eltfp25519_1w(C) do { \
+	(C)[0] = 0; \
+	(C)[1] = 0; \
+	(C)[2] = 0; \
+	(C)[3] = 0; \
+} while (0)
+
+__aligned(32) static const u64 table_ladder_8k[252 * NUM_WORDS_ELTFP25519] = {
+	/*   1 */ 0xfffffffffffffff3UL, 0xffffffffffffffffUL,
+		  0xffffffffffffffffUL, 0x5fffffffffffffffUL,
+	/*   2 */ 0x6b8220f416aafe96UL, 0x82ebeb2b4f566a34UL,
+		  0xd5a9a5b075a5950fUL, 0x5142b2cf4b2488f4UL,
+	/*   3 */ 0x6aaebc750069680cUL, 0x89cf7820a0f99c41UL,
+		  0x2a58d9183b56d0f4UL, 0x4b5aca80e36011a4UL,
+	/*   4 */ 0x329132348c29745dUL, 0xf4a2e616e1642fd7UL,
+		  0x1e45bb03ff67bc34UL, 0x306912d0f42a9b4aUL,
+	/*   5 */ 0xff886507e6af7154UL, 0x04f50e13dfeec82fUL,
+		  0xaa512fe82abab5ceUL, 0x174e251a68d5f222UL,
+	/*   6 */ 0xcf96700d82028898UL, 0x1743e3370a2c02c5UL,
+		  0x379eec98b4e86eaaUL, 0x0c59888a51e0482eUL,
+	/*   7 */ 0xfbcbf1d699b5d189UL, 0xacaef0d58e9fdc84UL,
+		  0xc1c20d06231f7614UL, 0x2938218da274f972UL,
+	/*   8 */ 0xf6af49beff1d7f18UL, 0xcc541c22387ac9c2UL,
+		  0x96fcc9ef4015c56bUL, 0x69c1627c690913a9UL,
+	/*   9 */ 0x7a86fd2f4733db0eUL, 0xfdb8c4f29e087de9UL,
+		  0x095e4b1a8ea2a229UL, 0x1ad7a7c829b37a79UL,
+	/*  10 */ 0x342d89cad17ea0c0UL, 0x67bedda6cced2051UL,
+		  0x19ca31bf2bb42f74UL, 0x3df7b4c84980acbbUL,
+	/*  11 */ 0xa8c6444dc80ad883UL, 0xb91e440366e3ab85UL,
+		  0xc215cda00164f6d8UL, 0x3d867c6ef247e668UL,
+	/*  12 */ 0xc7dd582bcc3e658cUL, 0xfd2c4748ee0e5528UL,
+		  0xa0fd9b95cc9f4f71UL, 0x7529d871b0675ddfUL,
+	/*  13 */ 0xb8f568b42d3cbd78UL, 0x1233011b91f3da82UL,
+		  0x2dce6ccd4a7c3b62UL, 0x75e7fc8e9e498603UL,
+	/*  14 */ 0x2f4f13f1fcd0b6ecUL, 0xf1a8ca1f29ff7a45UL,
+		  0xc249c1a72981e29bUL, 0x6ebe0dbb8c83b56aUL,
+	/*  15 */ 0x7114fa8d170bb222UL, 0x65a2dcd5bf93935fUL,
+		  0xbdc41f68b59c979aUL, 0x2f0eef79a2ce9289UL,
+	/*  16 */ 0x42ecbf0c083c37ceUL, 0x2930bc09ec496322UL,
+		  0xf294b0c19cfeac0dUL, 0x3780aa4bedfabb80UL,
+	/*  17 */ 0x56c17d3e7cead929UL, 0xe7cb4beb2e5722c5UL,
+		  0x0ce931732dbfe15aUL, 0x41b883c7621052f8UL,
+	/*  18 */ 0xdbf75ca0c3d25350UL, 0x2936be086eb1e351UL,
+		  0xc936e03cb4a9b212UL, 0x1d45bf82322225aaUL,
+	/*  19 */ 0xe81ab1036a024cc5UL, 0xe212201c304c9a72UL,
+		  0xc5d73fba6832b1fcUL, 0x20ffdb5a4d839581UL,
+	/*  20 */ 0xa283d367be5d0fadUL, 0x6c2b25ca8b164475UL,
+		  0x9d4935467caaf22eUL, 0x5166408eee85ff49UL,
+	/*  21 */ 0x3c67baa2fab4e361UL, 0xb3e433c67ef35cefUL,
+		  0x5259729241159b1cUL, 0x6a621892d5b0ab33UL,
+	/*  22 */ 0x20b74a387555cdcbUL, 0x532aa10e1208923fUL,
+		  0xeaa17b7762281dd1UL, 0x61ab3443f05c44bfUL,
+	/*  23 */ 0x257a6c422324def8UL, 0x131c6c1017e3cf7fUL,
+		  0x23758739f630a257UL, 0x295a407a01a78580UL,
+	/*  24 */ 0xf8c443246d5da8d9UL, 0x19d775450c52fa5dUL,
+		  0x2afcfc92731bf83dUL, 0x7d10c8e81b2b4700UL,
+	/*  25 */ 0xc8e0271f70baa20bUL, 0x993748867ca63957UL,
+		  0x5412efb3cb7ed4bbUL, 0x3196d36173e62975UL,
+	/*  26 */ 0xde5bcad141c7dffcUL, 0x47cc8cd2b395c848UL,
+		  0xa34cd942e11af3cbUL, 0x0256dbf2d04ecec2UL,
+	/*  27 */ 0x875ab7e94b0e667fUL, 0xcad4dd83c0850d10UL,
+		  0x47f12e8f4e72c79fUL, 0x5f1a87bb8c85b19bUL,
+	/*  28 */ 0x7ae9d0b6437f51b8UL, 0x12c7ce5518879065UL,
+		  0x2ade09fe5cf77aeeUL, 0x23a05a2f7d2c5627UL,
+	/*  29 */ 0x5908e128f17c169aUL, 0xf77498dd8ad0852dUL,
+		  0x74b4c4ceab102f64UL, 0x183abadd10139845UL,
+	/*  30 */ 0xb165ba8daa92aaacUL, 0xd5c5ef9599386705UL,
+		  0xbe2f8f0cf8fc40d1UL, 0x2701e635ee204514UL,
+	/*  31 */ 0x629fa80020156514UL, 0xf223868764a8c1ceUL,
+		  0x5b894fff0b3f060eUL, 0x60d9944cf708a3faUL,
+	/*  32 */ 0xaeea001a1c7a201fUL, 0xebf16a633ee2ce63UL,
+		  0x6f7709594c7a07e1UL, 0x79b958150d0208cbUL,
+	/*  33 */ 0x24b55e5301d410e7UL, 0xe3a34edff3fdc84dUL,
+		  0xd88768e4904032d8UL, 0x131384427b3aaeecUL,
+	/*  34 */ 0x8405e51286234f14UL, 0x14dc4739adb4c529UL,
+		  0xb8a2b5b250634ffdUL, 0x2fe2a94ad8a7ff93UL,
+	/*  35 */ 0xec5c57efe843faddUL, 0x2843ce40f0bb9918UL,
+		  0xa4b561d6cf3d6305UL, 0x743629bde8fb777eUL,
+	/*  36 */ 0x343edd46bbaf738fUL, 0xed981828b101a651UL,
+		  0xa401760b882c797aUL, 0x1fc223e28dc88730UL,
+	/*  37 */ 0x48604e91fc0fba0eUL, 0xb637f78f052c6fa4UL,
+		  0x91ccac3d09e9239cUL, 0x23f7eed4437a687cUL,
+	/*  38 */ 0x5173b1118d9bd800UL, 0x29d641b63189d4a7UL,
+		  0xfdbf177988bbc586UL, 0x2959894fcad81df5UL,
+	/*  39 */ 0xaebc8ef3b4bbc899UL, 0x4148995ab26992b9UL,
+		  0x24e20b0134f92cfbUL, 0x40d158894a05dee8UL,
+	/*  40 */ 0x46b00b1185af76f6UL, 0x26bac77873187a79UL,
+		  0x3dc0bf95ab8fff5fUL, 0x2a608bd8945524d7UL,
+	/*  41 */ 0x26449588bd446302UL, 0x7c4bc21c0388439cUL,
+		  0x8e98a4f383bd11b2UL, 0x26218d7bc9d876b9UL,
+	/*  42 */ 0xe3081542997c178aUL, 0x3c2d29a86fb6606fUL,
+		  0x5c217736fa279374UL, 0x7dde05734afeb1faUL,
+	/*  43 */ 0x3bf10e3906d42babUL, 0xe4f7803e1980649cUL,
+		  0xe6053bf89595bf7aUL, 0x394faf38da245530UL,
+	/*  44 */ 0x7a8efb58896928f4UL, 0xfbc778e9cc6a113cUL,
+		  0x72670ce330af596fUL, 0x48f222a81d3d6cf7UL,
+	/*  45 */ 0xf01fce410d72caa7UL, 0x5a20ecc7213b5595UL,
+		  0x7bc21165c1fa1483UL, 0x07f89ae31da8a741UL,
+	/*  46 */ 0x05d2c2b4c6830ff9UL, 0xd43e330fc6316293UL,
+		  0xa5a5590a96d3a904UL, 0x705edb91a65333b6UL,
+	/*  47 */ 0x048ee15e0bb9a5f7UL, 0x3240cfca9e0aaf5dUL,
+		  0x8f4b71ceedc4a40bUL, 0x621c0da3de544a6dUL,
+	/*  48 */ 0x92872836a08c4091UL, 0xce8375b010c91445UL,
+		  0x8a72eb524f276394UL, 0x2667fcfa7ec83635UL,
+	/*  49 */ 0x7f4c173345e8752aUL, 0x061b47feee7079a5UL,
+		  0x25dd9afa9f86ff34UL, 0x3780cef5425dc89cUL,
+	/*  50 */ 0x1a46035a513bb4e9UL, 0x3e1ef379ac575adaUL,
+		  0xc78c5f1c5fa24b50UL, 0x321a967634fd9f22UL,
+	/*  51 */ 0x946707b8826e27faUL, 0x3dca84d64c506fd0UL,
+		  0xc189218075e91436UL, 0x6d9284169b3b8484UL,
+	/*  52 */ 0x3a67e840383f2ddfUL, 0x33eec9a30c4f9b75UL,
+		  0x3ec7c86fa783ef47UL, 0x26ec449fbac9fbc4UL,
+	/*  53 */ 0x5c0f38cba09b9e7dUL, 0x81168cc762a3478cUL,
+		  0x3e23b0d306fc121cUL, 0x5a238aa0a5efdcddUL,
+	/*  54 */ 0x1ba26121c4ea43ffUL, 0x36f8c77f7c8832b5UL,
+		  0x88fbea0b0adcf99aUL, 0x5ca9938ec25bebf9UL,
+	/*  55 */ 0xd5436a5e51fccda0UL, 0x1dbc4797c2cd893bUL,
+		  0x19346a65d3224a08UL, 0x0f5034e49b9af466UL,
+	/*  56 */ 0xf23c3967a1e0b96eUL, 0xe58b08fa867a4d88UL,
+		  0xfb2fabc6a7341679UL, 0x2a75381eb6026946UL,
+	/*  57 */ 0xc80a3be4c19420acUL, 0x66b1f6c681f2b6dcUL,
+		  0x7cf7036761e93388UL, 0x25abbbd8a660a4c4UL,
+	/*  58 */ 0x91ea12ba14fd5198UL, 0x684950fc4a3cffa9UL,
+		  0xf826842130f5ad28UL, 0x3ea988f75301a441UL,
+	/*  59 */ 0xc978109a695f8c6fUL, 0x1746eb4a0530c3f3UL,
+		  0x444d6d77b4459995UL, 0x75952b8c054e5cc7UL,
+	/*  60 */ 0xa3703f7915f4d6aaUL, 0x66c346202f2647d8UL,
+		  0xd01469df811d644bUL, 0x77fea47d81a5d71fUL,
+	/*  61 */ 0xc5e9529ef57ca381UL, 0x6eeeb4b9ce2f881aUL,
+		  0xb6e91a28e8009bd6UL, 0x4b80be3e9afc3fecUL,
+	/*  62 */ 0x7e3773c526aed2c5UL, 0x1b4afcb453c9a49dUL,
+		  0xa920bdd7baffb24dUL, 0x7c54699f122d400eUL,
+	/*  63 */ 0xef46c8e14fa94bc8UL, 0xe0b074ce2952ed5eUL,
+		  0xbea450e1dbd885d5UL, 0x61b68649320f712cUL,
+	/*  64 */ 0x8a485f7309ccbdd1UL, 0xbd06320d7d4d1a2dUL,
+		  0x25232973322dbef4UL, 0x445dc4758c17f770UL,
+	/*  65 */ 0xdb0434177cc8933cUL, 0xed6fe82175ea059fUL,
+		  0x1efebefdc053db34UL, 0x4adbe867c65daf99UL,
+	/*  66 */ 0x3acd71a2a90609dfUL, 0xe5e991856dd04050UL,
+		  0x1ec69b688157c23cUL, 0x697427f6885cfe4dUL,
+	/*  67 */ 0xd7be7b9b65e1a851UL, 0xa03d28d522c536ddUL,
+		  0x28399d658fd2b645UL, 0x49e5b7e17c2641e1UL,
+	/*  68 */ 0x6f8c3a98700457a4UL, 0x5078f0a25ebb6778UL,
+		  0xd13c3ccbc382960fUL, 0x2e003258a7df84b1UL,
+	/*  69 */ 0x8ad1f39be6296a1cUL, 0xc1eeaa652a5fbfb2UL,
+		  0x33ee0673fd26f3cbUL, 0x59256173a69d2cccUL,
+	/*  70 */ 0x41ea07aa4e18fc41UL, 0xd9fc19527c87a51eUL,
+		  0xbdaacb805831ca6fUL, 0x445b652dc916694fUL,
+	/*  71 */ 0xce92a3a7f2172315UL, 0x1edc282de11b9964UL,
+		  0xa1823aafe04c314aUL, 0x790a2d94437cf586UL,
+	/*  72 */ 0x71c447fb93f6e009UL, 0x8922a56722845276UL,
+		  0xbf70903b204f5169UL, 0x2f7a89891ba319feUL,
+	/*  73 */ 0x02a08eb577e2140cUL, 0xed9a4ed4427bdcf4UL,
+		  0x5253ec44e4323cd1UL, 0x3e88363c14e9355bUL,
+	/*  74 */ 0xaa66c14277110b8cUL, 0x1ae0391610a23390UL,
+		  0x2030bd12c93fc2a2UL, 0x3ee141579555c7abUL,
+	/*  75 */ 0x9214de3a6d6e7d41UL, 0x3ccdd88607f17efeUL,
+		  0x674f1288f8e11217UL, 0x5682250f329f93d0UL,
+	/*  76 */ 0x6cf00b136d2e396eUL, 0x6e4cf86f1014debfUL,
+		  0x5930b1b5bfcc4e83UL, 0x047069b48aba16b6UL,
+	/*  77 */ 0x0d4ce4ab69b20793UL, 0xb24db91a97d0fb9eUL,
+		  0xcdfa50f54e00d01dUL, 0x221b1085368bddb5UL,
+	/*  78 */ 0xe7e59468b1e3d8d2UL, 0x53c56563bd122f93UL,
+		  0xeee8a903e0663f09UL, 0x61efa662cbbe3d42UL,
+	/*  79 */ 0x2cf8ddddde6eab2aUL, 0x9bf80ad51435f231UL,
+		  0x5deadacec9f04973UL, 0x29275b5d41d29b27UL,
+	/*  80 */ 0xcfde0f0895ebf14fUL, 0xb9aab96b054905a7UL,
+		  0xcae80dd9a1c420fdUL, 0x0a63bf2f1673bbc7UL,
+	/*  81 */ 0x092f6e11958fbc8cUL, 0x672a81e804822fadUL,
+		  0xcac8351560d52517UL, 0x6f3f7722c8f192f8UL,
+	/*  82 */ 0xf8ba90ccc2e894b7UL, 0x2c7557a438ff9f0dUL,
+		  0x894d1d855ae52359UL, 0x68e122157b743d69UL,
+	/*  83 */ 0xd87e5570cfb919f3UL, 0x3f2cdecd95798db9UL,
+		  0x2121154710c0a2ceUL, 0x3c66a115246dc5b2UL,
+	/*  84 */ 0xcbedc562294ecb72UL, 0xba7143c36a280b16UL,
+		  0x9610c2efd4078b67UL, 0x6144735d946a4b1eUL,
+	/*  85 */ 0x536f111ed75b3350UL, 0x0211db8c2041d81bUL,
+		  0xf93cb1000e10413cUL, 0x149dfd3c039e8876UL,
+	/*  86 */ 0xd479dde46b63155bUL, 0xb66e15e93c837976UL,
+		  0xdafde43b1f13e038UL, 0x5fafda1a2e4b0b35UL,
+	/*  87 */ 0x3600bbdf17197581UL, 0x3972050bbe3cd2c2UL,
+		  0x5938906dbdd5be86UL, 0x34fce5e43f9b860fUL,
+	/*  88 */ 0x75a8a4cd42d14d02UL, 0x828dabc53441df65UL,
+		  0x33dcabedd2e131d3UL, 0x3ebad76fb814d25fUL,
+	/*  89 */ 0xd4906f566f70e10fUL, 0x5d12f7aa51690f5aUL,
+		  0x45adb16e76cefcf2UL, 0x01f768aead232999UL,
+	/*  90 */ 0x2b6cc77b6248febdUL, 0x3cd30628ec3aaffdUL,
+		  0xce1c0b80d4ef486aUL, 0x4c3bff2ea6f66c23UL,
+	/*  91 */ 0x3f2ec4094aeaeb5fUL, 0x61b19b286e372ca7UL,
+		  0x5eefa966de2a701dUL, 0x23b20565de55e3efUL,
+	/*  92 */ 0xe301ca5279d58557UL, 0x07b2d4ce27c2874fUL,
+		  0xa532cd8a9dcf1d67UL, 0x2a52fee23f2bff56UL,
+	/*  93 */ 0x8624efb37cd8663dUL, 0xbbc7ac20ffbd7594UL,
+		  0x57b85e9c82d37445UL, 0x7b3052cb86a6ec66UL,
+	/*  94 */ 0x3482f0ad2525e91eUL, 0x2cb68043d28edca0UL,
+		  0xaf4f6d052e1b003aUL, 0x185f8c2529781b0aUL,
+	/*  95 */ 0xaa41de5bd80ce0d6UL, 0x9407b2416853e9d6UL,
+		  0x563ec36e357f4c3aUL, 0x4cc4b8dd0e297bceUL,
+	/*  96 */ 0xa2fc1a52ffb8730eUL, 0x1811f16e67058e37UL,
+		  0x10f9a366cddf4ee1UL, 0x72f4a0c4a0b9f099UL,
+	/*  97 */ 0x8c16c06f663f4ea7UL, 0x693b3af74e970fbaUL,
+		  0x2102e7f1d69ec345UL, 0x0ba53cbc968a8089UL,
+	/*  98 */ 0xca3d9dc7fea15537UL, 0x4c6824bb51536493UL,
+		  0xb9886314844006b1UL, 0x40d2a72ab454cc60UL,
+	/*  99 */ 0x5936a1b712570975UL, 0x91b9d648debda657UL,
+		  0x3344094bb64330eaUL, 0x006ba10d12ee51d0UL,
+	/* 100 */ 0x19228468f5de5d58UL, 0x0eb12f4c38cc05b0UL,
+		  0xa1039f9dd5601990UL, 0x4502d4ce4fff0e0bUL,
+	/* 101 */ 0xeb2054106837c189UL, 0xd0f6544c6dd3b93cUL,
+		  0x40727064c416d74fUL, 0x6e15c6114b502ef0UL,
+	/* 102 */ 0x4df2a398cfb1a76bUL, 0x11256c7419f2f6b1UL,
+		  0x4a497962066e6043UL, 0x705b3aab41355b44UL,
+	/* 103 */ 0x365ef536d797b1d8UL, 0x00076bd622ddf0dbUL,
+		  0x3bbf33b0e0575a88UL, 0x3777aa05c8e4ca4dUL,
+	/* 104 */ 0x392745c85578db5fUL, 0x6fda4149dbae5ae2UL,
+		  0xb1f0b00b8adc9867UL, 0x09963437d36f1da3UL,
+	/* 105 */ 0x7e824e90a5dc3853UL, 0xccb5f6641f135cbdUL,
+		  0x6736d86c87ce8fccUL, 0x625f3ce26604249fUL,
+	/* 106 */ 0xaf8ac8059502f63fUL, 0x0c05e70a2e351469UL,
+		  0x35292e9c764b6305UL, 0x1a394360c7e23ac3UL,
+	/* 107 */ 0xd5c6d53251183264UL, 0x62065abd43c2b74fUL,
+		  0xb5fbf5d03b973f9bUL, 0x13a3da3661206e5eUL,
+	/* 108 */ 0xc6bd5837725d94e5UL, 0x18e30912205016c5UL,
+		  0x2088ce1570033c68UL, 0x7fba1f495c837987UL,
+	/* 109 */ 0x5a8c7423f2f9079dUL, 0x1735157b34023fc5UL,
+		  0xe4f9b49ad2fab351UL, 0x6691ff72c878e33cUL,
+	/* 110 */ 0x122c2adedc5eff3eUL, 0xf8dd4bf1d8956cf4UL,
+		  0xeb86205d9e9e5bdaUL, 0x049b92b9d975c743UL,
+	/* 111 */ 0xa5379730b0f6c05aUL, 0x72a0ffacc6f3a553UL,
+		  0xb0032c34b20dcd6dUL, 0x470e9dbc88d5164aUL,
+	/* 112 */ 0xb19cf10ca237c047UL, 0xb65466711f6c81a2UL,
+		  0xb3321bd16dd80b43UL, 0x48c14f600c5fbe8eUL,
+	/* 113 */ 0x66451c264aa6c803UL, 0xb66e3904a4fa7da6UL,
+		  0xd45f19b0b3128395UL, 0x31602627c3c9bc10UL,
+	/* 114 */ 0x3120dc4832e4e10dUL, 0xeb20c46756c717f7UL,
+		  0x00f52e3f67280294UL, 0x566d4fc14730c509UL,
+	/* 115 */ 0x7e3a5d40fd837206UL, 0xc1e926dc7159547aUL,
+		  0x216730fba68d6095UL, 0x22e8c3843f69cea7UL,
+	/* 116 */ 0x33d074e8930e4b2bUL, 0xb6e4350e84d15816UL,
+		  0x5534c26ad6ba2365UL, 0x7773c12f89f1f3f3UL,
+	/* 117 */ 0x8cba404da57962aaUL, 0x5b9897a81999ce56UL,
+		  0x508e862f121692fcUL, 0x3a81907fa093c291UL,
+	/* 118 */ 0x0dded0ff4725a510UL, 0x10d8cc10673fc503UL,
+		  0x5b9d151c9f1f4e89UL, 0x32a5c1d5cb09a44cUL,
+	/* 119 */ 0x1e0aa442b90541fbUL, 0x5f85eb7cc1b485dbUL,
+		  0xbee595ce8a9df2e5UL, 0x25e496c722422236UL,
+	/* 120 */ 0x5edf3c46cd0fe5b9UL, 0x34e75a7ed2a43388UL,
+		  0xe488de11d761e352UL, 0x0e878a01a085545cUL,
+	/* 121 */ 0xba493c77e021bb04UL, 0x2b4d1843c7df899aUL,
+		  0x9ea37a487ae80d67UL, 0x67a9958011e41794UL,
+	/* 122 */ 0x4b58051a6697b065UL, 0x47e33f7d8d6ba6d4UL,
+		  0xbb4da8d483ca46c1UL, 0x68becaa181c2db0dUL,
+	/* 123 */ 0x8d8980e90b989aa5UL, 0xf95eb14a2c93c99bUL,
+		  0x51c6c7c4796e73a2UL, 0x6e228363b5efb569UL,
+	/* 124 */ 0xc6bbc0b02dd624c8UL, 0x777eb47dec8170eeUL,
+		  0x3cde15a004cfafa9UL, 0x1dc6bc087160bf9bUL,
+	/* 125 */ 0x2e07e043eec34002UL, 0x18e9fc677a68dc7fUL,
+		  0xd8da03188bd15b9aUL, 0x48fbc3bb00568253UL,
+	/* 126 */ 0x57547d4cfb654ce1UL, 0xd3565b82a058e2adUL,
+		  0xf63eaf0bbf154478UL, 0x47531ef114dfbb18UL,
+	/* 127 */ 0xe1ec630a4278c587UL, 0x5507d546ca8e83f3UL,
+		  0x85e135c63adc0c2bUL, 0x0aa7efa85682844eUL,
+	/* 128 */ 0x72691ba8b3e1f615UL, 0x32b4e9701fbe3ffaUL,
+		  0x97b6d92e39bb7868UL, 0x2cfe53dea02e39e8UL,
+	/* 129 */ 0x687392cd85cd52b0UL, 0x27ff66c910e29831UL,
+		  0x97134556a9832d06UL, 0x269bb0360a84f8a0UL,
+	/* 130 */ 0x706e55457643f85cUL, 0x3734a48c9b597d1bUL,
+		  0x7aee91e8c6efa472UL, 0x5cd6abc198a9d9e0UL,
+	/* 131 */ 0x0e04de06cb3ce41aUL, 0xd8c6eb893402e138UL,
+		  0x904659bb686e3772UL, 0x7215c371746ba8c8UL,
+	/* 132 */ 0xfd12a97eeae4a2d9UL, 0x9514b7516394f2c5UL,
+		  0x266fd5809208f294UL, 0x5c847085619a26b9UL,
+	/* 133 */ 0x52985410fed694eaUL, 0x3c905b934a2ed254UL,
+		  0x10bb47692d3be467UL, 0x063b3d2d69e5e9e1UL,
+	/* 134 */ 0x472726eedda57debUL, 0xefb6c4ae10f41891UL,
+		  0x2b1641917b307614UL, 0x117c554fc4f45b7cUL,
+	/* 135 */ 0xc07cf3118f9d8812UL, 0x01dbd82050017939UL,
+		  0xd7e803f4171b2827UL, 0x1015e87487d225eaUL,
+	/* 136 */ 0xc58de3fed23acc4dUL, 0x50db91c294a7be2dUL,
+		  0x0b94d43d1c9cf457UL, 0x6b1640fa6e37524aUL,
+	/* 137 */ 0x692f346c5fda0d09UL, 0x200b1c59fa4d3151UL,
+		  0xb8c46f760777a296UL, 0x4b38395f3ffdfbcfUL,
+	/* 138 */ 0x18d25e00be54d671UL, 0x60d50582bec8aba6UL,
+		  0x87ad8f263b78b982UL, 0x50fdf64e9cda0432UL,
+	/* 139 */ 0x90f567aac578dcf0UL, 0xef1e9b0ef2a3133bUL,
+		  0x0eebba9242d9de71UL, 0x15473c9bf03101c7UL,
+	/* 140 */ 0x7c77e8ae56b78095UL, 0xb678e7666e6f078eUL,
+		  0x2da0b9615348ba1fUL, 0x7cf931c1ff733f0bUL,
+	/* 141 */ 0x26b357f50a0a366cUL, 0xe9708cf42b87d732UL,
+		  0xc13aeea5f91cb2c0UL, 0x35d90c991143bb4cUL,
+	/* 142 */ 0x47c1c404a9a0d9dcUL, 0x659e58451972d251UL,
+		  0x3875a8c473b38c31UL, 0x1fbd9ed379561f24UL,
+	/* 143 */ 0x11fabc6fd41ec28dUL, 0x7ef8dfe3cd2a2dcaUL,
+		  0x72e73b5d8c404595UL, 0x6135fa4954b72f27UL,
+	/* 144 */ 0xccfc32a2de24b69cUL, 0x3f55698c1f095d88UL,
+		  0xbe3350ed5ac3f929UL, 0x5e9bf806ca477eebUL,
+	/* 145 */ 0xe9ce8fb63c309f68UL, 0x5376f63565e1f9f4UL,
+		  0xd1afcfb35a6393f1UL, 0x6632a1ede5623506UL,
+	/* 146 */ 0x0b7d6c390c2ded4cUL, 0x56cb3281df04cb1fUL,
+		  0x66305a1249ecc3c7UL, 0x5d588b60a38ca72aUL,
+	/* 147 */ 0xa6ecbf78e8e5f42dUL, 0x86eeb44b3c8a3eecUL,
+		  0xec219c48fbd21604UL, 0x1aaf1af517c36731UL,
+	/* 148 */ 0xc306a2836769bde7UL, 0x208280622b1e2adbUL,
+		  0x8027f51ffbff94a6UL, 0x76cfa1ce1124f26bUL,
+	/* 149 */ 0x18eb00562422abb6UL, 0xf377c4d58f8c29c3UL,
+		  0x4dbbc207f531561aUL, 0x0253b7f082128a27UL,
+	/* 150 */ 0x3d1f091cb62c17e0UL, 0x4860e1abd64628a9UL,
+		  0x52d17436309d4253UL, 0x356f97e13efae576UL,
+	/* 151 */ 0xd351e11aa150535bUL, 0x3e6b45bb1dd878ccUL,
+		  0x0c776128bed92c98UL, 0x1d34ae93032885b8UL,
+	/* 152 */ 0x4ba0488ca85ba4c3UL, 0x985348c33c9ce6ceUL,
+		  0x66124c6f97bda770UL, 0x0f81a0290654124aUL,
+	/* 153 */ 0x9ed09ca6569b86fdUL, 0x811009fd18af9a2dUL,
+		  0xff08d03f93d8c20aUL, 0x52a148199faef26bUL,
+	/* 154 */ 0x3e03f9dc2d8d1b73UL, 0x4205801873961a70UL,
+		  0xc0d987f041a35970UL, 0x07aa1f15a1c0d549UL,
+	/* 155 */ 0xdfd46ce08cd27224UL, 0x6d0a024f934e4239UL,
+		  0x808a7a6399897b59UL, 0x0a4556e9e13d95a2UL,
+	/* 156 */ 0xd21a991fe9c13045UL, 0x9b0e8548fe7751b8UL,
+		  0x5da643cb4bf30035UL, 0x77db28d63940f721UL,
+	/* 157 */ 0xfc5eeb614adc9011UL, 0x5229419ae8c411ebUL,
+		  0x9ec3e7787d1dcf74UL, 0x340d053e216e4cb5UL,
+	/* 158 */ 0xcac7af39b48df2b4UL, 0xc0faec2871a10a94UL,
+		  0x140a69245ca575edUL, 0x0cf1c37134273a4cUL,
+	/* 159 */ 0xc8ee306ac224b8a5UL, 0x57eaee7ccb4930b0UL,
+		  0xa1e806bdaacbe74fUL, 0x7d9a62742eeb657dUL,
+	/* 160 */ 0x9eb6b6ef546c4830UL, 0x885cca1fddb36e2eUL,
+		  0xe6b9f383ef0d7105UL, 0x58654fef9d2e0412UL,
+	/* 161 */ 0xa905c4ffbe0e8e26UL, 0x942de5df9b31816eUL,
+		  0x497d723f802e88e1UL, 0x30684dea602f408dUL,
+	/* 162 */ 0x21e5a278a3e6cb34UL, 0xaefb6e6f5b151dc4UL,
+		  0xb30b8e049d77ca15UL, 0x28c3c9cf53b98981UL,
+	/* 163 */ 0x287fb721556cdd2aUL, 0x0d317ca897022274UL,
+		  0x7468c7423a543258UL, 0x4a7f11464eb5642fUL,
+	/* 164 */ 0xa237a4774d193aa6UL, 0xd865986ea92129a1UL,
+		  0x24c515ecf87c1a88UL, 0x604003575f39f5ebUL,
+	/* 165 */ 0x47b9f189570a9b27UL, 0x2b98cede465e4b78UL,
+		  0x026df551dbb85c20UL, 0x74fcd91047e21901UL,
+	/* 166 */ 0x13e2a90a23c1bfa3UL, 0x0cb0074e478519f6UL,
+		  0x5ff1cbbe3af6cf44UL, 0x67fe5438be812dbeUL,
+	/* 167 */ 0xd13cf64fa40f05b0UL, 0x054dfb2f32283787UL,
+		  0x4173915b7f0d2aeaUL, 0x482f144f1f610d4eUL,
+	/* 168 */ 0xf6210201b47f8234UL, 0x5d0ae1929e70b990UL,
+		  0xdcd7f455b049567cUL, 0x7e93d0f1f0916f01UL,
+	/* 169 */ 0xdd79cbf18a7db4faUL, 0xbe8391bf6f74c62fUL,
+		  0x027145d14b8291bdUL, 0x585a73ea2cbf1705UL,
+	/* 170 */ 0x485ca03e928a0db2UL, 0x10fc01a5742857e7UL,
+		  0x2f482edbd6d551a7UL, 0x0f0433b5048fdb8aUL,
+	/* 171 */ 0x60da2e8dd7dc6247UL, 0x88b4c9d38cd4819aUL,
+		  0x13033ac001f66697UL, 0x273b24fe3b367d75UL,
+	/* 172 */ 0xc6e8f66a31b3b9d4UL, 0x281514a494df49d5UL,
+		  0xd1726fdfc8b23da7UL, 0x4b3ae7d103dee548UL,
+	/* 173 */ 0xc6256e19ce4b9d7eUL, 0xff5c5cf186e3c61cUL,
+		  0xacc63ca34b8ec145UL, 0x74621888fee66574UL,
+	/* 174 */ 0x956f409645290a1eUL, 0xef0bf8e3263a962eUL,
+		  0xed6a50eb5ec2647bUL, 0x0694283a9dca7502UL,
+	/* 175 */ 0x769b963643a2dcd1UL, 0x42b7c8ea09fc5353UL,
+		  0x4f002aee13397eabUL, 0x63005e2c19b7d63aUL,
+	/* 176 */ 0xca6736da63023beaUL, 0x966c7f6db12a99b7UL,
+		  0xace09390c537c5e1UL, 0x0b696063a1aa89eeUL,
+	/* 177 */ 0xebb03e97288c56e5UL, 0x432a9f9f938c8be8UL,
+		  0xa6a5a93d5b717f71UL, 0x1a5fb4c3e18f9d97UL,
+	/* 178 */ 0x1c94e7ad1c60cdceUL, 0xee202a43fc02c4a0UL,
+		  0x8dafe4d867c46a20UL, 0x0a10263c8ac27b58UL,
+	/* 179 */ 0xd0dea9dfe4432a4aUL, 0x856af87bbe9277c5UL,
+		  0xce8472acc212c71aUL, 0x6f151b6d9bbb1e91UL,
+	/* 180 */ 0x26776c527ceed56aUL, 0x7d211cb7fbf8faecUL,
+		  0x37ae66a6fd4609ccUL, 0x1f81b702d2770c42UL,
+	/* 181 */ 0x2fb0b057eac58392UL, 0xe1dd89fe29744e9dUL,
+		  0xc964f8eb17beb4f8UL, 0x29571073c9a2d41eUL,
+	/* 182 */ 0xa948a18981c0e254UL, 0x2df6369b65b22830UL,
+		  0xa33eb2d75fcfd3c6UL, 0x078cd6ec4199a01fUL,
+	/* 183 */ 0x4a584a41ad900d2fUL, 0x32142b78e2c74c52UL,
+		  0x68c4e8338431c978UL, 0x7f69ea9008689fc2UL,
+	/* 184 */ 0x52f2c81e46a38265UL, 0xfd78072d04a832fdUL,
+		  0x8cd7d5fa25359e94UL, 0x4de71b7454cc29d2UL,
+	/* 185 */ 0x42eb60ad1eda6ac9UL, 0x0aad37dfdbc09c3aUL,
+		  0x81004b71e33cc191UL, 0x44e6be345122803cUL,
+	/* 186 */ 0x03fe8388ba1920dbUL, 0xf5d57c32150db008UL,
+		  0x49c8c4281af60c29UL, 0x21edb518de701aeeUL,
+	/* 187 */ 0x7fb63e418f06dc99UL, 0xa4460d99c166d7b8UL,
+		  0x24dd5248ce520a83UL, 0x5ec3ad712b928358UL,
+	/* 188 */ 0x15022a5fbd17930fUL, 0xa4f64a77d82570e3UL,
+		  0x12bc8d6915783712UL, 0x498194c0fc620abbUL,
+	/* 189 */ 0x38a2d9d255686c82UL, 0x785c6bd9193e21f0UL,
+		  0xe4d5c81ab24a5484UL, 0x56307860b2e20989UL,
+	/* 190 */ 0x429d55f78b4d74c4UL, 0x22f1834643350131UL,
+		  0x1e60c24598c71fffUL, 0x59f2f014979983efUL,
+	/* 191 */ 0x46a47d56eb494a44UL, 0x3e22a854d636a18eUL,
+		  0xb346e15274491c3bUL, 0x2ceafd4e5390cde7UL,
+	/* 192 */ 0xba8a8538be0d6675UL, 0x4b9074bb50818e23UL,
+		  0xcbdab89085d304c3UL, 0x61a24fe0e56192c4UL,
+	/* 193 */ 0xcb7615e6db525bcbUL, 0xdd7d8c35a567e4caUL,
+		  0xe6b4153acafcdd69UL, 0x2d668e097f3c9766UL,
+	/* 194 */ 0xa57e7e265ce55ef0UL, 0x5d9f4e527cd4b967UL,
+		  0xfbc83606492fd1e5UL, 0x090d52beb7c3f7aeUL,
+	/* 195 */ 0x09b9515a1e7b4d7cUL, 0x1f266a2599da44c0UL,
+		  0xa1c49548e2c55504UL, 0x7ef04287126f15ccUL,
+	/* 196 */ 0xfed1659dbd30ef15UL, 0x8b4ab9eec4e0277bUL,
+		  0x884d6236a5df3291UL, 0x1fd96ea6bf5cf788UL,
+	/* 197 */ 0x42a161981f190d9aUL, 0x61d849507e6052c1UL,
+		  0x9fe113bf285a2cd5UL, 0x7c22d676dbad85d8UL,
+	/* 198 */ 0x82e770ed2bfbd27dUL, 0x4c05b2ece996f5a5UL,
+		  0xcd40a9c2b0900150UL, 0x5895319213d9bf64UL,
+	/* 199 */ 0xe7cc5d703fea2e08UL, 0xb50c491258e2188cUL,
+		  0xcce30baa48205bf0UL, 0x537c659ccfa32d62UL,
+	/* 200 */ 0x37b6623a98cfc088UL, 0xfe9bed1fa4d6aca4UL,
+		  0x04d29b8e56a8d1b0UL, 0x725f71c40b519575UL,
+	/* 201 */ 0x28c7f89cd0339ce6UL, 0x8367b14469ddc18bUL,
+		  0x883ada83a6a1652cUL, 0x585f1974034d6c17UL,
+	/* 202 */ 0x89cfb266f1b19188UL, 0xe63b4863e7c35217UL,
+		  0xd88c9da6b4c0526aUL, 0x3e035c9df0954635UL,
+	/* 203 */ 0xdd9d5412fb45de9dUL, 0xdd684532e4cff40dUL,
+		  0x4b5c999b151d671cUL, 0x2d8c2cc811e7f690UL,
+	/* 204 */ 0x7f54be1d90055d40UL, 0xa464c5df464aaf40UL,
+		  0x33979624f0e917beUL, 0x2c018dc527356b30UL,
+	/* 205 */ 0xa5415024e330b3d4UL, 0x73ff3d96691652d3UL,
+		  0x94ec42c4ef9b59f1UL, 0x0747201618d08e5aUL,
+	/* 206 */ 0x4d6ca48aca411c53UL, 0x66415f2fcfa66119UL,
+		  0x9c4dd40051e227ffUL, 0x59810bc09a02f7ebUL,
+	/* 207 */ 0x2a7eb171b3dc101dUL, 0x441c5ab99ffef68eUL,
+		  0x32025c9b93b359eaUL, 0x5e8ce0a71e9d112fUL,
+	/* 208 */ 0xbfcccb92429503fdUL, 0xd271ba752f095d55UL,
+		  0x345ead5e972d091eUL, 0x18c8df11a83103baUL,
+	/* 209 */ 0x90cd949a9aed0f4cUL, 0xc5d1f4cb6660e37eUL,
+		  0xb8cac52d56c52e0bUL, 0x6e42e400c5808e0dUL,
+	/* 210 */ 0xa3b46966eeaefd23UL, 0x0c4f1f0be39ecdcaUL,
+		  0x189dc8c9d683a51dUL, 0x51f27f054c09351bUL,
+	/* 211 */ 0x4c487ccd2a320682UL, 0x587ea95bb3df1c96UL,
+		  0xc8ccf79e555cb8e8UL, 0x547dc829a206d73dUL,
+	/* 212 */ 0xb822a6cd80c39b06UL, 0xe96d54732000d4c6UL,
+		  0x28535b6f91463b4dUL, 0x228f4660e2486e1dUL,
+	/* 213 */ 0x98799538de8d3abfUL, 0x8cd8330045ebca6eUL,
+		  0x79952a008221e738UL, 0x4322e1a7535cd2bbUL,
+	/* 214 */ 0xb114c11819d1801cUL, 0x2016e4d84f3f5ec7UL,
+		  0xdd0e2df409260f4cUL, 0x5ec362c0ae5f7266UL,
+	/* 215 */ 0xc0462b18b8b2b4eeUL, 0x7cc8d950274d1afbUL,
+		  0xf25f7105436b02d2UL, 0x43bbf8dcbff9ccd3UL,
+	/* 216 */ 0xb6ad1767a039e9dfUL, 0xb0714da8f69d3583UL,
+		  0x5e55fa18b42931f5UL, 0x4ed5558f33c60961UL,
+	/* 217 */ 0x1fe37901c647a5ddUL, 0x593ddf1f8081d357UL,
+		  0x0249a4fd813fd7a6UL, 0x69acca274e9caf61UL,
+	/* 218 */ 0x047ba3ea330721c9UL, 0x83423fc20e7e1ea0UL,
+		  0x1df4c0af01314a60UL, 0x09a62dab89289527UL,
+	/* 219 */ 0xa5b325a49cc6cb00UL, 0xe94b5dc654b56cb6UL,
+		  0x3be28779adc994a0UL, 0x4296e8f8ba3a4aadUL,
+	/* 220 */ 0x328689761e451eabUL, 0x2e4d598bff59594aUL,
+		  0x49b96853d7a7084aUL, 0x4980a319601420a8UL,
+	/* 221 */ 0x9565b9e12f552c42UL, 0x8a5318db7100fe96UL,
+		  0x05c90b4d43add0d7UL, 0x538b4cd66a5d4edaUL,
+	/* 222 */ 0xf4e94fc3e89f039fUL, 0x592c9af26f618045UL,
+		  0x08a36eb5fd4b9550UL, 0x25fffaf6c2ed1419UL,
+	/* 223 */ 0x34434459cc79d354UL, 0xeeecbfb4b1d5476bUL,
+		  0xddeb34a061615d99UL, 0x5129cecceb64b773UL,
+	/* 224 */ 0xee43215894993520UL, 0x772f9c7cf14c0b3bUL,
+		  0xd2e2fce306bedad5UL, 0x715f42b546f06a97UL,
+	/* 225 */ 0x434ecdceda5b5f1aUL, 0x0da17115a49741a9UL,
+		  0x680bd77c73edad2eUL, 0x487c02354edd9041UL,
+	/* 226 */ 0xb8efeff3a70ed9c4UL, 0x56a32aa3e857e302UL,
+		  0xdf3a68bd48a2a5a0UL, 0x07f650b73176c444UL,
+	/* 227 */ 0xe38b9b1626e0ccb1UL, 0x79e053c18b09fb36UL,
+		  0x56d90319c9f94964UL, 0x1ca941e7ac9ff5c4UL,
+	/* 228 */ 0x49c4df29162fa0bbUL, 0x8488cf3282b33305UL,
+		  0x95dfda14cabb437dUL, 0x3391f78264d5ad86UL,
+	/* 229 */ 0x729ae06ae2b5095dUL, 0xd58a58d73259a946UL,
+		  0xe9834262d13921edUL, 0x27fedafaa54bb592UL,
+	/* 230 */ 0xa99dc5b829ad48bbUL, 0x5f025742499ee260UL,
+		  0x802c8ecd5d7513fdUL, 0x78ceb3ef3f6dd938UL,
+	/* 231 */ 0xc342f44f8a135d94UL, 0x7b9edb44828cdda3UL,
+		  0x9436d11a0537cfe7UL, 0x5064b164ec1ab4c8UL,
+	/* 232 */ 0x7020eccfd37eb2fcUL, 0x1f31ea3ed90d25fcUL,
+		  0x1b930d7bdfa1bb34UL, 0x5344467a48113044UL,
+	/* 233 */ 0x70073170f25e6dfbUL, 0xe385dc1a50114cc8UL,
+		  0x2348698ac8fc4f00UL, 0x2a77a55284dd40d8UL,
+	/* 234 */ 0xfe06afe0c98c6ce4UL, 0xc235df96dddfd6e4UL,
+		  0x1428d01e33bf1ed3UL, 0x785768ec9300bdafUL,
+	/* 235 */ 0x9702e57a91deb63bUL, 0x61bdb8bfe5ce8b80UL,
+		  0x645b426f3d1d58acUL, 0x4804a82227a557bcUL,
+	/* 236 */ 0x8e57048ab44d2601UL, 0x68d6501a4b3a6935UL,
+		  0xc39c9ec3f9e1c293UL, 0x4172f257d4de63e2UL,
+	/* 237 */ 0xd368b450330c6401UL, 0x040d3017418f2391UL,
+		  0x2c34bb6090b7d90dUL, 0x16f649228fdfd51fUL,
+	/* 238 */ 0xbea6818e2b928ef5UL, 0xe28ccf91cdc11e72UL,
+		  0x594aaa68e77a36cdUL, 0x313034806c7ffd0fUL,
+	/* 239 */ 0x8a9d27ac2249bd65UL, 0x19a3b464018e9512UL,
+		  0xc26ccff352b37ec7UL, 0x056f68341d797b21UL,
+	/* 240 */ 0x5e79d6757efd2327UL, 0xfabdbcb6553afe15UL,
+		  0xd3e7222c6eaf5a60UL, 0x7046c76d4dae743bUL,
+	/* 241 */ 0x660be872b18d4a55UL, 0x19992518574e1496UL,
+		  0xc103053a302bdcbbUL, 0x3ed8e9800b218e8eUL,
+	/* 242 */ 0x7b0b9239fa75e03eUL, 0xefe9fb684633c083UL,
+		  0x98a35fbe391a7793UL, 0x6065510fe2d0fe34UL,
+	/* 243 */ 0x55cb668548abad0cUL, 0xb4584548da87e527UL,
+		  0x2c43ecea0107c1ddUL, 0x526028809372de35UL,
+	/* 244 */ 0x3415c56af9213b1fUL, 0x5bee1a4d017e98dbUL,
+		  0x13f6b105b5cf709bUL, 0x5ff20e3482b29ab6UL,
+	/* 245 */ 0x0aa29c75cc2e6c90UL, 0xfc7d73ca3a70e206UL,
+		  0x899fc38fc4b5c515UL, 0x250386b124ffc207UL,
+	/* 246 */ 0x54ea28d5ae3d2b56UL, 0x9913149dd6de60ceUL,
+		  0x16694fc58f06d6c1UL, 0x46b23975eb018fc7UL,
+	/* 247 */ 0x470a6a0fb4b7b4e2UL, 0x5d92475a8f7253deUL,
+		  0xabeee5b52fbd3adbUL, 0x7fa20801a0806968UL,
+	/* 248 */ 0x76f3faf19f7714d2UL, 0xb3e840c12f4660c3UL,
+		  0x0fb4cd8df212744eUL, 0x4b065a251d3a2dd2UL,
+	/* 249 */ 0x5cebde383d77cd4aUL, 0x6adf39df882c9cb1UL,
+		  0xa2dd242eb09af759UL, 0x3147c0e50e5f6422UL,
+	/* 250 */ 0x164ca5101d1350dbUL, 0xf8d13479c33fc962UL,
+		  0xe640ce4d13e5da08UL, 0x4bdee0c45061f8baUL,
+	/* 251 */ 0xd7c46dc1a4edb1c9UL, 0x5514d7b6437fd98aUL,
+		  0x58942f6bb2a1c00bUL, 0x2dffb2ab1d70710eUL,
+	/* 252 */ 0xccdfcf2fc18b6d68UL, 0xa8ebcba8b7806167UL,
+		  0x980697f95e2937e3UL, 0x02fbba1cd0126e8cUL
+};
+
+/* c is two 512-bit products: c0[0:7]=a0[0:3]*b0[0:3] and c1[8:15]=a1[4:7]*b1[4:7]
+ * a is two 256-bit integers: a0[0:3] and a1[4:7]
+ * b is two 256-bit integers: b0[0:3] and b1[4:7]
+ */
+static void mul2_256x256_integer_adx(u64 *const c, const u64 *const a,
+				     const u64 *const b)
+{
+	asm volatile(
+		"xorl %%r14d, %%r14d ;"
+		"movq   (%1), %%rdx; "	/* A[0] */
+		"mulx   (%2),  %%r8, %%r15; " /* A[0]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"movq %%r8, (%0) ;"
+		"mulx  8(%2), %%r10, %%rax; " /* A[0]*B[1] */
+		"adox %%r10, %%r15 ;"
+		"mulx 16(%2),  %%r8, %%rbx; " /* A[0]*B[2] */
+		"adox  %%r8, %%rax ;"
+		"mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */
+		"adox %%r10, %%rbx ;"
+		/******************************************/
+		"adox %%r14, %%rcx ;"
+
+		"movq  8(%1), %%rdx; "	/* A[1] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[1]*B[0] */
+		"adox %%r15,  %%r8 ;"
+		"movq  %%r8, 8(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[1]*B[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rax ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[1]*B[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%rbx ;"
+		"mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%rcx ;"
+		/******************************************/
+		"adox %%r14, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+
+		"movq 16(%1), %%rdx; " /* A[2] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx   (%2),  %%r8,  %%r9; " /* A[2]*B[0] */
+		"adox %%rax,  %%r8 ;"
+		"movq %%r8, 16(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[2]*B[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rbx ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[2]*B[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%rcx ;"
+		"mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%r15 ;"
+		/******************************************/
+		"adox %%r14, %%rax ;"
+		"adcx %%r14, %%rax ;"
+
+		"movq 24(%1), %%rdx; " /* A[3] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx   (%2),  %%r8,  %%r9; " /* A[3]*B[0] */
+		"adox %%rbx,  %%r8 ;"
+		"movq %%r8, 24(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[3]*B[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rcx ;"
+		"movq %%rcx, 32(%0) ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[3]*B[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%rax ;"
+		"movq %%rax, 48(%0) ;"
+		/******************************************/
+		"adox %%r14, %%rbx ;"
+		"adcx %%r14, %%rbx ;"
+		"movq %%rbx, 56(%0) ;"
+
+		"movq 32(%1), %%rdx; "	/* C[0] */
+		"mulx 32(%2),  %%r8, %%r15; " /* C[0]*D[0] */
+		"xorl %%r10d, %%r10d ;"
+		"movq %%r8, 64(%0);"
+		"mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */
+		"adox %%r10, %%r15 ;"
+		"mulx 48(%2),  %%r8, %%rbx; " /* C[0]*D[2] */
+		"adox  %%r8, %%rax ;"
+		"mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */
+		"adox %%r10, %%rbx ;"
+		/******************************************/
+		"adox %%r14, %%rcx ;"
+
+		"movq 40(%1), %%rdx; " /* C[1] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[1]*D[0] */
+		"adox %%r15,  %%r8 ;"
+		"movq  %%r8, 72(%0);"
+		"mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rax ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[1]*D[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%rbx ;"
+		"mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%rcx ;"
+		/******************************************/
+		"adox %%r14, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+
+		"movq 48(%1), %%rdx; " /* C[2] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[2]*D[0] */
+		"adox %%rax,  %%r8 ;"
+		"movq  %%r8, 80(%0);"
+		"mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rbx ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[2]*D[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%rcx ;"
+		"mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%r15 ;"
+		/******************************************/
+		"adox %%r14, %%rax ;"
+		"adcx %%r14, %%rax ;"
+
+		"movq 56(%1), %%rdx; " /* C[3] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[3]*D[0] */
+		"adox %%rbx,  %%r8 ;"
+		"movq  %%r8, 88(%0);"
+		"mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rcx ;"
+		"movq %%rcx,  96(%0) ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[3]*D[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%r15 ;"
+		"movq %%r15, 104(%0) ;"
+		"mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%rax ;"
+		"movq %%rax, 112(%0) ;"
+		/******************************************/
+		"adox %%r14, %%rbx ;"
+		"adcx %%r14, %%rbx ;"
+		"movq %%rbx, 120(%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r14", "%r15");
+}
+
+static void mul2_256x256_integer_bmi2(u64 *const c, const u64 *const a,
+				      const u64 *const b)
+{
+	asm volatile(
+		"movq   (%1), %%rdx; "	/* A[0] */
+		"mulx   (%2),  %%r8, %%r15; " /* A[0]*B[0] */
+		"movq %%r8,  (%0) ;"
+		"mulx  8(%2), %%r10, %%rax; " /* A[0]*B[1] */
+		"addq %%r10, %%r15 ;"
+		"mulx 16(%2),  %%r8, %%rbx; " /* A[0]*B[2] */
+		"adcq  %%r8, %%rax ;"
+		"mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */
+		"adcq %%r10, %%rbx ;"
+		/******************************************/
+		"adcq    $0, %%rcx ;"
+
+		"movq  8(%1), %%rdx; "	/* A[1] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[1]*B[0] */
+		"addq %%r15,  %%r8 ;"
+		"movq %%r8, 8(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[1]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[1]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%r15 ;"
+
+		"addq  %%r9, %%rax ;"
+		"adcq %%r11, %%rbx ;"
+		"adcq %%r13, %%rcx ;"
+		"adcq    $0, %%r15 ;"
+
+		"movq 16(%1), %%rdx; "	/* A[2] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[2]*B[0] */
+		"addq %%rax,  %%r8 ;"
+		"movq %%r8, 16(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[2]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[2]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rax ;"
+
+		"addq  %%r9, %%rbx ;"
+		"adcq %%r11, %%rcx ;"
+		"adcq %%r13, %%r15 ;"
+		"adcq    $0, %%rax ;"
+
+		"movq 24(%1), %%rdx; "	/* A[3] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[3]*B[0] */
+		"addq %%rbx,  %%r8 ;"
+		"movq %%r8, 24(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[3]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[3]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rbx ;"
+
+		"addq  %%r9, %%rcx ;"
+		"movq %%rcx, 32(%0) ;"
+		"adcq %%r11, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"adcq %%r13, %%rax ;"
+		"movq %%rax, 48(%0) ;"
+		"adcq    $0, %%rbx ;"
+		"movq %%rbx, 56(%0) ;"
+
+		"movq 32(%1), %%rdx; "	/* C[0] */
+		"mulx 32(%2),  %%r8, %%r15; " /* C[0]*D[0] */
+		"movq %%r8, 64(%0) ;"
+		"mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */
+		"addq %%r10, %%r15 ;"
+		"mulx 48(%2),  %%r8, %%rbx; " /* C[0]*D[2] */
+		"adcq  %%r8, %%rax ;"
+		"mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */
+		"adcq %%r10, %%rbx ;"
+		/******************************************/
+		"adcq    $0, %%rcx ;"
+
+		"movq 40(%1), %%rdx; "	/* C[1] */
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[1]*D[0] */
+		"addq %%r15,  %%r8 ;"
+		"movq %%r8, 72(%0) ;"
+		"mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[1]*D[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%r15 ;"
+
+		"addq  %%r9, %%rax ;"
+		"adcq %%r11, %%rbx ;"
+		"adcq %%r13, %%rcx ;"
+		"adcq    $0, %%r15 ;"
+
+		"movq 48(%1), %%rdx; "	/* C[2] */
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[2]*D[0] */
+		"addq %%rax,  %%r8 ;"
+		"movq %%r8, 80(%0) ;"
+		"mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[2]*D[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rax ;"
+
+		"addq  %%r9, %%rbx ;"
+		"adcq %%r11, %%rcx ;"
+		"adcq %%r13, %%r15 ;"
+		"adcq    $0, %%rax ;"
+
+		"movq 56(%1), %%rdx; "	/* C[3] */
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[3]*D[0] */
+		"addq %%rbx,  %%r8 ;"
+		"movq %%r8, 88(%0) ;"
+		"mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[3]*D[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rbx ;"
+
+		"addq  %%r9, %%rcx ;"
+		"movq %%rcx,  96(%0) ;"
+		"adcq %%r11, %%r15 ;"
+		"movq %%r15, 104(%0) ;"
+		"adcq %%r13, %%rax ;"
+		"movq %%rax, 112(%0) ;"
+		"adcq    $0, %%rbx ;"
+		"movq %%rbx, 120(%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r15");
+}
+
+static void sqr2_256x256_integer_adx(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movq   (%1), %%rdx        ;" /* A[0]      */
+		"mulx  8(%1),  %%r8, %%r14 ;" /* A[1]*A[0] */
+		"xorl %%r15d, %%r15d;"
+		"mulx 16(%1),  %%r9, %%r10 ;" /* A[2]*A[0] */
+		"adcx %%r14,  %%r9 ;"
+		"mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */
+		"adcx %%rax, %%r10 ;"
+		"movq 24(%1), %%rdx        ;" /* A[3]      */
+		"mulx  8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */
+		"adcx %%rcx, %%r11 ;"
+		"mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */
+		"adcx %%rax, %%rbx ;"
+		"movq  8(%1), %%rdx        ;" /* A[1]      */
+		"adcx %%r15, %%r13 ;"
+		"mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */
+		"movq    $0, %%r14 ;"
+		/******************************************/
+		"adcx %%r15, %%r14 ;"
+
+		"xorl %%r15d, %%r15d;"
+		"adox %%rax, %%r10 ;"
+		"adcx  %%r8,  %%r8 ;"
+		"adox %%rcx, %%r11 ;"
+		"adcx  %%r9,  %%r9 ;"
+		"adox %%r15, %%rbx ;"
+		"adcx %%r10, %%r10 ;"
+		"adox %%r15, %%r13 ;"
+		"adcx %%r11, %%r11 ;"
+		"adox %%r15, %%r14 ;"
+		"adcx %%rbx, %%rbx ;"
+		"adcx %%r13, %%r13 ;"
+		"adcx %%r14, %%r14 ;"
+
+		"movq   (%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */
+		/*******************/
+		"movq %%rax,  0(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"movq  8(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9, 16(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"movq 16(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11, 32(%0) ;"
+		"adcq %%rcx, %%rbx ;"
+		"movq %%rbx, 40(%0) ;"
+		"movq 24(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 48(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 56(%0) ;"
+
+
+		"movq 32(%1), %%rdx        ;" /* B[0]      */
+		"mulx 40(%1),  %%r8, %%r14 ;" /* B[1]*B[0] */
+		"xorl %%r15d, %%r15d;"
+		"mulx 48(%1),  %%r9, %%r10 ;" /* B[2]*B[0] */
+		"adcx %%r14,  %%r9 ;"
+		"mulx 56(%1), %%rax, %%rcx ;" /* B[3]*B[0] */
+		"adcx %%rax, %%r10 ;"
+		"movq 56(%1), %%rdx        ;" /* B[3]      */
+		"mulx 40(%1), %%r11, %%rbx ;" /* B[1]*B[3] */
+		"adcx %%rcx, %%r11 ;"
+		"mulx 48(%1), %%rax, %%r13 ;" /* B[2]*B[3] */
+		"adcx %%rax, %%rbx ;"
+		"movq 40(%1), %%rdx        ;" /* B[1]      */
+		"adcx %%r15, %%r13 ;"
+		"mulx 48(%1), %%rax, %%rcx ;" /* B[2]*B[1] */
+		"movq    $0, %%r14 ;"
+		/******************************************/
+		"adcx %%r15, %%r14 ;"
+
+		"xorl %%r15d, %%r15d;"
+		"adox %%rax, %%r10 ;"
+		"adcx  %%r8,  %%r8 ;"
+		"adox %%rcx, %%r11 ;"
+		"adcx  %%r9,  %%r9 ;"
+		"adox %%r15, %%rbx ;"
+		"adcx %%r10, %%r10 ;"
+		"adox %%r15, %%r13 ;"
+		"adcx %%r11, %%r11 ;"
+		"adox %%r15, %%r14 ;"
+		"adcx %%rbx, %%rbx ;"
+		"adcx %%r13, %%r13 ;"
+		"adcx %%r14, %%r14 ;"
+
+		"movq 32(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* B[0]^2 */
+		/*******************/
+		"movq %%rax,  64(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  72(%0) ;"
+		"movq 40(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* B[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9,  80(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10,  88(%0) ;"
+		"movq 48(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* B[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11,  96(%0) ;"
+		"adcq %%rcx, %%rbx ;"
+		"movq %%rbx, 104(%0) ;"
+		"movq 56(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* B[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 112(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 120(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r14", "%r15");
+}
+
+static void sqr2_256x256_integer_bmi2(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movq  8(%1), %%rdx        ;" /* A[1]      */
+		"mulx   (%1),  %%r8,  %%r9 ;" /* A[0]*A[1] */
+		"mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */
+		"mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */
+
+		"movq 16(%1), %%rdx        ;" /* A[2]      */
+		"mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */
+		"mulx   (%1), %%rax, %%rdx ;" /* A[0]*A[2] */
+
+		"addq %%rax,  %%r9 ;"
+		"adcq %%rdx, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq %%r14, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"movq    $0, %%r14 ;"
+		"adcq    $0, %%r14 ;"
+
+		"movq   (%1), %%rdx        ;" /* A[0]      */
+		"mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */
+
+		"addq %%rax, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq    $0, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"adcq    $0, %%r14 ;"
+
+		"shldq $1, %%r13, %%r14 ;"
+		"shldq $1, %%r15, %%r13 ;"
+		"shldq $1, %%r11, %%r15 ;"
+		"shldq $1, %%r10, %%r11 ;"
+		"shldq $1,  %%r9, %%r10 ;"
+		"shldq $1,  %%r8,  %%r9 ;"
+		"shlq  $1,  %%r8        ;"
+
+		/*******************/
+		"mulx %%rdx, %%rax, %%rcx ; " /* A[0]^2 */
+		/*******************/
+		"movq %%rax,  0(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"movq  8(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* A[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9, 16(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"movq 16(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* A[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11, 32(%0) ;"
+		"adcq %%rcx, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"movq 24(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* A[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 48(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 56(%0) ;"
+
+		"movq 40(%1), %%rdx        ;" /* B[1]      */
+		"mulx 32(%1),  %%r8,  %%r9 ;" /* B[0]*B[1] */
+		"mulx 48(%1), %%r10, %%r11 ;" /* B[2]*B[1] */
+		"mulx 56(%1), %%rcx, %%r14 ;" /* B[3]*B[1] */
+
+		"movq 48(%1), %%rdx        ;" /* B[2]      */
+		"mulx 56(%1), %%r15, %%r13 ;" /* B[3]*B[2] */
+		"mulx 32(%1), %%rax, %%rdx ;" /* B[0]*B[2] */
+
+		"addq %%rax,  %%r9 ;"
+		"adcq %%rdx, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq %%r14, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"movq    $0, %%r14 ;"
+		"adcq    $0, %%r14 ;"
+
+		"movq 32(%1), %%rdx        ;" /* B[0]      */
+		"mulx 56(%1), %%rax, %%rcx ;" /* B[0]*B[3] */
+
+		"addq %%rax, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq    $0, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"adcq    $0, %%r14 ;"
+
+		"shldq $1, %%r13, %%r14 ;"
+		"shldq $1, %%r15, %%r13 ;"
+		"shldq $1, %%r11, %%r15 ;"
+		"shldq $1, %%r10, %%r11 ;"
+		"shldq $1,  %%r9, %%r10 ;"
+		"shldq $1,  %%r8,  %%r9 ;"
+		"shlq  $1,  %%r8        ;"
+
+		/*******************/
+		"mulx %%rdx, %%rax, %%rcx ; " /* B[0]^2 */
+		/*******************/
+		"movq %%rax,  64(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  72(%0) ;"
+		"movq 40(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* B[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9,  80(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10,  88(%0) ;"
+		"movq 48(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* B[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11,  96(%0) ;"
+		"adcq %%rcx, %%r15 ;"
+		"movq %%r15, 104(%0) ;"
+		"movq 56(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* B[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 112(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 120(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11", "%r13", "%r14", "%r15");
+}
+
+static void red_eltfp25519_2w_adx(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movl    $38, %%edx; "	/* 2*c = 38 = 2^256 */
+		"mulx 32(%1),  %%r8, %%r10; " /* c*C[4] */
+		"xorl %%ebx, %%ebx ;"
+		"adox   (%1),  %%r8 ;"
+		"mulx 40(%1),  %%r9, %%r11; " /* c*C[5] */
+		"adcx %%r10,  %%r9 ;"
+		"adox  8(%1),  %%r9 ;"
+		"mulx 48(%1), %%r10, %%rax; " /* c*C[6] */
+		"adcx %%r11, %%r10 ;"
+		"adox 16(%1), %%r10 ;"
+		"mulx 56(%1), %%r11, %%rcx; " /* c*C[7] */
+		"adcx %%rax, %%r11 ;"
+		"adox 24(%1), %%r11 ;"
+		/***************************************/
+		"adcx %%rbx, %%rcx ;"
+		"adox  %%rbx, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */
+		"adcx %%rcx,  %%r8 ;"
+		"adcx %%rbx,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcx %%rbx, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcx %%rbx, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+
+		"mulx  96(%1),  %%r8, %%r10; " /* c*C[4] */
+		"xorl %%ebx, %%ebx ;"
+		"adox 64(%1),  %%r8 ;"
+		"mulx 104(%1),  %%r9, %%r11; " /* c*C[5] */
+		"adcx %%r10,  %%r9 ;"
+		"adox 72(%1),  %%r9 ;"
+		"mulx 112(%1), %%r10, %%rax; " /* c*C[6] */
+		"adcx %%r11, %%r10 ;"
+		"adox 80(%1), %%r10 ;"
+		"mulx 120(%1), %%r11, %%rcx; " /* c*C[7] */
+		"adcx %%rax, %%r11 ;"
+		"adox 88(%1), %%r11 ;"
+		/****************************************/
+		"adcx %%rbx, %%rcx ;"
+		"adox  %%rbx, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */
+		"adcx %%rcx,  %%r8 ;"
+		"adcx %%rbx,  %%r9 ;"
+		"movq  %%r9, 40(%0) ;"
+		"adcx %%rbx, %%r10 ;"
+		"movq %%r10, 48(%0) ;"
+		"adcx %%rbx, %%r11 ;"
+		"movq %%r11, 56(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8, 32(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11");
+}
+
+static void red_eltfp25519_2w_bmi2(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movl    $38, %%edx ; "       /* 2*c = 38 = 2^256 */
+		"mulx 32(%1),  %%r8, %%r10 ;" /* c*C[4] */
+		"mulx 40(%1),  %%r9, %%r11 ;" /* c*C[5] */
+		"addq %%r10,  %%r9 ;"
+		"mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */
+		"adcq %%r11, %%r10 ;"
+		"mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */
+		"adcq %%rax, %%r11 ;"
+		/***************************************/
+		"adcq    $0, %%rcx ;"
+		"addq   (%1),  %%r8 ;"
+		"adcq  8(%1),  %%r9 ;"
+		"adcq 16(%1), %%r10 ;"
+		"adcq 24(%1), %%r11 ;"
+		"adcq     $0, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */
+		"addq %%rcx,  %%r8 ;"
+		"adcq    $0,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcq    $0, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcq    $0, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+
+		"mulx  96(%1),  %%r8, %%r10 ;" /* c*C[4] */
+		"mulx 104(%1),  %%r9, %%r11 ;" /* c*C[5] */
+		"addq %%r10,  %%r9 ;"
+		"mulx 112(%1), %%r10, %%rax ;" /* c*C[6] */
+		"adcq %%r11, %%r10 ;"
+		"mulx 120(%1), %%r11, %%rcx ;" /* c*C[7] */
+		"adcq %%rax, %%r11 ;"
+		/****************************************/
+		"adcq    $0, %%rcx ;"
+		"addq 64(%1),  %%r8 ;"
+		"adcq 72(%1),  %%r9 ;"
+		"adcq 80(%1), %%r10 ;"
+		"adcq 88(%1), %%r11 ;"
+		"adcq     $0, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */
+		"addq %%rcx,  %%r8 ;"
+		"adcq    $0,  %%r9 ;"
+		"movq  %%r9, 40(%0) ;"
+		"adcq    $0, %%r10 ;"
+		"movq %%r10, 48(%0) ;"
+		"adcq    $0, %%r11 ;"
+		"movq %%r11, 56(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8, 32(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11");
+}
+
+static void mul_256x256_integer_adx(u64 *const c, const u64 *const a,
+				    const u64 *const b)
+{
+	asm volatile(
+		"movq   (%1), %%rdx; "	/* A[0] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[0]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"movq  %%r8,  (%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[0]*B[1] */
+		"adox  %%r9, %%r10 ;"
+		"movq %%r10, 8(%0) ;"
+		"mulx 16(%2), %%r15, %%r13; " /* A[0]*B[2] */
+		"adox %%r11, %%r15 ;"
+		"mulx 24(%2), %%r14, %%rdx; " /* A[0]*B[3] */
+		"adox %%r13, %%r14 ;"
+		"movq $0, %%rax ;"
+		/******************************************/
+		"adox %%rdx, %%rax ;"
+
+		"movq  8(%1), %%rdx; "	/* A[1] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[1]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"adcx 8(%0),  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[1]*B[1] */
+		"adox  %%r9, %%r10 ;"
+		"adcx %%r15, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"mulx 16(%2), %%r15, %%r13; " /* A[1]*B[2] */
+		"adox %%r11, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+		"movq $0, %%r8  ;"
+		"mulx 24(%2), %%r14, %%rdx; " /* A[1]*B[3] */
+		"adox %%r13, %%r14 ;"
+		"adcx %%rax, %%r14 ;"
+		"movq $0, %%rax ;"
+		/******************************************/
+		"adox %%rdx, %%rax ;"
+		"adcx  %%r8, %%rax ;"
+
+		"movq 16(%1), %%rdx; "	/* A[2] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[2]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"adcx 16(%0), %%r8 ;"
+		"movq  %%r8, 16(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[2]*B[1] */
+		"adox  %%r9, %%r10 ;"
+		"adcx %%r15, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"mulx 16(%2), %%r15, %%r13; " /* A[2]*B[2] */
+		"adox %%r11, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+		"movq $0, %%r8  ;"
+		"mulx 24(%2), %%r14, %%rdx; " /* A[2]*B[3] */
+		"adox %%r13, %%r14 ;"
+		"adcx %%rax, %%r14 ;"
+		"movq $0, %%rax ;"
+		/******************************************/
+		"adox %%rdx, %%rax ;"
+		"adcx  %%r8, %%rax ;"
+
+		"movq 24(%1), %%rdx; "	/* A[3] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[3]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"adcx 24(%0), %%r8 ;"
+		"movq  %%r8, 24(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[3]*B[1] */
+		"adox  %%r9, %%r10 ;"
+		"adcx %%r15, %%r10 ;"
+		"movq %%r10, 32(%0) ;"
+		"mulx 16(%2), %%r15, %%r13; " /* A[3]*B[2] */
+		"adox %%r11, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"movq $0, %%r8  ;"
+		"mulx 24(%2), %%r14, %%rdx; " /* A[3]*B[3] */
+		"adox %%r13, %%r14 ;"
+		"adcx %%rax, %%r14 ;"
+		"movq %%r14, 48(%0) ;"
+		"movq $0, %%rax ;"
+		/******************************************/
+		"adox %%rdx, %%rax ;"
+		"adcx  %%r8, %%rax ;"
+		"movq %%rax, 56(%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11",
+		  "%r13", "%r14", "%r15");
+}
+
+static void mul_256x256_integer_bmi2(u64 *const c, const u64 *const a,
+				     const u64 *const b)
+{
+	asm volatile(
+		"movq   (%1), %%rdx; "	/* A[0] */
+		"mulx   (%2),  %%r8, %%r15; " /* A[0]*B[0] */
+		"movq %%r8,  (%0) ;"
+		"mulx  8(%2), %%r10, %%rax; " /* A[0]*B[1] */
+		"addq %%r10, %%r15 ;"
+		"mulx 16(%2),  %%r8, %%rbx; " /* A[0]*B[2] */
+		"adcq  %%r8, %%rax ;"
+		"mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */
+		"adcq %%r10, %%rbx ;"
+		/******************************************/
+		"adcq    $0, %%rcx ;"
+
+		"movq  8(%1), %%rdx; "	/* A[1] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[1]*B[0] */
+		"addq %%r15,  %%r8 ;"
+		"movq %%r8, 8(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[1]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[1]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%r15 ;"
+
+		"addq  %%r9, %%rax ;"
+		"adcq %%r11, %%rbx ;"
+		"adcq %%r13, %%rcx ;"
+		"adcq    $0, %%r15 ;"
+
+		"movq 16(%1), %%rdx; "	/* A[2] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[2]*B[0] */
+		"addq %%rax,  %%r8 ;"
+		"movq %%r8, 16(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[2]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[2]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rax ;"
+
+		"addq  %%r9, %%rbx ;"
+		"adcq %%r11, %%rcx ;"
+		"adcq %%r13, %%r15 ;"
+		"adcq    $0, %%rax ;"
+
+		"movq 24(%1), %%rdx; "	/* A[3] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[3]*B[0] */
+		"addq %%rbx,  %%r8 ;"
+		"movq %%r8, 24(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[3]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[3]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rbx ;"
+
+		"addq  %%r9, %%rcx ;"
+		"movq %%rcx, 32(%0) ;"
+		"adcq %%r11, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"adcq %%r13, %%rax ;"
+		"movq %%rax, 48(%0) ;"
+		"adcq    $0, %%rbx ;"
+		"movq %%rbx, 56(%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r15");
+}
+
+static void sqr_256x256_integer_adx(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movq   (%1), %%rdx        ;" /* A[0]      */
+		"mulx  8(%1),  %%r8, %%r14 ;" /* A[1]*A[0] */
+		"xorl %%r15d, %%r15d;"
+		"mulx 16(%1),  %%r9, %%r10 ;" /* A[2]*A[0] */
+		"adcx %%r14,  %%r9 ;"
+		"mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */
+		"adcx %%rax, %%r10 ;"
+		"movq 24(%1), %%rdx        ;" /* A[3]      */
+		"mulx  8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */
+		"adcx %%rcx, %%r11 ;"
+		"mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */
+		"adcx %%rax, %%rbx ;"
+		"movq  8(%1), %%rdx        ;" /* A[1]      */
+		"adcx %%r15, %%r13 ;"
+		"mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */
+		"movq    $0, %%r14 ;"
+		/******************************************/
+		"adcx %%r15, %%r14 ;"
+
+		"xorl %%r15d, %%r15d;"
+		"adox %%rax, %%r10 ;"
+		"adcx  %%r8,  %%r8 ;"
+		"adox %%rcx, %%r11 ;"
+		"adcx  %%r9,  %%r9 ;"
+		"adox %%r15, %%rbx ;"
+		"adcx %%r10, %%r10 ;"
+		"adox %%r15, %%r13 ;"
+		"adcx %%r11, %%r11 ;"
+		"adox %%r15, %%r14 ;"
+		"adcx %%rbx, %%rbx ;"
+		"adcx %%r13, %%r13 ;"
+		"adcx %%r14, %%r14 ;"
+
+		"movq   (%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */
+		/*******************/
+		"movq %%rax,  0(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"movq  8(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9, 16(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"movq 16(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11, 32(%0) ;"
+		"adcq %%rcx, %%rbx ;"
+		"movq %%rbx, 40(%0) ;"
+		"movq 24(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 48(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 56(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r14", "%r15");
+}
+
+static void sqr_256x256_integer_bmi2(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movq  8(%1), %%rdx        ;" /* A[1]      */
+		"mulx   (%1),  %%r8,  %%r9 ;" /* A[0]*A[1] */
+		"mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */
+		"mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */
+
+		"movq 16(%1), %%rdx        ;" /* A[2]      */
+		"mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */
+		"mulx   (%1), %%rax, %%rdx ;" /* A[0]*A[2] */
+
+		"addq %%rax,  %%r9 ;"
+		"adcq %%rdx, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq %%r14, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"movq    $0, %%r14 ;"
+		"adcq    $0, %%r14 ;"
+
+		"movq   (%1), %%rdx        ;" /* A[0]      */
+		"mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */
+
+		"addq %%rax, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq    $0, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"adcq    $0, %%r14 ;"
+
+		"shldq $1, %%r13, %%r14 ;"
+		"shldq $1, %%r15, %%r13 ;"
+		"shldq $1, %%r11, %%r15 ;"
+		"shldq $1, %%r10, %%r11 ;"
+		"shldq $1,  %%r9, %%r10 ;"
+		"shldq $1,  %%r8,  %%r9 ;"
+		"shlq  $1,  %%r8        ;"
+
+		/*******************/
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */
+		/*******************/
+		"movq %%rax,  0(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"movq  8(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9, 16(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"movq 16(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11, 32(%0) ;"
+		"adcq %%rcx, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"movq 24(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 48(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 56(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11", "%r13", "%r14", "%r15");
+}
+
+static void red_eltfp25519_1w_adx(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movl    $38, %%edx ;"	/* 2*c = 38 = 2^256 */
+		"mulx 32(%1),  %%r8, %%r10 ;" /* c*C[4] */
+		"xorl %%ebx, %%ebx ;"
+		"adox   (%1),  %%r8 ;"
+		"mulx 40(%1),  %%r9, %%r11 ;" /* c*C[5] */
+		"adcx %%r10,  %%r9 ;"
+		"adox  8(%1),  %%r9 ;"
+		"mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */
+		"adcx %%r11, %%r10 ;"
+		"adox 16(%1), %%r10 ;"
+		"mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */
+		"adcx %%rax, %%r11 ;"
+		"adox 24(%1), %%r11 ;"
+		/***************************************/
+		"adcx %%rbx, %%rcx ;"
+		"adox  %%rbx, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */
+		"adcx %%rcx,  %%r8 ;"
+		"adcx %%rbx,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcx %%rbx, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcx %%rbx, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11");
+}
+
+static void red_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movl    $38, %%edx ;"	/* 2*c = 38 = 2^256 */
+		"mulx 32(%1),  %%r8, %%r10 ;" /* c*C[4] */
+		"mulx 40(%1),  %%r9, %%r11 ;" /* c*C[5] */
+		"addq %%r10,  %%r9 ;"
+		"mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */
+		"adcq %%r11, %%r10 ;"
+		"mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */
+		"adcq %%rax, %%r11 ;"
+		/***************************************/
+		"adcq    $0, %%rcx ;"
+		"addq   (%1),  %%r8 ;"
+		"adcq  8(%1),  %%r9 ;"
+		"adcq 16(%1), %%r10 ;"
+		"adcq 24(%1), %%r11 ;"
+		"adcq     $0, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */
+		"addq %%rcx,  %%r8 ;"
+		"adcq    $0,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcq    $0, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcq    $0, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11");
+}
+
+static __always_inline void
+add_eltfp25519_1w_adx(u64 *const c, const u64 *const a, const u64 *const b)
+{
+	asm volatile(
+		"mov     $38, %%eax ;"
+		"xorl  %%ecx, %%ecx ;"
+		"movq   (%2),  %%r8 ;"
+		"adcx   (%1),  %%r8 ;"
+		"movq  8(%2),  %%r9 ;"
+		"adcx  8(%1),  %%r9 ;"
+		"movq 16(%2), %%r10 ;"
+		"adcx 16(%1), %%r10 ;"
+		"movq 24(%2), %%r11 ;"
+		"adcx 24(%1), %%r11 ;"
+		"cmovc %%eax, %%ecx ;"
+		"xorl %%eax, %%eax  ;"
+		"adcx %%rcx,  %%r8  ;"
+		"adcx %%rax,  %%r9  ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcx %%rax, %%r10  ;"
+		"movq %%r10, 16(%0) ;"
+		"adcx %%rax, %%r11  ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $38, %%ecx ;"
+		"cmovc %%ecx, %%eax ;"
+		"addq %%rax,  %%r8  ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11");
+}
+
+static __always_inline void
+add_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a, const u64 *const b)
+{
+	asm volatile(
+		"mov     $38, %%eax ;"
+		"movq   (%2),  %%r8 ;"
+		"addq   (%1),  %%r8 ;"
+		"movq  8(%2),  %%r9 ;"
+		"adcq  8(%1),  %%r9 ;"
+		"movq 16(%2), %%r10 ;"
+		"adcq 16(%1), %%r10 ;"
+		"movq 24(%2), %%r11 ;"
+		"adcq 24(%1), %%r11 ;"
+		"mov      $0, %%ecx ;"
+		"cmovc %%eax, %%ecx ;"
+		"addq %%rcx,  %%r8  ;"
+		"adcq    $0,  %%r9  ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcq    $0, %%r10  ;"
+		"movq %%r10, 16(%0) ;"
+		"adcq    $0, %%r11  ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx  ;"
+		"cmovc %%eax, %%ecx ;"
+		"addq %%rcx,  %%r8  ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11");
+}
+
+static __always_inline void
+sub_eltfp25519_1w(u64 *const c, const u64 *const a, const u64 *const b)
+{
+	asm volatile(
+		"mov     $38, %%eax ;"
+		"movq   (%1),  %%r8 ;"
+		"subq   (%2),  %%r8 ;"
+		"movq  8(%1),  %%r9 ;"
+		"sbbq  8(%2),  %%r9 ;"
+		"movq 16(%1), %%r10 ;"
+		"sbbq 16(%2), %%r10 ;"
+		"movq 24(%1), %%r11 ;"
+		"sbbq 24(%2), %%r11 ;"
+		"mov      $0, %%ecx ;"
+		"cmovc %%eax, %%ecx ;"
+		"subq %%rcx,  %%r8  ;"
+		"sbbq    $0,  %%r9  ;"
+		"movq  %%r9,  8(%0) ;"
+		"sbbq    $0, %%r10  ;"
+		"movq %%r10, 16(%0) ;"
+		"sbbq    $0, %%r11  ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx  ;"
+		"cmovc %%eax, %%ecx ;"
+		"subq %%rcx,  %%r8  ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11");
+}
+
+/* Multiplication by a24 = (A+2)/4 = (486662+2)/4 = 121666 */
+static __always_inline void
+mul_a24_eltfp25519_1w(u64 *const c, const u64 *const a)
+{
+	const u64 a24 = 121666;
+	asm volatile(
+		"movq     %2, %%rdx ;"
+		"mulx   (%1),  %%r8, %%r10 ;"
+		"mulx  8(%1),  %%r9, %%r11 ;"
+		"addq %%r10,  %%r9 ;"
+		"mulx 16(%1), %%r10, %%rax ;"
+		"adcq %%r11, %%r10 ;"
+		"mulx 24(%1), %%r11, %%rcx ;"
+		"adcq %%rax, %%r11 ;"
+		/**************************/
+		"adcq    $0, %%rcx ;"
+		"movl   $38, %%edx ;" /* 2*c = 38 = 2^256 mod 2^255-19*/
+		"imul %%rdx, %%rcx ;"
+		"addq %%rcx,  %%r8 ;"
+		"adcq    $0,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcq    $0, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcq    $0, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(a24)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11");
+}
+
+static void inv_eltfp25519_1w_adx(u64 *const c, const u64 *const a)
+{
+	struct {
+		eltfp25519_1w_buffer buffer;
+		eltfp25519_1w x0, x1, x2;
+	} __aligned(32) m;
+	u64 *T[4];
+
+	T[0] = m.x0;
+	T[1] = c; /* x^(-1) */
+	T[2] = m.x1;
+	T[3] = m.x2;
+
+	copy_eltfp25519_1w(T[1], a);
+	sqrn_eltfp25519_1w_adx(T[1], 1);
+	copy_eltfp25519_1w(T[2], T[1]);
+	sqrn_eltfp25519_1w_adx(T[2], 2);
+	mul_eltfp25519_1w_adx(T[0], a, T[2]);
+	mul_eltfp25519_1w_adx(T[1], T[1], T[0]);
+	copy_eltfp25519_1w(T[2], T[1]);
+	sqrn_eltfp25519_1w_adx(T[2], 1);
+	mul_eltfp25519_1w_adx(T[0], T[0], T[2]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_adx(T[2], 5);
+	mul_eltfp25519_1w_adx(T[0], T[0], T[2]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_adx(T[2], 10);
+	mul_eltfp25519_1w_adx(T[2], T[2], T[0]);
+	copy_eltfp25519_1w(T[3], T[2]);
+	sqrn_eltfp25519_1w_adx(T[3], 20);
+	mul_eltfp25519_1w_adx(T[3], T[3], T[2]);
+	sqrn_eltfp25519_1w_adx(T[3], 10);
+	mul_eltfp25519_1w_adx(T[3], T[3], T[0]);
+	copy_eltfp25519_1w(T[0], T[3]);
+	sqrn_eltfp25519_1w_adx(T[0], 50);
+	mul_eltfp25519_1w_adx(T[0], T[0], T[3]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_adx(T[2], 100);
+	mul_eltfp25519_1w_adx(T[2], T[2], T[0]);
+	sqrn_eltfp25519_1w_adx(T[2], 50);
+	mul_eltfp25519_1w_adx(T[2], T[2], T[3]);
+	sqrn_eltfp25519_1w_adx(T[2], 5);
+	mul_eltfp25519_1w_adx(T[1], T[1], T[2]);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+static void inv_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a)
+{
+	struct {
+		eltfp25519_1w_buffer buffer;
+		eltfp25519_1w x0, x1, x2;
+	} __aligned(32) m;
+	u64 *T[5];
+
+	T[0] = m.x0;
+	T[1] = c; /* x^(-1) */
+	T[2] = m.x1;
+	T[3] = m.x2;
+
+	copy_eltfp25519_1w(T[1], a);
+	sqrn_eltfp25519_1w_bmi2(T[1], 1);
+	copy_eltfp25519_1w(T[2], T[1]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 2);
+	mul_eltfp25519_1w_bmi2(T[0], a, T[2]);
+	mul_eltfp25519_1w_bmi2(T[1], T[1], T[0]);
+	copy_eltfp25519_1w(T[2], T[1]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 1);
+	mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 5);
+	mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 10);
+	mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]);
+	copy_eltfp25519_1w(T[3], T[2]);
+	sqrn_eltfp25519_1w_bmi2(T[3], 20);
+	mul_eltfp25519_1w_bmi2(T[3], T[3], T[2]);
+	sqrn_eltfp25519_1w_bmi2(T[3], 10);
+	mul_eltfp25519_1w_bmi2(T[3], T[3], T[0]);
+	copy_eltfp25519_1w(T[0], T[3]);
+	sqrn_eltfp25519_1w_bmi2(T[0], 50);
+	mul_eltfp25519_1w_bmi2(T[0], T[0], T[3]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 100);
+	mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 50);
+	mul_eltfp25519_1w_bmi2(T[2], T[2], T[3]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 5);
+	mul_eltfp25519_1w_bmi2(T[1], T[1], T[2]);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+/* Given c, a 256-bit number, fred_eltfp25519_1w updates c
+ * with a number such that 0 <= C < 2**255-19.
+ */
+static __always_inline void fred_eltfp25519_1w(u64 *const c)
+{
+	u64 tmp0 = 38, tmp1 = 19;
+	asm volatile(
+		"btrq   $63,    %3 ;" /* Put bit 255 in carry flag and clear */
+		"cmovncl %k5,   %k4 ;" /* c[255] ? 38 : 19 */
+
+		/* Add either 19 or 38 to c */
+		"addq    %4,   %0 ;"
+		"adcq    $0,   %1 ;"
+		"adcq    $0,   %2 ;"
+		"adcq    $0,   %3 ;"
+
+		/* Test for bit 255 again; only triggered on overflow modulo 2^255-19 */
+		"movl    $0,  %k4 ;"
+		"cmovnsl %k5,  %k4 ;" /* c[255] ? 0 : 19 */
+		"btrq   $63,   %3 ;" /* Clear bit 255 */
+
+		/* Subtract 19 if necessary */
+		"subq    %4,   %0 ;"
+		"sbbq    $0,   %1 ;"
+		"sbbq    $0,   %2 ;"
+		"sbbq    $0,   %3 ;"
+
+		: "+r"(c[0]), "+r"(c[1]), "+r"(c[2]), "+r"(c[3]), "+r"(tmp0),
+		  "+r"(tmp1)
+		:
+		: "memory", "cc");
+}
+
+static __always_inline void cswap(u8 bit, u64 *const px, u64 *const py)
+{
+	u64 temp;
+	asm volatile(
+		"test %9, %9 ;"
+		"movq %0, %8 ;"
+		"cmovnzq %4, %0 ;"
+		"cmovnzq %8, %4 ;"
+		"movq %1, %8 ;"
+		"cmovnzq %5, %1 ;"
+		"cmovnzq %8, %5 ;"
+		"movq %2, %8 ;"
+		"cmovnzq %6, %2 ;"
+		"cmovnzq %8, %6 ;"
+		"movq %3, %8 ;"
+		"cmovnzq %7, %3 ;"
+		"cmovnzq %8, %7 ;"
+		: "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]),
+		  "+r"(py[0]), "+r"(py[1]), "+r"(py[2]), "+r"(py[3]),
+		  "=r"(temp)
+		: "r"(bit)
+		: "cc"
+	);
+}
+
+static __always_inline void cselect(u8 bit, u64 *const px, const u64 *const py)
+{
+	asm volatile(
+		"test %4, %4 ;"
+		"cmovnzq %5, %0 ;"
+		"cmovnzq %6, %1 ;"
+		"cmovnzq %7, %2 ;"
+		"cmovnzq %8, %3 ;"
+		: "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3])
+		: "r"(bit), "rm"(py[0]), "rm"(py[1]), "rm"(py[2]), "rm"(py[3])
+		: "cc"
+	);
+}
+
+static void curve25519_adx(u8 shared[CURVE25519_KEY_SIZE],
+			   const u8 private_key[CURVE25519_KEY_SIZE],
+			   const u8 session_key[CURVE25519_KEY_SIZE])
+{
+	struct {
+		u64 buffer[4 * NUM_WORDS_ELTFP25519];
+		u64 coordinates[4 * NUM_WORDS_ELTFP25519];
+		u64 workspace[6 * NUM_WORDS_ELTFP25519];
+		u8 session[CURVE25519_KEY_SIZE];
+		u8 private[CURVE25519_KEY_SIZE];
+	} __aligned(32) m;
+
+	int i = 0, j = 0;
+	u64 prev = 0;
+	u64 *const X1 = (u64 *)m.session;
+	u64 *const key = (u64 *)m.private;
+	u64 *const Px = m.coordinates + 0;
+	u64 *const Pz = m.coordinates + 4;
+	u64 *const Qx = m.coordinates + 8;
+	u64 *const Qz = m.coordinates + 12;
+	u64 *const X2 = Qx;
+	u64 *const Z2 = Qz;
+	u64 *const X3 = Px;
+	u64 *const Z3 = Pz;
+	u64 *const X2Z2 = Qx;
+	u64 *const X3Z3 = Px;
+
+	u64 *const A = m.workspace + 0;
+	u64 *const B = m.workspace + 4;
+	u64 *const D = m.workspace + 8;
+	u64 *const C = m.workspace + 12;
+	u64 *const DA = m.workspace + 16;
+	u64 *const CB = m.workspace + 20;
+	u64 *const AB = A;
+	u64 *const DC = D;
+	u64 *const DACB = DA;
+
+	memcpy(m.private, private_key, sizeof(m.private));
+	memcpy(m.session, session_key, sizeof(m.session));
+
+	curve25519_clamp_secret(m.private);
+
+	/* As in the draft:
+	 * When receiving such an array, implementations of curve25519
+	 * MUST mask the most-significant bit in the final byte. This
+	 * is done to preserve compatibility with point formats which
+	 * reserve the sign bit for use in other protocols and to
+	 * increase resistance to implementation fingerprinting
+	 */
+	m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1;
+
+	copy_eltfp25519_1w(Px, X1);
+	setzero_eltfp25519_1w(Pz);
+	setzero_eltfp25519_1w(Qx);
+	setzero_eltfp25519_1w(Qz);
+
+	Pz[0] = 1;
+	Qx[0] = 1;
+
+	/* main-loop */
+	prev = 0;
+	j = 62;
+	for (i = 3; i >= 0; --i) {
+		while (j >= 0) {
+			u64 bit = (key[i] >> j) & 0x1;
+			u64 swap = bit ^ prev;
+			prev = bit;
+
+			add_eltfp25519_1w_adx(A, X2, Z2);	/* A = (X2+Z2) */
+			sub_eltfp25519_1w(B, X2, Z2);		/* B = (X2-Z2) */
+			add_eltfp25519_1w_adx(C, X3, Z3);	/* C = (X3+Z3) */
+			sub_eltfp25519_1w(D, X3, Z3);		/* D = (X3-Z3) */
+			mul_eltfp25519_2w_adx(DACB, AB, DC);	/* [DA|CB] = [A|B]*[D|C] */
+
+			cselect(swap, A, C);
+			cselect(swap, B, D);
+
+			sqr_eltfp25519_2w_adx(AB);		/* [AA|BB] = [A^2|B^2] */
+			add_eltfp25519_1w_adx(X3, DA, CB);	/* X3 = (DA+CB) */
+			sub_eltfp25519_1w(Z3, DA, CB);		/* Z3 = (DA-CB) */
+			sqr_eltfp25519_2w_adx(X3Z3);		/* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */
+
+			copy_eltfp25519_1w(X2, B);		/* X2 = B^2 */
+			sub_eltfp25519_1w(Z2, A, B);		/* Z2 = E = AA-BB */
+
+			mul_a24_eltfp25519_1w(B, Z2);		/* B = a24*E */
+			add_eltfp25519_1w_adx(B, B, X2);	/* B = a24*E+B */
+			mul_eltfp25519_2w_adx(X2Z2, X2Z2, AB);	/* [X2|Z2] = [B|E]*[A|a24*E+B] */
+			mul_eltfp25519_1w_adx(Z3, Z3, X1);	/* Z3 = Z3*X1 */
+			--j;
+		}
+		j = 63;
+	}
+
+	inv_eltfp25519_1w_adx(A, Qz);
+	mul_eltfp25519_1w_adx((u64 *)shared, Qx, A);
+	fred_eltfp25519_1w((u64 *)shared);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+static void curve25519_adx_base(u8 session_key[CURVE25519_KEY_SIZE],
+				const u8 private_key[CURVE25519_KEY_SIZE])
+{
+	struct {
+		u64 buffer[4 * NUM_WORDS_ELTFP25519];
+		u64 coordinates[4 * NUM_WORDS_ELTFP25519];
+		u64 workspace[4 * NUM_WORDS_ELTFP25519];
+		u8 private[CURVE25519_KEY_SIZE];
+	} __aligned(32) m;
+
+	const int ite[4] = { 64, 64, 64, 63 };
+	const int q = 3;
+	u64 swap = 1;
+
+	int i = 0, j = 0, k = 0;
+	u64 *const key = (u64 *)m.private;
+	u64 *const Ur1 = m.coordinates + 0;
+	u64 *const Zr1 = m.coordinates + 4;
+	u64 *const Ur2 = m.coordinates + 8;
+	u64 *const Zr2 = m.coordinates + 12;
+
+	u64 *const UZr1 = m.coordinates + 0;
+	u64 *const ZUr2 = m.coordinates + 8;
+
+	u64 *const A = m.workspace + 0;
+	u64 *const B = m.workspace + 4;
+	u64 *const C = m.workspace + 8;
+	u64 *const D = m.workspace + 12;
+
+	u64 *const AB = m.workspace + 0;
+	u64 *const CD = m.workspace + 8;
+
+	const u64 *const P = table_ladder_8k;
+
+	memcpy(m.private, private_key, sizeof(m.private));
+
+	curve25519_clamp_secret(m.private);
+
+	setzero_eltfp25519_1w(Ur1);
+	setzero_eltfp25519_1w(Zr1);
+	setzero_eltfp25519_1w(Zr2);
+	Ur1[0] = 1;
+	Zr1[0] = 1;
+	Zr2[0] = 1;
+
+	/* G-S */
+	Ur2[3] = 0x1eaecdeee27cab34UL;
+	Ur2[2] = 0xadc7a0b9235d48e2UL;
+	Ur2[1] = 0xbbf095ae14b2edf8UL;
+	Ur2[0] = 0x7e94e1fec82faabdUL;
+
+	/* main-loop */
+	j = q;
+	for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) {
+		while (j < ite[i]) {
+			u64 bit = (key[i] >> j) & 0x1;
+			k = (64 * i + j - q);
+			swap = swap ^ bit;
+			cswap(swap, Ur1, Ur2);
+			cswap(swap, Zr1, Zr2);
+			swap = bit;
+			/* Addition */
+			sub_eltfp25519_1w(B, Ur1, Zr1);		/* B = Ur1-Zr1 */
+			add_eltfp25519_1w_adx(A, Ur1, Zr1);	/* A = Ur1+Zr1 */
+			mul_eltfp25519_1w_adx(C, &P[4 * k], B);	/* C = M0-B */
+			sub_eltfp25519_1w(B, A, C);		/* B = (Ur1+Zr1) - M*(Ur1-Zr1) */
+			add_eltfp25519_1w_adx(A, A, C);		/* A = (Ur1+Zr1) + M*(Ur1-Zr1) */
+			sqr_eltfp25519_2w_adx(AB);		/* A = A^2      |  B = B^2 */
+			mul_eltfp25519_2w_adx(UZr1, ZUr2, AB);	/* Ur1 = Zr2*A  |  Zr1 = Ur2*B */
+			++j;
+		}
+		j = 0;
+	}
+
+	/* Doubling */
+	for (i = 0; i < q; ++i) {
+		add_eltfp25519_1w_adx(A, Ur1, Zr1);	/*  A = Ur1+Zr1 */
+		sub_eltfp25519_1w(B, Ur1, Zr1);		/*  B = Ur1-Zr1 */
+		sqr_eltfp25519_2w_adx(AB);		/*  A = A**2     B = B**2 */
+		copy_eltfp25519_1w(C, B);		/*  C = B */
+		sub_eltfp25519_1w(B, A, B);		/*  B = A-B */
+		mul_a24_eltfp25519_1w(D, B);		/*  D = my_a24*B */
+		add_eltfp25519_1w_adx(D, D, C);		/*  D = D+C */
+		mul_eltfp25519_2w_adx(UZr1, AB, CD);	/*  Ur1 = A*B   Zr1 = Zr1*A */
+	}
+
+	/* Convert to affine coordinates */
+	inv_eltfp25519_1w_adx(A, Zr1);
+	mul_eltfp25519_1w_adx((u64 *)session_key, Ur1, A);
+	fred_eltfp25519_1w((u64 *)session_key);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+static void curve25519_bmi2(u8 shared[CURVE25519_KEY_SIZE],
+			    const u8 private_key[CURVE25519_KEY_SIZE],
+			    const u8 session_key[CURVE25519_KEY_SIZE])
+{
+	struct {
+		u64 buffer[4 * NUM_WORDS_ELTFP25519];
+		u64 coordinates[4 * NUM_WORDS_ELTFP25519];
+		u64 workspace[6 * NUM_WORDS_ELTFP25519];
+		u8 session[CURVE25519_KEY_SIZE];
+		u8 private[CURVE25519_KEY_SIZE];
+	} __aligned(32) m;
+
+	int i = 0, j = 0;
+	u64 prev = 0;
+	u64 *const X1 = (u64 *)m.session;
+	u64 *const key = (u64 *)m.private;
+	u64 *const Px = m.coordinates + 0;
+	u64 *const Pz = m.coordinates + 4;
+	u64 *const Qx = m.coordinates + 8;
+	u64 *const Qz = m.coordinates + 12;
+	u64 *const X2 = Qx;
+	u64 *const Z2 = Qz;
+	u64 *const X3 = Px;
+	u64 *const Z3 = Pz;
+	u64 *const X2Z2 = Qx;
+	u64 *const X3Z3 = Px;
+
+	u64 *const A = m.workspace + 0;
+	u64 *const B = m.workspace + 4;
+	u64 *const D = m.workspace + 8;
+	u64 *const C = m.workspace + 12;
+	u64 *const DA = m.workspace + 16;
+	u64 *const CB = m.workspace + 20;
+	u64 *const AB = A;
+	u64 *const DC = D;
+	u64 *const DACB = DA;
+
+	memcpy(m.private, private_key, sizeof(m.private));
+	memcpy(m.session, session_key, sizeof(m.session));
+
+	curve25519_clamp_secret(m.private);
+
+	/* As in the draft:
+	 * When receiving such an array, implementations of curve25519
+	 * MUST mask the most-significant bit in the final byte. This
+	 * is done to preserve compatibility with point formats which
+	 * reserve the sign bit for use in other protocols and to
+	 * increase resistance to implementation fingerprinting
+	 */
+	m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1;
+
+	copy_eltfp25519_1w(Px, X1);
+	setzero_eltfp25519_1w(Pz);
+	setzero_eltfp25519_1w(Qx);
+	setzero_eltfp25519_1w(Qz);
+
+	Pz[0] = 1;
+	Qx[0] = 1;
+
+	/* main-loop */
+	prev = 0;
+	j = 62;
+	for (i = 3; i >= 0; --i) {
+		while (j >= 0) {
+			u64 bit = (key[i] >> j) & 0x1;
+			u64 swap = bit ^ prev;
+			prev = bit;
+
+			add_eltfp25519_1w_bmi2(A, X2, Z2);	/* A = (X2+Z2) */
+			sub_eltfp25519_1w(B, X2, Z2);		/* B = (X2-Z2) */
+			add_eltfp25519_1w_bmi2(C, X3, Z3);	/* C = (X3+Z3) */
+			sub_eltfp25519_1w(D, X3, Z3);		/* D = (X3-Z3) */
+			mul_eltfp25519_2w_bmi2(DACB, AB, DC);	/* [DA|CB] = [A|B]*[D|C] */
+
+			cselect(swap, A, C);
+			cselect(swap, B, D);
+
+			sqr_eltfp25519_2w_bmi2(AB);		/* [AA|BB] = [A^2|B^2] */
+			add_eltfp25519_1w_bmi2(X3, DA, CB);	/* X3 = (DA+CB) */
+			sub_eltfp25519_1w(Z3, DA, CB);		/* Z3 = (DA-CB) */
+			sqr_eltfp25519_2w_bmi2(X3Z3);		/* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */
+
+			copy_eltfp25519_1w(X2, B);		/* X2 = B^2 */
+			sub_eltfp25519_1w(Z2, A, B);		/* Z2 = E = AA-BB */
+
+			mul_a24_eltfp25519_1w(B, Z2);		/* B = a24*E */
+			add_eltfp25519_1w_bmi2(B, B, X2);	/* B = a24*E+B */
+			mul_eltfp25519_2w_bmi2(X2Z2, X2Z2, AB);	/* [X2|Z2] = [B|E]*[A|a24*E+B] */
+			mul_eltfp25519_1w_bmi2(Z3, Z3, X1);	/* Z3 = Z3*X1 */
+			--j;
+		}
+		j = 63;
+	}
+
+	inv_eltfp25519_1w_bmi2(A, Qz);
+	mul_eltfp25519_1w_bmi2((u64 *)shared, Qx, A);
+	fred_eltfp25519_1w((u64 *)shared);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+static void curve25519_bmi2_base(u8 session_key[CURVE25519_KEY_SIZE],
+				 const u8 private_key[CURVE25519_KEY_SIZE])
+{
+	struct {
+		u64 buffer[4 * NUM_WORDS_ELTFP25519];
+		u64 coordinates[4 * NUM_WORDS_ELTFP25519];
+		u64 workspace[4 * NUM_WORDS_ELTFP25519];
+		u8 private[CURVE25519_KEY_SIZE];
+	} __aligned(32) m;
+
+	const int ite[4] = { 64, 64, 64, 63 };
+	const int q = 3;
+	u64 swap = 1;
+
+	int i = 0, j = 0, k = 0;
+	u64 *const key = (u64 *)m.private;
+	u64 *const Ur1 = m.coordinates + 0;
+	u64 *const Zr1 = m.coordinates + 4;
+	u64 *const Ur2 = m.coordinates + 8;
+	u64 *const Zr2 = m.coordinates + 12;
+
+	u64 *const UZr1 = m.coordinates + 0;
+	u64 *const ZUr2 = m.coordinates + 8;
+
+	u64 *const A = m.workspace + 0;
+	u64 *const B = m.workspace + 4;
+	u64 *const C = m.workspace + 8;
+	u64 *const D = m.workspace + 12;
+
+	u64 *const AB = m.workspace + 0;
+	u64 *const CD = m.workspace + 8;
+
+	const u64 *const P = table_ladder_8k;
+
+	memcpy(m.private, private_key, sizeof(m.private));
+
+	curve25519_clamp_secret(m.private);
+
+	setzero_eltfp25519_1w(Ur1);
+	setzero_eltfp25519_1w(Zr1);
+	setzero_eltfp25519_1w(Zr2);
+	Ur1[0] = 1;
+	Zr1[0] = 1;
+	Zr2[0] = 1;
+
+	/* G-S */
+	Ur2[3] = 0x1eaecdeee27cab34UL;
+	Ur2[2] = 0xadc7a0b9235d48e2UL;
+	Ur2[1] = 0xbbf095ae14b2edf8UL;
+	Ur2[0] = 0x7e94e1fec82faabdUL;
+
+	/* main-loop */
+	j = q;
+	for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) {
+		while (j < ite[i]) {
+			u64 bit = (key[i] >> j) & 0x1;
+			k = (64 * i + j - q);
+			swap = swap ^ bit;
+			cswap(swap, Ur1, Ur2);
+			cswap(swap, Zr1, Zr2);
+			swap = bit;
+			/* Addition */
+			sub_eltfp25519_1w(B, Ur1, Zr1);		/* B = Ur1-Zr1 */
+			add_eltfp25519_1w_bmi2(A, Ur1, Zr1);	/* A = Ur1+Zr1 */
+			mul_eltfp25519_1w_bmi2(C, &P[4 * k], B);/* C = M0-B */
+			sub_eltfp25519_1w(B, A, C);		/* B = (Ur1+Zr1) - M*(Ur1-Zr1) */
+			add_eltfp25519_1w_bmi2(A, A, C);	/* A = (Ur1+Zr1) + M*(Ur1-Zr1) */
+			sqr_eltfp25519_2w_bmi2(AB);		/* A = A^2      |  B = B^2 */
+			mul_eltfp25519_2w_bmi2(UZr1, ZUr2, AB);	/* Ur1 = Zr2*A  |  Zr1 = Ur2*B */
+			++j;
+		}
+		j = 0;
+	}
+
+	/* Doubling */
+	for (i = 0; i < q; ++i) {
+		add_eltfp25519_1w_bmi2(A, Ur1, Zr1);	/*  A = Ur1+Zr1 */
+		sub_eltfp25519_1w(B, Ur1, Zr1);		/*  B = Ur1-Zr1 */
+		sqr_eltfp25519_2w_bmi2(AB);		/*  A = A**2     B = B**2 */
+		copy_eltfp25519_1w(C, B);		/*  C = B */
+		sub_eltfp25519_1w(B, A, B);		/*  B = A-B */
+		mul_a24_eltfp25519_1w(D, B);		/*  D = my_a24*B */
+		add_eltfp25519_1w_bmi2(D, D, C);	/*  D = D+C */
+		mul_eltfp25519_2w_bmi2(UZr1, AB, CD);	/*  Ur1 = A*B   Zr1 = Zr1*A */
+	}
+
+	/* Convert to affine coordinates */
+	inv_eltfp25519_1w_bmi2(A, Zr1);
+	mul_eltfp25519_1w_bmi2((u64 *)session_key, Ur1, A);
+	fred_eltfp25519_1w((u64 *)session_key);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+void curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE],
+		     const u8 secret[CURVE25519_KEY_SIZE],
+		     const u8 basepoint[CURVE25519_KEY_SIZE])
+{
+	if (static_branch_likely(&curve25519_use_adx))
+		curve25519_adx(mypublic, secret, basepoint);
+	else if (static_branch_likely(&curve25519_use_bmi2))
+		curve25519_bmi2(mypublic, secret, basepoint);
+	else
+		curve25519_generic(mypublic, secret, basepoint);
+}
+EXPORT_SYMBOL(curve25519_arch);
+
+void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE],
+			  const u8 secret[CURVE25519_KEY_SIZE])
+{
+	if (static_branch_likely(&curve25519_use_adx))
+		curve25519_adx_base(pub, secret);
+	else if (static_branch_likely(&curve25519_use_bmi2))
+		curve25519_bmi2_base(pub, secret);
+	else
+		curve25519_generic(pub, secret, curve25519_base_point);
+}
+EXPORT_SYMBOL(curve25519_base_arch);
+
+static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf,
+				 unsigned int len)
+{
+	u8 *secret = kpp_tfm_ctx(tfm);
+
+	if (!len)
+		curve25519_generate_secret(secret);
+	else if (len == CURVE25519_KEY_SIZE &&
+		 crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE))
+		memcpy(secret, buf, CURVE25519_KEY_SIZE);
+	else
+		return -EINVAL;
+	return 0;
+}
+
+static int curve25519_generate_public_key(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	const u8 *secret = kpp_tfm_ctx(tfm);
+	u8 buf[CURVE25519_KEY_SIZE];
+	int copied, nbytes;
+
+	if (req->src)
+		return -EINVAL;
+
+	curve25519_base_arch(buf, secret);
+
+	/* might want less than we've got */
+	nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+								nbytes),
+				     buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+	return 0;
+}
+
+static int curve25519_compute_shared_secret(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	const u8 *secret = kpp_tfm_ctx(tfm);
+	u8 public_key[CURVE25519_KEY_SIZE];
+	u8 buf[CURVE25519_KEY_SIZE];
+	int copied, nbytes;
+
+	if (!req->src)
+		return -EINVAL;
+
+	copied = sg_copy_to_buffer(req->src,
+				   sg_nents_for_len(req->src,
+						    CURVE25519_KEY_SIZE),
+				   public_key, CURVE25519_KEY_SIZE);
+	if (copied != CURVE25519_KEY_SIZE)
+		return -EINVAL;
+
+	curve25519_arch(buf, secret, public_key);
+
+	/* might want less than we've got */
+	nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+								nbytes),
+				     buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+	return 0;
+}
+
+static unsigned int curve25519_max_size(struct crypto_kpp *tfm)
+{
+	return CURVE25519_KEY_SIZE;
+}
+
+static struct kpp_alg curve25519_alg = {
+	.base.cra_name		= "curve25519",
+	.base.cra_driver_name	= "curve25519-x86",
+	.base.cra_priority	= 200,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_ctxsize	= CURVE25519_KEY_SIZE,
+
+	.set_secret		= curve25519_set_secret,
+	.generate_public_key	= curve25519_generate_public_key,
+	.compute_shared_secret	= curve25519_compute_shared_secret,
+	.max_size		= curve25519_max_size,
+};
+
+static int __init curve25519_mod_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_BMI2))
+		static_branch_enable(&curve25519_use_bmi2);
+	else if (boot_cpu_has(X86_FEATURE_ADX))
+		static_branch_enable(&curve25519_use_adx);
+	else
+		return 0;
+	return crypto_register_kpp(&curve25519_alg);
+}
+
+static void __exit curve25519_mod_exit(void)
+{
+	if (boot_cpu_has(X86_FEATURE_BMI2) ||
+	    boot_cpu_has(X86_FEATURE_ADX))
+		crypto_unregister_kpp(&curve25519_alg);
+}
+
+module_init(curve25519_mod_init);
+module_exit(curve25519_mod_exit);
+
+MODULE_ALIAS_CRYPTO("curve25519");
+MODULE_ALIAS_CRYPTO("curve25519-x86");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 4a1c05dce950..370cd88068ec 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -7,47 +7,23 @@
 
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
 #include <crypto/internal/simd.h>
-#include <crypto/poly1305.h>
 #include <linux/crypto.h>
+#include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <asm/simd.h>
 
-struct poly1305_simd_desc_ctx {
-	struct poly1305_desc_ctx base;
-	/* derived key u set? */
-	bool uset;
-#ifdef CONFIG_AS_AVX2
-	/* derived keys r^3, r^4 set? */
-	bool wset;
-#endif
-	/* derived Poly1305 key r^2 */
-	u32 u[5];
-	/* ... silently appended r^3 and r^4 when using AVX2 */
-};
-
 asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src,
 				    const u32 *r, unsigned int blocks);
 asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r,
 				     unsigned int blocks, const u32 *u);
-#ifdef CONFIG_AS_AVX2
 asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r,
 				     unsigned int blocks, const u32 *u);
-static bool poly1305_use_avx2;
-#endif
-
-static int poly1305_simd_init(struct shash_desc *desc)
-{
-	struct poly1305_simd_desc_ctx *sctx = shash_desc_ctx(desc);
 
-	sctx->uset = false;
-#ifdef CONFIG_AS_AVX2
-	sctx->wset = false;
-#endif
-
-	return crypto_poly1305_init(desc);
-}
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_simd);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2);
 
 static void poly1305_simd_mult(u32 *a, const u32 *b)
 {
@@ -60,72 +36,85 @@ static void poly1305_simd_mult(u32 *a, const u32 *b)
 	poly1305_block_sse2(a, m, b, 1);
 }
 
+static unsigned int poly1305_scalar_blocks(struct poly1305_desc_ctx *dctx,
+					   const u8 *src, unsigned int srclen)
+{
+	unsigned int datalen;
+
+	if (unlikely(!dctx->sset)) {
+		datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
+		src += srclen - datalen;
+		srclen = datalen;
+	}
+	if (srclen >= POLY1305_BLOCK_SIZE) {
+		poly1305_core_blocks(&dctx->h, dctx->r, src,
+				     srclen / POLY1305_BLOCK_SIZE, 1);
+		srclen %= POLY1305_BLOCK_SIZE;
+	}
+	return srclen;
+}
+
 static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
 					 const u8 *src, unsigned int srclen)
 {
-	struct poly1305_simd_desc_ctx *sctx;
 	unsigned int blocks, datalen;
 
-	BUILD_BUG_ON(offsetof(struct poly1305_simd_desc_ctx, base));
-	sctx = container_of(dctx, struct poly1305_simd_desc_ctx, base);
-
 	if (unlikely(!dctx->sset)) {
 		datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
 		src += srclen - datalen;
 		srclen = datalen;
 	}
 
-#ifdef CONFIG_AS_AVX2
-	if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) {
-		if (unlikely(!sctx->wset)) {
-			if (!sctx->uset) {
-				memcpy(sctx->u, dctx->r.r, sizeof(sctx->u));
-				poly1305_simd_mult(sctx->u, dctx->r.r);
-				sctx->uset = true;
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    static_branch_likely(&poly1305_use_avx2) &&
+	    srclen >= POLY1305_BLOCK_SIZE * 4) {
+		if (unlikely(dctx->rset < 4)) {
+			if (dctx->rset < 2) {
+				dctx->r[1] = dctx->r[0];
+				poly1305_simd_mult(dctx->r[1].r, dctx->r[0].r);
 			}
-			memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u));
-			poly1305_simd_mult(sctx->u + 5, dctx->r.r);
-			memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u));
-			poly1305_simd_mult(sctx->u + 10, dctx->r.r);
-			sctx->wset = true;
+			dctx->r[2] = dctx->r[1];
+			poly1305_simd_mult(dctx->r[2].r, dctx->r[0].r);
+			dctx->r[3] = dctx->r[2];
+			poly1305_simd_mult(dctx->r[3].r, dctx->r[0].r);
+			dctx->rset = 4;
 		}
 		blocks = srclen / (POLY1305_BLOCK_SIZE * 4);
-		poly1305_4block_avx2(dctx->h.h, src, dctx->r.r, blocks,
-				     sctx->u);
+		poly1305_4block_avx2(dctx->h.h, src, dctx->r[0].r, blocks,
+				     dctx->r[1].r);
 		src += POLY1305_BLOCK_SIZE * 4 * blocks;
 		srclen -= POLY1305_BLOCK_SIZE * 4 * blocks;
 	}
-#endif
+
 	if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) {
-		if (unlikely(!sctx->uset)) {
-			memcpy(sctx->u, dctx->r.r, sizeof(sctx->u));
-			poly1305_simd_mult(sctx->u, dctx->r.r);
-			sctx->uset = true;
+		if (unlikely(dctx->rset < 2)) {
+			dctx->r[1] = dctx->r[0];
+			poly1305_simd_mult(dctx->r[1].r, dctx->r[0].r);
+			dctx->rset = 2;
 		}
 		blocks = srclen / (POLY1305_BLOCK_SIZE * 2);
-		poly1305_2block_sse2(dctx->h.h, src, dctx->r.r, blocks,
-				     sctx->u);
+		poly1305_2block_sse2(dctx->h.h, src, dctx->r[0].r,
+				     blocks, dctx->r[1].r);
 		src += POLY1305_BLOCK_SIZE * 2 * blocks;
 		srclen -= POLY1305_BLOCK_SIZE * 2 * blocks;
 	}
 	if (srclen >= POLY1305_BLOCK_SIZE) {
-		poly1305_block_sse2(dctx->h.h, src, dctx->r.r, 1);
+		poly1305_block_sse2(dctx->h.h, src, dctx->r[0].r, 1);
 		srclen -= POLY1305_BLOCK_SIZE;
 	}
 	return srclen;
 }
 
-static int poly1305_simd_update(struct shash_desc *desc,
-				const u8 *src, unsigned int srclen)
+void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key)
 {
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-	unsigned int bytes;
-
-	/* kernel_fpu_begin/end is costly, use fallback for small updates */
-	if (srclen <= 288 || !crypto_simd_usable())
-		return crypto_poly1305_update(desc, src, srclen);
+	poly1305_init_generic(desc, key);
+}
+EXPORT_SYMBOL(poly1305_init_arch);
 
-	kernel_fpu_begin();
+void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
+			  unsigned int srclen)
+{
+	unsigned int bytes;
 
 	if (unlikely(dctx->buflen)) {
 		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
@@ -135,34 +124,84 @@ static int poly1305_simd_update(struct shash_desc *desc,
 		dctx->buflen += bytes;
 
 		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_simd_blocks(dctx, dctx->buf,
-					     POLY1305_BLOCK_SIZE);
+			if (static_branch_likely(&poly1305_use_simd) &&
+			    likely(crypto_simd_usable())) {
+				kernel_fpu_begin();
+				poly1305_simd_blocks(dctx, dctx->buf,
+						     POLY1305_BLOCK_SIZE);
+				kernel_fpu_end();
+			} else {
+				poly1305_scalar_blocks(dctx, dctx->buf,
+						       POLY1305_BLOCK_SIZE);
+			}
 			dctx->buflen = 0;
 		}
 	}
 
 	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
-		bytes = poly1305_simd_blocks(dctx, src, srclen);
+		if (static_branch_likely(&poly1305_use_simd) &&
+		    likely(crypto_simd_usable())) {
+			kernel_fpu_begin();
+			bytes = poly1305_simd_blocks(dctx, src, srclen);
+			kernel_fpu_end();
+		} else {
+			bytes = poly1305_scalar_blocks(dctx, src, srclen);
+		}
 		src += srclen - bytes;
 		srclen = bytes;
 	}
 
-	kernel_fpu_end();
-
 	if (unlikely(srclen)) {
 		dctx->buflen = srclen;
 		memcpy(dctx->buf, src, srclen);
 	}
+}
+EXPORT_SYMBOL(poly1305_update_arch);
+
+void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *digest)
+{
+	poly1305_final_generic(desc, digest);
+}
+EXPORT_SYMBOL(poly1305_final_arch);
+
+static int crypto_poly1305_init(struct shash_desc *desc)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	poly1305_core_init(&dctx->h);
+	dctx->buflen = 0;
+	dctx->rset = 0;
+	dctx->sset = false;
+
+	return 0;
+}
+
+static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (unlikely(!dctx->sset))
+		return -ENOKEY;
+
+	poly1305_final_generic(dctx, dst);
+	return 0;
+}
+
+static int poly1305_simd_update(struct shash_desc *desc,
+				const u8 *src, unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
 
+	poly1305_update_arch(dctx, src, srclen);
 	return 0;
 }
 
 static struct shash_alg alg = {
 	.digestsize	= POLY1305_DIGEST_SIZE,
-	.init		= poly1305_simd_init,
+	.init		= crypto_poly1305_init,
 	.update		= poly1305_simd_update,
 	.final		= crypto_poly1305_final,
-	.descsize	= sizeof(struct poly1305_simd_desc_ctx),
+	.descsize	= sizeof(struct poly1305_desc_ctx),
 	.base		= {
 		.cra_name		= "poly1305",
 		.cra_driver_name	= "poly1305-simd",
@@ -175,16 +214,16 @@ static struct shash_alg alg = {
 static int __init poly1305_simd_mod_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2))
-		return -ENODEV;
-
-#ifdef CONFIG_AS_AVX2
-	poly1305_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) &&
-			    boot_cpu_has(X86_FEATURE_AVX2) &&
-			    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
-	alg.descsize = sizeof(struct poly1305_simd_desc_ctx);
-	if (poly1305_use_avx2)
-		alg.descsize += 10 * sizeof(u32);
-#endif
+		return 0;
+
+	static_branch_enable(&poly1305_use_simd);
+
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_AVX2) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
+		static_branch_enable(&poly1305_use_avx2);
+
 	return crypto_register_shash(&alg);
 }
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index dc64b16e6b71..3be51aa06e67 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3324,8 +3324,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	return 0;
 }
 
+#ifdef CONFIG_RETPOLINE
+static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr);
+static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr);
+#endif
+
 struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
+#ifdef CONFIG_RETPOLINE
+	if (x86_pmu.guest_get_msrs == intel_guest_get_msrs)
+		return intel_guest_get_msrs(nr);
+	else if (x86_pmu.guest_get_msrs == core_guest_get_msrs)
+		return core_guest_get_msrs(nr);
+#endif
 	if (x86_pmu.guest_get_msrs)
 		return x86_pmu.guest_get_msrs(nr);
 	*nr = 0;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4fc61483919a..b79cd6aa4075 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -156,10 +156,8 @@ enum kvm_reg {
 	VCPU_REGS_R15 = __VCPU_REGS_R15,
 #endif
 	VCPU_REGS_RIP,
-	NR_VCPU_REGS
-};
+	NR_VCPU_REGS,
 
-enum kvm_reg_ex {
 	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
 	VCPU_EXREG_CR3,
 	VCPU_EXREG_RFLAGS,
@@ -454,6 +452,11 @@ struct kvm_pmc {
 	u64 eventsel;
 	struct perf_event *perf_event;
 	struct kvm_vcpu *vcpu;
+	/*
+	 * eventsel value for general purpose counters,
+	 * ctrl value for fixed counters.
+	 */
+	u64 current_config;
 };
 
 struct kvm_pmu {
@@ -472,7 +475,21 @@ struct kvm_pmu {
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
 	struct irq_work irq_work;
-	u64 reprogram_pmi;
+	DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+	DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
+	DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
+
+	/*
+	 * The gate to release perf_events not marked in
+	 * pmc_in_use only once in a vcpu time slice.
+	 */
+	bool need_cleanup;
+
+	/*
+	 * The total number of programmed perf_events and it helps to avoid
+	 * redundant check before cleanup if guest don't use vPMU at all.
+	 */
+	u8 event_count;
 };
 
 struct kvm_pmu_ops;
@@ -565,6 +582,7 @@ struct kvm_vcpu_arch {
 	u64 smbase;
 	u64 smi_count;
 	bool tpr_access_reporting;
+	bool xsaves_enabled;
 	u64 ia32_xss;
 	u64 microcode_version;
 	u64 arch_capabilities;
@@ -1041,7 +1059,6 @@ struct kvm_x86_ops {
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
 	void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
-	void (*decache_cr3)(struct kvm_vcpu *vcpu);
 	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -1090,7 +1107,7 @@ struct kvm_x86_ops {
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
-	bool (*get_enable_apicv)(struct kvm_vcpu *vcpu);
+	bool (*get_enable_apicv)(struct kvm *kvm);
 	void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
 	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
 	void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
@@ -1357,6 +1374,7 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 
 void kvm_enable_efer_bits(u64);
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
+int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data);
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data);
 int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu);
@@ -1577,6 +1595,8 @@ bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
 void kvm_make_mclock_inprogress_request(struct kvm *kvm);
 void kvm_make_scan_ioapic_request(struct kvm *kvm);
+void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
+				       unsigned long *vcpu_bitmap);
 
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6a3124664289..084e98da04a7 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -409,6 +409,8 @@
 #define MSR_AMD_PSTATE_DEF_BASE		0xc0010064
 #define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
+#define MSR_AMD_PPIN_CTL		0xc00102f0
+#define MSR_AMD_PPIN			0xc00102f1
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
 #define MSR_AMD64_BU_CFG2		0xc001102a
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0bc530c4eb13..ad97dc155195 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1463,6 +1463,12 @@ static inline bool arch_has_pfn_modify_check(void)
 	return boot_cpu_has_bug(X86_BUG_L1TF);
 }
 
+#define arch_faults_on_old_pte arch_faults_on_old_pte
+static inline bool arch_faults_on_old_pte(void)
+{
+	return false;
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 5e8319bb207a..23c626a742e8 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -26,10 +26,11 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define POKE_MAX_OPCODE_SIZE	5
 
 struct text_poke_loc {
-	void *detour;
 	void *addr;
-	size_t len;
-	const char opcode[POKE_MAX_OPCODE_SIZE];
+	int len;
+	s32 rel32;
+	u8 opcode;
+	const u8 text[POKE_MAX_OPCODE_SIZE];
 };
 
 extern void text_poke_early(void *addr, const void *opcode, size_t len);
@@ -51,8 +52,10 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len);
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_kgdb(void *addr, const void *opcode, 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, void *handler);
+extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate);
 extern void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries);
+extern void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
+			       const void *opcode, size_t len, const void *emulate);
 extern int after_bootmem;
 extern __ro_after_init struct mm_struct *poking_mm;
 extern __ro_after_init unsigned long poking_addr;
@@ -63,8 +66,17 @@ static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 
-#define INT3_INSN_SIZE 1
-#define CALL_INSN_SIZE 5
+#define INT3_INSN_SIZE		1
+#define INT3_INSN_OPCODE	0xCC
+
+#define CALL_INSN_SIZE		5
+#define CALL_INSN_OPCODE	0xE8
+
+#define JMP32_INSN_SIZE		5
+#define JMP32_INSN_OPCODE	0xE9
+
+#define JMP8_INSN_SIZE		2
+#define JMP8_INSN_OPCODE	0xEB
 
 static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
 {
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9d3a971ea364..9ec463fe96f2 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -956,16 +956,15 @@ NOKPROBE_SYMBOL(patch_cmp);
 int poke_int3_handler(struct pt_regs *regs)
 {
 	struct text_poke_loc *tp;
-	unsigned char int3 = 0xcc;
 	void *ip;
 
 	/*
 	 * Having observed our INT3 instruction, we now must observe
 	 * bp_patching.nr_entries.
 	 *
-	 * 	nr_entries != 0			INT3
-	 * 	WMB				RMB
-	 * 	write INT3			if (nr_entries)
+	 *	nr_entries != 0			INT3
+	 *	WMB				RMB
+	 *	write INT3			if (nr_entries)
 	 *
 	 * Idem for other elements in bp_patching.
 	 */
@@ -978,9 +977,9 @@ int poke_int3_handler(struct pt_regs *regs)
 		return 0;
 
 	/*
-	 * Discount the sizeof(int3). See text_poke_bp_batch().
+	 * Discount the INT3. See text_poke_bp_batch().
 	 */
-	ip = (void *) regs->ip - sizeof(int3);
+	ip = (void *) regs->ip - INT3_INSN_SIZE;
 
 	/*
 	 * Skip the binary search if there is a single member in the vector.
@@ -997,8 +996,28 @@ int poke_int3_handler(struct pt_regs *regs)
 			return 0;
 	}
 
-	/* set up the specified breakpoint detour */
-	regs->ip = (unsigned long) tp->detour;
+	ip += tp->len;
+
+	switch (tp->opcode) {
+	case INT3_INSN_OPCODE:
+		/*
+		 * Someone poked an explicit INT3, they'll want to handle it,
+		 * do not consume.
+		 */
+		return 0;
+
+	case CALL_INSN_OPCODE:
+		int3_emulate_call(regs, (long)ip + tp->rel32);
+		break;
+
+	case JMP32_INSN_OPCODE:
+	case JMP8_INSN_OPCODE:
+		int3_emulate_jmp(regs, (long)ip + tp->rel32);
+		break;
+
+	default:
+		BUG();
+	}
 
 	return 1;
 }
@@ -1014,7 +1033,7 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  * synchronization using int3 breakpoint.
  *
  * The way it is done:
- * 	- For each entry in the vector:
+ *	- For each entry in the vector:
  *		- add a int3 trap to the address that will be patched
  *	- sync cores
  *	- For each entry in the vector:
@@ -1027,9 +1046,9 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  */
 void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 {
-	int patched_all_but_first = 0;
-	unsigned char int3 = 0xcc;
+	unsigned char int3 = INT3_INSN_OPCODE;
 	unsigned int i;
+	int do_sync;
 
 	lockdep_assert_held(&text_mutex);
 
@@ -1053,16 +1072,16 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 	/*
 	 * Second step: update all but the first byte of the patched range.
 	 */
-	for (i = 0; i < nr_entries; i++) {
+	for (do_sync = 0, i = 0; i < nr_entries; i++) {
 		if (tp[i].len - sizeof(int3) > 0) {
 			text_poke((char *)tp[i].addr + sizeof(int3),
-				  (const char *)tp[i].opcode + sizeof(int3),
+				  (const char *)tp[i].text + sizeof(int3),
 				  tp[i].len - sizeof(int3));
-			patched_all_but_first++;
+			do_sync++;
 		}
 	}
 
-	if (patched_all_but_first) {
+	if (do_sync) {
 		/*
 		 * According to Intel, this core syncing is very likely
 		 * not necessary and we'd be safe even without it. But
@@ -1075,10 +1094,17 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 	 * Third step: replace the first byte (int3) by the first byte of
 	 * replacing opcode.
 	 */
-	for (i = 0; i < nr_entries; i++)
-		text_poke(tp[i].addr, tp[i].opcode, sizeof(int3));
+	for (do_sync = 0, i = 0; i < nr_entries; i++) {
+		if (tp[i].text[0] == INT3_INSN_OPCODE)
+			continue;
+
+		text_poke(tp[i].addr, tp[i].text, sizeof(int3));
+		do_sync++;
+	}
+
+	if (do_sync)
+		on_each_cpu(do_sync_core, NULL, 1);
 
-	on_each_cpu(do_sync_core, NULL, 1);
 	/*
 	 * sync_core() implies an smp_mb() and orders this store against
 	 * the writing of the new instruction.
@@ -1087,6 +1113,60 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 	bp_patching.nr_entries = 0;
 }
 
+void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
+			const void *opcode, size_t len, const void *emulate)
+{
+	struct insn insn;
+
+	if (!opcode)
+		opcode = (void *)tp->text;
+	else
+		memcpy((void *)tp->text, opcode, len);
+
+	if (!emulate)
+		emulate = opcode;
+
+	kernel_insn_init(&insn, emulate, MAX_INSN_SIZE);
+	insn_get_length(&insn);
+
+	BUG_ON(!insn_complete(&insn));
+	BUG_ON(len != insn.length);
+
+	tp->addr = addr;
+	tp->len = len;
+	tp->opcode = insn.opcode.bytes[0];
+
+	switch (tp->opcode) {
+	case INT3_INSN_OPCODE:
+		break;
+
+	case CALL_INSN_OPCODE:
+	case JMP32_INSN_OPCODE:
+	case JMP8_INSN_OPCODE:
+		tp->rel32 = insn.immediate.value;
+		break;
+
+	default: /* assume NOP */
+		switch (len) {
+		case 2: /* NOP2 -- emulate as JMP8+0 */
+			BUG_ON(memcmp(emulate, ideal_nops[len], len));
+			tp->opcode = JMP8_INSN_OPCODE;
+			tp->rel32 = 0;
+			break;
+
+		case 5: /* NOP5 -- emulate as JMP32+0 */
+			BUG_ON(memcmp(emulate, ideal_nops[NOP_ATOMIC5], len));
+			tp->opcode = JMP32_INSN_OPCODE;
+			tp->rel32 = 0;
+			break;
+
+		default: /* unknown instruction */
+			BUG();
+		}
+		break;
+	}
+}
+
 /**
  * text_poke_bp() -- update instructions on live kernel on SMP
  * @addr:	address to patch
@@ -1098,20 +1178,10 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
  * dynamically allocated memory. This function should be used when it is
  * not possible to allocate memory.
  */
-void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
 {
-	struct text_poke_loc tp = {
-		.detour = handler,
-		.addr = addr,
-		.len = len,
-	};
-
-	if (len > POKE_MAX_OPCODE_SIZE) {
-		WARN_ONCE(1, "len is larger than %d\n", POKE_MAX_OPCODE_SIZE);
-		return;
-	}
-
-	memcpy((void *)tp.opcode, opcode, len);
+	struct text_poke_loc tp;
 
+	text_poke_loc_init(&tp, addr, opcode, len, emulate);
 	text_poke_bp_batch(&tp, 1);
 }
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index a6ac3712db8b..4bbccb9d16dc 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -510,10 +510,9 @@ static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size)
 	iommu_size -= round_up(a, PMD_PAGE_SIZE) - a;
 
 	if (iommu_size < 64*1024*1024) {
-		pr_warning(
-			"PCI-DMA: Warning: Small IOMMU %luMB."
+		pr_warn("PCI-DMA: Warning: Small IOMMU %luMB."
 			" Consider increasing the AGP aperture in BIOS\n",
-				iommu_size >> 20);
+			iommu_size >> 20);
 	}
 
 	return iommu_size;
@@ -665,8 +664,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
 
  nommu:
 	/* Should not happen anymore */
-	pr_warning("PCI-DMA: More than 4GB of RAM and no IOMMU\n"
-	       "falling back to iommu=soft.\n");
+	pr_warn("PCI-DMA: More than 4GB of RAM and no IOMMU - falling back to iommu=soft.\n");
 	return -1;
 }
 
@@ -733,8 +731,8 @@ int __init gart_iommu_init(void)
 	    !gart_iommu_aperture ||
 	    (no_agp && init_amd_gatt(&info) < 0)) {
 		if (max_pfn > MAX_DMA32_PFN) {
-			pr_warning("More than 4GB of memory but GART IOMMU not available.\n");
-			pr_warning("falling back to iommu=soft.\n");
+			pr_warn("More than 4GB of memory but GART IOMMU not available.\n");
+			pr_warn("falling back to iommu=soft.\n");
 		}
 		return 0;
 	}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2b0faf86da1b..05feaec5d3d7 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -780,8 +780,8 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 
 	res = (((u64)deltapm) *  mult) >> 22;
 	do_div(res, 1000000);
-	pr_warning("APIC calibration not consistent "
-		   "with PM-Timer: %ldms instead of 100ms\n",(long)res);
+	pr_warn("APIC calibration not consistent "
+		"with PM-Timer: %ldms instead of 100ms\n", (long)res);
 
 	/* Correct the lapic counter value */
 	res = (((u64)(*delta)) * pm_100ms);
@@ -977,7 +977,7 @@ static int __init calibrate_APIC_clock(void)
 	 */
 	if (lapic_timer_period < (1000000 / HZ)) {
 		local_irq_enable();
-		pr_warning("APIC frequency too slow, disabling apic timer\n");
+		pr_warn("APIC frequency too slow, disabling apic timer\n");
 		return -1;
 	}
 
@@ -1021,7 +1021,7 @@ static int __init calibrate_APIC_clock(void)
 	local_irq_enable();
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
-		pr_warning("APIC timer disabled due to verification failure\n");
+		pr_warn("APIC timer disabled due to verification failure\n");
 		return -1;
 	}
 
@@ -1095,8 +1095,8 @@ static void local_apic_timer_interrupt(void)
 	 * spurious.
 	 */
 	if (!evt->event_handler) {
-		pr_warning("Spurious LAPIC timer interrupt on cpu %d\n",
-			   smp_processor_id());
+		pr_warn("Spurious LAPIC timer interrupt on cpu %d\n",
+			smp_processor_id());
 		/* Switch it off */
 		lapic_timer_shutdown(evt);
 		return;
@@ -1811,11 +1811,11 @@ static int __init setup_nox2apic(char *str)
 		int apicid = native_apic_msr_read(APIC_ID);
 
 		if (apicid >= 255) {
-			pr_warning("Apicid: %08x, cannot enforce nox2apic\n",
-				   apicid);
+			pr_warn("Apicid: %08x, cannot enforce nox2apic\n",
+				apicid);
 			return 0;
 		}
-		pr_warning("x2apic already enabled.\n");
+		pr_warn("x2apic already enabled.\n");
 		__x2apic_disable();
 	}
 	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
@@ -1983,7 +1983,7 @@ static int __init apic_verify(void)
 	 */
 	features = cpuid_edx(1);
 	if (!(features & (1 << X86_FEATURE_APIC))) {
-		pr_warning("Could not enable APIC!\n");
+		pr_warn("Could not enable APIC!\n");
 		return -1;
 	}
 	set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
@@ -2410,9 +2410,8 @@ int generic_processor_info(int apicid, int version)
 	    disabled_cpu_apicid == apicid) {
 		int thiscpu = num_processors + disabled_cpus;
 
-		pr_warning("APIC: Disabling requested cpu."
-			   " Processor %d/0x%x ignored.\n",
-			   thiscpu, apicid);
+		pr_warn("APIC: Disabling requested cpu."
+			" Processor %d/0x%x ignored.\n", thiscpu, apicid);
 
 		disabled_cpus++;
 		return -ENODEV;
@@ -2426,8 +2425,7 @@ int generic_processor_info(int apicid, int version)
 	    apicid != boot_cpu_physical_apicid) {
 		int thiscpu = max + disabled_cpus - 1;
 
-		pr_warning(
-			"APIC: NR_CPUS/possible_cpus limit of %i almost"
+		pr_warn("APIC: NR_CPUS/possible_cpus limit of %i almost"
 			" reached. Keeping one slot for boot cpu."
 			"  Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
 
@@ -2438,9 +2436,8 @@ int generic_processor_info(int apicid, int version)
 	if (num_processors >= nr_cpu_ids) {
 		int thiscpu = max + disabled_cpus;
 
-		pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
-			   "reached. Processor %d/0x%x ignored.\n",
-			   max, thiscpu, apicid);
+		pr_warn("APIC: NR_CPUS/possible_cpus limit of %i reached. "
+			"Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
 
 		disabled_cpus++;
 		return -EINVAL;
@@ -2470,13 +2467,13 @@ int generic_processor_info(int apicid, int version)
 	 * Validate version
 	 */
 	if (version == 0x0) {
-		pr_warning("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n",
-			   cpu, apicid);
+		pr_warn("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n",
+			cpu, apicid);
 		version = 0x10;
 	}
 
 	if (version != boot_cpu_apic_version) {
-		pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
+		pr_warn("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
 			boot_cpu_apic_version, cpu, version);
 	}
 
@@ -2845,7 +2842,7 @@ static int __init apic_set_verbosity(char *arg)
 		apic_verbosity = APIC_VERBOSE;
 #ifdef CONFIG_X86_64
 	else {
-		pr_warning("APIC Verbosity level %s not recognised"
+		pr_warn("APIC Verbosity level %s not recognised"
 			" use apic=verbose or apic=debug\n", arg);
 		return -EINVAL;
 	}
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 6ea7fdc82f3c..5167bd2bb6b1 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -583,7 +583,7 @@ bool amd_filter_mce(struct mce *m)
  * - Prevent possible spurious interrupts from the IF bank on Family 0x17
  *   Models 0x10-0x2F due to Erratum #1114.
  */
-void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
+static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 {
 	int i, num_msrs;
 	u64 hwcr;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 743370ee4983..5f42f25bac8f 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -488,8 +488,9 @@ int mce_usable_address(struct mce *m)
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
-	/* Checks after this one are Intel-specific: */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	/* Checks after this one are Intel/Zhaoxin-specific: */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 1;
 
 	if (!(m->status & MCI_STATUS_MISCV))
@@ -507,10 +508,13 @@ EXPORT_SYMBOL_GPL(mce_usable_address);
 
 bool mce_is_memory_error(struct mce *m)
 {
-	if (m->cpuvendor == X86_VENDOR_AMD ||
-	    m->cpuvendor == X86_VENDOR_HYGON) {
+	switch (m->cpuvendor) {
+	case X86_VENDOR_AMD:
+	case X86_VENDOR_HYGON:
 		return amd_mce_is_memory_error(m);
-	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
+
+	case X86_VENDOR_INTEL:
+	case X86_VENDOR_ZHAOXIN:
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
 		 *
@@ -527,9 +531,10 @@ bool mce_is_memory_error(struct mce *m)
 		return (m->status & 0xef80) == BIT(7) ||
 		       (m->status & 0xef00) == BIT(8) ||
 		       (m->status & 0xeffc) == 0xc;
-	}
 
-	return false;
+	default:
+		return false;
+	}
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
@@ -1127,6 +1132,12 @@ static bool __mc_check_crashing_cpu(int cpu)
 		u64 mcgstatus;
 
 		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) {
+			if (mcgstatus & MCG_STATUS_LMCES)
+				return false;
+		}
+
 		if (mcgstatus & MCG_STATUS_RIPV) {
 			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 			return true;
@@ -1277,9 +1288,10 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	/*
 	 * Check if this MCE is signaled to only this logical processor,
-	 * on Intel only.
+	 * on Intel, Zhaoxin only.
 	 */
-	if (m.cpuvendor == X86_VENDOR_INTEL)
+	if (m.cpuvendor == X86_VENDOR_INTEL ||
+	    m.cpuvendor == X86_VENDOR_ZHAOXIN)
 		lmce = m.mcgstatus & MCG_STATUS_LMCES;
 
 	/*
@@ -1697,6 +1709,18 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		if (c->x86 == 6 && c->x86_model == 45)
 			quirk_no_way_out = quirk_sandybridge_ifu;
 	}
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+		 * synchronization with a one second timeout.
+		 */
+		if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+			if (cfg->monarch_timeout < 0)
+				cfg->monarch_timeout = USEC_PER_SEC;
+		}
+	}
+
 	if (cfg->monarch_timeout < 0)
 		cfg->monarch_timeout = 0;
 	if (cfg->bootlog != 0)
@@ -1760,6 +1784,35 @@ static void mce_centaur_feature_init(struct cpuinfo_x86 *c)
 	}
 }
 
+static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c)
+{
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+
+	/*
+	 * These CPUs have MCA bank 8 which reports only one error type called
+	 * SVAD (System View Address Decoder). The reporting of that error is
+	 * controlled by IA32_MC8.CTL.0.
+	 *
+	 * If enabled, prefetching on these CPUs will cause SVAD MCE when
+	 * virtual machines start and result in a system  panic. Always disable
+	 * bank 8 SVAD error by default.
+	 */
+	if ((c->x86 == 7 && c->x86_model == 0x1b) ||
+	    (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+		if (this_cpu_read(mce_num_banks) > 8)
+			mce_banks[8].ctl = 0;
+	}
+
+	intel_init_cmci();
+	intel_init_lmce();
+	mce_adjust_timer = cmci_intel_adjust_timer;
+}
+
+static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c)
+{
+	intel_clear_lmce();
+}
+
 static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 {
 	switch (c->x86_vendor) {
@@ -1781,6 +1834,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_centaur_feature_init(c);
 		break;
 
+	case X86_VENDOR_ZHAOXIN:
+		mce_zhaoxin_feature_init(c);
+		break;
+
 	default:
 		break;
 	}
@@ -1792,6 +1849,11 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
 	case X86_VENDOR_INTEL:
 		mce_intel_feature_clear(c);
 		break;
+
+	case X86_VENDOR_ZHAOXIN:
+		mce_zhaoxin_feature_clear(c);
+		break;
+
 	default:
 		break;
 	}
@@ -2014,15 +2076,16 @@ static void mce_disable_error_reporting(void)
 static void vendor_disable_error_reporting(void)
 {
 	/*
-	 * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs
-	 * are socket-wide.
-	 * Disabling them for just a single offlined CPU is bad, since it will
-	 * inhibit reporting for all shared resources on the socket like the
-	 * last level cache (LLC), the integrated memory controller (iMC), etc.
+	 * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these
+	 * MSRs are socket-wide. Disabling them for just a single offlined CPU
+	 * is bad, since it will inhibit reporting for all shared resources on
+	 * the socket like the last level cache (LLC), the integrated memory
+	 * controller (iMC), etc.
 	 */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN)
 		return;
 
 	mce_disable_error_reporting();
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 88cd9598fa57..e270d0770134 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -85,8 +85,10 @@ static int cmci_supported(int *banks)
 	 * initialization is vendor keyed and this
 	 * makes sure none of the backdoors are entered otherwise.
 	 */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 0;
+
 	if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
 		return 0;
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
@@ -423,7 +425,7 @@ void cmci_disable_bank(int bank)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
-static void intel_init_cmci(void)
+void intel_init_cmci(void)
 {
 	int banks;
 
@@ -442,7 +444,7 @@ static void intel_init_cmci(void)
 	cmci_recheck();
 }
 
-static void intel_init_lmce(void)
+void intel_init_lmce(void)
 {
 	u64 val;
 
@@ -455,7 +457,7 @@ static void intel_init_lmce(void)
 		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
 }
 
-static void intel_clear_lmce(void)
+void intel_clear_lmce(void)
 {
 	u64 val;
 
@@ -482,6 +484,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
 	case INTEL_FAM6_BROADWELL_D:
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_ICELAKE_X:
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
 
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 43031db429d2..842b273bce31 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -45,11 +45,17 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval);
 bool mce_intel_cmci_poll(void);
 void mce_intel_hcpu_update(unsigned long cpu);
 void cmci_disable_bank(int bank);
+void intel_init_cmci(void);
+void intel_init_lmce(void);
+void intel_clear_lmce(void);
 #else
 # define cmci_intel_adjust_timer mce_adjust_timer_default
 static inline bool mce_intel_cmci_poll(void) { return false; }
 static inline void mce_intel_hcpu_update(unsigned long cpu) { }
 static inline void cmci_disable_bank(int bank) { }
+static inline void intel_init_cmci(void) { }
+static inline void intel_init_lmce(void) { }
+static inline void intel_clear_lmce(void) { }
 #endif
 
 void mce_timer_kick(unsigned long interval);
diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index 6e2becf547c5..d01e0da0163a 100644
--- a/arch/x86/kernel/cpu/mce/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -40,15 +40,58 @@
 #define THERMAL_THROTTLING_EVENT	0
 #define POWER_LIMIT_EVENT		1
 
-/*
- * Current thermal event state:
+/**
+ * struct _thermal_state - Represent the current thermal event state
+ * @next_check:			Stores the next timestamp, when it is allowed
+ *				to log the next warning message.
+ * @last_interrupt_time:	Stores the timestamp for the last threshold
+ *				high event.
+ * @therm_work:			Delayed workqueue structure
+ * @count:			Stores the current running count for thermal
+ *				or power threshold interrupts.
+ * @last_count:			Stores the previous running count for thermal
+ *				or power threshold interrupts.
+ * @max_time_ms:		This shows the maximum amount of time CPU was
+ *				in throttled state for a single thermal
+ *				threshold high to low state.
+ * @total_time_ms:		This is a cumulative time during which CPU was
+ *				in the throttled state.
+ * @rate_control_active:	Set when a throttling message is logged.
+ *				This is used for the purpose of rate-control.
+ * @new_event:			Stores the last high/low status of the
+ *				THERM_STATUS_PROCHOT or
+ *				THERM_STATUS_POWER_LIMIT.
+ * @level:			Stores whether this _thermal_state instance is
+ *				for a CORE level or for PACKAGE level.
+ * @sample_index:		Index for storing the next sample in the buffer
+ *				temp_samples[].
+ * @sample_count:		Total number of samples collected in the buffer
+ *				temp_samples[].
+ * @average:			The last moving average of temperature samples
+ * @baseline_temp:		Temperature at which thermal threshold high
+ *				interrupt was generated.
+ * @temp_samples:		Storage for temperature samples to calculate
+ *				moving average.
+ *
+ * This structure is used to represent data related to thermal state for a CPU.
+ * There is a separate storage for core and package level for each CPU.
  */
 struct _thermal_state {
-	bool			new_event;
-	int			event;
 	u64			next_check;
+	u64			last_interrupt_time;
+	struct delayed_work	therm_work;
 	unsigned long		count;
 	unsigned long		last_count;
+	unsigned long		max_time_ms;
+	unsigned long		total_time_ms;
+	bool			rate_control_active;
+	bool			new_event;
+	u8			level;
+	u8			sample_index;
+	u8			sample_count;
+	u8			average;
+	u8			baseline_temp;
+	u8			temp_samples[3];
 };
 
 struct thermal_state {
@@ -121,8 +164,22 @@ define_therm_throt_device_one_ro(package_throttle_count);
 define_therm_throt_device_show_func(package_power_limit, count);
 define_therm_throt_device_one_ro(package_power_limit_count);
 
+define_therm_throt_device_show_func(core_throttle, max_time_ms);
+define_therm_throt_device_one_ro(core_throttle_max_time_ms);
+
+define_therm_throt_device_show_func(package_throttle, max_time_ms);
+define_therm_throt_device_one_ro(package_throttle_max_time_ms);
+
+define_therm_throt_device_show_func(core_throttle, total_time_ms);
+define_therm_throt_device_one_ro(core_throttle_total_time_ms);
+
+define_therm_throt_device_show_func(package_throttle, total_time_ms);
+define_therm_throt_device_one_ro(package_throttle_total_time_ms);
+
 static struct attribute *thermal_throttle_attrs[] = {
 	&dev_attr_core_throttle_count.attr,
+	&dev_attr_core_throttle_max_time_ms.attr,
+	&dev_attr_core_throttle_total_time_ms.attr,
 	NULL
 };
 
@@ -135,6 +192,105 @@ static const struct attribute_group thermal_attr_group = {
 #define CORE_LEVEL	0
 #define PACKAGE_LEVEL	1
 
+#define THERM_THROT_POLL_INTERVAL	HZ
+#define THERM_STATUS_PROCHOT_LOG	BIT(1)
+
+static void clear_therm_status_log(int level)
+{
+	int msr;
+	u64 msr_val;
+
+	if (level == CORE_LEVEL)
+		msr = MSR_IA32_THERM_STATUS;
+	else
+		msr = MSR_IA32_PACKAGE_THERM_STATUS;
+
+	rdmsrl(msr, msr_val);
+	wrmsrl(msr, msr_val & ~THERM_STATUS_PROCHOT_LOG);
+}
+
+static void get_therm_status(int level, bool *proc_hot, u8 *temp)
+{
+	int msr;
+	u64 msr_val;
+
+	if (level == CORE_LEVEL)
+		msr = MSR_IA32_THERM_STATUS;
+	else
+		msr = MSR_IA32_PACKAGE_THERM_STATUS;
+
+	rdmsrl(msr, msr_val);
+	if (msr_val & THERM_STATUS_PROCHOT_LOG)
+		*proc_hot = true;
+	else
+		*proc_hot = false;
+
+	*temp = (msr_val >> 16) & 0x7F;
+}
+
+static void throttle_active_work(struct work_struct *work)
+{
+	struct _thermal_state *state = container_of(to_delayed_work(work),
+						struct _thermal_state, therm_work);
+	unsigned int i, avg, this_cpu = smp_processor_id();
+	u64 now = get_jiffies_64();
+	bool hot;
+	u8 temp;
+
+	get_therm_status(state->level, &hot, &temp);
+	/* temperature value is offset from the max so lesser means hotter */
+	if (!hot && temp > state->baseline_temp) {
+		if (state->rate_control_active)
+			pr_info("CPU%d: %s temperature/speed normal (total events = %lu)\n",
+				this_cpu,
+				state->level == CORE_LEVEL ? "Core" : "Package",
+				state->count);
+
+		state->rate_control_active = false;
+		return;
+	}
+
+	if (time_before64(now, state->next_check) &&
+			  state->rate_control_active)
+		goto re_arm;
+
+	state->next_check = now + CHECK_INTERVAL;
+
+	if (state->count != state->last_count) {
+		/* There was one new thermal interrupt */
+		state->last_count = state->count;
+		state->average = 0;
+		state->sample_count = 0;
+		state->sample_index = 0;
+	}
+
+	state->temp_samples[state->sample_index] = temp;
+	state->sample_count++;
+	state->sample_index = (state->sample_index + 1) % ARRAY_SIZE(state->temp_samples);
+	if (state->sample_count < ARRAY_SIZE(state->temp_samples))
+		goto re_arm;
+
+	avg = 0;
+	for (i = 0; i < ARRAY_SIZE(state->temp_samples); ++i)
+		avg += state->temp_samples[i];
+
+	avg /= ARRAY_SIZE(state->temp_samples);
+
+	if (state->average > avg) {
+		pr_warn("CPU%d: %s temperature is above threshold, cpu clock is throttled (total events = %lu)\n",
+			this_cpu,
+			state->level == CORE_LEVEL ? "Core" : "Package",
+			state->count);
+		state->rate_control_active = true;
+	}
+
+	state->average = avg;
+
+re_arm:
+	clear_therm_status_log(state->level);
+	schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL);
+}
+
 /***
  * therm_throt_process - Process thermal throttling event from interrupt
  * @curr: Whether the condition is current or not (boolean), since the
@@ -178,27 +334,33 @@ static void therm_throt_process(bool new_event, int event, int level)
 	if (new_event)
 		state->count++;
 
-	if (time_before64(now, state->next_check) &&
-			state->count != state->last_count)
+	if (event != THERMAL_THROTTLING_EVENT)
 		return;
 
-	state->next_check = now + CHECK_INTERVAL;
-	state->last_count = state->count;
+	if (new_event && !state->last_interrupt_time) {
+		bool hot;
+		u8 temp;
+
+		get_therm_status(state->level, &hot, &temp);
+		/*
+		 * Ignore short temperature spike as the system is not close
+		 * to PROCHOT. 10C offset is large enough to ignore. It is
+		 * already dropped from the high threshold temperature.
+		 */
+		if (temp > 10)
+			return;
 
-	/* if we just entered the thermal event */
-	if (new_event) {
-		if (event == THERMAL_THROTTLING_EVENT)
-			pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
-				this_cpu,
-				level == CORE_LEVEL ? "Core" : "Package",
-				state->count);
-		return;
-	}
-	if (old_event) {
-		if (event == THERMAL_THROTTLING_EVENT)
-			pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
-				level == CORE_LEVEL ? "Core" : "Package");
-		return;
+		state->baseline_temp = temp;
+		state->last_interrupt_time = now;
+		schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL);
+	} else if (old_event && state->last_interrupt_time) {
+		unsigned long throttle_time;
+
+		throttle_time = jiffies_delta_to_msecs(now - state->last_interrupt_time);
+		if (throttle_time > state->max_time_ms)
+			state->max_time_ms = throttle_time;
+		state->total_time_ms += throttle_time;
+		state->last_interrupt_time = 0;
 	}
 }
 
@@ -244,20 +406,47 @@ static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu)
 	if (err)
 		return err;
 
-	if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
+	if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) {
 		err = sysfs_add_file_to_group(&dev->kobj,
 					      &dev_attr_core_power_limit_count.attr,
 					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+	}
+
 	if (cpu_has(c, X86_FEATURE_PTS)) {
 		err = sysfs_add_file_to_group(&dev->kobj,
 					      &dev_attr_package_throttle_count.attr,
 					      thermal_attr_group.name);
-		if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
+		if (err)
+			goto del_group;
+
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_package_throttle_max_time_ms.attr,
+					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_package_throttle_total_time_ms.attr,
+					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+
+		if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) {
 			err = sysfs_add_file_to_group(&dev->kobj,
 					&dev_attr_package_power_limit_count.attr,
 					thermal_attr_group.name);
+			if (err)
+				goto del_group;
+		}
 	}
 
+	return 0;
+
+del_group:
+	sysfs_remove_group(&dev->kobj, &thermal_attr_group);
+
 	return err;
 }
 
@@ -269,15 +458,29 @@ static void thermal_throttle_remove_dev(struct device *dev)
 /* Get notified when a cpu comes on/off. Be hotplug friendly. */
 static int thermal_throttle_online(unsigned int cpu)
 {
+	struct thermal_state *state = &per_cpu(thermal_state, cpu);
 	struct device *dev = get_cpu_device(cpu);
 
+	state->package_throttle.level = PACKAGE_LEVEL;
+	state->core_throttle.level = CORE_LEVEL;
+
+	INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work);
+	INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work);
+
 	return thermal_throttle_add_dev(dev, cpu);
 }
 
 static int thermal_throttle_offline(unsigned int cpu)
 {
+	struct thermal_state *state = &per_cpu(thermal_state, cpu);
 	struct device *dev = get_cpu_device(cpu);
 
+	cancel_delayed_work(&state->package_throttle.therm_work);
+	cancel_delayed_work(&state->core_throttle.therm_work);
+
+	state->package_throttle.rate_control_active = false;
+	state->core_throttle.rate_control_active = false;
+
 	thermal_throttle_remove_dev(dev);
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index a0e52bd00ecc..3f6b137ef4e6 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -567,7 +567,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 void reload_ucode_amd(void)
 {
 	struct microcode_amd *mc;
-	u32 rev, dummy;
+	u32 rev, dummy __always_unused;
 
 	mc = (struct microcode_amd *)amd_ucode_patch;
 
@@ -673,7 +673,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 	struct ucode_cpu_info *uci;
 	struct ucode_patch *p;
 	enum ucode_state ret;
-	u32 rev, dummy;
+	u32 rev, dummy __always_unused;
 
 	BUG_ON(raw_smp_processor_id() != cpu);
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index cb0fdcaf1415..7019d4b2df0c 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -63,11 +63,6 @@ LIST_HEAD(microcode_cache);
  */
 static DEFINE_MUTEX(microcode_mutex);
 
-/*
- * Serialize late loading so that CPUs get updated one-by-one.
- */
-static DEFINE_RAW_SPINLOCK(update_lock);
-
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -566,11 +561,18 @@ static int __reload_late(void *info)
 	if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
 		return -1;
 
-	raw_spin_lock(&update_lock);
-	apply_microcode_local(&err);
-	raw_spin_unlock(&update_lock);
+	/*
+	 * On an SMT system, it suffices to load the microcode on one sibling of
+	 * the core because the microcode engine is shared between the threads.
+	 * Synchronization still needs to take place so that no concurrent
+	 * loading attempts happen on multiple threads of an SMT core. See
+	 * below.
+	 */
+	if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu)
+		apply_microcode_local(&err);
+	else
+		goto wait_for_siblings;
 
-	/* siblings return UCODE_OK because their engine got updated already */
 	if (err > UCODE_NFOUND) {
 		pr_warn("Error reloading microcode on CPU %d\n", cpu);
 		ret = -1;
@@ -578,14 +580,18 @@ static int __reload_late(void *info)
 		ret = 1;
 	}
 
+wait_for_siblings:
+	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC))
+		panic("Timeout during microcode update!\n");
+
 	/*
-	 * Increase the wait timeout to a safe value here since we're
-	 * serializing the microcode update and that could take a while on a
-	 * large number of CPUs. And that is fine as the *actual* timeout will
-	 * be determined by the last CPU finished updating and thus cut short.
+	 * At least one thread has completed update on each core.
+	 * For others, simply call the update to make sure the
+	 * per-cpu cpuinfo can be updated with right microcode
+	 * revision.
 	 */
-	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus()))
-		panic("Timeout during microcode update!\n");
+	if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu)
+		apply_microcode_local(&err);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index ce799cfe9434..6a99535d7f37 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -791,6 +791,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
 	struct microcode_intel *mc;
 	enum ucode_state ret;
 	static int prev_rev;
@@ -836,7 +837,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 		return UCODE_ERROR;
 	}
 
-	if (rev != prev_rev) {
+	if (bsp && rev != prev_rev) {
 		pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
 			rev,
 			mc->hdr.date & 0xffff,
@@ -852,7 +853,7 @@ out:
 	c->microcode	 = rev;
 
 	/* Update boot_cpu_data's revision too, if we're on the BSP: */
-	if (c->cpu_index == boot_cpu_data.cpu_index)
+	if (bsp)
 		boot_cpu_data.microcode = rev;
 
 	return ret;
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 044053235302..c1a8b9e71408 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -89,8 +89,7 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 		return;
 	}
 
-	text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE,
-		     (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
+	text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE, NULL);
 }
 
 void arch_jump_label_transform(struct jump_entry *entry,
@@ -147,11 +146,9 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
 	}
 
 	__jump_label_set_jump_code(entry, type,
-				   (union jump_code_union *) &tp->opcode, 0);
+				   (union jump_code_union *)&tp->text, 0);
 
-	tp->addr = entry_code;
-	tp->detour = entry_code + JUMP_LABEL_NOP_SIZE;
-	tp->len = JUMP_LABEL_NOP_SIZE;
+	text_poke_loc_init(tp, entry_code, NULL, JUMP_LABEL_NOP_SIZE, NULL);
 
 	tp_vec_nr++;
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index b348dd506d58..8900329c28a7 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -437,8 +437,7 @@ void arch_optimize_kprobes(struct list_head *oplist)
 		insn_buff[0] = RELATIVEJUMP_OPCODE;
 		*(s32 *)(&insn_buff[1]) = rel;
 
-		text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE,
-			     op->optinsn.insn);
+		text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, NULL);
 
 		list_del_init(&op->list);
 	}
@@ -448,12 +447,18 @@ void arch_optimize_kprobes(struct list_head *oplist)
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
 	u8 insn_buff[RELATIVEJUMP_SIZE];
+	u8 emulate_buff[RELATIVEJUMP_SIZE];
 
 	/* Set int3 to first byte for kprobes */
 	insn_buff[0] = BREAKPOINT_INSTRUCTION;
 	memcpy(insn_buff + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+
+	emulate_buff[0] = RELATIVEJUMP_OPCODE;
+	*(s32 *)(&emulate_buff[1]) = (s32)((long)op->optinsn.insn -
+			((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
 	text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE,
-		     op->optinsn.insn);
+		     emulate_buff);
 }
 
 /*
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index e820568ed4d5..32ef1ee733b7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -33,6 +33,7 @@
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
 #include <asm/tlb.h>
+#include <asm/cpuidle_haltpoll.h>
 
 static int kvmapf = 1;
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 86663874ef04..e6d7894ad127 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -207,8 +207,8 @@ void __init setup_per_cpu_areas(void)
 					    pcpu_cpu_distance,
 					    pcpu_fc_alloc, pcpu_fc_free);
 		if (rc < 0)
-			pr_warning("%s allocator failed (%d), falling back to page size\n",
-				   pcpu_fc_names[pcpu_chosen_fc], rc);
+			pr_warn("%s allocator failed (%d), falling back to page size\n",
+				pcpu_fc_names[pcpu_chosen_fc], rc);
 	}
 	if (rc < 0)
 		rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index a49fe1dcb47e..4c61f0713832 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -57,7 +57,7 @@ void __init tboot_probe(void)
 	 */
 	if (!e820__mapped_any(boot_params.tboot_addr,
 			     boot_params.tboot_addr, E820_TYPE_RESERVED)) {
-		pr_warning("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n");
+		pr_warn("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n");
 		return;
 	}
 
@@ -65,13 +65,12 @@ void __init tboot_probe(void)
 	set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr);
 	tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE);
 	if (memcmp(&tboot_uuid, &tboot->uuid, sizeof(tboot->uuid))) {
-		pr_warning("tboot at 0x%llx is invalid\n",
-			   boot_params.tboot_addr);
+		pr_warn("tboot at 0x%llx is invalid\n", boot_params.tboot_addr);
 		tboot = NULL;
 		return;
 	}
 	if (tboot->version < 5) {
-		pr_warning("tboot version is invalid: %u\n", tboot->version);
+		pr_warn("tboot version is invalid: %u\n", tboot->version);
 		tboot = NULL;
 		return;
 	}
@@ -289,7 +288,7 @@ static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
 
 	if (sleep_state >= ACPI_S_STATE_COUNT ||
 	    acpi_shutdown_map[sleep_state] == -1) {
-		pr_warning("unsupported sleep state 0x%x\n", sleep_state);
+		pr_warn("unsupported sleep state 0x%x\n", sleep_state);
 		return -1;
 	}
 
@@ -302,7 +301,7 @@ static int tboot_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b)
 	if (!tboot_enabled())
 		return 0;
 
-	pr_warning("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)");
+	pr_warn("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)");
 	return -ENODEV;
 }
 
@@ -320,7 +319,7 @@ static int tboot_wait_for_aps(int num_aps)
 	}
 
 	if (timeout)
-		pr_warning("tboot wait for APs timeout\n");
+		pr_warn("tboot wait for APs timeout\n");
 
 	return !(atomic_read((atomic_t *)&tboot->num_in_wfs) == num_aps);
 }
@@ -516,7 +515,7 @@ int tboot_force_iommu(void)
 		return 1;
 
 	if (no_iommu || swiotlb || dmar_disabled)
-		pr_warning("Forcing Intel-IOMMU to enabled\n");
+		pr_warn("Forcing Intel-IOMMU to enabled\n");
 
 	dmar_disabled = 0;
 #ifdef CONFIG_SWIOTLB
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index ec534f978867..b8acf639abd1 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -364,12 +364,12 @@ retry:
 		/* Force it to 0 if random warps brought us here */
 		atomic_set(&test_runs, 0);
 
-		pr_warning("TSC synchronization [CPU#%d -> CPU#%d]:\n",
+		pr_warn("TSC synchronization [CPU#%d -> CPU#%d]:\n",
 			smp_processor_id(), cpu);
-		pr_warning("Measured %Ld cycles TSC warp between CPUs, "
-			   "turning off TSC clock.\n", max_warp);
+		pr_warn("Measured %Ld cycles TSC warp between CPUs, "
+			"turning off TSC clock.\n", max_warp);
 		if (random_warps)
-			pr_warning("TSC warped randomly between CPUs\n");
+			pr_warn("TSC warped randomly between CPUs\n");
 		mark_tsc_unstable("check_tsc_sync_source failed");
 	}
 
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 548fefed71ee..b4a304893189 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -91,7 +91,7 @@ const char * const umip_insns[5] = {
 
 #define umip_pr_err(regs, fmt, ...) \
 	umip_printk(regs, KERN_ERR, fmt, ##__VA_ARGS__)
-#define umip_pr_warning(regs, fmt, ...) \
+#define umip_pr_warn(regs, fmt, ...) \
 	umip_printk(regs, KERN_WARNING, fmt,  ##__VA_ARGS__)
 
 /**
@@ -380,14 +380,14 @@ bool fixup_umip_exception(struct pt_regs *regs)
 	if (umip_inst < 0)
 		return false;
 
-	umip_pr_warning(regs, "%s instruction cannot be used by applications.\n",
+	umip_pr_warn(regs, "%s instruction cannot be used by applications.\n",
 			umip_insns[umip_inst]);
 
 	/* Do not emulate (spoof) SLDT or STR. */
 	if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT)
 		return false;
 
-	umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n");
+	umip_pr_warn(regs, "For now, expensive software emulation returns the result.\n");
 
 	if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size,
 			      user_64bit_mode(regs)))
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 31ecf7a76d5a..b19ef421084d 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -8,9 +8,9 @@ kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
-kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
+kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
-			   hyperv.o page_track.o debugfs.o
+			   hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o
 kvm-amd-y		+= svm.o pmu_amd.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index f68c0c753c38..c0aa07487eb8 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -816,8 +816,6 @@ static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func,
 	return __do_cpuid_func(entry, func, nent, maxnent);
 }
 
-#undef F
-
 struct kvm_cpuid_param {
 	u32 func;
 	bool (*qualifier)(const struct kvm_cpuid_param *param);
@@ -1015,6 +1013,12 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 		*ebx = entry->ebx;
 		*ecx = entry->ecx;
 		*edx = entry->edx;
+		if (function == 7 && index == 0) {
+			u64 data;
+		        if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) &&
+			    (data & TSX_CTRL_CPUID_CLEAR))
+				*ebx &= ~(F(RTM) | F(HLE));
+		}
 	} else {
 		*eax = *ebx = *ecx = *edx = 0;
 		/*
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 698efb8c3897..952d1a4f4d7e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2770,11 +2770,10 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 		return emulate_ud(ctxt);
 
 	ops->get_msr(ctxt, MSR_EFER, &efer);
-	setup_syscalls_segments(ctxt, &cs, &ss);
-
 	if (!(efer & EFER_SCE))
 		return emulate_ud(ctxt);
 
+	setup_syscalls_segments(ctxt, &cs, &ss);
 	ops->get_msr(ctxt, MSR_STAR, &msr_data);
 	msr_data >>= 32;
 	cs_sel = (u16)(msr_data & 0xfffc);
@@ -2838,12 +2837,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->mode == X86EMUL_MODE_PROT64)
 		return X86EMUL_UNHANDLEABLE;
 
-	setup_syscalls_segments(ctxt, &cs, &ss);
-
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
 	if ((msr_data & 0xfffc) == 0x0)
 		return emulate_gp(ctxt, 0);
 
+	setup_syscalls_segments(ctxt, &cs, &ss);
 	ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
 	cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK;
 	ss_sel = cs_sel + 8;
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index d859ae8890d0..9fd2dd89a1c5 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -271,8 +271,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
 	bool mask_before, mask_after;
-	int old_remote_irr, old_delivery_status;
 	union kvm_ioapic_redirect_entry *e;
+	unsigned long vcpu_bitmap;
+	int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode;
 
 	switch (ioapic->ioregsel) {
 	case IOAPIC_REG_VERSION:
@@ -296,6 +297,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		/* Preserve read-only fields */
 		old_remote_irr = e->fields.remote_irr;
 		old_delivery_status = e->fields.delivery_status;
+		old_dest_id = e->fields.dest_id;
+		old_dest_mode = e->fields.dest_mode;
 		if (ioapic->ioregsel & 1) {
 			e->bits &= 0xffffffff;
 			e->bits |= (u64) val << 32;
@@ -321,7 +324,34 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
 		    && ioapic->irr & (1 << index))
 			ioapic_service(ioapic, index, false);
-		kvm_make_scan_ioapic_request(ioapic->kvm);
+		if (e->fields.delivery_mode == APIC_DM_FIXED) {
+			struct kvm_lapic_irq irq;
+
+			irq.shorthand = 0;
+			irq.vector = e->fields.vector;
+			irq.delivery_mode = e->fields.delivery_mode << 8;
+			irq.dest_id = e->fields.dest_id;
+			irq.dest_mode = e->fields.dest_mode;
+			bitmap_zero(&vcpu_bitmap, 16);
+			kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
+						 &vcpu_bitmap);
+			if (old_dest_mode != e->fields.dest_mode ||
+			    old_dest_id != e->fields.dest_id) {
+				/*
+				 * Update vcpu_bitmap with vcpus specified in
+				 * the previous request as well. This is done to
+				 * keep ioapic_handled_vectors synchronized.
+				 */
+				irq.dest_id = old_dest_id;
+				irq.dest_mode = old_dest_mode;
+				kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
+							 &vcpu_bitmap);
+			}
+			kvm_make_scan_ioapic_request_mask(ioapic->kvm,
+							  &vcpu_bitmap);
+		} else {
+			kvm_make_scan_ioapic_request(ioapic->kvm);
+		}
 		break;
 	}
 }
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 1cc6c47dc77e..58767020de41 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -37,22 +37,50 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14)
 BUILD_KVM_GPR_ACCESSORS(r15, R15)
 #endif
 
-static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
-					      enum kvm_reg reg)
+static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
+					     enum kvm_reg reg)
 {
-	if (!test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail))
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
+					 enum kvm_reg reg)
+{
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
+					       enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
+					   enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg)
+{
+	if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS))
+		return 0;
+
+	if (!kvm_register_is_available(vcpu, reg))
 		kvm_x86_ops->cache_reg(vcpu, reg);
 
 	return vcpu->arch.regs[reg];
 }
 
-static inline void kvm_register_write(struct kvm_vcpu *vcpu,
-				      enum kvm_reg reg,
+static inline void kvm_register_write(struct kvm_vcpu *vcpu, int reg,
 				      unsigned long val)
 {
+	if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS))
+		return;
+
 	vcpu->arch.regs[reg] = val;
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	kvm_register_mark_dirty(vcpu, reg);
 }
 
 static inline unsigned long kvm_rip_read(struct kvm_vcpu *vcpu)
@@ -79,9 +107,8 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
 {
 	might_sleep();  /* on svm */
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_avail))
-		kvm_x86_ops->cache_reg(vcpu, (enum kvm_reg)VCPU_EXREG_PDPTR);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR))
+		kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR);
 
 	return vcpu->arch.walk_mmu->pdptrs[index];
 }
@@ -109,8 +136,8 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask)
 
 static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu)
 {
-	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
-		kvm_x86_ops->decache_cr3(vcpu);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3))
+		kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_CR3);
 	return vcpu->arch.cr3;
 }
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b29d00b661ff..cf9177b4a07f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -557,60 +557,53 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
 			irq->level, irq->trig_mode, dest_map);
 }
 
+static int __pv_send_ipi(unsigned long *ipi_bitmap, struct kvm_apic_map *map,
+			 struct kvm_lapic_irq *irq, u32 min)
+{
+	int i, count = 0;
+	struct kvm_vcpu *vcpu;
+
+	if (min > map->max_apic_id)
+		return 0;
+
+	for_each_set_bit(i, ipi_bitmap,
+		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
+		if (map->phys_map[min + i]) {
+			vcpu = map->phys_map[min + i]->vcpu;
+			count += kvm_apic_set_irq(vcpu, irq, NULL);
+		}
+	}
+
+	return count;
+}
+
 int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
 		    unsigned long ipi_bitmap_high, u32 min,
 		    unsigned long icr, int op_64_bit)
 {
-	int i;
 	struct kvm_apic_map *map;
-	struct kvm_vcpu *vcpu;
 	struct kvm_lapic_irq irq = {0};
 	int cluster_size = op_64_bit ? 64 : 32;
-	int count = 0;
+	int count;
+
+	if (icr & (APIC_DEST_MASK | APIC_SHORT_MASK))
+		return -KVM_EINVAL;
 
 	irq.vector = icr & APIC_VECTOR_MASK;
 	irq.delivery_mode = icr & APIC_MODE_MASK;
 	irq.level = (icr & APIC_INT_ASSERT) != 0;
 	irq.trig_mode = icr & APIC_INT_LEVELTRIG;
 
-	if (icr & APIC_DEST_MASK)
-		return -KVM_EINVAL;
-	if (icr & APIC_SHORT_MASK)
-		return -KVM_EINVAL;
-
 	rcu_read_lock();
 	map = rcu_dereference(kvm->arch.apic_map);
 
-	if (unlikely(!map)) {
-		count = -EOPNOTSUPP;
-		goto out;
-	}
-
-	if (min > map->max_apic_id)
-		goto out;
-	/* Bits above cluster_size are masked in the caller.  */
-	for_each_set_bit(i, &ipi_bitmap_low,
-		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
-		if (map->phys_map[min + i]) {
-			vcpu = map->phys_map[min + i]->vcpu;
-			count += kvm_apic_set_irq(vcpu, &irq, NULL);
-		}
+	count = -EOPNOTSUPP;
+	if (likely(map)) {
+		count = __pv_send_ipi(&ipi_bitmap_low, map, &irq, min);
+		min += cluster_size;
+		count += __pv_send_ipi(&ipi_bitmap_high, map, &irq, min);
 	}
 
-	min += cluster_size;
-
-	if (min > map->max_apic_id)
-		goto out;
-
-	for_each_set_bit(i, &ipi_bitmap_high,
-		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
-		if (map->phys_map[min + i]) {
-			vcpu = map->phys_map[min + i]->vcpu;
-			count += kvm_apic_set_irq(vcpu, &irq, NULL);
-		}
-	}
-
-out:
 	rcu_read_unlock();
 	return count;
 }
@@ -1124,6 +1117,50 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	return result;
 }
 
+/*
+ * This routine identifies the destination vcpus mask meant to receive the
+ * IOAPIC interrupts. It either uses kvm_apic_map_get_dest_lapic() to find
+ * out the destination vcpus array and set the bitmap or it traverses to
+ * each available vcpu to identify the same.
+ */
+void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			      unsigned long *vcpu_bitmap)
+{
+	struct kvm_lapic **dest_vcpu = NULL;
+	struct kvm_lapic *src = NULL;
+	struct kvm_apic_map *map;
+	struct kvm_vcpu *vcpu;
+	unsigned long bitmap;
+	int i, vcpu_idx;
+	bool ret;
+
+	rcu_read_lock();
+	map = rcu_dereference(kvm->arch.apic_map);
+
+	ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dest_vcpu,
+					  &bitmap);
+	if (ret) {
+		for_each_set_bit(i, &bitmap, 16) {
+			if (!dest_vcpu[i])
+				continue;
+			vcpu_idx = dest_vcpu[i]->vcpu->vcpu_idx;
+			__set_bit(vcpu_idx, vcpu_bitmap);
+		}
+	} else {
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			if (!kvm_apic_present(vcpu))
+				continue;
+			if (!kvm_apic_match_dest(vcpu, NULL,
+						 irq->delivery_mode,
+						 irq->dest_id,
+						 irq->dest_mode))
+				continue;
+			__set_bit(i, vcpu_bitmap);
+		}
+	}
+	rcu_read_unlock();
+}
+
 int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 {
 	return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
@@ -2709,7 +2746,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	 * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs
 	 * and leave the INIT pending.
 	 */
-	if (is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu)) {
+	if (kvm_vcpu_latch_init(vcpu)) {
 		WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED);
 		if (test_bit(KVM_APIC_SIPI, &apic->pending_events))
 			clear_bit(KVM_APIC_SIPI, &apic->pending_events);
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 1f5014852e20..39925afdfcdc 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -226,6 +226,9 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
 
 void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu);
 
+void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			      unsigned long *vcpu_bitmap);
+
 bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu);
 int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2ce9da58611e..6f92b40d798c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4395,7 +4395,7 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3,
 			kvm_make_request(KVM_REQ_LOAD_CR3, vcpu);
 			if (!skip_tlb_flush) {
 				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
-				kvm_x86_ops->tlb_flush(vcpu, true);
+				kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 			}
 
 			/*
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 3521e2d176f2..3521e2d176f2 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 97b21e7fd013..97b21e7fd013 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 46875bbd0419..d5e6d5b3f06f 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -62,8 +62,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 
-	if (!test_and_set_bit(pmc->idx,
-			      (unsigned long *)&pmu->reprogram_pmi)) {
+	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 	}
@@ -76,8 +75,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 
-	if (!test_and_set_bit(pmc->idx,
-			      (unsigned long *)&pmu->reprogram_pmi)) {
+	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 
@@ -137,7 +135,37 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 	}
 
 	pmc->perf_event = event;
-	clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi);
+	pmc_to_pmu(pmc)->event_count++;
+	clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
+}
+
+static void pmc_pause_counter(struct kvm_pmc *pmc)
+{
+	u64 counter = pmc->counter;
+
+	if (!pmc->perf_event)
+		return;
+
+	/* update counter, reset event value to avoid redundant accumulation */
+	counter += perf_event_pause(pmc->perf_event, true);
+	pmc->counter = counter & pmc_bitmask(pmc);
+}
+
+static bool pmc_resume_counter(struct kvm_pmc *pmc)
+{
+	if (!pmc->perf_event)
+		return false;
+
+	/* recalibrate sample period and check if it's accepted by perf core */
+	if (perf_event_period(pmc->perf_event,
+			(-pmc->counter) & pmc_bitmask(pmc)))
+		return false;
+
+	/* reuse perf_event to serve as pmc_reprogram_counter() does*/
+	perf_event_enable(pmc->perf_event);
+
+	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
+	return true;
 }
 
 void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
@@ -154,7 +182,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
 	pmc->eventsel = eventsel;
 
-	pmc_stop_counter(pmc);
+	pmc_pause_counter(pmc);
 
 	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
 		return;
@@ -193,6 +221,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	if (type == PERF_TYPE_RAW)
 		config = eventsel & X86_RAW_EVENT_MASK;
 
+	if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
+		return;
+
+	pmc_release_perf_event(pmc);
+
+	pmc->current_config = eventsel;
 	pmc_reprogram_counter(pmc, type, config,
 			      !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
 			      !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
@@ -209,7 +243,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
 	struct kvm_pmu_event_filter *filter;
 	struct kvm *kvm = pmc->vcpu->kvm;
 
-	pmc_stop_counter(pmc);
+	pmc_pause_counter(pmc);
 
 	if (!en_field || !pmc_is_enabled(pmc))
 		return;
@@ -224,6 +258,12 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
 			return;
 	}
 
+	if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc))
+		return;
+
+	pmc_release_perf_event(pmc);
+
+	pmc->current_config = (u64)ctrl;
 	pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
 			      kvm_x86_ops->pmu_ops->find_fixed_event(idx),
 			      !(en_field & 0x2), /* exclude user */
@@ -253,27 +293,32 @@ EXPORT_SYMBOL_GPL(reprogram_counter);
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	u64 bitmask;
 	int bit;
 
-	bitmask = pmu->reprogram_pmi;
-
-	for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
+	for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
 		struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit);
 
 		if (unlikely(!pmc || !pmc->perf_event)) {
-			clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi);
+			clear_bit(bit, pmu->reprogram_pmi);
 			continue;
 		}
 
 		reprogram_counter(pmu, bit);
 	}
+
+	/*
+	 * Unused perf_events are only released if the corresponding MSRs
+	 * weren't accessed during the last vCPU time slice. kvm_arch_sched_in
+	 * triggers KVM_REQ_PMU if cleanup is needed.
+	 */
+	if (unlikely(pmu->need_cleanup))
+		kvm_pmu_cleanup(vcpu);
 }
 
 /* check if idx is a valid index to access PMU */
-int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
-	return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx);
+	return kvm_x86_ops->pmu_ops->is_valid_rdpmc_ecx(vcpu, idx);
 }
 
 bool is_vmware_backdoor_pmc(u32 pmc_idx)
@@ -323,7 +368,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 	if (is_vmware_backdoor_pmc(idx))
 		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
 
-	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask);
+	pmc = kvm_x86_ops->pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask);
 	if (!pmc)
 		return 1;
 
@@ -339,7 +384,17 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
 
 bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
-	return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+	return kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr) ||
+		kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+}
+
+static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr);
+
+	if (pmc)
+		__set_bit(pmc->idx, pmu->pmc_in_use);
 }
 
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
@@ -349,6 +404,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
+	kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index);
 	return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info);
 }
 
@@ -376,9 +432,45 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
 	memset(pmu, 0, sizeof(*pmu));
 	kvm_x86_ops->pmu_ops->init(vcpu);
 	init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
+	pmu->event_count = 0;
+	pmu->need_cleanup = false;
 	kvm_pmu_refresh(vcpu);
 }
 
+static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+	if (pmc_is_fixed(pmc))
+		return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
+			pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3;
+
+	return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
+}
+
+/* Release perf_events for vPMCs that have been unused for a full time slice.  */
+void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc = NULL;
+	DECLARE_BITMAP(bitmask, X86_PMC_IDX_MAX);
+	int i;
+
+	pmu->need_cleanup = false;
+
+	bitmap_andnot(bitmask, pmu->all_valid_pmc_idx,
+		      pmu->pmc_in_use, X86_PMC_IDX_MAX);
+
+	for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) {
+		pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, i);
+
+		if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc))
+			pmc_stop_counter(pmc);
+	}
+
+	bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX);
+}
+
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_pmu_reset(vcpu);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 58265f761c3b..7ebb62326c14 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -25,9 +25,10 @@ struct kvm_pmu_ops {
 	unsigned (*find_fixed_event)(int idx);
 	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
 	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
-	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx,
-					  u64 *mask);
-	int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
+	struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu,
+		unsigned int idx, u64 *mask);
+	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr);
+	int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx);
 	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
@@ -55,12 +56,21 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 	return counter & pmc_bitmask(pmc);
 }
 
-static inline void pmc_stop_counter(struct kvm_pmc *pmc)
+static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
 {
 	if (pmc->perf_event) {
-		pmc->counter = pmc_read_counter(pmc);
 		perf_event_release_kernel(pmc->perf_event);
 		pmc->perf_event = NULL;
+		pmc->current_config = 0;
+		pmc_to_pmu(pmc)->event_count--;
+	}
+}
+
+static inline void pmc_stop_counter(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event) {
+		pmc->counter = pmc_read_counter(pmc);
+		pmc_release_perf_event(pmc);
 	}
 }
 
@@ -79,6 +89,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc)
 	return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc);
 }
 
+static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu,
+						 u64 data)
+{
+	return !(pmu->global_ctrl_mask & data);
+}
+
 /* returns general purpose PMC with the specified MSR. Note that it can be
  * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a
  * paramenter to tell them apart.
@@ -110,13 +126,14 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
 void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
-int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx);
+int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx);
 bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
 void kvm_pmu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_init(struct kvm_vcpu *vcpu);
+void kvm_pmu_cleanup(struct kvm_vcpu *vcpu);
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp);
 
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index c8388389a3b0..ce0b10fe5e2b 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -174,7 +174,7 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 }
 
 /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
-static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
@@ -184,7 +184,8 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 }
 
 /* idx is the ECX register of RDPMC instruction */
-static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask)
+static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
+	unsigned int idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *counters;
@@ -199,13 +200,19 @@ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u
 
 static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
+	/* All MSRs refer to exactly one PMC, so msr_idx_to_pmc is enough.  */
+	return false;
+}
+
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
+{
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	int ret = false;
+	struct kvm_pmc *pmc;
 
-	ret = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER) ||
-		get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
+	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
+	pmc = pmc ? pmc : get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
 
-	return ret;
+	return pmc;
 }
 
 static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
@@ -272,6 +279,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->nr_arch_fixed_counters = 0;
 	pmu->global_status = 0;
+	bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters);
 }
 
 static void amd_pmu_init(struct kvm_vcpu *vcpu)
@@ -285,6 +293,7 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
 		pmu->gp_counters[i].type = KVM_PMC_GP;
 		pmu->gp_counters[i].vcpu = vcpu;
 		pmu->gp_counters[i].idx = i;
+		pmu->gp_counters[i].current_config = 0;
 	}
 }
 
@@ -306,8 +315,9 @@ struct kvm_pmu_ops amd_pmu_ops = {
 	.find_fixed_event = amd_find_fixed_event,
 	.pmc_is_enabled = amd_pmc_is_enabled,
 	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
+	.rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = amd_msr_idx_to_pmc,
-	.is_valid_msr_idx = amd_is_valid_msr_idx,
+	.is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx,
 	.is_valid_msr = amd_is_valid_msr,
 	.get_msr = amd_pmu_get_msr,
 	.set_msr = amd_pmu_set_msr,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c5673bda4b66..362e874297e4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -38,6 +38,7 @@
 #include <linux/file.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
+#include <linux/rwsem.h>
 
 #include <asm/apic.h>
 #include <asm/perf_event.h>
@@ -418,9 +419,13 @@ enum {
 
 #define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL
 
+static int sev_flush_asids(void);
+static DECLARE_RWSEM(sev_deactivate_lock);
+static DEFINE_MUTEX(sev_bitmap_lock);
 static unsigned int max_sev_asid;
 static unsigned int min_sev_asid;
 static unsigned long *sev_asid_bitmap;
+static unsigned long *sev_reclaim_asid_bitmap;
 #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
 
 struct enc_region {
@@ -1235,11 +1240,15 @@ static __init int sev_hardware_setup(void)
 	/* Minimum ASID value that should be used for SEV guest */
 	min_sev_asid = cpuid_edx(0x8000001F);
 
-	/* Initialize SEV ASID bitmap */
+	/* Initialize SEV ASID bitmaps */
 	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
 	if (!sev_asid_bitmap)
 		return 1;
 
+	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+	if (!sev_reclaim_asid_bitmap)
+		return 1;
+
 	status = kmalloc(sizeof(*status), GFP_KERNEL);
 	if (!status)
 		return 1;
@@ -1418,8 +1427,12 @@ static __exit void svm_hardware_unsetup(void)
 {
 	int cpu;
 
-	if (svm_sev_enabled())
+	if (svm_sev_enabled()) {
 		bitmap_free(sev_asid_bitmap);
+		bitmap_free(sev_reclaim_asid_bitmap);
+
+		sev_flush_asids();
+	}
 
 	for_each_possible_cpu(cpu)
 		svm_cpu_uninit(cpu);
@@ -1729,25 +1742,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static void __sev_asid_free(int asid)
+static void sev_asid_free(int asid)
 {
 	struct svm_cpu_data *sd;
 	int cpu, pos;
 
+	mutex_lock(&sev_bitmap_lock);
+
 	pos = asid - 1;
-	clear_bit(pos, sev_asid_bitmap);
+	__set_bit(pos, sev_reclaim_asid_bitmap);
 
 	for_each_possible_cpu(cpu) {
 		sd = per_cpu(svm_data, cpu);
 		sd->sev_vmcbs[pos] = NULL;
 	}
-}
 
-static void sev_asid_free(struct kvm *kvm)
-{
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-
-	__sev_asid_free(sev->asid);
+	mutex_unlock(&sev_bitmap_lock);
 }
 
 static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
@@ -1764,10 +1774,12 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 
 	/* deactivate handle */
 	data->handle = handle;
+
+	/* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */
+	down_read(&sev_deactivate_lock);
 	sev_guest_deactivate(data, NULL);
+	up_read(&sev_deactivate_lock);
 
-	wbinvd_on_all_cpus();
-	sev_guest_df_flush(NULL);
 	kfree(data);
 
 	decommission = kzalloc(sizeof(*decommission), GFP_KERNEL);
@@ -1916,7 +1928,7 @@ static void sev_vm_destroy(struct kvm *kvm)
 	mutex_unlock(&kvm->lock);
 
 	sev_unbind_asid(kvm, sev->handle);
-	sev_asid_free(kvm);
+	sev_asid_free(sev->asid);
 }
 
 static void avic_vm_destroy(struct kvm *kvm)
@@ -2370,7 +2382,7 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
 		break;
 	default:
-		BUG();
+		WARN_ON_ONCE(1);
 	}
 }
 
@@ -2523,10 +2535,6 @@ static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 }
 
-static void svm_decache_cr3(struct kvm_vcpu *vcpu)
-{
-}
-
 static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 {
 }
@@ -4997,6 +5005,18 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
+#ifdef CONFIG_RETPOLINE
+	if (exit_code == SVM_EXIT_MSR)
+		return msr_interception(svm);
+	else if (exit_code == SVM_EXIT_VINTR)
+		return interrupt_window_interception(svm);
+	else if (exit_code == SVM_EXIT_INTR)
+		return intr_interception(svm);
+	else if (exit_code == SVM_EXIT_HLT)
+		return halt_interception(svm);
+	else if (exit_code == SVM_EXIT_NPF)
+		return npf_interception(svm);
+#endif
 	return svm_exit_handlers[exit_code](svm);
 }
 
@@ -5092,8 +5112,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm_nested_virtualize_tpr(vcpu) ||
-	    kvm_vcpu_apicv_active(vcpu))
+	if (svm_nested_virtualize_tpr(vcpu))
 		return;
 
 	clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
@@ -5110,9 +5129,9 @@ static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 	return;
 }
 
-static bool svm_get_enable_apicv(struct kvm_vcpu *vcpu)
+static bool svm_get_enable_apicv(struct kvm *kvm)
 {
-	return avic && irqchip_split(vcpu->kvm);
+	return avic && irqchip_split(kvm);
 }
 
 static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
@@ -5634,7 +5653,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 
 	clgi();
-	kvm_load_guest_xcr0(vcpu);
+	kvm_load_guest_xsave_state(vcpu);
 
 	if (lapic_in_kernel(vcpu) &&
 		vcpu->arch.apic->lapic_timer.timer_advance_ns)
@@ -5784,7 +5803,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(&svm->vcpu);
 
-	kvm_put_guest_xcr0(vcpu);
+	kvm_load_host_xsave_state(vcpu);
 	stgi();
 
 	/* Any pending NMI will happen here */
@@ -5893,6 +5912,9 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+				    boot_cpu_has(X86_FEATURE_XSAVES);
+
 	/* Update nrips enabled cache */
 	svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS);
 
@@ -5968,7 +5990,7 @@ static bool svm_mpx_supported(void)
 
 static bool svm_xsaves_supported(void)
 {
-	return false;
+	return boot_cpu_has(X86_FEATURE_XSAVES);
 }
 
 static bool svm_umip_emulated(void)
@@ -6270,18 +6292,73 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int sev_flush_asids(void)
+{
+	int ret, error;
+
+	/*
+	 * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail,
+	 * so it must be guarded.
+	 */
+	down_write(&sev_deactivate_lock);
+
+	wbinvd_on_all_cpus();
+	ret = sev_guest_df_flush(&error);
+
+	up_write(&sev_deactivate_lock);
+
+	if (ret)
+		pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error);
+
+	return ret;
+}
+
+/* Must be called with the sev_bitmap_lock held */
+static bool __sev_recycle_asids(void)
+{
+	int pos;
+
+	/* Check if there are any ASIDs to reclaim before performing a flush */
+	pos = find_next_bit(sev_reclaim_asid_bitmap,
+			    max_sev_asid, min_sev_asid - 1);
+	if (pos >= max_sev_asid)
+		return false;
+
+	if (sev_flush_asids())
+		return false;
+
+	bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
+		   max_sev_asid);
+	bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);
+
+	return true;
+}
+
 static int sev_asid_new(void)
 {
+	bool retry = true;
 	int pos;
 
+	mutex_lock(&sev_bitmap_lock);
+
 	/*
 	 * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid.
 	 */
+again:
 	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1);
-	if (pos >= max_sev_asid)
+	if (pos >= max_sev_asid) {
+		if (retry && __sev_recycle_asids()) {
+			retry = false;
+			goto again;
+		}
+		mutex_unlock(&sev_bitmap_lock);
 		return -EBUSY;
+	}
+
+	__set_bit(pos, sev_asid_bitmap);
+
+	mutex_unlock(&sev_bitmap_lock);
 
-	set_bit(pos, sev_asid_bitmap);
 	return pos + 1;
 }
 
@@ -6309,7 +6386,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return 0;
 
 e_free:
-	__sev_asid_free(asid);
+	sev_asid_free(asid);
 	return ret;
 }
 
@@ -6319,12 +6396,6 @@ static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
 	int asid = sev_get_asid(kvm);
 	int ret;
 
-	wbinvd_on_all_cpus();
-
-	ret = sev_guest_df_flush(error);
-	if (ret)
-		return ret;
-
 	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		return -ENOMEM;
@@ -7214,7 +7285,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.get_cpl = svm_get_cpl,
 	.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
 	.decache_cr0_guest_bits = svm_decache_cr0_guest_bits,
-	.decache_cr3 = svm_decache_cr3,
 	.decache_cr4_guest_bits = svm_decache_cr4_guest_bits,
 	.set_cr0 = svm_set_cr0,
 	.set_cr3 = svm_set_cr3,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0e7c9301fe86..4aea7d304beb 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -10,6 +10,7 @@
 #include "hyperv.h"
 #include "mmu.h"
 #include "nested.h"
+#include "pmu.h"
 #include "trace.h"
 #include "x86.h"
 
@@ -27,6 +28,16 @@ module_param(nested_early_check, bool, S_IRUGO);
 	failed;								\
 })
 
+#define SET_MSR_OR_WARN(vcpu, idx, data)				\
+({									\
+	bool failed = kvm_set_msr(vcpu, idx, data);			\
+	if (failed)							\
+		pr_warn_ratelimited(					\
+				"%s cannot write MSR (0x%x, 0x%llx)\n",	\
+				__func__, idx, data);			\
+	failed;								\
+})
+
 /*
  * Hyper-V requires all of these, so mark them as supported even though
  * they are just treated the same as all-context.
@@ -257,7 +268,7 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	vmx->nested.cached_shadow_vmcs12 = NULL;
 	/* Unpin physical memory we referred to in the vmcs02 */
 	if (vmx->nested.apic_access_page) {
-		kvm_release_page_dirty(vmx->nested.apic_access_page);
+		kvm_release_page_clean(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = NULL;
 	}
 	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
@@ -929,6 +940,57 @@ fail:
 	return i + 1;
 }
 
+static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu,
+					    u32 msr_index,
+					    u64 *data)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * If the L0 hypervisor stored a more accurate value for the TSC that
+	 * does not include the time taken for emulation of the L2->L1
+	 * VM-exit in L0, use the more accurate value.
+	 */
+	if (msr_index == MSR_IA32_TSC) {
+		int index = vmx_find_msr_index(&vmx->msr_autostore.guest,
+					       MSR_IA32_TSC);
+
+		if (index >= 0) {
+			u64 val = vmx->msr_autostore.guest.val[index].value;
+
+			*data = kvm_read_l1_tsc(vcpu, val);
+			return true;
+		}
+	}
+
+	if (kvm_get_msr(vcpu, msr_index, data)) {
+		pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__,
+			msr_index);
+		return false;
+	}
+	return true;
+}
+
+static bool read_and_check_msr_entry(struct kvm_vcpu *vcpu, u64 gpa, int i,
+				     struct vmx_msr_entry *e)
+{
+	if (kvm_vcpu_read_guest(vcpu,
+				gpa + i * sizeof(*e),
+				e, 2 * sizeof(u32))) {
+		pr_debug_ratelimited(
+			"%s cannot read MSR entry (%u, 0x%08llx)\n",
+			__func__, i, gpa + i * sizeof(*e));
+		return false;
+	}
+	if (nested_vmx_store_msr_check(vcpu, e)) {
+		pr_debug_ratelimited(
+			"%s check failed (%u, 0x%x, 0x%x)\n",
+			__func__, i, e->index, e->reserved);
+		return false;
+	}
+	return true;
+}
+
 static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 {
 	u64 data;
@@ -940,26 +1002,12 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 		if (unlikely(i >= max_msr_list_size))
 			return -EINVAL;
 
-		if (kvm_vcpu_read_guest(vcpu,
-					gpa + i * sizeof(e),
-					&e, 2 * sizeof(u32))) {
-			pr_debug_ratelimited(
-				"%s cannot read MSR entry (%u, 0x%08llx)\n",
-				__func__, i, gpa + i * sizeof(e));
+		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
 			return -EINVAL;
-		}
-		if (nested_vmx_store_msr_check(vcpu, &e)) {
-			pr_debug_ratelimited(
-				"%s check failed (%u, 0x%x, 0x%x)\n",
-				__func__, i, e.index, e.reserved);
-			return -EINVAL;
-		}
-		if (kvm_get_msr(vcpu, e.index, &data)) {
-			pr_debug_ratelimited(
-				"%s cannot read MSR (%u, 0x%x)\n",
-				__func__, i, e.index);
+
+		if (!nested_vmx_get_vmexit_msr_value(vcpu, e.index, &data))
 			return -EINVAL;
-		}
+
 		if (kvm_vcpu_write_guest(vcpu,
 					 gpa + i * sizeof(e) +
 					     offsetof(struct vmx_msr_entry, value),
@@ -973,6 +1021,60 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	return 0;
 }
 
+static bool nested_msr_store_list_has_msr(struct kvm_vcpu *vcpu, u32 msr_index)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	u32 count = vmcs12->vm_exit_msr_store_count;
+	u64 gpa = vmcs12->vm_exit_msr_store_addr;
+	struct vmx_msr_entry e;
+	u32 i;
+
+	for (i = 0; i < count; i++) {
+		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
+			return false;
+
+		if (e.index == msr_index)
+			return true;
+	}
+	return false;
+}
+
+static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu,
+					   u32 msr_index)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmx_msrs *autostore = &vmx->msr_autostore.guest;
+	bool in_vmcs12_store_list;
+	int msr_autostore_index;
+	bool in_autostore_list;
+	int last;
+
+	msr_autostore_index = vmx_find_msr_index(autostore, msr_index);
+	in_autostore_list = msr_autostore_index >= 0;
+	in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index);
+
+	if (in_vmcs12_store_list && !in_autostore_list) {
+		if (autostore->nr == NR_LOADSTORE_MSRS) {
+			/*
+			 * Emulated VMEntry does not fail here.  Instead a less
+			 * accurate value will be returned by
+			 * nested_vmx_get_vmexit_msr_value() using kvm_get_msr()
+			 * instead of reading the value from the vmcs02 VMExit
+			 * MSR-store area.
+			 */
+			pr_warn_ratelimited(
+				"Not enough msr entries in msr_autostore.  Can't add msr %x\n",
+				msr_index);
+			return;
+		}
+		last = autostore->nr++;
+		autostore->val[last].index = msr_index;
+	} else if (!in_vmcs12_store_list && in_autostore_list) {
+		last = --autostore->nr;
+		autostore->val[msr_autostore_index] = autostore->val[last];
+	}
+}
+
 static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	unsigned long invalid_mask;
@@ -1012,7 +1114,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
 		kvm_mmu_new_cr3(vcpu, cr3, false);
 
 	vcpu->arch.cr3 = cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	kvm_init_mmu(vcpu, false);
 
@@ -1024,7 +1126,9 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
  * populated by L2 differently than TLB entries populated
  * by L1.
  *
- * If L1 uses EPT, then TLB entries are tagged with different EPTP.
+ * If L0 uses EPT, L1 and L2 run with different EPTP because
+ * guest_mode is part of kvm_mmu_page_role. Thus, TLB entries
+ * are tagged with different EPTP.
  *
  * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
  * with different VPID (L1 entries are tagged with vmx->vpid
@@ -1034,7 +1138,7 @@ static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	return nested_cpu_has_ept(vmcs12) ||
+	return enable_ept ||
 	       (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
 }
 
@@ -2018,7 +2122,7 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
 	 * addresses are constant (for vmcs02), the counts can change based
 	 * on L2's behavior, e.g. switching to/from long mode.
 	 */
-	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+	vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val));
 	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
 	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
@@ -2073,6 +2177,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 	exec_control &= ~CPU_BASED_TPR_SHADOW;
 	exec_control |= vmcs12->cpu_based_vm_exec_control;
 
+	vmx->nested.l1_tpr_threshold = -1;
 	if (exec_control & CPU_BASED_TPR_SHADOW)
 		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
 #ifdef CONFIG_X86_64
@@ -2285,6 +2390,13 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
 	}
 
+	/*
+	 * Make sure the msr_autostore list is up to date before we set the
+	 * count in the vmcs02.
+	 */
+	prepare_vmx_msr_autostore_list(&vmx->vcpu, MSR_IA32_TSC);
+
+	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, vmx->msr_autostore.guest.nr);
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 
@@ -2381,9 +2493,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	if (nested_cpu_has_ept(vmcs12))
 		nested_ept_init_mmu_context(vcpu);
-	else if (nested_cpu_has2(vmcs12,
-				 SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
-		vmx_flush_tlb(vcpu, true);
 
 	/*
 	 * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
@@ -2418,6 +2527,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 				entry_failure_code))
 		return -EINVAL;
 
+	/*
+	 * Immediately write vmcs02.GUEST_CR3.  It will be propagated to vmcs12
+	 * on nested VM-Exit, which can occur without actually running L2 and
+	 * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with
+	 * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the
+	 * transition to HLT instead of running L2.
+	 */
+	if (enable_ept)
+		vmcs_writel(GUEST_CR3, vmcs12->guest_cr3);
+
 	/* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */
 	if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) &&
 	    is_pae_paging(vcpu)) {
@@ -2430,6 +2549,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (!enable_ept)
 		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+			    vmcs12->guest_ia32_perf_global_ctrl))
+		return -EINVAL;
+
 	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
 	kvm_rip_write(vcpu, vmcs12->guest_rip);
 	return 0;
@@ -2664,6 +2788,11 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(!kvm_pat_valid(vmcs12->host_ia32_pat)))
 		return -EINVAL;
 
+	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
+					   vmcs12->host_ia32_perf_global_ctrl)))
+		return -EINVAL;
+
 #ifdef CONFIG_X86_64
 	ia32e = !!(vcpu->arch.efer & EFER_LMA);
 #else
@@ -2779,6 +2908,11 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
+					   vmcs12->guest_ia32_perf_global_ctrl)))
+		return -EINVAL;
+
 	/*
 	 * If the load IA32_EFER VM-entry control is 1, the following checks
 	 * are performed on the field for the IA32_EFER MSR:
@@ -2933,7 +3067,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		 * to it so we can release it later.
 		 */
 		if (vmx->nested.apic_access_page) { /* shouldn't happen */
-			kvm_release_page_dirty(vmx->nested.apic_access_page);
+			kvm_release_page_clean(vmx->nested.apic_access_page);
 			vmx->nested.apic_access_page = NULL;
 		}
 		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
@@ -3461,6 +3595,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		if (block_nested_events)
 			return -EBUSY;
+		clear_bit(KVM_APIC_INIT, &apic->pending_events);
 		nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
 		return 0;
 	}
@@ -3864,8 +3999,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 		vcpu->arch.pat = vmcs12->host_ia32_pat;
 	}
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
-		vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
-			vmcs12->host_ia32_perf_global_ctrl);
+		SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+				vmcs12->host_ia32_perf_global_ctrl);
 
 	/* Set L1 segment info according to Intel SDM
 	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
@@ -3984,7 +4119,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 
 	nested_ept_uninit_mmu_context(vcpu);
 	vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	/*
 	 * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -4112,6 +4247,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+	if (vmx->nested.l1_tpr_threshold != -1)
+		vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold);
 
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
@@ -4119,15 +4256,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	if (vmx->nested.change_vmcs01_virtual_apic_mode) {
 		vmx->nested.change_vmcs01_virtual_apic_mode = false;
 		vmx_set_virtual_apic_mode(vcpu);
-	} else if (!nested_cpu_has_ept(vmcs12) &&
-		   nested_cpu_has2(vmcs12,
-				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb(vcpu, true);
 	}
 
 	/* Unpin physical memory we referred to in vmcs02 */
 	if (vmx->nested.apic_access_page) {
-		kvm_release_page_dirty(vmx->nested.apic_access_page);
+		kvm_release_page_clean(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = NULL;
 	}
 	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
@@ -4327,6 +4460,27 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 	return 0;
 }
 
+void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx;
+
+	if (!nested_vmx_allowed(vcpu))
+		return;
+
+	vmx = to_vmx(vcpu);
+	if (kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) {
+		vmx->nested.msrs.entry_ctls_high |=
+				VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		vmx->nested.msrs.exit_ctls_high |=
+				VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+	} else {
+		vmx->nested.msrs.entry_ctls_high &=
+				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		vmx->nested.msrs.exit_ctls_high &=
+				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+	}
+}
+
 static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
 {
 	gva_t gva;
@@ -5766,7 +5920,7 @@ error_guest_mode:
 	return ret;
 }
 
-void nested_vmx_vcpu_setup(void)
+void nested_vmx_set_vmcs_shadowing_bitmap(void)
 {
 	if (enable_shadow_vmcs) {
 		vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
@@ -6047,23 +6201,23 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 		init_vmcs_shadow_fields();
 	}
 
-	exit_handlers[EXIT_REASON_VMCLEAR]	= handle_vmclear,
-	exit_handlers[EXIT_REASON_VMLAUNCH]	= handle_vmlaunch,
-	exit_handlers[EXIT_REASON_VMPTRLD]	= handle_vmptrld,
-	exit_handlers[EXIT_REASON_VMPTRST]	= handle_vmptrst,
-	exit_handlers[EXIT_REASON_VMREAD]	= handle_vmread,
-	exit_handlers[EXIT_REASON_VMRESUME]	= handle_vmresume,
-	exit_handlers[EXIT_REASON_VMWRITE]	= handle_vmwrite,
-	exit_handlers[EXIT_REASON_VMOFF]	= handle_vmoff,
-	exit_handlers[EXIT_REASON_VMON]		= handle_vmon,
-	exit_handlers[EXIT_REASON_INVEPT]	= handle_invept,
-	exit_handlers[EXIT_REASON_INVVPID]	= handle_invvpid,
-	exit_handlers[EXIT_REASON_VMFUNC]	= handle_vmfunc,
+	exit_handlers[EXIT_REASON_VMCLEAR]	= handle_vmclear;
+	exit_handlers[EXIT_REASON_VMLAUNCH]	= handle_vmlaunch;
+	exit_handlers[EXIT_REASON_VMPTRLD]	= handle_vmptrld;
+	exit_handlers[EXIT_REASON_VMPTRST]	= handle_vmptrst;
+	exit_handlers[EXIT_REASON_VMREAD]	= handle_vmread;
+	exit_handlers[EXIT_REASON_VMRESUME]	= handle_vmresume;
+	exit_handlers[EXIT_REASON_VMWRITE]	= handle_vmwrite;
+	exit_handlers[EXIT_REASON_VMOFF]	= handle_vmoff;
+	exit_handlers[EXIT_REASON_VMON]		= handle_vmon;
+	exit_handlers[EXIT_REASON_INVEPT]	= handle_invept;
+	exit_handlers[EXIT_REASON_INVVPID]	= handle_invvpid;
+	exit_handlers[EXIT_REASON_VMFUNC]	= handle_vmfunc;
 
 	kvm_x86_ops->check_nested_events = vmx_check_nested_events;
 	kvm_x86_ops->get_nested_state = vmx_get_nested_state;
 	kvm_x86_ops->set_nested_state = vmx_set_nested_state;
-	kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages,
+	kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages;
 	kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs;
 	kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version;
 
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 6280f33e5fa6..fc874d4ead0f 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -21,7 +21,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 				bool apicv);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
-void nested_vmx_vcpu_setup(void);
+void nested_vmx_set_vmcs_shadowing_bitmap(void);
 void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
 enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 						     bool from_vmentry);
@@ -33,6 +33,7 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata);
 int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 			u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
+void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu);
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {
@@ -256,7 +257,7 @@ static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1)
 	return ((val & fixed1) | fixed0) == val;
 }
 
-static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+static inline bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
@@ -270,7 +271,7 @@ static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 	return fixed_bits_valid(val, fixed0, fixed1);
 }
 
-static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+static inline bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
@@ -278,7 +279,7 @@ static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 	return fixed_bits_valid(val, fixed0, fixed1);
 }
 
-static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
+static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr4_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr4_fixed1;
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 3e9c059099e9..7023138b1cb0 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -15,6 +15,7 @@
 #include "x86.h"
 #include "cpuid.h"
 #include "lapic.h"
+#include "nested.h"
 #include "pmu.h"
 
 static struct kvm_event_hw_type_mapping intel_arch_events[] = {
@@ -46,6 +47,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 		if (old_ctrl == new_ctrl)
 			continue;
 
+		__set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use);
 		reprogram_fixed_counter(pmc, new_ctrl, i);
 	}
 
@@ -111,7 +113,7 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 }
 
 /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
-static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+static int intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
@@ -122,8 +124,8 @@ static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 		(fixed && idx >= pmu->nr_arch_fixed_counters);
 }
 
-static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
-					    unsigned idx, u64 *mask)
+static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
+					    unsigned int idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
@@ -162,6 +164,18 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	return ret;
 }
 
+static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+
+	pmc = get_fixed_pmc(pmu, msr);
+	pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0);
+	pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0);
+
+	return pmc;
+}
+
 static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -223,7 +237,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_GLOBAL_CTRL:
 		if (pmu->global_ctrl == data)
 			return 0;
-		if (!(data & pmu->global_ctrl_mask)) {
+		if (kvm_valid_perf_global_ctrl(pmu, data)) {
 			global_ctrl_changed(pmu, data);
 			return 0;
 		}
@@ -317,6 +331,13 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
 	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
 		pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+
+	bitmap_set(pmu->all_valid_pmc_idx,
+		0, pmu->nr_arch_gp_counters);
+	bitmap_set(pmu->all_valid_pmc_idx,
+		INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters);
+
+	nested_vmx_pmu_entry_exit_ctls_update(vcpu);
 }
 
 static void intel_pmu_init(struct kvm_vcpu *vcpu)
@@ -328,12 +349,14 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 		pmu->gp_counters[i].type = KVM_PMC_GP;
 		pmu->gp_counters[i].vcpu = vcpu;
 		pmu->gp_counters[i].idx = i;
+		pmu->gp_counters[i].current_config = 0;
 	}
 
 	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
 		pmu->fixed_counters[i].type = KVM_PMC_FIXED;
 		pmu->fixed_counters[i].vcpu = vcpu;
 		pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
+		pmu->fixed_counters[i].current_config = 0;
 	}
 }
 
@@ -366,8 +389,9 @@ struct kvm_pmu_ops intel_pmu_ops = {
 	.find_fixed_event = intel_find_fixed_event,
 	.pmc_is_enabled = intel_pmc_is_enabled,
 	.pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
+	.rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = intel_msr_idx_to_pmc,
-	.is_valid_msr_idx = intel_is_valid_msr_idx,
+	.is_valid_rdpmc_ecx = intel_is_valid_rdpmc_ecx,
 	.is_valid_msr = intel_is_valid_msr,
 	.get_msr = intel_pmu_get_msr,
 	.set_msr = intel_pmu_set_msr,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 04a8212704c1..d175429c91b0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -106,8 +106,6 @@ module_param(enable_apicv, bool, S_IRUGO);
 static bool __read_mostly nested = 1;
 module_param(nested, bool, S_IRUGO);
 
-static u64 __read_mostly host_xss;
-
 bool __read_mostly enable_pml = 1;
 module_param_named(pml, enable_pml, bool, S_IRUGO);
 
@@ -450,6 +448,7 @@ const u32 vmx_msr_index[] = {
 	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
 #endif
 	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
+	MSR_IA32_TSX_CTRL,
 };
 
 #if IS_ENABLED(CONFIG_HYPERV)
@@ -638,6 +637,23 @@ struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
 	return NULL;
 }
 
+static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data)
+{
+	int ret = 0;
+
+	u64 old_msr_data = msr->data;
+	msr->data = data;
+	if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
+		preempt_disable();
+		ret = kvm_set_shared_msr(msr->index, msr->data,
+					 msr->mask);
+		preempt_enable();
+		if (ret)
+			msr->data = old_msr_data;
+	}
+	return ret;
+}
+
 void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
 {
 	vmcs_clear(loaded_vmcs->vmcs);
@@ -726,8 +742,8 @@ static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg,
 	bool ret;
 	u32 mask = 1 << (seg * SEG_FIELD_NR + field);
 
-	if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) {
-		vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS);
+	if (!kvm_register_is_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS)) {
+		kvm_register_mark_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS);
 		vmx->segment_cache.bitmask = 0;
 	}
 	ret = vmx->segment_cache.bitmask & mask;
@@ -835,7 +851,7 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 	vm_exit_controls_clearbit(vmx, exit);
 }
 
-static int find_msr(struct vmx_msrs *m, unsigned int msr)
+int vmx_find_msr_index(struct vmx_msrs *m, u32 msr)
 {
 	unsigned int i;
 
@@ -869,7 +885,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 		}
 		break;
 	}
-	i = find_msr(&m->guest, msr);
+	i = vmx_find_msr_index(&m->guest, msr);
 	if (i < 0)
 		goto skip_guest;
 	--m->guest.nr;
@@ -877,7 +893,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
 
 skip_guest:
-	i = find_msr(&m->host, msr);
+	i = vmx_find_msr_index(&m->host, msr);
 	if (i < 0)
 		return;
 
@@ -936,12 +952,12 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	i = find_msr(&m->guest, msr);
+	i = vmx_find_msr_index(&m->guest, msr);
 	if (!entry_only)
-		j = find_msr(&m->host, msr);
+		j = vmx_find_msr_index(&m->host, msr);
 
-	if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) ||
-		(j < 0 &&  m->host.nr == NR_AUTOLOAD_MSRS)) {
+	if ((i < 0 && m->guest.nr == NR_LOADSTORE_MSRS) ||
+		(j < 0 &&  m->host.nr == NR_LOADSTORE_MSRS)) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
@@ -1418,35 +1434,44 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
 
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long rflags, save_rflags;
 
-	if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) {
-		__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_RFLAGS)) {
+		kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS);
 		rflags = vmcs_readl(GUEST_RFLAGS);
-		if (to_vmx(vcpu)->rmode.vm86_active) {
+		if (vmx->rmode.vm86_active) {
 			rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
-			save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+			save_rflags = vmx->rmode.save_rflags;
 			rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
 		}
-		to_vmx(vcpu)->rflags = rflags;
+		vmx->rflags = rflags;
 	}
-	return to_vmx(vcpu)->rflags;
+	return vmx->rflags;
 }
 
 void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
-	unsigned long old_rflags = vmx_get_rflags(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long old_rflags;
 
-	__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
-	to_vmx(vcpu)->rflags = rflags;
-	if (to_vmx(vcpu)->rmode.vm86_active) {
-		to_vmx(vcpu)->rmode.save_rflags = rflags;
+	if (enable_unrestricted_guest) {
+		kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS);
+		vmx->rflags = rflags;
+		vmcs_writel(GUEST_RFLAGS, rflags);
+		return;
+	}
+
+	old_rflags = vmx_get_rflags(vcpu);
+	vmx->rflags = rflags;
+	if (vmx->rmode.vm86_active) {
+		vmx->rmode.save_rflags = rflags;
 		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
 	}
 	vmcs_writel(GUEST_RFLAGS, rflags);
 
-	if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM)
-		to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
+	if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM)
+		vmx->emulation_required = emulation_required(vcpu);
 }
 
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
@@ -1683,6 +1708,9 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 	index = __find_msr_index(vmx, MSR_TSC_AUX);
 	if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
 		move_msr_up(vmx, index, save_nmsrs++);
+	index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL);
+	if (index >= 0)
+		move_msr_up(vmx, index, save_nmsrs++);
 
 	vmx->save_nmsrs = save_nmsrs;
 	vmx->guest_msrs_ready = false;
@@ -1782,6 +1810,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
+	case MSR_IA32_TSX_CTRL:
+		if (!msr_info->host_initiated &&
+		    !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR))
+			return 1;
+		goto find_shared_msr;
 	case MSR_IA32_UMWAIT_CONTROL:
 		if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
 			return 1;
@@ -1826,14 +1859,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index,
 				       &msr_info->data);
-	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported() ||
-		    (!msr_info->host_initiated &&
-		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
-			return 1;
-		msr_info->data = vcpu->arch.ia32_xss;
-		break;
 	case MSR_IA32_RTIT_CTL:
 		if (pt_mode != PT_MODE_HOST_GUEST)
 			return 1;
@@ -1884,8 +1909,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
 			return 1;
-		/* Else, falls through */
+		goto find_shared_msr;
 	default:
+	find_shared_msr:
 		msr = find_msr_entry(vmx, msr_info->index);
 		if (msr) {
 			msr_info->data = msr->data;
@@ -2001,6 +2027,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					      MSR_IA32_SPEC_CTRL,
 					      MSR_TYPE_RW);
 		break;
+	case MSR_IA32_TSX_CTRL:
+		if (!msr_info->host_initiated &&
+		    !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR))
+			return 1;
+		if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR))
+			return 1;
+		goto find_shared_msr;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -2069,25 +2102,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!nested_vmx_allowed(vcpu))
 			return 1;
 		return vmx_set_vmx_msr(vcpu, msr_index, data);
-	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported() ||
-		    (!msr_info->host_initiated &&
-		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
-			return 1;
-		/*
-		 * The only supported bit as of Skylake is bit 8, but
-		 * it is not supported on KVM.
-		 */
-		if (data != 0)
-			return 1;
-		vcpu->arch.ia32_xss = data;
-		if (vcpu->arch.ia32_xss != host_xss)
-			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
-				vcpu->arch.ia32_xss, host_xss, false);
-		else
-			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
-		break;
 	case MSR_IA32_RTIT_CTL:
 		if ((pt_mode != PT_MODE_HOST_GUEST) ||
 			vmx_rtit_ctl_check(vcpu, data) ||
@@ -2152,23 +2166,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Check reserved bit, higher 32 bits should be zero */
 		if ((data >> 32) != 0)
 			return 1;
-		/* Else, falls through */
+		goto find_shared_msr;
+
 	default:
+	find_shared_msr:
 		msr = find_msr_entry(vmx, msr_index);
-		if (msr) {
-			u64 old_msr_data = msr->data;
-			msr->data = data;
-			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
-				preempt_disable();
-				ret = kvm_set_shared_msr(msr->index, msr->data,
-							 msr->mask);
-				preempt_enable();
-				if (ret)
-					msr->data = old_msr_data;
-			}
-			break;
-		}
-		ret = kvm_set_msr_common(vcpu, msr_info);
+		if (msr)
+			ret = vmx_set_guest_msr(vmx, msr, data);
+		else
+			ret = kvm_set_msr_common(vcpu, msr_info);
 	}
 
 	return ret;
@@ -2176,7 +2182,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 {
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, reg);
+
 	switch (reg) {
 	case VCPU_REGS_RSP:
 		vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP);
@@ -2188,7 +2195,12 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 		if (enable_ept)
 			ept_save_pdptrs(vcpu);
 		break;
+	case VCPU_EXREG_CR3:
+		if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu)))
+			vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+		break;
 	default:
+		WARN_ON_ONCE(1);
 		break;
 	}
 }
@@ -2859,13 +2871,6 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
 }
 
-static void vmx_decache_cr3(struct kvm_vcpu *vcpu)
-{
-	if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu)))
-		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
-}
-
 static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
@@ -2878,8 +2883,7 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_dirty))
+	if (!kvm_register_is_dirty(vcpu, VCPU_EXREG_PDPTR))
 		return;
 
 	if (is_pae_paging(vcpu)) {
@@ -2901,10 +2905,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 	}
 
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_dirty);
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
 }
 
 static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
@@ -2913,8 +2914,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
-		vmx_decache_cr3(vcpu);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3))
+		vmx_cache_reg(vcpu, VCPU_EXREG_CR3);
 	if (!(cr0 & X86_CR0_PG)) {
 		/* From paging/starting to nonpaging */
 		exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING |
@@ -2995,6 +2996,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
 void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	struct kvm *kvm = vcpu->kvm;
+	bool update_guest_cr3 = true;
 	unsigned long guest_cr3;
 	u64 eptp;
 
@@ -3011,15 +3013,20 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 			spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
 		}
 
-		if (enable_unrestricted_guest || is_paging(vcpu) ||
-		    is_guest_mode(vcpu))
-			guest_cr3 = kvm_read_cr3(vcpu);
-		else
+		/* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */
+		if (is_guest_mode(vcpu))
+			update_guest_cr3 = false;
+		else if (!enable_unrestricted_guest && !is_paging(vcpu))
 			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
+		else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+			guest_cr3 = vcpu->arch.cr3;
+		else /* vmcs01.GUEST_CR3 is already up-to-date. */
+			update_guest_cr3 = false;
 		ept_load_pdptrs(vcpu);
 	}
 
-	vmcs_writel(GUEST_CR3, guest_cr3);
+	if (update_guest_cr3)
+		vmcs_writel(GUEST_CR3, guest_cr3);
 }
 
 int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -3753,7 +3760,7 @@ void pt_update_intercept_for_msr(struct vcpu_vmx *vmx)
 	}
 }
 
-static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu)
+static bool vmx_get_enable_apicv(struct kvm *kvm)
 {
 	return enable_apicv;
 }
@@ -4046,6 +4053,8 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
 
+		vcpu->arch.xsaves_enabled = xsaves_enabled;
+
 		if (!xsaves_enabled)
 			exec_control &= ~SECONDARY_EXEC_XSAVES;
 
@@ -4158,14 +4167,13 @@ static void ept_set_mmio_spte_mask(void)
 #define VMX_XSS_EXIT_BITMAP 0
 
 /*
- * Sets up the vmcs for emulated real mode.
+ * Noting that the initialization of Guest-state Area of VMCS is in
+ * vmx_vcpu_reset().
  */
-static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
+static void init_vmcs(struct vcpu_vmx *vmx)
 {
-	int i;
-
 	if (nested)
-		nested_vmx_vcpu_setup();
+		nested_vmx_set_vmcs_shadowing_bitmap();
 
 	if (cpu_has_vmx_msr_bitmap())
 		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
@@ -4174,7 +4182,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	/* Control */
 	pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx));
-	vmx->hv_deadline_tsc = -1;
 
 	exec_controls_set(vmx, vmx_exec_control(vmx));
 
@@ -4223,21 +4230,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 
-	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
-		u32 index = vmx_msr_index[i];
-		u32 data_low, data_high;
-		int j = vmx->nmsrs;
-
-		if (rdmsr_safe(index, &data_low, &data_high) < 0)
-			continue;
-		if (wrmsr_safe(index, data_low, data_high) < 0)
-			continue;
-		vmx->guest_msrs[j].index = i;
-		vmx->guest_msrs[j].data = 0;
-		vmx->guest_msrs[j].mask = -1ull;
-		++vmx->nmsrs;
-	}
-
 	vm_exit_controls_set(vmx, vmx_vmexit_ctrl());
 
 	/* 22.2.1, 20.8.1 */
@@ -4248,6 +4240,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	set_cr4_guest_host_mask(vmx);
 
+	if (vmx->vpid != 0)
+		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+
 	if (vmx_xsaves_supported())
 		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
 
@@ -4350,9 +4345,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 
-	if (vmx->vpid != 0)
-		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
-
 	cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
 	vmx->vcpu.arch.cr0 = cr0;
 	vmx_set_cr0(vcpu, cr0); /* enter rmode */
@@ -4707,7 +4699,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int handle_external_interrupt(struct kvm_vcpu *vcpu)
+static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.irq_exits;
 	return 1;
@@ -4979,21 +4971,6 @@ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 	vmcs_writel(GUEST_DR7, val);
 }
 
-static int handle_cpuid(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_cpuid(vcpu);
-}
-
-static int handle_rdmsr(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_rdmsr(vcpu);
-}
-
-static int handle_wrmsr(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_wrmsr(vcpu);
-}
-
 static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
 {
 	kvm_apic_update_ppr(vcpu);
@@ -5010,11 +4987,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_halt(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_halt(vcpu);
-}
-
 static int handle_vmcall(struct kvm_vcpu *vcpu)
 {
 	return kvm_emulate_hypercall(vcpu);
@@ -5562,11 +5534,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
 	[EXIT_REASON_CR_ACCESS]               = handle_cr,
 	[EXIT_REASON_DR_ACCESS]               = handle_dr,
-	[EXIT_REASON_CPUID]                   = handle_cpuid,
-	[EXIT_REASON_MSR_READ]                = handle_rdmsr,
-	[EXIT_REASON_MSR_WRITE]               = handle_wrmsr,
+	[EXIT_REASON_CPUID]                   = kvm_emulate_cpuid,
+	[EXIT_REASON_MSR_READ]                = kvm_emulate_rdmsr,
+	[EXIT_REASON_MSR_WRITE]               = kvm_emulate_wrmsr,
 	[EXIT_REASON_PENDING_INTERRUPT]       = handle_interrupt_window,
-	[EXIT_REASON_HLT]                     = handle_halt,
+	[EXIT_REASON_HLT]                     = kvm_emulate_halt,
 	[EXIT_REASON_INVD]		      = handle_invd,
 	[EXIT_REASON_INVLPG]		      = handle_invlpg,
 	[EXIT_REASON_RDPMC]                   = handle_rdpmc,
@@ -5939,9 +5911,23 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	}
 
 	if (exit_reason < kvm_vmx_max_exit_handlers
-	    && kvm_vmx_exit_handlers[exit_reason])
+	    && kvm_vmx_exit_handlers[exit_reason]) {
+#ifdef CONFIG_RETPOLINE
+		if (exit_reason == EXIT_REASON_MSR_WRITE)
+			return kvm_emulate_wrmsr(vcpu);
+		else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER)
+			return handle_preemption_timer(vcpu);
+		else if (exit_reason == EXIT_REASON_PENDING_INTERRUPT)
+			return handle_interrupt_window(vcpu);
+		else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
+			return handle_external_interrupt(vcpu);
+		else if (exit_reason == EXIT_REASON_HLT)
+			return kvm_emulate_halt(vcpu);
+		else if (exit_reason == EXIT_REASON_EPT_MISCONFIG)
+			return handle_ept_misconfig(vcpu);
+#endif
 		return kvm_vmx_exit_handlers[exit_reason](vcpu);
-	else {
+	} else {
 		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
 				exit_reason);
 		dump_vmcs();
@@ -6027,17 +6013,17 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	int tpr_threshold;
 
 	if (is_guest_mode(vcpu) &&
 		nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
 		return;
 
-	if (irr == -1 || tpr < irr) {
-		vmcs_write32(TPR_THRESHOLD, 0);
-		return;
-	}
-
-	vmcs_write32(TPR_THRESHOLD, irr);
+	tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr;
+	if (is_guest_mode(vcpu))
+		to_vmx(vcpu)->nested.l1_tpr_threshold = tpr_threshold;
+	else
+		vmcs_write32(TPR_THRESHOLD, tpr_threshold);
 }
 
 void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
@@ -6514,9 +6500,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vmx->nested.need_vmcs12_to_shadow_sync)
 		nested_sync_vmcs12_to_shadow(vcpu);
 
-	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP))
 		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
-	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
 	cr3 = __get_current_cr3_fast();
@@ -6539,7 +6525,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
-	kvm_load_guest_xcr0(vcpu);
+	kvm_load_guest_xsave_state(vcpu);
 
 	if (static_cpu_has(X86_FEATURE_PKU) &&
 	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
@@ -6646,7 +6632,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 			__write_pkru(vmx->host_pkru);
 	}
 
-	kvm_put_guest_xcr0(vcpu);
+	kvm_load_host_xsave_state(vcpu);
 
 	vmx->nested.nested_run_pending = 0;
 	vmx->idt_vectoring_info = 0;
@@ -6700,7 +6686,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	int err;
 	struct vcpu_vmx *vmx;
 	unsigned long *msr_bitmap;
-	int cpu;
+	int i, cpu;
 
 	BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0,
 		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
@@ -6752,6 +6738,34 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx->guest_msrs)
 		goto free_pml;
 
+	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
+		u32 index = vmx_msr_index[i];
+		u32 data_low, data_high;
+		int j = vmx->nmsrs;
+
+		if (rdmsr_safe(index, &data_low, &data_high) < 0)
+			continue;
+		if (wrmsr_safe(index, data_low, data_high) < 0)
+			continue;
+
+		vmx->guest_msrs[j].index = i;
+		vmx->guest_msrs[j].data = 0;
+		switch (index) {
+		case MSR_IA32_TSX_CTRL:
+			/*
+			 * No need to pass TSX_CTRL_CPUID_CLEAR through, so
+			 * let's avoid changing CPUID bits under the host
+			 * kernel's feet.
+			 */
+			vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+			break;
+		default:
+			vmx->guest_msrs[j].mask = -1ull;
+			break;
+		}
+		++vmx->nmsrs;
+	}
+
 	err = alloc_loaded_vmcs(&vmx->vmcs01);
 	if (err < 0)
 		goto free_msrs;
@@ -6776,7 +6790,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	cpu = get_cpu();
 	vmx_vcpu_load(&vmx->vcpu, cpu);
 	vmx->vcpu.cpu = cpu;
-	vmx_vcpu_setup(vmx);
+	init_vmcs(vmx);
 	vmx_vcpu_put(&vmx->vcpu);
 	put_cpu();
 	if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
@@ -6996,6 +7010,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
 	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
 	cr4_fixed1_update(X86_CR4_UMIP,       ecx, bit(X86_FEATURE_UMIP));
+	cr4_fixed1_update(X86_CR4_LA57,       ecx, bit(X86_FEATURE_LA57));
 
 #undef cr4_fixed1_update
 }
@@ -7090,6 +7105,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	/* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */
+	vcpu->arch.xsaves_enabled = false;
+
 	if (cpu_has_secondary_exec_ctrls()) {
 		vmx_compute_secondary_exec_control(vmx);
 		vmcs_set_secondary_exec_control(vmx);
@@ -7097,10 +7115,12 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 
 	if (nested_vmx_allowed(vcpu))
 		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+			FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX |
 			FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
 	else
 		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
-			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+			~(FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX |
+			  FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX);
 
 	if (nested_vmx_allowed(vcpu)) {
 		nested_vmx_cr_fixed1_bits_update(vcpu);
@@ -7110,6 +7130,15 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT))
 		update_intel_pt_cfg(vcpu);
+
+	if (boot_cpu_has(X86_FEATURE_RTM)) {
+		struct shared_msr_entry *msr;
+		msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL);
+		if (msr) {
+			bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM);
+			vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE);
+		}
+	}
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -7598,9 +7627,6 @@ static __init int hardware_setup(void)
 		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");
 	}
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		rdmsrl(MSR_IA32_XSS, host_xss);
-
 	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
 	    !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
 		enable_vpid = 0;
@@ -7781,7 +7807,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.get_cpl = vmx_get_cpl,
 	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
 	.decache_cr0_guest_bits = vmx_decache_cr0_guest_bits,
-	.decache_cr3 = vmx_decache_cr3,
 	.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
 	.set_cr0 = vmx_set_cr0,
 	.set_cr3 = vmx_set_cr3,
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 5a0f34b1e226..7c1b978b2df4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -22,11 +22,11 @@ extern u32 get_umwait_control_msr(void);
 
 #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
 
-#define NR_AUTOLOAD_MSRS 8
+#define NR_LOADSTORE_MSRS 8
 
 struct vmx_msrs {
 	unsigned int		nr;
-	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
+	struct vmx_msr_entry	val[NR_LOADSTORE_MSRS];
 };
 
 struct shared_msr_entry {
@@ -167,6 +167,9 @@ struct nested_vmx {
 	u64 vmcs01_debugctl;
 	u64 vmcs01_guest_bndcfgs;
 
+	/* to migrate it to L1 if L2 writes to L1's CR8 directly */
+	int l1_tpr_threshold;
+
 	u16 vpid02;
 	u16 last_vpid;
 
@@ -230,6 +233,10 @@ struct vcpu_vmx {
 		struct vmx_msrs host;
 	} msr_autoload;
 
+	struct msr_autostore {
+		struct vmx_msrs guest;
+	} msr_autostore;
+
 	struct {
 		int vm86_active;
 		ulong save_rflags;
@@ -334,6 +341,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
 struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr);
 void pt_update_intercept_for_msr(struct vcpu_vmx *vmx);
 void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
+int vmx_find_msr_index(struct vmx_msrs *m, u32 msr);
 
 #define POSTED_INTR_ON  0
 #define POSTED_INTR_SN  1
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 783aa8d141bf..cf917139de6b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -177,6 +177,8 @@ struct kvm_shared_msrs {
 static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
 static struct kvm_shared_msrs __percpu *shared_msrs;
 
+static u64 __read_mostly host_xss;
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pf_fixed", VCPU_STAT(pf_fixed) },
 	{ "pf_guest", VCPU_STAT(pf_guest) },
@@ -261,23 +263,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	}
 }
 
-static void shared_msr_update(unsigned slot, u32 msr)
-{
-	u64 value;
-	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
-
-	/* only read, and nobody should modify it at this time,
-	 * so don't need lock */
-	if (slot >= shared_msrs_global.nr) {
-		printk(KERN_ERR "kvm: invalid MSR slot!");
-		return;
-	}
-	rdmsrl_safe(msr, &value);
-	smsr->values[slot].host = value;
-	smsr->values[slot].curr = value;
-}
-
 void kvm_define_shared_msr(unsigned slot, u32 msr)
 {
 	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
@@ -289,10 +274,16 @@ EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
 
 static void kvm_shared_msr_cpu_online(void)
 {
-	unsigned i;
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	u64 value;
+	int i;
 
-	for (i = 0; i < shared_msrs_global.nr; ++i)
-		shared_msr_update(i, shared_msrs_global.msrs[i]);
+	for (i = 0; i < shared_msrs_global.nr; ++i) {
+		rdmsrl_safe(shared_msrs_global.msrs[i], &value);
+		smsr->values[i].host = value;
+		smsr->values[i].curr = value;
+	}
 }
 
 int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
@@ -301,13 +292,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 	int err;
 
-	if (((value ^ smsr->values[slot].curr) & mask) == 0)
+	value = (value & mask) | (smsr->values[slot].host & ~mask);
+	if (value == smsr->values[slot].curr)
 		return 0;
-	smsr->values[slot].curr = value;
 	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
 	if (err)
 		return 1;
 
+	smsr->values[slot].curr = value;
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
@@ -710,10 +702,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 	ret = 1;
 
 	memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs));
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_dirty);
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
+
 out:
 
 	return ret;
@@ -723,7 +713,6 @@ EXPORT_SYMBOL_GPL(load_pdptrs);
 bool pdptrs_changed(struct kvm_vcpu *vcpu)
 {
 	u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)];
-	bool changed = true;
 	int offset;
 	gfn_t gfn;
 	int r;
@@ -731,8 +720,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	if (!is_pae_paging(vcpu))
 		return false;
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_avail))
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR))
 		return true;
 
 	gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT;
@@ -740,11 +728,9 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
 				       PFERR_USER_MASK | PFERR_WRITE_MASK);
 	if (r < 0)
-		goto out;
-	changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
-out:
+		return true;
 
-	return changed;
+	return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
 }
 EXPORT_SYMBOL_GPL(pdptrs_changed);
 
@@ -813,27 +799,34 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
-void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 {
-	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
-			!vcpu->guest_xcr0_loaded) {
-		/* kvm_set_xcr() also depends on this */
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
-		vcpu->guest_xcr0_loaded = 1;
+
+		if (vcpu->arch.xsaves_enabled &&
+		    vcpu->arch.ia32_xss != host_xss)
+			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
 }
-EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
+EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
 
-void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_xcr0_loaded) {
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
-		vcpu->guest_xcr0_loaded = 0;
+
+		if (vcpu->arch.xsaves_enabled &&
+		    vcpu->arch.ia32_xss != host_xss)
+			wrmsrl(MSR_IA32_XSS, host_xss);
 	}
+
 }
-EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
+EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
 
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
@@ -985,7 +978,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush);
 	vcpu->arch.cr3 = cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	return 0;
 }
@@ -1314,23 +1307,15 @@ static u64 kvm_get_arch_capabilities(void)
 		data |= ARCH_CAP_MDS_NO;
 
 	/*
-	 * On TAA affected systems, export MDS_NO=0 when:
-	 *	- TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
-	 *	- Updated microcode is present. This is detected by
-	 *	  the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
-	 *	  that VERW clears CPU buffers.
-	 *
-	 * When MDS_NO=0 is exported, guests deploy clear CPU buffer
-	 * mitigation and don't complain:
-	 *
-	 *	"Vulnerable: Clear CPU buffers attempted, no microcode"
-	 *
-	 * If TSX is disabled on the system, guests are also mitigated against
-	 * TAA and clear CPU buffer mitigation is not required for guests.
+	 * On TAA affected systems:
+	 *      - nothing to do if TSX is disabled on the host.
+	 *      - we emulate TSX_CTRL if present on the host.
+	 *	  This lets the guest use VERW to clear CPU buffers.
 	 */
-	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
-	    (data & ARCH_CAP_TSX_CTRL_MSR))
-		data &= ~ARCH_CAP_MDS_NO;
+	if (!boot_cpu_has(X86_FEATURE_RTM))
+		data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR);
+	else if (!boot_cpu_has_bug(X86_BUG_TAA))
+		data |= ARCH_CAP_TAA_NO;
 
 	return data;
 }
@@ -1478,8 +1463,8 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
-static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
-			 bool host_initiated)
+int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
+		  bool host_initiated)
 {
 	struct msr_data msr;
 	int ret;
@@ -1554,20 +1539,25 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 }
 
 #ifdef CONFIG_X86_64
+struct pvclock_clock {
+	int vclock_mode;
+	u64 cycle_last;
+	u64 mask;
+	u32 mult;
+	u32 shift;
+};
+
 struct pvclock_gtod_data {
 	seqcount_t	seq;
 
-	struct { /* extract of a clocksource struct */
-		int vclock_mode;
-		u64	cycle_last;
-		u64	mask;
-		u32	mult;
-		u32	shift;
-	} clock;
+	struct pvclock_clock clock; /* extract of a clocksource struct */
+	struct pvclock_clock raw_clock; /* extract of a clocksource struct */
 
+	u64		boot_ns_raw;
 	u64		boot_ns;
 	u64		nsec_base;
 	u64		wall_time_sec;
+	u64		monotonic_raw_nsec;
 };
 
 static struct pvclock_gtod_data pvclock_gtod_data;
@@ -1575,9 +1565,10 @@ static struct pvclock_gtod_data pvclock_gtod_data;
 static void update_pvclock_gtod(struct timekeeper *tk)
 {
 	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
-	u64 boot_ns;
+	u64 boot_ns, boot_ns_raw;
 
 	boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot));
+	boot_ns_raw = ktime_to_ns(ktime_add(tk->tkr_raw.base, tk->offs_boot));
 
 	write_seqcount_begin(&vdata->seq);
 
@@ -1588,11 +1579,20 @@ static void update_pvclock_gtod(struct timekeeper *tk)
 	vdata->clock.mult		= tk->tkr_mono.mult;
 	vdata->clock.shift		= tk->tkr_mono.shift;
 
+	vdata->raw_clock.vclock_mode	= tk->tkr_raw.clock->archdata.vclock_mode;
+	vdata->raw_clock.cycle_last	= tk->tkr_raw.cycle_last;
+	vdata->raw_clock.mask		= tk->tkr_raw.mask;
+	vdata->raw_clock.mult		= tk->tkr_raw.mult;
+	vdata->raw_clock.shift		= tk->tkr_raw.shift;
+
 	vdata->boot_ns			= boot_ns;
 	vdata->nsec_base		= tk->tkr_mono.xtime_nsec;
 
 	vdata->wall_time_sec            = tk->xtime_sec;
 
+	vdata->boot_ns_raw		= boot_ns_raw;
+	vdata->monotonic_raw_nsec	= tk->tkr_raw.xtime_nsec;
+
 	write_seqcount_end(&vdata->seq);
 }
 #endif
@@ -2016,21 +2016,21 @@ static u64 read_tsc(void)
 	return last;
 }
 
-static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
+static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp,
+			  int *mode)
 {
 	long v;
-	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	u64 tsc_pg_val;
 
-	switch (gtod->clock.vclock_mode) {
+	switch (clock->vclock_mode) {
 	case VCLOCK_HVCLOCK:
 		tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
 						  tsc_timestamp);
 		if (tsc_pg_val != U64_MAX) {
 			/* TSC page valid */
 			*mode = VCLOCK_HVCLOCK;
-			v = (tsc_pg_val - gtod->clock.cycle_last) &
-				gtod->clock.mask;
+			v = (tsc_pg_val - clock->cycle_last) &
+				clock->mask;
 		} else {
 			/* TSC page invalid */
 			*mode = VCLOCK_NONE;
@@ -2039,8 +2039,8 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 	case VCLOCK_TSC:
 		*mode = VCLOCK_TSC;
 		*tsc_timestamp = read_tsc();
-		v = (*tsc_timestamp - gtod->clock.cycle_last) &
-			gtod->clock.mask;
+		v = (*tsc_timestamp - clock->cycle_last) &
+			clock->mask;
 		break;
 	default:
 		*mode = VCLOCK_NONE;
@@ -2049,10 +2049,10 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 	if (*mode == VCLOCK_NONE)
 		*tsc_timestamp = v = 0;
 
-	return v * gtod->clock.mult;
+	return v * clock->mult;
 }
 
-static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
+static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp)
 {
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;
@@ -2061,10 +2061,10 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
 
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
-		ns = gtod->nsec_base;
-		ns += vgettsc(tsc_timestamp, &mode);
+		ns = gtod->monotonic_raw_nsec;
+		ns += vgettsc(&gtod->raw_clock, tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
-		ns += gtod->boot_ns;
+		ns += gtod->boot_ns_raw;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	*t = ns;
 
@@ -2082,7 +2082,7 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
 		seq = read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->nsec_base;
-		ns += vgettsc(tsc_timestamp, &mode);
+		ns += vgettsc(&gtod->clock, tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
@@ -2099,7 +2099,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
 	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
 		return false;
 
-	return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns,
+	return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns,
 						      tsc_timestamp));
 }
 
@@ -2722,6 +2722,20 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
+	case MSR_IA32_XSS:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+			return 1;
+		/*
+		 * We do support PT if kvm_x86_ops->pt_supported(), but we do
+		 * not support IA32_XSS[bit 8]. Guests will have to use
+		 * RDMSR/WRMSR rather than XSAVES/XRSTORS to save/restore PT
+		 * MSRs.
+		 */
+		if (data != 0)
+			return 1;
+		vcpu->arch.ia32_xss = data;
+		break;
 	case MSR_SMI_COUNT:
 		if (!msr_info->host_initiated)
 			return 1;
@@ -3049,6 +3063,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
 		return get_msr_mce(vcpu, msr_info->index, &msr_info->data,
 				   msr_info->host_initiated);
+	case MSR_IA32_XSS:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+			return 1;
+		msr_info->data = vcpu->arch.ia32_xss;
+		break;
 	case MSR_K7_CLK_CTL:
 		/*
 		 * Provide expected ramp-up count for K7. All other
@@ -3826,12 +3846,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 			else
 				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
-			if (lapic_in_kernel(vcpu)) {
-				if (events->smi.latched_init)
-					set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
-				else
-					clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
-			}
+		}
+
+		if (lapic_in_kernel(vcpu)) {
+			if (events->smi.latched_init)
+				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+			else
+				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 		}
 	}
 
@@ -4422,6 +4443,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_SET_NESTED_STATE: {
 		struct kvm_nested_state __user *user_kvm_nested_state = argp;
 		struct kvm_nested_state kvm_state;
+		int idx;
 
 		r = -EINVAL;
 		if (!kvm_x86_ops->set_nested_state)
@@ -4445,7 +4467,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		    && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
 			break;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_GET_SUPPORTED_HV_CPUID: {
@@ -4947,9 +4971,6 @@ set_identity_unlock:
 		if (!irqchip_kernel(kvm))
 			goto set_irqchip_out;
 		r = kvm_vm_ioctl_set_irqchip(kvm, chip);
-		if (r)
-			goto set_irqchip_out;
-		r = 0;
 	set_irqchip_out:
 		kfree(chip);
 		break;
@@ -6138,7 +6159,7 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase)
 static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
 			      u32 pmc)
 {
-	return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc);
+	return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc);
 }
 
 static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
@@ -7868,6 +7889,19 @@ static void process_smi(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
+void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
+				       unsigned long *vcpu_bitmap)
+{
+	cpumask_var_t cpus;
+
+	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
+
+	kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC,
+				    vcpu_bitmap, cpus);
+
+	free_cpumask_var(cpus);
+}
+
 void kvm_make_scan_ioapic_request(struct kvm *kvm)
 {
 	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
@@ -7945,7 +7979,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 	 */
 	put_page(page);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
 
 void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu)
 {
@@ -8704,8 +8737,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	    mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
 		goto out;
 
-	/* INITs are latched while in SMM */
-	if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
+	/*
+	 * KVM_MP_STATE_INIT_RECEIVED means the processor is in
+	 * INIT state; latched init should be reported using
+	 * KVM_SET_VCPU_EVENTS, so reject it here.
+	 */
+	if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) &&
 	    (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
 	     mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
 		goto out;
@@ -8797,7 +8834,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	vcpu->arch.cr2 = sregs->cr2;
 	mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
 	vcpu->arch.cr3 = sregs->cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	kvm_set_cr8(vcpu, sregs->cr8);
 
@@ -9324,6 +9361,9 @@ int kvm_arch_hardware_setup(void)
 		kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		rdmsrl(MSR_IA32_XSS, host_xss);
+
 	kvm_init_msr_list();
 	return 0;
 }
@@ -9377,7 +9417,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_pio_data;
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
-		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
+		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm);
 		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
@@ -9446,7 +9486,13 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
 	vcpu->arch.l1tf_flush_l1d = true;
+	if (pmu->version && unlikely(pmu->event_count)) {
+		pmu->need_cleanup = true;
+		kvm_make_request(KVM_REQ_PMU, vcpu);
+	}
 	kvm_x86_ops->sched_in(vcpu, cpu);
 }
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index dbf7442a822b..29391af8871d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -238,8 +238,7 @@ static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 	return false;
 }
 
-static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu,
-					       enum kvm_reg reg)
+static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, int reg)
 {
 	unsigned long val = kvm_register_read(vcpu, reg);
 
@@ -247,8 +246,7 @@ static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu,
 }
 
 static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
-				       enum kvm_reg reg,
-				       unsigned long val)
+				       int reg, unsigned long val)
 {
 	if (!is_64_bit_mode(vcpu))
 		val = (u32)val;
@@ -260,6 +258,11 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
 	return !(kvm->arch.disabled_quirks & quirk);
 }
 
+static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu)
+{
+	return is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu);
+}
+
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 
@@ -366,7 +369,7 @@ static inline bool kvm_pat_valid(u64 data)
 	return (data | ((data & 0x0202020202020202ull) << 1)) == data;
 }
 
-void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
-void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu);
+void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
 
 #endif
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 84373dc9b341..bbc68a54795e 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -13,7 +13,7 @@ CFLAGS_REMOVE_mem_encrypt_identity.o	= -pg
 endif
 
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o
+	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 79eb55ce69a9..49d7814b59a9 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -193,8 +193,8 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 	int ret;
 	WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n"));
 	if (f->armed) {
-		pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n",
-			   f->addr, f->count, !!f->old_presence);
+		pr_warn("double-arm: addr 0x%08lx, ref %d, old %d\n",
+			f->addr, f->count, !!f->old_presence);
 	}
 	ret = clear_page_presence(f, true);
 	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"),
@@ -341,8 +341,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 		 * something external causing them (f.e. using a debugger while
 		 * mmio tracing enabled), or erroneous behaviour
 		 */
-		pr_warning("unexpected debug trap on CPU %d.\n",
-			   smp_processor_id());
+		pr_warn("unexpected debug trap on CPU %d.\n", smp_processor_id());
 		goto out;
 	}
 
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
new file mode 100644
index 000000000000..f5b85bdc0535
--- /dev/null
+++ b/arch/x86/mm/maccess.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+
+#ifdef CONFIG_X86_64
+static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits)
+{
+	return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
+}
+
+static __always_inline bool invalid_probe_range(u64 vaddr)
+{
+	/*
+	 * Range covering the highest possible canonical userspace address
+	 * as well as non-canonical address range. For the canonical range
+	 * we also need to include the userspace guard page.
+	 */
+	return vaddr < TASK_SIZE_MAX + PAGE_SIZE ||
+	       canonical_address(vaddr, boot_cpu_data.x86_virt_bits) != vaddr;
+}
+#else
+static __always_inline bool invalid_probe_range(u64 vaddr)
+{
+	return vaddr < TASK_SIZE_MAX;
+}
+#endif
+
+long probe_kernel_read_strict(void *dst, const void *src, size_t size)
+{
+	if (unlikely(invalid_probe_range((unsigned long)src)))
+		return -EFAULT;
+
+	return __probe_kernel_read(dst, src, size);
+}
+
+long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, long count)
+{
+	if (unlikely(invalid_probe_range((unsigned long)unsafe_addr)))
+		return -EFAULT;
+
+	return __strncpy_from_unsafe(dst, unsafe_addr, count);
+}
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index b8ef8557d4b3..673de6063345 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -394,7 +394,7 @@ static void enter_uniprocessor(void)
 	}
 out:
 	if (num_online_cpus() > 1)
-		pr_warning("multiple CPUs still online, may miss events.\n");
+		pr_warn("multiple CPUs still online, may miss events.\n");
 }
 
 static void leave_uniprocessor(void)
@@ -418,8 +418,8 @@ static void leave_uniprocessor(void)
 static void enter_uniprocessor(void)
 {
 	if (num_online_cpus() > 1)
-		pr_warning("multiple CPUs are online, may miss events. "
-			   "Suggest booting with maxcpus=1 kernel argument.\n");
+		pr_warn("multiple CPUs are online, may miss events. "
+			"Suggest booting with maxcpus=1 kernel argument.\n");
 }
 
 static void leave_uniprocessor(void)
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index abffa0be80da..7f1d2034df1e 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -438,7 +438,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 		goto no_emu;
 
 	if (numa_cleanup_meminfo(&ei) < 0) {
-		pr_warning("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
+		pr_warn("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
 		goto no_emu;
 	}
 
@@ -449,7 +449,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 		phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
 					      phys_size, PAGE_SIZE);
 		if (!phys) {
-			pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
+			pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
 			goto no_emu;
 		}
 		memblock_reserve(phys, phys_size);
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index a8bd952e136d..92153d054d6c 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -127,9 +127,9 @@ static int __init init(void)
 		return -ENXIO;
 	}
 
-	pr_warning("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, "
-		   "and writing 16 kB of rubbish in there.\n",
-		   size >> 10, mmio_address);
+	pr_warn("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, "
+		"and writing 16 kB of rubbish in there.\n",
+		size >> 10, mmio_address);
 	do_test(size);
 	do_test_bulk_ioremapping();
 	pr_info("All done.\n");
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 991549a1c5f3..b8be18427277 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -9,9 +9,11 @@
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
 #include <linux/bpf.h>
-
+#include <linux/memory.h>
+#include <asm/extable.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
+#include <asm/text-patching.h>
 
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -96,6 +98,7 @@ static int bpf_size_to_x86_bytes(int bpf_size)
 
 /* Pick a register outside of BPF range for JIT internal work */
 #define AUX_REG (MAX_BPF_JIT_REG + 1)
+#define X86_REG_R9 (MAX_BPF_JIT_REG + 2)
 
 /*
  * The following table maps BPF registers to x86-64 registers.
@@ -104,8 +107,8 @@ static int bpf_size_to_x86_bytes(int bpf_size)
  * register in load/store instructions, it always needs an
  * extra byte of encoding and is callee saved.
  *
- * Also x86-64 register R9 is unused. x86-64 register R10 is
- * used for blinding (if enabled).
+ * x86-64 register R9 is not used by BPF programs, but can be used by BPF
+ * trampoline. x86-64 register R10 is used for blinding (if enabled).
  */
 static const int reg2hex[] = {
 	[BPF_REG_0] = 0,  /* RAX */
@@ -121,6 +124,20 @@ static const int reg2hex[] = {
 	[BPF_REG_FP] = 5, /* RBP readonly */
 	[BPF_REG_AX] = 2, /* R10 temp register */
 	[AUX_REG] = 3,    /* R11 temp register */
+	[X86_REG_R9] = 1, /* R9 register, 6th function argument */
+};
+
+static const int reg2pt_regs[] = {
+	[BPF_REG_0] = offsetof(struct pt_regs, ax),
+	[BPF_REG_1] = offsetof(struct pt_regs, di),
+	[BPF_REG_2] = offsetof(struct pt_regs, si),
+	[BPF_REG_3] = offsetof(struct pt_regs, dx),
+	[BPF_REG_4] = offsetof(struct pt_regs, cx),
+	[BPF_REG_5] = offsetof(struct pt_regs, r8),
+	[BPF_REG_6] = offsetof(struct pt_regs, bx),
+	[BPF_REG_7] = offsetof(struct pt_regs, r13),
+	[BPF_REG_8] = offsetof(struct pt_regs, r14),
+	[BPF_REG_9] = offsetof(struct pt_regs, r15),
 };
 
 /*
@@ -135,6 +152,7 @@ static bool is_ereg(u32 reg)
 			     BIT(BPF_REG_7) |
 			     BIT(BPF_REG_8) |
 			     BIT(BPF_REG_9) |
+			     BIT(X86_REG_R9) |
 			     BIT(BPF_REG_AX));
 }
 
@@ -186,7 +204,10 @@ struct jit_context {
 #define BPF_MAX_INSN_SIZE	128
 #define BPF_INSN_SAFETY		64
 
-#define PROLOGUE_SIZE		20
+/* Number of bytes emit_patch() needs to generate instructions */
+#define X86_PATCH_SIZE		5
+
+#define PROLOGUE_SIZE		25
 
 /*
  * Emit x86-64 prologue code for BPF program and check its size.
@@ -195,8 +216,13 @@ struct jit_context {
 static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 {
 	u8 *prog = *pprog;
-	int cnt = 0;
+	int cnt = X86_PATCH_SIZE;
 
+	/* BPF trampoline can be made to work without these nops,
+	 * but let's waste 5 bytes for now and optimize later
+	 */
+	memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt);
+	prog += cnt;
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	/* sub rsp, rounded_stack_depth */
@@ -213,6 +239,89 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	*pprog = prog;
 }
 
+static int emit_patch(u8 **pprog, void *func, void *ip, u8 opcode)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	s64 offset;
+
+	offset = func - (ip + X86_PATCH_SIZE);
+	if (!is_simm32(offset)) {
+		pr_err("Target call %p is out of range\n", func);
+		return -ERANGE;
+	}
+	EMIT1_off32(opcode, offset);
+	*pprog = prog;
+	return 0;
+}
+
+static int emit_call(u8 **pprog, void *func, void *ip)
+{
+	return emit_patch(pprog, func, ip, 0xE8);
+}
+
+static int emit_jump(u8 **pprog, void *func, void *ip)
+{
+	return emit_patch(pprog, func, ip, 0xE9);
+}
+
+static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
+				void *old_addr, void *new_addr,
+				const bool text_live)
+{
+	const u8 *nop_insn = ideal_nops[NOP_ATOMIC5];
+	u8 old_insn[X86_PATCH_SIZE];
+	u8 new_insn[X86_PATCH_SIZE];
+	u8 *prog;
+	int ret;
+
+	memcpy(old_insn, nop_insn, X86_PATCH_SIZE);
+	if (old_addr) {
+		prog = old_insn;
+		ret = t == BPF_MOD_CALL ?
+		      emit_call(&prog, old_addr, ip) :
+		      emit_jump(&prog, old_addr, ip);
+		if (ret)
+			return ret;
+	}
+
+	memcpy(new_insn, nop_insn, X86_PATCH_SIZE);
+	if (new_addr) {
+		prog = new_insn;
+		ret = t == BPF_MOD_CALL ?
+		      emit_call(&prog, new_addr, ip) :
+		      emit_jump(&prog, new_addr, ip);
+		if (ret)
+			return ret;
+	}
+
+	ret = -EBUSY;
+	mutex_lock(&text_mutex);
+	if (memcmp(ip, old_insn, X86_PATCH_SIZE))
+		goto out;
+	if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
+		if (text_live)
+			text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
+		else
+			memcpy(ip, new_insn, X86_PATCH_SIZE);
+	}
+	ret = 0;
+out:
+	mutex_unlock(&text_mutex);
+	return ret;
+}
+
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
+		       void *old_addr, void *new_addr)
+{
+	if (!is_kernel_text((long)ip) &&
+	    !is_bpf_text_address((long)ip))
+		/* BPF poking in modules is not supported */
+		return -EINVAL;
+
+	return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
+}
+
 /*
  * Generate the following code:
  *
@@ -227,7 +336,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
  *   goto *(prog->bpf_func + prologue_size);
  * out:
  */
-static void emit_bpf_tail_call(u8 **pprog)
+static void emit_bpf_tail_call_indirect(u8 **pprog)
 {
 	u8 *prog = *pprog;
 	int label1, label2, label3;
@@ -294,6 +403,68 @@ static void emit_bpf_tail_call(u8 **pprog)
 	*pprog = prog;
 }
 
+static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
+				      u8 **pprog, int addr, u8 *image)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	/*
+	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+	 *	goto out;
+	 */
+	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
+	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);         /* cmp eax, MAX_TAIL_CALL_CNT */
+	EMIT2(X86_JA, 14);                            /* ja out */
+	EMIT3(0x83, 0xC0, 0x01);                      /* add eax, 1 */
+	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
+
+	poke->ip = image + (addr - X86_PATCH_SIZE);
+	poke->adj_off = PROLOGUE_SIZE;
+
+	memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
+	prog += X86_PATCH_SIZE;
+	/* out: */
+
+	*pprog = prog;
+}
+
+static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
+{
+	struct bpf_jit_poke_descriptor *poke;
+	struct bpf_array *array;
+	struct bpf_prog *target;
+	int i, ret;
+
+	for (i = 0; i < prog->aux->size_poke_tab; i++) {
+		poke = &prog->aux->poke_tab[i];
+		WARN_ON_ONCE(READ_ONCE(poke->ip_stable));
+
+		if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
+			continue;
+
+		array = container_of(poke->tail_call.map, struct bpf_array, map);
+		mutex_lock(&array->aux->poke_mutex);
+		target = array->ptrs[poke->tail_call.key];
+		if (target) {
+			/* Plain memcpy is used when image is not live yet
+			 * and still not locked as read-only. Once poke
+			 * location is active (poke->ip_stable), any parallel
+			 * bpf_arch_text_poke() might occur still on the
+			 * read-write image until we finally locked it as
+			 * read-only. Both modifications on the given image
+			 * are under text_mutex to avoid interference.
+			 */
+			ret = __bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, NULL,
+						   (u8 *)target->bpf_func +
+						   poke->adj_off, false);
+			BUG_ON(ret < 0);
+		}
+		WRITE_ONCE(poke->ip_stable, true);
+		mutex_unlock(&array->aux->poke_mutex);
+	}
+}
+
 static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
 			   u32 dst_reg, const u32 imm32)
 {
@@ -377,6 +548,96 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
 	*pprog = prog;
 }
 
+/* LDX: dst_reg = *(u8*)(src_reg + off) */
+static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	switch (size) {
+	case BPF_B:
+		/* Emit 'movzx rax, byte ptr [rax + off]' */
+		EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
+		break;
+	case BPF_H:
+		/* Emit 'movzx rax, word ptr [rax + off]' */
+		EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
+		break;
+	case BPF_W:
+		/* Emit 'mov eax, dword ptr [rax+0x14]' */
+		if (is_ereg(dst_reg) || is_ereg(src_reg))
+			EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
+		else
+			EMIT1(0x8B);
+		break;
+	case BPF_DW:
+		/* Emit 'mov rax, qword ptr [rax+0x14]' */
+		EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
+		break;
+	}
+	/*
+	 * If insn->off == 0 we can save one extra byte, but
+	 * special case of x86 R13 which always needs an offset
+	 * is not worth the hassle
+	 */
+	if (is_imm8(off))
+		EMIT2(add_2reg(0x40, src_reg, dst_reg), off);
+	else
+		EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), off);
+	*pprog = prog;
+}
+
+/* STX: *(u8*)(dst_reg + off) = src_reg */
+static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	switch (size) {
+	case BPF_B:
+		/* Emit 'mov byte ptr [rax + off], al' */
+		if (is_ereg(dst_reg) || is_ereg(src_reg) ||
+		    /* We have to add extra byte for x86 SIL, DIL regs */
+		    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
+			EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
+		else
+			EMIT1(0x88);
+		break;
+	case BPF_H:
+		if (is_ereg(dst_reg) || is_ereg(src_reg))
+			EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
+		else
+			EMIT2(0x66, 0x89);
+		break;
+	case BPF_W:
+		if (is_ereg(dst_reg) || is_ereg(src_reg))
+			EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
+		else
+			EMIT1(0x89);
+		break;
+	case BPF_DW:
+		EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
+		break;
+	}
+	if (is_imm8(off))
+		EMIT2(add_2reg(0x40, dst_reg, src_reg), off);
+	else
+		EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), off);
+	*pprog = prog;
+}
+
+static bool ex_handler_bpf(const struct exception_table_entry *x,
+			   struct pt_regs *regs, int trapnr,
+			   unsigned long error_code, unsigned long fault_addr)
+{
+	u32 reg = x->fixup >> 8;
+
+	/* jump over faulting load and clear dest register */
+	*(unsigned long *)((void *)regs + reg) = 0;
+	regs->ip += x->fixup & 0xff;
+	return true;
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
@@ -384,7 +645,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	int insn_cnt = bpf_prog->len;
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
-	int i, cnt = 0;
+	int i, cnt = 0, excnt = 0;
 	int proglen = 0;
 	u8 *prog = temp;
 
@@ -747,64 +1008,64 @@ st:			if (is_imm8(insn->off))
 
 			/* STX: *(u8*)(dst_reg + off) = src_reg */
 		case BPF_STX | BPF_MEM | BPF_B:
-			/* Emit 'mov byte ptr [rax + off], al' */
-			if (is_ereg(dst_reg) || is_ereg(src_reg) ||
-			    /* We have to add extra byte for x86 SIL, DIL regs */
-			    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
-				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
-			else
-				EMIT1(0x88);
-			goto stx;
 		case BPF_STX | BPF_MEM | BPF_H:
-			if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
-			else
-				EMIT2(0x66, 0x89);
-			goto stx;
 		case BPF_STX | BPF_MEM | BPF_W:
-			if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
-			else
-				EMIT1(0x89);
-			goto stx;
 		case BPF_STX | BPF_MEM | BPF_DW:
-			EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
-stx:			if (is_imm8(insn->off))
-				EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
-			else
-				EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
-					    insn->off);
+			emit_stx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
 			break;
 
 			/* LDX: dst_reg = *(u8*)(src_reg + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
-			/* Emit 'movzx rax, byte ptr [rax + off]' */
-			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
-			goto ldx;
+		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
 		case BPF_LDX | BPF_MEM | BPF_H:
-			/* Emit 'movzx rax, word ptr [rax + off]' */
-			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
-			goto ldx;
+		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
 		case BPF_LDX | BPF_MEM | BPF_W:
-			/* Emit 'mov eax, dword ptr [rax+0x14]' */
-			if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
-			else
-				EMIT1(0x8B);
-			goto ldx;
+		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 		case BPF_LDX | BPF_MEM | BPF_DW:
-			/* Emit 'mov rax, qword ptr [rax+0x14]' */
-			EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
-ldx:			/*
-			 * If insn->off == 0 we can save one extra byte, but
-			 * special case of x86 R13 which always needs an offset
-			 * is not worth the hassle
-			 */
-			if (is_imm8(insn->off))
-				EMIT2(add_2reg(0x40, src_reg, dst_reg), insn->off);
-			else
-				EMIT1_off32(add_2reg(0x80, src_reg, dst_reg),
-					    insn->off);
+		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+			emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
+			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
+				struct exception_table_entry *ex;
+				u8 *_insn = image + proglen;
+				s64 delta;
+
+				if (!bpf_prog->aux->extable)
+					break;
+
+				if (excnt >= bpf_prog->aux->num_exentries) {
+					pr_err("ex gen bug\n");
+					return -EFAULT;
+				}
+				ex = &bpf_prog->aux->extable[excnt++];
+
+				delta = _insn - (u8 *)&ex->insn;
+				if (!is_simm32(delta)) {
+					pr_err("extable->insn doesn't fit into 32-bit\n");
+					return -EFAULT;
+				}
+				ex->insn = delta;
+
+				delta = (u8 *)ex_handler_bpf - (u8 *)&ex->handler;
+				if (!is_simm32(delta)) {
+					pr_err("extable->handler doesn't fit into 32-bit\n");
+					return -EFAULT;
+				}
+				ex->handler = delta;
+
+				if (dst_reg > BPF_REG_9) {
+					pr_err("verifier error\n");
+					return -EFAULT;
+				}
+				/*
+				 * Compute size of x86 insn and its target dest x86 register.
+				 * ex_handler_bpf() will use lower 8 bits to adjust
+				 * pt_regs->ip to jump over this x86 instruction
+				 * and upper bits to figure out which pt_regs to zero out.
+				 * End result: x86 insn "mov rbx, qword ptr [rax+0x14]"
+				 * of 4 bytes will be ignored and rbx will be zero inited.
+				 */
+				ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8);
+			}
 			break;
 
 			/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
@@ -827,17 +1088,16 @@ xadd:			if (is_imm8(insn->off))
 			/* call */
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
-			jmp_offset = func - (image + addrs[i]);
-			if (!imm32 || !is_simm32(jmp_offset)) {
-				pr_err("unsupported BPF func %d addr %p image %p\n",
-				       imm32, func, image);
+			if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
 				return -EINVAL;
-			}
-			EMIT1_off32(0xE8, jmp_offset);
 			break;
 
 		case BPF_JMP | BPF_TAIL_CALL:
-			emit_bpf_tail_call(&prog);
+			if (imm32)
+				emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
+							  &prog, addrs[i], image);
+			else
+				emit_bpf_tail_call_indirect(&prog);
 			break;
 
 			/* cond jump */
@@ -909,6 +1169,16 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP32 | BPF_JSLT | BPF_K:
 		case BPF_JMP32 | BPF_JSGE | BPF_K:
 		case BPF_JMP32 | BPF_JSLE | BPF_K:
+			/* test dst_reg, dst_reg to save one extra byte */
+			if (imm32 == 0) {
+				if (BPF_CLASS(insn->code) == BPF_JMP)
+					EMIT1(add_2mod(0x48, dst_reg, dst_reg));
+				else if (is_ereg(dst_reg))
+					EMIT1(add_2mod(0x40, dst_reg, dst_reg));
+				EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg));
+				goto emit_cond_jmp;
+			}
+
 			/* cmp dst_reg, imm8/32 */
 			if (BPF_CLASS(insn->code) == BPF_JMP)
 				EMIT1(add_1mod(0x48, dst_reg));
@@ -1048,9 +1318,218 @@ emit_jmp:
 		addrs[i] = proglen;
 		prog = temp;
 	}
+
+	if (image && excnt != bpf_prog->aux->num_exentries) {
+		pr_err("extable is not populated\n");
+		return -EFAULT;
+	}
 	return proglen;
 }
 
+static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args,
+		      int stack_size)
+{
+	int i;
+	/* Store function arguments to stack.
+	 * For a function that accepts two pointers the sequence will be:
+	 * mov QWORD PTR [rbp-0x10],rdi
+	 * mov QWORD PTR [rbp-0x8],rsi
+	 */
+	for (i = 0; i < min(nr_args, 6); i++)
+		emit_stx(prog, bytes_to_bpf_size(m->arg_size[i]),
+			 BPF_REG_FP,
+			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
+			 -(stack_size - i * 8));
+}
+
+static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args,
+			 int stack_size)
+{
+	int i;
+
+	/* Restore function arguments from stack.
+	 * For a function that accepts two pointers the sequence will be:
+	 * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10]
+	 * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8]
+	 */
+	for (i = 0; i < min(nr_args, 6); i++)
+		emit_ldx(prog, bytes_to_bpf_size(m->arg_size[i]),
+			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
+			 BPF_REG_FP,
+			 -(stack_size - i * 8));
+}
+
+static int invoke_bpf(struct btf_func_model *m, u8 **pprog,
+		      struct bpf_prog **progs, int prog_cnt, int stack_size)
+{
+	u8 *prog = *pprog;
+	int cnt = 0, i;
+
+	for (i = 0; i < prog_cnt; i++) {
+		if (emit_call(&prog, __bpf_prog_enter, prog))
+			return -EINVAL;
+		/* remember prog start time returned by __bpf_prog_enter */
+		emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
+
+		/* arg1: lea rdi, [rbp - stack_size] */
+		EMIT4(0x48, 0x8D, 0x7D, -stack_size);
+		/* arg2: progs[i]->insnsi for interpreter */
+		if (!progs[i]->jited)
+			emit_mov_imm64(&prog, BPF_REG_2,
+				       (long) progs[i]->insnsi >> 32,
+				       (u32) (long) progs[i]->insnsi);
+		/* call JITed bpf program or interpreter */
+		if (emit_call(&prog, progs[i]->bpf_func, prog))
+			return -EINVAL;
+
+		/* arg1: mov rdi, progs[i] */
+		emit_mov_imm64(&prog, BPF_REG_1, (long) progs[i] >> 32,
+			       (u32) (long) progs[i]);
+		/* arg2: mov rsi, rbx <- start time in nsec */
+		emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
+		if (emit_call(&prog, __bpf_prog_exit, prog))
+			return -EINVAL;
+	}
+	*pprog = prog;
+	return 0;
+}
+
+/* Example:
+ * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
+ * its 'struct btf_func_model' will be nr_args=2
+ * The assembly code when eth_type_trans is executing after trampoline:
+ *
+ * push rbp
+ * mov rbp, rsp
+ * sub rsp, 16                     // space for skb and dev
+ * push rbx                        // temp regs to pass start time
+ * mov qword ptr [rbp - 16], rdi   // save skb pointer to stack
+ * mov qword ptr [rbp - 8], rsi    // save dev pointer to stack
+ * call __bpf_prog_enter           // rcu_read_lock and preempt_disable
+ * mov rbx, rax                    // remember start time in bpf stats are enabled
+ * lea rdi, [rbp - 16]             // R1==ctx of bpf prog
+ * call addr_of_jited_FENTRY_prog
+ * movabsq rdi, 64bit_addr_of_struct_bpf_prog  // unused if bpf stats are off
+ * mov rsi, rbx                    // prog start time
+ * call __bpf_prog_exit            // rcu_read_unlock, preempt_enable and stats math
+ * mov rdi, qword ptr [rbp - 16]   // restore skb pointer from stack
+ * mov rsi, qword ptr [rbp - 8]    // restore dev pointer from stack
+ * pop rbx
+ * leave
+ * ret
+ *
+ * eth_type_trans has 5 byte nop at the beginning. These 5 bytes will be
+ * replaced with 'call generated_bpf_trampoline'. When it returns
+ * eth_type_trans will continue executing with original skb and dev pointers.
+ *
+ * The assembly code when eth_type_trans is called from trampoline:
+ *
+ * push rbp
+ * mov rbp, rsp
+ * sub rsp, 24                     // space for skb, dev, return value
+ * push rbx                        // temp regs to pass start time
+ * mov qword ptr [rbp - 24], rdi   // save skb pointer to stack
+ * mov qword ptr [rbp - 16], rsi   // save dev pointer to stack
+ * call __bpf_prog_enter           // rcu_read_lock and preempt_disable
+ * mov rbx, rax                    // remember start time if bpf stats are enabled
+ * lea rdi, [rbp - 24]             // R1==ctx of bpf prog
+ * call addr_of_jited_FENTRY_prog  // bpf prog can access skb and dev
+ * movabsq rdi, 64bit_addr_of_struct_bpf_prog  // unused if bpf stats are off
+ * mov rsi, rbx                    // prog start time
+ * call __bpf_prog_exit            // rcu_read_unlock, preempt_enable and stats math
+ * mov rdi, qword ptr [rbp - 24]   // restore skb pointer from stack
+ * mov rsi, qword ptr [rbp - 16]   // restore dev pointer from stack
+ * call eth_type_trans+5           // execute body of eth_type_trans
+ * mov qword ptr [rbp - 8], rax    // save return value
+ * call __bpf_prog_enter           // rcu_read_lock and preempt_disable
+ * mov rbx, rax                    // remember start time in bpf stats are enabled
+ * lea rdi, [rbp - 24]             // R1==ctx of bpf prog
+ * call addr_of_jited_FEXIT_prog   // bpf prog can access skb, dev, return value
+ * movabsq rdi, 64bit_addr_of_struct_bpf_prog  // unused if bpf stats are off
+ * mov rsi, rbx                    // prog start time
+ * call __bpf_prog_exit            // rcu_read_unlock, preempt_enable and stats math
+ * mov rax, qword ptr [rbp - 8]    // restore eth_type_trans's return value
+ * pop rbx
+ * leave
+ * add rsp, 8                      // skip eth_type_trans's frame
+ * ret                             // return to its caller
+ */
+int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
+				struct bpf_prog **fentry_progs, int fentry_cnt,
+				struct bpf_prog **fexit_progs, int fexit_cnt,
+				void *orig_call)
+{
+	int cnt = 0, nr_args = m->nr_args;
+	int stack_size = nr_args * 8;
+	u8 *prog;
+
+	/* x86-64 supports up to 6 arguments. 7+ can be added in the future */
+	if (nr_args > 6)
+		return -ENOTSUPP;
+
+	if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
+	    (flags & BPF_TRAMP_F_SKIP_FRAME))
+		return -EINVAL;
+
+	if (flags & BPF_TRAMP_F_CALL_ORIG)
+		stack_size += 8; /* room for return value of orig_call */
+
+	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+		/* skip patched call instruction and point orig_call to actual
+		 * body of the kernel function.
+		 */
+		orig_call += X86_PATCH_SIZE;
+
+	prog = image;
+
+	EMIT1(0x55);		 /* push rbp */
+	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
+	EMIT1(0x53);		 /* push rbx */
+
+	save_regs(m, &prog, nr_args, stack_size);
+
+	if (fentry_cnt)
+		if (invoke_bpf(m, &prog, fentry_progs, fentry_cnt, stack_size))
+			return -EINVAL;
+
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
+		if (fentry_cnt)
+			restore_regs(m, &prog, nr_args, stack_size);
+
+		/* call original function */
+		if (emit_call(&prog, orig_call, prog))
+			return -EINVAL;
+		/* remember return value in a stack for bpf prog to access */
+		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
+	}
+
+	if (fexit_cnt)
+		if (invoke_bpf(m, &prog, fexit_progs, fexit_cnt, stack_size))
+			return -EINVAL;
+
+	if (flags & BPF_TRAMP_F_RESTORE_REGS)
+		restore_regs(m, &prog, nr_args, stack_size);
+
+	if (flags & BPF_TRAMP_F_CALL_ORIG)
+		/* restore original return value back into RAX */
+		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
+
+	EMIT1(0x5B); /* pop rbx */
+	EMIT1(0xC9); /* leave */
+	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+		/* skip our return address and return to parent */
+		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
+	EMIT1(0xC3); /* ret */
+	/* One half of the page has active running trampoline.
+	 * Another half is an area for next trampoline.
+	 * Make sure the trampoline generation logic doesn't overflow.
+	 */
+	if (WARN_ON_ONCE(prog - (u8 *)image > PAGE_SIZE / 2 - BPF_INSN_SAFETY))
+		return -EFAULT;
+	return 0;
+}
+
 struct x64_jit_data {
 	struct bpf_binary_header *header;
 	int *addrs;
@@ -1148,12 +1627,24 @@ out_image:
 			break;
 		}
 		if (proglen == oldproglen) {
-			header = bpf_jit_binary_alloc(proglen, &image,
-						      1, jit_fill_hole);
+			/*
+			 * The number of entries in extable is the number of BPF_LDX
+			 * insns that access kernel memory via "pointer to BTF type".
+			 * The verifier changed their opcode from LDX|MEM|size
+			 * to LDX|PROBE_MEM|size to make JITing easier.
+			 */
+			u32 align = __alignof__(struct exception_table_entry);
+			u32 extable_size = prog->aux->num_exentries *
+				sizeof(struct exception_table_entry);
+
+			/* allocate module memory for x86 insns and extable */
+			header = bpf_jit_binary_alloc(roundup(proglen, align) + extable_size,
+						      &image, align, jit_fill_hole);
 			if (!header) {
 				prog = orig_prog;
 				goto out_addrs;
 			}
+			prog->aux->extable = (void *) image + roundup(proglen, align);
 		}
 		oldproglen = proglen;
 		cond_resched();
@@ -1164,6 +1655,7 @@ out_image:
 
 	if (image) {
 		if (!prog->is_func || extra_pass) {
+			bpf_tail_call_direct_fixup(prog);
 			bpf_jit_binary_lock_ro(header);
 		} else {
 			jit_data->addrs = addrs;
diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h
index 71e8a67337e2..276cf79b5d24 100644
--- a/arch/x86/oprofile/op_x86_model.h
+++ b/arch/x86/oprofile/op_x86_model.h
@@ -67,13 +67,13 @@ static inline void op_x86_warn_in_use(int counter)
 	 * cannot be monitored by any other counter, contact your
 	 * hardware or BIOS vendor.
 	 */
-	pr_warning("oprofile: counter #%d on cpu #%d may already be used\n",
-		   counter, smp_processor_id());
+	pr_warn("oprofile: counter #%d on cpu #%d may already be used\n",
+		counter, smp_processor_id());
 }
 
 static inline void op_x86_warn_reserved(int counter)
 {
-	pr_warning("oprofile: counter #%d is already reserved\n", counter);
+	pr_warn("oprofile: counter #%d is already reserved\n", counter);
 }
 
 extern u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c
index 6d193bb36021..089413cd944e 100644
--- a/arch/x86/platform/olpc/olpc-xo15-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo15-sci.c
@@ -39,7 +39,7 @@ static int set_lid_wake_behavior(bool wake_on_close)
 
 	status = acpi_execute_simple_method(NULL, "\\_SB.PCI0.LID.LIDW", wake_on_close);
 	if (ACPI_FAILURE(status)) {
-		pr_warning(PFX "failed to set lid behavior\n");
+		pr_warn(PFX "failed to set lid behavior\n");
 		return 1;
 	}
 
diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c
index bf6016f8db4e..6259563760f9 100644
--- a/arch/x86/platform/sfi/sfi.c
+++ b/arch/x86/platform/sfi/sfi.c
@@ -26,8 +26,7 @@ static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 static void __init mp_sfi_register_lapic(u8 id)
 {
 	if (MAX_LOCAL_APIC - id <= 0) {
-		pr_warning("Processor #%d invalid (max %d)\n",
-			id, MAX_LOCAL_APIC);
+		pr_warn("Processor #%d invalid (max %d)\n", id, MAX_LOCAL_APIC);
 		return;
 	}
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 548d1e0a5ba1..33b0e20df7fc 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -412,7 +412,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 
 		remap_range_size = xen_find_pfn_range(&remap_pfn);
 		if (!remap_range_size) {
-			pr_warning("Unable to find available pfn range, not remapping identity pages\n");
+			pr_warn("Unable to find available pfn range, not remapping identity pages\n");
 			xen_set_identity_and_release_chunk(cur_pfn,
 						cur_pfn + left, nr_pages);
 			break;
author	Arnaldo Carvalho de Melo <acme@redhat.com>	2019-11-26 15:06:19 +0100
committer	Arnaldo Carvalho de Melo <acme@redhat.com>	2019-11-26 15:06:19 +0100
commit	2ea352d5960ad469f5712cf3e293db97beac4e01 (patch)
tree	c24ae19073f2884867b310ee193d36a82075b60f /arch/x86
parent	Merge branch 'x86/core' into perf/core, to resolve conflicts and to pick up c... (diff)
parent	Merge tag 'for-linus-5.5-1' of git://github.com/cminyard/linux-ipmi (diff)
download	linux-2ea352d5960ad469f5712cf3e293db97beac4e01.tar.xz linux-2ea352d5960ad469f5712cf3e293db97beac4e01.zip