Merge branch 'linus' into x86/urgent, to pick up dependent changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

85 files changed, 1263 insertions, 1405 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index de071d7e67b6..6bc9dd6e7534 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -22,7 +22,7 @@ config X86_64
 	def_bool y
 	depends on 64BIT
 	# Options that are inherently 64-bit kernel only:
-	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_SUPPORTS_INT128
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_SOFT_DIRTY
@@ -44,11 +44,9 @@ config X86
 	#
 	select ACPI_LEGACY_TABLES_LOOKUP	if ACPI
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
-	select ANON_INODES
 	select ARCH_32BIT_OFF_T			if X86_32
 	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_CLOCKSOURCE_INIT
-	select ARCH_DISCARD_MEMBLOCK
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
@@ -304,9 +302,6 @@ config ZONE_DMA32
 config AUDIT_ARCH
 	def_bool y if X86_64
 
-config ARCH_SUPPORTS_OPTIMIZED_INLINING
-	def_bool y
-
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 15d0fbe27872..f730680dc818 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -266,20 +266,6 @@ config CPA_DEBUG
 	---help---
 	  Do change_page_attr() self-tests every 30 seconds.
 
-config OPTIMIZE_INLINING
-	bool "Allow gcc to uninline functions marked 'inline'"
-	---help---
-	  This option determines if the kernel forces gcc to inline the functions
-	  developers have marked 'inline'. Doing so takes away freedom from gcc to
-	  do what it thinks is best, which is desirable for the gcc 3.x series of
-	  compilers. The gcc 4.x series have a rewritten inlining algorithm and
-	  enabling this option will generate a smaller kernel there. Hopefully
-	  this algorithm is so good that allowing gcc 4.x and above to make the
-	  decision will become the default in the future. Until then this option
-	  is there to test gcc for this.
-
-	  If unsure, say N.
-
 config DEBUG_ENTRY
 	bool "Debug low-level entry code"
 	depends on DEBUG_KERNEL
diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c
index 3ea71b871813..bdeee1b830be 100644
--- a/arch/x86/crypto/aegis128-aesni-glue.c
+++ b/arch/x86/crypto/aegis128-aesni-glue.c
@@ -11,8 +11,8 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
@@ -242,131 +242,35 @@ static void crypto_aegis128_aesni_exit_tfm(struct crypto_aead *aead)
 {
 }
 
-static int cryptd_aegis128_aesni_setkey(struct crypto_aead *aead,
-					const u8 *key, unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-
-static int cryptd_aegis128_aesni_setauthsize(struct crypto_aead *aead,
-					     unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-
-static int cryptd_aegis128_aesni_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-
-static int cryptd_aegis128_aesni_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-
-static int cryptd_aegis128_aesni_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__aegis128-aesni", CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-
-static void cryptd_aegis128_aesni_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
-static struct aead_alg crypto_aegis128_aesni_alg[] = {
-	{
-		.setkey = crypto_aegis128_aesni_setkey,
-		.setauthsize = crypto_aegis128_aesni_setauthsize,
-		.encrypt = crypto_aegis128_aesni_encrypt,
-		.decrypt = crypto_aegis128_aesni_decrypt,
-		.init = crypto_aegis128_aesni_init_tfm,
-		.exit = crypto_aegis128_aesni_exit_tfm,
-
-		.ivsize = AEGIS128_NONCE_SIZE,
-		.maxauthsize = AEGIS128_MAX_AUTH_SIZE,
-		.chunksize = AEGIS128_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_INTERNAL,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct aegis_ctx) +
-				__alignof__(struct aegis_ctx),
-			.cra_alignmask = 0,
-
-			.cra_name = "__aegis128",
-			.cra_driver_name = "__aegis128-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
-	}, {
-		.setkey = cryptd_aegis128_aesni_setkey,
-		.setauthsize = cryptd_aegis128_aesni_setauthsize,
-		.encrypt = cryptd_aegis128_aesni_encrypt,
-		.decrypt = cryptd_aegis128_aesni_decrypt,
-		.init = cryptd_aegis128_aesni_init_tfm,
-		.exit = cryptd_aegis128_aesni_exit_tfm,
-
-		.ivsize = AEGIS128_NONCE_SIZE,
-		.maxauthsize = AEGIS128_MAX_AUTH_SIZE,
-		.chunksize = AEGIS128_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_ASYNC,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct cryptd_aead *),
-			.cra_alignmask = 0,
-
-			.cra_priority = 400,
-
-			.cra_name = "aegis128",
-			.cra_driver_name = "aegis128-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
+static struct aead_alg crypto_aegis128_aesni_alg = {
+	.setkey = crypto_aegis128_aesni_setkey,
+	.setauthsize = crypto_aegis128_aesni_setauthsize,
+	.encrypt = crypto_aegis128_aesni_encrypt,
+	.decrypt = crypto_aegis128_aesni_decrypt,
+	.init = crypto_aegis128_aesni_init_tfm,
+	.exit = crypto_aegis128_aesni_exit_tfm,
+
+	.ivsize = AEGIS128_NONCE_SIZE,
+	.maxauthsize = AEGIS128_MAX_AUTH_SIZE,
+	.chunksize = AEGIS128_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_INTERNAL,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct aegis_ctx) +
+			       __alignof__(struct aegis_ctx),
+		.cra_alignmask = 0,
+		.cra_priority = 400,
+
+		.cra_name = "__aegis128",
+		.cra_driver_name = "__aegis128-aesni",
+
+		.cra_module = THIS_MODULE,
 	}
 };
 
+static struct simd_aead_alg *simd_alg;
+
 static int __init crypto_aegis128_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
@@ -374,14 +278,13 @@ static int __init crypto_aegis128_aesni_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_aegis128_aesni_alg,
-				     ARRAY_SIZE(crypto_aegis128_aesni_alg));
+	return simd_register_aeads_compat(&crypto_aegis128_aesni_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_aegis128_aesni_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_aegis128_aesni_alg,
-				ARRAY_SIZE(crypto_aegis128_aesni_alg));
+	simd_unregister_aeads(&crypto_aegis128_aesni_alg, 1, &simd_alg);
 }
 
 module_init(crypto_aegis128_aesni_module_init);
diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c
index 1b1b39c66c5e..80d917f7e467 100644
--- a/arch/x86/crypto/aegis128l-aesni-glue.c
+++ b/arch/x86/crypto/aegis128l-aesni-glue.c
@@ -11,8 +11,8 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
@@ -242,131 +242,35 @@ static void crypto_aegis128l_aesni_exit_tfm(struct crypto_aead *aead)
 {
 }
 
-static int cryptd_aegis128l_aesni_setkey(struct crypto_aead *aead,
-					 const u8 *key, unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-
-static int cryptd_aegis128l_aesni_setauthsize(struct crypto_aead *aead,
-					      unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-
-static int cryptd_aegis128l_aesni_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-
-static int cryptd_aegis128l_aesni_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-
-static int cryptd_aegis128l_aesni_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__aegis128l-aesni", CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-
-static void cryptd_aegis128l_aesni_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
-static struct aead_alg crypto_aegis128l_aesni_alg[] = {
-	{
-		.setkey = crypto_aegis128l_aesni_setkey,
-		.setauthsize = crypto_aegis128l_aesni_setauthsize,
-		.encrypt = crypto_aegis128l_aesni_encrypt,
-		.decrypt = crypto_aegis128l_aesni_decrypt,
-		.init = crypto_aegis128l_aesni_init_tfm,
-		.exit = crypto_aegis128l_aesni_exit_tfm,
-
-		.ivsize = AEGIS128L_NONCE_SIZE,
-		.maxauthsize = AEGIS128L_MAX_AUTH_SIZE,
-		.chunksize = AEGIS128L_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_INTERNAL,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct aegis_ctx) +
-				__alignof__(struct aegis_ctx),
-			.cra_alignmask = 0,
-
-			.cra_name = "__aegis128l",
-			.cra_driver_name = "__aegis128l-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
-	}, {
-		.setkey = cryptd_aegis128l_aesni_setkey,
-		.setauthsize = cryptd_aegis128l_aesni_setauthsize,
-		.encrypt = cryptd_aegis128l_aesni_encrypt,
-		.decrypt = cryptd_aegis128l_aesni_decrypt,
-		.init = cryptd_aegis128l_aesni_init_tfm,
-		.exit = cryptd_aegis128l_aesni_exit_tfm,
-
-		.ivsize = AEGIS128L_NONCE_SIZE,
-		.maxauthsize = AEGIS128L_MAX_AUTH_SIZE,
-		.chunksize = AEGIS128L_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_ASYNC,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct cryptd_aead *),
-			.cra_alignmask = 0,
-
-			.cra_priority = 400,
-
-			.cra_name = "aegis128l",
-			.cra_driver_name = "aegis128l-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
+static struct aead_alg crypto_aegis128l_aesni_alg = {
+	.setkey = crypto_aegis128l_aesni_setkey,
+	.setauthsize = crypto_aegis128l_aesni_setauthsize,
+	.encrypt = crypto_aegis128l_aesni_encrypt,
+	.decrypt = crypto_aegis128l_aesni_decrypt,
+	.init = crypto_aegis128l_aesni_init_tfm,
+	.exit = crypto_aegis128l_aesni_exit_tfm,
+
+	.ivsize = AEGIS128L_NONCE_SIZE,
+	.maxauthsize = AEGIS128L_MAX_AUTH_SIZE,
+	.chunksize = AEGIS128L_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_INTERNAL,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct aegis_ctx) +
+			       __alignof__(struct aegis_ctx),
+		.cra_alignmask = 0,
+		.cra_priority = 400,
+
+		.cra_name = "__aegis128l",
+		.cra_driver_name = "__aegis128l-aesni",
+
+		.cra_module = THIS_MODULE,
 	}
 };
 
+static struct simd_aead_alg *simd_alg;
+
 static int __init crypto_aegis128l_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
@@ -374,14 +278,13 @@ static int __init crypto_aegis128l_aesni_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_aegis128l_aesni_alg,
-				     ARRAY_SIZE(crypto_aegis128l_aesni_alg));
+	return simd_register_aeads_compat(&crypto_aegis128l_aesni_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_aegis128l_aesni_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_aegis128l_aesni_alg,
-				ARRAY_SIZE(crypto_aegis128l_aesni_alg));
+	simd_unregister_aeads(&crypto_aegis128l_aesni_alg, 1, &simd_alg);
 }
 
 module_init(crypto_aegis128l_aesni_module_init);
diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c
index 6227ca3220a0..716eecb66bd5 100644
--- a/arch/x86/crypto/aegis256-aesni-glue.c
+++ b/arch/x86/crypto/aegis256-aesni-glue.c
@@ -11,8 +11,8 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
@@ -242,131 +242,35 @@ static void crypto_aegis256_aesni_exit_tfm(struct crypto_aead *aead)
 {
 }
 
-static int cryptd_aegis256_aesni_setkey(struct crypto_aead *aead,
-					const u8 *key, unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-
-static int cryptd_aegis256_aesni_setauthsize(struct crypto_aead *aead,
-					     unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-
-static int cryptd_aegis256_aesni_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-
-static int cryptd_aegis256_aesni_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-
-static int cryptd_aegis256_aesni_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__aegis256-aesni", CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-
-static void cryptd_aegis256_aesni_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
-static struct aead_alg crypto_aegis256_aesni_alg[] = {
-	{
-		.setkey = crypto_aegis256_aesni_setkey,
-		.setauthsize = crypto_aegis256_aesni_setauthsize,
-		.encrypt = crypto_aegis256_aesni_encrypt,
-		.decrypt = crypto_aegis256_aesni_decrypt,
-		.init = crypto_aegis256_aesni_init_tfm,
-		.exit = crypto_aegis256_aesni_exit_tfm,
-
-		.ivsize = AEGIS256_NONCE_SIZE,
-		.maxauthsize = AEGIS256_MAX_AUTH_SIZE,
-		.chunksize = AEGIS256_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_INTERNAL,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct aegis_ctx) +
-				__alignof__(struct aegis_ctx),
-			.cra_alignmask = 0,
-
-			.cra_name = "__aegis256",
-			.cra_driver_name = "__aegis256-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
-	}, {
-		.setkey = cryptd_aegis256_aesni_setkey,
-		.setauthsize = cryptd_aegis256_aesni_setauthsize,
-		.encrypt = cryptd_aegis256_aesni_encrypt,
-		.decrypt = cryptd_aegis256_aesni_decrypt,
-		.init = cryptd_aegis256_aesni_init_tfm,
-		.exit = cryptd_aegis256_aesni_exit_tfm,
-
-		.ivsize = AEGIS256_NONCE_SIZE,
-		.maxauthsize = AEGIS256_MAX_AUTH_SIZE,
-		.chunksize = AEGIS256_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_ASYNC,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct cryptd_aead *),
-			.cra_alignmask = 0,
-
-			.cra_priority = 400,
-
-			.cra_name = "aegis256",
-			.cra_driver_name = "aegis256-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
+static struct aead_alg crypto_aegis256_aesni_alg = {
+	.setkey = crypto_aegis256_aesni_setkey,
+	.setauthsize = crypto_aegis256_aesni_setauthsize,
+	.encrypt = crypto_aegis256_aesni_encrypt,
+	.decrypt = crypto_aegis256_aesni_decrypt,
+	.init = crypto_aegis256_aesni_init_tfm,
+	.exit = crypto_aegis256_aesni_exit_tfm,
+
+	.ivsize = AEGIS256_NONCE_SIZE,
+	.maxauthsize = AEGIS256_MAX_AUTH_SIZE,
+	.chunksize = AEGIS256_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_INTERNAL,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct aegis_ctx) +
+			       __alignof__(struct aegis_ctx),
+		.cra_alignmask = 0,
+		.cra_priority = 400,
+
+		.cra_name = "__aegis256",
+		.cra_driver_name = "__aegis256-aesni",
+
+		.cra_module = THIS_MODULE,
 	}
 };
 
+static struct simd_aead_alg *simd_alg;
+
 static int __init crypto_aegis256_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
@@ -374,14 +278,13 @@ static int __init crypto_aegis256_aesni_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_aegis256_aesni_alg,
-				    ARRAY_SIZE(crypto_aegis256_aesni_alg));
+	return simd_register_aeads_compat(&crypto_aegis256_aesni_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_aegis256_aesni_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_aegis256_aesni_alg,
-				ARRAY_SIZE(crypto_aegis256_aesni_alg));
+	simd_unregister_aeads(&crypto_aegis256_aesni_alg, 1, &simd_alg);
 }
 
 module_init(crypto_aegis256_aesni_module_init);
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 1e3d2102033a..21c246799aa5 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -25,14 +25,13 @@
 #include <linux/err.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
-#include <crypto/cryptd.h>
 #include <crypto/ctr.h>
 #include <crypto/b128ops.h>
 #include <crypto/gcm.h>
 #include <crypto/xts.h>
 #include <asm/cpu_device_id.h>
-#include <asm/fpu/api.h>
 #include <asm/crypto/aes.h>
+#include <asm/simd.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/simd.h>
@@ -333,7 +332,7 @@ static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx,
 		return -EINVAL;
 	}
 
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		err = crypto_aes_expand_key(ctx, in_key, key_len);
 	else {
 		kernel_fpu_begin();
@@ -354,7 +353,7 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		crypto_aes_encrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -367,7 +366,7 @@ static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		crypto_aes_decrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -643,29 +642,6 @@ static int xts_decrypt(struct skcipher_request *req)
 				   aes_ctx(ctx->raw_crypt_ctx));
 }
 
-static int rfc4106_init(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni",
-				       CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-
-static void rfc4106_exit(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
 static int
 rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
 {
@@ -710,15 +686,8 @@ static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
 	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
 }
 
-static int gcmaes_wrapper_set_key(struct crypto_aead *parent, const u8 *key,
-				  unsigned int key_len)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, key_len);
-}
-
+/* This is the Integrity Check Value (aka the authentication tag) length and can
+ * be 8, 12 or 16 bytes long. */
 static int common_rfc4106_set_authsize(struct crypto_aead *aead,
 				       unsigned int authsize)
 {
@@ -734,17 +703,6 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead,
 	return 0;
 }
 
-/* This is the Integrity Check Value (aka the authentication tag length and can
- * be 8, 12 or 16 bytes long. */
-static int gcmaes_wrapper_set_authsize(struct crypto_aead *parent,
-				       unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-
 static int generic_gcmaes_set_authsize(struct crypto_aead *tfm,
 				       unsigned int authsize)
 {
@@ -964,38 +922,6 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 	return gcmaes_decrypt(req, req->assoclen - 8, ctx->hash_subkey, iv,
 			      aes_ctx);
 }
-
-static int gcmaes_wrapper_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	tfm = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		tfm = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, tfm);
-
-	return crypto_aead_encrypt(req);
-}
-
-static int gcmaes_wrapper_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	tfm = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		tfm = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, tfm);
-
-	return crypto_aead_decrypt(req);
-}
 #endif
 
 static struct crypto_alg aesni_algs[] = { {
@@ -1148,31 +1074,7 @@ static int generic_gcmaes_decrypt(struct aead_request *req)
 			      aes_ctx);
 }
 
-static int generic_gcmaes_init(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__driver-generic-gcm-aes-aesni",
-				       CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-
-	return 0;
-}
-
-static void generic_gcmaes_exit(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
-static struct aead_alg aesni_aead_algs[] = { {
+static struct aead_alg aesni_aeads[] = { {
 	.setkey			= common_rfc4106_set_key,
 	.setauthsize		= common_rfc4106_set_authsize,
 	.encrypt		= helper_rfc4106_encrypt,
@@ -1180,8 +1082,9 @@ static struct aead_alg aesni_aead_algs[] = { {
 	.ivsize			= GCM_RFC4106_IV_SIZE,
 	.maxauthsize		= 16,
 	.base = {
-		.cra_name		= "__gcm-aes-aesni",
-		.cra_driver_name	= "__driver-gcm-aes-aesni",
+		.cra_name		= "__rfc4106(gcm(aes))",
+		.cra_driver_name	= "__rfc4106-gcm-aesni",
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize		= 1,
 		.cra_ctxsize		= sizeof(struct aesni_rfc4106_gcm_ctx),
@@ -1189,24 +1092,6 @@ static struct aead_alg aesni_aead_algs[] = { {
 		.cra_module		= THIS_MODULE,
 	},
 }, {
-	.init			= rfc4106_init,
-	.exit			= rfc4106_exit,
-	.setkey			= gcmaes_wrapper_set_key,
-	.setauthsize		= gcmaes_wrapper_set_authsize,
-	.encrypt		= gcmaes_wrapper_encrypt,
-	.decrypt		= gcmaes_wrapper_decrypt,
-	.ivsize			= GCM_RFC4106_IV_SIZE,
-	.maxauthsize		= 16,
-	.base = {
-		.cra_name		= "rfc4106(gcm(aes))",
-		.cra_driver_name	= "rfc4106-gcm-aesni",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct cryptd_aead *),
-		.cra_module		= THIS_MODULE,
-	},
-}, {
 	.setkey			= generic_gcmaes_set_key,
 	.setauthsize		= generic_gcmaes_set_authsize,
 	.encrypt		= generic_gcmaes_encrypt,
@@ -1214,38 +1099,21 @@ static struct aead_alg aesni_aead_algs[] = { {
 	.ivsize			= GCM_AES_IV_SIZE,
 	.maxauthsize		= 16,
 	.base = {
-		.cra_name		= "__generic-gcm-aes-aesni",
-		.cra_driver_name	= "__driver-generic-gcm-aes-aesni",
-		.cra_priority		= 0,
+		.cra_name		= "__gcm(aes)",
+		.cra_driver_name	= "__generic-gcm-aesni",
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize		= 1,
 		.cra_ctxsize		= sizeof(struct generic_gcmaes_ctx),
 		.cra_alignmask		= AESNI_ALIGN - 1,
 		.cra_module		= THIS_MODULE,
 	},
-}, {
-	.init			= generic_gcmaes_init,
-	.exit			= generic_gcmaes_exit,
-	.setkey			= gcmaes_wrapper_set_key,
-	.setauthsize		= gcmaes_wrapper_set_authsize,
-	.encrypt		= gcmaes_wrapper_encrypt,
-	.decrypt		= gcmaes_wrapper_decrypt,
-	.ivsize			= GCM_AES_IV_SIZE,
-	.maxauthsize		= 16,
-	.base = {
-		.cra_name		= "gcm(aes)",
-		.cra_driver_name	= "generic-gcm-aesni",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct cryptd_aead *),
-		.cra_module		= THIS_MODULE,
-	},
 } };
 #else
-static struct aead_alg aesni_aead_algs[0];
+static struct aead_alg aesni_aeads[0];
 #endif
 
+static struct simd_aead_alg *aesni_simd_aeads[ARRAY_SIZE(aesni_aeads)];
 
 static const struct x86_cpu_id aesni_cpu_id[] = {
 	X86_FEATURE_MATCH(X86_FEATURE_AES),
@@ -1253,23 +1121,9 @@ static const struct x86_cpu_id aesni_cpu_id[] = {
 };
 MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
 
-static void aesni_free_simds(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers) &&
-		    aesni_simd_skciphers[i]; i++)
-		simd_skcipher_free(aesni_simd_skciphers[i]);
-}
-
 static int __init aesni_init(void)
 {
-	struct simd_skcipher_alg *simd;
-	const char *basename;
-	const char *algname;
-	const char *drvname;
 	int err;
-	int i;
 
 	if (!x86_match_cpu(aesni_cpu_id))
 		return -ENODEV;
@@ -1304,36 +1158,22 @@ static int __init aesni_init(void)
 	if (err)
 		return err;
 
-	err = crypto_register_skciphers(aesni_skciphers,
-					ARRAY_SIZE(aesni_skciphers));
+	err = simd_register_skciphers_compat(aesni_skciphers,
+					     ARRAY_SIZE(aesni_skciphers),
+					     aesni_simd_skciphers);
 	if (err)
 		goto unregister_algs;
 
-	err = crypto_register_aeads(aesni_aead_algs,
-				    ARRAY_SIZE(aesni_aead_algs));
+	err = simd_register_aeads_compat(aesni_aeads, ARRAY_SIZE(aesni_aeads),
+					 aesni_simd_aeads);
 	if (err)
 		goto unregister_skciphers;
 
-	for (i = 0; i < ARRAY_SIZE(aesni_skciphers); i++) {
-		algname = aesni_skciphers[i].base.cra_name + 2;
-		drvname = aesni_skciphers[i].base.cra_driver_name + 2;
-		basename = aesni_skciphers[i].base.cra_driver_name;
-		simd = simd_skcipher_create_compat(algname, drvname, basename);
-		err = PTR_ERR(simd);
-		if (IS_ERR(simd))
-			goto unregister_simds;
-
-		aesni_simd_skciphers[i] = simd;
-	}
-
 	return 0;
 
-unregister_simds:
-	aesni_free_simds();
-	crypto_unregister_aeads(aesni_aead_algs, ARRAY_SIZE(aesni_aead_algs));
 unregister_skciphers:
-	crypto_unregister_skciphers(aesni_skciphers,
-				    ARRAY_SIZE(aesni_skciphers));
+	simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
+				  aesni_simd_skciphers);
 unregister_algs:
 	crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
 	return err;
@@ -1341,10 +1181,10 @@ unregister_algs:
 
 static void __exit aesni_exit(void)
 {
-	aesni_free_simds();
-	crypto_unregister_aeads(aesni_aead_algs, ARRAY_SIZE(aesni_aead_algs));
-	crypto_unregister_skciphers(aesni_skciphers,
-				    ARRAY_SIZE(aesni_skciphers));
+	simd_unregister_aeads(aesni_aeads, ARRAY_SIZE(aesni_aeads),
+			      aesni_simd_aeads);
+	simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
+				  aesni_simd_skciphers);
 	crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
 }
 
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 45c1c4143176..4967ad620775 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -12,10 +12,10 @@
 
 #include <crypto/algapi.h>
 #include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/fpu/api.h>
 #include <asm/simd.h>
 
 #define CHACHA_STATE_ALIGN 16
@@ -170,7 +170,7 @@ static int chacha_simd(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	int err;
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_chacha_crypt(req);
 
 	err = skcipher_walk_virt(&walk, req, true);
@@ -193,7 +193,7 @@ static int xchacha_simd(struct skcipher_request *req)
 	u8 real_iv[16];
 	int err;
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_xchacha_crypt(req);
 
 	err = skcipher_walk_virt(&walk, req, true);
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index c8d9cdacbf10..cb4ab6645106 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -32,10 +32,11 @@
 #include <linux/kernel.h>
 #include <linux/crc32.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
-#include <asm/fpu/api.h>
+#include <asm/simd.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
@@ -54,7 +55,7 @@ static u32 __attribute__((pure))
 	unsigned int iremainder;
 	unsigned int prealign;
 
-	if (len < PCLMUL_MIN_LEN + SCALE_F_MASK || !irq_fpu_usable())
+	if (len < PCLMUL_MIN_LEN + SCALE_F_MASK || !crypto_simd_usable())
 		return crc32_le(crc, p, len);
 
 	if ((long)p & SCALE_F_MASK) {
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 5773e1161072..a58fe217c856 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -29,10 +29,11 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
-#include <asm/fpu/internal.h>
+#include <asm/simd.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
@@ -177,7 +178,7 @@ static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data,
 	 * use faster PCL version if datasize is large enough to
 	 * overcome kernel fpu state save/restore overhead
 	 */
-	if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) {
+	if (len >= CRC32C_PCL_BREAKEVEN && crypto_simd_usable()) {
 		kernel_fpu_begin();
 		*crcp = crc_pcl(data, len, *crcp);
 		kernel_fpu_end();
@@ -189,7 +190,7 @@ static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data,
 static int __crc32c_pcl_intel_finup(u32 *crcp, const u8 *data, unsigned int len,
 				u8 *out)
 {
-	if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) {
+	if (len >= CRC32C_PCL_BREAKEVEN && crypto_simd_usable()) {
 		kernel_fpu_begin();
 		*(__le32 *)out = ~cpu_to_le32(crc_pcl(data, len, *crcp));
 		kernel_fpu_end();
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index 0e785c0b2354..3c81e15b0873 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -26,12 +26,13 @@
 #include <linux/module.h>
 #include <linux/crc-t10dif.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
-#include <asm/fpu/api.h>
 #include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
+#include <asm/simd.h>
 
 asmlinkage u16 crc_t10dif_pcl(u16 init_crc, const u8 *buf, size_t len);
 
@@ -53,7 +54,7 @@ static int chksum_update(struct shash_desc *desc, const u8 *data,
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	if (length >= 16 && irq_fpu_usable()) {
+	if (length >= 16 && crypto_simd_usable()) {
 		kernel_fpu_begin();
 		ctx->crc = crc_t10dif_pcl(ctx->crc, data, length);
 		kernel_fpu_end();
@@ -70,15 +71,14 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
-			u8 *out)
+static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out)
 {
-	if (len >= 16 && irq_fpu_usable()) {
+	if (len >= 16 && crypto_simd_usable()) {
 		kernel_fpu_begin();
-		*(__u16 *)out = crc_t10dif_pcl(*crcp, data, len);
+		*(__u16 *)out = crc_t10dif_pcl(crc, data, len);
 		kernel_fpu_end();
 	} else
-		*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+		*(__u16 *)out = crc_t10dif_generic(crc, data, len);
 	return 0;
 }
 
@@ -87,15 +87,13 @@ static int chksum_finup(struct shash_desc *desc, const u8 *data,
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	return __chksum_finup(&ctx->crc, data, len, out);
+	return __chksum_finup(ctx->crc, data, len, out);
 }
 
 static int chksum_digest(struct shash_desc *desc, const u8 *data,
 			 unsigned int length, u8 *out)
 {
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	return __chksum_finup(&ctx->crc, data, length, out);
+	return __chksum_finup(0, data, length, out);
 }
 
 static struct shash_alg alg = {
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 3582ae885ee1..e3f3e6fd9d65 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -19,8 +19,9 @@
 #include <crypto/cryptd.h>
 #include <crypto/gf128mul.h>
 #include <crypto/internal/hash.h>
-#include <asm/fpu/api.h>
+#include <crypto/internal/simd.h>
 #include <asm/cpu_device_id.h>
+#include <asm/simd.h>
 
 #define GHASH_BLOCK_SIZE	16
 #define GHASH_DIGEST_SIZE	16
@@ -171,7 +172,6 @@ static int ghash_async_init(struct ahash_request *req)
 	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
 	desc->tfm = child;
-	desc->flags = req->base.flags;
 	return crypto_shash_init(desc);
 }
 
@@ -182,7 +182,7 @@ static int ghash_async_update(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -200,7 +200,7 @@ static int ghash_async_final(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -241,7 +241,7 @@ static int ghash_async_digest(struct ahash_request *req)
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -251,7 +251,6 @@ static int ghash_async_digest(struct ahash_request *req)
 		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
 		desc->tfm = child;
-		desc->flags = req->base.flags;
 		return shash_ahash_digest(req, desc);
 	}
 }
diff --git a/arch/x86/crypto/morus1280-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c
index 6634907d6ccd..679627a2a824 100644
--- a/arch/x86/crypto/morus1280-avx2-glue.c
+++ b/arch/x86/crypto/morus1280-avx2-glue.c
@@ -12,6 +12,7 @@
  */
 
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/morus1280_glue.h>
 #include <linux/module.h>
 #include <asm/fpu/api.h>
@@ -35,7 +36,9 @@ asmlinkage void crypto_morus1280_avx2_dec_tail(void *state, const void *src,
 asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor,
 					    u64 assoclen, u64 cryptlen);
 
-MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400);
+MORUS1280_DECLARE_ALG(avx2, "morus1280-avx2", 400);
+
+static struct simd_aead_alg *simd_alg;
 
 static int __init crypto_morus1280_avx2_module_init(void)
 {
@@ -44,14 +47,13 @@ static int __init crypto_morus1280_avx2_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_morus1280_avx2_algs,
-				     ARRAY_SIZE(crypto_morus1280_avx2_algs));
+	return simd_register_aeads_compat(&crypto_morus1280_avx2_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_morus1280_avx2_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_morus1280_avx2_algs,
-				ARRAY_SIZE(crypto_morus1280_avx2_algs));
+	simd_unregister_aeads(&crypto_morus1280_avx2_alg, 1, &simd_alg);
 }
 
 module_init(crypto_morus1280_avx2_module_init);
diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c
index f40244eaf14d..c35c0638d0bb 100644
--- a/arch/x86/crypto/morus1280-sse2-glue.c
+++ b/arch/x86/crypto/morus1280-sse2-glue.c
@@ -12,6 +12,7 @@
  */
 
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/morus1280_glue.h>
 #include <linux/module.h>
 #include <asm/fpu/api.h>
@@ -35,7 +36,9 @@ asmlinkage void crypto_morus1280_sse2_dec_tail(void *state, const void *src,
 asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor,
 					    u64 assoclen, u64 cryptlen);
 
-MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350);
+MORUS1280_DECLARE_ALG(sse2, "morus1280-sse2", 350);
+
+static struct simd_aead_alg *simd_alg;
 
 static int __init crypto_morus1280_sse2_module_init(void)
 {
@@ -43,14 +46,13 @@ static int __init crypto_morus1280_sse2_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_morus1280_sse2_algs,
-				     ARRAY_SIZE(crypto_morus1280_sse2_algs));
+	return simd_register_aeads_compat(&crypto_morus1280_sse2_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_morus1280_sse2_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_morus1280_sse2_algs,
-				ARRAY_SIZE(crypto_morus1280_sse2_algs));
+	simd_unregister_aeads(&crypto_morus1280_sse2_alg, 1, &simd_alg);
 }
 
 module_init(crypto_morus1280_sse2_module_init);
diff --git a/arch/x86/crypto/morus1280_glue.c b/arch/x86/crypto/morus1280_glue.c
index 7e600f8bcdad..30fc1bd98ec3 100644
--- a/arch/x86/crypto/morus1280_glue.c
+++ b/arch/x86/crypto/morus1280_glue.c
@@ -11,7 +11,6 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/morus1280_glue.h>
@@ -205,90 +204,6 @@ void crypto_morus1280_glue_init_ops(struct crypto_aead *aead,
 }
 EXPORT_SYMBOL_GPL(crypto_morus1280_glue_init_ops);
 
-int cryptd_morus1280_glue_setkey(struct crypto_aead *aead, const u8 *key,
-				 unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_setkey);
-
-int cryptd_morus1280_glue_setauthsize(struct crypto_aead *aead,
-				      unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_setauthsize);
-
-int cryptd_morus1280_glue_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_encrypt);
-
-int cryptd_morus1280_glue_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_decrypt);
-
-int cryptd_morus1280_glue_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	const char *name = crypto_aead_alg(aead)->base.cra_driver_name;
-	char internal_name[CRYPTO_MAX_ALG_NAME];
-
-	if (snprintf(internal_name, CRYPTO_MAX_ALG_NAME, "__%s", name)
-			>= CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	cryptd_tfm = cryptd_alloc_aead(internal_name, CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_init_tfm);
-
-void cryptd_morus1280_glue_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_exit_tfm);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
 MODULE_DESCRIPTION("MORUS-1280 AEAD mode -- glue for x86 optimizations");
diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c
index 9afaf8f8565a..32da56b3bdad 100644
--- a/arch/x86/crypto/morus640-sse2-glue.c
+++ b/arch/x86/crypto/morus640-sse2-glue.c
@@ -12,6 +12,7 @@
  */
 
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/morus640_glue.h>
 #include <linux/module.h>
 #include <asm/fpu/api.h>
@@ -35,7 +36,9 @@ asmlinkage void crypto_morus640_sse2_dec_tail(void *state, const void *src,
 asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor,
 					   u64 assoclen, u64 cryptlen);
 
-MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400);
+MORUS640_DECLARE_ALG(sse2, "morus640-sse2", 400);
+
+static struct simd_aead_alg *simd_alg;
 
 static int __init crypto_morus640_sse2_module_init(void)
 {
@@ -43,14 +46,13 @@ static int __init crypto_morus640_sse2_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_morus640_sse2_algs,
-				     ARRAY_SIZE(crypto_morus640_sse2_algs));
+	return simd_register_aeads_compat(&crypto_morus640_sse2_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_morus640_sse2_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_morus640_sse2_algs,
-				ARRAY_SIZE(crypto_morus640_sse2_algs));
+	simd_unregister_aeads(&crypto_morus640_sse2_alg, 1, &simd_alg);
 }
 
 module_init(crypto_morus640_sse2_module_init);
diff --git a/arch/x86/crypto/morus640_glue.c b/arch/x86/crypto/morus640_glue.c
index cb3a81732016..1dea33d84426 100644
--- a/arch/x86/crypto/morus640_glue.c
+++ b/arch/x86/crypto/morus640_glue.c
@@ -11,7 +11,6 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/morus640_glue.h>
@@ -200,90 +199,6 @@ void crypto_morus640_glue_init_ops(struct crypto_aead *aead,
 }
 EXPORT_SYMBOL_GPL(crypto_morus640_glue_init_ops);
 
-int cryptd_morus640_glue_setkey(struct crypto_aead *aead, const u8 *key,
-				unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_setkey);
-
-int cryptd_morus640_glue_setauthsize(struct crypto_aead *aead,
-				     unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_setauthsize);
-
-int cryptd_morus640_glue_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_encrypt);
-
-int cryptd_morus640_glue_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_decrypt);
-
-int cryptd_morus640_glue_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	const char *name = crypto_aead_alg(aead)->base.cra_driver_name;
-	char internal_name[CRYPTO_MAX_ALG_NAME];
-
-	if (snprintf(internal_name, CRYPTO_MAX_ALG_NAME, "__%s", name)
-			>= CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	cryptd_tfm = cryptd_alloc_aead(internal_name, CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_init_tfm);
-
-void cryptd_morus640_glue_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_exit_tfm);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
 MODULE_DESCRIPTION("MORUS-640 AEAD mode -- glue for x86 optimizations");
diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
index 20d815ea4b6a..f7567cbd35b6 100644
--- a/arch/x86/crypto/nhpoly1305-avx2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -7,9 +7,10 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
-#include <asm/fpu/api.h>
+#include <asm/simd.h>
 
 asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
 			u8 hash[NH_HASH_BYTES]);
@@ -24,7 +25,7 @@ static void _nh_avx2(const u32 *key, const u8 *message, size_t message_len,
 static int nhpoly1305_avx2_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
 {
-	if (srclen < 64 || !irq_fpu_usable())
+	if (srclen < 64 || !crypto_simd_usable())
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
index ed68d164ce14..a661ede3b5cf 100644
--- a/arch/x86/crypto/nhpoly1305-sse2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -7,9 +7,10 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
-#include <asm/fpu/api.h>
+#include <asm/simd.h>
 
 asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
 			u8 hash[NH_HASH_BYTES]);
@@ -24,7 +25,7 @@ static void _nh_sse2(const u32 *key, const u8 *message, size_t message_len,
 static int nhpoly1305_sse2_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
 {
-	if (srclen < 64 || !irq_fpu_usable())
+	if (srclen < 64 || !crypto_simd_usable())
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 88cc01506c84..6eb65b237b3c 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -11,11 +11,11 @@
 
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/poly1305.h>
 #include <linux/crypto.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/fpu/api.h>
 #include <asm/simd.h>
 
 struct poly1305_simd_desc_ctx {
@@ -126,7 +126,7 @@ static int poly1305_simd_update(struct shash_desc *desc,
 	unsigned int bytes;
 
 	/* kernel_fpu_begin/end is costly, use fallback for small updates */
-	if (srclen <= 288 || !may_use_simd())
+	if (srclen <= 288 || !crypto_simd_usable())
 		return crypto_poly1305_update(desc, src, srclen);
 
 	kernel_fpu_begin();
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 7391c7de72c7..42f177afc33a 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -22,6 +22,7 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -29,7 +30,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
-#include <asm/fpu/api.h>
+#include <asm/simd.h>
 
 typedef void (sha1_transform_fn)(u32 *digest, const char *data,
 				unsigned int rounds);
@@ -39,7 +40,7 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
 		return crypto_sha1_update(desc, data, len);
 
@@ -57,7 +58,7 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
 static int sha1_finup(struct shash_desc *desc, const u8 *data,
 		      unsigned int len, u8 *out, sha1_transform_fn *sha1_xform)
 {
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		return crypto_sha1_finup(desc, data, len, out);
 
 	kernel_fpu_begin();
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 773a873d2b28..73867da3cbee 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -30,6 +30,7 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -37,8 +38,8 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
-#include <asm/fpu/api.h>
 #include <linux/string.h>
+#include <asm/simd.h>
 
 asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data,
 				       u64 rounds);
@@ -49,7 +50,7 @@ static int sha256_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
 		return crypto_sha256_update(desc, data, len);
 
@@ -67,7 +68,7 @@ static int sha256_update(struct shash_desc *desc, const u8 *data,
 static int sha256_finup(struct shash_desc *desc, const u8 *data,
 	      unsigned int len, u8 *out, sha256_transform_fn *sha256_xform)
 {
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		return crypto_sha256_finup(desc, data, len, out);
 
 	kernel_fpu_begin();
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index f1b811b60ba6..458356a3f124 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -28,16 +28,16 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/cryptohash.h>
+#include <linux/string.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha512_base.h>
-#include <asm/fpu/api.h>
-
-#include <linux/string.h>
+#include <asm/simd.h>
 
 asmlinkage void sha512_transform_ssse3(u64 *digest, const char *data,
 				       u64 rounds);
@@ -49,7 +49,7 @@ static int sha512_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
 		return crypto_sha512_update(desc, data, len);
 
@@ -67,7 +67,7 @@ static int sha512_update(struct shash_desc *desc, const u8 *data,
 static int sha512_finup(struct shash_desc *desc, const u8 *data,
 	      unsigned int len, u8 *out, sha512_transform_fn *sha512_xform)
 {
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		return crypto_sha512_finup(desc, data, len, out);
 
 	kernel_fpu_begin();
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 7bc105f47d21..a986b3c8294c 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -25,12 +25,14 @@
 #include <linux/uprobes.h>
 #include <linux/livepatch.h>
 #include <linux/syscalls.h>
+#include <linux/uaccess.h>
 
 #include <asm/desc.h>
 #include <asm/traps.h>
 #include <asm/vdso.h>
-#include <linux/uaccess.h>
 #include <asm/cpufeature.h>
+#include <asm/fpu/api.h>
+#include <asm/nospec-branch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -196,6 +198,13 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
 		exit_to_usermode_loop(regs, cached_flags);
 
+	/* Reload ti->flags; we may have rescheduled above. */
+	cached_flags = READ_ONCE(ti->flags);
+
+	fpregs_assert_state_consistent();
+	if (unlikely(cached_flags & _TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+
 #ifdef CONFIG_COMPAT
 	/*
 	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
@@ -212,6 +221,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 #endif
 
 	user_enter_irqoff();
+
+	mds_user_clear_cpu_buffers();
 }
 
 #define SYSCALL_EXIT_WORK_FLAGS				\
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 1f9607ed087c..4cd5f982b1e5 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -398,7 +398,12 @@
 384	i386	arch_prctl		sys_arch_prctl			__ia32_compat_sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents_time32	__ia32_compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq			__ia32_sys_rseq
-# don't use numbers 387 through 392, add new calls at the end
+387	i386	open_tree		sys_open_tree			__ia32_sys_open_tree
+388	i386	move_mount		sys_move_mount			__ia32_sys_move_mount
+389	i386	fsopen			sys_fsopen			__ia32_sys_fsopen
+390	i386	fsconfig		sys_fsconfig			__ia32_sys_fsconfig
+391	i386	fsmount			sys_fsmount			__ia32_sys_fsmount
+392	i386	fspick			sys_fspick			__ia32_sys_fspick
 393	i386	semget			sys_semget    			__ia32_sys_semget
 394	i386	semctl			sys_semctl    			__ia32_compat_sys_semctl
 395	i386	shmget			sys_shmget    			__ia32_sys_shmget
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 92ee0b4378d4..64ca0d06259a 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -343,6 +343,12 @@
 332	common	statx			__x64_sys_statx
 333	common	io_pgetevents		__x64_sys_io_pgetevents
 334	common	rseq			__x64_sys_rseq
+335	common	open_tree		__x64_sys_open_tree
+336	common	move_mount		__x64_sys_move_mount
+337	common	fsopen			__x64_sys_fsopen
+338	common	fsconfig		__x64_sys_fsconfig
+339	common	fsmount			__x64_sys_fsmount
+340	common	fspick			__x64_sys_fspick
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
 424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 7cdd7b13bbda..890a3fb5706f 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -23,7 +23,7 @@
 #include <linux/device.h>
 #include <linux/coredump.h>
 
-#include <asm-generic/sizes.h>
+#include <linux/sizes.h>
 #include <asm/perf_event.h>
 
 #include "../perf_event.h"
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 4d5fcd47ab75..629d1ee05599 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -221,8 +221,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 				 size_t frame_size,
 				 void __user **fpstate)
 {
-	struct fpu *fpu = &current->thread.fpu;
-	unsigned long sp;
+	unsigned long sp, fx_aligned, math_size;
 
 	/* Default to using normal stack */
 	sp = regs->sp;
@@ -236,15 +235,11 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 		 ksig->ka.sa.sa_restorer)
 		sp = (unsigned long) ksig->ka.sa.sa_restorer;
 
-	if (fpu->initialized) {
-		unsigned long fx_aligned, math_size;
-
-		sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
-		*fpstate = (struct _fpstate_32 __user *) sp;
-		if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
-				    math_size) < 0)
-			return (void __user *) -1L;
-	}
+	sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
+	*fpstate = (struct _fpstate_32 __user *) sp;
+	if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
+				     math_size) < 0)
+		return (void __user *) -1L;
 
 	sp -= frame_size;
 	/* Align the stack pointer according to the i386 ABI,
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 981ff9479648..75f27ee2c263 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -344,6 +344,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
@@ -382,5 +383,7 @@
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 #define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
+#define X86_BUG_MDS			X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
+#define X86_BUG_MSBDS_ONLY		X86_BUG(20) /* CPU is only affected by the  MSDBS variant of BUG_MDS */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index ce4d176b3d13..6b15a24930e0 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -13,14 +13,7 @@
 #include <asm/swiotlb.h>
 #include <linux/dma-contiguous.h>
 
-#ifdef CONFIG_ISA
-# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
-#else
-# define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
-#endif
-
 extern int iommu_merge;
-extern struct device x86_dma_fallback_dev;
 extern int panic_on_overflow;
 
 extern const struct dma_map_ops *dma_ops;
@@ -30,7 +23,4 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return dma_ops;
 }
 
-bool arch_dma_alloc_attrs(struct device **dev);
-#define arch_dma_alloc_attrs arch_dma_alloc_attrs
-
 #endif
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index b56d504af654..b774c52e5411 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -10,6 +10,7 @@
 
 #ifndef _ASM_X86_FPU_API_H
 #define _ASM_X86_FPU_API_H
+#include <linux/bottom_half.h>
 
 /*
  * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
@@ -21,6 +22,36 @@
 extern void kernel_fpu_begin(void);
 extern void kernel_fpu_end(void);
 extern bool irq_fpu_usable(void);
+extern void fpregs_mark_activate(void);
+
+/*
+ * Use fpregs_lock() while editing CPU's FPU registers or fpu->state.
+ * A context switch will (and softirq might) save CPU's FPU registers to
+ * fpu->state and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in
+ * a random state.
+ */
+static inline void fpregs_lock(void)
+{
+	preempt_disable();
+	local_bh_disable();
+}
+
+static inline void fpregs_unlock(void)
+{
+	local_bh_enable();
+	preempt_enable();
+}
+
+#ifdef CONFIG_X86_DEBUG_FPU
+extern void fpregs_assert_state_consistent(void);
+#else
+static inline void fpregs_assert_state_consistent(void) { }
+#endif
+
+/*
+ * Load the task FPU state before returning to userspace.
+ */
+extern void switch_fpu_return(void);
 
 /*
  * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 745a19d34f23..9e27fa05a7ae 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -14,6 +14,7 @@
 #include <linux/compat.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 
 #include <asm/user.h>
 #include <asm/fpu/api.h>
@@ -24,14 +25,12 @@
 /*
  * High level FPU state handling functions:
  */
-extern void fpu__initialize(struct fpu *fpu);
 extern void fpu__prepare_read(struct fpu *fpu);
 extern void fpu__prepare_write(struct fpu *fpu);
 extern void fpu__save(struct fpu *fpu);
-extern void fpu__restore(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
 extern void fpu__drop(struct fpu *fpu);
-extern int  fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu);
+extern int  fpu__copy(struct task_struct *dst, struct task_struct *src);
 extern void fpu__clear(struct fpu *fpu);
 extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
 extern int  dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
@@ -122,6 +121,21 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu);
 	err;								\
 })
 
+#define kernel_insn_err(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile("1:" #insn "\n\t"					\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
 #define kernel_insn(insn, output, input...)				\
 	asm volatile("1:" #insn "\n\t"					\
 		     "2:\n"						\
@@ -150,6 +164,14 @@ static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
 		kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
+static inline int copy_kernel_to_fxregs_err(struct fxregs_state *fx)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else
+		return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
 static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
 {
 	if (IS_ENABLED(CONFIG_X86_32))
@@ -163,6 +185,11 @@ static inline void copy_kernel_to_fregs(struct fregs_state *fx)
 	kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
+static inline int copy_kernel_to_fregs_err(struct fregs_state *fx)
+{
+	return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
 static inline int copy_user_to_fregs(struct fregs_state __user *fx)
 {
 	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
@@ -363,6 +390,21 @@ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
 }
 
 /*
+ * Restore xstate from kernel space xsave area, return an error code instead of
+ * an exception.
+ */
+static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err;
+
+	XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+
+	return err;
+}
+
+/*
  * These must be called with preempt disabled. Returns
  * 'true' if the FPU state is still intact and we can
  * keep registers active.
@@ -487,6 +529,25 @@ static inline void fpregs_activate(struct fpu *fpu)
 }
 
 /*
+ * Internal helper, do not use directly. Use switch_fpu_return() instead.
+ */
+static inline void __fpregs_load_activate(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+	int cpu = smp_processor_id();
+
+	if (WARN_ON_ONCE(current->mm == NULL))
+		return;
+
+	if (!fpregs_state_valid(fpu, cpu)) {
+		copy_kernel_to_fpregs(&fpu->state);
+		fpregs_activate(fpu);
+		fpu->last_cpu = cpu;
+	}
+	clear_thread_flag(TIF_NEED_FPU_LOAD);
+}
+
+/*
  * FPU state switching for scheduling.
  *
  * This is a two-stage process:
@@ -494,12 +555,23 @@ static inline void fpregs_activate(struct fpu *fpu)
  *  - switch_fpu_prepare() saves the old state.
  *    This is done within the context of the old process.
  *
- *  - switch_fpu_finish() restores the new state as
- *    necessary.
+ *  - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state
+ *    will get loaded on return to userspace, or when the kernel needs it.
+ *
+ * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers
+ * are saved in the current thread's FPU register state.
+ *
+ * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not
+ * hold current()'s FPU registers. It is required to load the
+ * registers before returning to userland or using the content
+ * otherwise.
+ *
+ * The FPU context is only stored/restored for a user task and
+ * ->mm is used to distinguish between kernel and user threads.
  */
 static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
+	if (static_cpu_has(X86_FEATURE_FPU) && current->mm) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
 		else
@@ -507,8 +579,7 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 
 		/* But leave fpu_fpregs_owner_ctx! */
 		trace_x86_fpu_regs_deactivated(old_fpu);
-	} else
-		old_fpu->last_cpu = -1;
+	}
 }
 
 /*
@@ -516,36 +587,32 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
  */
 
 /*
- * Set up the userspace FPU context for the new task, if the task
- * has used the FPU.
+ * Load PKRU from the FPU context if available. Delay loading of the
+ * complete FPU state until the return to userland.
  */
-static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
+static inline void switch_fpu_finish(struct fpu *new_fpu)
 {
-	bool preload = static_cpu_has(X86_FEATURE_FPU) &&
-		       new_fpu->initialized;
+	u32 pkru_val = init_pkru_value;
+	struct pkru_state *pk;
 
-	if (preload) {
-		if (!fpregs_state_valid(new_fpu, cpu))
-			copy_kernel_to_fpregs(&new_fpu->state);
-		fpregs_activate(new_fpu);
-	}
-}
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return;
 
-/*
- * Needs to be preemption-safe.
- *
- * NOTE! user_fpu_begin() must be used only immediately before restoring
- * the save state. It does not do any saving/restoring on its own. In
- * lazy FPU mode, it is just an optimization to avoid a #NM exception,
- * the task can lose the FPU right after preempt_enable().
- */
-static inline void user_fpu_begin(void)
-{
-	struct fpu *fpu = &current->thread.fpu;
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return;
 
-	preempt_disable();
-	fpregs_activate(fpu);
-	preempt_enable();
+	/*
+	 * PKRU state is switched eagerly because it needs to be valid before we
+	 * return to userland e.g. for a copy_to_user() operation.
+	 */
+	if (current->mm) {
+		pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU);
+		if (pk)
+			pkru_val = pk->pkru;
+	}
+	__write_pkru(pkru_val);
 }
 
 /*
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
index 44bbc39a57b3..7fb516b6893a 100644
--- a/arch/x86/include/asm/fpu/signal.h
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -22,7 +22,7 @@ int ia32_setup_frame(int sig, struct ksignal *ksig,
 
 extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
 			      struct task_struct *tsk);
-extern void convert_to_fxsr(struct task_struct *tsk,
+extern void convert_to_fxsr(struct fxregs_state *fxsave,
 			    const struct user_i387_ia32_struct *env);
 
 unsigned long
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 2e32e178e064..f098f6cab94b 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -294,15 +294,6 @@ struct fpu {
 	unsigned int			last_cpu;
 
 	/*
-	 * @initialized:
-	 *
-	 * This flag indicates whether this context is initialized: if the task
-	 * is not running then we can restore from this context, if the task
-	 * is running then we should save into this context.
-	 */
-	unsigned char			initialized;
-
-	/*
 	 * @avx512_timestamp:
 	 *
 	 * Records the timestamp of AVX512 use during last context switch.
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 48581988d78c..7e42b285c856 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -2,9 +2,11 @@
 #ifndef __ASM_X86_XSAVE_H
 #define __ASM_X86_XSAVE_H
 
+#include <linux/uaccess.h>
 #include <linux/types.h>
+
 #include <asm/processor.h>
-#include <linux/uaccess.h>
+#include <asm/user.h>
 
 /* Bit 63 of XCR0 is reserved for future expansion */
 #define XFEATURE_MASK_EXTEND	(~(XFEATURE_MASK_FPSSE | (1ULL << 63)))
@@ -46,8 +48,8 @@ extern void __init update_regset_xstate_info(unsigned int size,
 					     u64 xstate_mask);
 
 void fpu__xstate_clear_all_cpu_caps(void);
-void *get_xsave_addr(struct xregs_state *xsave, int xstate);
-const void *get_xsave_field_ptr(int xstate_field);
+void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
+const void *get_xsave_field_ptr(int xfeature_nr);
 int using_compacted_format(void);
 int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
 int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 7469d321f072..f65cfb48cfdd 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -17,8 +17,4 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
-
 #endif /* _ASM_X86_HUGETLB_H */
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 2bdbbbcfa393..cdf44aa9a501 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: GPL-2.0 */
 
 /*
  * This file contains definitions from Hyper-V Hypervisor Top-Level Functional
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 058e40fed167..8a0e56e1dcc9 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -6,6 +6,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/nospec-branch.h>
+
 /* Provide __cpuidle; we can't safely include <linux/cpu.h> */
 #define __cpuidle __attribute__((__section__(".cpuidle.text")))
 
@@ -54,11 +56,13 @@ static inline void native_irq_enable(void)
 
 static inline __cpuidle void native_safe_halt(void)
 {
+	mds_idle_clear_cpu_buffers();
 	asm volatile("sti; hlt": : :"memory");
 }
 
 static inline __cpuidle void native_halt(void)
 {
+	mds_idle_clear_cpu_buffers();
 	asm volatile("hlt": : :"memory");
 }
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1378518cf63f..88dd202c8b00 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_MSR_INDEX_H
 #define _ASM_X86_MSR_INDEX_H
 
+#include <linux/bits.h>
+
 /*
  * CPU model specific register (MSR) numbers.
  *
@@ -40,14 +42,14 @@
 /* Intel MSRs. Some also available on other CPUs */
 
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
-#define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_IBRS			BIT(0)	   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP_SHIFT		1	   /* Single Thread Indirect Branch Predictor (STIBP) bit */
-#define SPEC_CTRL_STIBP			(1 << SPEC_CTRL_STIBP_SHIFT)	/* STIBP mask */
+#define SPEC_CTRL_STIBP			BIT(SPEC_CTRL_STIBP_SHIFT)	/* STIBP mask */
 #define SPEC_CTRL_SSBD_SHIFT		2	   /* Speculative Store Bypass Disable bit */
-#define SPEC_CTRL_SSBD			(1 << SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
+#define SPEC_CTRL_SSBD			BIT(SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
-#define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
+#define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
 
 #define MSR_PPIN_CTL			0x0000004e
 #define MSR_PPIN			0x0000004f
@@ -69,20 +71,25 @@
 #define MSR_MTRRcap			0x000000fe
 
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
-#define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
-#define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
-#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	(1 << 3)   /* Skip L1D flush on vmentry */
-#define ARCH_CAP_SSB_NO			(1 << 4)   /*
-						    * Not susceptible to Speculative Store Bypass
-						    * attack, so no Speculative Store Bypass
-						    * control required.
-						    */
+#define ARCH_CAP_RDCL_NO		BIT(0)	/* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL		BIT(1)	/* Enhanced IBRS support */
+#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	BIT(3)	/* Skip L1D flush on vmentry */
+#define ARCH_CAP_SSB_NO			BIT(4)	/*
+						 * Not susceptible to Speculative Store Bypass
+						 * attack, so no Speculative Store Bypass
+						 * control required.
+						 */
+#define ARCH_CAP_MDS_NO			BIT(5)   /*
+						  * Not susceptible to
+						  * Microarchitectural Data
+						  * Sampling (MDS) vulnerabilities.
+						  */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
-#define L1D_FLUSH			(1 << 0)   /*
-						    * Writeback and invalidate the
-						    * L1 data cache.
-						    */
+#define L1D_FLUSH			BIT(0)	/*
+						 * Writeback and invalidate the
+						 * L1 data cache.
+						 */
 
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 39a2fb29378a..eb0f80ce8524 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -6,6 +6,7 @@
 #include <linux/sched/idle.h>
 
 #include <asm/cpufeature.h>
+#include <asm/nospec-branch.h>
 
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
@@ -40,6 +41,8 @@ static inline void __monitorx(const void *eax, unsigned long ecx,
 
 static inline void __mwait(unsigned long eax, unsigned long ecx)
 {
+	mds_idle_clear_cpu_buffers();
+
 	/* "mwait %eax, %ecx;" */
 	asm volatile(".byte 0x0f, 0x01, 0xc9;"
 		     :: "a" (eax), "c" (ecx));
@@ -74,6 +77,8 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 			    unsigned long ecx)
 {
+	/* No MDS buffer clear as this is AMD/HYGON only */
+
 	/* "mwaitx %eax, %ebx, %ecx;" */
 	asm volatile(".byte 0x0f, 0x01, 0xfb;"
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
@@ -81,6 +86,8 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
+	mds_idle_clear_cpu_buffers();
+
 	trace_hardirqs_on();
 	/* "mwait %eax, %ecx;" */
 	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index daf25b60c9e3..109f974f9835 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -308,6 +308,56 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+DECLARE_STATIC_KEY_FALSE(mds_user_clear);
+DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
+
+#include <asm/segment.h>
+
+/**
+ * mds_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * This uses the otherwise unused and obsolete VERW instruction in
+ * combination with microcode which triggers a CPU buffer flush when the
+ * instruction is executed.
+ */
+static inline void mds_clear_cpu_buffers(void)
+{
+	static const u16 ds = __KERNEL_DS;
+
+	/*
+	 * Has to be the memory-operand variant because only that
+	 * guarantees the CPU buffer flush functionality according to
+	 * documentation. The register-operand variant does not.
+	 * Works with any segment selector, but a valid writable
+	 * data segment is the fastest variant.
+	 *
+	 * "cc" clobber is required because VERW modifies ZF.
+	 */
+	asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc");
+}
+
+/**
+ * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_user_clear_cpu_buffers(void)
+{
+	if (static_branch_likely(&mds_user_clear))
+		mds_clear_cpu_buffers();
+}
+
+/**
+ * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_idle_clear_cpu_buffers(void)
+{
+	if (static_branch_likely(&mds_idle_clear))
+		mds_clear_cpu_buffers();
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3a221942f805..5e0509b41986 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -23,6 +23,8 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/x86_init.h>
+#include <asm/fpu/xstate.h>
+#include <asm/fpu/api.h>
 
 extern pgd_t early_top_pgt[PTRS_PER_PGD];
 int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
@@ -127,14 +129,29 @@ static inline int pte_dirty(pte_t pte)
 static inline u32 read_pkru(void)
 {
 	if (boot_cpu_has(X86_FEATURE_OSPKE))
-		return __read_pkru();
+		return rdpkru();
 	return 0;
 }
 
 static inline void write_pkru(u32 pkru)
 {
-	if (boot_cpu_has(X86_FEATURE_OSPKE))
-		__write_pkru(pkru);
+	struct pkru_state *pk;
+
+	if (!boot_cpu_has(X86_FEATURE_OSPKE))
+		return;
+
+	pk = get_xsave_addr(&current->thread.fpu.state.xsave, XFEATURE_PKRU);
+
+	/*
+	 * The PKRU value in xstate needs to be in sync with the value that is
+	 * written to the CPU. The FPU restore on return to userland would
+	 * otherwise load the previous value again.
+	 */
+	fpregs_lock();
+	if (pk)
+		pk->pkru = pkru;
+	__write_pkru(pkru);
+	fpregs_unlock();
 }
 
 static inline int pte_young(pte_t pte)
@@ -1358,6 +1375,12 @@ static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
 #define PKRU_WD_BIT 0x2
 #define PKRU_BITS_PER_PKEY 2
 
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+extern u32 init_pkru_value;
+#else
+#define init_pkru_value	0
+#endif
+
 static inline bool __pkru_allows_read(u32 pkru, u16 pkey)
 {
 	int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7e99ef67bff0..c34a35c78618 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -978,4 +978,10 @@ enum l1tf_mitigations {
 
 extern enum l1tf_mitigations l1tf_mitigation;
 
+enum mds_mitigations {
+	MDS_MITIGATION_OFF,
+	MDS_MITIGATION_FULL,
+	MDS_MITIGATION_VMWERV,
+};
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 43c029cdc3fe..0a3c4cab39db 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -92,7 +92,7 @@ static inline void native_write_cr8(unsigned long val)
 #endif
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-static inline u32 __read_pkru(void)
+static inline u32 rdpkru(void)
 {
 	u32 ecx = 0;
 	u32 edx, pkru;
@@ -107,7 +107,7 @@ static inline u32 __read_pkru(void)
 	return pkru;
 }
 
-static inline void __write_pkru(u32 pkru)
+static inline void wrpkru(u32 pkru)
 {
 	u32 ecx = 0, edx = 0;
 
@@ -118,8 +118,21 @@ static inline void __write_pkru(u32 pkru)
 	asm volatile(".byte 0x0f,0x01,0xef\n\t"
 		     : : "a" (pkru), "c"(ecx), "d"(edx));
 }
+
+static inline void __write_pkru(u32 pkru)
+{
+	/*
+	 * WRPKRU is relatively expensive compared to RDPKRU.
+	 * Avoid WRPKRU when it would not change the value.
+	 */
+	if (pkru == rdpkru())
+		return;
+
+	wrpkru(pkru);
+}
+
 #else
-static inline u32 __read_pkru(void)
+static inline u32 rdpkru(void)
 {
 	return 0;
 }
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 4c305471ec33..b05ad16174e5 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -105,7 +105,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	memcpy(&regs->bx + i, args, n * sizeof(args[0]));
 }
 
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
 {
 	return AUDIT_ARCH_I386;
 }
@@ -160,10 +160,12 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	}
 }
 
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
 {
 	/* x32 tasks should be considered AUDIT_ARCH_X86_64. */
-	return in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
+	return (IS_ENABLED(CONFIG_IA32_EMULATION) &&
+		task->thread_info.status & TS_COMPAT)
+		? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
 }
 #endif	/* CONFIG_X86_32 */
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e0eccbcb8447..f9453536f9bb 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -88,6 +88,7 @@ struct thread_info {
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
 #define TIF_PATCH_PENDING	13	/* pending live patching update */
+#define TIF_NEED_FPU_LOAD	14	/* load FPU on return to userspace */
 #define TIF_NOCPUID		15	/* CPUID is not accessible in userland */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
@@ -117,6 +118,7 @@ struct thread_info {
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_PATCH_PENDING	(1 << TIF_PATCH_PENDING)
+#define _TIF_NEED_FPU_LOAD	(1 << TIF_NEED_FPU_LOAD)
 #define _TIF_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h
index e0e6d7f21399..6b1e87194809 100644
--- a/arch/x86/include/asm/trace/exceptions.h
+++ b/arch/x86/include/asm/trace/exceptions.h
@@ -30,7 +30,7 @@ DECLARE_EVENT_CLASS(x86_exceptions,
 		__entry->error_code = error_code;
 	),
 
-	TP_printk("address=%pf ip=%pf error_code=0x%lx",
+	TP_printk("address=%ps ip=%ps error_code=0x%lx",
 		  (void *)__entry->address, (void *)__entry->ip,
 		  __entry->error_code) );
 
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 069c04be1507..879b77792f94 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -13,22 +13,22 @@ DECLARE_EVENT_CLASS(x86_fpu,
 
 	TP_STRUCT__entry(
 		__field(struct fpu *, fpu)
-		__field(bool, initialized)
+		__field(bool, load_fpu)
 		__field(u64, xfeatures)
 		__field(u64, xcomp_bv)
 		),
 
 	TP_fast_assign(
 		__entry->fpu		= fpu;
-		__entry->initialized	= fpu->initialized;
+		__entry->load_fpu	= test_thread_flag(TIF_NEED_FPU_LOAD);
 		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
 			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
 		}
 	),
-	TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx",
+	TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx",
 			__entry->fpu,
-			__entry->initialized,
+			__entry->load_fpu,
 			__entry->xfeatures,
 			__entry->xcomp_bv
 	)
@@ -64,11 +64,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated,
 	TP_ARGS(fpu)
 );
 
-DEFINE_EVENT(x86_fpu, x86_fpu_activate_state,
-	TP_PROTO(struct fpu *fpu),
-	TP_ARGS(fpu)
-);
-
 DEFINE_EVENT(x86_fpu, x86_fpu_init_state,
 	TP_PROTO(struct fpu *fpu),
 	TP_ARGS(fpu)
diff --git a/arch/x86/include/uapi/asm/sockios.h b/arch/x86/include/uapi/asm/sockios.h
deleted file mode 100644
index def6d4746ee7..000000000000
--- a/arch/x86/include/uapi/asm/sockios.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/sockios.h>
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8dcbf6890714..9fc92e4539d8 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -197,7 +197,7 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
 }
 
 static int __init
-acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
+acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end)
 {
 	struct acpi_madt_local_x2apic *processor = NULL;
 #ifdef CONFIG_X86_X2APIC
@@ -210,7 +210,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 	if (BAD_MADT_ENTRY(processor, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 #ifdef CONFIG_X86_X2APIC
 	apic_id = processor->local_apic_id;
@@ -242,7 +242,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 }
 
 static int __init
-acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end)
+acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end)
 {
 	struct acpi_madt_local_apic *processor = NULL;
 
@@ -251,7 +251,7 @@ acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end)
 	if (BAD_MADT_ENTRY(processor, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	/* Ignore invalid ID */
 	if (processor->id == 0xff)
@@ -272,7 +272,7 @@ acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end)
 }
 
 static int __init
-acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end)
+acpi_parse_sapic(union acpi_subtable_headers *header, const unsigned long end)
 {
 	struct acpi_madt_local_sapic *processor = NULL;
 
@@ -281,7 +281,7 @@ acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end)
 	if (BAD_MADT_ENTRY(processor, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */
 			    processor->processor_id, /* ACPI ID */
@@ -291,7 +291,7 @@ acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end)
 }
 
 static int __init
-acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
+acpi_parse_lapic_addr_ovr(union acpi_subtable_headers * header,
 			  const unsigned long end)
 {
 	struct acpi_madt_local_apic_override *lapic_addr_ovr = NULL;
@@ -301,7 +301,7 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
 	if (BAD_MADT_ENTRY(lapic_addr_ovr, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	acpi_lapic_addr = lapic_addr_ovr->address;
 
@@ -309,7 +309,7 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
 }
 
 static int __init
-acpi_parse_x2apic_nmi(struct acpi_subtable_header *header,
+acpi_parse_x2apic_nmi(union acpi_subtable_headers *header,
 		      const unsigned long end)
 {
 	struct acpi_madt_local_x2apic_nmi *x2apic_nmi = NULL;
@@ -319,7 +319,7 @@ acpi_parse_x2apic_nmi(struct acpi_subtable_header *header,
 	if (BAD_MADT_ENTRY(x2apic_nmi, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	if (x2apic_nmi->lint != 1)
 		printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n");
@@ -328,7 +328,7 @@ acpi_parse_x2apic_nmi(struct acpi_subtable_header *header,
 }
 
 static int __init
-acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long end)
+acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long end)
 {
 	struct acpi_madt_local_apic_nmi *lapic_nmi = NULL;
 
@@ -337,7 +337,7 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e
 	if (BAD_MADT_ENTRY(lapic_nmi, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	if (lapic_nmi->lint != 1)
 		printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n");
@@ -449,7 +449,7 @@ static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity,
 }
 
 static int __init
-acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
+acpi_parse_ioapic(union acpi_subtable_headers * header, const unsigned long end)
 {
 	struct acpi_madt_io_apic *ioapic = NULL;
 	struct ioapic_domain_cfg cfg = {
@@ -462,7 +462,7 @@ acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
 	if (BAD_MADT_ENTRY(ioapic, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	/* Statically assign IRQ numbers for IOAPICs hosting legacy IRQs */
 	if (ioapic->global_irq_base < nr_legacy_irqs())
@@ -508,7 +508,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
 }
 
 static int __init
-acpi_parse_int_src_ovr(struct acpi_subtable_header * header,
+acpi_parse_int_src_ovr(union acpi_subtable_headers * header,
 		       const unsigned long end)
 {
 	struct acpi_madt_interrupt_override *intsrc = NULL;
@@ -518,7 +518,7 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header,
 	if (BAD_MADT_ENTRY(intsrc, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	if (intsrc->source_irq == acpi_gbl_FADT.sci_interrupt) {
 		acpi_sci_ioapic_setup(intsrc->source_irq,
@@ -550,7 +550,7 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header,
 }
 
 static int __init
-acpi_parse_nmi_src(struct acpi_subtable_header * header, const unsigned long end)
+acpi_parse_nmi_src(union acpi_subtable_headers * header, const unsigned long end)
 {
 	struct acpi_madt_nmi_source *nmi_src = NULL;
 
@@ -559,7 +559,7 @@ acpi_parse_nmi_src(struct acpi_subtable_header * header, const unsigned long end
 	if (BAD_MADT_ENTRY(nmi_src, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	/* TBD: Support nimsrc entries? */
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 2c0aa34af69c..bf7f13ea3c64 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -233,9 +233,6 @@ static dma_addr_t gart_map_page(struct device *dev, struct page *page,
 	unsigned long bus;
 	phys_addr_t paddr = page_to_phys(page) + offset;
 
-	if (!dev)
-		dev = &x86_dma_fallback_dev;
-
 	if (!need_iommu(dev, paddr, size))
 		return paddr;
 
@@ -392,9 +389,6 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	if (nents == 0)
 		return 0;
 
-	if (!dev)
-		dev = &x86_dma_fallback_dev;
-
 	out		= 0;
 	start		= 0;
 	start_sg	= sg;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 29630393f300..03b4cc0ec3a7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -37,6 +37,7 @@
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
+static void __init mds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
 u64 x86_spec_ctrl_base;
@@ -63,6 +64,13 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 /* Control unconditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+/* Control MDS CPU buffer clear before returning to user space */
+DEFINE_STATIC_KEY_FALSE(mds_user_clear);
+EXPORT_SYMBOL_GPL(mds_user_clear);
+/* Control MDS CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
+EXPORT_SYMBOL_GPL(mds_idle_clear);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -101,6 +109,10 @@ void __init check_bugs(void)
 
 	l1tf_select_mitigation();
 
+	mds_select_mitigation();
+
+	arch_smt_update();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -207,6 +219,61 @@ static void x86_amd_ssb_disable(void)
 }
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"MDS: " fmt
+
+/* Default mitigation for MDS-affected CPUs */
+static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL;
+static bool mds_nosmt __ro_after_init = false;
+
+static const char * const mds_strings[] = {
+	[MDS_MITIGATION_OFF]	= "Vulnerable",
+	[MDS_MITIGATION_FULL]	= "Mitigation: Clear CPU buffers",
+	[MDS_MITIGATION_VMWERV]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
+};
+
+static void __init mds_select_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) {
+		mds_mitigation = MDS_MITIGATION_OFF;
+		return;
+	}
+
+	if (mds_mitigation == MDS_MITIGATION_FULL) {
+		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
+			mds_mitigation = MDS_MITIGATION_VMWERV;
+
+		static_branch_enable(&mds_user_clear);
+
+		if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
+		    (mds_nosmt || cpu_mitigations_auto_nosmt()))
+			cpu_smt_disable(false);
+	}
+
+	pr_info("%s\n", mds_strings[mds_mitigation]);
+}
+
+static int __init mds_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MDS))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		mds_mitigation = MDS_MITIGATION_OFF;
+	else if (!strcmp(str, "full"))
+		mds_mitigation = MDS_MITIGATION_FULL;
+	else if (!strcmp(str, "full,nosmt")) {
+		mds_mitigation = MDS_MITIGATION_FULL;
+		mds_nosmt = true;
+	}
+
+	return 0;
+}
+early_param("mds", mds_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V2 : " fmt
 
 static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
@@ -575,9 +642,6 @@ specv2_set_mode:
 
 	/* Set up IBPB and STIBP depending on the general spectre V2 command */
 	spectre_v2_user_select_mitigation(cmd);
-
-	/* Enable STIBP if appropriate */
-	arch_smt_update();
 }
 
 static void update_stibp_msr(void * __unused)
@@ -611,6 +675,31 @@ static void update_indir_branch_cond(void)
 		static_branch_disable(&switch_to_cond_stibp);
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+/* Update the static key controlling the MDS CPU buffer clear in idle */
+static void update_mds_branch_idle(void)
+{
+	/*
+	 * Enable the idle clearing if SMT is active on CPUs which are
+	 * affected only by MSBDS and not any other MDS variant.
+	 *
+	 * The other variants cannot be mitigated when SMT is enabled, so
+	 * clearing the buffers on idle just to prevent the Store Buffer
+	 * repartitioning leak would be a window dressing exercise.
+	 */
+	if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY))
+		return;
+
+	if (sched_smt_active())
+		static_branch_enable(&mds_idle_clear);
+	else
+		static_branch_disable(&mds_idle_clear);
+}
+
+#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
+
 void arch_smt_update(void)
 {
 	/* Enhanced IBRS implies STIBP. No update required. */
@@ -632,6 +721,17 @@ void arch_smt_update(void)
 		break;
 	}
 
+	switch (mds_mitigation) {
+	case MDS_MITIGATION_FULL:
+	case MDS_MITIGATION_VMWERV:
+		if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
+			pr_warn_once(MDS_MSG_SMT);
+		update_mds_branch_idle();
+		break;
+	case MDS_MITIGATION_OFF:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 
@@ -1043,7 +1143,7 @@ static void __init l1tf_select_mitigation(void)
 		pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n",
 				half_pa);
 		pr_info("However, doing so will make a part of your RAM unusable.\n");
-		pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n");
+		pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html might help you decide.\n");
 		return;
 	}
 
@@ -1076,6 +1176,7 @@ static int __init l1tf_cmdline(char *str)
 early_param("l1tf", l1tf_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt) fmt
 
 #ifdef CONFIG_SYSFS
 
@@ -1114,6 +1215,23 @@ static ssize_t l1tf_show_state(char *buf)
 }
 #endif
 
+static ssize_t mds_show_state(char *buf)
+{
+	if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
+		return sprintf(buf, "%s; SMT Host state unknown\n",
+			       mds_strings[mds_mitigation]);
+	}
+
+	if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) {
+		return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+			       (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" :
+			        sched_smt_active() ? "mitigated" : "disabled"));
+	}
+
+	return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+		       sched_smt_active() ? "vulnerable" : "disabled");
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@@ -1180,6 +1298,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
 			return l1tf_show_state(buf);
 		break;
+
+	case X86_BUG_MDS:
+		return mds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1211,4 +1333,9 @@ ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *b
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
 }
+
+ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_MDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 37640544e12f..d7f55ad2dfb1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -372,6 +372,8 @@ static bool pku_disabled;
 
 static __always_inline void setup_pku(struct cpuinfo_x86 *c)
 {
+	struct pkru_state *pk;
+
 	/* check the boot processor, plus compile options for PKU: */
 	if (!cpu_feature_enabled(X86_FEATURE_PKU))
 		return;
@@ -382,6 +384,9 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c)
 		return;
 
 	cr4_set_bits(X86_CR4_PKE);
+	pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU);
+	if (pk)
+		pk->pkru = init_pkru_value;
 	/*
 	 * Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE
 	 * cpuid bit to be set.  We need to ensure that we
@@ -935,61 +940,77 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #endif
 }
 
-static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_TABLET,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL_MID,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_MID,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_CENTAUR,	5 },
-	{ X86_VENDOR_INTEL,	5 },
-	{ X86_VENDOR_NSC,	5 },
-	{ X86_VENDOR_ANY,	4 },
-	{}
-};
+#define NO_SPECULATION	BIT(0)
+#define NO_MELTDOWN	BIT(1)
+#define NO_SSB		BIT(2)
+#define NO_L1TF		BIT(3)
+#define NO_MDS		BIT(4)
+#define MSBDS_ONLY	BIT(5)
 
-static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
-	{ X86_VENDOR_AMD },
-	{ X86_VENDOR_HYGON },
-	{}
-};
+#define VULNWL(_vendor, _family, _model, _whitelist)	\
+	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
 
-/* Only list CPUs which speculate but are non susceptible to SSB */
-static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_CORE_YONAH		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
-	{ X86_VENDOR_AMD,	0x12,					},
-	{ X86_VENDOR_AMD,	0x11,					},
-	{ X86_VENDOR_AMD,	0x10,					},
-	{ X86_VENDOR_AMD,	0xf,					},
-	{}
-};
+#define VULNWL_INTEL(model, whitelist)		\
+	VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
+
+#define VULNWL_AMD(family, whitelist)		\
+	VULNWL(AMD, family, X86_MODEL_ANY, whitelist)
+
+#define VULNWL_HYGON(family, whitelist)		\
+	VULNWL(HYGON, family, X86_MODEL_ANY, whitelist)
+
+static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
+	VULNWL(ANY,	4, X86_MODEL_ANY,	NO_SPECULATION),
+	VULNWL(CENTAUR,	5, X86_MODEL_ANY,	NO_SPECULATION),
+	VULNWL(INTEL,	5, X86_MODEL_ANY,	NO_SPECULATION),
+	VULNWL(NSC,	5, X86_MODEL_ANY,	NO_SPECULATION),
+
+	/* Intel Family 6 */
+	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION),
+	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION),
 
-static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
-	/* in addition to cpu_no_speculation */
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_PLUS	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
+	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_SILVERMONT_X,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+
+	VULNWL_INTEL(CORE_YONAH,		NO_SSB),
+
+	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY),
+
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF),
+	VULNWL_INTEL(ATOM_GOLDMONT_X,		NO_MDS | NO_L1TF),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF),
+
+	/* AMD Family 0xf - 0x12 */
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+
+	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
 	{}
 };
 
+static bool __init cpu_matches(unsigned long which)
+{
+	const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
+
+	return m && !!(m->driver_data & which);
+}
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
 
-	if (x86_match_cpu(cpu_no_speculation))
+	if (cpu_matches(NO_SPECULATION))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
@@ -998,15 +1019,20 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
 
-	if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
-	   !(ia32_cap & ARCH_CAP_SSB_NO) &&
+	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
 	if (ia32_cap & ARCH_CAP_IBRS_ALL)
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
 
-	if (x86_match_cpu(cpu_no_meltdown))
+	if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) {
+		setup_force_cpu_bug(X86_BUG_MDS);
+		if (cpu_matches(MSBDS_ONLY))
+			setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
+	}
+
+	if (cpu_matches(NO_MELTDOWN))
 		return;
 
 	/* Rogue Data Cache Load? No! */
@@ -1015,7 +1041,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
-	if (x86_match_cpu(cpu_no_l1tf))
+	if (cpu_matches(NO_L1TF))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_L1TF);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 8a4a7823451a..c321f4f513f9 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -428,7 +428,7 @@ static int do_microcode_update(const void __user *buf, size_t size)
 
 static int microcode_open(struct inode *inode, struct file *file)
 {
-	return capable(CAP_SYS_RAWIO) ? nonseekable_open(inode, file) : -EPERM;
+	return capable(CAP_SYS_RAWIO) ? stream_open(inode, file) : -EPERM;
 }
 
 static ssize_t microcode_write(struct file *file, const char __user *buf,
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 50d5848bf22e..6c4f01540833 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -525,7 +525,8 @@ static const struct pci_device_id intel_early_ids[] __initconst = {
 	INTEL_I945G_IDS(&gen3_early_ops),
 	INTEL_I945GM_IDS(&gen3_early_ops),
 	INTEL_VLV_IDS(&gen6_early_ops),
-	INTEL_PINEVIEW_IDS(&gen3_early_ops),
+	INTEL_PINEVIEW_G_IDS(&gen3_early_ops),
+	INTEL_PINEVIEW_M_IDS(&gen3_early_ops),
 	INTEL_I965G_IDS(&gen3_early_ops),
 	INTEL_G33_IDS(&gen3_early_ops),
 	INTEL_I965GM_IDS(&gen3_early_ops),
@@ -547,6 +548,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = {
 	INTEL_GLK_IDS(&gen9_early_ops),
 	INTEL_CNL_IDS(&gen9_early_ops),
 	INTEL_ICL_11_IDS(&gen11_early_ops),
+	INTEL_EHL_IDS(&gen11_early_ops),
 };
 
 struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 2e5003fef51a..ce243f76bdb7 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -101,24 +101,21 @@ static void __kernel_fpu_begin(void)
 
 	kernel_fpu_disable();
 
-	if (fpu->initialized) {
-		/*
-		 * Ignore return value -- we don't care if reg state
-		 * is clobbered.
-		 */
-		copy_fpregs_to_fpstate(fpu);
-	} else {
-		__cpu_invalidate_fpregs_state();
+	if (current->mm) {
+		if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
+			set_thread_flag(TIF_NEED_FPU_LOAD);
+			/*
+			 * Ignore return value -- we don't care if reg state
+			 * is clobbered.
+			 */
+			copy_fpregs_to_fpstate(fpu);
+		}
 	}
+	__cpu_invalidate_fpregs_state();
 }
 
 static void __kernel_fpu_end(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
-
-	if (fpu->initialized)
-		copy_kernel_to_fpregs(&fpu->state);
-
 	kernel_fpu_enable();
 }
 
@@ -145,15 +142,17 @@ void fpu__save(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	preempt_disable();
+	fpregs_lock();
 	trace_x86_fpu_before_save(fpu);
-	if (fpu->initialized) {
+
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
 		if (!copy_fpregs_to_fpstate(fpu)) {
 			copy_kernel_to_fpregs(&fpu->state);
 		}
 	}
+
 	trace_x86_fpu_after_save(fpu);
-	preempt_enable();
+	fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(fpu__save);
 
@@ -186,11 +185,14 @@ void fpstate_init(union fpregs_state *state)
 }
 EXPORT_SYMBOL_GPL(fpstate_init);
 
-int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+int fpu__copy(struct task_struct *dst, struct task_struct *src)
 {
+	struct fpu *dst_fpu = &dst->thread.fpu;
+	struct fpu *src_fpu = &src->thread.fpu;
+
 	dst_fpu->last_cpu = -1;
 
-	if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU))
+	if (!static_cpu_has(X86_FEATURE_FPU))
 		return 0;
 
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
@@ -202,16 +204,23 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
 
 	/*
-	 * Save current FPU registers directly into the child
-	 * FPU context, without any memory-to-memory copying.
+	 * If the FPU registers are not current just memcpy() the state.
+	 * Otherwise save current FPU registers directly into the child's FPU
+	 * context, without any memory-to-memory copying.
 	 *
 	 * ( The function 'fails' in the FNSAVE case, which destroys
-	 *   register contents so we have to copy them back. )
+	 *   register contents so we have to load them back. )
 	 */
-	if (!copy_fpregs_to_fpstate(dst_fpu)) {
-		memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size);
-		copy_kernel_to_fpregs(&src_fpu->state);
-	}
+	fpregs_lock();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size);
+
+	else if (!copy_fpregs_to_fpstate(dst_fpu))
+		copy_kernel_to_fpregs(&dst_fpu->state);
+
+	fpregs_unlock();
+
+	set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD);
 
 	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
@@ -223,20 +232,14 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
  * Activate the current task's in-memory FPU context,
  * if it has not been used before:
  */
-void fpu__initialize(struct fpu *fpu)
+static void fpu__initialize(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	if (!fpu->initialized) {
-		fpstate_init(&fpu->state);
-		trace_x86_fpu_init_state(fpu);
-
-		trace_x86_fpu_activate_state(fpu);
-		/* Safe to do for the current task: */
-		fpu->initialized = 1;
-	}
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+	fpstate_init(&fpu->state);
+	trace_x86_fpu_init_state(fpu);
 }
-EXPORT_SYMBOL_GPL(fpu__initialize);
 
 /*
  * This function must be called before we read a task's fpstate.
@@ -248,32 +251,20 @@ EXPORT_SYMBOL_GPL(fpu__initialize);
  *
  * - or it's called for stopped tasks (ptrace), in which case the
  *   registers were already saved by the context-switch code when
- *   the task scheduled out - we only have to initialize the registers
- *   if they've never been initialized.
+ *   the task scheduled out.
  *
  * If the task has used the FPU before then save it.
  */
 void fpu__prepare_read(struct fpu *fpu)
 {
-	if (fpu == &current->thread.fpu) {
+	if (fpu == &current->thread.fpu)
 		fpu__save(fpu);
-	} else {
-		if (!fpu->initialized) {
-			fpstate_init(&fpu->state);
-			trace_x86_fpu_init_state(fpu);
-
-			trace_x86_fpu_activate_state(fpu);
-			/* Safe to do for current and for stopped child tasks: */
-			fpu->initialized = 1;
-		}
-	}
 }
 
 /*
  * This function must be called before we write a task's fpstate.
  *
- * If the task has used the FPU before then invalidate any cached FPU registers.
- * If the task has not used the FPU before then initialize its fpstate.
+ * Invalidate any cached FPU registers.
  *
  * After this function call, after registers in the fpstate are
  * modified and the child task has woken up, the child task will
@@ -290,44 +281,11 @@ void fpu__prepare_write(struct fpu *fpu)
 	 */
 	WARN_ON_FPU(fpu == &current->thread.fpu);
 
-	if (fpu->initialized) {
-		/* Invalidate any cached state: */
-		__fpu_invalidate_fpregs_state(fpu);
-	} else {
-		fpstate_init(&fpu->state);
-		trace_x86_fpu_init_state(fpu);
-
-		trace_x86_fpu_activate_state(fpu);
-		/* Safe to do for stopped child tasks: */
-		fpu->initialized = 1;
-	}
+	/* Invalidate any cached state: */
+	__fpu_invalidate_fpregs_state(fpu);
 }
 
 /*
- * 'fpu__restore()' is called to copy FPU registers from
- * the FPU fpstate to the live hw registers and to activate
- * access to the hardware registers, so that FPU instructions
- * can be used afterwards.
- *
- * Must be called with kernel preemption disabled (for example
- * with local interrupts disabled, as it is in the case of
- * do_device_not_available()).
- */
-void fpu__restore(struct fpu *fpu)
-{
-	fpu__initialize(fpu);
-
-	/* Avoid __kernel_fpu_begin() right after fpregs_activate() */
-	kernel_fpu_disable();
-	trace_x86_fpu_before_restore(fpu);
-	fpregs_activate(fpu);
-	copy_kernel_to_fpregs(&fpu->state);
-	trace_x86_fpu_after_restore(fpu);
-	kernel_fpu_enable();
-}
-EXPORT_SYMBOL_GPL(fpu__restore);
-
-/*
  * Drops current FPU state: deactivates the fpregs and
  * the fpstate. NOTE: it still leaves previous contents
  * in the fpregs in the eager-FPU case.
@@ -341,17 +299,13 @@ void fpu__drop(struct fpu *fpu)
 	preempt_disable();
 
 	if (fpu == &current->thread.fpu) {
-		if (fpu->initialized) {
-			/* Ignore delayed exceptions from user space */
-			asm volatile("1: fwait\n"
-				     "2:\n"
-				     _ASM_EXTABLE(1b, 2b));
-			fpregs_deactivate(fpu);
-		}
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		fpregs_deactivate(fpu);
 	}
 
-	fpu->initialized = 0;
-
 	trace_x86_fpu_dropped(fpu);
 
 	preempt_enable();
@@ -363,6 +317,8 @@ void fpu__drop(struct fpu *fpu)
  */
 static inline void copy_init_fpstate_to_fpregs(void)
 {
+	fpregs_lock();
+
 	if (use_xsave())
 		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
 	else if (static_cpu_has(X86_FEATURE_FXSR))
@@ -372,6 +328,9 @@ static inline void copy_init_fpstate_to_fpregs(void)
 
 	if (boot_cpu_has(X86_FEATURE_OSPKE))
 		copy_init_pkru_to_fpregs();
+
+	fpregs_mark_activate();
+	fpregs_unlock();
 }
 
 /*
@@ -389,16 +348,52 @@ void fpu__clear(struct fpu *fpu)
 	/*
 	 * Make sure fpstate is cleared and initialized.
 	 */
-	if (static_cpu_has(X86_FEATURE_FPU)) {
-		preempt_disable();
-		fpu__initialize(fpu);
-		user_fpu_begin();
+	fpu__initialize(fpu);
+	if (static_cpu_has(X86_FEATURE_FPU))
 		copy_init_fpstate_to_fpregs();
-		preempt_enable();
-	}
 }
 
 /*
+ * Load FPU context before returning to userspace.
+ */
+void switch_fpu_return(void)
+{
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return;
+
+	__fpregs_load_activate();
+}
+EXPORT_SYMBOL_GPL(switch_fpu_return);
+
+#ifdef CONFIG_X86_DEBUG_FPU
+/*
+ * If current FPU state according to its tracking (loaded FPU context on this
+ * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is
+ * loaded on return to userland.
+ */
+void fpregs_assert_state_consistent(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		return;
+
+	WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id()));
+}
+EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent);
+#endif
+
+void fpregs_mark_activate(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	fpregs_activate(fpu);
+	fpu->last_cpu = smp_processor_id();
+	clear_thread_flag(TIF_NEED_FPU_LOAD);
+}
+EXPORT_SYMBOL_GPL(fpregs_mark_activate);
+
+/*
  * x87 math exception handling:
  */
 
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 6abd83572b01..20d8fa7124c7 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -239,8 +239,6 @@ static void __init fpu__init_system_ctx_switch(void)
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
-
-	WARN_ON_FPU(current->thread.fpu.initialized);
 }
 
 /*
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index bc02f5144b95..d652b939ccfb 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -15,16 +15,12 @@
  */
 int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
 {
-	struct fpu *target_fpu = &target->thread.fpu;
-
-	return target_fpu->initialized ? regset->n : 0;
+	return regset->n;
 }
 
 int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
 {
-	struct fpu *target_fpu = &target->thread.fpu;
-
-	if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized)
+	if (boot_cpu_has(X86_FEATURE_FXSR))
 		return regset->n;
 	else
 		return 0;
@@ -269,11 +265,10 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 		memcpy(&to[i], &from[i], sizeof(to[0]));
 }
 
-void convert_to_fxsr(struct task_struct *tsk,
+void convert_to_fxsr(struct fxregs_state *fxsave,
 		     const struct user_i387_ia32_struct *env)
 
 {
-	struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
 	struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
 	struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
 	int i;
@@ -350,7 +345,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
 	if (!ret)
-		convert_to_fxsr(target, &env);
+		convert_to_fxsr(&target->thread.fpu.state.fxsave, &env);
 
 	/*
 	 * update the header bit in the xsave header, indicating the
@@ -371,16 +366,9 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
 {
 	struct task_struct *tsk = current;
-	struct fpu *fpu = &tsk->thread.fpu;
-	int fpvalid;
-
-	fpvalid = fpu->initialized;
-	if (fpvalid)
-		fpvalid = !fpregs_get(tsk, NULL,
-				      0, sizeof(struct user_i387_ia32_struct),
-				      ufpu, NULL);
 
-	return fpvalid;
+	return !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct),
+			   ufpu, NULL);
 }
 EXPORT_SYMBOL(dump_fpu);
 
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index f6a1d299627c..5a8d118bc423 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -92,13 +92,13 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 		return err;
 
 	err |= __put_user(FP_XSTATE_MAGIC2,
-			  (__u32 *)(buf + fpu_user_xstate_size));
+			  (__u32 __user *)(buf + fpu_user_xstate_size));
 
 	/*
 	 * Read the xfeatures which we copied (directly from the cpu or
 	 * from the state in task struct) to the user buffers.
 	 */
-	err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures);
+	err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
 
 	/*
 	 * For legacy compatible, we always set FP/SSE bits in the bit
@@ -113,7 +113,7 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 	 */
 	xfeatures |= XFEATURE_MASK_FPSSE;
 
-	err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures);
+	err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
 
 	return err;
 }
@@ -144,9 +144,10 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
  *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
  *	buf != buf_fx for 32-bit frames with fxstate.
  *
- * If the fpu, extended register state is live, save the state directly
- * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
- * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ * Try to save it directly to the user frame with disabled page fault handler.
+ * If this fails then do the slow path where the FPU state is first saved to
+ * task's fpu->state and then copy it to the user frame pointed to by the
+ * aligned pointer 'buf_fx'.
  *
  * If this is a 32-bit frame with fxstate, put a fsave header before
  * the aligned state at 'buf_fx'.
@@ -156,10 +157,9 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
  */
 int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 {
-	struct fpu *fpu = &current->thread.fpu;
-	struct xregs_state *xsave = &fpu->state.xsave;
 	struct task_struct *tsk = current;
 	int ia32_fxstate = (buf != buf_fx);
+	int ret;
 
 	ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
@@ -172,28 +172,34 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 			sizeof(struct user_i387_ia32_struct), NULL,
 			(struct _fpstate_32 __user *) buf) ? -1 : 1;
 
-	if (fpu->initialized || using_compacted_format()) {
-		/* Save the live register state to the user directly. */
-		if (copy_fpregs_to_sigframe(buf_fx))
-			return -1;
-		/* Update the thread's fxstate to save the fsave header. */
-		if (ia32_fxstate)
-			copy_fxregs_to_kernel(fpu);
-	} else {
-		/*
-		 * It is a *bug* if kernel uses compacted-format for xsave
-		 * area and we copy it out directly to a signal frame. It
-		 * should have been handled above by saving the registers
-		 * directly.
-		 */
-		if (boot_cpu_has(X86_FEATURE_XSAVES)) {
-			WARN_ONCE(1, "x86/fpu: saving compacted-format xsave area to a signal frame!\n");
-			return -1;
-		}
-
-		fpstate_sanitize_xstate(fpu);
-		if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size))
-			return -1;
+retry:
+	/*
+	 * Load the FPU registers if they are not valid for the current task.
+	 * With a valid FPU state we can attempt to save the state directly to
+	 * userland's stack frame which will likely succeed. If it does not,
+	 * resolve the fault in the user memory and try again.
+	 */
+	fpregs_lock();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		__fpregs_load_activate();
+
+	pagefault_disable();
+	ret = copy_fpregs_to_sigframe(buf_fx);
+	pagefault_enable();
+	fpregs_unlock();
+
+	if (ret) {
+		int aligned_size;
+		int nr_pages;
+
+		aligned_size = offset_in_page(buf_fx) + fpu_user_xstate_size;
+		nr_pages = DIV_ROUND_UP(aligned_size, PAGE_SIZE);
+
+		ret = get_user_pages_unlocked((unsigned long)buf_fx, nr_pages,
+					      NULL, FOLL_WRITE);
+		if (ret == nr_pages)
+			goto retry;
+		return -EFAULT;
 	}
 
 	/* Save the fsave header for the 32-bit frames. */
@@ -207,11 +213,11 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 }
 
 static inline void
-sanitize_restored_xstate(struct task_struct *tsk,
+sanitize_restored_xstate(union fpregs_state *state,
 			 struct user_i387_ia32_struct *ia32_env,
 			 u64 xfeatures, int fx_only)
 {
-	struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+	struct xregs_state *xsave = &state->xsave;
 	struct xstate_header *header = &xsave->header;
 
 	if (use_xsave()) {
@@ -238,17 +244,18 @@ sanitize_restored_xstate(struct task_struct *tsk,
 		 */
 		xsave->i387.mxcsr &= mxcsr_feature_mask;
 
-		convert_to_fxsr(tsk, ia32_env);
+		if (ia32_env)
+			convert_to_fxsr(&state->fxsave, ia32_env);
 	}
 }
 
 /*
  * Restore the extended state if present. Otherwise, restore the FP/SSE state.
  */
-static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
+static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
 {
 	if (use_xsave()) {
-		if ((unsigned long)buf % 64 || fx_only) {
+		if (fx_only) {
 			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
 			return copy_user_to_fxregs(buf);
@@ -266,12 +273,15 @@ static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_
 
 static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 {
+	struct user_i387_ia32_struct *envp = NULL;
+	int state_size = fpu_kernel_xstate_size;
 	int ia32_fxstate = (buf != buf_fx);
 	struct task_struct *tsk = current;
 	struct fpu *fpu = &tsk->thread.fpu;
-	int state_size = fpu_kernel_xstate_size;
+	struct user_i387_ia32_struct env;
 	u64 xfeatures = 0;
 	int fx_only = 0;
+	int ret = 0;
 
 	ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
@@ -284,8 +294,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 	if (!access_ok(buf, size))
 		return -EACCES;
 
-	fpu__initialize(fpu);
-
 	if (!static_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_set(current, NULL,
 				       0, sizeof(struct user_i387_ia32_struct),
@@ -308,61 +316,101 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		}
 	}
 
+	/*
+	 * The current state of the FPU registers does not matter. By setting
+	 * TIF_NEED_FPU_LOAD unconditionally it is ensured that the our xstate
+	 * is not modified on context switch and that the xstate is considered
+	 * to be loaded again on return to userland (overriding last_cpu avoids
+	 * the optimisation).
+	 */
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+	__fpu_invalidate_fpregs_state(fpu);
+
+	if ((unsigned long)buf_fx % 64)
+		fx_only = 1;
+	/*
+	 * For 32-bit frames with fxstate, copy the fxstate so it can be
+	 * reconstructed later.
+	 */
 	if (ia32_fxstate) {
+		ret = __copy_from_user(&env, buf, sizeof(env));
+		if (ret)
+			goto err_out;
+		envp = &env;
+	} else {
 		/*
-		 * For 32-bit frames with fxstate, copy the user state to the
-		 * thread's fpu state, reconstruct fxstate from the fsave
-		 * header. Validate and sanitize the copied state.
+		 * Attempt to restore the FPU registers directly from user
+		 * memory. For that to succeed, the user access cannot cause
+		 * page faults. If it does, fall back to the slow path below,
+		 * going through the kernel buffer with the enabled pagefault
+		 * handler.
 		 */
-		struct user_i387_ia32_struct env;
-		int err = 0;
+		fpregs_lock();
+		pagefault_disable();
+		ret = copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only);
+		pagefault_enable();
+		if (!ret) {
+			fpregs_mark_activate();
+			fpregs_unlock();
+			return 0;
+		}
+		fpregs_unlock();
+	}
 
-		/*
-		 * Drop the current fpu which clears fpu->initialized. This ensures
-		 * that any context-switch during the copy of the new state,
-		 * avoids the intermediate state from getting restored/saved.
-		 * Thus avoiding the new restored state from getting corrupted.
-		 * We will be ready to restore/save the state only after
-		 * fpu->initialized is again set.
-		 */
-		fpu__drop(fpu);
+
+	if (use_xsave() && !fx_only) {
+		u64 init_bv = xfeatures_mask & ~xfeatures;
 
 		if (using_compacted_format()) {
-			err = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
+			ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
 		} else {
-			err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
+			ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
 
-			if (!err && state_size > offsetof(struct xregs_state, header))
-				err = validate_xstate_header(&fpu->state.xsave.header);
+			if (!ret && state_size > offsetof(struct xregs_state, header))
+				ret = validate_xstate_header(&fpu->state.xsave.header);
 		}
+		if (ret)
+			goto err_out;
 
-		if (err || __copy_from_user(&env, buf, sizeof(env))) {
-			fpstate_init(&fpu->state);
-			trace_x86_fpu_init_state(fpu);
-			err = -1;
-		} else {
-			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
+		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
+
+		fpregs_lock();
+		if (unlikely(init_bv))
+			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+		ret = copy_kernel_to_xregs_err(&fpu->state.xsave, xfeatures);
+
+	} else if (use_fxsr()) {
+		ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size);
+		if (ret) {
+			ret = -EFAULT;
+			goto err_out;
 		}
 
-		local_bh_disable();
-		fpu->initialized = 1;
-		fpu__restore(fpu);
-		local_bh_enable();
+		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
 
-		return err;
-	} else {
-		/*
-		 * For 64-bit frames and 32-bit fsave frames, restore the user
-		 * state to the registers directly (with exceptions handled).
-		 */
-		user_fpu_begin();
-		if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) {
-			fpu__clear(fpu);
-			return -1;
+		fpregs_lock();
+		if (use_xsave()) {
+			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
+			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
 		}
+
+		ret = copy_kernel_to_fxregs_err(&fpu->state.fxsave);
+	} else {
+		ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size);
+		if (ret)
+			goto err_out;
+
+		fpregs_lock();
+		ret = copy_kernel_to_fregs_err(&fpu->state.fsave);
 	}
+	if (!ret)
+		fpregs_mark_activate();
+	fpregs_unlock();
 
-	return 0;
+err_out:
+	if (ret)
+		fpu__clear(fpu);
+	return ret;
 }
 
 static inline int xstate_sigframe_size(void)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d7432c2b1051..9c459fd1d38e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -805,20 +805,18 @@ void fpu__resume_cpu(void)
 }
 
 /*
- * Given an xstate feature mask, calculate where in the xsave
+ * Given an xstate feature nr, calculate where in the xsave
  * buffer the state is.  Callers should ensure that the buffer
  * is valid.
  */
-static void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask)
+static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 {
-	int feature_nr = fls64(xstate_feature_mask) - 1;
-
-	if (!xfeature_enabled(feature_nr)) {
+	if (!xfeature_enabled(xfeature_nr)) {
 		WARN_ON_FPU(1);
 		return NULL;
 	}
 
-	return (void *)xsave + xstate_comp_offsets[feature_nr];
+	return (void *)xsave + xstate_comp_offsets[xfeature_nr];
 }
 /*
  * Given the xsave area and a state inside, this function returns the
@@ -832,13 +830,13 @@ static void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask
  *
  * Inputs:
  *	xstate: the thread's storage area for all FPU data
- *	xstate_feature: state which is defined in xsave.h (e.g.
- *	XFEATURE_MASK_FP, XFEATURE_MASK_SSE, etc...)
+ *	xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP,
+ *	XFEATURE_SSE, etc...)
  * Output:
  *	address of the state in the xsave area, or NULL if the
  *	field is not present in the xsave buffer.
  */
-void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
+void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 {
 	/*
 	 * Do we even *have* xsave state?
@@ -851,11 +849,11 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
 	 * have not enabled.  Remember that pcntxt_mask is
 	 * what we write to the XCR0 register.
 	 */
-	WARN_ONCE(!(xfeatures_mask & xstate_feature),
+	WARN_ONCE(!(xfeatures_mask & BIT_ULL(xfeature_nr)),
 		  "get of unsupported state");
 	/*
 	 * This assumes the last 'xsave*' instruction to
-	 * have requested that 'xstate_feature' be saved.
+	 * have requested that 'xfeature_nr' be saved.
 	 * If it did not, we might be seeing and old value
 	 * of the field in the buffer.
 	 *
@@ -864,10 +862,10 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
 	 * or because the "init optimization" caused it
 	 * to not be saved.
 	 */
-	if (!(xsave->header.xfeatures & xstate_feature))
+	if (!(xsave->header.xfeatures & BIT_ULL(xfeature_nr)))
 		return NULL;
 
-	return __raw_xsave_addr(xsave, xstate_feature);
+	return __raw_xsave_addr(xsave, xfeature_nr);
 }
 EXPORT_SYMBOL_GPL(get_xsave_addr);
 
@@ -882,25 +880,23 @@ EXPORT_SYMBOL_GPL(get_xsave_addr);
  * Note that this only works on the current task.
  *
  * Inputs:
- *	@xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP,
- *	XFEATURE_MASK_SSE, etc...)
+ *	@xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP,
+ *	XFEATURE_SSE, etc...)
  * Output:
  *	address of the state in the xsave area or NULL if the state
  *	is not present or is in its 'init state'.
  */
-const void *get_xsave_field_ptr(int xsave_state)
+const void *get_xsave_field_ptr(int xfeature_nr)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
-	if (!fpu->initialized)
-		return NULL;
 	/*
 	 * fpu__save() takes the CPU's xstate registers
 	 * and saves them off to the 'fpu memory buffer.
 	 */
 	fpu__save(fpu);
 
-	return get_xsave_addr(&fpu->state.xsave, xsave_state);
+	return get_xsave_addr(&fpu->state.xsave, xfeature_nr);
 }
 
 #ifdef CONFIG_ARCH_HAS_PKEYS
@@ -1016,7 +1012,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 		 * Copy only in-use xstates:
 		 */
 		if ((header.xfeatures >> i) & 1) {
-			void *src = __raw_xsave_addr(xsave, 1 << i);
+			void *src = __raw_xsave_addr(xsave, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
@@ -1102,7 +1098,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i
 		 * Copy only in-use xstates:
 		 */
 		if ((header.xfeatures >> i) & 1) {
-			void *src = __raw_xsave_addr(xsave, 1 << i);
+			void *src = __raw_xsave_addr(xsave, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
@@ -1159,7 +1155,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
 		u64 mask = ((u64)1 << i);
 
 		if (hdr.xfeatures & mask) {
-			void *dst = __raw_xsave_addr(xsave, 1 << i);
+			void *dst = __raw_xsave_addr(xsave, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
@@ -1213,7 +1209,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
 		u64 mask = ((u64)1 << i);
 
 		if (hdr.xfeatures & mask) {
-			void *dst = __raw_xsave_addr(xsave, 1 << i);
+			void *dst = __raw_xsave_addr(xsave, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c
index e47cd9390ab4..85de790583f9 100644
--- a/arch/x86/kernel/ima_arch.c
+++ b/arch/x86/kernel/ima_arch.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2018 IBM Corporation
  */
 #include <linux/efi.h>
+#include <linux/module.h>
 #include <linux/ima.h>
 
 extern struct boot_params boot_params;
@@ -64,12 +65,19 @@ static const char * const sb_arch_rules[] = {
 	"appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig",
 #endif /* CONFIG_KEXEC_VERIFY_SIG */
 	"measure func=KEXEC_KERNEL_CHECK",
+#if !IS_ENABLED(CONFIG_MODULE_SIG)
+	"appraise func=MODULE_CHECK appraise_type=imasig",
+#endif
+	"measure func=MODULE_CHECK",
 	NULL
 };
 
 const char * const *arch_get_ima_policy(void)
 {
-	if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot())
+	if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot()) {
+		if (IS_ENABLED(CONFIG_MODULE_SIG))
+			set_module_sig_enforced();
 		return sb_arch_rules;
+	}
 	return NULL;
 }
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 3755d0310026..05b09896cfaf 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -35,6 +35,7 @@
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 #include <asm/cache.h>
+#include <asm/nospec-branch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -551,6 +552,9 @@ nmi_restart:
 		write_cr2(this_cpu_read(nmi_cr2));
 	if (this_cpu_dec_return(nmi_state))
 		goto nmi_restart;
+
+	if (user_mode(regs))
+		mds_user_clear_cpu_buffers();
 }
 NOKPROBE_SYMBOL(do_nmi);
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index d460998ae828..dcd272dbd0a9 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -51,14 +51,6 @@ int iommu_pass_through __read_mostly;
 
 extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
 
-/* Dummy device used for NULL arguments (normally ISA). */
-struct device x86_dma_fallback_dev = {
-	.init_name = "fallback device",
-	.coherent_dma_mask = ISA_DMA_BIT_MASK,
-	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
-};
-EXPORT_SYMBOL(x86_dma_fallback_dev);
-
 void __init pci_iommu_alloc(void)
 {
 	struct iommu_table_entry *p;
@@ -77,18 +69,6 @@ void __init pci_iommu_alloc(void)
 	}
 }
 
-bool arch_dma_alloc_attrs(struct device **dev)
-{
-	if (!*dev)
-		*dev = &x86_dma_fallback_dev;
-
-	if (!is_device_dma_capable(*dev))
-		return false;
-	return true;
-
-}
-EXPORT_SYMBOL(arch_dma_alloc_attrs);
-
 /*
  * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
  * parameter documentation.
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index d1d312d012a6..75fea0d48c0e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -101,7 +101,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	dst->thread.vm86 = NULL;
 #endif
 
-	return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
+	return fpu__copy(dst, src);
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 70933193878c..2399e910d109 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -241,7 +241,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	switch_fpu_prepare(prev_fpu, cpu);
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_prepare(prev_fpu, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -274,9 +275,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
-	 * the GDT and LDT are properly updated, and must be
-	 * done before fpu__restore(), so the TS bit is up
-	 * to date.
+	 * the GDT and LDT are properly updated.
 	 */
 	arch_end_context_switch(next_p);
 
@@ -297,10 +296,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
-	switch_fpu_finish(next_fpu, cpu);
-
 	this_cpu_write(current_task, next_p);
 
+	switch_fpu_finish(next_fpu);
+
 	/* Load the Intel cache allocation PQR MSR. */
 	resctrl_sched_in();
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 844a28b29967..f8e1af380cdf 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -521,7 +521,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
 		     this_cpu_read(irq_count) != -1);
 
-	switch_fpu_prepare(prev_fpu, cpu);
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_prepare(prev_fpu, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -539,9 +540,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.  This
 	 * must be done after loading TLS entries in the GDT but before
-	 * loading segments that might reference them, and and it must
-	 * be done before fpu__restore(), so the TS bit is up to
-	 * date.
+	 * loading segments that might reference them.
 	 */
 	arch_end_context_switch(next_p);
 
@@ -569,14 +568,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	x86_fsgsbase_load(prev, next);
 
-	switch_fpu_finish(next_fpu, cpu);
-
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
 	this_cpu_write(current_task, next_p);
 	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
+	switch_fpu_finish(next_fpu);
+
 	/* Reload sp0. */
 	update_task_stack(next_p);
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index dff90fb6a9af..364813cea647 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -205,7 +205,7 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 		put_user_ex(regs->ss, &sc->ss);
 #endif /* CONFIG_X86_32 */
 
-		put_user_ex(fpstate, &sc->fpstate);
+		put_user_ex(fpstate, (unsigned long __user *)&sc->fpstate);
 
 		/* non-iBCS2 extensions.. */
 		put_user_ex(mask, &sc->oldmask);
@@ -245,7 +245,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	unsigned long sp = regs->sp;
 	unsigned long buf_fx = 0;
 	int onsigstack = on_sig_stack(sp);
-	struct fpu *fpu = &current->thread.fpu;
+	int ret;
 
 	/* redzone */
 	if (IS_ENABLED(CONFIG_X86_64))
@@ -264,11 +264,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		sp = (unsigned long) ka->sa.sa_restorer;
 	}
 
-	if (fpu->initialized) {
-		sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32),
-					  &buf_fx, &math_size);
-		*fpstate = (void __user *)sp;
-	}
+	sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32),
+				  &buf_fx, &math_size);
+	*fpstate = (void __user *)sp;
 
 	sp = align_sigframe(sp - frame_size);
 
@@ -280,8 +278,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		return (void __user *)-1L;
 
 	/* save i387 and extended state */
-	if (fpu->initialized &&
-	    copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
+	ret = copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size);
+	if (ret < 0)
 		return (void __user *)-1L;
 
 	return (void __user *)sp;
@@ -574,7 +572,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 			restorer = NULL;
 			err |= -EFAULT;
 		}
-		put_user_ex(restorer, &frame->pretcode);
+		put_user_ex(restorer, (unsigned long __user *)&frame->pretcode);
 	} put_user_catch(err);
 
 	err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
@@ -765,8 +763,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		/*
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
-		if (fpu->initialized)
-			fpu__clear(fpu);
+		fpu__clear(fpu);
 	}
 	signal_setup_done(failed, ksig, stepping);
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d26f9e9c3d83..7de466eb960b 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -58,6 +58,7 @@
 #include <asm/alternative.h>
 #include <asm/fpu/xstate.h>
 #include <asm/trace/mpx.h>
+#include <asm/nospec-branch.h>
 #include <asm/mpx.h>
 #include <asm/vm86.h>
 #include <asm/umip.h>
@@ -367,6 +368,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 		regs->ip = (unsigned long)general_protection;
 		regs->sp = (unsigned long)&gpregs->orig_ax;
 
+		/*
+		 * This situation can be triggered by userspace via
+		 * modify_ldt(2) and the return does not take the regular
+		 * user space exit, so a CPU buffer clear is required when
+		 * MDS mitigation is enabled.
+		 */
+		mds_user_clear_cpu_buffers();
 		return;
 	}
 #endif
@@ -456,7 +464,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	 * which is all zeros which indicates MPX was not
 	 * responsible for the exception.
 	 */
-	bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
 	if (!bndcsr)
 		goto exit_trap;
 
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 72fa955f4a15..fc042419e670 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -27,7 +27,6 @@ config KVM
 	depends on X86_LOCAL_APIC
 	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
-	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQFD
 	select IRQ_BYPASS_MANAGER
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index fd3951638ae4..bbbe611f0c49 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -410,7 +410,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	/* cpuid 7.0.edx*/
 	const u32 kvm_cpuid_7_0_edx_x86_features =
 		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
-		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP);
+		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
+		F(MD_CLEAR);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 6bdca39829bc..08715034e315 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -140,7 +140,7 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	pt_element_t *table;
 	struct page *page;
 
-	npages = get_user_pages_fast((unsigned long)ptep_user, 1, 1, &page);
+	npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
 	/* Check if the user is doing something meaningless. */
 	if (unlikely(npages != 1))
 		return -EFAULT;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 406b558abfef..6b92eaf4a3b1 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1805,7 +1805,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
 		return NULL;
 
 	/* Pin the user virtual address. */
-	npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
+	npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
 	if (npinned != npages) {
 		pr_err("SEV: Failure locking %lu pages.\n", npages);
 		goto err;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0c955bb286ff..e1fa935a545f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6431,8 +6431,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
 
+	/* L1D Flush includes CPU buffer clear to mitigate MDS */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
+	else if (static_branch_unlikely(&mds_user_clear))
+		mds_clear_cpu_buffers();
 
 	if (vcpu->arch.cr2 != read_cr2())
 		write_cr2(vcpu->arch.cr2);
@@ -6500,7 +6503,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	if (static_cpu_has(X86_FEATURE_PKU) &&
 	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
-		vcpu->arch.pkru = __read_pkru();
+		vcpu->arch.pkru = rdpkru();
 		if (vcpu->arch.pkru != vmx->host_pkru)
 			__write_pkru(vmx->host_pkru);
 	}
@@ -6668,8 +6671,8 @@ free_partial_vcpu:
 	return ERR_PTR(err);
 }
 
-#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
-#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n"
+#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n"
 
 static int vmx_vm_init(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b5edc8e3ce1d..d75bb97b983c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3681,15 +3681,15 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 	 */
 	valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
 	while (valid) {
-		u64 feature = valid & -valid;
-		int index = fls64(feature) - 1;
-		void *src = get_xsave_addr(xsave, feature);
+		u64 xfeature_mask = valid & -valid;
+		int xfeature_nr = fls64(xfeature_mask) - 1;
+		void *src = get_xsave_addr(xsave, xfeature_nr);
 
 		if (src) {
 			u32 size, offset, ecx, edx;
-			cpuid_count(XSTATE_CPUID, index,
+			cpuid_count(XSTATE_CPUID, xfeature_nr,
 				    &size, &offset, &ecx, &edx);
-			if (feature == XFEATURE_MASK_PKRU)
+			if (xfeature_nr == XFEATURE_PKRU)
 				memcpy(dest + offset, &vcpu->arch.pkru,
 				       sizeof(vcpu->arch.pkru));
 			else
@@ -3697,7 +3697,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 
 		}
 
-		valid -= feature;
+		valid -= xfeature_mask;
 	}
 }
 
@@ -3724,22 +3724,22 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 	 */
 	valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
 	while (valid) {
-		u64 feature = valid & -valid;
-		int index = fls64(feature) - 1;
-		void *dest = get_xsave_addr(xsave, feature);
+		u64 xfeature_mask = valid & -valid;
+		int xfeature_nr = fls64(xfeature_mask) - 1;
+		void *dest = get_xsave_addr(xsave, xfeature_nr);
 
 		if (dest) {
 			u32 size, offset, ecx, edx;
-			cpuid_count(XSTATE_CPUID, index,
+			cpuid_count(XSTATE_CPUID, xfeature_nr,
 				    &size, &offset, &ecx, &edx);
-			if (feature == XFEATURE_MASK_PKRU)
+			if (xfeature_nr == XFEATURE_PKRU)
 				memcpy(&vcpu->arch.pkru, src + offset,
 				       sizeof(vcpu->arch.pkru));
 			else
 				memcpy(dest, src + offset, size);
 		}
 
-		valid -= feature;
+		valid -= xfeature_mask;
 	}
 }
 
@@ -7899,6 +7899,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		wait_lapic_expire(vcpu);
 	guest_enter_irqoff();
 
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
@@ -8157,22 +8161,30 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	preempt_disable();
+	fpregs_lock();
+
 	copy_fpregs_to_fpstate(&current->thread.fpu);
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
-	preempt_enable();
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+
 	trace_kvm_fpu(1);
 }
 
 /* When vcpu_run ends, restore user space FPU context. */
 static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	preempt_disable();
+	fpregs_lock();
+
 	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
 	copy_kernel_to_fpregs(&current->thread.fpu.state);
-	preempt_enable();
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
 }
@@ -8870,11 +8882,11 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		if (init_event)
 			kvm_put_guest_fpu(vcpu);
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
-					XFEATURE_MASK_BNDREGS);
+					XFEATURE_BNDREGS);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state));
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
-					XFEATURE_MASK_BNDCSR);
+					XFEATURE_BNDCSR);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
 		if (init_event)
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 9e2ba7e667f6..a873da6b46d6 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -113,9 +113,6 @@ void math_emulate(struct math_emu_info *info)
 	unsigned long code_base = 0;
 	unsigned long code_limit = 0;	/* Initialized to stop compiler warnings */
 	struct desc_struct code_descriptor;
-	struct fpu *fpu = &current->thread.fpu;
-
-	fpu__initialize(fpu);
 
 #ifdef RE_ENTRANT_CHECKING
 	if (emulating) {
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 3c4568f8fb28..b0a2de8d2f9e 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -145,7 +145,7 @@ __visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup
 				       unsigned long error_code,
 				       unsigned long fault_addr)
 {
-	if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pF)\n",
+	if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
 			 (unsigned int)regs->cx, regs->ip, (void *)regs->ip))
 		show_stack_regs(regs);
 
@@ -162,7 +162,7 @@ __visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup
 				       unsigned long error_code,
 				       unsigned long fault_addr)
 {
-	if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pF)\n",
+	if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
 			 (unsigned int)regs->cx, (unsigned int)regs->dx,
 			 (unsigned int)regs->ax,  regs->ip, (void *)regs->ip))
 		show_stack_regs(regs);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 92e4c4b85bba..fab095362c50 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -203,7 +203,7 @@ static __init int setup_hugepagesz(char *opt)
 }
 __setup("hugepagesz=", setup_hugepagesz);
 
-#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
+#ifdef CONFIG_CONTIG_ALLOC
 static __init int gigantic_pages_init(void)
 {
 	/* With compaction or CMA we can allocate gigantic pages at runtime */
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 85c94f9a87f8..075e568098f2 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -850,24 +850,25 @@ void __init mem_init(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-		bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(int nid, u64 start, u64 size,
+			struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct zone *zone;
 
 	zone = page_zone(pfn_to_page(start_pfn));
-	return __remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(zone, start_pfn, nr_pages, altmap);
 }
 #endif
 #endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5cd125bd2a85..62fc457f3849 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -841,11 +841,11 @@ static void update_end_of_memory_vars(u64 start, u64 size)
 }
 
 int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap, bool want_memblock)
+				struct mhp_restrictions *restrictions)
 {
 	int ret;
 
-	ret = __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	ret = __add_pages(nid, start_pfn, nr_pages, restrictions);
 	WARN_ON_ONCE(ret);
 
 	/* update max_pfn, max_low_pfn and high_memory */
@@ -855,15 +855,15 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	return ret;
 }
 
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-		bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
 	init_memory_mapping(start, start + size);
 
-	return add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
 #define PAGE_INUSE 0xFD
@@ -1205,24 +1205,20 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end)
 	remove_pagetable(start, end, true, NULL);
 }
 
-int __ref arch_remove_memory(int nid, u64 start, u64 size,
-				struct vmem_altmap *altmap)
+void __ref arch_remove_memory(int nid, u64 start, u64 size,
+			      struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct page *page = pfn_to_page(start_pfn);
 	struct zone *zone;
-	int ret;
 
 	/* With altmap the first mapped page is offset from @start */
 	if (altmap)
 		page += vmem_altmap_offset(altmap);
 	zone = page_zone(page);
-	ret = __remove_pages(zone, start_pfn, nr_pages, altmap);
-	WARN_ON_ONCE(ret);
+	__remove_pages(zone, start_pfn, nr_pages, altmap);
 	kernel_physical_mapping_remove(start, start + size);
-
-	return ret;
 }
 #endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index c805db6236b4..59726aaf4671 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -142,7 +142,7 @@ int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
 		goto err_out;
 	}
 	/* get bndregs field from current task's xsave area */
-	bndregs = get_xsave_field_ptr(XFEATURE_MASK_BNDREGS);
+	bndregs = get_xsave_field_ptr(XFEATURE_BNDREGS);
 	if (!bndregs) {
 		err = -EINVAL;
 		goto err_out;
@@ -190,7 +190,7 @@ static __user void *mpx_get_bounds_dir(void)
 	 * The bounds directory pointer is stored in a register
 	 * only accessible if we first do an xsave.
 	 */
-	bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
 	if (!bndcsr)
 		return MPX_INVALID_BOUNDS_DIR;
 
@@ -376,7 +376,7 @@ static int do_mpx_bt_fault(void)
 	const struct mpx_bndcsr *bndcsr;
 	struct mm_struct *mm = current->mm;
 
-	bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
 	if (!bndcsr)
 		return -EINVAL;
 	/*
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index 047a77f6a10c..1dcfc91c8f0c 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -18,6 +18,7 @@
 
 #include <asm/cpufeature.h>             /* boot_cpu_has, ...            */
 #include <asm/mmu_context.h>            /* vma_pkey()                   */
+#include <asm/fpu/internal.h>		/* init_fpstate			*/
 
 int __execute_only_pkey(struct mm_struct *mm)
 {
@@ -39,17 +40,12 @@ int __execute_only_pkey(struct mm_struct *mm)
 	 * dance to set PKRU if we do not need to.  Check it
 	 * first and assume that if the execute-only pkey is
 	 * write-disabled that we do not have to set it
-	 * ourselves.  We need preempt off so that nobody
-	 * can make fpregs inactive.
+	 * ourselves.
 	 */
-	preempt_disable();
 	if (!need_to_set_mm_pkey &&
-	    current->thread.fpu.initialized &&
 	    !__pkru_allows_read(read_pkru(), execute_only_pkey)) {
-		preempt_enable();
 		return execute_only_pkey;
 	}
-	preempt_enable();
 
 	/*
 	 * Set up PKRU so that it denies access for everything
@@ -131,7 +127,6 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey
  * in the process's lifetime will not accidentally get access
  * to data which is pkey-protected later on.
  */
-static
 u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) |
 		      PKRU_AD_KEY( 4) | PKRU_AD_KEY( 5) | PKRU_AD_KEY( 6) |
 		      PKRU_AD_KEY( 7) | PKRU_AD_KEY( 8) | PKRU_AD_KEY( 9) |
@@ -148,13 +143,6 @@ void copy_init_pkru_to_fpregs(void)
 {
 	u32 init_pkru_value_snapshot = READ_ONCE(init_pkru_value);
 	/*
-	 * Any write to PKRU takes it out of the XSAVE 'init
-	 * state' which increases context switch cost.  Avoid
-	 * writing 0 when PKRU was already 0.
-	 */
-	if (!init_pkru_value_snapshot && !read_pkru())
-		return;
-	/*
 	 * Override the PKRU state that came from 'init_fpstate'
 	 * with the baseline from the process.
 	 */
@@ -174,6 +162,7 @@ static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf,
 static ssize_t init_pkru_write_file(struct file *file,
 		 const char __user *user_buf, size_t count, loff_t *ppos)
 {
+	struct pkru_state *pk;
 	char buf[32];
 	ssize_t len;
 	u32 new_init_pkru;
@@ -196,6 +185,10 @@ static ssize_t init_pkru_write_file(struct file *file,
 		return -EINVAL;
 
 	WRITE_ONCE(init_pkru_value, new_init_pkru);
+	pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU);
+	if (!pk)
+		return -EINVAL;
+	pk->pkru = new_init_pkru;
 	return count;
 }
 
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 0d9cdffce6ac..b29e82f190c7 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -117,6 +117,8 @@ static bool is_simm32(s64 value)
 #define IA32_JLE 0x7E
 #define IA32_JG  0x7F
 
+#define COND_JMP_OPCODE_INVALID	(0xFF)
+
 /*
  * Map eBPF registers to IA32 32bit registers or stack scratch space.
  *
@@ -698,19 +700,12 @@ static inline void emit_ia32_neg64(const u8 dst[], bool dstk, u8 **pprog)
 		      STACK_VAR(dst_hi));
 	}
 
-	/* xor ecx,ecx */
-	EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX));
-	/* sub dreg_lo,ecx */
-	EMIT2(0x2B, add_2reg(0xC0, dreg_lo, IA32_ECX));
-	/* mov dreg_lo,ecx */
-	EMIT2(0x89, add_2reg(0xC0, dreg_lo, IA32_ECX));
-
-	/* xor ecx,ecx */
-	EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX));
-	/* sbb dreg_hi,ecx */
-	EMIT2(0x19, add_2reg(0xC0, dreg_hi, IA32_ECX));
-	/* mov dreg_hi,ecx */
-	EMIT2(0x89, add_2reg(0xC0, dreg_hi, IA32_ECX));
+	/* neg dreg_lo */
+	EMIT2(0xF7, add_1reg(0xD8, dreg_lo));
+	/* adc dreg_hi,0x0 */
+	EMIT3(0x83, add_1reg(0xD0, dreg_hi), 0x00);
+	/* neg dreg_hi */
+	EMIT2(0xF7, add_1reg(0xD8, dreg_hi));
 
 	if (dstk) {
 		/* mov dword ptr [ebp+off],dreg_lo */
@@ -1613,6 +1608,75 @@ static inline void emit_push_r64(const u8 src[], u8 **pprog)
 	*pprog = prog;
 }
 
+static u8 get_cond_jmp_opcode(const u8 op, bool is_cmp_lo)
+{
+	u8 jmp_cond;
+
+	/* Convert BPF opcode to x86 */
+	switch (op) {
+	case BPF_JEQ:
+		jmp_cond = IA32_JE;
+		break;
+	case BPF_JSET:
+	case BPF_JNE:
+		jmp_cond = IA32_JNE;
+		break;
+	case BPF_JGT:
+		/* GT is unsigned '>', JA in x86 */
+		jmp_cond = IA32_JA;
+		break;
+	case BPF_JLT:
+		/* LT is unsigned '<', JB in x86 */
+		jmp_cond = IA32_JB;
+		break;
+	case BPF_JGE:
+		/* GE is unsigned '>=', JAE in x86 */
+		jmp_cond = IA32_JAE;
+		break;
+	case BPF_JLE:
+		/* LE is unsigned '<=', JBE in x86 */
+		jmp_cond = IA32_JBE;
+		break;
+	case BPF_JSGT:
+		if (!is_cmp_lo)
+			/* Signed '>', GT in x86 */
+			jmp_cond = IA32_JG;
+		else
+			/* GT is unsigned '>', JA in x86 */
+			jmp_cond = IA32_JA;
+		break;
+	case BPF_JSLT:
+		if (!is_cmp_lo)
+			/* Signed '<', LT in x86 */
+			jmp_cond = IA32_JL;
+		else
+			/* LT is unsigned '<', JB in x86 */
+			jmp_cond = IA32_JB;
+		break;
+	case BPF_JSGE:
+		if (!is_cmp_lo)
+			/* Signed '>=', GE in x86 */
+			jmp_cond = IA32_JGE;
+		else
+			/* GE is unsigned '>=', JAE in x86 */
+			jmp_cond = IA32_JAE;
+		break;
+	case BPF_JSLE:
+		if (!is_cmp_lo)
+			/* Signed '<=', LE in x86 */
+			jmp_cond = IA32_JLE;
+		else
+			/* LE is unsigned '<=', JBE in x86 */
+			jmp_cond = IA32_JBE;
+		break;
+	default: /* to silence GCC warning */
+		jmp_cond = COND_JMP_OPCODE_INVALID;
+		break;
+	}
+
+	return jmp_cond;
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
@@ -2069,10 +2133,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_JMP | BPF_JLT | BPF_X:
 		case BPF_JMP | BPF_JGE | BPF_X:
 		case BPF_JMP | BPF_JLE | BPF_X:
-		case BPF_JMP | BPF_JSGT | BPF_X:
-		case BPF_JMP | BPF_JSLE | BPF_X:
-		case BPF_JMP | BPF_JSLT | BPF_X:
-		case BPF_JMP | BPF_JSGE | BPF_X:
 		case BPF_JMP32 | BPF_JEQ | BPF_X:
 		case BPF_JMP32 | BPF_JNE | BPF_X:
 		case BPF_JMP32 | BPF_JGT | BPF_X:
@@ -2118,6 +2178,40 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));
 			goto emit_cond_jmp;
 		}
+		case BPF_JMP | BPF_JSGT | BPF_X:
+		case BPF_JMP | BPF_JSLE | BPF_X:
+		case BPF_JMP | BPF_JSLT | BPF_X:
+		case BPF_JMP | BPF_JSGE | BPF_X: {
+			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 sreg_lo = sstk ? IA32_ECX : src_lo;
+			u8 sreg_hi = sstk ? IA32_EBX : src_hi;
+
+			if (dstk) {
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+				      STACK_VAR(dst_lo));
+				EMIT3(0x8B,
+				      add_2reg(0x40, IA32_EBP,
+					       IA32_EDX),
+				      STACK_VAR(dst_hi));
+			}
+
+			if (sstk) {
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+				      STACK_VAR(src_lo));
+				EMIT3(0x8B,
+				      add_2reg(0x40, IA32_EBP,
+					       IA32_EBX),
+				      STACK_VAR(src_hi));
+			}
+
+			/* cmp dreg_hi,sreg_hi */
+			EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
+			EMIT2(IA32_JNE, 10);
+			/* cmp dreg_lo,sreg_lo */
+			EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));
+			goto emit_cond_jmp_signed;
+		}
 		case BPF_JMP | BPF_JSET | BPF_X:
 		case BPF_JMP32 | BPF_JSET | BPF_X: {
 			bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP;
@@ -2194,10 +2288,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_JMP | BPF_JLT | BPF_K:
 		case BPF_JMP | BPF_JGE | BPF_K:
 		case BPF_JMP | BPF_JLE | BPF_K:
-		case BPF_JMP | BPF_JSGT | BPF_K:
-		case BPF_JMP | BPF_JSLE | BPF_K:
-		case BPF_JMP | BPF_JSLT | BPF_K:
-		case BPF_JMP | BPF_JSGE | BPF_K:
 		case BPF_JMP32 | BPF_JEQ | BPF_K:
 		case BPF_JMP32 | BPF_JNE | BPF_K:
 		case BPF_JMP32 | BPF_JGT | BPF_K:
@@ -2238,50 +2328,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			/* cmp dreg_lo,sreg_lo */
 			EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));
 
-emit_cond_jmp:		/* Convert BPF opcode to x86 */
-			switch (BPF_OP(code)) {
-			case BPF_JEQ:
-				jmp_cond = IA32_JE;
-				break;
-			case BPF_JSET:
-			case BPF_JNE:
-				jmp_cond = IA32_JNE;
-				break;
-			case BPF_JGT:
-				/* GT is unsigned '>', JA in x86 */
-				jmp_cond = IA32_JA;
-				break;
-			case BPF_JLT:
-				/* LT is unsigned '<', JB in x86 */
-				jmp_cond = IA32_JB;
-				break;
-			case BPF_JGE:
-				/* GE is unsigned '>=', JAE in x86 */
-				jmp_cond = IA32_JAE;
-				break;
-			case BPF_JLE:
-				/* LE is unsigned '<=', JBE in x86 */
-				jmp_cond = IA32_JBE;
-				break;
-			case BPF_JSGT:
-				/* Signed '>', GT in x86 */
-				jmp_cond = IA32_JG;
-				break;
-			case BPF_JSLT:
-				/* Signed '<', LT in x86 */
-				jmp_cond = IA32_JL;
-				break;
-			case BPF_JSGE:
-				/* Signed '>=', GE in x86 */
-				jmp_cond = IA32_JGE;
-				break;
-			case BPF_JSLE:
-				/* Signed '<=', LE in x86 */
-				jmp_cond = IA32_JLE;
-				break;
-			default: /* to silence GCC warning */
+emit_cond_jmp:		jmp_cond = get_cond_jmp_opcode(BPF_OP(code), false);
+			if (jmp_cond == COND_JMP_OPCODE_INVALID)
 				return -EFAULT;
-			}
 			jmp_offset = addrs[i + insn->off] - addrs[i];
 			if (is_imm8(jmp_offset)) {
 				EMIT2(jmp_cond, jmp_offset);
@@ -2291,7 +2340,66 @@ emit_cond_jmp:		/* Convert BPF opcode to x86 */
 				pr_err("cond_jmp gen bug %llx\n", jmp_offset);
 				return -EFAULT;
 			}
+			break;
+		}
+		case BPF_JMP | BPF_JSGT | BPF_K:
+		case BPF_JMP | BPF_JSLE | BPF_K:
+		case BPF_JMP | BPF_JSLT | BPF_K:
+		case BPF_JMP | BPF_JSGE | BPF_K: {
+			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 sreg_lo = IA32_ECX;
+			u8 sreg_hi = IA32_EBX;
+			u32 hi;
 
+			if (dstk) {
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+				      STACK_VAR(dst_lo));
+				EMIT3(0x8B,
+				      add_2reg(0x40, IA32_EBP,
+					       IA32_EDX),
+				      STACK_VAR(dst_hi));
+			}
+
+			/* mov ecx,imm32 */
+			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
+			hi = imm32 & (1 << 31) ? (u32)~0 : 0;
+			/* mov ebx,imm32 */
+			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi);
+			/* cmp dreg_hi,sreg_hi */
+			EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
+			EMIT2(IA32_JNE, 10);
+			/* cmp dreg_lo,sreg_lo */
+			EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));
+
+			/*
+			 * For simplicity of branch offset computation,
+			 * let's use fixed jump coding here.
+			 */
+emit_cond_jmp_signed:	/* Check the condition for low 32-bit comparison */
+			jmp_cond = get_cond_jmp_opcode(BPF_OP(code), true);
+			if (jmp_cond == COND_JMP_OPCODE_INVALID)
+				return -EFAULT;
+			jmp_offset = addrs[i + insn->off] - addrs[i] + 8;
+			if (is_simm32(jmp_offset)) {
+				EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset);
+			} else {
+				pr_err("cond_jmp gen bug %llx\n", jmp_offset);
+				return -EFAULT;
+			}
+			EMIT2(0xEB, 6);
+
+			/* Check the condition for high 32-bit comparison */
+			jmp_cond = get_cond_jmp_opcode(BPF_OP(code), false);
+			if (jmp_cond == COND_JMP_OPCODE_INVALID)
+				return -EFAULT;
+			jmp_offset = addrs[i + insn->off] - addrs[i];
+			if (is_simm32(jmp_offset)) {
+				EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset);
+			} else {
+				pr_err("cond_jmp gen bug %llx\n", jmp_offset);
+				return -EFAULT;
+			}
 			break;
 		}
 		case BPF_JMP | BPF_JA:
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 52e55108404e..d3a73f9335e1 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1119,6 +1119,8 @@ static const struct dmi_system_id pciirq_dmi_table[] __initconst = {
 
 void __init pcibios_irq_init(void)
 {
+	struct irq_routing_table *rtable = NULL;
+
 	DBG(KERN_DEBUG "PCI: IRQ init\n");
 
 	if (raw_pci_ops == NULL)
@@ -1129,8 +1131,10 @@ void __init pcibios_irq_init(void)
 	pirq_table = pirq_find_routing_table();
 
 #ifdef CONFIG_PCI_BIOS
-	if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN))
+	if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN)) {
 		pirq_table = pcibios_get_irq_routing_table();
+		rtable = pirq_table;
+	}
 #endif
 	if (pirq_table) {
 		pirq_peer_trick();
@@ -1145,8 +1149,10 @@ void __init pcibios_irq_init(void)
 		 * If we're using the I/O APIC, avoid using the PCI IRQ
 		 * routing table
 		 */
-		if (io_apic_assign_pci_irqs)
+		if (io_apic_assign_pci_irqs) {
+			kfree(rtable);
 			pirq_table = NULL;
+		}
 	}
 
 	x86_init.pci.fixup_irqs();
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
index bcddf09b5aa3..4845b8c7be7f 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -90,7 +90,6 @@ static int get_e820_md5(struct e820_table *table, void *buf)
 	}
 
 	desc->tfm = tfm;
-	desc->flags = 0;
 
 	size = offsetof(struct e820_table, entries) +
 		sizeof(struct e820_entry) * table->nr_entries;
diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h
index ef898af102d1..56a2f0913e3c 100644
--- a/arch/x86/um/asm/syscall.h
+++ b/arch/x86/um/asm/syscall.h
@@ -9,7 +9,7 @@ typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
 					  unsigned long, unsigned long,
 					  unsigned long, unsigned long);
 
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
 {
 #ifdef CONFIG_X86_32
 	return AUDIT_ARCH_I386;
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 0766a08bdf45..07054572297f 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -105,7 +105,7 @@ void xen_mc_flush(void)
 		for (i = 0; i < b->mcidx; i++) {
 			if (b->entries[i].result < 0) {
 #if MC_DEBUG
-				pr_err("  call %2d: op=%lu arg=[%lx] result=%ld\t%pF\n",
+				pr_err("  call %2d: op=%lu arg=[%lx] result=%ld\t%pS\n",
 				       i + 1,
 				       b->debug[i].op,
 				       b->debug[i].args[0],