257 files changed, 6776 insertions, 2730 deletions

diff --git a/Documentation/devicetree/bindings/crypto/qcom-qce.txt b/Documentation/devicetree/bindings/crypto/qcom-qce.txt
deleted file mode 100644
index fdd53b184ba8..000000000000
--- a/Documentation/devicetree/bindings/crypto/qcom-qce.txt
+++ /dev/null
@@ -1,25 +0,0 @@
-Qualcomm crypto engine driver
-
-Required properties:
-
-- compatible  : should be "qcom,crypto-v5.1"
-- reg         : specifies base physical address and size of the registers map
-- clocks      : phandle to clock-controller plus clock-specifier pair
-- clock-names : "iface" clocks register interface
-                "bus" clocks data transfer interface
-                "core" clocks rest of the crypto block
-- dmas        : DMA specifiers for tx and rx dma channels. For more see
-                Documentation/devicetree/bindings/dma/dma.txt
-- dma-names   : DMA request names should be "rx" and "tx"
-
-Example:
-	crypto@fd45a000 {
-		compatible = "qcom,crypto-v5.1";
-		reg = <0xfd45a000 0x6000>;
-		clocks = <&gcc GCC_CE2_AHB_CLK>,
-			 <&gcc GCC_CE2_AXI_CLK>,
-			 <&gcc GCC_CE2_CLK>;
-		clock-names = "iface", "bus", "core";
-		dmas = <&cryptobam 2>, <&cryptobam 3>;
-		dma-names = "rx", "tx";
-	};
diff --git a/Documentation/devicetree/bindings/crypto/qcom-qce.yaml b/Documentation/devicetree/bindings/crypto/qcom-qce.yaml
new file mode 100644
index 000000000000..e375bd981300
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/qcom-qce.yaml
@@ -0,0 +1,123 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/crypto/qcom-qce.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm crypto engine driver
+
+maintainers:
+  - Bhupesh Sharma <bhupesh.sharma@linaro.org>
+
+description:
+  This document defines the binding for the QCE crypto
+  controller found on Qualcomm parts.
+
+properties:
+  compatible:
+    oneOf:
+      - const: qcom,crypto-v5.1
+        deprecated: true
+        description: Kept only for ABI backward compatibility
+
+      - const: qcom,crypto-v5.4
+        deprecated: true
+        description: Kept only for ABI backward compatibility
+
+      - items:
+          - enum:
+              - qcom,ipq6018-qce
+              - qcom,ipq8074-qce
+              - qcom,msm8996-qce
+              - qcom,sdm845-qce
+          - const: qcom,ipq4019-qce
+          - const: qcom,qce
+
+      - items:
+          - enum:
+              - qcom,sm8250-qce
+              - qcom,sm8350-qce
+              - qcom,sm8450-qce
+              - qcom,sm8550-qce
+          - const: qcom,sm8150-qce
+          - const: qcom,qce
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: iface clocks register interface.
+      - description: bus clocks data transfer interface.
+      - description: core clocks rest of the crypto block.
+
+  clock-names:
+    items:
+      - const: iface
+      - const: bus
+      - const: core
+
+  iommus:
+    minItems: 1
+    maxItems: 8
+    description:
+      phandle to apps_smmu node with sid mask.
+
+  interconnects:
+    maxItems: 1
+    description:
+      Interconnect path between qce crypto and main memory.
+
+  interconnect-names:
+    const: memory
+
+  dmas:
+    items:
+      - description: DMA specifiers for rx dma channel.
+      - description: DMA specifiers for tx dma channel.
+
+  dma-names:
+    items:
+      - const: rx
+      - const: tx
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,crypto-v5.1
+              - qcom,crypto-v5.4
+              - qcom,ipq4019-qce
+
+    then:
+      required:
+        - clocks
+        - clock-names
+
+required:
+  - compatible
+  - reg
+  - dmas
+  - dma-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,gcc-apq8084.h>
+    crypto-engine@fd45a000 {
+        compatible = "qcom,ipq6018-qce", "qcom,ipq4019-qce", "qcom,qce";
+        reg = <0xfd45a000 0x6000>;
+        clocks = <&gcc GCC_CE2_AHB_CLK>,
+                 <&gcc GCC_CE2_AXI_CLK>,
+                 <&gcc GCC_CE2_CLK>;
+        clock-names = "iface", "bus", "core";
+        dmas = <&cryptobam 2>, <&cryptobam 3>;
+        dma-names = "rx", "tx";
+        iommus = <&apps_smmu 0x584 0x0011>,
+                 <&apps_smmu 0x586 0x0011>,
+                 <&apps_smmu 0x594 0x0011>,
+                 <&apps_smmu 0x596 0x0011>;
+    };
diff --git a/MAINTAINERS b/MAINTAINERS
index f0abf21883af..cd69cdfc23a2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2269,7 +2269,7 @@ F:	arch/arm/boot/dts/intel-ixp*
 F:	arch/arm/mach-ixp4xx/
 F:	drivers/bus/intel-ixp4xx-eb.c
 F:	drivers/clocksource/timer-ixp4xx.c
-F:	drivers/crypto/ixp4xx_crypto.c
+F:	drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c
 F:	drivers/gpio/gpio-ixp4xx.c
 F:	drivers/irqchip/irq-ixp4xx.c
 
@@ -10391,7 +10391,7 @@ INTEL IXP4XX CRYPTO SUPPORT
 M:	Corentin Labbe <clabbe@baylibre.com>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
-F:	drivers/crypto/ixp4xx_crypto.c
+F:	drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c
 
 INTEL ISHTP ECLITE DRIVER
 M:	Sumesh K Naduvalath <sumesh.k.naduvalath@intel.com>
@@ -10426,11 +10426,11 @@ INTEL KEEM BAY OCS AES/SM4 CRYPTO DRIVER
 M:	Daniele Alessandrelli <daniele.alessandrelli@intel.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/crypto/intel,keembay-ocs-aes.yaml
-F:	drivers/crypto/keembay/Kconfig
-F:	drivers/crypto/keembay/Makefile
-F:	drivers/crypto/keembay/keembay-ocs-aes-core.c
-F:	drivers/crypto/keembay/ocs-aes.c
-F:	drivers/crypto/keembay/ocs-aes.h
+F:	drivers/crypto/intel/keembay/Kconfig
+F:	drivers/crypto/intel/keembay/Makefile
+F:	drivers/crypto/intel/keembay/keembay-ocs-aes-core.c
+F:	drivers/crypto/intel/keembay/ocs-aes.c
+F:	drivers/crypto/intel/keembay/ocs-aes.h
 
 INTEL KEEM BAY OCS ECC CRYPTO DRIVER
 M:	Daniele Alessandrelli <daniele.alessandrelli@intel.com>
@@ -10438,20 +10438,20 @@ M:	Prabhjot Khurana <prabhjot.khurana@intel.com>
 M:	Mark Gross <mgross@linux.intel.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/crypto/intel,keembay-ocs-ecc.yaml
-F:	drivers/crypto/keembay/Kconfig
-F:	drivers/crypto/keembay/Makefile
-F:	drivers/crypto/keembay/keembay-ocs-ecc.c
+F:	drivers/crypto/intel/keembay/Kconfig
+F:	drivers/crypto/intel/keembay/Makefile
+F:	drivers/crypto/intel/keembay/keembay-ocs-ecc.c
 
 INTEL KEEM BAY OCS HCU CRYPTO DRIVER
 M:	Daniele Alessandrelli <daniele.alessandrelli@intel.com>
 M:	Declan Murphy <declan.murphy@intel.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/crypto/intel,keembay-ocs-hcu.yaml
-F:	drivers/crypto/keembay/Kconfig
-F:	drivers/crypto/keembay/Makefile
-F:	drivers/crypto/keembay/keembay-ocs-hcu-core.c
-F:	drivers/crypto/keembay/ocs-hcu.c
-F:	drivers/crypto/keembay/ocs-hcu.h
+F:	drivers/crypto/intel/keembay/Kconfig
+F:	drivers/crypto/intel/keembay/Makefile
+F:	drivers/crypto/intel/keembay/keembay-ocs-hcu-core.c
+F:	drivers/crypto/intel/keembay/ocs-hcu.c
+F:	drivers/crypto/intel/keembay/ocs-hcu.h
 
 INTEL THUNDER BAY EMMC PHY DRIVER
 M:	Nandhini Srikandan <nandhini.srikandan@intel.com>
@@ -17027,7 +17027,7 @@ QAT DRIVER
 M:	Giovanni Cabiddu <giovanni.cabiddu@intel.com>
 L:	qat-linux@intel.com
 S:	Supported
-F:	drivers/crypto/qat/
+F:	drivers/crypto/intel/qat/
 
 QCOM AUDIO (ASoC) DRIVERS
 M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
@@ -17295,6 +17295,7 @@ M:	Thara Gopinath <thara.gopinath@gmail.com>
 L:	linux-crypto@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
+F:	Documentation/devicetree/bindings/crypto/qcom-qce.yaml
 F:	drivers/crypto/qce/
 
 QUALCOMM EMAC GIGABIT ETHERNET DRIVER
diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi
index f110d6cc195d..6e9bad8f6f33 100644
--- a/arch/arm64/boot/dts/qcom/sm8550.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi
@@ -1850,7 +1850,7 @@
 		};
 
 		crypto: crypto@1de0000 {
-			compatible = "qcom,sm8550-qce";
+			compatible = "qcom,sm8550-qce", "qcom,sm8150-qce", "qcom,qce";
 			reg = <0x0 0x01dfa000 0x0 0x6000>;
 			dmas = <&cryptobam 4>, <&cryptobam 5>;
 			dma-names = "rx", "tx";
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index 7278a37c2d5c..baf450717b24 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -15,6 +15,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 
 	.text
@@ -620,12 +621,12 @@ SYM_FUNC_END(aesbs_decrypt8)
 	.endm
 
 	.align		4
-SYM_FUNC_START(aesbs_ecb_encrypt)
+SYM_TYPED_FUNC_START(aesbs_ecb_encrypt)
 	__ecb_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
 SYM_FUNC_END(aesbs_ecb_encrypt)
 
 	.align		4
-SYM_FUNC_START(aesbs_ecb_decrypt)
+SYM_TYPED_FUNC_START(aesbs_ecb_decrypt)
 	__ecb_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
 SYM_FUNC_END(aesbs_ecb_decrypt)
 
@@ -799,11 +800,11 @@ SYM_FUNC_END(__xts_crypt8)
 	ret
 	.endm
 
-SYM_FUNC_START(aesbs_xts_encrypt)
+SYM_TYPED_FUNC_START(aesbs_xts_encrypt)
 	__xts_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
 SYM_FUNC_END(aesbs_xts_encrypt)
 
-SYM_FUNC_START(aesbs_xts_decrypt)
+SYM_TYPED_FUNC_START(aesbs_xts_decrypt)
 	__xts_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
 SYM_FUNC_END(aesbs_xts_decrypt)
 
diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig
index c1b964447401..7113f9355165 100644
--- a/arch/powerpc/crypto/Kconfig
+++ b/arch/powerpc/crypto/Kconfig
@@ -94,4 +94,21 @@ config CRYPTO_AES_PPC_SPE
 	  architecture specific assembler implementations that work on 1KB
 	  tables or 256 bytes S-boxes.
 
+config CRYPTO_AES_GCM_P10
+	tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)"
+	depends on PPC64 && CPU_LITTLE_ENDIAN
+	select CRYPTO_LIB_AES
+	select CRYPTO_ALGAPI
+	select CRYPTO_AEAD
+	default m
+	help
+	  AEAD cipher: AES cipher algorithms (FIPS-197)
+	  GCM (Galois/Counter Mode) authenticated encryption mode (NIST SP800-38D)
+	  Architecture: powerpc64 using:
+	    - little-endian
+	    - Power10 or later features
+
+	  Support for cryptographic acceleration instructions on Power10 or
+	  later CPU. This module supports stitched acceleration for AES/GCM.
+
 endmenu
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 4808d97fede5..05c7486f42c5 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
 obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o
 obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o
 obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o
+obj-$(CONFIG_CRYPTO_AES_GCM_P10) += aes-gcm-p10-crypto.o
 
 aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
 md5-ppc-y := md5-asm.o md5-glue.o
@@ -21,3 +22,15 @@ sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
 sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
 crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
 crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
+aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp8-ppc.o aesp8-ppc.o
+
+quiet_cmd_perl = PERL    $@
+      cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@
+
+targets += aesp8-ppc.S ghashp8-ppc.S
+
+$(obj)/aesp8-ppc.S $(obj)/ghashp8-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
+	$(call if_changed,perl)
+
+OBJECT_FILES_NON_STANDARD_aesp8-ppc.o := y
+OBJECT_FILES_NON_STANDARD_ghashp8-ppc.o := y
diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c
new file mode 100644
index 000000000000..bd3475f5348d
--- /dev/null
+++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c
@@ -0,0 +1,343 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Glue code for accelerated AES-GCM stitched implementation for ppc64le.
+ *
+ * Copyright 2022- IBM Inc. All rights reserved
+ */
+
+#include <asm/unaligned.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/b128ops.h>
+#include <crypto/gf128mul.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+#define	PPC_ALIGN		16
+#define GCM_IV_SIZE		12
+
+MODULE_DESCRIPTION("PPC64le AES-GCM with Stitched implementation");
+MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("aes");
+
+asmlinkage int aes_p8_set_encrypt_key(const u8 *userKey, const int bits,
+				      void *key);
+asmlinkage void aes_p8_encrypt(const u8 *in, u8 *out, const void *key);
+asmlinkage void aes_p10_gcm_encrypt(u8 *in, u8 *out, size_t len,
+				    void *rkey, u8 *iv, void *Xi);
+asmlinkage void aes_p10_gcm_decrypt(u8 *in, u8 *out, size_t len,
+				    void *rkey, u8 *iv, void *Xi);
+asmlinkage void gcm_init_htable(unsigned char htable[256], unsigned char Xi[16]);
+asmlinkage void gcm_ghash_p8(unsigned char *Xi, unsigned char *Htable,
+		unsigned char *aad, unsigned int alen);
+
+struct aes_key {
+	u8 key[AES_MAX_KEYLENGTH];
+	u64 rounds;
+};
+
+struct gcm_ctx {
+	u8 iv[16];
+	u8 ivtag[16];
+	u8 aad_hash[16];
+	u64 aadLen;
+	u64 Plen;	/* offset 56 - used in aes_p10_gcm_{en/de}crypt */
+};
+struct Hash_ctx {
+	u8 H[16];	/* subkey */
+	u8 Htable[256];	/* Xi, Hash table(offset 32) */
+};
+
+struct p10_aes_gcm_ctx {
+	struct aes_key enc_key;
+};
+
+static void vsx_begin(void)
+{
+	preempt_disable();
+	enable_kernel_vsx();
+}
+
+static void vsx_end(void)
+{
+	disable_kernel_vsx();
+	preempt_enable();
+}
+
+static void set_subkey(unsigned char *hash)
+{
+	*(u64 *)&hash[0] = be64_to_cpup((__be64 *)&hash[0]);
+	*(u64 *)&hash[8] = be64_to_cpup((__be64 *)&hash[8]);
+}
+
+/*
+ * Compute aad if any.
+ *   - Hash aad and copy to Xi.
+ */
+static void set_aad(struct gcm_ctx *gctx, struct Hash_ctx *hash,
+		    unsigned char *aad, int alen)
+{
+	int i;
+	u8 nXi[16] = {0, };
+
+	gctx->aadLen = alen;
+	i = alen & ~0xf;
+	if (i) {
+		gcm_ghash_p8(nXi, hash->Htable+32, aad, i);
+		aad += i;
+		alen -= i;
+	}
+	if (alen) {
+		for (i = 0; i < alen; i++)
+			nXi[i] ^= aad[i];
+
+		memset(gctx->aad_hash, 0, 16);
+		gcm_ghash_p8(gctx->aad_hash, hash->Htable+32, nXi, 16);
+	} else {
+		memcpy(gctx->aad_hash, nXi, 16);
+	}
+
+	memcpy(hash->Htable, gctx->aad_hash, 16);
+}
+
+static void gcmp10_init(struct gcm_ctx *gctx, u8 *iv, unsigned char *rdkey,
+			struct Hash_ctx *hash, u8 *assoc, unsigned int assoclen)
+{
+	__be32 counter = cpu_to_be32(1);
+
+	aes_p8_encrypt(hash->H, hash->H, rdkey);
+	set_subkey(hash->H);
+	gcm_init_htable(hash->Htable+32, hash->H);
+
+	*((__be32 *)(iv+12)) = counter;
+
+	gctx->Plen = 0;
+
+	/*
+	 * Encrypt counter vector as iv tag and increment counter.
+	 */
+	aes_p8_encrypt(iv, gctx->ivtag, rdkey);
+
+	counter = cpu_to_be32(2);
+	*((__be32 *)(iv+12)) = counter;
+	memcpy(gctx->iv, iv, 16);
+
+	gctx->aadLen = assoclen;
+	memset(gctx->aad_hash, 0, 16);
+	if (assoclen)
+		set_aad(gctx, hash, assoc, assoclen);
+}
+
+static void finish_tag(struct gcm_ctx *gctx, struct Hash_ctx *hash, int len)
+{
+	int i;
+	unsigned char len_ac[16 + PPC_ALIGN];
+	unsigned char *aclen = PTR_ALIGN((void *)len_ac, PPC_ALIGN);
+	__be64 clen = cpu_to_be64(len << 3);
+	__be64 alen = cpu_to_be64(gctx->aadLen << 3);
+
+	if (len == 0 && gctx->aadLen == 0) {
+		memcpy(hash->Htable, gctx->ivtag, 16);
+		return;
+	}
+
+	/*
+	 * Len is in bits.
+	 */
+	*((__be64 *)(aclen)) = alen;
+	*((__be64 *)(aclen+8)) = clen;
+
+	/*
+	 * hash (AAD len and len)
+	 */
+	gcm_ghash_p8(hash->Htable, hash->Htable+32, aclen, 16);
+
+	for (i = 0; i < 16; i++)
+		hash->Htable[i] ^= gctx->ivtag[i];
+}
+
+static int set_authsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	switch (authsize) {
+	case 4:
+	case 8:
+	case 12:
+	case 13:
+	case 14:
+	case 15:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int p10_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key,
+			     unsigned int keylen)
+{
+	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
+	struct p10_aes_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	vsx_begin();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	vsx_end();
+
+	return ret ? -EINVAL : 0;
+}
+
+static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
+{
+	struct crypto_tfm *tfm = req->base.tfm;
+	struct p10_aes_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
+	u8 databuf[sizeof(struct gcm_ctx) + PPC_ALIGN];
+	struct gcm_ctx *gctx = PTR_ALIGN((void *)databuf, PPC_ALIGN);
+	u8 hashbuf[sizeof(struct Hash_ctx) + PPC_ALIGN];
+	struct Hash_ctx *hash = PTR_ALIGN((void *)hashbuf, PPC_ALIGN);
+	struct scatter_walk assoc_sg_walk;
+	struct skcipher_walk walk;
+	u8 *assocmem = NULL;
+	u8 *assoc;
+	unsigned int assoclen = req->assoclen;
+	unsigned int cryptlen = req->cryptlen;
+	unsigned char ivbuf[AES_BLOCK_SIZE+PPC_ALIGN];
+	unsigned char *iv = PTR_ALIGN((void *)ivbuf, PPC_ALIGN);
+	int ret;
+	unsigned long auth_tag_len = crypto_aead_authsize(__crypto_aead_cast(tfm));
+	u8 otag[16];
+	int total_processed = 0;
+
+	memset(databuf, 0, sizeof(databuf));
+	memset(hashbuf, 0, sizeof(hashbuf));
+	memset(ivbuf, 0, sizeof(ivbuf));
+	memcpy(iv, req->iv, GCM_IV_SIZE);
+
+	/* Linearize assoc, if not already linear */
+	if (req->src->length >= assoclen && req->src->length) {
+		scatterwalk_start(&assoc_sg_walk, req->src);
+		assoc = scatterwalk_map(&assoc_sg_walk);
+	} else {
+		gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			      GFP_KERNEL : GFP_ATOMIC;
+
+		/* assoc can be any length, so must be on heap */
+		assocmem = kmalloc(assoclen, flags);
+		if (unlikely(!assocmem))
+			return -ENOMEM;
+		assoc = assocmem;
+
+		scatterwalk_map_and_copy(assoc, req->src, 0, assoclen, 0);
+	}
+
+	vsx_begin();
+	gcmp10_init(gctx, iv, (unsigned char *) &ctx->enc_key, hash, assoc, assoclen);
+	vsx_end();
+
+	if (!assocmem)
+		scatterwalk_unmap(assoc);
+	else
+		kfree(assocmem);
+
+	if (enc)
+		ret = skcipher_walk_aead_encrypt(&walk, req, false);
+	else
+		ret = skcipher_walk_aead_decrypt(&walk, req, false);
+	if (ret)
+		return ret;
+
+	while (walk.nbytes > 0 && ret == 0) {
+
+		vsx_begin();
+		if (enc)
+			aes_p10_gcm_encrypt(walk.src.virt.addr,
+					    walk.dst.virt.addr,
+					    walk.nbytes,
+					    &ctx->enc_key, gctx->iv, hash->Htable);
+		else
+			aes_p10_gcm_decrypt(walk.src.virt.addr,
+					    walk.dst.virt.addr,
+					    walk.nbytes,
+					    &ctx->enc_key, gctx->iv, hash->Htable);
+		vsx_end();
+
+		total_processed += walk.nbytes;
+		ret = skcipher_walk_done(&walk, 0);
+	}
+
+	if (ret)
+		return ret;
+
+	/* Finalize hash */
+	vsx_begin();
+	finish_tag(gctx, hash, total_processed);
+	vsx_end();
+
+	/* copy Xi to end of dst */
+	if (enc)
+		scatterwalk_map_and_copy(hash->Htable, req->dst, req->assoclen + cryptlen,
+					 auth_tag_len, 1);
+	else {
+		scatterwalk_map_and_copy(otag, req->src,
+					 req->assoclen + cryptlen - auth_tag_len,
+					 auth_tag_len, 0);
+
+		if (crypto_memneq(otag, hash->Htable, auth_tag_len)) {
+			memzero_explicit(hash->Htable, 16);
+			return -EBADMSG;
+		}
+	}
+
+	return 0;
+}
+
+static int p10_aes_gcm_encrypt(struct aead_request *req)
+{
+	return p10_aes_gcm_crypt(req, 1);
+}
+
+static int p10_aes_gcm_decrypt(struct aead_request *req)
+{
+	return p10_aes_gcm_crypt(req, 0);
+}
+
+static struct aead_alg gcm_aes_alg = {
+	.ivsize			= GCM_IV_SIZE,
+	.maxauthsize		= 16,
+
+	.setauthsize		= set_authsize,
+	.setkey			= p10_aes_gcm_setkey,
+	.encrypt		= p10_aes_gcm_encrypt,
+	.decrypt		= p10_aes_gcm_decrypt,
+
+	.base.cra_name		= "gcm(aes)",
+	.base.cra_driver_name	= "aes_gcm_p10",
+	.base.cra_priority	= 2100,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct p10_aes_gcm_ctx),
+	.base.cra_module	= THIS_MODULE,
+};
+
+static int __init p10_init(void)
+{
+	return crypto_register_aead(&gcm_aes_alg);
+}
+
+static void __exit p10_exit(void)
+{
+	crypto_unregister_aead(&gcm_aes_alg);
+}
+
+module_cpu_feature_match(PPC_MODULE_FEATURE_P10, p10_init);
+module_exit(p10_exit);
diff --git a/arch/powerpc/crypto/aes-gcm-p10.S b/arch/powerpc/crypto/aes-gcm-p10.S
new file mode 100644
index 000000000000..a51f4b265308
--- /dev/null
+++ b/arch/powerpc/crypto/aes-gcm-p10.S
@@ -0,0 +1,1521 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+ #
+ # Accelerated AES-GCM stitched implementation for ppc64le.
+ #
+ # Copyright 2022- IBM Inc. All rights reserved
+ #
+ #===================================================================================
+ # Written by Danny Tsen <dtsen@linux.ibm.com>
+ #
+ # GHASH is based on the Karatsuba multiplication method.
+ #
+ #    Xi xor X1
+ #
+ #    X1 * H^4 + X2 * H^3 + x3 * H^2 + X4 * H =
+ #      (X1.h * H4.h + xX.l * H4.l + X1 * H4) +
+ #      (X2.h * H3.h + X2.l * H3.l + X2 * H3) +
+ #      (X3.h * H2.h + X3.l * H2.l + X3 * H2) +
+ #      (X4.h * H.h + X4.l * H.l + X4 * H)
+ #
+ # Xi = v0
+ # H Poly = v2
+ # Hash keys = v3 - v14
+ #     ( H.l, H, H.h)
+ #     ( H^2.l, H^2, H^2.h)
+ #     ( H^3.l, H^3, H^3.h)
+ #     ( H^4.l, H^4, H^4.h)
+ #
+ # v30 is IV
+ # v31 - counter 1
+ #
+ # AES used,
+ #     vs0 - vs14 for round keys
+ #     v15, v16, v17, v18, v19, v20, v21, v22 for 8 blocks (encrypted)
+ #
+ # This implementation uses stitched AES-GCM approach to improve overall performance.
+ # AES is implemented with 8x blocks and GHASH is using 2 4x blocks.
+ #
+ # ===================================================================================
+ #
+
+#include <asm/ppc_asm.h>
+#include <linux/linkage.h>
+
+.machine        "any"
+.text
+
+ # 4x loops
+ # v15 - v18 - input states
+ # vs1 - vs9 - round keys
+ #
+.macro Loop_aes_middle4x
+	xxlor	19+32, 1, 1
+	xxlor	20+32, 2, 2
+	xxlor	21+32, 3, 3
+	xxlor	22+32, 4, 4
+
+	vcipher	15, 15, 19
+	vcipher	16, 16, 19
+	vcipher	17, 17, 19
+	vcipher	18, 18, 19
+
+	vcipher	15, 15, 20
+	vcipher	16, 16, 20
+	vcipher	17, 17, 20
+	vcipher	18, 18, 20
+
+	vcipher	15, 15, 21
+	vcipher	16, 16, 21
+	vcipher	17, 17, 21
+	vcipher	18, 18, 21
+
+	vcipher	15, 15, 22
+	vcipher	16, 16, 22
+	vcipher	17, 17, 22
+	vcipher	18, 18, 22
+
+	xxlor	19+32, 5, 5
+	xxlor	20+32, 6, 6
+	xxlor	21+32, 7, 7
+	xxlor	22+32, 8, 8
+
+	vcipher	15, 15, 19
+	vcipher	16, 16, 19
+	vcipher	17, 17, 19
+	vcipher	18, 18, 19
+
+	vcipher	15, 15, 20
+	vcipher	16, 16, 20
+	vcipher	17, 17, 20
+	vcipher	18, 18, 20
+
+	vcipher	15, 15, 21
+	vcipher	16, 16, 21
+	vcipher	17, 17, 21
+	vcipher	18, 18, 21
+
+	vcipher	15, 15, 22
+	vcipher	16, 16, 22
+	vcipher	17, 17, 22
+	vcipher	18, 18, 22
+
+	xxlor	23+32, 9, 9
+	vcipher	15, 15, 23
+	vcipher	16, 16, 23
+	vcipher	17, 17, 23
+	vcipher	18, 18, 23
+.endm
+
+ # 8x loops
+ # v15 - v22 - input states
+ # vs1 - vs9 - round keys
+ #
+.macro Loop_aes_middle8x
+	xxlor	23+32, 1, 1
+	xxlor	24+32, 2, 2
+	xxlor	25+32, 3, 3
+	xxlor	26+32, 4, 4
+
+	vcipher	15, 15, 23
+	vcipher	16, 16, 23
+	vcipher	17, 17, 23
+	vcipher	18, 18, 23
+	vcipher	19, 19, 23
+	vcipher	20, 20, 23
+	vcipher	21, 21, 23
+	vcipher	22, 22, 23
+
+	vcipher	15, 15, 24
+	vcipher	16, 16, 24
+	vcipher	17, 17, 24
+	vcipher	18, 18, 24
+	vcipher	19, 19, 24
+	vcipher	20, 20, 24
+	vcipher	21, 21, 24
+	vcipher	22, 22, 24
+
+	vcipher	15, 15, 25
+	vcipher	16, 16, 25
+	vcipher	17, 17, 25
+	vcipher	18, 18, 25
+	vcipher	19, 19, 25
+	vcipher	20, 20, 25
+	vcipher	21, 21, 25
+	vcipher	22, 22, 25
+
+	vcipher	15, 15, 26
+	vcipher	16, 16, 26
+	vcipher	17, 17, 26
+	vcipher	18, 18, 26
+	vcipher	19, 19, 26
+	vcipher	20, 20, 26
+	vcipher	21, 21, 26
+	vcipher	22, 22, 26
+
+	xxlor	23+32, 5, 5
+	xxlor	24+32, 6, 6
+	xxlor	25+32, 7, 7
+	xxlor	26+32, 8, 8
+
+	vcipher	15, 15, 23
+	vcipher	16, 16, 23
+	vcipher	17, 17, 23
+	vcipher	18, 18, 23
+	vcipher	19, 19, 23
+	vcipher	20, 20, 23
+	vcipher	21, 21, 23
+	vcipher	22, 22, 23
+
+	vcipher	15, 15, 24
+	vcipher	16, 16, 24
+	vcipher	17, 17, 24
+	vcipher	18, 18, 24
+	vcipher	19, 19, 24
+	vcipher	20, 20, 24
+	vcipher	21, 21, 24
+	vcipher	22, 22, 24
+
+	vcipher	15, 15, 25
+	vcipher	16, 16, 25
+	vcipher	17, 17, 25
+	vcipher	18, 18, 25
+	vcipher	19, 19, 25
+	vcipher	20, 20, 25
+	vcipher	21, 21, 25
+	vcipher	22, 22, 25
+
+	vcipher	15, 15, 26
+	vcipher	16, 16, 26
+	vcipher	17, 17, 26
+	vcipher	18, 18, 26
+	vcipher	19, 19, 26
+	vcipher	20, 20, 26
+	vcipher	21, 21, 26
+	vcipher	22, 22, 26
+
+	xxlor	23+32, 9, 9
+	vcipher	15, 15, 23
+	vcipher	16, 16, 23
+	vcipher	17, 17, 23
+	vcipher	18, 18, 23
+	vcipher	19, 19, 23
+	vcipher	20, 20, 23
+	vcipher	21, 21, 23
+	vcipher	22, 22, 23
+.endm
+
+.macro Loop_aes_middle_1x
+	xxlor	19+32, 1, 1
+	xxlor	20+32, 2, 2
+	xxlor	21+32, 3, 3
+	xxlor	22+32, 4, 4
+
+	vcipher 15, 15, 19
+	vcipher 15, 15, 20
+	vcipher 15, 15, 21
+	vcipher 15, 15, 22
+
+	xxlor	19+32, 5, 5
+	xxlor	20+32, 6, 6
+	xxlor	21+32, 7, 7
+	xxlor	22+32, 8, 8
+
+	vcipher 15, 15, 19
+	vcipher 15, 15, 20
+	vcipher 15, 15, 21
+	vcipher 15, 15, 22
+
+	xxlor	19+32, 9, 9
+	vcipher 15, 15, 19
+.endm
+
+ #
+ # Compute 4x hash values based on Karatsuba method.
+ #
+.macro ppc_aes_gcm_ghash
+	vxor		15, 15, 0
+
+	vpmsumd		23, 12, 15		# H4.L * X.L
+	vpmsumd		24, 9, 16
+	vpmsumd		25, 6, 17
+	vpmsumd		26, 3, 18
+
+	vxor		23, 23, 24
+	vxor		23, 23, 25
+	vxor		23, 23, 26		# L
+
+	vpmsumd		24, 13, 15		# H4.L * X.H + H4.H * X.L
+	vpmsumd		25, 10, 16		# H3.L * X1.H + H3.H * X1.L
+	vpmsumd		26, 7, 17
+	vpmsumd		27, 4, 18
+
+	vxor		24, 24, 25
+	vxor		24, 24, 26
+	vxor		24, 24, 27		# M
+
+	# sum hash and reduction with H Poly
+	vpmsumd		28, 23, 2		# reduction
+
+	vxor		29, 29, 29
+	vsldoi		26, 24, 29, 8		# mL
+	vsldoi		29, 29, 24, 8		# mH
+	vxor		23, 23, 26		# mL + L
+
+	vsldoi		23, 23, 23, 8		# swap
+	vxor		23, 23, 28
+
+	vpmsumd		24, 14, 15		# H4.H * X.H
+	vpmsumd		25, 11, 16
+	vpmsumd		26, 8, 17
+	vpmsumd		27, 5, 18
+
+	vxor		24, 24, 25
+	vxor		24, 24, 26
+	vxor		24, 24, 27
+
+	vxor		24, 24, 29
+
+	# sum hash and reduction with H Poly
+	vsldoi		27, 23, 23, 8		# swap
+	vpmsumd		23, 23, 2
+	vxor		27, 27, 24
+	vxor		23, 23, 27
+
+	xxlor		32, 23+32, 23+32		# update hash
+
+.endm
+
+ #
+ # Combine two 4x ghash
+ # v15 - v22 - input blocks
+ #
+.macro ppc_aes_gcm_ghash2_4x
+	# first 4x hash
+	vxor		15, 15, 0		# Xi + X
+
+	vpmsumd		23, 12, 15		# H4.L * X.L
+	vpmsumd		24, 9, 16
+	vpmsumd		25, 6, 17
+	vpmsumd		26, 3, 18
+
+	vxor		23, 23, 24
+	vxor		23, 23, 25
+	vxor		23, 23, 26		# L
+
+	vpmsumd		24, 13, 15		# H4.L * X.H + H4.H * X.L
+	vpmsumd		25, 10, 16		# H3.L * X1.H + H3.H * X1.L
+	vpmsumd		26, 7, 17
+	vpmsumd		27, 4, 18
+
+	vxor		24, 24, 25
+	vxor		24, 24, 26
+
+	# sum hash and reduction with H Poly
+	vpmsumd		28, 23, 2		# reduction
+
+	vxor		29, 29, 29
+
+	vxor		24, 24, 27		# M
+	vsldoi		26, 24, 29, 8		# mL
+	vsldoi		29, 29, 24, 8		# mH
+	vxor		23, 23, 26		# mL + L
+
+	vsldoi		23, 23, 23, 8		# swap
+	vxor		23, 23, 28
+
+	vpmsumd		24, 14, 15		# H4.H * X.H
+	vpmsumd		25, 11, 16
+	vpmsumd		26, 8, 17
+	vpmsumd		27, 5, 18
+
+	vxor		24, 24, 25
+	vxor		24, 24, 26
+	vxor		24, 24, 27		# H
+
+	vxor		24, 24, 29		# H + mH
+
+	# sum hash and reduction with H Poly
+	vsldoi		27, 23, 23, 8		# swap
+	vpmsumd		23, 23, 2
+	vxor		27, 27, 24
+	vxor		27, 23, 27		# 1st Xi
+
+	# 2nd 4x hash
+	vpmsumd		24, 9, 20
+	vpmsumd		25, 6, 21
+	vpmsumd		26, 3, 22
+	vxor		19, 19, 27		# Xi + X
+	vpmsumd		23, 12, 19		# H4.L * X.L
+
+	vxor		23, 23, 24
+	vxor		23, 23, 25
+	vxor		23, 23, 26		# L
+
+	vpmsumd		24, 13, 19		# H4.L * X.H + H4.H * X.L
+	vpmsumd		25, 10, 20		# H3.L * X1.H + H3.H * X1.L
+	vpmsumd		26, 7, 21
+	vpmsumd		27, 4, 22
+
+	vxor		24, 24, 25
+	vxor		24, 24, 26
+
+	# sum hash and reduction with H Poly
+	vpmsumd		28, 23, 2		# reduction
+
+	vxor		29, 29, 29
+
+	vxor		24, 24, 27		# M
+	vsldoi		26, 24, 29, 8		# mL
+	vsldoi		29, 29, 24, 8		# mH
+	vxor		23, 23, 26		# mL + L
+
+	vsldoi		23, 23, 23, 8		# swap
+	vxor		23, 23, 28
+
+	vpmsumd		24, 14, 19		# H4.H * X.H
+	vpmsumd		25, 11, 20
+	vpmsumd		26, 8, 21
+	vpmsumd		27, 5, 22
+
+	vxor		24, 24, 25
+	vxor		24, 24, 26
+	vxor		24, 24, 27		# H
+
+	vxor		24, 24, 29		# H + mH
+
+	# sum hash and reduction with H Poly
+	vsldoi		27, 23, 23, 8		# swap
+	vpmsumd		23, 23, 2
+	vxor		27, 27, 24
+	vxor		23, 23, 27
+
+	xxlor		32, 23+32, 23+32		# update hash
+
+.endm
+
+ #
+ # Compute update single hash
+ #
+.macro ppc_update_hash_1x
+	vxor		28, 28, 0
+
+	vxor		19, 19, 19
+
+	vpmsumd		22, 3, 28		# L
+	vpmsumd		23, 4, 28		# M
+	vpmsumd		24, 5, 28		# H
+
+	vpmsumd		27, 22, 2		# reduction
+
+	vsldoi		25, 23, 19, 8		# mL
+	vsldoi		26, 19, 23, 8		# mH
+	vxor		22, 22, 25		# LL + LL
+	vxor		24, 24, 26		# HH + HH
+
+	vsldoi		22, 22, 22, 8		# swap
+	vxor		22, 22, 27
+
+	vsldoi		20, 22, 22, 8		# swap
+	vpmsumd		22, 22, 2		# reduction
+	vxor		20, 20, 24
+	vxor		22, 22, 20
+
+	vmr		0, 22			# update hash
+
+.endm
+
+.macro SAVE_REGS
+	stdu 1,-640(1)
+	mflr 0
+
+	std	14,112(1)
+	std	15,120(1)
+	std	16,128(1)
+	std	17,136(1)
+	std	18,144(1)
+	std	19,152(1)
+	std	20,160(1)
+	std	21,168(1)
+	li	9, 256
+	stvx	20, 9, 1
+	addi	9, 9, 16
+	stvx	21, 9, 1
+	addi	9, 9, 16
+	stvx	22, 9, 1
+	addi	9, 9, 16
+	stvx	23, 9, 1
+	addi	9, 9, 16
+	stvx	24, 9, 1
+	addi	9, 9, 16
+	stvx	25, 9, 1
+	addi	9, 9, 16
+	stvx	26, 9, 1
+	addi	9, 9, 16
+	stvx	27, 9, 1
+	addi	9, 9, 16
+	stvx	28, 9, 1
+	addi	9, 9, 16
+	stvx	29, 9, 1
+	addi	9, 9, 16
+	stvx	30, 9, 1
+	addi	9, 9, 16
+	stvx	31, 9, 1
+	stxv	14, 464(1)
+	stxv	15, 480(1)
+	stxv	16, 496(1)
+	stxv	17, 512(1)
+	stxv	18, 528(1)
+	stxv	19, 544(1)
+	stxv	20, 560(1)
+	stxv	21, 576(1)
+	stxv	22, 592(1)
+	std	0, 656(1)
+.endm
+
+.macro RESTORE_REGS
+	lxv	14, 464(1)
+	lxv	15, 480(1)
+	lxv	16, 496(1)
+	lxv	17, 512(1)
+	lxv	18, 528(1)
+	lxv	19, 544(1)
+	lxv	20, 560(1)
+	lxv	21, 576(1)
+	lxv	22, 592(1)
+	li	9, 256
+	lvx	20, 9, 1
+	addi	9, 9, 16
+	lvx	21, 9, 1
+	addi	9, 9, 16
+	lvx	22, 9, 1
+	addi	9, 9, 16
+	lvx	23, 9, 1
+	addi	9, 9, 16
+	lvx	24, 9, 1
+	addi	9, 9, 16
+	lvx	25, 9, 1
+	addi	9, 9, 16
+	lvx	26, 9, 1
+	addi	9, 9, 16
+	lvx	27, 9, 1
+	addi	9, 9, 16
+	lvx	28, 9, 1
+	addi	9, 9, 16
+	lvx	29, 9, 1
+	addi	9, 9, 16
+	lvx	30, 9, 1
+	addi	9, 9, 16
+	lvx	31, 9, 1
+
+	ld	0, 656(1)
+	ld      14,112(1)
+	ld      15,120(1)
+	ld      16,128(1)
+	ld      17,136(1)
+	ld      18,144(1)
+	ld      19,152(1)
+	ld      20,160(1)
+	ld	21,168(1)
+
+	mtlr	0
+	addi	1, 1, 640
+.endm
+
+.macro LOAD_HASH_TABLE
+	# Load Xi
+	lxvb16x	32, 0, 8	# load Xi
+
+	# load Hash - h^4, h^3, h^2, h
+	li	10, 32
+	lxvd2x	2+32, 10, 8	# H Poli
+	li	10, 48
+	lxvd2x	3+32, 10, 8	# Hl
+	li	10, 64
+	lxvd2x	4+32, 10, 8	# H
+	li	10, 80
+	lxvd2x	5+32, 10, 8	# Hh
+
+	li	10, 96
+	lxvd2x	6+32, 10, 8	# H^2l
+	li	10, 112
+	lxvd2x	7+32, 10, 8	# H^2
+	li	10, 128
+	lxvd2x	8+32, 10, 8	# H^2h
+
+	li	10, 144
+	lxvd2x	9+32, 10, 8	# H^3l
+	li	10, 160
+	lxvd2x	10+32, 10, 8	# H^3
+	li	10, 176
+	lxvd2x	11+32, 10, 8	# H^3h
+
+	li	10, 192
+	lxvd2x	12+32, 10, 8	# H^4l
+	li	10, 208
+	lxvd2x	13+32, 10, 8	# H^4
+	li	10, 224
+	lxvd2x	14+32, 10, 8	# H^4h
+.endm
+
+ #
+ # aes_p10_gcm_encrypt (const void *inp, void *out, size_t len,
+ #               const char *rk, unsigned char iv[16], void *Xip);
+ #
+ #    r3 - inp
+ #    r4 - out
+ #    r5 - len
+ #    r6 - AES round keys
+ #    r7 - iv and other data
+ #    r8 - Xi, HPoli, hash keys
+ #
+ #    rounds is at offset 240 in rk
+ #    Xi is at 0 in gcm_table (Xip).
+ #
+_GLOBAL(aes_p10_gcm_encrypt)
+.align 5
+
+	SAVE_REGS
+
+	LOAD_HASH_TABLE
+
+	# initialize ICB: GHASH( IV ), IV - r7
+	lxvb16x	30+32, 0, 7	# load IV  - v30
+
+	mr	12, 5		# length
+	li	11, 0		# block index
+
+	# counter 1
+	vxor	31, 31, 31
+	vspltisb 22, 1
+	vsldoi	31, 31, 22,1	# counter 1
+
+	# load round key to VSR
+	lxv	0, 0(6)
+	lxv	1, 0x10(6)
+	lxv	2, 0x20(6)
+	lxv	3, 0x30(6)
+	lxv	4, 0x40(6)
+	lxv	5, 0x50(6)
+	lxv	6, 0x60(6)
+	lxv	7, 0x70(6)
+	lxv	8, 0x80(6)
+	lxv	9, 0x90(6)
+	lxv	10, 0xa0(6)
+
+	# load rounds - 10 (128), 12 (192), 14 (256)
+	lwz	9,240(6)
+
+	#
+	# vxor	state, state, w # addroundkey
+	xxlor	32+29, 0, 0
+	vxor	15, 30, 29	# IV + round key - add round key 0
+
+	cmpdi	9, 10
+	beq	Loop_aes_gcm_8x
+
+	# load 2 more round keys (v11, v12)
+	lxv	11, 0xb0(6)
+	lxv	12, 0xc0(6)
+
+	cmpdi	9, 12
+	beq	Loop_aes_gcm_8x
+
+	# load 2 more round keys (v11, v12, v13, v14)
+	lxv	13, 0xd0(6)
+	lxv	14, 0xe0(6)
+	cmpdi	9, 14
+	beq	Loop_aes_gcm_8x
+
+	b	aes_gcm_out
+
+.align 5
+Loop_aes_gcm_8x:
+	mr	14, 3
+	mr	9, 4
+
+	#
+	# check partial block
+	#
+Continue_partial_check:
+	ld	15, 56(7)
+	cmpdi	15, 0
+	beq	Continue
+	bgt	Final_block
+	cmpdi	15, 16
+	blt	Final_block
+
+Continue:
+	# n blcoks
+	li	10, 128
+	divdu	10, 12, 10	# n 128 bytes-blocks
+	cmpdi	10, 0
+	beq	Loop_last_block
+
+	vaddudm	30, 30, 31	# IV + counter
+	vxor	16, 30, 29
+	vaddudm	30, 30, 31
+	vxor	17, 30, 29
+	vaddudm	30, 30, 31
+	vxor	18, 30, 29
+	vaddudm	30, 30, 31
+	vxor	19, 30, 29
+	vaddudm	30, 30, 31
+	vxor	20, 30, 29
+	vaddudm	30, 30, 31
+	vxor	21, 30, 29
+	vaddudm	30, 30, 31
+	vxor	22, 30, 29
+
+	mtctr	10
+
+	li	15, 16
+	li	16, 32
+	li	17, 48
+	li	18, 64
+	li	19, 80
+	li	20, 96
+	li	21, 112
+
+	lwz	10, 240(6)
+
+Loop_8x_block:
+
+	lxvb16x		15, 0, 14	# load block
+	lxvb16x		16, 15, 14	# load block
+	lxvb16x		17, 16, 14	# load block
+	lxvb16x		18, 17, 14	# load block
+	lxvb16x		19, 18, 14	# load block
+	lxvb16x		20, 19, 14	# load block
+	lxvb16x		21, 20, 14	# load block
+	lxvb16x		22, 21, 14	# load block
+	addi		14, 14, 128
+
+	Loop_aes_middle8x
+
+	xxlor	23+32, 10, 10
+
+	cmpdi	10, 10
+	beq	Do_next_ghash
+
+	# 192 bits
+	xxlor	24+32, 11, 11
+
+	vcipher	15, 15, 23
+	vcipher	16, 16, 23
+	vcipher	17, 17, 23
+	vcipher	18, 18, 23
+	vcipher	19, 19, 23
+	vcipher	20, 20, 23
+	vcipher	21, 21, 23
+	vcipher	22, 22, 23
+
+	vcipher	15, 15, 24
+	vcipher	16, 16, 24
+	vcipher	17, 17, 24
+	vcipher	18, 18, 24
+	vcipher	19, 19, 24
+	vcipher	20, 20, 24
+	vcipher	21, 21, 24
+	vcipher	22, 22, 24
+
+	xxlor	23+32, 12, 12
+
+	cmpdi	10, 12
+	beq	Do_next_ghash
+
+	# 256 bits
+	xxlor	24+32, 13, 13
+
+	vcipher	15, 15, 23
+	vcipher	16, 16, 23
+	vcipher	17, 17, 23
+	vcipher	18, 18, 23
+	vcipher	19, 19, 23
+	vcipher	20, 20, 23
+	vcipher	21, 21, 23
+	vcipher	22, 22, 23
+
+	vcipher	15, 15, 24
+	vcipher	16, 16, 24
+	vcipher	17, 17, 24
+	vcipher	18, 18, 24
+	vcipher	19, 19, 24
+	vcipher	20, 20, 24
+	vcipher	21, 21, 24
+	vcipher	22, 22, 24
+
+	xxlor	23+32, 14, 14
+
+	cmpdi	10, 14
+	beq	Do_next_ghash
+	b	aes_gcm_out
+
+Do_next_ghash:
+
+	#
+	# last round
+	vcipherlast     15, 15, 23
+	vcipherlast     16, 16, 23
+
+	xxlxor		47, 47, 15
+	stxvb16x        47, 0, 9	# store output
+	xxlxor		48, 48, 16
+	stxvb16x        48, 15, 9	# store output
+
+	vcipherlast     17, 17, 23
+	vcipherlast     18, 18, 23
+
+	xxlxor		49, 49, 17
+	stxvb16x        49, 16, 9	# store output
+	xxlxor		50, 50, 18
+	stxvb16x        50, 17, 9	# store output
+
+	vcipherlast     19, 19, 23
+	vcipherlast     20, 20, 23
+
+	xxlxor		51, 51, 19
+	stxvb16x        51, 18, 9	# store output
+	xxlxor		52, 52, 20
+	stxvb16x        52, 19, 9	# store output
+
+	vcipherlast     21, 21, 23
+	vcipherlast     22, 22, 23
+
+	xxlxor		53, 53, 21
+	stxvb16x        53, 20, 9	# store output
+	xxlxor		54, 54, 22
+	stxvb16x        54, 21, 9	# store output
+
+	addi		9, 9, 128
+
+	# ghash here
+	ppc_aes_gcm_ghash2_4x
+
+	xxlor	27+32, 0, 0
+	vaddudm 30, 30, 31		# IV + counter
+	vmr	29, 30
+	vxor    15, 30, 27		# add round key
+	vaddudm 30, 30, 31
+	vxor    16, 30, 27
+	vaddudm 30, 30, 31
+	vxor    17, 30, 27
+	vaddudm 30, 30, 31
+	vxor    18, 30, 27
+	vaddudm 30, 30, 31
+	vxor    19, 30, 27
+	vaddudm 30, 30, 31
+	vxor    20, 30, 27
+	vaddudm 30, 30, 31
+	vxor    21, 30, 27
+	vaddudm 30, 30, 31
+	vxor    22, 30, 27
+
+	addi    12, 12, -128
+	addi    11, 11, 128
+
+	bdnz	Loop_8x_block
+
+	vmr	30, 29
+	stxvb16x 30+32, 0, 7		# update IV
+
+Loop_last_block:
+	cmpdi   12, 0
+	beq     aes_gcm_out
+
+	# loop last few blocks
+	li      10, 16
+	divdu   10, 12, 10
+
+	mtctr   10
+
+	lwz	10, 240(6)
+
+	cmpdi   12, 16
+	blt     Final_block
+
+Next_rem_block:
+	lxvb16x 15, 0, 14		# load block
+
+	Loop_aes_middle_1x
+
+	xxlor	23+32, 10, 10
+
+	cmpdi	10, 10
+	beq	Do_next_1x
+
+	# 192 bits
+	xxlor	24+32, 11, 11
+
+	vcipher	15, 15, 23
+	vcipher	15, 15, 24
+
+	xxlor	23+32, 12, 12
+
+	cmpdi	10, 12
+	beq	Do_next_1x
+
+	# 256 bits
+	xxlor	24+32, 13, 13
+
+	vcipher	15, 15, 23
+	vcipher	15, 15, 24
+
+	xxlor	23+32, 14, 14
+
+	cmpdi	10, 14
+	beq	Do_next_1x
+
+Do_next_1x:
+	vcipherlast     15, 15, 23
+
+	xxlxor		47, 47, 15
+	stxvb16x	47, 0, 9	# store output
+	addi		14, 14, 16
+	addi		9, 9, 16
+
+	vmr		28, 15
+	ppc_update_hash_1x
+
+	addi		12, 12, -16
+	addi		11, 11, 16
+	xxlor		19+32, 0, 0
+	vaddudm		30, 30, 31		# IV + counter
+	vxor		15, 30, 19		# add round key
+
+	bdnz	Next_rem_block
+
+	li	15, 0
+	std	15, 56(7)		# clear partial?
+	stxvb16x 30+32, 0, 7		# update IV
+	cmpdi	12, 0
+	beq	aes_gcm_out
+
+Final_block:
+	lwz	10, 240(6)
+	Loop_aes_middle_1x
+
+	xxlor	23+32, 10, 10
+
+	cmpdi	10, 10
+	beq	Do_final_1x
+
+	# 192 bits
+	xxlor	24+32, 11, 11
+
+	vcipher	15, 15, 23
+	vcipher	15, 15, 24
+
+	xxlor	23+32, 12, 12
+
+	cmpdi	10, 12
+	beq	Do_final_1x
+
+	# 256 bits
+	xxlor	24+32, 13, 13
+
+	vcipher	15, 15, 23
+	vcipher	15, 15, 24
+
+	xxlor	23+32, 14, 14
+
+	cmpdi	10, 14
+	beq	Do_final_1x
+
+Do_final_1x:
+	vcipherlast     15, 15, 23
+
+	# check partial block
+	li	21, 0			# encrypt
+	ld	15, 56(7)		# partial?
+	cmpdi	15, 0
+	beq	Normal_block
+	bl	Do_partial_block
+
+	cmpdi	12, 0
+	ble aes_gcm_out
+
+	b Continue_partial_check
+
+Normal_block:
+	lxvb16x	15, 0, 14		# load last block
+	xxlxor	47, 47, 15
+
+	# create partial block mask
+	li	15, 16
+	sub	15, 15, 12		# index to the mask
+
+	vspltisb	16, -1		# first 16 bytes - 0xffff...ff
+	vspltisb	17, 0		# second 16 bytes - 0x0000...00
+	li	10, 192
+	stvx	16, 10, 1
+	addi	10, 10, 16
+	stvx	17, 10, 1
+
+	addi	10, 1, 192
+	lxvb16x	16, 15, 10		# load partial block mask
+	xxland	47, 47, 16
+
+	vmr	28, 15
+	ppc_update_hash_1x
+
+	# * should store only the remaining bytes.
+	bl	Write_partial_block
+
+	stxvb16x 30+32, 0, 7		# update IV
+	std	12, 56(7)		# update partial?
+	li	16, 16
+
+	stxvb16x	32, 0, 8		# write out Xi
+	stxvb16x	32, 16, 8		# write out Xi
+	b aes_gcm_out
+
+ #
+ # Compute data mask
+ #
+.macro GEN_MASK _mask _start _end
+	vspltisb	16, -1		# first 16 bytes - 0xffff...ff
+	vspltisb	17, 0		# second 16 bytes - 0x0000...00
+	li	10, 192
+	stxvb16x	17+32, 10, 1
+	add	10, 10, \_start
+	stxvb16x	16+32, 10, 1
+	add	10, 10, \_end
+	stxvb16x	17+32, 10, 1
+
+	addi	10, 1, 192
+	lxvb16x	\_mask, 0, 10		# load partial block mask
+.endm
+
+ #
+ # Handle multiple partial blocks for encrypt and decrypt
+ #   operations.
+ #
+SYM_FUNC_START_LOCAL(Do_partial_block)
+	add	17, 15, 5
+	cmpdi	17, 16
+	bgt	Big_block
+	GEN_MASK 18, 15, 5
+	b	_Partial
+SYM_FUNC_END(Do_partial_block)
+Big_block:
+	li	16, 16
+	GEN_MASK 18, 15, 16
+
+_Partial:
+	lxvb16x	17+32, 0, 14		# load last block
+	sldi	16, 15, 3
+	mtvsrdd	32+16, 0, 16
+	vsro	17, 17, 16
+	xxlxor	47, 47, 17+32
+	xxland	47, 47, 18
+
+	vxor	0, 0, 0			# clear Xi
+	vmr	28, 15
+
+	cmpdi	21, 0			# encrypt/decrypt ops?
+	beq	Skip_decrypt
+	xxland	32+28, 32+17, 18
+
+Skip_decrypt:
+
+	ppc_update_hash_1x
+
+	li	16, 16
+	lxvb16x 32+29, 16, 8
+	vxor	0, 0, 29
+	stxvb16x 32, 0, 8		# save Xi
+	stxvb16x 32, 16, 8		# save Xi
+
+	# store partial block
+	# loop the rest of the stream if any
+	sldi	16, 15, 3
+	mtvsrdd	32+16, 0, 16
+	vslo	15, 15, 16
+	#stxvb16x 15+32, 0, 9		# last block
+
+	li	16, 16
+	sub	17, 16, 15		# 16 - partial
+
+	add	16, 15, 5
+	cmpdi	16, 16
+	bgt	Larger_16
+	mr	17, 5
+Larger_16:
+
+	# write partial
+	li		10, 192
+	stxvb16x	15+32, 10, 1	# save current block
+
+	addi		10, 9, -1
+	addi		16, 1, 191
+	mtctr		17		# move partial byte count
+
+Write_last_partial:
+        lbzu		18, 1(16)
+	stbu		18, 1(10)
+        bdnz		Write_last_partial
+	# Complete loop partial
+
+	add	14, 14, 17
+	add	9, 9, 17
+	sub	12, 12, 17
+	add	11, 11, 17
+
+	add	15, 15, 5
+	cmpdi	15, 16
+	blt	Save_partial
+
+	vaddudm	30, 30, 31
+	stxvb16x 30+32, 0, 7		# update IV
+	xxlor	32+29, 0, 0
+	vxor	15, 30, 29		# IV + round key - add round key 0
+	li	15, 0
+	std	15, 56(7)		# partial done - clear
+	b	Partial_done
+Save_partial:
+	std	15, 56(7)		# partial
+
+Partial_done:
+	blr
+
+ #
+ # Write partial block
+ # r9 - output
+ # r12 - remaining bytes
+ # v15 - partial input data
+ #
+SYM_FUNC_START_LOCAL(Write_partial_block)
+	li		10, 192
+	stxvb16x	15+32, 10, 1		# last block
+
+	addi		10, 9, -1
+	addi		16, 1, 191
+
+        mtctr		12			# remaining bytes
+	li		15, 0
+
+Write_last_byte:
+        lbzu		14, 1(16)
+	stbu		14, 1(10)
+        bdnz		Write_last_byte
+	blr
+SYM_FUNC_END(Write_partial_block)
+
+aes_gcm_out:
+	# out = state
+	stxvb16x	32, 0, 8		# write out Xi
+	add	3, 11, 12		# return count
+
+	RESTORE_REGS
+	blr
+
+ #
+ # 8x Decrypt
+ #
+_GLOBAL(aes_p10_gcm_decrypt)
+.align 5
+
+	SAVE_REGS
+
+	LOAD_HASH_TABLE
+
+	# initialize ICB: GHASH( IV ), IV - r7
+	lxvb16x	30+32, 0, 7	# load IV  - v30
+
+	mr	12, 5		# length
+	li	11, 0		# block index
+
+	# counter 1
+	vxor	31, 31, 31
+	vspltisb 22, 1
+	vsldoi	31, 31, 22,1	# counter 1
+
+	# load round key to VSR
+	lxv	0, 0(6)
+	lxv	1, 0x10(6)
+	lxv	2, 0x20(6)
+	lxv	3, 0x30(6)
+	lxv	4, 0x40(6)
+	lxv	5, 0x50(6)
+	lxv	6, 0x60(6)
+	lxv	7, 0x70(6)
+	lxv	8, 0x80(6)
+	lxv	9, 0x90(6)
+	lxv	10, 0xa0(6)
+
+	# load rounds - 10 (128), 12 (192), 14 (256)
+	lwz	9,240(6)
+
+	#
+	# vxor	state, state, w # addroundkey
+	xxlor	32+29, 0, 0
+	vxor	15, 30, 29	# IV + round key - add round key 0
+
+	cmpdi	9, 10
+	beq	Loop_aes_gcm_8x_dec
+
+	# load 2 more round keys (v11, v12)
+	lxv	11, 0xb0(6)
+	lxv	12, 0xc0(6)
+
+	cmpdi	9, 12
+	beq	Loop_aes_gcm_8x_dec
+
+	# load 2 more round keys (v11, v12, v13, v14)
+	lxv	13, 0xd0(6)
+	lxv	14, 0xe0(6)
+	cmpdi	9, 14
+	beq	Loop_aes_gcm_8x_dec
+
+	b	aes_gcm_out
+
+.align 5
+Loop_aes_gcm_8x_dec:
+	mr	14, 3
+	mr	9, 4
+
+	#
+	# check partial block
+	#
+Continue_partial_check_dec:
+	ld	15, 56(7)
+	cmpdi	15, 0
+	beq	Continue_dec
+	bgt	Final_block_dec
+	cmpdi	15, 16
+	blt	Final_block_dec
+
+Continue_dec:
+	# n blcoks
+	li	10, 128
+	divdu	10, 12, 10	# n 128 bytes-blocks
+	cmpdi	10, 0
+	beq	Loop_last_block_dec
+
+	vaddudm	30, 30, 31	# IV + counter
+	vxor	16, 30, 29
+	vaddudm	30, 30, 31
+	vxor	17, 30, 29
+	vaddudm	30, 30, 31
+	vxor	18, 30, 29
+	vaddudm	30, 30, 31
+	vxor	19, 30, 29
+	vaddudm	30, 30, 31
+	vxor	20, 30, 29
+	vaddudm	30, 30, 31
+	vxor	21, 30, 29
+	vaddudm	30, 30, 31
+	vxor	22, 30, 29
+
+	mtctr	10
+
+	li	15, 16
+	li	16, 32
+	li	17, 48
+	li	18, 64
+	li	19, 80
+	li	20, 96
+	li	21, 112
+
+	lwz	10, 240(6)
+
+Loop_8x_block_dec:
+
+	lxvb16x		15, 0, 14	# load block
+	lxvb16x		16, 15, 14	# load block
+	lxvb16x		17, 16, 14	# load block
+	lxvb16x		18, 17, 14	# load block
+	lxvb16x		19, 18, 14	# load block
+	lxvb16x		20, 19, 14	# load block
+	lxvb16x		21, 20, 14	# load block
+	lxvb16x		22, 21, 14	# load block
+	addi		14, 14, 128
+
+	Loop_aes_middle8x
+
+	xxlor	23+32, 10, 10
+
+	cmpdi	10, 10
+	beq	Do_next_ghash_dec
+
+	# 192 bits
+	xxlor	24+32, 11, 11
+
+	vcipher	15, 15, 23
+	vcipher	16, 16, 23
+	vcipher	17, 17, 23
+	vcipher	18, 18, 23
+	vcipher	19, 19, 23
+	vcipher	20, 20, 23
+	vcipher	21, 21, 23
+	vcipher	22, 22, 23
+
+	vcipher	15, 15, 24
+	vcipher	16, 16, 24
+	vcipher	17, 17, 24
+	vcipher	18, 18, 24
+	vcipher	19, 19, 24
+	vcipher	20, 20, 24
+	vcipher	21, 21, 24
+	vcipher	22, 22, 24
+
+	xxlor	23+32, 12, 12
+
+	cmpdi	10, 12
+	beq	Do_next_ghash_dec
+
+	# 256 bits
+	xxlor	24+32, 13, 13
+
+	vcipher	15, 15, 23
+	vcipher	16, 16, 23
+	vcipher	17, 17, 23
+	vcipher	18, 18, 23
+	vcipher	19, 19, 23
+	vcipher	20, 20, 23
+	vcipher	21, 21, 23
+	vcipher	22, 22, 23
+
+	vcipher	15, 15, 24
+	vcipher	16, 16, 24
+	vcipher	17, 17, 24
+	vcipher	18, 18, 24
+	vcipher	19, 19, 24
+	vcipher	20, 20, 24
+	vcipher	21, 21, 24
+	vcipher	22, 22, 24
+
+	xxlor	23+32, 14, 14
+
+	cmpdi	10, 14
+	beq	Do_next_ghash_dec
+	b	aes_gcm_out
+
+Do_next_ghash_dec:
+
+	#
+	# last round
+	vcipherlast     15, 15, 23
+	vcipherlast     16, 16, 23
+
+	xxlxor		47, 47, 15
+	stxvb16x        47, 0, 9	# store output
+	xxlxor		48, 48, 16
+	stxvb16x        48, 15, 9	# store output
+
+	vcipherlast     17, 17, 23
+	vcipherlast     18, 18, 23
+
+	xxlxor		49, 49, 17
+	stxvb16x        49, 16, 9	# store output
+	xxlxor		50, 50, 18
+	stxvb16x        50, 17, 9	# store output
+
+	vcipherlast     19, 19, 23
+	vcipherlast     20, 20, 23
+
+	xxlxor		51, 51, 19
+	stxvb16x        51, 18, 9	# store output
+	xxlxor		52, 52, 20
+	stxvb16x        52, 19, 9	# store output
+
+	vcipherlast     21, 21, 23
+	vcipherlast     22, 22, 23
+
+	xxlxor		53, 53, 21
+	stxvb16x        53, 20, 9	# store output
+	xxlxor		54, 54, 22
+	stxvb16x        54, 21, 9	# store output
+
+	addi		9, 9, 128
+
+	xxlor           15+32, 15, 15
+	xxlor           16+32, 16, 16
+	xxlor           17+32, 17, 17
+	xxlor           18+32, 18, 18
+	xxlor           19+32, 19, 19
+	xxlor           20+32, 20, 20
+	xxlor           21+32, 21, 21
+	xxlor           22+32, 22, 22
+
+	# ghash here
+	ppc_aes_gcm_ghash2_4x
+
+	xxlor	27+32, 0, 0
+	vaddudm 30, 30, 31		# IV + counter
+	vmr	29, 30
+	vxor    15, 30, 27		# add round key
+	vaddudm 30, 30, 31
+	vxor    16, 30, 27
+	vaddudm 30, 30, 31
+	vxor    17, 30, 27
+	vaddudm 30, 30, 31
+	vxor    18, 30, 27
+	vaddudm 30, 30, 31
+	vxor    19, 30, 27
+	vaddudm 30, 30, 31
+	vxor    20, 30, 27
+	vaddudm 30, 30, 31
+	vxor    21, 30, 27
+	vaddudm 30, 30, 31
+	vxor    22, 30, 27
+
+	addi    12, 12, -128
+	addi    11, 11, 128
+
+	bdnz	Loop_8x_block_dec
+
+	vmr	30, 29
+	stxvb16x 30+32, 0, 7		# update IV
+
+Loop_last_block_dec:
+	cmpdi   12, 0
+	beq     aes_gcm_out
+
+	# loop last few blocks
+	li      10, 16
+	divdu   10, 12, 10
+
+	mtctr   10
+
+	lwz	10, 240(6)
+
+	cmpdi   12, 16
+	blt     Final_block_dec
+
+Next_rem_block_dec:
+	lxvb16x 15, 0, 14		# load block
+
+	Loop_aes_middle_1x
+
+	xxlor	23+32, 10, 10
+
+	cmpdi	10, 10
+	beq	Do_next_1x_dec
+
+	# 192 bits
+	xxlor	24+32, 11, 11
+
+	vcipher	15, 15, 23
+	vcipher	15, 15, 24
+
+	xxlor	23+32, 12, 12
+
+	cmpdi	10, 12
+	beq	Do_next_1x_dec
+
+	# 256 bits
+	xxlor	24+32, 13, 13
+
+	vcipher	15, 15, 23
+	vcipher	15, 15, 24
+
+	xxlor	23+32, 14, 14
+
+	cmpdi	10, 14
+	beq	Do_next_1x_dec
+
+Do_next_1x_dec:
+	vcipherlast     15, 15, 23
+
+	xxlxor		47, 47, 15
+	stxvb16x	47, 0, 9	# store output
+	addi		14, 14, 16
+	addi		9, 9, 16
+
+	xxlor           28+32, 15, 15
+	#vmr		28, 15
+	ppc_update_hash_1x
+
+	addi		12, 12, -16
+	addi		11, 11, 16
+	xxlor		19+32, 0, 0
+	vaddudm		30, 30, 31		# IV + counter
+	vxor		15, 30, 19		# add round key
+
+	bdnz	Next_rem_block_dec
+
+	li	15, 0
+	std	15, 56(7)		# clear partial?
+	stxvb16x 30+32, 0, 7		# update IV
+	cmpdi	12, 0
+	beq	aes_gcm_out
+
+Final_block_dec:
+	lwz	10, 240(6)
+	Loop_aes_middle_1x
+
+	xxlor	23+32, 10, 10
+
+	cmpdi	10, 10
+	beq	Do_final_1x_dec
+
+	# 192 bits
+	xxlor	24+32, 11, 11
+
+	vcipher	15, 15, 23
+	vcipher	15, 15, 24
+
+	xxlor	23+32, 12, 12
+
+	cmpdi	10, 12
+	beq	Do_final_1x_dec
+
+	# 256 bits
+	xxlor	24+32, 13, 13
+
+	vcipher	15, 15, 23
+	vcipher	15, 15, 24
+
+	xxlor	23+32, 14, 14
+
+	cmpdi	10, 14
+	beq	Do_final_1x_dec
+
+Do_final_1x_dec:
+	vcipherlast     15, 15, 23
+
+	# check partial block
+	li	21, 1			# decrypt
+	ld	15, 56(7)		# partial?
+	cmpdi	15, 0
+	beq	Normal_block_dec
+	bl	Do_partial_block
+	cmpdi	12, 0
+	ble aes_gcm_out
+
+	b Continue_partial_check_dec
+
+Normal_block_dec:
+	lxvb16x	15, 0, 14		# load last block
+	xxlxor	47, 47, 15
+
+	# create partial block mask
+	li	15, 16
+	sub	15, 15, 12		# index to the mask
+
+	vspltisb	16, -1		# first 16 bytes - 0xffff...ff
+	vspltisb	17, 0		# second 16 bytes - 0x0000...00
+	li	10, 192
+	stvx	16, 10, 1
+	addi	10, 10, 16
+	stvx	17, 10, 1
+
+	addi	10, 1, 192
+	lxvb16x	16, 15, 10		# load partial block mask
+	xxland	47, 47, 16
+
+	xxland	32+28, 15, 16
+	#vmr	28, 15
+	ppc_update_hash_1x
+
+	# * should store only the remaining bytes.
+	bl	Write_partial_block
+
+	stxvb16x 30+32, 0, 7		# update IV
+	std	12, 56(7)		# update partial?
+	li	16, 16
+
+	stxvb16x	32, 0, 8		# write out Xi
+	stxvb16x	32, 16, 8		# write out Xi
+	b aes_gcm_out
diff --git a/arch/powerpc/crypto/aesp8-ppc.pl b/arch/powerpc/crypto/aesp8-ppc.pl
new file mode 100644
index 000000000000..1f22aec27d79
--- /dev/null
+++ b/arch/powerpc/crypto/aesp8-ppc.pl
@@ -0,0 +1,585 @@
+#! /usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from CRYPTOGAMs[1] and is included here using the option
+# in the license to distribute the code under the GPL. Therefore this program
+# is free software; you can redistribute it and/or modify it under the terms of
+# the GNU General Public License version 2 as published by the Free Software
+# Foundation.
+#
+# [1] https://www.openssl.org/~appro/cryptogams/
+
+# Copyright (c) 2006-2017, CRYPTOGAMS by <appro@openssl.org>
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#
+#       * Redistributions of source code must retain copyright notices,
+#         this list of conditions and the following disclaimer.
+#
+#       * Redistributions in binary form must reproduce the above
+#         copyright notice, this list of conditions and the following
+#         disclaimer in the documentation and/or other materials
+#         provided with the distribution.
+#
+#       * Neither the name of the CRYPTOGAMS nor the names of its
+#         copyright holder and contributors may be used to endorse or
+#         promote products derived from this software without specific
+#         prior written permission.
+#
+# ALTERNATIVELY, provided that this notice is retained in full, this
+# product may be distributed under the terms of the GNU General Public
+# License (GPL), in which case the provisions of the GPL apply INSTEAD OF
+# those given above.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see https://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# This module implements support for AES instructions as per PowerISA
+# specification version 2.07, first implemented by POWER8 processor.
+# The module is endian-agnostic in sense that it supports both big-
+# and little-endian cases. Data alignment in parallelizable modes is
+# handled with VSX loads and stores, which implies MSR.VSX flag being
+# set. It should also be noted that ISA specification doesn't prohibit
+# alignment exceptions for these instructions on page boundaries.
+# Initially alignment was handled in pure AltiVec/VMX way [when data
+# is aligned programmatically, which in turn guarantees exception-
+# free execution], but it turned to hamper performance when vcipher
+# instructions are interleaved. It's reckoned that eventual
+# misalignment penalties at page boundaries are in average lower
+# than additional overhead in pure AltiVec approach.
+#
+# May 2016
+#
+# Add XTS subroutine, 9x on little- and 12x improvement on big-endian
+# systems were measured.
+#
+######################################################################
+# Current large-block performance in cycles per byte processed with
+# 128-bit key (less is better).
+#
+#		CBC en-/decrypt	CTR	XTS
+# POWER8[le]	3.96/0.72	0.74	1.1
+# POWER8[be]	3.75/0.65	0.66	1.0
+
+$flavour = shift;
+
+if ($flavour =~ /64/) {
+	$SIZE_T	=8;
+	$LRSAVE	=2*$SIZE_T;
+	$STU	="stdu";
+	$POP	="ld";
+	$PUSH	="std";
+	$UCMP	="cmpld";
+	$SHL	="sldi";
+} elsif ($flavour =~ /32/) {
+	$SIZE_T	=4;
+	$LRSAVE	=$SIZE_T;
+	$STU	="stwu";
+	$POP	="lwz";
+	$PUSH	="stw";
+	$UCMP	="cmplw";
+	$SHL	="slwi";
+} else { die "nonsense $flavour"; }
+
+$LITTLE_ENDIAN = ($flavour=~/le$/) ? $SIZE_T : 0;
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}ppc-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/ppc-xlate.pl" and -f $xlate) or
+die "can't locate ppc-xlate.pl";
+
+open STDOUT,"| $^X $xlate $flavour ".shift || die "can't call $xlate: $!";
+
+$FRAME=8*$SIZE_T;
+$prefix="aes_p8";
+
+$sp="r1";
+$vrsave="r12";
+
+#########################################################################
+{{{	# Key setup procedures						#
+my ($inp,$bits,$out,$ptr,$cnt,$rounds)=map("r$_",(3..8));
+my ($zero,$in0,$in1,$key,$rcon,$mask,$tmp)=map("v$_",(0..6));
+my ($stage,$outperm,$outmask,$outhead,$outtail)=map("v$_",(7..11));
+
+$code.=<<___;
+.machine	"any"
+
+.text
+
+.align	7
+rcon:
+.long	0x01000000, 0x01000000, 0x01000000, 0x01000000	?rev
+.long	0x1b000000, 0x1b000000, 0x1b000000, 0x1b000000	?rev
+.long	0x0d0e0f0c, 0x0d0e0f0c, 0x0d0e0f0c, 0x0d0e0f0c	?rev
+.long	0,0,0,0						?asis
+Lconsts:
+	mflr	r0
+	bcl	20,31,\$+4
+	mflr	$ptr	 #vvvvv "distance between . and rcon
+	addi	$ptr,$ptr,-0x48
+	mtlr	r0
+	blr
+	.long	0
+	.byte	0,12,0x14,0,0,0,0,0
+.asciz	"AES for PowerISA 2.07, CRYPTOGAMS by <appro\@openssl.org>"
+
+.globl	.${prefix}_set_encrypt_key
+Lset_encrypt_key:
+	mflr		r11
+	$PUSH		r11,$LRSAVE($sp)
+
+	li		$ptr,-1
+	${UCMP}i	$inp,0
+	beq-		Lenc_key_abort		# if ($inp==0) return -1;
+	${UCMP}i	$out,0
+	beq-		Lenc_key_abort		# if ($out==0) return -1;
+	li		$ptr,-2
+	cmpwi		$bits,128
+	blt-		Lenc_key_abort
+	cmpwi		$bits,256
+	bgt-		Lenc_key_abort
+	andi.		r0,$bits,0x3f
+	bne-		Lenc_key_abort
+
+	lis		r0,0xfff0
+	mfspr		$vrsave,256
+	mtspr		256,r0
+
+	bl		Lconsts
+	mtlr		r11
+
+	neg		r9,$inp
+	lvx		$in0,0,$inp
+	addi		$inp,$inp,15		# 15 is not typo
+	lvsr		$key,0,r9		# borrow $key
+	li		r8,0x20
+	cmpwi		$bits,192
+	lvx		$in1,0,$inp
+	le?vspltisb	$mask,0x0f		# borrow $mask
+	lvx		$rcon,0,$ptr
+	le?vxor		$key,$key,$mask		# adjust for byte swap
+	lvx		$mask,r8,$ptr
+	addi		$ptr,$ptr,0x10
+	vperm		$in0,$in0,$in1,$key	# align [and byte swap in LE]
+	li		$cnt,8
+	vxor		$zero,$zero,$zero
+	mtctr		$cnt
+
+	?lvsr		$outperm,0,$out
+	vspltisb	$outmask,-1
+	lvx		$outhead,0,$out
+	?vperm		$outmask,$zero,$outmask,$outperm
+
+	blt		Loop128
+	addi		$inp,$inp,8
+	beq		L192
+	addi		$inp,$inp,8
+	b		L256
+
+.align	4
+Loop128:
+	vperm		$key,$in0,$in0,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in0,$in0,$key
+	bdnz		Loop128
+
+	lvx		$rcon,0,$ptr		# last two round keys
+
+	vperm		$key,$in0,$in0,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in0,$in0,$key
+
+	vperm		$key,$in0,$in0,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vxor		$in0,$in0,$key
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+
+	addi		$inp,$out,15		# 15 is not typo
+	addi		$out,$out,0x50
+
+	li		$rounds,10
+	b		Ldone
+
+.align	4
+L192:
+	lvx		$tmp,0,$inp
+	li		$cnt,4
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+	vperm		$in1,$in1,$tmp,$key	# align [and byte swap in LE]
+	vspltisb	$key,8			# borrow $key
+	mtctr		$cnt
+	vsububm		$mask,$mask,$key	# adjust the mask
+
+Loop192:
+	vperm		$key,$in1,$in1,$mask	# roate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	vcipherlast	$key,$key,$rcon
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+
+	 vsldoi		$stage,$zero,$in1,8
+	vspltw		$tmp,$in0,3
+	vxor		$tmp,$tmp,$in1
+	vsldoi		$in1,$zero,$in1,12	# >>32
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in1,$in1,$tmp
+	vxor		$in0,$in0,$key
+	vxor		$in1,$in1,$key
+	 vsldoi		$stage,$stage,$in0,8
+
+	vperm		$key,$in1,$in1,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$stage,$stage,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	 vsldoi		$stage,$in0,$in1,8
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	 vperm		$outtail,$stage,$stage,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vspltw		$tmp,$in0,3
+	vxor		$tmp,$tmp,$in1
+	vsldoi		$in1,$zero,$in1,12	# >>32
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in1,$in1,$tmp
+	vxor		$in0,$in0,$key
+	vxor		$in1,$in1,$key
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+	 addi		$inp,$out,15		# 15 is not typo
+	 addi		$out,$out,16
+	bdnz		Loop192
+
+	li		$rounds,12
+	addi		$out,$out,0x20
+	b		Ldone
+
+.align	4
+L256:
+	lvx		$tmp,0,$inp
+	li		$cnt,7
+	li		$rounds,14
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+	vperm		$in1,$in1,$tmp,$key	# align [and byte swap in LE]
+	mtctr		$cnt
+
+Loop256:
+	vperm		$key,$in1,$in1,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$in1,$in1,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in0,$in0,$key
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+	 addi		$inp,$out,15		# 15 is not typo
+	 addi		$out,$out,16
+	bdz		Ldone
+
+	vspltw		$key,$in0,3		# just splat
+	vsldoi		$tmp,$zero,$in1,12	# >>32
+	vsbox		$key,$key
+
+	vxor		$in1,$in1,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in1,$in1,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in1,$in1,$tmp
+
+	vxor		$in1,$in1,$key
+	b		Loop256
+
+.align	4
+Ldone:
+	lvx		$in1,0,$inp		# redundant in aligned case
+	vsel		$in1,$outhead,$in1,$outmask
+	stvx		$in1,0,$inp
+	li		$ptr,0
+	mtspr		256,$vrsave
+	stw		$rounds,0($out)
+
+Lenc_key_abort:
+	mr		r3,$ptr
+	blr
+	.long		0
+	.byte		0,12,0x14,1,0,0,3,0
+	.long		0
+.size	.${prefix}_set_encrypt_key,.-.${prefix}_set_encrypt_key
+
+.globl	.${prefix}_set_decrypt_key
+	$STU		$sp,-$FRAME($sp)
+	mflr		r10
+	$PUSH		r10,$FRAME+$LRSAVE($sp)
+	bl		Lset_encrypt_key
+	mtlr		r10
+
+	cmpwi		r3,0
+	bne-		Ldec_key_abort
+
+	slwi		$cnt,$rounds,4
+	subi		$inp,$out,240		# first round key
+	srwi		$rounds,$rounds,1
+	add		$out,$inp,$cnt		# last round key
+	mtctr		$rounds
+
+Ldeckey:
+	lwz		r0, 0($inp)
+	lwz		r6, 4($inp)
+	lwz		r7, 8($inp)
+	lwz		r8, 12($inp)
+	addi		$inp,$inp,16
+	lwz		r9, 0($out)
+	lwz		r10,4($out)
+	lwz		r11,8($out)
+	lwz		r12,12($out)
+	stw		r0, 0($out)
+	stw		r6, 4($out)
+	stw		r7, 8($out)
+	stw		r8, 12($out)
+	subi		$out,$out,16
+	stw		r9, -16($inp)
+	stw		r10,-12($inp)
+	stw		r11,-8($inp)
+	stw		r12,-4($inp)
+	bdnz		Ldeckey
+
+	xor		r3,r3,r3		# return value
+Ldec_key_abort:
+	addi		$sp,$sp,$FRAME
+	blr
+	.long		0
+	.byte		0,12,4,1,0x80,0,3,0
+	.long		0
+.size	.${prefix}_set_decrypt_key,.-.${prefix}_set_decrypt_key
+___
+}}}
+#########################################################################
+{{{	# Single block en- and decrypt procedures			#
+sub gen_block () {
+my $dir = shift;
+my $n   = $dir eq "de" ? "n" : "";
+my ($inp,$out,$key,$rounds,$idx)=map("r$_",(3..7));
+
+$code.=<<___;
+.globl	.${prefix}_${dir}crypt
+	lwz		$rounds,240($key)
+	lis		r0,0xfc00
+	mfspr		$vrsave,256
+	li		$idx,15			# 15 is not typo
+	mtspr		256,r0
+
+	lvx		v0,0,$inp
+	neg		r11,$out
+	lvx		v1,$idx,$inp
+	lvsl		v2,0,$inp		# inpperm
+	le?vspltisb	v4,0x0f
+	?lvsl		v3,0,r11		# outperm
+	le?vxor		v2,v2,v4
+	li		$idx,16
+	vperm		v0,v0,v1,v2		# align [and byte swap in LE]
+	lvx		v1,0,$key
+	?lvsl		v5,0,$key		# keyperm
+	srwi		$rounds,$rounds,1
+	lvx		v2,$idx,$key
+	addi		$idx,$idx,16
+	subi		$rounds,$rounds,1
+	?vperm		v1,v1,v2,v5		# align round key
+
+	vxor		v0,v0,v1
+	lvx		v1,$idx,$key
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+Loop_${dir}c:
+	?vperm		v2,v2,v1,v5
+	v${n}cipher	v0,v0,v2
+	lvx		v2,$idx,$key
+	addi		$idx,$idx,16
+	?vperm		v1,v1,v2,v5
+	v${n}cipher	v0,v0,v1
+	lvx		v1,$idx,$key
+	addi		$idx,$idx,16
+	bdnz		Loop_${dir}c
+
+	?vperm		v2,v2,v1,v5
+	v${n}cipher	v0,v0,v2
+	lvx		v2,$idx,$key
+	?vperm		v1,v1,v2,v5
+	v${n}cipherlast	v0,v0,v1
+
+	vspltisb	v2,-1
+	vxor		v1,v1,v1
+	li		$idx,15			# 15 is not typo
+	?vperm		v2,v1,v2,v3		# outmask
+	le?vxor		v3,v3,v4
+	lvx		v1,0,$out		# outhead
+	vperm		v0,v0,v0,v3		# rotate [and byte swap in LE]
+	vsel		v1,v1,v0,v2
+	lvx		v4,$idx,$out
+	stvx		v1,0,$out
+	vsel		v0,v0,v4,v2
+	stvx		v0,$idx,$out
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,3,0
+	.long		0
+.size	.${prefix}_${dir}crypt,.-.${prefix}_${dir}crypt
+___
+}
+&gen_block("en");
+&gen_block("de");
+}}}
+
+my $consts=1;
+foreach(split("\n",$code)) {
+        s/\`([^\`]*)\`/eval($1)/geo;
+
+	# constants table endian-specific conversion
+	if ($consts && m/\.(long|byte)\s+(.+)\s+(\?[a-z]*)$/o) {
+	    my $conv=$3;
+	    my @bytes=();
+
+	    # convert to endian-agnostic format
+	    if ($1 eq "long") {
+	      foreach (split(/,\s*/,$2)) {
+		my $l = /^0/?oct:int;
+		push @bytes,($l>>24)&0xff,($l>>16)&0xff,($l>>8)&0xff,$l&0xff;
+	      }
+	    } else {
+		@bytes = map(/^0/?oct:int,split(/,\s*/,$2));
+	    }
+
+	    # little-endian conversion
+	    if ($flavour =~ /le$/o) {
+		SWITCH: for($conv)  {
+		    /\?inv/ && do   { @bytes=map($_^0xf,@bytes); last; };
+		    /\?rev/ && do   { @bytes=reverse(@bytes);    last; };
+		}
+	    }
+
+	    #emit
+	    print ".byte\t",join(',',map (sprintf("0x%02x",$_),@bytes)),"\n";
+	    next;
+	}
+	$consts=0 if (m/Lconsts:/o);	# end of table
+
+	# instructions prefixed with '?' are endian-specific and need
+	# to be adjusted accordingly...
+	if ($flavour =~ /le$/o) {	# little-endian
+	    s/le\?//o		or
+	    s/be\?/#be#/o	or
+	    s/\?lvsr/lvsl/o	or
+	    s/\?lvsl/lvsr/o	or
+	    s/\?(vperm\s+v[0-9]+,\s*)(v[0-9]+,\s*)(v[0-9]+,\s*)(v[0-9]+)/$1$3$2$4/o or
+	    s/\?(vsldoi\s+v[0-9]+,\s*)(v[0-9]+,)\s*(v[0-9]+,\s*)([0-9]+)/$1$3$2 16-$4/o or
+	    s/\?(vspltw\s+v[0-9]+,\s*)(v[0-9]+,)\s*([0-9])/$1$2 3-$3/o;
+	} else {			# big-endian
+	    s/le\?/#le#/o	or
+	    s/be\?//o		or
+	    s/\?([a-z]+)/$1/o;
+	}
+
+        print $_,"\n";
+}
+
+close STDOUT;
diff --git a/arch/powerpc/crypto/ghashp8-ppc.pl b/arch/powerpc/crypto/ghashp8-ppc.pl
new file mode 100644
index 000000000000..b56603b4a893
--- /dev/null
+++ b/arch/powerpc/crypto/ghashp8-ppc.pl
@@ -0,0 +1,370 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore this program is free software;
+# you can redistribute it and/or modify it under the terms of the GNU General
+# Public License version 2 as published by the Free Software Foundation.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see https://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# GHASH for PowerISA v2.07.
+#
+# July 2014
+#
+# Accurate performance measurements are problematic, because it's
+# always virtualized setup with possibly throttled processor.
+# Relative comparison is therefore more informative. This initial
+# version is ~2.1x slower than hardware-assisted AES-128-CTR, ~12x
+# faster than "4-bit" integer-only compiler-generated 64-bit code.
+# "Initial version" means that there is room for futher improvement.
+
+$flavour=shift;
+$output =shift;
+
+if ($flavour =~ /64/) {
+	$SIZE_T=8;
+	$LRSAVE=2*$SIZE_T;
+	$STU="stdu";
+	$POP="ld";
+	$PUSH="std";
+} elsif ($flavour =~ /32/) {
+	$SIZE_T=4;
+	$LRSAVE=$SIZE_T;
+	$STU="stwu";
+	$POP="lwz";
+	$PUSH="stw";
+} else { die "nonsense $flavour"; }
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}ppc-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/ppc-xlate.pl" and -f $xlate) or
+die "can't locate ppc-xlate.pl";
+
+open STDOUT,"| $^X $xlate $flavour $output" || die "can't call $xlate: $!";
+
+my ($Xip,$Htbl,$inp,$len)=map("r$_",(3..6));	# argument block
+
+my ($Xl,$Xm,$Xh,$IN)=map("v$_",(0..3));
+my ($zero,$t0,$t1,$t2,$xC2,$H,$Hh,$Hl,$lemask)=map("v$_",(4..12));
+my ($Xl1,$Xm1,$Xh1,$IN1,$H2,$H2h,$H2l)=map("v$_",(13..19));
+my $vrsave="r12";
+my ($t4,$t5,$t6) = ($Hl,$H,$Hh);
+
+$code=<<___;
+.machine	"any"
+
+.text
+
+.globl	.gcm_init_p8
+	lis		r0,0xfff0
+	li		r8,0x10
+	mfspr		$vrsave,256
+	li		r9,0x20
+	mtspr		256,r0
+	li		r10,0x30
+	lvx_u		$H,0,r4			# load H
+	le?xor		r7,r7,r7
+	le?addi		r7,r7,0x8		# need a vperm start with 08
+	le?lvsr		5,0,r7
+	le?vspltisb	6,0x0f
+	le?vxor		5,5,6			# set a b-endian mask
+	le?vperm	$H,$H,$H,5
+
+	vspltisb	$xC2,-16		# 0xf0
+	vspltisb	$t0,1			# one
+	vaddubm		$xC2,$xC2,$xC2		# 0xe0
+	vxor		$zero,$zero,$zero
+	vor		$xC2,$xC2,$t0		# 0xe1
+	vsldoi		$xC2,$xC2,$zero,15	# 0xe1...
+	vsldoi		$t1,$zero,$t0,1		# ...1
+	vaddubm		$xC2,$xC2,$xC2		# 0xc2...
+	vspltisb	$t2,7
+	vor		$xC2,$xC2,$t1		# 0xc2....01
+	vspltb		$t1,$H,0		# most significant byte
+	vsl		$H,$H,$t0		# H<<=1
+	vsrab		$t1,$t1,$t2		# broadcast carry bit
+	vand		$t1,$t1,$xC2
+	vxor		$H,$H,$t1		# twisted H
+
+	vsldoi		$H,$H,$H,8		# twist even more ...
+	vsldoi		$xC2,$zero,$xC2,8	# 0xc2.0
+	vsldoi		$Hl,$zero,$H,8		# ... and split
+	vsldoi		$Hh,$H,$zero,8
+
+	stvx_u		$xC2,0,r3		# save pre-computed table
+	stvx_u		$Hl,r8,r3
+	stvx_u		$H, r9,r3
+	stvx_u		$Hh,r10,r3
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,2,0
+	.long		0
+.size	.gcm_init_p8,.-.gcm_init_p8
+
+.globl	.gcm_init_htable
+	lis		r0,0xfff0
+	li		r8,0x10
+	mfspr		$vrsave,256
+	li		r9,0x20
+	mtspr		256,r0
+	li		r10,0x30
+	lvx_u		$H,0,r4			# load H
+
+	vspltisb	$xC2,-16		# 0xf0
+	vspltisb	$t0,1			# one
+	vaddubm		$xC2,$xC2,$xC2		# 0xe0
+	vxor		$zero,$zero,$zero
+	vor		$xC2,$xC2,$t0		# 0xe1
+	vsldoi		$xC2,$xC2,$zero,15	# 0xe1...
+	vsldoi		$t1,$zero,$t0,1		# ...1
+	vaddubm		$xC2,$xC2,$xC2		# 0xc2...
+	vspltisb	$t2,7
+	vor		$xC2,$xC2,$t1		# 0xc2....01
+	vspltb		$t1,$H,0		# most significant byte
+	vsl		$H,$H,$t0		# H<<=1
+	vsrab		$t1,$t1,$t2		# broadcast carry bit
+	vand		$t1,$t1,$xC2
+	vxor		$IN,$H,$t1		# twisted H
+
+	vsldoi		$H,$IN,$IN,8		# twist even more ...
+	vsldoi		$xC2,$zero,$xC2,8	# 0xc2.0
+	vsldoi		$Hl,$zero,$H,8		# ... and split
+	vsldoi		$Hh,$H,$zero,8
+
+	stvx_u		$xC2,0,r3		# save pre-computed table
+	stvx_u		$Hl,r8,r3
+	li		r8,0x40
+	stvx_u		$H, r9,r3
+	li		r9,0x50
+	stvx_u		$Hh,r10,r3
+	li		r10,0x60
+
+	vpmsumd		$Xl,$IN,$Hl		# H.lo·H.lo
+	vpmsumd		$Xm,$IN,$H		# H.hi·H.lo+H.lo·H.hi
+	vpmsumd		$Xh,$IN,$Hh		# H.hi·H.hi
+
+	vpmsumd		$t2,$Xl,$xC2		# 1st reduction phase
+
+	vsldoi		$t0,$Xm,$zero,8
+	vsldoi		$t1,$zero,$Xm,8
+	vxor		$Xl,$Xl,$t0
+	vxor		$Xh,$Xh,$t1
+
+	vsldoi		$Xl,$Xl,$Xl,8
+	vxor		$Xl,$Xl,$t2
+
+	vsldoi		$t1,$Xl,$Xl,8		# 2nd reduction phase
+	vpmsumd		$Xl,$Xl,$xC2
+	vxor		$t1,$t1,$Xh
+	vxor		$IN1,$Xl,$t1
+
+	vsldoi		$H2,$IN1,$IN1,8
+	vsldoi		$H2l,$zero,$H2,8
+	vsldoi		$H2h,$H2,$zero,8
+
+	stvx_u		$H2l,r8,r3		# save H^2
+	li		r8,0x70
+	stvx_u		$H2,r9,r3
+	li		r9,0x80
+	stvx_u		$H2h,r10,r3
+	li		r10,0x90
+
+	vpmsumd		$Xl,$IN,$H2l		# H.lo·H^2.lo
+	 vpmsumd	$Xl1,$IN1,$H2l		# H^2.lo·H^2.lo
+	vpmsumd		$Xm,$IN,$H2		# H.hi·H^2.lo+H.lo·H^2.hi
+	 vpmsumd	$Xm1,$IN1,$H2		# H^2.hi·H^2.lo+H^2.lo·H^2.hi
+	vpmsumd		$Xh,$IN,$H2h		# H.hi·H^2.hi
+	 vpmsumd	$Xh1,$IN1,$H2h		# H^2.hi·H^2.hi
+
+	vpmsumd		$t2,$Xl,$xC2		# 1st reduction phase
+	 vpmsumd	$t6,$Xl1,$xC2		# 1st reduction phase
+
+	vsldoi		$t0,$Xm,$zero,8
+	vsldoi		$t1,$zero,$Xm,8
+	 vsldoi		$t4,$Xm1,$zero,8
+	 vsldoi		$t5,$zero,$Xm1,8
+	vxor		$Xl,$Xl,$t0
+	vxor		$Xh,$Xh,$t1
+	 vxor		$Xl1,$Xl1,$t4
+	 vxor		$Xh1,$Xh1,$t5
+
+	vsldoi		$Xl,$Xl,$Xl,8
+	 vsldoi		$Xl1,$Xl1,$Xl1,8
+	vxor		$Xl,$Xl,$t2
+	 vxor		$Xl1,$Xl1,$t6
+
+	vsldoi		$t1,$Xl,$Xl,8		# 2nd reduction phase
+	 vsldoi		$t5,$Xl1,$Xl1,8		# 2nd reduction phase
+	vpmsumd		$Xl,$Xl,$xC2
+	 vpmsumd	$Xl1,$Xl1,$xC2
+	vxor		$t1,$t1,$Xh
+	 vxor		$t5,$t5,$Xh1
+	vxor		$Xl,$Xl,$t1
+	 vxor		$Xl1,$Xl1,$t5
+
+	vsldoi		$H,$Xl,$Xl,8
+	 vsldoi		$H2,$Xl1,$Xl1,8
+	vsldoi		$Hl,$zero,$H,8
+	vsldoi		$Hh,$H,$zero,8
+	 vsldoi		$H2l,$zero,$H2,8
+	 vsldoi		$H2h,$H2,$zero,8
+
+	stvx_u		$Hl,r8,r3		# save H^3
+	li		r8,0xa0
+	stvx_u		$H,r9,r3
+	li		r9,0xb0
+	stvx_u		$Hh,r10,r3
+	li		r10,0xc0
+	 stvx_u		$H2l,r8,r3		# save H^4
+	 stvx_u		$H2,r9,r3
+	 stvx_u		$H2h,r10,r3
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,2,0
+	.long		0
+.size	.gcm_init_htable,.-.gcm_init_htable
+
+.globl	.gcm_gmult_p8
+	lis		r0,0xfff8
+	li		r8,0x10
+	mfspr		$vrsave,256
+	li		r9,0x20
+	mtspr		256,r0
+	li		r10,0x30
+	lvx_u		$IN,0,$Xip		# load Xi
+
+	lvx_u		$Hl,r8,$Htbl		# load pre-computed table
+	 le?lvsl	$lemask,r0,r0
+	lvx_u		$H, r9,$Htbl
+	 le?vspltisb	$t0,0x07
+	lvx_u		$Hh,r10,$Htbl
+	 le?vxor	$lemask,$lemask,$t0
+	lvx_u		$xC2,0,$Htbl
+	 le?vperm	$IN,$IN,$IN,$lemask
+	vxor		$zero,$zero,$zero
+
+	vpmsumd		$Xl,$IN,$Hl		# H.lo·Xi.lo
+	vpmsumd		$Xm,$IN,$H		# H.hi·Xi.lo+H.lo·Xi.hi
+	vpmsumd		$Xh,$IN,$Hh		# H.hi·Xi.hi
+
+	vpmsumd		$t2,$Xl,$xC2		# 1st phase
+
+	vsldoi		$t0,$Xm,$zero,8
+	vsldoi		$t1,$zero,$Xm,8
+	vxor		$Xl,$Xl,$t0
+	vxor		$Xh,$Xh,$t1
+
+	vsldoi		$Xl,$Xl,$Xl,8
+	vxor		$Xl,$Xl,$t2
+
+	vsldoi		$t1,$Xl,$Xl,8		# 2nd phase
+	vpmsumd		$Xl,$Xl,$xC2
+	vxor		$t1,$t1,$Xh
+	vxor		$Xl,$Xl,$t1
+
+	le?vperm	$Xl,$Xl,$Xl,$lemask
+	stvx_u		$Xl,0,$Xip		# write out Xi
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,2,0
+	.long		0
+.size	.gcm_gmult_p8,.-.gcm_gmult_p8
+
+.globl	.gcm_ghash_p8
+	lis		r0,0xfff8
+	li		r8,0x10
+	mfspr		$vrsave,256
+	li		r9,0x20
+	mtspr		256,r0
+	li		r10,0x30
+	lvx_u		$Xl,0,$Xip		# load Xi
+
+	lvx_u		$Hl,r8,$Htbl		# load pre-computed table
+	 le?lvsl	$lemask,r0,r0
+	lvx_u		$H, r9,$Htbl
+	 le?vspltisb	$t0,0x07
+	lvx_u		$Hh,r10,$Htbl
+	 le?vxor	$lemask,$lemask,$t0
+	lvx_u		$xC2,0,$Htbl
+	 le?vperm	$Xl,$Xl,$Xl,$lemask
+	vxor		$zero,$zero,$zero
+
+	lvx_u		$IN,0,$inp
+	addi		$inp,$inp,16
+	subi		$len,$len,16
+	 le?vperm	$IN,$IN,$IN,$lemask
+	vxor		$IN,$IN,$Xl
+	b		Loop
+
+.align	5
+Loop:
+	 subic		$len,$len,16
+	vpmsumd		$Xl,$IN,$Hl		# H.lo·Xi.lo
+	 subfe.		r0,r0,r0		# borrow?-1:0
+	vpmsumd		$Xm,$IN,$H		# H.hi·Xi.lo+H.lo·Xi.hi
+	 and		r0,r0,$len
+	vpmsumd		$Xh,$IN,$Hh		# H.hi·Xi.hi
+	 add		$inp,$inp,r0
+
+	vpmsumd		$t2,$Xl,$xC2		# 1st phase
+
+	vsldoi		$t0,$Xm,$zero,8
+	vsldoi		$t1,$zero,$Xm,8
+	vxor		$Xl,$Xl,$t0
+	vxor		$Xh,$Xh,$t1
+
+	vsldoi		$Xl,$Xl,$Xl,8
+	vxor		$Xl,$Xl,$t2
+	 lvx_u		$IN,0,$inp
+	 addi		$inp,$inp,16
+
+	vsldoi		$t1,$Xl,$Xl,8		# 2nd phase
+	vpmsumd		$Xl,$Xl,$xC2
+	 le?vperm	$IN,$IN,$IN,$lemask
+	vxor		$t1,$t1,$Xh
+	vxor		$IN,$IN,$t1
+	vxor		$IN,$IN,$Xl
+	beq		Loop			# did $len-=16 borrow?
+
+	vxor		$Xl,$Xl,$t1
+	le?vperm	$Xl,$Xl,$Xl,$lemask
+	stvx_u		$Xl,0,$Xip		# write out Xi
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,4,0
+	.long		0
+.size	.gcm_ghash_p8,.-.gcm_ghash_p8
+
+.asciz  "GHASH for PowerISA 2.07, CRYPTOGAMS by <appro\@openssl.org>"
+.align  2
+___
+
+foreach (split("\n",$code)) {
+	if ($flavour =~ /le$/o) {	# little-endian
+	    s/le\?//o		or
+	    s/be\?/#be#/o;
+	} else {
+	    s/le\?/#le#/o	or
+	    s/be\?//o;
+	}
+	print $_,"\n";
+}
+
+close STDOUT; # enforce flush
diff --git a/arch/powerpc/crypto/ppc-xlate.pl b/arch/powerpc/crypto/ppc-xlate.pl
new file mode 100644
index 000000000000..23cca703ce29
--- /dev/null
+++ b/arch/powerpc/crypto/ppc-xlate.pl
@@ -0,0 +1,229 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# PowerPC assembler distiller by <appro>.
+
+my $flavour = shift;
+my $output = shift;
+open STDOUT,">$output" || die "can't open $output: $!";
+
+my %GLOBALS;
+my $dotinlocallabels=($flavour=~/linux/)?1:0;
+
+################################################################
+# directives which need special treatment on different platforms
+################################################################
+my $globl = sub {
+    my $junk = shift;
+    my $name = shift;
+    my $global = \$GLOBALS{$name};
+    my $ret;
+
+    $name =~ s|^[\.\_]||;
+
+    SWITCH: for ($flavour) {
+	/aix/		&& do { $name = ".$name";
+				last;
+			      };
+	/osx/		&& do { $name = "_$name";
+				last;
+			      };
+	/linux/
+			&& do {	$ret = "_GLOBAL($name)";
+				last;
+			      };
+    }
+
+    $ret = ".globl	$name\nalign 5\n$name:" if (!$ret);
+    $$global = $name;
+    $ret;
+};
+my $text = sub {
+    my $ret = ($flavour =~ /aix/) ? ".csect\t.text[PR],7" : ".text";
+    $ret = ".abiversion	2\n".$ret	if ($flavour =~ /linux.*64le/);
+    $ret;
+};
+my $machine = sub {
+    my $junk = shift;
+    my $arch = shift;
+    if ($flavour =~ /osx/)
+    {	$arch =~ s/\"//g;
+	$arch = ($flavour=~/64/) ? "ppc970-64" : "ppc970" if ($arch eq "any");
+    }
+    ".machine	$arch";
+};
+my $size = sub {
+    if ($flavour =~ /linux/)
+    {	shift;
+	my $name = shift; $name =~ s|^[\.\_]||;
+	my $ret  = ".size	$name,.-".($flavour=~/64$/?".":"").$name;
+	$ret .= "\n.size	.$name,.-.$name" if ($flavour=~/64$/);
+	$ret;
+    }
+    else
+    {	"";	}
+};
+my $asciz = sub {
+    shift;
+    my $line = join(",",@_);
+    if ($line =~ /^"(.*)"$/)
+    {	".byte	" . join(",",unpack("C*",$1),0) . "\n.align	2";	}
+    else
+    {	"";	}
+};
+my $quad = sub {
+    shift;
+    my @ret;
+    my ($hi,$lo);
+    for (@_) {
+	if (/^0x([0-9a-f]*?)([0-9a-f]{1,8})$/io)
+	{  $hi=$1?"0x$1":"0"; $lo="0x$2";  }
+	elsif (/^([0-9]+)$/o)
+	{  $hi=$1>>32; $lo=$1&0xffffffff;  } # error-prone with 32-bit perl
+	else
+	{  $hi=undef; $lo=$_; }
+
+	if (defined($hi))
+	{  push(@ret,$flavour=~/le$/o?".long\t$lo,$hi":".long\t$hi,$lo");  }
+	else
+	{  push(@ret,".quad	$lo");  }
+    }
+    join("\n",@ret);
+};
+
+################################################################
+# simplified mnemonics not handled by at least one assembler
+################################################################
+my $cmplw = sub {
+    my $f = shift;
+    my $cr = 0; $cr = shift if ($#_>1);
+    # Some out-of-date 32-bit GNU assembler just can't handle cmplw...
+    ($flavour =~ /linux.*32/) ?
+	"	.long	".sprintf "0x%x",31<<26|$cr<<23|$_[0]<<16|$_[1]<<11|64 :
+	"	cmplw	".join(',',$cr,@_);
+};
+my $bdnz = sub {
+    my $f = shift;
+    my $bo = $f=~/[\+\-]/ ? 16+9 : 16;	# optional "to be taken" hint
+    "	bc	$bo,0,".shift;
+} if ($flavour!~/linux/);
+my $bltlr = sub {
+    my $f = shift;
+    my $bo = $f=~/\-/ ? 12+2 : 12;	# optional "not to be taken" hint
+    ($flavour =~ /linux/) ?		# GNU as doesn't allow most recent hints
+	"	.long	".sprintf "0x%x",19<<26|$bo<<21|16<<1 :
+	"	bclr	$bo,0";
+};
+my $bnelr = sub {
+    my $f = shift;
+    my $bo = $f=~/\-/ ? 4+2 : 4;	# optional "not to be taken" hint
+    ($flavour =~ /linux/) ?		# GNU as doesn't allow most recent hints
+	"	.long	".sprintf "0x%x",19<<26|$bo<<21|2<<16|16<<1 :
+	"	bclr	$bo,2";
+};
+my $beqlr = sub {
+    my $f = shift;
+    my $bo = $f=~/-/ ? 12+2 : 12;	# optional "not to be taken" hint
+    ($flavour =~ /linux/) ?		# GNU as doesn't allow most recent hints
+	"	.long	".sprintf "0x%X",19<<26|$bo<<21|2<<16|16<<1 :
+	"	bclr	$bo,2";
+};
+# GNU assembler can't handle extrdi rA,rS,16,48, or when sum of last two
+# arguments is 64, with "operand out of range" error.
+my $extrdi = sub {
+    my ($f,$ra,$rs,$n,$b) = @_;
+    $b = ($b+$n)&63; $n = 64-$n;
+    "	rldicl	$ra,$rs,$b,$n";
+};
+my $vmr = sub {
+    my ($f,$vx,$vy) = @_;
+    "	vor	$vx,$vy,$vy";
+};
+
+# Some ABIs specify vrsave, special-purpose register #256, as reserved
+# for system use.
+my $no_vrsave = ($flavour =~ /linux-ppc64le/);
+my $mtspr = sub {
+    my ($f,$idx,$ra) = @_;
+    if ($idx == 256 && $no_vrsave) {
+	"	or	$ra,$ra,$ra";
+    } else {
+	"	mtspr	$idx,$ra";
+    }
+};
+my $mfspr = sub {
+    my ($f,$rd,$idx) = @_;
+    if ($idx == 256 && $no_vrsave) {
+	"	li	$rd,-1";
+    } else {
+	"	mfspr	$rd,$idx";
+    }
+};
+
+# PowerISA 2.06 stuff
+sub vsxmem_op {
+    my ($f, $vrt, $ra, $rb, $op) = @_;
+    "	.long	".sprintf "0x%X",(31<<26)|($vrt<<21)|($ra<<16)|($rb<<11)|($op*2+1);
+}
+# made-up unaligned memory reference AltiVec/VMX instructions
+my $lvx_u	= sub {	vsxmem_op(@_, 844); };	# lxvd2x
+my $stvx_u	= sub {	vsxmem_op(@_, 972); };	# stxvd2x
+my $lvdx_u	= sub {	vsxmem_op(@_, 588); };	# lxsdx
+my $stvdx_u	= sub {	vsxmem_op(@_, 716); };	# stxsdx
+my $lvx_4w	= sub { vsxmem_op(@_, 780); };	# lxvw4x
+my $stvx_4w	= sub { vsxmem_op(@_, 908); };	# stxvw4x
+
+# PowerISA 2.07 stuff
+sub vcrypto_op {
+    my ($f, $vrt, $vra, $vrb, $op) = @_;
+    "	.long	".sprintf "0x%X",(4<<26)|($vrt<<21)|($vra<<16)|($vrb<<11)|$op;
+}
+my $vcipher	= sub { vcrypto_op(@_, 1288); };
+my $vcipherlast	= sub { vcrypto_op(@_, 1289); };
+my $vncipher	= sub { vcrypto_op(@_, 1352); };
+my $vncipherlast= sub { vcrypto_op(@_, 1353); };
+my $vsbox	= sub { vcrypto_op(@_, 0, 1480); };
+my $vshasigmad	= sub { my ($st,$six)=splice(@_,-2); vcrypto_op(@_, $st<<4|$six, 1730); };
+my $vshasigmaw	= sub { my ($st,$six)=splice(@_,-2); vcrypto_op(@_, $st<<4|$six, 1666); };
+my $vpmsumb	= sub { vcrypto_op(@_, 1032); };
+my $vpmsumd	= sub { vcrypto_op(@_, 1224); };
+my $vpmsubh	= sub { vcrypto_op(@_, 1096); };
+my $vpmsumw	= sub { vcrypto_op(@_, 1160); };
+my $vaddudm	= sub { vcrypto_op(@_, 192);  };
+my $vadduqm	= sub { vcrypto_op(@_, 256);  };
+
+my $mtsle	= sub {
+    my ($f, $arg) = @_;
+    "	.long	".sprintf "0x%X",(31<<26)|($arg<<21)|(147*2);
+};
+
+print "#include <asm/ppc_asm.h>\n" if $flavour =~ /linux/;
+
+while($line=<>) {
+
+    $line =~ s|[#!;].*$||;	# get rid of asm-style comments...
+    $line =~ s|/\*.*\*/||;	# ... and C-style comments...
+    $line =~ s|^\s+||;		# ... and skip white spaces in beginning...
+    $line =~ s|\s+$||;		# ... and at the end
+
+    {
+	$line =~ s|\b\.L(\w+)|L$1|g;	# common denominator for Locallabel
+	$line =~ s|\bL(\w+)|\.L$1|g	if ($dotinlocallabels);
+    }
+
+    {
+	$line =~ s|^\s*(\.?)(\w+)([\.\+\-]?)\s*||;
+	my $c = $1; $c = "\t" if ($c eq "");
+	my $mnemonic = $2;
+	my $f = $3;
+	my $opcode = eval("\$$mnemonic");
+	$line =~ s/\b(c?[rf]|v|vs)([0-9]+)\b/$2/g if ($c ne "." and $flavour !~ /osx/);
+	if (ref($opcode) eq 'CODE') { $line = &$opcode($f,split(',',$line)); }
+	elsif ($mnemonic)           { $line = $c.$mnemonic.$f."\t".$line; }
+    }
+
+    print $line if ($line);
+    print "\n";
+}
+
+close STDOUT;
diff --git a/arch/powerpc/include/asm/cpufeature.h b/arch/powerpc/include/asm/cpufeature.h
index f6f790a90367..2dcc66225e7f 100644
--- a/arch/powerpc/include/asm/cpufeature.h
+++ b/arch/powerpc/include/asm/cpufeature.h
@@ -22,6 +22,7 @@
  */
 
 #define PPC_MODULE_FEATURE_VEC_CRYPTO			(32 + ilog2(PPC_FEATURE2_VEC_CRYPTO))
+#define PPC_MODULE_FEATURE_P10				(32 + ilog2(PPC_FEATURE2_ARCH_3_1))
 
 #define cpu_feature(x)		(x)
 
diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
index cdf3215ec272..ad7f4c891625 100644
--- a/arch/x86/crypto/aegis128-aesni-asm.S
+++ b/arch/x86/crypto/aegis128-aesni-asm.S
@@ -201,8 +201,8 @@ SYM_FUNC_START(crypto_aegis128_aesni_init)
 	movdqa KEY, STATE4
 
 	/* load the constants: */
-	movdqa .Laegis128_const_0, STATE2
-	movdqa .Laegis128_const_1, STATE1
+	movdqa .Laegis128_const_0(%rip), STATE2
+	movdqa .Laegis128_const_1(%rip), STATE1
 	pxor STATE2, STATE3
 	pxor STATE1, STATE4
 
@@ -682,7 +682,7 @@ SYM_TYPED_FUNC_START(crypto_aegis128_aesni_dec_tail)
 	punpcklbw T0, T0
 	punpcklbw T0, T0
 	punpcklbw T0, T0
-	movdqa .Laegis128_counter, T1
+	movdqa .Laegis128_counter(%rip), T1
 	pcmpgtb T1, T0
 	pand T0, MSG
 
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 837c1e0aa021..3ac7487ecad2 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -288,53 +288,53 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	# Encrypt/Decrypt first few blocks
 
 	and	$(3<<4), %r12
-	jz	_initial_num_blocks_is_0_\@
+	jz	.L_initial_num_blocks_is_0_\@
 	cmp	$(2<<4), %r12
-	jb	_initial_num_blocks_is_1_\@
-	je	_initial_num_blocks_is_2_\@
-_initial_num_blocks_is_3_\@:
+	jb	.L_initial_num_blocks_is_1_\@
+	je	.L_initial_num_blocks_is_2_\@
+.L_initial_num_blocks_is_3_\@:
 	INITIAL_BLOCKS_ENC_DEC	%xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
 %xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, \operation
 	sub	$48, %r13
-	jmp	_initial_blocks_\@
-_initial_num_blocks_is_2_\@:
+	jmp	.L_initial_blocks_\@
+.L_initial_num_blocks_is_2_\@:
 	INITIAL_BLOCKS_ENC_DEC	%xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
 %xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, \operation
 	sub	$32, %r13
-	jmp	_initial_blocks_\@
-_initial_num_blocks_is_1_\@:
+	jmp	.L_initial_blocks_\@
+.L_initial_num_blocks_is_1_\@:
 	INITIAL_BLOCKS_ENC_DEC	%xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
 %xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, \operation
 	sub	$16, %r13
-	jmp	_initial_blocks_\@
-_initial_num_blocks_is_0_\@:
+	jmp	.L_initial_blocks_\@
+.L_initial_num_blocks_is_0_\@:
 	INITIAL_BLOCKS_ENC_DEC	%xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
 %xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, \operation
-_initial_blocks_\@:
+.L_initial_blocks_\@:
 
 	# Main loop - Encrypt/Decrypt remaining blocks
 
 	test	%r13, %r13
-	je	_zero_cipher_left_\@
+	je	.L_zero_cipher_left_\@
 	sub	$64, %r13
-	je	_four_cipher_left_\@
-_crypt_by_4_\@:
+	je	.L_four_cipher_left_\@
+.L_crypt_by_4_\@:
 	GHASH_4_ENCRYPT_4_PARALLEL_\operation	%xmm9, %xmm10, %xmm11, %xmm12, \
 	%xmm13, %xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, \
 	%xmm7, %xmm8, enc
 	add	$64, %r11
 	sub	$64, %r13
-	jne	_crypt_by_4_\@
-_four_cipher_left_\@:
+	jne	.L_crypt_by_4_\@
+.L_four_cipher_left_\@:
 	GHASH_LAST_4	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \
 %xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8
-_zero_cipher_left_\@:
+.L_zero_cipher_left_\@:
 	movdqu %xmm8, AadHash(%arg2)
 	movdqu %xmm0, CurCount(%arg2)
 
 	mov	%arg5, %r13
 	and	$15, %r13			# %r13 = arg5 (mod 16)
-	je	_multiple_of_16_bytes_\@
+	je	.L_multiple_of_16_bytes_\@
 
 	mov %r13, PBlockLen(%arg2)
 
@@ -348,14 +348,14 @@ _zero_cipher_left_\@:
 	movdqu %xmm0, PBlockEncKey(%arg2)
 
 	cmp	$16, %arg5
-	jge _large_enough_update_\@
+	jge	.L_large_enough_update_\@
 
 	lea (%arg4,%r11,1), %r10
 	mov %r13, %r12
 	READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1
-	jmp _data_read_\@
+	jmp	.L_data_read_\@
 
-_large_enough_update_\@:
+.L_large_enough_update_\@:
 	sub	$16, %r11
 	add	%r13, %r11
 
@@ -374,7 +374,7 @@ _large_enough_update_\@:
 	# shift right 16-r13 bytes
 	pshufb  %xmm2, %xmm1
 
-_data_read_\@:
+.L_data_read_\@:
 	lea ALL_F+16(%rip), %r12
 	sub %r13, %r12
 
@@ -409,19 +409,19 @@ _data_read_\@:
 	# Output %r13 bytes
 	movq %xmm0, %rax
 	cmp $8, %r13
-	jle _less_than_8_bytes_left_\@
+	jle .L_less_than_8_bytes_left_\@
 	mov %rax, (%arg3 , %r11, 1)
 	add $8, %r11
 	psrldq $8, %xmm0
 	movq %xmm0, %rax
 	sub $8, %r13
-_less_than_8_bytes_left_\@:
+.L_less_than_8_bytes_left_\@:
 	mov %al,  (%arg3, %r11, 1)
 	add $1, %r11
 	shr $8, %rax
 	sub $1, %r13
-	jne _less_than_8_bytes_left_\@
-_multiple_of_16_bytes_\@:
+	jne .L_less_than_8_bytes_left_\@
+.L_multiple_of_16_bytes_\@:
 .endm
 
 # GCM_COMPLETE Finishes update of tag of last partial block
@@ -434,11 +434,11 @@ _multiple_of_16_bytes_\@:
 	mov PBlockLen(%arg2), %r12
 
 	test %r12, %r12
-	je _partial_done\@
+	je .L_partial_done\@
 
 	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
 
-_partial_done\@:
+.L_partial_done\@:
 	mov AadLen(%arg2), %r12  # %r13 = aadLen (number of bytes)
 	shl	$3, %r12		  # convert into number of bits
 	movd	%r12d, %xmm15		  # len(A) in %xmm15
@@ -457,44 +457,44 @@ _partial_done\@:
 	movdqu OrigIV(%arg2), %xmm0       # %xmm0 = Y0
 	ENCRYPT_SINGLE_BLOCK	%xmm0,  %xmm1	  # E(K, Y0)
 	pxor	%xmm8, %xmm0
-_return_T_\@:
+.L_return_T_\@:
 	mov	\AUTHTAG, %r10                     # %r10 = authTag
 	mov	\AUTHTAGLEN, %r11                    # %r11 = auth_tag_len
 	cmp	$16, %r11
-	je	_T_16_\@
+	je	.L_T_16_\@
 	cmp	$8, %r11
-	jl	_T_4_\@
-_T_8_\@:
+	jl	.L_T_4_\@
+.L_T_8_\@:
 	movq	%xmm0, %rax
 	mov	%rax, (%r10)
 	add	$8, %r10
 	sub	$8, %r11
 	psrldq	$8, %xmm0
 	test	%r11, %r11
-	je	_return_T_done_\@
-_T_4_\@:
+	je	.L_return_T_done_\@
+.L_T_4_\@:
 	movd	%xmm0, %eax
 	mov	%eax, (%r10)
 	add	$4, %r10
 	sub	$4, %r11
 	psrldq	$4, %xmm0
 	test	%r11, %r11
-	je	_return_T_done_\@
-_T_123_\@:
+	je	.L_return_T_done_\@
+.L_T_123_\@:
 	movd	%xmm0, %eax
 	cmp	$2, %r11
-	jl	_T_1_\@
+	jl	.L_T_1_\@
 	mov	%ax, (%r10)
 	cmp	$2, %r11
-	je	_return_T_done_\@
+	je	.L_return_T_done_\@
 	add	$2, %r10
 	sar	$16, %eax
-_T_1_\@:
+.L_T_1_\@:
 	mov	%al, (%r10)
-	jmp	_return_T_done_\@
-_T_16_\@:
+	jmp	.L_return_T_done_\@
+.L_T_16_\@:
 	movdqu	%xmm0, (%r10)
-_return_T_done_\@:
+.L_return_T_done_\@:
 .endm
 
 #ifdef __x86_64__
@@ -563,30 +563,30 @@ _return_T_done_\@:
 # Clobbers %rax, DLEN and XMM1
 .macro READ_PARTIAL_BLOCK DPTR DLEN XMM1 XMMDst
         cmp $8, \DLEN
-        jl _read_lt8_\@
+        jl .L_read_lt8_\@
         mov (\DPTR), %rax
         movq %rax, \XMMDst
         sub $8, \DLEN
-        jz _done_read_partial_block_\@
+        jz .L_done_read_partial_block_\@
 	xor %eax, %eax
-_read_next_byte_\@:
+.L_read_next_byte_\@:
         shl $8, %rax
         mov 7(\DPTR, \DLEN, 1), %al
         dec \DLEN
-        jnz _read_next_byte_\@
+        jnz .L_read_next_byte_\@
         movq %rax, \XMM1
 	pslldq $8, \XMM1
         por \XMM1, \XMMDst
-	jmp _done_read_partial_block_\@
-_read_lt8_\@:
+	jmp .L_done_read_partial_block_\@
+.L_read_lt8_\@:
 	xor %eax, %eax
-_read_next_byte_lt8_\@:
+.L_read_next_byte_lt8_\@:
         shl $8, %rax
         mov -1(\DPTR, \DLEN, 1), %al
         dec \DLEN
-        jnz _read_next_byte_lt8_\@
+        jnz .L_read_next_byte_lt8_\@
         movq %rax, \XMMDst
-_done_read_partial_block_\@:
+.L_done_read_partial_block_\@:
 .endm
 
 # CALC_AAD_HASH: Calculates the hash of the data which will not be encrypted.
@@ -600,8 +600,8 @@ _done_read_partial_block_\@:
 	pxor	   \TMP6, \TMP6
 
 	cmp	   $16, %r11
-	jl	   _get_AAD_rest\@
-_get_AAD_blocks\@:
+	jl	   .L_get_AAD_rest\@
+.L_get_AAD_blocks\@:
 	movdqu	   (%r10), \TMP7
 	pshufb	   %xmm14, \TMP7 # byte-reflect the AAD data
 	pxor	   \TMP7, \TMP6
@@ -609,14 +609,14 @@ _get_AAD_blocks\@:
 	add	   $16, %r10
 	sub	   $16, %r11
 	cmp	   $16, %r11
-	jge	   _get_AAD_blocks\@
+	jge	   .L_get_AAD_blocks\@
 
 	movdqu	   \TMP6, \TMP7
 
 	/* read the last <16B of AAD */
-_get_AAD_rest\@:
+.L_get_AAD_rest\@:
 	test	   %r11, %r11
-	je	   _get_AAD_done\@
+	je	   .L_get_AAD_done\@
 
 	READ_PARTIAL_BLOCK %r10, %r11, \TMP1, \TMP7
 	pshufb	   %xmm14, \TMP7 # byte-reflect the AAD data
@@ -624,7 +624,7 @@ _get_AAD_rest\@:
 	GHASH_MUL  \TMP7, \HASHKEY, \TMP1, \TMP2, \TMP3, \TMP4, \TMP5
 	movdqu \TMP7, \TMP6
 
-_get_AAD_done\@:
+.L_get_AAD_done\@:
 	movdqu \TMP6, AadHash(%arg2)
 .endm
 
@@ -637,21 +637,21 @@ _get_AAD_done\@:
 	AAD_HASH operation
 	mov 	PBlockLen(%arg2), %r13
 	test	%r13, %r13
-	je	_partial_block_done_\@	# Leave Macro if no partial blocks
+	je	.L_partial_block_done_\@	# Leave Macro if no partial blocks
 	# Read in input data without over reading
 	cmp	$16, \PLAIN_CYPH_LEN
-	jl	_fewer_than_16_bytes_\@
+	jl	.L_fewer_than_16_bytes_\@
 	movups	(\PLAIN_CYPH_IN), %xmm1	# If more than 16 bytes, just fill xmm
-	jmp	_data_read_\@
+	jmp	.L_data_read_\@
 
-_fewer_than_16_bytes_\@:
+.L_fewer_than_16_bytes_\@:
 	lea	(\PLAIN_CYPH_IN, \DATA_OFFSET, 1), %r10
 	mov	\PLAIN_CYPH_LEN, %r12
 	READ_PARTIAL_BLOCK %r10 %r12 %xmm0 %xmm1
 
 	mov PBlockLen(%arg2), %r13
 
-_data_read_\@:				# Finished reading in data
+.L_data_read_\@:				# Finished reading in data
 
 	movdqu	PBlockEncKey(%arg2), %xmm9
 	movdqu	HashKey(%arg2), %xmm13
@@ -674,9 +674,9 @@ _data_read_\@:				# Finished reading in data
 	sub	$16, %r10
 	# Determine if if partial block is not being filled and
 	# shift mask accordingly
-	jge	_no_extra_mask_1_\@
+	jge	.L_no_extra_mask_1_\@
 	sub	%r10, %r12
-_no_extra_mask_1_\@:
+.L_no_extra_mask_1_\@:
 
 	movdqu	ALL_F-SHIFT_MASK(%r12), %xmm1
 	# get the appropriate mask to mask out bottom r13 bytes of xmm9
@@ -689,17 +689,17 @@ _no_extra_mask_1_\@:
 	pxor	%xmm3, \AAD_HASH
 
 	test	%r10, %r10
-	jl	_partial_incomplete_1_\@
+	jl	.L_partial_incomplete_1_\@
 
 	# GHASH computation for the last <16 Byte block
 	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
 	xor	%eax, %eax
 
 	mov	%rax, PBlockLen(%arg2)
-	jmp	_dec_done_\@
-_partial_incomplete_1_\@:
+	jmp	.L_dec_done_\@
+.L_partial_incomplete_1_\@:
 	add	\PLAIN_CYPH_LEN, PBlockLen(%arg2)
-_dec_done_\@:
+.L_dec_done_\@:
 	movdqu	\AAD_HASH, AadHash(%arg2)
 .else
 	pxor	%xmm1, %xmm9			# Plaintext XOR E(K, Yn)
@@ -710,9 +710,9 @@ _dec_done_\@:
 	sub	$16, %r10
 	# Determine if if partial block is not being filled and
 	# shift mask accordingly
-	jge	_no_extra_mask_2_\@
+	jge	.L_no_extra_mask_2_\@
 	sub	%r10, %r12
-_no_extra_mask_2_\@:
+.L_no_extra_mask_2_\@:
 
 	movdqu	ALL_F-SHIFT_MASK(%r12), %xmm1
 	# get the appropriate mask to mask out bottom r13 bytes of xmm9
@@ -724,17 +724,17 @@ _no_extra_mask_2_\@:
 	pxor	%xmm9, \AAD_HASH
 
 	test	%r10, %r10
-	jl	_partial_incomplete_2_\@
+	jl	.L_partial_incomplete_2_\@
 
 	# GHASH computation for the last <16 Byte block
 	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
 	xor	%eax, %eax
 
 	mov	%rax, PBlockLen(%arg2)
-	jmp	_encode_done_\@
-_partial_incomplete_2_\@:
+	jmp	.L_encode_done_\@
+.L_partial_incomplete_2_\@:
 	add	\PLAIN_CYPH_LEN, PBlockLen(%arg2)
-_encode_done_\@:
+.L_encode_done_\@:
 	movdqu	\AAD_HASH, AadHash(%arg2)
 
 	movdqa	SHUF_MASK(%rip), %xmm10
@@ -744,32 +744,32 @@ _encode_done_\@:
 .endif
 	# output encrypted Bytes
 	test	%r10, %r10
-	jl	_partial_fill_\@
+	jl	.L_partial_fill_\@
 	mov	%r13, %r12
 	mov	$16, %r13
 	# Set r13 to be the number of bytes to write out
 	sub	%r12, %r13
-	jmp	_count_set_\@
-_partial_fill_\@:
+	jmp	.L_count_set_\@
+.L_partial_fill_\@:
 	mov	\PLAIN_CYPH_LEN, %r13
-_count_set_\@:
+.L_count_set_\@:
 	movdqa	%xmm9, %xmm0
 	movq	%xmm0, %rax
 	cmp	$8, %r13
-	jle	_less_than_8_bytes_left_\@
+	jle	.L_less_than_8_bytes_left_\@
 
 	mov	%rax, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
 	add	$8, \DATA_OFFSET
 	psrldq	$8, %xmm0
 	movq	%xmm0, %rax
 	sub	$8, %r13
-_less_than_8_bytes_left_\@:
+.L_less_than_8_bytes_left_\@:
 	movb	%al, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
 	add	$1, \DATA_OFFSET
 	shr	$8, %rax
 	sub	$1, %r13
-	jne	_less_than_8_bytes_left_\@
-_partial_block_done_\@:
+	jne	.L_less_than_8_bytes_left_\@
+.L_partial_block_done_\@:
 .endm # PARTIAL_BLOCK
 
 /*
@@ -813,14 +813,14 @@ _partial_block_done_\@:
 	shr	$2,%eax				# 128->4, 192->6, 256->8
 	add	$5,%eax			      # 128->9, 192->11, 256->13
 
-aes_loop_initial_\@:
+.Laes_loop_initial_\@:
 	MOVADQ	(%r10),\TMP1
 .irpc	index, \i_seq
 	aesenc	\TMP1, %xmm\index
 .endr
 	add	$16,%r10
 	sub	$1,%eax
-	jnz	aes_loop_initial_\@
+	jnz	.Laes_loop_initial_\@
 
 	MOVADQ	(%r10), \TMP1
 .irpc index, \i_seq
@@ -861,7 +861,7 @@ aes_loop_initial_\@:
 	GHASH_MUL  %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
 .endif
 	cmp	   $64, %r13
-	jl	_initial_blocks_done\@
+	jl	.L_initial_blocks_done\@
 	# no need for precomputed values
 /*
 *
@@ -908,18 +908,18 @@ aes_loop_initial_\@:
 	mov	   keysize,%eax
 	shr	   $2,%eax			# 128->4, 192->6, 256->8
 	sub	   $4,%eax			# 128->0, 192->2, 256->4
-	jz	   aes_loop_pre_done\@
+	jz	   .Laes_loop_pre_done\@
 
-aes_loop_pre_\@:
+.Laes_loop_pre_\@:
 	MOVADQ	   (%r10),\TMP2
 .irpc	index, 1234
 	aesenc	   \TMP2, %xmm\index
 .endr
 	add	   $16,%r10
 	sub	   $1,%eax
-	jnz	   aes_loop_pre_\@
+	jnz	   .Laes_loop_pre_\@
 
-aes_loop_pre_done\@:
+.Laes_loop_pre_done\@:
 	MOVADQ	   (%r10), \TMP2
 	aesenclast \TMP2, \XMM1
 	aesenclast \TMP2, \XMM2
@@ -963,7 +963,7 @@ aes_loop_pre_done\@:
 	pshufb %xmm14, \XMM3 # perform a 16 byte swap
 	pshufb %xmm14, \XMM4 # perform a 16 byte swap
 
-_initial_blocks_done\@:
+.L_initial_blocks_done\@:
 
 .endm
 
@@ -1095,18 +1095,18 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	mov	  keysize,%eax
 	shr	  $2,%eax			# 128->4, 192->6, 256->8
 	sub	  $4,%eax			# 128->0, 192->2, 256->4
-	jz	  aes_loop_par_enc_done\@
+	jz	  .Laes_loop_par_enc_done\@
 
-aes_loop_par_enc\@:
+.Laes_loop_par_enc\@:
 	MOVADQ	  (%r10),\TMP3
 .irpc	index, 1234
 	aesenc	  \TMP3, %xmm\index
 .endr
 	add	  $16,%r10
 	sub	  $1,%eax
-	jnz	  aes_loop_par_enc\@
+	jnz	  .Laes_loop_par_enc\@
 
-aes_loop_par_enc_done\@:
+.Laes_loop_par_enc_done\@:
 	MOVADQ	  (%r10), \TMP3
 	aesenclast \TMP3, \XMM1           # Round 10
 	aesenclast \TMP3, \XMM2
@@ -1303,18 +1303,18 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	mov	  keysize,%eax
 	shr	  $2,%eax		        # 128->4, 192->6, 256->8
 	sub	  $4,%eax			# 128->0, 192->2, 256->4
-	jz	  aes_loop_par_dec_done\@
+	jz	  .Laes_loop_par_dec_done\@
 
-aes_loop_par_dec\@:
+.Laes_loop_par_dec\@:
 	MOVADQ	  (%r10),\TMP3
 .irpc	index, 1234
 	aesenc	  \TMP3, %xmm\index
 .endr
 	add	  $16,%r10
 	sub	  $1,%eax
-	jnz	  aes_loop_par_dec\@
+	jnz	  .Laes_loop_par_dec\@
 
-aes_loop_par_dec_done\@:
+.Laes_loop_par_dec_done\@:
 	MOVADQ	  (%r10), \TMP3
 	aesenclast \TMP3, \XMM1           # last round
 	aesenclast \TMP3, \XMM2
@@ -2717,7 +2717,7 @@ SYM_FUNC_END(aesni_cts_cbc_dec)
  *	BSWAP_MASK == endian swapping mask
  */
 SYM_FUNC_START_LOCAL(_aesni_inc_init)
-	movaps .Lbswap_mask, BSWAP_MASK
+	movaps .Lbswap_mask(%rip), BSWAP_MASK
 	movaps IV, CTR
 	pshufb BSWAP_MASK, CTR
 	mov $1, TCTR_LOW
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index 0852ab573fd3..46cddd78857b 100644
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -154,30 +154,6 @@ SHIFT_MASK:      .octa     0x0f0e0d0c0b0a09080706050403020100
 ALL_F:           .octa     0xffffffffffffffffffffffffffffffff
                  .octa     0x00000000000000000000000000000000
 
-.section .rodata
-.align 16
-.type aad_shift_arr, @object
-.size aad_shift_arr, 272
-aad_shift_arr:
-        .octa     0xffffffffffffffffffffffffffffffff
-        .octa     0xffffffffffffffffffffffffffffff0C
-        .octa     0xffffffffffffffffffffffffffff0D0C
-        .octa     0xffffffffffffffffffffffffff0E0D0C
-        .octa     0xffffffffffffffffffffffff0F0E0D0C
-        .octa     0xffffffffffffffffffffff0C0B0A0908
-        .octa     0xffffffffffffffffffff0D0C0B0A0908
-        .octa     0xffffffffffffffffff0E0D0C0B0A0908
-        .octa     0xffffffffffffffff0F0E0D0C0B0A0908
-        .octa     0xffffffffffffff0C0B0A090807060504
-        .octa     0xffffffffffff0D0C0B0A090807060504
-        .octa     0xffffffffff0E0D0C0B0A090807060504
-        .octa     0xffffffff0F0E0D0C0B0A090807060504
-        .octa     0xffffff0C0B0A09080706050403020100
-        .octa     0xffff0D0C0B0A09080706050403020100
-        .octa     0xff0E0D0C0B0A09080706050403020100
-        .octa     0x0F0E0D0C0B0A09080706050403020100
-
-
 .text
 
 
@@ -302,68 +278,68 @@ VARIABLE_OFFSET = 16*8
         mov     %r13, %r12
         shr     $4, %r12
         and     $7, %r12
-        jz      _initial_num_blocks_is_0\@
+        jz      .L_initial_num_blocks_is_0\@
 
         cmp     $7, %r12
-        je      _initial_num_blocks_is_7\@
+        je      .L_initial_num_blocks_is_7\@
         cmp     $6, %r12
-        je      _initial_num_blocks_is_6\@
+        je      .L_initial_num_blocks_is_6\@
         cmp     $5, %r12
-        je      _initial_num_blocks_is_5\@
+        je      .L_initial_num_blocks_is_5\@
         cmp     $4, %r12
-        je      _initial_num_blocks_is_4\@
+        je      .L_initial_num_blocks_is_4\@
         cmp     $3, %r12
-        je      _initial_num_blocks_is_3\@
+        je      .L_initial_num_blocks_is_3\@
         cmp     $2, %r12
-        je      _initial_num_blocks_is_2\@
+        je      .L_initial_num_blocks_is_2\@
 
-        jmp     _initial_num_blocks_is_1\@
+        jmp     .L_initial_num_blocks_is_1\@
 
-_initial_num_blocks_is_7\@:
+.L_initial_num_blocks_is_7\@:
         \INITIAL_BLOCKS  \REP, 7, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
         sub     $16*7, %r13
-        jmp     _initial_blocks_encrypted\@
+        jmp     .L_initial_blocks_encrypted\@
 
-_initial_num_blocks_is_6\@:
+.L_initial_num_blocks_is_6\@:
         \INITIAL_BLOCKS  \REP, 6, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
         sub     $16*6, %r13
-        jmp     _initial_blocks_encrypted\@
+        jmp     .L_initial_blocks_encrypted\@
 
-_initial_num_blocks_is_5\@:
+.L_initial_num_blocks_is_5\@:
         \INITIAL_BLOCKS  \REP, 5, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
         sub     $16*5, %r13
-        jmp     _initial_blocks_encrypted\@
+        jmp     .L_initial_blocks_encrypted\@
 
-_initial_num_blocks_is_4\@:
+.L_initial_num_blocks_is_4\@:
         \INITIAL_BLOCKS  \REP, 4, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
         sub     $16*4, %r13
-        jmp     _initial_blocks_encrypted\@
+        jmp     .L_initial_blocks_encrypted\@
 
-_initial_num_blocks_is_3\@:
+.L_initial_num_blocks_is_3\@:
         \INITIAL_BLOCKS  \REP, 3, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
         sub     $16*3, %r13
-        jmp     _initial_blocks_encrypted\@
+        jmp     .L_initial_blocks_encrypted\@
 
-_initial_num_blocks_is_2\@:
+.L_initial_num_blocks_is_2\@:
         \INITIAL_BLOCKS  \REP, 2, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
         sub     $16*2, %r13
-        jmp     _initial_blocks_encrypted\@
+        jmp     .L_initial_blocks_encrypted\@
 
-_initial_num_blocks_is_1\@:
+.L_initial_num_blocks_is_1\@:
         \INITIAL_BLOCKS  \REP, 1, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
         sub     $16*1, %r13
-        jmp     _initial_blocks_encrypted\@
+        jmp     .L_initial_blocks_encrypted\@
 
-_initial_num_blocks_is_0\@:
+.L_initial_num_blocks_is_0\@:
         \INITIAL_BLOCKS  \REP, 0, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
 
 
-_initial_blocks_encrypted\@:
+.L_initial_blocks_encrypted\@:
         test    %r13, %r13
-        je      _zero_cipher_left\@
+        je      .L_zero_cipher_left\@
 
         sub     $128, %r13
-        je      _eight_cipher_left\@
+        je      .L_eight_cipher_left\@
 
 
 
@@ -373,9 +349,9 @@ _initial_blocks_encrypted\@:
         vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
 
 
-_encrypt_by_8_new\@:
+.L_encrypt_by_8_new\@:
         cmp     $(255-8), %r15d
-        jg      _encrypt_by_8\@
+        jg      .L_encrypt_by_8\@
 
 
 
@@ -383,30 +359,30 @@ _encrypt_by_8_new\@:
         \GHASH_8_ENCRYPT_8_PARALLEL      \REP, %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, out_order, \ENC_DEC
         add     $128, %r11
         sub     $128, %r13
-        jne     _encrypt_by_8_new\@
+        jne     .L_encrypt_by_8_new\@
 
         vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
-        jmp     _eight_cipher_left\@
+        jmp     .L_eight_cipher_left\@
 
-_encrypt_by_8\@:
+.L_encrypt_by_8\@:
         vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
         add     $8, %r15b
         \GHASH_8_ENCRYPT_8_PARALLEL      \REP, %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, in_order, \ENC_DEC
         vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
         add     $128, %r11
         sub     $128, %r13
-        jne     _encrypt_by_8_new\@
+        jne     .L_encrypt_by_8_new\@
 
         vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
 
 
 
 
-_eight_cipher_left\@:
+.L_eight_cipher_left\@:
         \GHASH_LAST_8    %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8
 
 
-_zero_cipher_left\@:
+.L_zero_cipher_left\@:
         vmovdqu %xmm14, AadHash(arg2)
         vmovdqu %xmm9, CurCount(arg2)
 
@@ -414,7 +390,7 @@ _zero_cipher_left\@:
         mov     arg5, %r13
         and     $15, %r13                            # r13 = (arg5 mod 16)
 
-        je      _multiple_of_16_bytes\@
+        je      .L_multiple_of_16_bytes\@
 
         # handle the last <16 Byte block separately
 
@@ -428,7 +404,7 @@ _zero_cipher_left\@:
         vmovdqu %xmm9, PBlockEncKey(arg2)
 
         cmp $16, arg5
-        jge _large_enough_update\@
+        jge .L_large_enough_update\@
 
         lea (arg4,%r11,1), %r10
         mov %r13, %r12
@@ -440,9 +416,9 @@ _zero_cipher_left\@:
 						     # able to shift 16-r13 bytes (r13 is the
 	# number of bytes in plaintext mod 16)
 
-        jmp _final_ghash_mul\@
+        jmp .L_final_ghash_mul\@
 
-_large_enough_update\@:
+.L_large_enough_update\@:
         sub $16, %r11
         add %r13, %r11
 
@@ -461,7 +437,7 @@ _large_enough_update\@:
         # shift right 16-r13 bytes
         vpshufb  %xmm2, %xmm1, %xmm1
 
-_final_ghash_mul\@:
+.L_final_ghash_mul\@:
         .if  \ENC_DEC ==  DEC
         vmovdqa %xmm1, %xmm2
         vpxor   %xmm1, %xmm9, %xmm9                  # Plaintext XOR E(K, Yn)
@@ -490,7 +466,7 @@ _final_ghash_mul\@:
         # output r13 Bytes
         vmovq   %xmm9, %rax
         cmp     $8, %r13
-        jle     _less_than_8_bytes_left\@
+        jle     .L_less_than_8_bytes_left\@
 
         mov     %rax, (arg3 , %r11)
         add     $8, %r11
@@ -498,15 +474,15 @@ _final_ghash_mul\@:
         vmovq   %xmm9, %rax
         sub     $8, %r13
 
-_less_than_8_bytes_left\@:
+.L_less_than_8_bytes_left\@:
         movb    %al, (arg3 , %r11)
         add     $1, %r11
         shr     $8, %rax
         sub     $1, %r13
-        jne     _less_than_8_bytes_left\@
+        jne     .L_less_than_8_bytes_left\@
         #############################
 
-_multiple_of_16_bytes\@:
+.L_multiple_of_16_bytes\@:
 .endm
 
 
@@ -519,12 +495,12 @@ _multiple_of_16_bytes\@:
 
         mov PBlockLen(arg2), %r12
         test %r12, %r12
-        je _partial_done\@
+        je .L_partial_done\@
 
 	#GHASH computation for the last <16 Byte block
         \GHASH_MUL       %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
 
-_partial_done\@:
+.L_partial_done\@:
         mov AadLen(arg2), %r12                          # r12 = aadLen (number of bytes)
         shl     $3, %r12                             # convert into number of bits
         vmovd   %r12d, %xmm15                        # len(A) in xmm15
@@ -547,49 +523,49 @@ _partial_done\@:
 
 
 
-_return_T\@:
+.L_return_T\@:
         mov     \AUTH_TAG, %r10              # r10 = authTag
         mov     \AUTH_TAG_LEN, %r11              # r11 = auth_tag_len
 
         cmp     $16, %r11
-        je      _T_16\@
+        je      .L_T_16\@
 
         cmp     $8, %r11
-        jl      _T_4\@
+        jl      .L_T_4\@
 
-_T_8\@:
+.L_T_8\@:
         vmovq   %xmm9, %rax
         mov     %rax, (%r10)
         add     $8, %r10
         sub     $8, %r11
         vpsrldq $8, %xmm9, %xmm9
         test    %r11, %r11
-        je     _return_T_done\@
-_T_4\@:
+        je     .L_return_T_done\@
+.L_T_4\@:
         vmovd   %xmm9, %eax
         mov     %eax, (%r10)
         add     $4, %r10
         sub     $4, %r11
         vpsrldq     $4, %xmm9, %xmm9
         test    %r11, %r11
-        je     _return_T_done\@
-_T_123\@:
+        je     .L_return_T_done\@
+.L_T_123\@:
         vmovd     %xmm9, %eax
         cmp     $2, %r11
-        jl     _T_1\@
+        jl     .L_T_1\@
         mov     %ax, (%r10)
         cmp     $2, %r11
-        je     _return_T_done\@
+        je     .L_return_T_done\@
         add     $2, %r10
         sar     $16, %eax
-_T_1\@:
+.L_T_1\@:
         mov     %al, (%r10)
-        jmp     _return_T_done\@
+        jmp     .L_return_T_done\@
 
-_T_16\@:
+.L_T_16\@:
         vmovdqu %xmm9, (%r10)
 
-_return_T_done\@:
+.L_return_T_done\@:
 .endm
 
 .macro CALC_AAD_HASH GHASH_MUL AAD AADLEN T1 T2 T3 T4 T5 T6 T7 T8
@@ -603,8 +579,8 @@ _return_T_done\@:
 	vpxor   \T8, \T8, \T8
 	vpxor   \T7, \T7, \T7
 	cmp     $16, %r11
-	jl      _get_AAD_rest8\@
-_get_AAD_blocks\@:
+	jl      .L_get_AAD_rest8\@
+.L_get_AAD_blocks\@:
 	vmovdqu (%r10), \T7
 	vpshufb SHUF_MASK(%rip), \T7, \T7
 	vpxor   \T7, \T8, \T8
@@ -613,29 +589,29 @@ _get_AAD_blocks\@:
 	sub     $16, %r12
 	sub     $16, %r11
 	cmp     $16, %r11
-	jge     _get_AAD_blocks\@
+	jge     .L_get_AAD_blocks\@
 	vmovdqu \T8, \T7
 	test    %r11, %r11
-	je      _get_AAD_done\@
+	je      .L_get_AAD_done\@
 
 	vpxor   \T7, \T7, \T7
 
 	/* read the last <16B of AAD. since we have at least 4B of
 	data right after the AAD (the ICV, and maybe some CT), we can
 	read 4B/8B blocks safely, and then get rid of the extra stuff */
-_get_AAD_rest8\@:
+.L_get_AAD_rest8\@:
 	cmp     $4, %r11
-	jle     _get_AAD_rest4\@
+	jle     .L_get_AAD_rest4\@
 	movq    (%r10), \T1
 	add     $8, %r10
 	sub     $8, %r11
 	vpslldq $8, \T1, \T1
 	vpsrldq $8, \T7, \T7
 	vpxor   \T1, \T7, \T7
-	jmp     _get_AAD_rest8\@
-_get_AAD_rest4\@:
+	jmp     .L_get_AAD_rest8\@
+.L_get_AAD_rest4\@:
 	test    %r11, %r11
-	jle      _get_AAD_rest0\@
+	jle     .L_get_AAD_rest0\@
 	mov     (%r10), %eax
 	movq    %rax, \T1
 	add     $4, %r10
@@ -643,20 +619,22 @@ _get_AAD_rest4\@:
 	vpslldq $12, \T1, \T1
 	vpsrldq $4, \T7, \T7
 	vpxor   \T1, \T7, \T7
-_get_AAD_rest0\@:
+.L_get_AAD_rest0\@:
 	/* finalize: shift out the extra bytes we read, and align
 	left. since pslldq can only shift by an immediate, we use
-	vpshufb and an array of shuffle masks */
-	movq    %r12, %r11
-	salq    $4, %r11
-	vmovdqu  aad_shift_arr(%r11), \T1
-	vpshufb \T1, \T7, \T7
-_get_AAD_rest_final\@:
+	vpshufb and a pair of shuffle masks */
+	leaq	ALL_F(%rip), %r11
+	subq	%r12, %r11
+	vmovdqu	16(%r11), \T1
+	andq	$~3, %r11
+	vpshufb (%r11), \T7, \T7
+	vpand	\T1, \T7, \T7
+.L_get_AAD_rest_final\@:
 	vpshufb SHUF_MASK(%rip), \T7, \T7
 	vpxor   \T8, \T7, \T7
 	\GHASH_MUL       \T7, \T2, \T1, \T3, \T4, \T5, \T6
 
-_get_AAD_done\@:
+.L_get_AAD_done\@:
         vmovdqu \T7, AadHash(arg2)
 .endm
 
@@ -707,28 +685,28 @@ _get_AAD_done\@:
         vpxor \XMMDst, \XMMDst, \XMMDst
 
         cmp $8, \DLEN
-        jl _read_lt8_\@
+        jl .L_read_lt8_\@
         mov (\DPTR), %rax
         vpinsrq $0, %rax, \XMMDst, \XMMDst
         sub $8, \DLEN
-        jz _done_read_partial_block_\@
+        jz .L_done_read_partial_block_\@
         xor %eax, %eax
-_read_next_byte_\@:
+.L_read_next_byte_\@:
         shl $8, %rax
         mov 7(\DPTR, \DLEN, 1), %al
         dec \DLEN
-        jnz _read_next_byte_\@
+        jnz .L_read_next_byte_\@
         vpinsrq $1, %rax, \XMMDst, \XMMDst
-        jmp _done_read_partial_block_\@
-_read_lt8_\@:
+        jmp .L_done_read_partial_block_\@
+.L_read_lt8_\@:
         xor %eax, %eax
-_read_next_byte_lt8_\@:
+.L_read_next_byte_lt8_\@:
         shl $8, %rax
         mov -1(\DPTR, \DLEN, 1), %al
         dec \DLEN
-        jnz _read_next_byte_lt8_\@
+        jnz .L_read_next_byte_lt8_\@
         vpinsrq $0, %rax, \XMMDst, \XMMDst
-_done_read_partial_block_\@:
+.L_done_read_partial_block_\@:
 .endm
 
 # PARTIAL_BLOCK: Handles encryption/decryption and the tag partial blocks
@@ -740,21 +718,21 @@ _done_read_partial_block_\@:
         AAD_HASH ENC_DEC
         mov 	PBlockLen(arg2), %r13
         test	%r13, %r13
-        je	_partial_block_done_\@	# Leave Macro if no partial blocks
+        je	.L_partial_block_done_\@	# Leave Macro if no partial blocks
         # Read in input data without over reading
         cmp	$16, \PLAIN_CYPH_LEN
-        jl	_fewer_than_16_bytes_\@
+        jl	.L_fewer_than_16_bytes_\@
         vmovdqu	(\PLAIN_CYPH_IN), %xmm1	# If more than 16 bytes, just fill xmm
-        jmp	_data_read_\@
+        jmp	.L_data_read_\@
 
-_fewer_than_16_bytes_\@:
+.L_fewer_than_16_bytes_\@:
         lea	(\PLAIN_CYPH_IN, \DATA_OFFSET, 1), %r10
         mov	\PLAIN_CYPH_LEN, %r12
         READ_PARTIAL_BLOCK %r10 %r12 %xmm1
 
         mov PBlockLen(arg2), %r13
 
-_data_read_\@:				# Finished reading in data
+.L_data_read_\@:				# Finished reading in data
 
         vmovdqu	PBlockEncKey(arg2), %xmm9
         vmovdqu	HashKey(arg2), %xmm13
@@ -777,9 +755,9 @@ _data_read_\@:				# Finished reading in data
         sub	$16, %r10
         # Determine if if partial block is not being filled and
         # shift mask accordingly
-        jge	_no_extra_mask_1_\@
+        jge	.L_no_extra_mask_1_\@
         sub	%r10, %r12
-_no_extra_mask_1_\@:
+.L_no_extra_mask_1_\@:
 
         vmovdqu	ALL_F-SHIFT_MASK(%r12), %xmm1
         # get the appropriate mask to mask out bottom r13 bytes of xmm9
@@ -792,17 +770,17 @@ _no_extra_mask_1_\@:
         vpxor	%xmm3, \AAD_HASH, \AAD_HASH
 
         test	%r10, %r10
-        jl	_partial_incomplete_1_\@
+        jl	.L_partial_incomplete_1_\@
 
         # GHASH computation for the last <16 Byte block
         \GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
         xor	%eax,%eax
 
         mov	%rax, PBlockLen(arg2)
-        jmp	_dec_done_\@
-_partial_incomplete_1_\@:
+        jmp	.L_dec_done_\@
+.L_partial_incomplete_1_\@:
         add	\PLAIN_CYPH_LEN, PBlockLen(arg2)
-_dec_done_\@:
+.L_dec_done_\@:
         vmovdqu	\AAD_HASH, AadHash(arg2)
 .else
         vpxor	%xmm1, %xmm9, %xmm9			# Plaintext XOR E(K, Yn)
@@ -813,9 +791,9 @@ _dec_done_\@:
         sub	$16, %r10
         # Determine if if partial block is not being filled and
         # shift mask accordingly
-        jge	_no_extra_mask_2_\@
+        jge	.L_no_extra_mask_2_\@
         sub	%r10, %r12
-_no_extra_mask_2_\@:
+.L_no_extra_mask_2_\@:
 
         vmovdqu	ALL_F-SHIFT_MASK(%r12), %xmm1
         # get the appropriate mask to mask out bottom r13 bytes of xmm9
@@ -827,17 +805,17 @@ _no_extra_mask_2_\@:
         vpxor	%xmm9, \AAD_HASH, \AAD_HASH
 
         test	%r10, %r10
-        jl	_partial_incomplete_2_\@
+        jl	.L_partial_incomplete_2_\@
 
         # GHASH computation for the last <16 Byte block
         \GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
         xor	%eax,%eax
 
         mov	%rax, PBlockLen(arg2)
-        jmp	_encode_done_\@
-_partial_incomplete_2_\@:
+        jmp	.L_encode_done_\@
+.L_partial_incomplete_2_\@:
         add	\PLAIN_CYPH_LEN, PBlockLen(arg2)
-_encode_done_\@:
+.L_encode_done_\@:
         vmovdqu	\AAD_HASH, AadHash(arg2)
 
         vmovdqa	SHUF_MASK(%rip), %xmm10
@@ -847,32 +825,32 @@ _encode_done_\@:
 .endif
         # output encrypted Bytes
         test	%r10, %r10
-        jl	_partial_fill_\@
+        jl	.L_partial_fill_\@
         mov	%r13, %r12
         mov	$16, %r13
         # Set r13 to be the number of bytes to write out
         sub	%r12, %r13
-        jmp	_count_set_\@
-_partial_fill_\@:
+        jmp	.L_count_set_\@
+.L_partial_fill_\@:
         mov	\PLAIN_CYPH_LEN, %r13
-_count_set_\@:
+.L_count_set_\@:
         vmovdqa	%xmm9, %xmm0
         vmovq	%xmm0, %rax
         cmp	$8, %r13
-        jle	_less_than_8_bytes_left_\@
+        jle	.L_less_than_8_bytes_left_\@
 
         mov	%rax, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
         add	$8, \DATA_OFFSET
         psrldq	$8, %xmm0
         vmovq	%xmm0, %rax
         sub	$8, %r13
-_less_than_8_bytes_left_\@:
+.L_less_than_8_bytes_left_\@:
         movb	%al, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
         add	$1, \DATA_OFFSET
         shr	$8, %rax
         sub	$1, %r13
-        jne	_less_than_8_bytes_left_\@
-_partial_block_done_\@:
+        jne	.L_less_than_8_bytes_left_\@
+.L_partial_block_done_\@:
 .endm # PARTIAL_BLOCK
 
 ###############################################################################
@@ -1073,7 +1051,7 @@ _partial_block_done_\@:
         vmovdqa  \XMM8, \T3
 
         cmp     $128, %r13
-        jl      _initial_blocks_done\@                  # no need for precomputed constants
+        jl      .L_initial_blocks_done\@                  # no need for precomputed constants
 
 ###############################################################################
 # Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
@@ -1215,7 +1193,7 @@ _partial_block_done_\@:
 
 ###############################################################################
 
-_initial_blocks_done\@:
+.L_initial_blocks_done\@:
 
 .endm
 
@@ -2023,7 +2001,7 @@ SYM_FUNC_END(aesni_gcm_finalize_avx_gen2)
         vmovdqa  \XMM8, \T3
 
         cmp     $128, %r13
-        jl      _initial_blocks_done\@                  # no need for precomputed constants
+        jl      .L_initial_blocks_done\@                  # no need for precomputed constants
 
 ###############################################################################
 # Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
@@ -2167,7 +2145,7 @@ SYM_FUNC_END(aesni_gcm_finalize_avx_gen2)
 
 ###############################################################################
 
-_initial_blocks_done\@:
+.L_initial_blocks_done\@:
 
 
 .endm
diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S
index 9243f6289d34..7c1abc513f34 100644
--- a/arch/x86/crypto/aria-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S
@@ -80,7 +80,7 @@
 	transpose_4x4(c0, c1, c2, c3, a0, a1);		\
 	transpose_4x4(d0, d1, d2, d3, a0, a1);		\
 							\
-	vmovdqu .Lshufb_16x16b, a0;			\
+	vmovdqu .Lshufb_16x16b(%rip), a0;		\
 	vmovdqu st1, a1;				\
 	vpshufb a0, a2, a2;				\
 	vpshufb a0, a3, a3;				\
@@ -132,7 +132,7 @@
 	transpose_4x4(c0, c1, c2, c3, a0, a1);		\
 	transpose_4x4(d0, d1, d2, d3, a0, a1);		\
 							\
-	vmovdqu .Lshufb_16x16b, a0;			\
+	vmovdqu .Lshufb_16x16b(%rip), a0;		\
 	vmovdqu st1, a1;				\
 	vpshufb a0, a2, a2;				\
 	vpshufb a0, a3, a3;				\
@@ -300,11 +300,11 @@
 			    x4, x5, x6, x7,		\
 			    t0, t1, t2, t3,		\
 			    t4, t5, t6, t7)		\
-	vmovdqa .Ltf_s2_bitmatrix, t0;			\
-	vmovdqa .Ltf_inv_bitmatrix, t1;			\
-	vmovdqa .Ltf_id_bitmatrix, t2;			\
-	vmovdqa .Ltf_aff_bitmatrix, t3;			\
-	vmovdqa .Ltf_x2_bitmatrix, t4;			\
+	vmovdqa .Ltf_s2_bitmatrix(%rip), t0;		\
+	vmovdqa .Ltf_inv_bitmatrix(%rip), t1;		\
+	vmovdqa .Ltf_id_bitmatrix(%rip), t2;		\
+	vmovdqa .Ltf_aff_bitmatrix(%rip), t3;		\
+	vmovdqa .Ltf_x2_bitmatrix(%rip), t4;		\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1;	\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5;	\
 	vgf2p8affineqb $(tf_inv_const), t1, x2, x2;	\
@@ -324,13 +324,13 @@
 		       x4, x5, x6, x7,			\
 		       t0, t1, t2, t3,			\
 		       t4, t5, t6, t7)			\
-	vmovdqa .Linv_shift_row, t0;			\
-	vmovdqa .Lshift_row, t1;			\
-	vbroadcastss .L0f0f0f0f, t6;			\
-	vmovdqa .Ltf_lo__inv_aff__and__s2, t2;		\
-	vmovdqa .Ltf_hi__inv_aff__and__s2, t3;		\
-	vmovdqa .Ltf_lo__x2__and__fwd_aff, t4;		\
-	vmovdqa .Ltf_hi__x2__and__fwd_aff, t5;		\
+	vmovdqa .Linv_shift_row(%rip), t0;		\
+	vmovdqa .Lshift_row(%rip), t1;			\
+	vbroadcastss .L0f0f0f0f(%rip), t6;		\
+	vmovdqa .Ltf_lo__inv_aff__and__s2(%rip), t2;	\
+	vmovdqa .Ltf_hi__inv_aff__and__s2(%rip), t3;	\
+	vmovdqa .Ltf_lo__x2__and__fwd_aff(%rip), t4;	\
+	vmovdqa .Ltf_hi__x2__and__fwd_aff(%rip), t5;	\
 							\
 	vaesenclast t7, x0, x0;				\
 	vaesenclast t7, x4, x4;				\
diff --git a/arch/x86/crypto/aria-aesni-avx2-asm_64.S b/arch/x86/crypto/aria-aesni-avx2-asm_64.S
index 82a14b4ad920..c60fa2980630 100644
--- a/arch/x86/crypto/aria-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/aria-aesni-avx2-asm_64.S
@@ -96,7 +96,7 @@
 	transpose_4x4(c0, c1, c2, c3, a0, a1);		\
 	transpose_4x4(d0, d1, d2, d3, a0, a1);		\
 							\
-	vbroadcasti128 .Lshufb_16x16b, a0;		\
+	vbroadcasti128 .Lshufb_16x16b(%rip), a0;	\
 	vmovdqu st1, a1;				\
 	vpshufb a0, a2, a2;				\
 	vpshufb a0, a3, a3;				\
@@ -148,7 +148,7 @@
 	transpose_4x4(c0, c1, c2, c3, a0, a1);		\
 	transpose_4x4(d0, d1, d2, d3, a0, a1);		\
 							\
-	vbroadcasti128 .Lshufb_16x16b, a0;		\
+	vbroadcasti128 .Lshufb_16x16b(%rip), a0;	\
 	vmovdqu st1, a1;				\
 	vpshufb a0, a2, a2;				\
 	vpshufb a0, a3, a3;				\
@@ -307,11 +307,11 @@
 			    x4, x5, x6, x7,		\
 			    t0, t1, t2, t3,		\
 			    t4, t5, t6, t7)		\
-	vpbroadcastq .Ltf_s2_bitmatrix, t0;		\
-	vpbroadcastq .Ltf_inv_bitmatrix, t1;		\
-	vpbroadcastq .Ltf_id_bitmatrix, t2;		\
-	vpbroadcastq .Ltf_aff_bitmatrix, t3;		\
-	vpbroadcastq .Ltf_x2_bitmatrix, t4;		\
+	vpbroadcastq .Ltf_s2_bitmatrix(%rip), t0;	\
+	vpbroadcastq .Ltf_inv_bitmatrix(%rip), t1;	\
+	vpbroadcastq .Ltf_id_bitmatrix(%rip), t2;	\
+	vpbroadcastq .Ltf_aff_bitmatrix(%rip), t3;	\
+	vpbroadcastq .Ltf_x2_bitmatrix(%rip), t4;	\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1;	\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5;	\
 	vgf2p8affineqb $(tf_inv_const), t1, x2, x2;	\
@@ -332,12 +332,12 @@
 		       t4, t5, t6, t7)			\
 	vpxor t7, t7, t7;				\
 	vpxor t6, t6, t6;				\
-	vbroadcasti128 .Linv_shift_row, t0;		\
-	vbroadcasti128 .Lshift_row, t1;			\
-	vbroadcasti128 .Ltf_lo__inv_aff__and__s2, t2;	\
-	vbroadcasti128 .Ltf_hi__inv_aff__and__s2, t3;	\
-	vbroadcasti128 .Ltf_lo__x2__and__fwd_aff, t4;	\
-	vbroadcasti128 .Ltf_hi__x2__and__fwd_aff, t5;	\
+	vbroadcasti128 .Linv_shift_row(%rip), t0;	\
+	vbroadcasti128 .Lshift_row(%rip), t1;		\
+	vbroadcasti128 .Ltf_lo__inv_aff__and__s2(%rip), t2; \
+	vbroadcasti128 .Ltf_hi__inv_aff__and__s2(%rip), t3; \
+	vbroadcasti128 .Ltf_lo__x2__and__fwd_aff(%rip), t4; \
+	vbroadcasti128 .Ltf_hi__x2__and__fwd_aff(%rip), t5; \
 							\
 	vextracti128 $1, x0, t6##_x;			\
 	vaesenclast t7##_x, x0##_x, x0##_x;		\
@@ -369,7 +369,7 @@
 	vaesdeclast t7##_x, t6##_x, t6##_x;		\
 	vinserti128 $1, t6##_x, x6, x6;			\
 							\
-	vpbroadcastd .L0f0f0f0f, t6;			\
+	vpbroadcastd .L0f0f0f0f(%rip), t6;		\
 							\
 	/* AES inverse shift rows */			\
 	vpshufb t0, x0, x0;				\
diff --git a/arch/x86/crypto/aria-gfni-avx512-asm_64.S b/arch/x86/crypto/aria-gfni-avx512-asm_64.S
index 3193f0701450..860887e5d02e 100644
--- a/arch/x86/crypto/aria-gfni-avx512-asm_64.S
+++ b/arch/x86/crypto/aria-gfni-avx512-asm_64.S
@@ -80,7 +80,7 @@
 	transpose_4x4(c0, c1, c2, c3, a0, a1);		\
 	transpose_4x4(d0, d1, d2, d3, a0, a1);		\
 							\
-	vbroadcasti64x2 .Lshufb_16x16b, a0;		\
+	vbroadcasti64x2 .Lshufb_16x16b(%rip), a0;	\
 	vmovdqu64 st1, a1;				\
 	vpshufb a0, a2, a2;				\
 	vpshufb a0, a3, a3;				\
@@ -132,7 +132,7 @@
 	transpose_4x4(c0, c1, c2, c3, a0, a1);		\
 	transpose_4x4(d0, d1, d2, d3, a0, a1);		\
 							\
-	vbroadcasti64x2 .Lshufb_16x16b, a0;		\
+	vbroadcasti64x2 .Lshufb_16x16b(%rip), a0;	\
 	vmovdqu64 st1, a1;				\
 	vpshufb a0, a2, a2;				\
 	vpshufb a0, a3, a3;				\
@@ -308,11 +308,11 @@
 			    x4, x5, x6, x7,		\
 			    t0, t1, t2, t3,		\
 			    t4, t5, t6, t7)		\
-	vpbroadcastq .Ltf_s2_bitmatrix, t0;		\
-	vpbroadcastq .Ltf_inv_bitmatrix, t1;		\
-	vpbroadcastq .Ltf_id_bitmatrix, t2;		\
-	vpbroadcastq .Ltf_aff_bitmatrix, t3;		\
-	vpbroadcastq .Ltf_x2_bitmatrix, t4;		\
+	vpbroadcastq .Ltf_s2_bitmatrix(%rip), t0;	\
+	vpbroadcastq .Ltf_inv_bitmatrix(%rip), t1;	\
+	vpbroadcastq .Ltf_id_bitmatrix(%rip), t2;	\
+	vpbroadcastq .Ltf_aff_bitmatrix(%rip), t3;	\
+	vpbroadcastq .Ltf_x2_bitmatrix(%rip), t4;	\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1;	\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5;	\
 	vgf2p8affineqb $(tf_inv_const), t1, x2, x2;	\
@@ -332,11 +332,11 @@
 			     y4, y5, y6, y7,		\
 			     t0, t1, t2, t3,		\
 			     t4, t5, t6, t7)		\
-	vpbroadcastq .Ltf_s2_bitmatrix, t0;		\
-	vpbroadcastq .Ltf_inv_bitmatrix, t1;		\
-	vpbroadcastq .Ltf_id_bitmatrix, t2;		\
-	vpbroadcastq .Ltf_aff_bitmatrix, t3;		\
-	vpbroadcastq .Ltf_x2_bitmatrix, t4;		\
+	vpbroadcastq .Ltf_s2_bitmatrix(%rip), t0;	\
+	vpbroadcastq .Ltf_inv_bitmatrix(%rip), t1;	\
+	vpbroadcastq .Ltf_id_bitmatrix(%rip), t2;	\
+	vpbroadcastq .Ltf_aff_bitmatrix(%rip), t3;	\
+	vpbroadcastq .Ltf_x2_bitmatrix(%rip), t4;	\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1;	\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5;	\
 	vgf2p8affineqb $(tf_inv_const), t1, x2, x2;	\
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index 4a30618281ec..646477a13e11 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -52,10 +52,10 @@
 	/* \
 	 * S-function with AES subbytes \
 	 */ \
-	vmovdqa .Linv_shift_row, t4; \
-	vbroadcastss .L0f0f0f0f, t7; \
-	vmovdqa .Lpre_tf_lo_s1, t0; \
-	vmovdqa .Lpre_tf_hi_s1, t1; \
+	vmovdqa .Linv_shift_row(%rip), t4; \
+	vbroadcastss .L0f0f0f0f(%rip), t7; \
+	vmovdqa .Lpre_tf_lo_s1(%rip), t0; \
+	vmovdqa .Lpre_tf_hi_s1(%rip), t1; \
 	\
 	/* AES inverse shift rows */ \
 	vpshufb t4, x0, x0; \
@@ -68,8 +68,8 @@
 	vpshufb t4, x6, x6; \
 	\
 	/* prefilter sboxes 1, 2 and 3 */ \
-	vmovdqa .Lpre_tf_lo_s4, t2; \
-	vmovdqa .Lpre_tf_hi_s4, t3; \
+	vmovdqa .Lpre_tf_lo_s4(%rip), t2; \
+	vmovdqa .Lpre_tf_hi_s4(%rip), t3; \
 	filter_8bit(x0, t0, t1, t7, t6); \
 	filter_8bit(x7, t0, t1, t7, t6); \
 	filter_8bit(x1, t0, t1, t7, t6); \
@@ -83,8 +83,8 @@
 	filter_8bit(x6, t2, t3, t7, t6); \
 	\
 	/* AES subbytes + AES shift rows */ \
-	vmovdqa .Lpost_tf_lo_s1, t0; \
-	vmovdqa .Lpost_tf_hi_s1, t1; \
+	vmovdqa .Lpost_tf_lo_s1(%rip), t0; \
+	vmovdqa .Lpost_tf_hi_s1(%rip), t1; \
 	vaesenclast t4, x0, x0; \
 	vaesenclast t4, x7, x7; \
 	vaesenclast t4, x1, x1; \
@@ -95,16 +95,16 @@
 	vaesenclast t4, x6, x6; \
 	\
 	/* postfilter sboxes 1 and 4 */ \
-	vmovdqa .Lpost_tf_lo_s3, t2; \
-	vmovdqa .Lpost_tf_hi_s3, t3; \
+	vmovdqa .Lpost_tf_lo_s3(%rip), t2; \
+	vmovdqa .Lpost_tf_hi_s3(%rip), t3; \
 	filter_8bit(x0, t0, t1, t7, t6); \
 	filter_8bit(x7, t0, t1, t7, t6); \
 	filter_8bit(x3, t0, t1, t7, t6); \
 	filter_8bit(x6, t0, t1, t7, t6); \
 	\
 	/* postfilter sbox 3 */ \
-	vmovdqa .Lpost_tf_lo_s2, t4; \
-	vmovdqa .Lpost_tf_hi_s2, t5; \
+	vmovdqa .Lpost_tf_lo_s2(%rip), t4; \
+	vmovdqa .Lpost_tf_hi_s2(%rip), t5; \
 	filter_8bit(x2, t2, t3, t7, t6); \
 	filter_8bit(x5, t2, t3, t7, t6); \
 	\
@@ -443,7 +443,7 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	transpose_4x4(c0, c1, c2, c3, a0, a1); \
 	transpose_4x4(d0, d1, d2, d3, a0, a1); \
 	\
-	vmovdqu .Lshufb_16x16b, a0; \
+	vmovdqu .Lshufb_16x16b(%rip), a0; \
 	vmovdqu st1, a1; \
 	vpshufb a0, a2, a2; \
 	vpshufb a0, a3, a3; \
@@ -482,7 +482,7 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 #define inpack16_pre(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
 		     y6, y7, rio, key) \
 	vmovq key, x0; \
-	vpshufb .Lpack_bswap, x0, x0; \
+	vpshufb .Lpack_bswap(%rip), x0, x0; \
 	\
 	vpxor 0 * 16(rio), x0, y7; \
 	vpxor 1 * 16(rio), x0, y6; \
@@ -533,7 +533,7 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	vmovdqu x0, stack_tmp0; \
 	\
 	vmovq key, x0; \
-	vpshufb .Lpack_bswap, x0, x0; \
+	vpshufb .Lpack_bswap(%rip), x0, x0; \
 	\
 	vpxor x0, y7, y7; \
 	vpxor x0, y6, y6; \
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index deaf62aa73a6..a0eb94e53b1b 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -64,12 +64,12 @@
 	/* \
 	 * S-function with AES subbytes \
 	 */ \
-	vbroadcasti128 .Linv_shift_row, t4; \
-	vpbroadcastd .L0f0f0f0f, t7; \
-	vbroadcasti128 .Lpre_tf_lo_s1, t5; \
-	vbroadcasti128 .Lpre_tf_hi_s1, t6; \
-	vbroadcasti128 .Lpre_tf_lo_s4, t2; \
-	vbroadcasti128 .Lpre_tf_hi_s4, t3; \
+	vbroadcasti128 .Linv_shift_row(%rip), t4; \
+	vpbroadcastd .L0f0f0f0f(%rip), t7; \
+	vbroadcasti128 .Lpre_tf_lo_s1(%rip), t5; \
+	vbroadcasti128 .Lpre_tf_hi_s1(%rip), t6; \
+	vbroadcasti128 .Lpre_tf_lo_s4(%rip), t2; \
+	vbroadcasti128 .Lpre_tf_hi_s4(%rip), t3; \
 	\
 	/* AES inverse shift rows */ \
 	vpshufb t4, x0, x0; \
@@ -115,8 +115,8 @@
 	vinserti128 $1, t2##_x, x6, x6; \
 	vextracti128 $1, x1, t3##_x; \
 	vextracti128 $1, x4, t2##_x; \
-	vbroadcasti128 .Lpost_tf_lo_s1, t0; \
-	vbroadcasti128 .Lpost_tf_hi_s1, t1; \
+	vbroadcasti128 .Lpost_tf_lo_s1(%rip), t0; \
+	vbroadcasti128 .Lpost_tf_hi_s1(%rip), t1; \
 	vaesenclast t4##_x, x2##_x, x2##_x; \
 	vaesenclast t4##_x, t6##_x, t6##_x; \
 	vinserti128 $1, t6##_x, x2, x2; \
@@ -131,16 +131,16 @@
 	vinserti128 $1, t2##_x, x4, x4; \
 	\
 	/* postfilter sboxes 1 and 4 */ \
-	vbroadcasti128 .Lpost_tf_lo_s3, t2; \
-	vbroadcasti128 .Lpost_tf_hi_s3, t3; \
+	vbroadcasti128 .Lpost_tf_lo_s3(%rip), t2; \
+	vbroadcasti128 .Lpost_tf_hi_s3(%rip), t3; \
 	filter_8bit(x0, t0, t1, t7, t6); \
 	filter_8bit(x7, t0, t1, t7, t6); \
 	filter_8bit(x3, t0, t1, t7, t6); \
 	filter_8bit(x6, t0, t1, t7, t6); \
 	\
 	/* postfilter sbox 3 */ \
-	vbroadcasti128 .Lpost_tf_lo_s2, t4; \
-	vbroadcasti128 .Lpost_tf_hi_s2, t5; \
+	vbroadcasti128 .Lpost_tf_lo_s2(%rip), t4; \
+	vbroadcasti128 .Lpost_tf_hi_s2(%rip), t5; \
 	filter_8bit(x2, t2, t3, t7, t6); \
 	filter_8bit(x5, t2, t3, t7, t6); \
 	\
@@ -475,7 +475,7 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	transpose_4x4(c0, c1, c2, c3, a0, a1); \
 	transpose_4x4(d0, d1, d2, d3, a0, a1); \
 	\
-	vbroadcasti128 .Lshufb_16x16b, a0; \
+	vbroadcasti128 .Lshufb_16x16b(%rip), a0; \
 	vmovdqu st1, a1; \
 	vpshufb a0, a2, a2; \
 	vpshufb a0, a3, a3; \
@@ -514,7 +514,7 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 #define inpack32_pre(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
 		     y6, y7, rio, key) \
 	vpbroadcastq key, x0; \
-	vpshufb .Lpack_bswap, x0, x0; \
+	vpshufb .Lpack_bswap(%rip), x0, x0; \
 	\
 	vpxor 0 * 32(rio), x0, y7; \
 	vpxor 1 * 32(rio), x0, y6; \
@@ -565,7 +565,7 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	vmovdqu x0, stack_tmp0; \
 	\
 	vpbroadcastq key, x0; \
-	vpshufb .Lpack_bswap, x0, x0; \
+	vpshufb .Lpack_bswap(%rip), x0, x0; \
 	\
 	vpxor x0, y7, y7; \
 	vpxor x0, y6, y6; \
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 347c059f5940..816b6bb8bded 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -77,11 +77,13 @@
 #define RXORbl %r9b
 
 #define xor2ror16(T0, T1, tmp1, tmp2, ab, dst) \
+	leaq T0(%rip), 			tmp1; \
 	movzbl ab ## bl,		tmp2 ## d; \
+	xorq (tmp1, tmp2, 8),		dst; \
+	leaq T1(%rip), 			tmp2; \
 	movzbl ab ## bh,		tmp1 ## d; \
 	rorq $16,			ab; \
-	xorq T0(, tmp2, 8),		dst; \
-	xorq T1(, tmp1, 8),		dst;
+	xorq (tmp2, tmp1, 8),		dst;
 
 /**********************************************************************
   1-way camellia
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index 0326a01503c3..b4e460a87f18 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -84,15 +84,19 @@
 
 #define lookup_32bit(src, dst, op1, op2, op3, interleave_op, il_reg) \
 	movzbl		src ## bh,     RID1d;    \
+	leaq		s1(%rip),      RID2;     \
+	movl		(RID2,RID1,4), dst ## d; \
 	movzbl		src ## bl,     RID2d;    \
+	leaq		s2(%rip),      RID1;     \
+	op1		(RID1,RID2,4), dst ## d; \
 	shrq $16,	src;                     \
-	movl		s1(, RID1, 4), dst ## d; \
-	op1		s2(, RID2, 4), dst ## d; \
 	movzbl		src ## bh,     RID1d;    \
+	leaq		s3(%rip),      RID2;     \
+	op2		(RID2,RID1,4), dst ## d; \
 	movzbl		src ## bl,     RID2d;    \
 	interleave_op(il_reg);			 \
-	op2		s3(, RID1, 4), dst ## d; \
-	op3		s4(, RID2, 4), dst ## d;
+	leaq		s4(%rip),      RID1;     \
+	op3		(RID1,RID2,4), dst ## d;
 
 #define dummy(d) /* do nothing */
 
@@ -151,15 +155,15 @@
 	subround(l ## 3, r ## 3, l ## 4, r ## 4, f);
 
 #define enc_preload_rkr() \
-	vbroadcastss	.L16_mask,                RKR;      \
+	vbroadcastss	.L16_mask(%rip),          RKR;      \
 	/* add 16-bit rotation to key rotations (mod 32) */ \
 	vpxor		kr(CTX),                  RKR, RKR;
 
 #define dec_preload_rkr() \
-	vbroadcastss	.L16_mask,                RKR;      \
+	vbroadcastss	.L16_mask(%rip),          RKR;      \
 	/* add 16-bit rotation to key rotations (mod 32) */ \
 	vpxor		kr(CTX),                  RKR, RKR; \
-	vpshufb		.Lbswap128_mask,          RKR, RKR;
+	vpshufb		.Lbswap128_mask(%rip),    RKR, RKR;
 
 #define transpose_2x4(x0, x1, t0, t1) \
 	vpunpckldq		x1, x0, t0; \
@@ -235,9 +239,9 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 
 	movq %rdi, CTX;
 
-	vmovdqa .Lbswap_mask, RKM;
-	vmovd .Lfirst_mask, R1ST;
-	vmovd .L32_mask, R32;
+	vmovdqa .Lbswap_mask(%rip), RKM;
+	vmovd .Lfirst_mask(%rip), R1ST;
+	vmovd .L32_mask(%rip), R32;
 	enc_preload_rkr();
 
 	inpack_blocks(RL1, RR1, RTMP, RX, RKM);
@@ -271,7 +275,7 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 	popq %rbx;
 	popq %r15;
 
-	vmovdqa .Lbswap_mask, RKM;
+	vmovdqa .Lbswap_mask(%rip), RKM;
 
 	outunpack_blocks(RR1, RL1, RTMP, RX, RKM);
 	outunpack_blocks(RR2, RL2, RTMP, RX, RKM);
@@ -308,9 +312,9 @@ SYM_FUNC_START_LOCAL(__cast5_dec_blk16)
 
 	movq %rdi, CTX;
 
-	vmovdqa .Lbswap_mask, RKM;
-	vmovd .Lfirst_mask, R1ST;
-	vmovd .L32_mask, R32;
+	vmovdqa .Lbswap_mask(%rip), RKM;
+	vmovd .Lfirst_mask(%rip), R1ST;
+	vmovd .L32_mask(%rip), R32;
 	dec_preload_rkr();
 
 	inpack_blocks(RL1, RR1, RTMP, RX, RKM);
@@ -341,7 +345,7 @@ SYM_FUNC_START_LOCAL(__cast5_dec_blk16)
 	round(RL, RR, 1, 2);
 	round(RR, RL, 0, 1);
 
-	vmovdqa .Lbswap_mask, RKM;
+	vmovdqa .Lbswap_mask(%rip), RKM;
 	popq %rbx;
 	popq %r15;
 
@@ -504,8 +508,8 @@ SYM_FUNC_START(cast5_ctr_16way)
 
 	vpcmpeqd RKR, RKR, RKR;
 	vpaddq RKR, RKR, RKR; /* low: -2, high: -2 */
-	vmovdqa .Lbswap_iv_mask, R1ST;
-	vmovdqa .Lbswap128_mask, RKM;
+	vmovdqa .Lbswap_iv_mask(%rip), R1ST;
+	vmovdqa .Lbswap128_mask(%rip), RKM;
 
 	/* load IV and byteswap */
 	vmovq (%rcx), RX;
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index 82b716fd5dba..9e86d460b409 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -84,15 +84,19 @@
 
 #define lookup_32bit(src, dst, op1, op2, op3, interleave_op, il_reg) \
 	movzbl		src ## bh,     RID1d;    \
+	leaq		s1(%rip),      RID2;     \
+	movl		(RID2,RID1,4), dst ## d; \
 	movzbl		src ## bl,     RID2d;    \
+	leaq		s2(%rip),      RID1;     \
+	op1		(RID1,RID2,4), dst ## d; \
 	shrq $16,	src;                     \
-	movl		s1(, RID1, 4), dst ## d; \
-	op1		s2(, RID2, 4), dst ## d; \
 	movzbl		src ## bh,     RID1d;    \
+	leaq		s3(%rip),      RID2;     \
+	op2		(RID2,RID1,4), dst ## d; \
 	movzbl		src ## bl,     RID2d;    \
 	interleave_op(il_reg);			 \
-	op2		s3(, RID1, 4), dst ## d; \
-	op3		s4(, RID2, 4), dst ## d;
+	leaq		s4(%rip),      RID1;     \
+	op3		(RID1,RID2,4), dst ## d;
 
 #define dummy(d) /* do nothing */
 
@@ -175,10 +179,10 @@
 	qop(RD, RC, 1);
 
 #define shuffle(mask) \
-	vpshufb		mask,            RKR, RKR;
+	vpshufb		mask(%rip),            RKR, RKR;
 
 #define preload_rkr(n, do_mask, mask) \
-	vbroadcastss	.L16_mask,                RKR;      \
+	vbroadcastss	.L16_mask(%rip),          RKR;      \
 	/* add 16-bit rotation to key rotations (mod 32) */ \
 	vpxor		(kr+n*16)(CTX),           RKR, RKR; \
 	do_mask(mask);
@@ -258,9 +262,9 @@ SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
 
 	movq %rdi, CTX;
 
-	vmovdqa .Lbswap_mask, RKM;
-	vmovd .Lfirst_mask, R1ST;
-	vmovd .L32_mask, R32;
+	vmovdqa .Lbswap_mask(%rip), RKM;
+	vmovd .Lfirst_mask(%rip), R1ST;
+	vmovd .L32_mask(%rip), R32;
 
 	inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -284,7 +288,7 @@ SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
 	popq %rbx;
 	popq %r15;
 
-	vmovdqa .Lbswap_mask, RKM;
+	vmovdqa .Lbswap_mask(%rip), RKM;
 
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -306,9 +310,9 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
 
 	movq %rdi, CTX;
 
-	vmovdqa .Lbswap_mask, RKM;
-	vmovd .Lfirst_mask, R1ST;
-	vmovd .L32_mask, R32;
+	vmovdqa .Lbswap_mask(%rip), RKM;
+	vmovd .Lfirst_mask(%rip), R1ST;
+	vmovd .L32_mask(%rip), R32;
 
 	inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -332,7 +336,7 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
 	popq %rbx;
 	popq %r15;
 
-	vmovdqa .Lbswap_mask, RKM;
+	vmovdqa .Lbswap_mask(%rip), RKM;
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
index ca53e96996ac..5d31137e2c7d 100644
--- a/arch/x86/crypto/crc32-pclmul_asm.S
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -90,7 +90,7 @@ SYM_FUNC_START(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligne
 	sub     $0x40, LEN
 	add     $0x40, BUF
 	cmp     $0x40, LEN
-	jb      less_64
+	jb      .Lless_64
 
 #ifdef __x86_64__
 	movdqa .Lconstant_R2R1(%rip), CONSTANT
@@ -98,7 +98,7 @@ SYM_FUNC_START(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligne
 	movdqa .Lconstant_R2R1, CONSTANT
 #endif
 
-loop_64:/*  64 bytes Full cache line folding */
+.Lloop_64:/*  64 bytes Full cache line folding */
 	prefetchnta    0x40(BUF)
 	movdqa  %xmm1, %xmm5
 	movdqa  %xmm2, %xmm6
@@ -139,8 +139,8 @@ loop_64:/*  64 bytes Full cache line folding */
 	sub     $0x40, LEN
 	add     $0x40, BUF
 	cmp     $0x40, LEN
-	jge     loop_64
-less_64:/*  Folding cache line into 128bit */
+	jge     .Lloop_64
+.Lless_64:/*  Folding cache line into 128bit */
 #ifdef __x86_64__
 	movdqa  .Lconstant_R4R3(%rip), CONSTANT
 #else
@@ -167,8 +167,8 @@ less_64:/*  Folding cache line into 128bit */
 	pxor    %xmm4, %xmm1
 
 	cmp     $0x10, LEN
-	jb      fold_64
-loop_16:/* Folding rest buffer into 128bit */
+	jb      .Lfold_64
+.Lloop_16:/* Folding rest buffer into 128bit */
 	movdqa  %xmm1, %xmm5
 	pclmulqdq $0x00, CONSTANT, %xmm1
 	pclmulqdq $0x11, CONSTANT, %xmm5
@@ -177,9 +177,9 @@ loop_16:/* Folding rest buffer into 128bit */
 	sub     $0x10, LEN
 	add     $0x10, BUF
 	cmp     $0x10, LEN
-	jge     loop_16
+	jge     .Lloop_16
 
-fold_64:
+.Lfold_64:
 	/* perform the last 64 bit fold, also adds 32 zeroes
 	 * to the input stream */
 	pclmulqdq $0x01, %xmm1, CONSTANT /* R4 * xmm1.low */
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index ec35915f0901..81ce0f4db555 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -49,15 +49,15 @@
 ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
 
 .macro LABEL prefix n
-\prefix\n\():
+.L\prefix\n\():
 .endm
 
 .macro JMPTBL_ENTRY i
-.quad crc_\i
+.quad .Lcrc_\i
 .endm
 
 .macro JNC_LESS_THAN j
-	jnc less_than_\j
+	jnc .Lless_than_\j
 .endm
 
 # Define threshold where buffers are considered "small" and routed to more
@@ -108,30 +108,30 @@ SYM_FUNC_START(crc_pcl)
 	neg     %bufp
 	and     $7, %bufp		# calculate the unalignment amount of
 					# the address
-	je      proc_block		# Skip if aligned
+	je      .Lproc_block		# Skip if aligned
 
 	## If len is less than 8 and we're unaligned, we need to jump
 	## to special code to avoid reading beyond the end of the buffer
 	cmp     $8, len
-	jae     do_align
+	jae     .Ldo_align
 	# less_than_8 expects length in upper 3 bits of len_dw
 	# less_than_8_post_shl1 expects length = carryflag * 8 + len_dw[31:30]
 	shl     $32-3+1, len_dw
-	jmp     less_than_8_post_shl1
+	jmp     .Lless_than_8_post_shl1
 
-do_align:
+.Ldo_align:
 	#### Calculate CRC of unaligned bytes of the buffer (if any)
 	movq    (bufptmp), tmp		# load a quadward from the buffer
 	add     %bufp, bufptmp		# align buffer pointer for quadword
 					# processing
 	sub     %bufp, len		# update buffer length
-align_loop:
+.Lalign_loop:
 	crc32b  %bl, crc_init_dw 	# compute crc32 of 1-byte
 	shr     $8, tmp			# get next byte
 	dec     %bufp
-	jne     align_loop
+	jne     .Lalign_loop
 
-proc_block:
+.Lproc_block:
 
 	################################################################
 	## 2) PROCESS  BLOCKS:
@@ -141,11 +141,11 @@ proc_block:
 	movq    len, tmp		# save num bytes in tmp
 
 	cmpq    $128*24, len
-	jae     full_block
+	jae     .Lfull_block
 
-continue_block:
+.Lcontinue_block:
 	cmpq    $SMALL_SIZE, len
-	jb      small
+	jb      .Lsmall
 
 	## len < 128*24
 	movq    $2731, %rax		# 2731 = ceil(2^16 / 24)
@@ -168,13 +168,14 @@ continue_block:
 	xor     crc2, crc2
 
 	## branch into array
-	mov	jump_table(,%rax,8), %bufp
+	leaq	jump_table(%rip), %bufp
+	mov	(%bufp,%rax,8), %bufp
 	JMP_NOSPEC bufp
 
 	################################################################
 	## 2a) PROCESS FULL BLOCKS:
 	################################################################
-full_block:
+.Lfull_block:
 	movl    $128,%eax
 	lea     128*8*2(block_0), block_1
 	lea     128*8*3(block_0), block_2
@@ -189,7 +190,6 @@ full_block:
 	## 3) CRC Array:
 	################################################################
 
-crc_array:
 	i=128
 .rept 128-1
 .altmacro
@@ -242,28 +242,28 @@ LABEL crc_ 0
 	ENDBR
 	mov     tmp, len
 	cmp     $128*24, tmp
-	jae     full_block
+	jae     .Lfull_block
 	cmp     $24, tmp
-	jae     continue_block
+	jae     .Lcontinue_block
 
-less_than_24:
+.Lless_than_24:
 	shl     $32-4, len_dw			# less_than_16 expects length
 						# in upper 4 bits of len_dw
-	jnc     less_than_16
+	jnc     .Lless_than_16
 	crc32q  (bufptmp), crc_init
 	crc32q  8(bufptmp), crc_init
-	jz      do_return
+	jz      .Ldo_return
 	add     $16, bufptmp
 	# len is less than 8 if we got here
 	# less_than_8 expects length in upper 3 bits of len_dw
 	# less_than_8_post_shl1 expects length = carryflag * 8 + len_dw[31:30]
 	shl     $2, len_dw
-	jmp     less_than_8_post_shl1
+	jmp     .Lless_than_8_post_shl1
 
 	#######################################################################
 	## 6) LESS THAN 256-bytes REMAIN AT THIS POINT (8-bits of len are full)
 	#######################################################################
-small:
+.Lsmall:
 	shl $32-8, len_dw		# Prepare len_dw for less_than_256
 	j=256
 .rept 5					# j = {256, 128, 64, 32, 16}
@@ -279,32 +279,32 @@ LABEL less_than_ %j			# less_than_j: Length should be in
 	crc32q  i(bufptmp), crc_init	# Compute crc32 of 8-byte data
 	i=i+8
 .endr
-	jz      do_return		# Return if remaining length is zero
+	jz      .Ldo_return		# Return if remaining length is zero
 	add     $j, bufptmp		# Advance buf
 .endr
 
-less_than_8:				# Length should be stored in
+.Lless_than_8:				# Length should be stored in
 					# upper 3 bits of len_dw
 	shl     $1, len_dw
-less_than_8_post_shl1:
-	jnc     less_than_4
+.Lless_than_8_post_shl1:
+	jnc     .Lless_than_4
 	crc32l  (bufptmp), crc_init_dw	# CRC of 4 bytes
-	jz      do_return		# return if remaining data is zero
+	jz      .Ldo_return		# return if remaining data is zero
 	add     $4, bufptmp
-less_than_4:				# Length should be stored in
+.Lless_than_4:				# Length should be stored in
 					# upper 2 bits of len_dw
 	shl     $1, len_dw
-	jnc     less_than_2
+	jnc     .Lless_than_2
 	crc32w  (bufptmp), crc_init_dw	# CRC of 2 bytes
-	jz      do_return		# return if remaining data is zero
+	jz      .Ldo_return		# return if remaining data is zero
 	add     $2, bufptmp
-less_than_2:				# Length should be stored in the MSB
+.Lless_than_2:				# Length should be stored in the MSB
 					# of len_dw
 	shl     $1, len_dw
-	jnc     less_than_1
+	jnc     .Lless_than_1
 	crc32b  (bufptmp), crc_init_dw	# CRC of 1 byte
-less_than_1:				# Length should be zero
-do_return:
+.Lless_than_1:				# Length should be zero
+.Ldo_return:
 	movq    crc_init, %rax
 	popq    %rsi
 	popq    %rdi
diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S
index f4c760f4cade..cf21b998e77c 100644
--- a/arch/x86/crypto/des3_ede-asm_64.S
+++ b/arch/x86/crypto/des3_ede-asm_64.S
@@ -129,21 +129,29 @@
 	movzbl RW0bl, RT2d; \
 	movzbl RW0bh, RT3d; \
 	shrq $16, RW0; \
-	movq s8(, RT0, 8), RT0; \
-	xorq s6(, RT1, 8), to; \
+	leaq s8(%rip), RW1; \
+	movq (RW1, RT0, 8), RT0; \
+	leaq s6(%rip), RW1; \
+	xorq (RW1, RT1, 8), to; \
 	movzbl RW0bl, RL1d; \
 	movzbl RW0bh, RT1d; \
 	shrl $16, RW0d; \
-	xorq s4(, RT2, 8), RT0; \
-	xorq s2(, RT3, 8), to; \
+	leaq s4(%rip), RW1; \
+	xorq (RW1, RT2, 8), RT0; \
+	leaq s2(%rip), RW1; \
+	xorq (RW1, RT3, 8), to; \
 	movzbl RW0bl, RT2d; \
 	movzbl RW0bh, RT3d; \
-	xorq s7(, RL1, 8), RT0; \
-	xorq s5(, RT1, 8), to; \
-	xorq s3(, RT2, 8), RT0; \
+	leaq s7(%rip), RW1; \
+	xorq (RW1, RL1, 8), RT0; \
+	leaq s5(%rip), RW1; \
+	xorq (RW1, RT1, 8), to; \
+	leaq s3(%rip), RW1; \
+	xorq (RW1, RT2, 8), RT0; \
 	load_next_key(n, RW0); \
 	xorq RT0, to; \
-	xorq s1(, RT3, 8), to; \
+	leaq s1(%rip), RW1; \
+	xorq (RW1, RT3, 8), to; \
 
 #define load_next_key(n, RWx) \
 	movq (((n) + 1) * 8)(CTX), RWx;
@@ -355,65 +363,89 @@ SYM_FUNC_END(des3_ede_x86_64_crypt_blk)
 	movzbl RW0bl, RT3d; \
 	movzbl RW0bh, RT1d; \
 	shrq $16, RW0; \
-	xorq s8(, RT3, 8), to##0; \
-	xorq s6(, RT1, 8), to##0; \
+	leaq s8(%rip), RT2; \
+	xorq (RT2, RT3, 8), to##0; \
+	leaq s6(%rip), RT2; \
+	xorq (RT2, RT1, 8), to##0; \
 	movzbl RW0bl, RT3d; \
 	movzbl RW0bh, RT1d; \
 	shrq $16, RW0; \
-	xorq s4(, RT3, 8), to##0; \
-	xorq s2(, RT1, 8), to##0; \
+	leaq s4(%rip), RT2; \
+	xorq (RT2, RT3, 8), to##0; \
+	leaq s2(%rip), RT2; \
+	xorq (RT2, RT1, 8), to##0; \
 	movzbl RW0bl, RT3d; \
 	movzbl RW0bh, RT1d; \
 	shrl $16, RW0d; \
-	xorq s7(, RT3, 8), to##0; \
-	xorq s5(, RT1, 8), to##0; \
+	leaq s7(%rip), RT2; \
+	xorq (RT2, RT3, 8), to##0; \
+	leaq s5(%rip), RT2; \
+	xorq (RT2, RT1, 8), to##0; \
 	movzbl RW0bl, RT3d; \
 	movzbl RW0bh, RT1d; \
 	load_next_key(n, RW0); \
-	xorq s3(, RT3, 8), to##0; \
-	xorq s1(, RT1, 8), to##0; \
+	leaq s3(%rip), RT2; \
+	xorq (RT2, RT3, 8), to##0; \
+	leaq s1(%rip), RT2; \
+	xorq (RT2, RT1, 8), to##0; \
 		xorq from##1, RW1; \
 		movzbl RW1bl, RT3d; \
 		movzbl RW1bh, RT1d; \
 		shrq $16, RW1; \
-		xorq s8(, RT3, 8), to##1; \
-		xorq s6(, RT1, 8), to##1; \
+		leaq s8(%rip), RT2; \
+		xorq (RT2, RT3, 8), to##1; \
+		leaq s6(%rip), RT2; \
+		xorq (RT2, RT1, 8), to##1; \
 		movzbl RW1bl, RT3d; \
 		movzbl RW1bh, RT1d; \
 		shrq $16, RW1; \
-		xorq s4(, RT3, 8), to##1; \
-		xorq s2(, RT1, 8), to##1; \
+		leaq s4(%rip), RT2; \
+		xorq (RT2, RT3, 8), to##1; \
+		leaq s2(%rip), RT2; \
+		xorq (RT2, RT1, 8), to##1; \
 		movzbl RW1bl, RT3d; \
 		movzbl RW1bh, RT1d; \
 		shrl $16, RW1d; \
-		xorq s7(, RT3, 8), to##1; \
-		xorq s5(, RT1, 8), to##1; \
+		leaq s7(%rip), RT2; \
+		xorq (RT2, RT3, 8), to##1; \
+		leaq s5(%rip), RT2; \
+		xorq (RT2, RT1, 8), to##1; \
 		movzbl RW1bl, RT3d; \
 		movzbl RW1bh, RT1d; \
 		do_movq(RW0, RW1); \
-		xorq s3(, RT3, 8), to##1; \
-		xorq s1(, RT1, 8), to##1; \
+		leaq s3(%rip), RT2; \
+		xorq (RT2, RT3, 8), to##1; \
+		leaq s1(%rip), RT2; \
+		xorq (RT2, RT1, 8), to##1; \
 			xorq from##2, RW2; \
 			movzbl RW2bl, RT3d; \
 			movzbl RW2bh, RT1d; \
 			shrq $16, RW2; \
-			xorq s8(, RT3, 8), to##2; \
-			xorq s6(, RT1, 8), to##2; \
+			leaq s8(%rip), RT2; \
+			xorq (RT2, RT3, 8), to##2; \
+			leaq s6(%rip), RT2; \
+			xorq (RT2, RT1, 8), to##2; \
 			movzbl RW2bl, RT3d; \
 			movzbl RW2bh, RT1d; \
 			shrq $16, RW2; \
-			xorq s4(, RT3, 8), to##2; \
-			xorq s2(, RT1, 8), to##2; \
+			leaq s4(%rip), RT2; \
+			xorq (RT2, RT3, 8), to##2; \
+			leaq s2(%rip), RT2; \
+			xorq (RT2, RT1, 8), to##2; \
 			movzbl RW2bl, RT3d; \
 			movzbl RW2bh, RT1d; \
 			shrl $16, RW2d; \
-			xorq s7(, RT3, 8), to##2; \
-			xorq s5(, RT1, 8), to##2; \
+			leaq s7(%rip), RT2; \
+			xorq (RT2, RT3, 8), to##2; \
+			leaq s5(%rip), RT2; \
+			xorq (RT2, RT1, 8), to##2; \
 			movzbl RW2bl, RT3d; \
 			movzbl RW2bh, RT1d; \
 			do_movq(RW0, RW2); \
-			xorq s3(, RT3, 8), to##2; \
-			xorq s1(, RT1, 8), to##2;
+			leaq s3(%rip), RT2; \
+			xorq (RT2, RT3, 8), to##2; \
+			leaq s1(%rip), RT2; \
+			xorq (RT2, RT1, 8), to##2;
 
 #define __movq(src, dst) \
 	movq src, dst;
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 257ed9446f3e..99cb983ded9e 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -93,7 +93,7 @@ SYM_FUNC_START(clmul_ghash_mul)
 	FRAME_BEGIN
 	movups (%rdi), DATA
 	movups (%rsi), SHASH
-	movaps .Lbswap_mask, BSWAP
+	movaps .Lbswap_mask(%rip), BSWAP
 	pshufb BSWAP, DATA
 	call __clmul_gf128mul_ble
 	pshufb BSWAP, DATA
@@ -110,7 +110,7 @@ SYM_FUNC_START(clmul_ghash_update)
 	FRAME_BEGIN
 	cmp $16, %rdx
 	jb .Lupdate_just_ret	# check length
-	movaps .Lbswap_mask, BSWAP
+	movaps .Lbswap_mask(%rip), BSWAP
 	movups (%rdi), DATA
 	movups (%rcx), SHASH
 	pshufb BSWAP, DATA
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index a96b2fd26dab..4b49bdc95265 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -485,18 +485,18 @@
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
-_loop:
+.L_loop:
 	/*
 	 * code loops through more than one block
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
 	test BLOCKS_CTR, BLOCKS_CTR
-	jnz _begin
+	jnz .L_begin
 	.align 32
-	jmp	_end
+	jmp	.L_end
 	.align 32
-_begin:
+.L_begin:
 
 	/*
 	 * Do first block
@@ -508,9 +508,6 @@ _begin:
 		.set j, j+2
 	.endr
 
-	jmp _loop0
-_loop0:
-
 	/*
 	 * rounds:
 	 * 10,12,14,16,18
@@ -545,7 +542,7 @@ _loop0:
 	UPDATE_HASH	16(HASH_PTR), E
 
 	test	BLOCKS_CTR, BLOCKS_CTR
-	jz	_loop
+	jz	.L_loop
 
 	mov	TB, B
 
@@ -562,8 +559,6 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	jmp	_loop1
-_loop1:
 	/*
 	 * rounds
 	 * 20+80,22+80,24+80,26+80,28+80
@@ -574,9 +569,6 @@ _loop1:
 		.set j, j+2
 	.endr
 
-	jmp	_loop2
-_loop2:
-
 	/*
 	 * rounds
 	 * 40+80,42+80,44+80,46+80,48+80
@@ -592,9 +584,6 @@ _loop2:
 	/* Move to the next block only if needed*/
 	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
-	jmp	_loop3
-_loop3:
-
 	/*
 	 * rounds
 	 * 60+80,62+80,64+80,66+80,68+80
@@ -623,10 +612,10 @@ _loop3:
 
 	xchg	WK_BUF, PRECALC_BUF
 
-	jmp	_loop
+	jmp	.L_loop
 
 	.align 32
-	_end:
+.L_end:
 
 .endm
 /*
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index 5555b5d5215a..53de72bdd851 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/crypto/sha256-avx-asm.S
@@ -360,7 +360,7 @@ SYM_TYPED_FUNC_START(sha256_transform_avx)
 	and	$~15, %rsp		# align stack pointer
 
 	shl     $6, NUM_BLKS		# convert to bytes
-	jz      done_hash
+	jz      .Ldone_hash
 	add     INP, NUM_BLKS		# pointer to end of data
 	mov     NUM_BLKS, _INP_END(%rsp)
 
@@ -377,7 +377,7 @@ SYM_TYPED_FUNC_START(sha256_transform_avx)
 	vmovdqa  PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
 	vmovdqa  _SHUF_00BA(%rip), SHUF_00BA
 	vmovdqa  _SHUF_DC00(%rip), SHUF_DC00
-loop0:
+.Lloop0:
 	lea     K256(%rip), TBL
 
 	## byte swap first 16 dwords
@@ -391,7 +391,7 @@ loop0:
 	## schedule 48 input dwords, by doing 3 rounds of 16 each
 	mov     $3, SRND
 .align 16
-loop1:
+.Lloop1:
 	vpaddd  (TBL), X0, XFER
 	vmovdqa XFER, _XFER(%rsp)
 	FOUR_ROUNDS_AND_SCHED
@@ -410,10 +410,10 @@ loop1:
 	FOUR_ROUNDS_AND_SCHED
 
 	sub     $1, SRND
-	jne     loop1
+	jne     .Lloop1
 
 	mov     $2, SRND
-loop2:
+.Lloop2:
 	vpaddd  (TBL), X0, XFER
 	vmovdqa XFER, _XFER(%rsp)
 	DO_ROUND        0
@@ -433,7 +433,7 @@ loop2:
 	vmovdqa X3, X1
 
 	sub     $1, SRND
-	jne     loop2
+	jne     .Lloop2
 
 	addm    (4*0)(CTX),a
 	addm    (4*1)(CTX),b
@@ -447,9 +447,9 @@ loop2:
 	mov     _INP(%rsp), INP
 	add     $64, INP
 	cmp     _INP_END(%rsp), INP
-	jne     loop0
+	jne     .Lloop0
 
-done_hash:
+.Ldone_hash:
 
 	mov	%rbp, %rsp
 	popq	%rbp
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 3eada9416852..9918212faf91 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/crypto/sha256-avx2-asm.S
@@ -538,12 +538,12 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx)
 	and	$-32, %rsp	# align rsp to 32 byte boundary
 
 	shl	$6, NUM_BLKS	# convert to bytes
-	jz	done_hash
+	jz	.Ldone_hash
 	lea	-64(INP, NUM_BLKS), NUM_BLKS # pointer to last block
 	mov	NUM_BLKS, _INP_END(%rsp)
 
 	cmp	NUM_BLKS, INP
-	je	only_one_block
+	je	.Lonly_one_block
 
 	## load initial digest
 	mov	(CTX), a
@@ -561,7 +561,7 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx)
 
 	mov	CTX, _CTX(%rsp)
 
-loop0:
+.Lloop0:
 	## Load first 16 dwords from two blocks
 	VMOVDQ	0*32(INP),XTMP0
 	VMOVDQ	1*32(INP),XTMP1
@@ -580,7 +580,7 @@ loop0:
 	vperm2i128	$0x20, XTMP3, XTMP1, X2
 	vperm2i128	$0x31, XTMP3, XTMP1, X3
 
-last_block_enter:
+.Llast_block_enter:
 	add	$64, INP
 	mov	INP, _INP(%rsp)
 
@@ -588,34 +588,40 @@ last_block_enter:
 	xor	SRND, SRND
 
 .align 16
-loop1:
-	vpaddd	K256+0*32(SRND), X0, XFER
+.Lloop1:
+	leaq	K256+0*32(%rip), INP		## reuse INP as scratch reg
+	vpaddd	(INP, SRND), X0, XFER
 	vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 0*32
 
-	vpaddd	K256+1*32(SRND), X0, XFER
+	leaq	K256+1*32(%rip), INP
+	vpaddd	(INP, SRND), X0, XFER
 	vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 1*32
 
-	vpaddd	K256+2*32(SRND), X0, XFER
+	leaq	K256+2*32(%rip), INP
+	vpaddd	(INP, SRND), X0, XFER
 	vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 2*32
 
-	vpaddd	K256+3*32(SRND), X0, XFER
+	leaq	K256+3*32(%rip), INP
+	vpaddd	(INP, SRND), X0, XFER
 	vmovdqa XFER, 3*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 3*32
 
 	add	$4*32, SRND
 	cmp	$3*4*32, SRND
-	jb	loop1
+	jb	.Lloop1
 
-loop2:
+.Lloop2:
 	## Do last 16 rounds with no scheduling
-	vpaddd	K256+0*32(SRND), X0, XFER
+	leaq	K256+0*32(%rip), INP
+	vpaddd	(INP, SRND), X0, XFER
 	vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
 	DO_4ROUNDS	_XFER + 0*32
 
-	vpaddd	K256+1*32(SRND), X1, XFER
+	leaq	K256+1*32(%rip), INP
+	vpaddd	(INP, SRND), X1, XFER
 	vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
 	DO_4ROUNDS	_XFER + 1*32
 	add	$2*32, SRND
@@ -624,7 +630,7 @@ loop2:
 	vmovdqa	X3, X1
 
 	cmp	$4*4*32, SRND
-	jb	loop2
+	jb	.Lloop2
 
 	mov	_CTX(%rsp), CTX
 	mov	_INP(%rsp), INP
@@ -639,17 +645,17 @@ loop2:
 	addm    (4*7)(CTX),h
 
 	cmp	_INP_END(%rsp), INP
-	ja	done_hash
+	ja	.Ldone_hash
 
 	#### Do second block using previously scheduled results
 	xor	SRND, SRND
 .align 16
-loop3:
+.Lloop3:
 	DO_4ROUNDS	 _XFER + 0*32 + 16
 	DO_4ROUNDS	 _XFER + 1*32 + 16
 	add	$2*32, SRND
 	cmp	$4*4*32, SRND
-	jb	loop3
+	jb	.Lloop3
 
 	mov	_CTX(%rsp), CTX
 	mov	_INP(%rsp), INP
@@ -665,10 +671,10 @@ loop3:
 	addm    (4*7)(CTX),h
 
 	cmp	_INP_END(%rsp), INP
-	jb	loop0
-	ja	done_hash
+	jb	.Lloop0
+	ja	.Ldone_hash
 
-do_last_block:
+.Ldo_last_block:
 	VMOVDQ	0*16(INP),XWORD0
 	VMOVDQ	1*16(INP),XWORD1
 	VMOVDQ	2*16(INP),XWORD2
@@ -679,9 +685,9 @@ do_last_block:
 	vpshufb	X_BYTE_FLIP_MASK, XWORD2, XWORD2
 	vpshufb	X_BYTE_FLIP_MASK, XWORD3, XWORD3
 
-	jmp	last_block_enter
+	jmp	.Llast_block_enter
 
-only_one_block:
+.Lonly_one_block:
 
 	## load initial digest
 	mov	(4*0)(CTX),a
@@ -698,9 +704,9 @@ only_one_block:
 	vmovdqa	_SHUF_DC00(%rip), SHUF_DC00
 
 	mov	CTX, _CTX(%rsp)
-	jmp	do_last_block
+	jmp	.Ldo_last_block
 
-done_hash:
+.Ldone_hash:
 
 	mov	%rbp, %rsp
 	pop	%rbp
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index 959288eecc68..93264ee44543 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -369,7 +369,7 @@ SYM_TYPED_FUNC_START(sha256_transform_ssse3)
 	and	$~15, %rsp
 
 	shl     $6, NUM_BLKS		 # convert to bytes
-	jz      done_hash
+	jz      .Ldone_hash
 	add     INP, NUM_BLKS
 	mov     NUM_BLKS, _INP_END(%rsp) # pointer to end of data
 
@@ -387,7 +387,7 @@ SYM_TYPED_FUNC_START(sha256_transform_ssse3)
 	movdqa  _SHUF_00BA(%rip), SHUF_00BA
 	movdqa  _SHUF_DC00(%rip), SHUF_DC00
 
-loop0:
+.Lloop0:
 	lea     K256(%rip), TBL
 
 	## byte swap first 16 dwords
@@ -401,7 +401,7 @@ loop0:
 	## schedule 48 input dwords, by doing 3 rounds of 16 each
 	mov     $3, SRND
 .align 16
-loop1:
+.Lloop1:
 	movdqa  (TBL), XFER
 	paddd   X0, XFER
 	movdqa  XFER, _XFER(%rsp)
@@ -424,10 +424,10 @@ loop1:
 	FOUR_ROUNDS_AND_SCHED
 
 	sub     $1, SRND
-	jne     loop1
+	jne     .Lloop1
 
 	mov     $2, SRND
-loop2:
+.Lloop2:
 	paddd   (TBL), X0
 	movdqa  X0, _XFER(%rsp)
 	DO_ROUND        0
@@ -446,7 +446,7 @@ loop2:
 	movdqa  X3, X1
 
 	sub     $1, SRND
-	jne     loop2
+	jne     .Lloop2
 
 	addm    (4*0)(CTX),a
 	addm    (4*1)(CTX),b
@@ -460,9 +460,9 @@ loop2:
 	mov     _INP(%rsp), INP
 	add     $64, INP
 	cmp     _INP_END(%rsp), INP
-	jne     loop0
+	jne     .Lloop0
 
-done_hash:
+.Ldone_hash:
 
 	mov	%rbp, %rsp
 	popq	%rbp
diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S
index b0984f19fdb4..d902b8ea0721 100644
--- a/arch/x86/crypto/sha512-avx-asm.S
+++ b/arch/x86/crypto/sha512-avx-asm.S
@@ -276,7 +276,7 @@ frame_size = frame_WK + WK_SIZE
 ########################################################################
 SYM_TYPED_FUNC_START(sha512_transform_avx)
 	test msglen, msglen
-	je nowork
+	je .Lnowork
 
 	# Save GPRs
 	push	%rbx
@@ -291,7 +291,7 @@ SYM_TYPED_FUNC_START(sha512_transform_avx)
 	sub     $frame_size, %rsp
 	and	$~(0x20 - 1), %rsp
 
-updateblock:
+.Lupdateblock:
 
 	# Load state variables
 	mov     DIGEST(0), a_64
@@ -348,7 +348,7 @@ updateblock:
 	# Advance to next message block
 	add     $16*8, msg
 	dec     msglen
-	jnz     updateblock
+	jnz     .Lupdateblock
 
 	# Restore Stack Pointer
 	mov	%rbp, %rsp
@@ -361,7 +361,7 @@ updateblock:
 	pop	%r12
 	pop	%rbx
 
-nowork:
+.Lnowork:
 	RET
 SYM_FUNC_END(sha512_transform_avx)
 
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index b1ca99055ef9..f08496cd6870 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -581,7 +581,7 @@ SYM_TYPED_FUNC_START(sha512_transform_rorx)
 	and	$~(0x20 - 1), %rsp
 
 	shl	$7, NUM_BLKS	# convert to bytes
-	jz	done_hash
+	jz	.Ldone_hash
 	add	INP, NUM_BLKS	# pointer to end of data
 	mov	NUM_BLKS, frame_INPEND(%rsp)
 
@@ -600,7 +600,7 @@ SYM_TYPED_FUNC_START(sha512_transform_rorx)
 
 	vmovdqa	PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
 
-loop0:
+.Lloop0:
 	lea	K512(%rip), TBL
 
 	## byte swap first 16 dwords
@@ -615,7 +615,7 @@ loop0:
 	movq	$4, frame_SRND(%rsp)
 
 .align 16
-loop1:
+.Lloop1:
 	vpaddq	(TBL), Y_0, XFER
 	vmovdqa XFER, frame_XFER(%rsp)
 	FOUR_ROUNDS_AND_SCHED
@@ -634,10 +634,10 @@ loop1:
 	FOUR_ROUNDS_AND_SCHED
 
 	subq	$1, frame_SRND(%rsp)
-	jne	loop1
+	jne	.Lloop1
 
 	movq	$2, frame_SRND(%rsp)
-loop2:
+.Lloop2:
 	vpaddq	(TBL), Y_0, XFER
 	vmovdqa XFER, frame_XFER(%rsp)
 	DO_4ROUNDS
@@ -650,7 +650,7 @@ loop2:
 	vmovdqa	Y_3, Y_1
 
 	subq	$1, frame_SRND(%rsp)
-	jne	loop2
+	jne	.Lloop2
 
 	mov	frame_CTX(%rsp), CTX2
 	addm	8*0(CTX2), a
@@ -665,9 +665,9 @@ loop2:
 	mov	frame_INP(%rsp), INP
 	add	$128, INP
 	cmp	frame_INPEND(%rsp), INP
-	jne	loop0
+	jne	.Lloop0
 
-done_hash:
+.Ldone_hash:
 
 	# Restore Stack Pointer
 	mov	%rbp, %rsp
diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S
index c06afb5270e5..65be30156816 100644
--- a/arch/x86/crypto/sha512-ssse3-asm.S
+++ b/arch/x86/crypto/sha512-ssse3-asm.S
@@ -278,7 +278,7 @@ frame_size = frame_WK + WK_SIZE
 SYM_TYPED_FUNC_START(sha512_transform_ssse3)
 
 	test msglen, msglen
-	je nowork
+	je .Lnowork
 
 	# Save GPRs
 	push	%rbx
@@ -293,7 +293,7 @@ SYM_TYPED_FUNC_START(sha512_transform_ssse3)
 	sub	$frame_size, %rsp
 	and	$~(0x20 - 1), %rsp
 
-updateblock:
+.Lupdateblock:
 
 # Load state variables
 	mov	DIGEST(0), a_64
@@ -350,7 +350,7 @@ updateblock:
 	# Advance to next message block
 	add	$16*8, msg
 	dec	msglen
-	jnz	updateblock
+	jnz	.Lupdateblock
 
 	# Restore Stack Pointer
 	mov	%rbp, %rsp
@@ -363,7 +363,7 @@ updateblock:
 	pop	%r12
 	pop	%rbx
 
-nowork:
+.Lnowork:
 	RET
 SYM_FUNC_END(sha512_transform_ssse3)
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 52398d49bc2f..69ae5e1b3120 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -12,6 +12,7 @@
 #include <linux/kvm_host.h>
 #include <linux/kernel.h>
 #include <linux/highmem.h>
+#include <linux/psp.h>
 #include <linux/psp-sev.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
diff --git a/crypto/acompress.c b/crypto/acompress.c
index c32c72048a1c..82a290df2822 100644
--- a/crypto/acompress.c
+++ b/crypto/acompress.c
@@ -6,25 +6,35 @@
  * Authors: Weigang Li <weigang.li@intel.com>
  *          Giovanni Cabiddu <giovanni.cabiddu@intel.com>
  */
+
+#include <crypto/internal/acompress.h>
+#include <linux/cryptouser.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/crypto.h>
-#include <crypto/algapi.h>
-#include <linux/cryptouser.h>
-#include <linux/compiler.h>
 #include <net/netlink.h>
-#include <crypto/internal/acompress.h>
-#include <crypto/internal/scompress.h>
-#include "internal.h"
+
+#include "compress.h"
+
+struct crypto_scomp;
 
 static const struct crypto_type crypto_acomp_type;
 
-#ifdef CONFIG_NET
-static int crypto_acomp_report(struct sk_buff *skb, struct crypto_alg *alg)
+static inline struct acomp_alg *__crypto_acomp_alg(struct crypto_alg *alg)
+{
+	return container_of(alg, struct acomp_alg, calg.base);
+}
+
+static inline struct acomp_alg *crypto_acomp_alg(struct crypto_acomp *tfm)
+{
+	return __crypto_acomp_alg(crypto_acomp_tfm(tfm)->__crt_alg);
+}
+
+static int __maybe_unused crypto_acomp_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_acomp racomp;
 
@@ -34,12 +44,6 @@ static int crypto_acomp_report(struct sk_buff *skb, struct crypto_alg *alg)
 
 	return nla_put(skb, CRYPTOCFGA_REPORT_ACOMP, sizeof(racomp), &racomp);
 }
-#else
-static int crypto_acomp_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
 
 static void crypto_acomp_show(struct seq_file *m, struct crypto_alg *alg)
 	__maybe_unused;
@@ -89,13 +93,44 @@ static unsigned int crypto_acomp_extsize(struct crypto_alg *alg)
 	return extsize;
 }
 
+static inline int __crypto_acomp_report_stat(struct sk_buff *skb,
+					     struct crypto_alg *alg)
+{
+	struct comp_alg_common *calg = __crypto_comp_alg_common(alg);
+	struct crypto_istat_compress *istat = comp_get_stat(calg);
+	struct crypto_stat_compress racomp;
+
+	memset(&racomp, 0, sizeof(racomp));
+
+	strscpy(racomp.type, "acomp", sizeof(racomp.type));
+	racomp.stat_compress_cnt = atomic64_read(&istat->compress_cnt);
+	racomp.stat_compress_tlen = atomic64_read(&istat->compress_tlen);
+	racomp.stat_decompress_cnt =  atomic64_read(&istat->decompress_cnt);
+	racomp.stat_decompress_tlen = atomic64_read(&istat->decompress_tlen);
+	racomp.stat_err_cnt = atomic64_read(&istat->err_cnt);
+
+	return nla_put(skb, CRYPTOCFGA_STAT_ACOMP, sizeof(racomp), &racomp);
+}
+
+#ifdef CONFIG_CRYPTO_STATS
+int crypto_acomp_report_stat(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return __crypto_acomp_report_stat(skb, alg);
+}
+#endif
+
 static const struct crypto_type crypto_acomp_type = {
 	.extsize = crypto_acomp_extsize,
 	.init_tfm = crypto_acomp_init_tfm,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_acomp_show,
 #endif
+#ifdef CONFIG_CRYPTO_USER
 	.report = crypto_acomp_report,
+#endif
+#ifdef CONFIG_CRYPTO_STATS
+	.report_stat = crypto_acomp_report_stat,
+#endif
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_ACOMPRESS_MASK,
 	.type = CRYPTO_ALG_TYPE_ACOMPRESS,
@@ -147,12 +182,24 @@ void acomp_request_free(struct acomp_req *req)
 }
 EXPORT_SYMBOL_GPL(acomp_request_free);
 
-int crypto_register_acomp(struct acomp_alg *alg)
+void comp_prepare_alg(struct comp_alg_common *alg)
 {
+	struct crypto_istat_compress *istat = comp_get_stat(alg);
 	struct crypto_alg *base = &alg->base;
 
-	base->cra_type = &crypto_acomp_type;
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		memset(istat, 0, sizeof(*istat));
+}
+
+int crypto_register_acomp(struct acomp_alg *alg)
+{
+	struct crypto_alg *base = &alg->calg.base;
+
+	comp_prepare_alg(&alg->calg);
+
+	base->cra_type = &crypto_acomp_type;
 	base->cra_flags |= CRYPTO_ALG_TYPE_ACOMPRESS;
 
 	return crypto_register_alg(base);
diff --git a/crypto/aead.c b/crypto/aead.c
index 16991095270d..ffc48a7dfb34 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -8,17 +8,27 @@
  */
 
 #include <crypto/internal/aead.h>
+#include <linux/cryptouser.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
-#include <linux/cryptouser.h>
+#include <linux/string.h>
 #include <net/netlink.h>
 
 #include "internal.h"
 
+static inline struct crypto_istat_aead *aead_get_stat(struct aead_alg *alg)
+{
+#ifdef CONFIG_CRYPTO_STATS
+	return &alg->stat;
+#else
+	return NULL;
+#endif
+}
+
 static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key,
 			    unsigned int keylen)
 {
@@ -80,39 +90,62 @@ int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
 }
 EXPORT_SYMBOL_GPL(crypto_aead_setauthsize);
 
+static inline int crypto_aead_errstat(struct crypto_istat_aead *istat, int err)
+{
+	if (!IS_ENABLED(CONFIG_CRYPTO_STATS))
+		return err;
+
+	if (err && err != -EINPROGRESS && err != -EBUSY)
+		atomic64_inc(&istat->err_cnt);
+
+	return err;
+}
+
 int crypto_aead_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_alg *alg = aead->base.__crt_alg;
-	unsigned int cryptlen = req->cryptlen;
+	struct aead_alg *alg = crypto_aead_alg(aead);
+	struct crypto_istat_aead *istat;
 	int ret;
 
-	crypto_stats_get(alg);
+	istat = aead_get_stat(alg);
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		atomic64_inc(&istat->encrypt_cnt);
+		atomic64_add(req->cryptlen, &istat->encrypt_tlen);
+	}
+
 	if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY)
 		ret = -ENOKEY;
 	else
-		ret = crypto_aead_alg(aead)->encrypt(req);
-	crypto_stats_aead_encrypt(cryptlen, alg, ret);
-	return ret;
+		ret = alg->encrypt(req);
+
+	return crypto_aead_errstat(istat, ret);
 }
 EXPORT_SYMBOL_GPL(crypto_aead_encrypt);
 
 int crypto_aead_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_alg *alg = aead->base.__crt_alg;
-	unsigned int cryptlen = req->cryptlen;
+	struct aead_alg *alg = crypto_aead_alg(aead);
+	struct crypto_istat_aead *istat;
 	int ret;
 
-	crypto_stats_get(alg);
+	istat = aead_get_stat(alg);
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		atomic64_inc(&istat->encrypt_cnt);
+		atomic64_add(req->cryptlen, &istat->encrypt_tlen);
+	}
+
 	if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY)
 		ret = -ENOKEY;
 	else if (req->cryptlen < crypto_aead_authsize(aead))
 		ret = -EINVAL;
 	else
-		ret = crypto_aead_alg(aead)->decrypt(req);
-	crypto_stats_aead_decrypt(cryptlen, alg, ret);
-	return ret;
+		ret = alg->decrypt(req);
+
+	return crypto_aead_errstat(istat, ret);
 }
 EXPORT_SYMBOL_GPL(crypto_aead_decrypt);
 
@@ -142,8 +175,8 @@ static int crypto_aead_init_tfm(struct crypto_tfm *tfm)
 	return 0;
 }
 
-#ifdef CONFIG_NET
-static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int __maybe_unused crypto_aead_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_aead raead;
 	struct aead_alg *aead = container_of(alg, struct aead_alg, base);
@@ -159,12 +192,6 @@ static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
 
 	return nla_put(skb, CRYPTOCFGA_REPORT_AEAD, sizeof(raead), &raead);
 }
-#else
-static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
 
 static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg)
 	__maybe_unused;
@@ -188,6 +215,26 @@ static void crypto_aead_free_instance(struct crypto_instance *inst)
 	aead->free(aead);
 }
 
+static int __maybe_unused crypto_aead_report_stat(
+	struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct aead_alg *aead = container_of(alg, struct aead_alg, base);
+	struct crypto_istat_aead *istat = aead_get_stat(aead);
+	struct crypto_stat_aead raead;
+
+	memset(&raead, 0, sizeof(raead));
+
+	strscpy(raead.type, "aead", sizeof(raead.type));
+
+	raead.stat_encrypt_cnt = atomic64_read(&istat->encrypt_cnt);
+	raead.stat_encrypt_tlen = atomic64_read(&istat->encrypt_tlen);
+	raead.stat_decrypt_cnt = atomic64_read(&istat->decrypt_cnt);
+	raead.stat_decrypt_tlen = atomic64_read(&istat->decrypt_tlen);
+	raead.stat_err_cnt = atomic64_read(&istat->err_cnt);
+
+	return nla_put(skb, CRYPTOCFGA_STAT_AEAD, sizeof(raead), &raead);
+}
+
 static const struct crypto_type crypto_aead_type = {
 	.extsize = crypto_alg_extsize,
 	.init_tfm = crypto_aead_init_tfm,
@@ -195,7 +242,12 @@ static const struct crypto_type crypto_aead_type = {
 #ifdef CONFIG_PROC_FS
 	.show = crypto_aead_show,
 #endif
+#ifdef CONFIG_CRYPTO_USER
 	.report = crypto_aead_report,
+#endif
+#ifdef CONFIG_CRYPTO_STATS
+	.report_stat = crypto_aead_report_stat,
+#endif
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_MASK,
 	.type = CRYPTO_ALG_TYPE_AEAD,
@@ -219,6 +271,7 @@ EXPORT_SYMBOL_GPL(crypto_alloc_aead);
 
 static int aead_prepare_alg(struct aead_alg *alg)
 {
+	struct crypto_istat_aead *istat = aead_get_stat(alg);
 	struct crypto_alg *base = &alg->base;
 
 	if (max3(alg->maxauthsize, alg->ivsize, alg->chunksize) >
@@ -232,6 +285,9 @@ static int aead_prepare_alg(struct aead_alg *alg)
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_AEAD;
 
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		memset(istat, 0, sizeof(*istat));
+
 	return 0;
 }
 
diff --git a/crypto/ahash.c b/crypto/ahash.c
index ff8c79d975c1..b8a607928e72 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -8,19 +8,18 @@
  * Copyright (c) 2008 Loc Ho <lho@amcc.com>
  */
 
-#include <crypto/internal/hash.h>
 #include <crypto/scatterwalk.h>
+#include <linux/cryptouser.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
-#include <linux/cryptouser.h>
-#include <linux/compiler.h>
+#include <linux/string.h>
 #include <net/netlink.h>
 
-#include "internal.h"
+#include "hash.h"
 
 static const struct crypto_type crypto_ahash_type;
 
@@ -296,55 +295,60 @@ static int crypto_ahash_op(struct ahash_request *req,
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	unsigned long alignmask = crypto_ahash_alignmask(tfm);
+	int err;
 
 	if ((unsigned long)req->result & alignmask)
-		return ahash_op_unaligned(req, op, has_state);
+		err = ahash_op_unaligned(req, op, has_state);
+	else
+		err = op(req);
 
-	return op(req);
+	return crypto_hash_errstat(crypto_hash_alg_common(tfm), err);
 }
 
 int crypto_ahash_final(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct crypto_alg *alg = tfm->base.__crt_alg;
-	unsigned int nbytes = req->nbytes;
-	int ret;
+	struct hash_alg_common *alg = crypto_hash_alg_common(tfm);
 
-	crypto_stats_get(alg);
-	ret = crypto_ahash_op(req, crypto_ahash_reqtfm(req)->final, true);
-	crypto_stats_ahash_final(nbytes, ret, alg);
-	return ret;
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_inc(&hash_get_stat(alg)->hash_cnt);
+
+	return crypto_ahash_op(req, tfm->final, true);
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_final);
 
 int crypto_ahash_finup(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct crypto_alg *alg = tfm->base.__crt_alg;
-	unsigned int nbytes = req->nbytes;
-	int ret;
+	struct hash_alg_common *alg = crypto_hash_alg_common(tfm);
 
-	crypto_stats_get(alg);
-	ret = crypto_ahash_op(req, crypto_ahash_reqtfm(req)->finup, true);
-	crypto_stats_ahash_final(nbytes, ret, alg);
-	return ret;
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_hash *istat = hash_get_stat(alg);
+
+		atomic64_inc(&istat->hash_cnt);
+		atomic64_add(req->nbytes, &istat->hash_tlen);
+	}
+
+	return crypto_ahash_op(req, tfm->finup, true);
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_finup);
 
 int crypto_ahash_digest(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct crypto_alg *alg = tfm->base.__crt_alg;
-	unsigned int nbytes = req->nbytes;
-	int ret;
+	struct hash_alg_common *alg = crypto_hash_alg_common(tfm);
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_hash *istat = hash_get_stat(alg);
+
+		atomic64_inc(&istat->hash_cnt);
+		atomic64_add(req->nbytes, &istat->hash_tlen);
+	}
 
-	crypto_stats_get(alg);
 	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
-		ret = -ENOKEY;
-	else
-		ret = crypto_ahash_op(req, tfm->digest, false);
-	crypto_stats_ahash_final(nbytes, ret, alg);
-	return ret;
+		return crypto_hash_errstat(alg, -ENOKEY);
+
+	return crypto_ahash_op(req, tfm->digest, false);
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_digest);
 
@@ -465,8 +469,8 @@ static void crypto_ahash_free_instance(struct crypto_instance *inst)
 	ahash->free(ahash);
 }
 
-#ifdef CONFIG_NET
-static int crypto_ahash_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int __maybe_unused crypto_ahash_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_hash rhash;
 
@@ -479,12 +483,6 @@ static int crypto_ahash_report(struct sk_buff *skb, struct crypto_alg *alg)
 
 	return nla_put(skb, CRYPTOCFGA_REPORT_HASH, sizeof(rhash), &rhash);
 }
-#else
-static int crypto_ahash_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
 
 static void crypto_ahash_show(struct seq_file *m, struct crypto_alg *alg)
 	__maybe_unused;
@@ -498,6 +496,12 @@ static void crypto_ahash_show(struct seq_file *m, struct crypto_alg *alg)
 		   __crypto_hash_alg_common(alg)->digestsize);
 }
 
+static int __maybe_unused crypto_ahash_report_stat(
+	struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return crypto_hash_report_stat(skb, alg, "ahash");
+}
+
 static const struct crypto_type crypto_ahash_type = {
 	.extsize = crypto_ahash_extsize,
 	.init_tfm = crypto_ahash_init_tfm,
@@ -505,7 +509,12 @@ static const struct crypto_type crypto_ahash_type = {
 #ifdef CONFIG_PROC_FS
 	.show = crypto_ahash_show,
 #endif
+#ifdef CONFIG_CRYPTO_USER
 	.report = crypto_ahash_report,
+#endif
+#ifdef CONFIG_CRYPTO_STATS
+	.report_stat = crypto_ahash_report_stat,
+#endif
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_AHASH_MASK,
 	.type = CRYPTO_ALG_TYPE_AHASH,
@@ -534,17 +543,70 @@ int crypto_has_ahash(const char *alg_name, u32 type, u32 mask)
 }
 EXPORT_SYMBOL_GPL(crypto_has_ahash);
 
+struct crypto_ahash *crypto_clone_ahash(struct crypto_ahash *hash)
+{
+	struct hash_alg_common *halg = crypto_hash_alg_common(hash);
+	struct crypto_tfm *tfm = crypto_ahash_tfm(hash);
+	struct crypto_ahash *nhash;
+	struct ahash_alg *alg;
+	int err;
+
+	if (!crypto_hash_alg_has_setkey(halg)) {
+		tfm = crypto_tfm_get(tfm);
+		if (IS_ERR(tfm))
+			return ERR_CAST(tfm);
+
+		return hash;
+	}
+
+	nhash = crypto_clone_tfm(&crypto_ahash_type, tfm);
+
+	if (IS_ERR(nhash))
+		return nhash;
+
+	nhash->init = hash->init;
+	nhash->update = hash->update;
+	nhash->final = hash->final;
+	nhash->finup = hash->finup;
+	nhash->digest = hash->digest;
+	nhash->export = hash->export;
+	nhash->import = hash->import;
+	nhash->setkey = hash->setkey;
+	nhash->reqsize = hash->reqsize;
+
+	if (tfm->__crt_alg->cra_type != &crypto_ahash_type)
+		return crypto_clone_shash_ops_async(nhash, hash);
+
+	err = -ENOSYS;
+	alg = crypto_ahash_alg(hash);
+	if (!alg->clone_tfm)
+		goto out_free_nhash;
+
+	err = alg->clone_tfm(nhash, hash);
+	if (err)
+		goto out_free_nhash;
+
+	return nhash;
+
+out_free_nhash:
+	crypto_free_ahash(nhash);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(crypto_clone_ahash);
+
 static int ahash_prepare_alg(struct ahash_alg *alg)
 {
 	struct crypto_alg *base = &alg->halg.base;
+	int err;
 
-	if (alg->halg.digestsize > HASH_MAX_DIGESTSIZE ||
-	    alg->halg.statesize > HASH_MAX_STATESIZE ||
-	    alg->halg.statesize == 0)
+	if (alg->halg.statesize == 0)
 		return -EINVAL;
 
+	err = hash_prepare_alg(&alg->halg);
+	if (err)
+		return err;
+
 	base->cra_type = &crypto_ahash_type;
-	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_AHASH;
 
 	return 0;
diff --git a/crypto/akcipher.c b/crypto/akcipher.c
index ab975a420e1e..186e762b509a 100644
--- a/crypto/akcipher.c
+++ b/crypto/akcipher.c
@@ -5,23 +5,20 @@
  * Copyright (c) 2015, Intel Corporation
  * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
  */
+#include <crypto/internal/akcipher.h>
+#include <linux/cryptouser.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/crypto.h>
-#include <linux/compiler.h>
-#include <crypto/algapi.h>
-#include <linux/cryptouser.h>
 #include <net/netlink.h>
-#include <crypto/akcipher.h>
-#include <crypto/internal/akcipher.h>
+
 #include "internal.h"
 
-#ifdef CONFIG_NET
-static int crypto_akcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int __maybe_unused crypto_akcipher_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_akcipher rakcipher;
 
@@ -32,12 +29,6 @@ static int crypto_akcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
 	return nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER,
 		       sizeof(rakcipher), &rakcipher);
 }
-#else
-static int crypto_akcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
 
 static void crypto_akcipher_show(struct seq_file *m, struct crypto_alg *alg)
 	__maybe_unused;
@@ -76,6 +67,30 @@ static void crypto_akcipher_free_instance(struct crypto_instance *inst)
 	akcipher->free(akcipher);
 }
 
+static int __maybe_unused crypto_akcipher_report_stat(
+	struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct akcipher_alg *akcipher = __crypto_akcipher_alg(alg);
+	struct crypto_istat_akcipher *istat;
+	struct crypto_stat_akcipher rakcipher;
+
+	istat = akcipher_get_stat(akcipher);
+
+	memset(&rakcipher, 0, sizeof(rakcipher));
+
+	strscpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
+	rakcipher.stat_encrypt_cnt = atomic64_read(&istat->encrypt_cnt);
+	rakcipher.stat_encrypt_tlen = atomic64_read(&istat->encrypt_tlen);
+	rakcipher.stat_decrypt_cnt = atomic64_read(&istat->decrypt_cnt);
+	rakcipher.stat_decrypt_tlen = atomic64_read(&istat->decrypt_tlen);
+	rakcipher.stat_sign_cnt = atomic64_read(&istat->sign_cnt);
+	rakcipher.stat_verify_cnt = atomic64_read(&istat->verify_cnt);
+	rakcipher.stat_err_cnt = atomic64_read(&istat->err_cnt);
+
+	return nla_put(skb, CRYPTOCFGA_STAT_AKCIPHER,
+		       sizeof(rakcipher), &rakcipher);
+}
+
 static const struct crypto_type crypto_akcipher_type = {
 	.extsize = crypto_alg_extsize,
 	.init_tfm = crypto_akcipher_init_tfm,
@@ -83,7 +98,12 @@ static const struct crypto_type crypto_akcipher_type = {
 #ifdef CONFIG_PROC_FS
 	.show = crypto_akcipher_show,
 #endif
+#ifdef CONFIG_CRYPTO_USER
 	.report = crypto_akcipher_report,
+#endif
+#ifdef CONFIG_CRYPTO_STATS
+	.report_stat = crypto_akcipher_report_stat,
+#endif
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_MASK,
 	.type = CRYPTO_ALG_TYPE_AKCIPHER,
@@ -108,11 +128,15 @@ EXPORT_SYMBOL_GPL(crypto_alloc_akcipher);
 
 static void akcipher_prepare_alg(struct akcipher_alg *alg)
 {
+	struct crypto_istat_akcipher *istat = akcipher_get_stat(alg);
 	struct crypto_alg *base = &alg->base;
 
 	base->cra_type = &crypto_akcipher_type;
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_AKCIPHER;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		memset(istat, 0, sizeof(*istat));
 }
 
 static int akcipher_default_op(struct akcipher_request *req)
diff --git a/crypto/algapi.c b/crypto/algapi.c
index d08f864f08be..d7eb8f9e9883 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -339,8 +339,6 @@ __crypto_register_alg(struct crypto_alg *alg, struct list_head *algs_to_put)
 
 	list_add(&alg->cra_list, &crypto_alg_list);
 
-	crypto_stats_init(alg);
-
 	if (larval) {
 		/* No cheating! */
 		alg->cra_flags &= ~CRYPTO_ALG_TESTED;
@@ -493,7 +491,9 @@ void crypto_unregister_alg(struct crypto_alg *alg)
 	if (WARN(ret, "Algorithm %s is not registered", alg->cra_driver_name))
 		return;
 
-	BUG_ON(refcount_read(&alg->cra_refcnt) != 1);
+	if (WARN_ON(refcount_read(&alg->cra_refcnt) != 1))
+		return;
+
 	if (alg->cra_destroy)
 		alg->cra_destroy(alg);
 
@@ -1038,219 +1038,6 @@ int crypto_type_has_alg(const char *name, const struct crypto_type *frontend,
 }
 EXPORT_SYMBOL_GPL(crypto_type_has_alg);
 
-#ifdef CONFIG_CRYPTO_STATS
-void crypto_stats_init(struct crypto_alg *alg)
-{
-	memset(&alg->stats, 0, sizeof(alg->stats));
-}
-EXPORT_SYMBOL_GPL(crypto_stats_init);
-
-void crypto_stats_get(struct crypto_alg *alg)
-{
-	crypto_alg_get(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_get);
-
-void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg,
-			       int ret)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.aead.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.aead.encrypt_cnt);
-		atomic64_add(cryptlen, &alg->stats.aead.encrypt_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_aead_encrypt);
-
-void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg,
-			       int ret)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.aead.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.aead.decrypt_cnt);
-		atomic64_add(cryptlen, &alg->stats.aead.decrypt_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_aead_decrypt);
-
-void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret,
-				   struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.akcipher.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.akcipher.encrypt_cnt);
-		atomic64_add(src_len, &alg->stats.akcipher.encrypt_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_akcipher_encrypt);
-
-void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret,
-				   struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.akcipher.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.akcipher.decrypt_cnt);
-		atomic64_add(src_len, &alg->stats.akcipher.decrypt_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_akcipher_decrypt);
-
-void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY)
-		atomic64_inc(&alg->stats.akcipher.err_cnt);
-	else
-		atomic64_inc(&alg->stats.akcipher.sign_cnt);
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_akcipher_sign);
-
-void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY)
-		atomic64_inc(&alg->stats.akcipher.err_cnt);
-	else
-		atomic64_inc(&alg->stats.akcipher.verify_cnt);
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_akcipher_verify);
-
-void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.compress.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.compress.compress_cnt);
-		atomic64_add(slen, &alg->stats.compress.compress_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_compress);
-
-void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.compress.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.compress.decompress_cnt);
-		atomic64_add(slen, &alg->stats.compress.decompress_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_decompress);
-
-void crypto_stats_ahash_update(unsigned int nbytes, int ret,
-			       struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY)
-		atomic64_inc(&alg->stats.hash.err_cnt);
-	else
-		atomic64_add(nbytes, &alg->stats.hash.hash_tlen);
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_ahash_update);
-
-void crypto_stats_ahash_final(unsigned int nbytes, int ret,
-			      struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.hash.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.hash.hash_cnt);
-		atomic64_add(nbytes, &alg->stats.hash.hash_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_ahash_final);
-
-void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret)
-{
-	if (ret)
-		atomic64_inc(&alg->stats.kpp.err_cnt);
-	else
-		atomic64_inc(&alg->stats.kpp.setsecret_cnt);
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_kpp_set_secret);
-
-void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret)
-{
-	if (ret)
-		atomic64_inc(&alg->stats.kpp.err_cnt);
-	else
-		atomic64_inc(&alg->stats.kpp.generate_public_key_cnt);
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_kpp_generate_public_key);
-
-void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret)
-{
-	if (ret)
-		atomic64_inc(&alg->stats.kpp.err_cnt);
-	else
-		atomic64_inc(&alg->stats.kpp.compute_shared_secret_cnt);
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_kpp_compute_shared_secret);
-
-void crypto_stats_rng_seed(struct crypto_alg *alg, int ret)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY)
-		atomic64_inc(&alg->stats.rng.err_cnt);
-	else
-		atomic64_inc(&alg->stats.rng.seed_cnt);
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_rng_seed);
-
-void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen,
-			       int ret)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.rng.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.rng.generate_cnt);
-		atomic64_add(dlen, &alg->stats.rng.generate_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_rng_generate);
-
-void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret,
-				   struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.cipher.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.cipher.encrypt_cnt);
-		atomic64_add(cryptlen, &alg->stats.cipher.encrypt_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_skcipher_encrypt);
-
-void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret,
-				   struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.cipher.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.cipher.decrypt_cnt);
-		atomic64_add(cryptlen, &alg->stats.cipher.decrypt_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_skcipher_decrypt);
-#endif
-
 static void __init crypto_start_tests(void)
 {
 	if (IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS))
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 1d017ec5c63c..63af72e19fa8 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -235,24 +235,31 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags,
 	struct alg_sock *ask = alg_sk(sk);
 	struct hash_ctx *ctx = ask->private;
 	struct ahash_request *req = &ctx->req;
-	char state[HASH_MAX_STATESIZE];
+	struct crypto_ahash *tfm;
 	struct sock *sk2;
 	struct alg_sock *ask2;
 	struct hash_ctx *ctx2;
+	char *state;
 	bool more;
 	int err;
 
+	tfm = crypto_ahash_reqtfm(req);
+	state = kmalloc(crypto_ahash_statesize(tfm), GFP_KERNEL);
+	err = -ENOMEM;
+	if (!state)
+		goto out;
+
 	lock_sock(sk);
 	more = ctx->more;
 	err = more ? crypto_ahash_export(req, state) : 0;
 	release_sock(sk);
 
 	if (err)
-		return err;
+		goto out_free_state;
 
 	err = af_alg_accept(ask->parent, newsock, kern);
 	if (err)
-		return err;
+		goto out_free_state;
 
 	sk2 = newsock->sk;
 	ask2 = alg_sk(sk2);
@@ -260,7 +267,7 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags,
 	ctx2->more = more;
 
 	if (!more)
-		return err;
+		goto out_free_state;
 
 	err = crypto_ahash_import(&ctx2->req, state);
 	if (err) {
@@ -268,6 +275,10 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags,
 		sock_put(sk2);
 	}
 
+out_free_state:
+	kfree_sensitive(state);
+
+out:
 	return err;
 }
 
diff --git a/crypto/api.c b/crypto/api.c
index e67cc63368ed..d375e8cd770d 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -408,6 +408,7 @@ struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type,
 		goto out_err;
 
 	tfm->__crt_alg = alg;
+	refcount_set(&tfm->refcnt, 1);
 
 	err = crypto_init_ops(tfm, type, mask);
 	if (err)
@@ -487,26 +488,43 @@ err:
 }
 EXPORT_SYMBOL_GPL(crypto_alloc_base);
 
-void *crypto_create_tfm_node(struct crypto_alg *alg,
-			const struct crypto_type *frontend,
-			int node)
+static void *crypto_alloc_tfmmem(struct crypto_alg *alg,
+				 const struct crypto_type *frontend, int node,
+				 gfp_t gfp)
 {
-	char *mem;
-	struct crypto_tfm *tfm = NULL;
+	struct crypto_tfm *tfm;
 	unsigned int tfmsize;
 	unsigned int total;
-	int err = -ENOMEM;
+	char *mem;
 
 	tfmsize = frontend->tfmsize;
 	total = tfmsize + sizeof(*tfm) + frontend->extsize(alg);
 
-	mem = kzalloc_node(total, GFP_KERNEL, node);
+	mem = kzalloc_node(total, gfp, node);
 	if (mem == NULL)
-		goto out_err;
+		return ERR_PTR(-ENOMEM);
 
 	tfm = (struct crypto_tfm *)(mem + tfmsize);
 	tfm->__crt_alg = alg;
 	tfm->node = node;
+	refcount_set(&tfm->refcnt, 1);
+
+	return mem;
+}
+
+void *crypto_create_tfm_node(struct crypto_alg *alg,
+			     const struct crypto_type *frontend,
+			     int node)
+{
+	struct crypto_tfm *tfm;
+	char *mem;
+	int err;
+
+	mem = crypto_alloc_tfmmem(alg, frontend, node, GFP_KERNEL);
+	if (IS_ERR(mem))
+		goto out;
+
+	tfm = (struct crypto_tfm *)(mem + frontend->tfmsize);
 
 	err = frontend->init_tfm(tfm);
 	if (err)
@@ -523,13 +541,38 @@ out_free_tfm:
 	if (err == -EAGAIN)
 		crypto_shoot_alg(alg);
 	kfree(mem);
-out_err:
 	mem = ERR_PTR(err);
 out:
 	return mem;
 }
 EXPORT_SYMBOL_GPL(crypto_create_tfm_node);
 
+void *crypto_clone_tfm(const struct crypto_type *frontend,
+		       struct crypto_tfm *otfm)
+{
+	struct crypto_alg *alg = otfm->__crt_alg;
+	struct crypto_tfm *tfm;
+	char *mem;
+
+	mem = ERR_PTR(-ESTALE);
+	if (unlikely(!crypto_mod_get(alg)))
+		goto out;
+
+	mem = crypto_alloc_tfmmem(alg, frontend, otfm->node, GFP_ATOMIC);
+	if (IS_ERR(mem)) {
+		crypto_mod_put(alg);
+		goto out;
+	}
+
+	tfm = (struct crypto_tfm *)(mem + frontend->tfmsize);
+	tfm->crt_flags = otfm->crt_flags;
+	tfm->exit = otfm->exit;
+
+out:
+	return mem;
+}
+EXPORT_SYMBOL_GPL(crypto_clone_tfm);
+
 struct crypto_alg *crypto_find_alg(const char *alg_name,
 				   const struct crypto_type *frontend,
 				   u32 type, u32 mask)
@@ -619,6 +662,8 @@ void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm)
 	if (IS_ERR_OR_NULL(mem))
 		return;
 
+	if (!refcount_dec_and_test(&tfm->refcnt))
+		return;
 	alg = tfm->__crt_alg;
 
 	if (!tfm->exit && alg->cra_exit)
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index f9cdc5e91664..5e2b2680d7db 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -11,8 +11,8 @@
 #include <linux/async_tx.h>
 #include <linux/gfp.h>
 
-/**
- * pq_scribble_page - space to hold throwaway P or Q buffer for
+/*
+ * struct pq_scribble_page - space to hold throwaway P or Q buffer for
  * synchronous gen_syndrome
  */
 static struct page *pq_scribble_page;
@@ -28,7 +28,7 @@ static struct page *pq_scribble_page;
 
 #define MAX_DISKS 255
 
-/**
+/*
  * do_async_gen_syndrome - asynchronously calculate P and/or Q
  */
 static __async_inline struct dma_async_tx_descriptor *
@@ -100,7 +100,7 @@ do_async_gen_syndrome(struct dma_chan *chan,
 	return tx;
 }
 
-/**
+/*
  * do_sync_gen_syndrome - synchronously calculate a raid6 syndrome
  */
 static void
@@ -281,7 +281,7 @@ pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, si
 /**
  * async_syndrome_val - asynchronously validate a raid6 syndrome
  * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
- * @offset: common offset into each block (src and dest) to start transaction
+ * @offsets: common offset into each block (src and dest) to start transaction
  * @disks: number of blocks (including missing P or Q, see below)
  * @len: length of operation in bytes
  * @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c
index 9256934312d7..ad72057a5e0d 100644
--- a/crypto/async_tx/async_tx.c
+++ b/crypto/async_tx/async_tx.c
@@ -124,7 +124,7 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx,
 
 
 /**
- * submit_disposition - flags for routing an incoming operation
+ * enum submit_disposition - flags for routing an incoming operation
  * @ASYNC_TX_SUBMITTED: we were able to append the new operation under the lock
  * @ASYNC_TX_CHANNEL_SWITCH: when the lock is dropped schedule a channel switch
  * @ASYNC_TX_DIRECT_SUBMIT: when the lock is dropped submit directly
@@ -258,7 +258,7 @@ EXPORT_SYMBOL_GPL(async_trigger_callback);
 
 /**
  * async_tx_quiesce - ensure tx is complete and freeable upon return
- * @tx - transaction to quiesce
+ * @tx: transaction to quiesce
  */
 void async_tx_quiesce(struct dma_async_tx_descriptor **tx)
 {
diff --git a/crypto/compress.h b/crypto/compress.h
new file mode 100644
index 000000000000..19f65516d699
--- /dev/null
+++ b/crypto/compress.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Cryptographic API.
+ *
+ * Copyright 2015 LG Electronics Inc.
+ * Copyright (c) 2016, Intel Corporation
+ * Copyright (c) 2023 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+#ifndef _LOCAL_CRYPTO_COMPRESS_H
+#define _LOCAL_CRYPTO_COMPRESS_H
+
+#include "internal.h"
+
+struct acomp_req;
+struct comp_alg_common;
+struct sk_buff;
+
+int crypto_init_scomp_ops_async(struct crypto_tfm *tfm);
+struct acomp_req *crypto_acomp_scomp_alloc_ctx(struct acomp_req *req);
+void crypto_acomp_scomp_free_ctx(struct acomp_req *req);
+
+int crypto_acomp_report_stat(struct sk_buff *skb, struct crypto_alg *alg);
+
+void comp_prepare_alg(struct comp_alg_common *alg);
+
+#endif	/* _LOCAL_CRYPTO_COMPRESS_H */
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 37365ed30b38..bbcc368b6a55 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -427,12 +427,12 @@ err_free_inst:
 	return err;
 }
 
-static int cryptd_hash_init_tfm(struct crypto_tfm *tfm)
+static int cryptd_hash_init_tfm(struct crypto_ahash *tfm)
 {
-	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
-	struct hashd_instance_ctx *ictx = crypto_instance_ctx(inst);
+	struct ahash_instance *inst = ahash_alg_instance(tfm);
+	struct hashd_instance_ctx *ictx = ahash_instance_ctx(inst);
 	struct crypto_shash_spawn *spawn = &ictx->spawn;
-	struct cryptd_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct crypto_shash *hash;
 
 	hash = crypto_spawn_shash(spawn);
@@ -440,15 +440,30 @@ static int cryptd_hash_init_tfm(struct crypto_tfm *tfm)
 		return PTR_ERR(hash);
 
 	ctx->child = hash;
-	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+	crypto_ahash_set_reqsize(tfm,
 				 sizeof(struct cryptd_hash_request_ctx) +
 				 crypto_shash_descsize(hash));
 	return 0;
 }
 
-static void cryptd_hash_exit_tfm(struct crypto_tfm *tfm)
+static int cryptd_hash_clone_tfm(struct crypto_ahash *ntfm,
+				 struct crypto_ahash *tfm)
 {
-	struct cryptd_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct cryptd_hash_ctx *nctx = crypto_ahash_ctx(ntfm);
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct crypto_shash *hash;
+
+	hash = crypto_clone_shash(ctx->child);
+	if (IS_ERR(hash))
+		return PTR_ERR(hash);
+
+	nctx->child = hash;
+	return 0;
+}
+
+static void cryptd_hash_exit_tfm(struct crypto_ahash *tfm)
+{
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
 
 	crypto_free_shash(ctx->child);
 }
@@ -677,8 +692,9 @@ static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	inst->alg.halg.statesize = alg->statesize;
 	inst->alg.halg.base.cra_ctxsize = sizeof(struct cryptd_hash_ctx);
 
-	inst->alg.halg.base.cra_init = cryptd_hash_init_tfm;
-	inst->alg.halg.base.cra_exit = cryptd_hash_exit_tfm;
+	inst->alg.init_tfm = cryptd_hash_init_tfm;
+	inst->alg.clone_tfm = cryptd_hash_clone_tfm;
+	inst->alg.exit_tfm = cryptd_hash_exit_tfm;
 
 	inst->alg.init   = cryptd_hash_init_enqueue;
 	inst->alg.update = cryptd_hash_update_enqueue;
diff --git a/crypto/crypto_user_stat.c b/crypto/crypto_user_stat.c
index 154884bf9275..d4f3d39b5137 100644
--- a/crypto/crypto_user_stat.c
+++ b/crypto/crypto_user_stat.c
@@ -6,18 +6,14 @@
  *
  */
 
-#include <linux/crypto.h>
-#include <linux/cryptouser.h>
-#include <linux/sched.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/cryptouser.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
 #include <net/netlink.h>
 #include <net/sock.h>
-#include <crypto/internal/skcipher.h>
-#include <crypto/internal/rng.h>
-#include <crypto/akcipher.h>
-#include <crypto/kpp.h>
-#include <crypto/internal/cryptouser.h>
-
-#include "internal.h"
 
 #define null_terminated(x)	(strnlen(x, sizeof(x)) < sizeof(x))
 
@@ -28,23 +24,6 @@ struct crypto_dump_info {
 	u16 nlmsg_flags;
 };
 
-static int crypto_report_aead(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_stat_aead raead;
-
-	memset(&raead, 0, sizeof(raead));
-
-	strscpy(raead.type, "aead", sizeof(raead.type));
-
-	raead.stat_encrypt_cnt = atomic64_read(&alg->stats.aead.encrypt_cnt);
-	raead.stat_encrypt_tlen = atomic64_read(&alg->stats.aead.encrypt_tlen);
-	raead.stat_decrypt_cnt = atomic64_read(&alg->stats.aead.decrypt_cnt);
-	raead.stat_decrypt_tlen = atomic64_read(&alg->stats.aead.decrypt_tlen);
-	raead.stat_err_cnt = atomic64_read(&alg->stats.aead.err_cnt);
-
-	return nla_put(skb, CRYPTOCFGA_STAT_AEAD, sizeof(raead), &raead);
-}
-
 static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_stat_cipher rcipher;
@@ -53,12 +32,6 @@ static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg)
 
 	strscpy(rcipher.type, "cipher", sizeof(rcipher.type));
 
-	rcipher.stat_encrypt_cnt = atomic64_read(&alg->stats.cipher.encrypt_cnt);
-	rcipher.stat_encrypt_tlen = atomic64_read(&alg->stats.cipher.encrypt_tlen);
-	rcipher.stat_decrypt_cnt =  atomic64_read(&alg->stats.cipher.decrypt_cnt);
-	rcipher.stat_decrypt_tlen = atomic64_read(&alg->stats.cipher.decrypt_tlen);
-	rcipher.stat_err_cnt =  atomic64_read(&alg->stats.cipher.err_cnt);
-
 	return nla_put(skb, CRYPTOCFGA_STAT_CIPHER, sizeof(rcipher), &rcipher);
 }
 
@@ -69,112 +42,10 @@ static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg)
 	memset(&rcomp, 0, sizeof(rcomp));
 
 	strscpy(rcomp.type, "compression", sizeof(rcomp.type));
-	rcomp.stat_compress_cnt = atomic64_read(&alg->stats.compress.compress_cnt);
-	rcomp.stat_compress_tlen = atomic64_read(&alg->stats.compress.compress_tlen);
-	rcomp.stat_decompress_cnt = atomic64_read(&alg->stats.compress.decompress_cnt);
-	rcomp.stat_decompress_tlen = atomic64_read(&alg->stats.compress.decompress_tlen);
-	rcomp.stat_err_cnt = atomic64_read(&alg->stats.compress.err_cnt);
 
 	return nla_put(skb, CRYPTOCFGA_STAT_COMPRESS, sizeof(rcomp), &rcomp);
 }
 
-static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_stat_compress racomp;
-
-	memset(&racomp, 0, sizeof(racomp));
-
-	strscpy(racomp.type, "acomp", sizeof(racomp.type));
-	racomp.stat_compress_cnt = atomic64_read(&alg->stats.compress.compress_cnt);
-	racomp.stat_compress_tlen = atomic64_read(&alg->stats.compress.compress_tlen);
-	racomp.stat_decompress_cnt =  atomic64_read(&alg->stats.compress.decompress_cnt);
-	racomp.stat_decompress_tlen = atomic64_read(&alg->stats.compress.decompress_tlen);
-	racomp.stat_err_cnt = atomic64_read(&alg->stats.compress.err_cnt);
-
-	return nla_put(skb, CRYPTOCFGA_STAT_ACOMP, sizeof(racomp), &racomp);
-}
-
-static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_stat_akcipher rakcipher;
-
-	memset(&rakcipher, 0, sizeof(rakcipher));
-
-	strscpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
-	rakcipher.stat_encrypt_cnt = atomic64_read(&alg->stats.akcipher.encrypt_cnt);
-	rakcipher.stat_encrypt_tlen = atomic64_read(&alg->stats.akcipher.encrypt_tlen);
-	rakcipher.stat_decrypt_cnt = atomic64_read(&alg->stats.akcipher.decrypt_cnt);
-	rakcipher.stat_decrypt_tlen = atomic64_read(&alg->stats.akcipher.decrypt_tlen);
-	rakcipher.stat_sign_cnt = atomic64_read(&alg->stats.akcipher.sign_cnt);
-	rakcipher.stat_verify_cnt = atomic64_read(&alg->stats.akcipher.verify_cnt);
-	rakcipher.stat_err_cnt = atomic64_read(&alg->stats.akcipher.err_cnt);
-
-	return nla_put(skb, CRYPTOCFGA_STAT_AKCIPHER,
-		       sizeof(rakcipher), &rakcipher);
-}
-
-static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_stat_kpp rkpp;
-
-	memset(&rkpp, 0, sizeof(rkpp));
-
-	strscpy(rkpp.type, "kpp", sizeof(rkpp.type));
-
-	rkpp.stat_setsecret_cnt = atomic64_read(&alg->stats.kpp.setsecret_cnt);
-	rkpp.stat_generate_public_key_cnt = atomic64_read(&alg->stats.kpp.generate_public_key_cnt);
-	rkpp.stat_compute_shared_secret_cnt = atomic64_read(&alg->stats.kpp.compute_shared_secret_cnt);
-	rkpp.stat_err_cnt = atomic64_read(&alg->stats.kpp.err_cnt);
-
-	return nla_put(skb, CRYPTOCFGA_STAT_KPP, sizeof(rkpp), &rkpp);
-}
-
-static int crypto_report_ahash(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_stat_hash rhash;
-
-	memset(&rhash, 0, sizeof(rhash));
-
-	strscpy(rhash.type, "ahash", sizeof(rhash.type));
-
-	rhash.stat_hash_cnt = atomic64_read(&alg->stats.hash.hash_cnt);
-	rhash.stat_hash_tlen = atomic64_read(&alg->stats.hash.hash_tlen);
-	rhash.stat_err_cnt = atomic64_read(&alg->stats.hash.err_cnt);
-
-	return nla_put(skb, CRYPTOCFGA_STAT_HASH, sizeof(rhash), &rhash);
-}
-
-static int crypto_report_shash(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_stat_hash rhash;
-
-	memset(&rhash, 0, sizeof(rhash));
-
-	strscpy(rhash.type, "shash", sizeof(rhash.type));
-
-	rhash.stat_hash_cnt =  atomic64_read(&alg->stats.hash.hash_cnt);
-	rhash.stat_hash_tlen = atomic64_read(&alg->stats.hash.hash_tlen);
-	rhash.stat_err_cnt = atomic64_read(&alg->stats.hash.err_cnt);
-
-	return nla_put(skb, CRYPTOCFGA_STAT_HASH, sizeof(rhash), &rhash);
-}
-
-static int crypto_report_rng(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_stat_rng rrng;
-
-	memset(&rrng, 0, sizeof(rrng));
-
-	strscpy(rrng.type, "rng", sizeof(rrng.type));
-
-	rrng.stat_generate_cnt = atomic64_read(&alg->stats.rng.generate_cnt);
-	rrng.stat_generate_tlen = atomic64_read(&alg->stats.rng.generate_tlen);
-	rrng.stat_seed_cnt = atomic64_read(&alg->stats.rng.seed_cnt);
-	rrng.stat_err_cnt = atomic64_read(&alg->stats.rng.err_cnt);
-
-	return nla_put(skb, CRYPTOCFGA_STAT_RNG, sizeof(rrng), &rrng);
-}
-
 static int crypto_reportstat_one(struct crypto_alg *alg,
 				 struct crypto_user_alg *ualg,
 				 struct sk_buff *skb)
@@ -204,15 +75,13 @@ static int crypto_reportstat_one(struct crypto_alg *alg,
 		goto out;
 	}
 
-	switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) {
-	case CRYPTO_ALG_TYPE_AEAD:
-		if (crypto_report_aead(skb, alg))
+	if (alg->cra_type && alg->cra_type->report_stat) {
+		if (alg->cra_type->report_stat(skb, alg))
 			goto nla_put_failure;
-		break;
-	case CRYPTO_ALG_TYPE_SKCIPHER:
-		if (crypto_report_cipher(skb, alg))
-			goto nla_put_failure;
-		break;
+		goto out;
+	}
+
+	switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) {
 	case CRYPTO_ALG_TYPE_CIPHER:
 		if (crypto_report_cipher(skb, alg))
 			goto nla_put_failure;
@@ -221,34 +90,6 @@ static int crypto_reportstat_one(struct crypto_alg *alg,
 		if (crypto_report_comp(skb, alg))
 			goto nla_put_failure;
 		break;
-	case CRYPTO_ALG_TYPE_ACOMPRESS:
-		if (crypto_report_acomp(skb, alg))
-			goto nla_put_failure;
-		break;
-	case CRYPTO_ALG_TYPE_SCOMPRESS:
-		if (crypto_report_acomp(skb, alg))
-			goto nla_put_failure;
-		break;
-	case CRYPTO_ALG_TYPE_AKCIPHER:
-		if (crypto_report_akcipher(skb, alg))
-			goto nla_put_failure;
-		break;
-	case CRYPTO_ALG_TYPE_KPP:
-		if (crypto_report_kpp(skb, alg))
-			goto nla_put_failure;
-		break;
-	case CRYPTO_ALG_TYPE_AHASH:
-		if (crypto_report_ahash(skb, alg))
-			goto nla_put_failure;
-		break;
-	case CRYPTO_ALG_TYPE_HASH:
-		if (crypto_report_shash(skb, alg))
-			goto nla_put_failure;
-		break;
-	case CRYPTO_ALG_TYPE_RNG:
-		if (crypto_report_rng(skb, alg))
-			goto nla_put_failure;
-		break;
 	default:
 		pr_err("ERROR: Unhandled alg %d in %s\n",
 		       alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL),
diff --git a/crypto/drbg.c b/crypto/drbg.c
index 982d4ca4526d..ff4ebbc68efa 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1546,7 +1546,7 @@ static int drbg_prepare_hrng(struct drbg_state *drbg)
 		const int err = PTR_ERR(drbg->jent);
 
 		drbg->jent = NULL;
-		if (fips_enabled || err != -ENOENT)
+		if (fips_enabled)
 			return err;
 		pr_info("DRBG: Continuing without Jitter RNG\n");
 	}
diff --git a/crypto/fips.c b/crypto/fips.c
index b05d3c7b3ca5..92fd506abb21 100644
--- a/crypto/fips.c
+++ b/crypto/fips.c
@@ -66,20 +66,11 @@ static struct ctl_table crypto_sysctl_table[] = {
 	{}
 };
 
-static struct ctl_table crypto_dir_table[] = {
-	{
-		.procname       = "crypto",
-		.mode           = 0555,
-		.child          = crypto_sysctl_table
-	},
-	{}
-};
-
 static struct ctl_table_header *crypto_sysctls;
 
 static void crypto_proc_fips_init(void)
 {
-	crypto_sysctls = register_sysctl_table(crypto_dir_table);
+	crypto_sysctls = register_sysctl("crypto", crypto_sysctl_table);
 }
 
 static void crypto_proc_fips_exit(void)
diff --git a/crypto/hash.h b/crypto/hash.h
new file mode 100644
index 000000000000..7e6c1a948692
--- /dev/null
+++ b/crypto/hash.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Cryptographic API.
+ *
+ * Copyright (c) 2023 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+#ifndef _LOCAL_CRYPTO_HASH_H
+#define _LOCAL_CRYPTO_HASH_H
+
+#include <crypto/internal/hash.h>
+#include <linux/cryptouser.h>
+
+#include "internal.h"
+
+static inline int crypto_hash_report_stat(struct sk_buff *skb,
+					  struct crypto_alg *alg,
+					  const char *type)
+{
+	struct hash_alg_common *halg = __crypto_hash_alg_common(alg);
+	struct crypto_istat_hash *istat = hash_get_stat(halg);
+	struct crypto_stat_hash rhash;
+
+	memset(&rhash, 0, sizeof(rhash));
+
+	strscpy(rhash.type, type, sizeof(rhash.type));
+
+	rhash.stat_hash_cnt = atomic64_read(&istat->hash_cnt);
+	rhash.stat_hash_tlen = atomic64_read(&istat->hash_tlen);
+	rhash.stat_err_cnt = atomic64_read(&istat->err_cnt);
+
+	return nla_put(skb, CRYPTOCFGA_STAT_HASH, sizeof(rhash), &rhash);
+}
+
+int crypto_init_shash_ops_async(struct crypto_tfm *tfm);
+struct crypto_ahash *crypto_clone_shash_ops_async(struct crypto_ahash *nhash,
+						  struct crypto_ahash *hash);
+
+int hash_prepare_alg(struct hash_alg_common *alg);
+
+#endif	/* _LOCAL_CRYPTO_HASH_H */
diff --git a/crypto/hmac.c b/crypto/hmac.c
index 3610ff0b6739..09a7872b4060 100644
--- a/crypto/hmac.c
+++ b/crypto/hmac.c
@@ -160,6 +160,20 @@ static int hmac_init_tfm(struct crypto_shash *parent)
 	return 0;
 }
 
+static int hmac_clone_tfm(struct crypto_shash *dst, struct crypto_shash *src)
+{
+	struct hmac_ctx *sctx = hmac_ctx(src);
+	struct hmac_ctx *dctx = hmac_ctx(dst);
+	struct crypto_shash *hash;
+
+	hash = crypto_clone_shash(sctx->hash);
+	if (IS_ERR(hash))
+		return PTR_ERR(hash);
+
+	dctx->hash = hash;
+	return 0;
+}
+
 static void hmac_exit_tfm(struct crypto_shash *parent)
 {
 	struct hmac_ctx *ctx = hmac_ctx(parent);
@@ -227,6 +241,7 @@ static int hmac_create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->alg.import = hmac_import;
 	inst->alg.setkey = hmac_setkey;
 	inst->alg.init_tfm = hmac_init_tfm;
+	inst->alg.clone_tfm = hmac_clone_tfm;
 	inst->alg.exit_tfm = hmac_exit_tfm;
 
 	inst->free = shash_free_singlespawn_instance;
diff --git a/crypto/internal.h b/crypto/internal.h
index 932f0aafddc3..8dd746b1130b 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -10,6 +10,7 @@
 
 #include <crypto/algapi.h>
 #include <linux/completion.h>
+#include <linux/err.h>
 #include <linux/jump_label.h>
 #include <linux/list.h>
 #include <linux/module.h>
@@ -47,6 +48,8 @@ extern struct list_head crypto_alg_list;
 extern struct rw_semaphore crypto_alg_sem;
 extern struct blocking_notifier_head crypto_chain;
 
+int alg_test(const char *driver, const char *alg, u32 type, u32 mask);
+
 #ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS
 static inline bool crypto_boot_test_finished(void)
 {
@@ -103,6 +106,8 @@ struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type,
 				      u32 mask);
 void *crypto_create_tfm_node(struct crypto_alg *alg,
 			const struct crypto_type *frontend, int node);
+void *crypto_clone_tfm(const struct crypto_type *frontend,
+		       struct crypto_tfm *otfm);
 
 static inline void *crypto_create_tfm(struct crypto_alg *alg,
 			const struct crypto_type *frontend)
@@ -184,5 +189,10 @@ static inline int crypto_is_test_larval(struct crypto_larval *larval)
 	return larval->alg.cra_driver_name[0];
 }
 
+static inline struct crypto_tfm *crypto_tfm_get(struct crypto_tfm *tfm)
+{
+	return refcount_inc_not_zero(&tfm->refcnt) ? tfm : ERR_PTR(-EOVERFLOW);
+}
+
 #endif	/* _CRYPTO_INTERNAL_H */
 
diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c
index 2d115bec15ae..b9edfaa51b27 100644
--- a/crypto/jitterentropy-kcapi.c
+++ b/crypto/jitterentropy-kcapi.c
@@ -37,6 +37,7 @@
  * DAMAGE.
  */
 
+#include <linux/fips.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -59,11 +60,6 @@ void jent_zfree(void *ptr)
 	kfree_sensitive(ptr);
 }
 
-void jent_panic(char *s)
-{
-	panic("%s", s);
-}
-
 void jent_memcpy(void *dest, const void *src, unsigned int n)
 {
 	memcpy(dest, src, n);
@@ -102,7 +98,6 @@ void jent_get_nstime(__u64 *out)
 struct jitterentropy {
 	spinlock_t jent_lock;
 	struct rand_data *entropy_collector;
-	unsigned int reset_cnt;
 };
 
 static int jent_kcapi_init(struct crypto_tfm *tfm)
@@ -138,32 +133,30 @@ static int jent_kcapi_random(struct crypto_rng *tfm,
 
 	spin_lock(&rng->jent_lock);
 
-	/* Return a permanent error in case we had too many resets in a row. */
-	if (rng->reset_cnt > (1<<10)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
 	ret = jent_read_entropy(rng->entropy_collector, rdata, dlen);
 
-	/* Reset RNG in case of health failures */
-	if (ret < -1) {
-		pr_warn_ratelimited("Reset Jitter RNG due to health test failure: %s failure\n",
-				    (ret == -2) ? "Repetition Count Test" :
-						  "Adaptive Proportion Test");
-
-		rng->reset_cnt++;
-
+	if (ret == -3) {
+		/* Handle permanent health test error */
+		/*
+		 * If the kernel was booted with fips=1, it implies that
+		 * the entire kernel acts as a FIPS 140 module. In this case
+		 * an SP800-90B permanent health test error is treated as
+		 * a FIPS module error.
+		 */
+		if (fips_enabled)
+			panic("Jitter RNG permanent health test failure\n");
+
+		pr_err("Jitter RNG permanent health test failure\n");
+		ret = -EFAULT;
+	} else if (ret == -2) {
+		/* Handle intermittent health test error */
+		pr_warn_ratelimited("Reset Jitter RNG due to intermittent health test failure\n");
 		ret = -EAGAIN;
-	} else {
-		rng->reset_cnt = 0;
-
-		/* Convert the Jitter RNG error into a usable error code */
-		if (ret == -1)
-			ret = -EINVAL;
+	} else if (ret == -1) {
+		/* Handle other errors */
+		ret = -EINVAL;
 	}
 
-out:
 	spin_unlock(&rng->jent_lock);
 
 	return ret;
@@ -197,6 +190,10 @@ static int __init jent_mod_init(void)
 
 	ret = jent_entropy_init();
 	if (ret) {
+		/* Handle permanent health test error */
+		if (fips_enabled)
+			panic("jitterentropy: Initialization failed with host not compliant with requirements: %d\n", ret);
+
 		pr_info("jitterentropy: Initialization failed with host not compliant with requirements: %d\n", ret);
 		return -EFAULT;
 	}
diff --git a/crypto/jitterentropy.c b/crypto/jitterentropy.c
index 93bff3213823..22f48bf4c6f5 100644
--- a/crypto/jitterentropy.c
+++ b/crypto/jitterentropy.c
@@ -85,10 +85,14 @@ struct rand_data {
 				      * bit generation */
 
 	/* Repetition Count Test */
-	int rct_count;			/* Number of stuck values */
+	unsigned int rct_count;			/* Number of stuck values */
 
-	/* Adaptive Proportion Test for a significance level of 2^-30 */
+	/* Intermittent health test failure threshold of 2^-30 */
+#define JENT_RCT_CUTOFF		30	/* Taken from SP800-90B sec 4.4.1 */
 #define JENT_APT_CUTOFF		325	/* Taken from SP800-90B sec 4.4.2 */
+	/* Permanent health test failure threshold of 2^-60 */
+#define JENT_RCT_CUTOFF_PERMANENT	60
+#define JENT_APT_CUTOFF_PERMANENT	355
 #define JENT_APT_WINDOW_SIZE	512	/* Data window size */
 	/* LSB of time stamp to process */
 #define JENT_APT_LSB		16
@@ -97,8 +101,6 @@ struct rand_data {
 	unsigned int apt_count;		/* APT counter */
 	unsigned int apt_base;		/* APT base reference */
 	unsigned int apt_base_set:1;	/* APT base reference set? */
-
-	unsigned int health_failure:1;	/* Permanent health failure */
 };
 
 /* Flags that can be used to initialize the RNG */
@@ -169,19 +171,26 @@ static void jent_apt_insert(struct rand_data *ec, unsigned int delta_masked)
 		return;
 	}
 
-	if (delta_masked == ec->apt_base) {
+	if (delta_masked == ec->apt_base)
 		ec->apt_count++;
 
-		if (ec->apt_count >= JENT_APT_CUTOFF)
-			ec->health_failure = 1;
-	}
-
 	ec->apt_observations++;
 
 	if (ec->apt_observations >= JENT_APT_WINDOW_SIZE)
 		jent_apt_reset(ec, delta_masked);
 }
 
+/* APT health test failure detection */
+static int jent_apt_permanent_failure(struct rand_data *ec)
+{
+	return (ec->apt_count >= JENT_APT_CUTOFF_PERMANENT) ? 1 : 0;
+}
+
+static int jent_apt_failure(struct rand_data *ec)
+{
+	return (ec->apt_count >= JENT_APT_CUTOFF) ? 1 : 0;
+}
+
 /***************************************************************************
  * Stuck Test and its use as Repetition Count Test
  *
@@ -206,55 +215,14 @@ static void jent_apt_insert(struct rand_data *ec, unsigned int delta_masked)
  */
 static void jent_rct_insert(struct rand_data *ec, int stuck)
 {
-	/*
-	 * If we have a count less than zero, a previous RCT round identified
-	 * a failure. We will not overwrite it.
-	 */
-	if (ec->rct_count < 0)
-		return;
-
 	if (stuck) {
 		ec->rct_count++;
-
-		/*
-		 * The cutoff value is based on the following consideration:
-		 * alpha = 2^-30 as recommended in FIPS 140-2 IG 9.8.
-		 * In addition, we require an entropy value H of 1/OSR as this
-		 * is the minimum entropy required to provide full entropy.
-		 * Note, we collect 64 * OSR deltas for inserting them into
-		 * the entropy pool which should then have (close to) 64 bits
-		 * of entropy.
-		 *
-		 * Note, ec->rct_count (which equals to value B in the pseudo
-		 * code of SP800-90B section 4.4.1) starts with zero. Hence
-		 * we need to subtract one from the cutoff value as calculated
-		 * following SP800-90B.
-		 */
-		if ((unsigned int)ec->rct_count >= (31 * ec->osr)) {
-			ec->rct_count = -1;
-			ec->health_failure = 1;
-		}
 	} else {
+		/* Reset RCT */
 		ec->rct_count = 0;
 	}
 }
 
-/*
- * Is there an RCT health test failure?
- *
- * @ec [in] Reference to entropy collector
- *
- * @return
- * 	0 No health test failure
- * 	1 Permanent health test failure
- */
-static int jent_rct_failure(struct rand_data *ec)
-{
-	if (ec->rct_count < 0)
-		return 1;
-	return 0;
-}
-
 static inline __u64 jent_delta(__u64 prev, __u64 next)
 {
 #define JENT_UINT64_MAX		(__u64)(~((__u64) 0))
@@ -303,18 +271,26 @@ static int jent_stuck(struct rand_data *ec, __u64 current_delta)
 	return 0;
 }
 
-/*
- * Report any health test failures
- *
- * @ec [in] Reference to entropy collector
- *
- * @return
- * 	0 No health test failure
- * 	1 Permanent health test failure
- */
+/* RCT health test failure detection */
+static int jent_rct_permanent_failure(struct rand_data *ec)
+{
+	return (ec->rct_count >= JENT_RCT_CUTOFF_PERMANENT) ? 1 : 0;
+}
+
+static int jent_rct_failure(struct rand_data *ec)
+{
+	return (ec->rct_count >= JENT_RCT_CUTOFF) ? 1 : 0;
+}
+
+/* Report of health test failures */
 static int jent_health_failure(struct rand_data *ec)
 {
-	return ec->health_failure;
+	return jent_rct_failure(ec) | jent_apt_failure(ec);
+}
+
+static int jent_permanent_health_failure(struct rand_data *ec)
+{
+	return jent_rct_permanent_failure(ec) | jent_apt_permanent_failure(ec);
 }
 
 /***************************************************************************
@@ -600,8 +576,8 @@ static void jent_gen_entropy(struct rand_data *ec)
  *
  * The following error codes can occur:
  *	-1	entropy_collector is NULL
- *	-2	RCT failed
- *	-3	APT test failed
+ *	-2	Intermittent health failure
+ *	-3	Permanent health failure
  */
 int jent_read_entropy(struct rand_data *ec, unsigned char *data,
 		      unsigned int len)
@@ -616,39 +592,23 @@ int jent_read_entropy(struct rand_data *ec, unsigned char *data,
 
 		jent_gen_entropy(ec);
 
-		if (jent_health_failure(ec)) {
-			int ret;
-
-			if (jent_rct_failure(ec))
-				ret = -2;
-			else
-				ret = -3;
-
+		if (jent_permanent_health_failure(ec)) {
 			/*
-			 * Re-initialize the noise source
-			 *
-			 * If the health test fails, the Jitter RNG remains
-			 * in failure state and will return a health failure
-			 * during next invocation.
+			 * At this point, the Jitter RNG instance is considered
+			 * as a failed instance. There is no rerun of the
+			 * startup test any more, because the caller
+			 * is assumed to not further use this instance.
 			 */
-			if (jent_entropy_init())
-				return ret;
-
-			/* Set APT to initial state */
-			jent_apt_reset(ec, 0);
-			ec->apt_base_set = 0;
-
-			/* Set RCT to initial state */
-			ec->rct_count = 0;
-
-			/* Re-enable Jitter RNG */
-			ec->health_failure = 0;
-
+			return -3;
+		} else if (jent_health_failure(ec)) {
 			/*
-			 * Return the health test failure status to the
-			 * caller as the generated value is not appropriate.
+			 * Perform startup health tests and return permanent
+			 * error if it fails.
 			 */
-			return ret;
+			if (jent_entropy_init())
+				return -3;
+
+			return -2;
 		}
 
 		if ((DATA_SIZE_BITS / 8) < len)
diff --git a/crypto/jitterentropy.h b/crypto/jitterentropy.h
index b7397b617ef0..5cc583f6bc6b 100644
--- a/crypto/jitterentropy.h
+++ b/crypto/jitterentropy.h
@@ -2,7 +2,6 @@
 
 extern void *jent_zalloc(unsigned int len);
 extern void jent_zfree(void *ptr);
-extern void jent_panic(char *s);
 extern void jent_memcpy(void *dest, const void *src, unsigned int n);
 extern void jent_get_nstime(__u64 *out);
 
diff --git a/crypto/kpp.c b/crypto/kpp.c
index 678e871ce418..74f2e8e918fa 100644
--- a/crypto/kpp.c
+++ b/crypto/kpp.c
@@ -5,23 +5,20 @@
  * Copyright (c) 2016, Intel Corporation
  * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
  */
+
+#include <crypto/internal/kpp.h>
+#include <linux/cryptouser.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
-#include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/crypto.h>
-#include <crypto/algapi.h>
-#include <linux/cryptouser.h>
-#include <linux/compiler.h>
 #include <net/netlink.h>
-#include <crypto/kpp.h>
-#include <crypto/internal/kpp.h>
+
 #include "internal.h"
 
-#ifdef CONFIG_NET
-static int crypto_kpp_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int __maybe_unused crypto_kpp_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_kpp rkpp;
 
@@ -31,12 +28,6 @@ static int crypto_kpp_report(struct sk_buff *skb, struct crypto_alg *alg)
 
 	return nla_put(skb, CRYPTOCFGA_REPORT_KPP, sizeof(rkpp), &rkpp);
 }
-#else
-static int crypto_kpp_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
 
 static void crypto_kpp_show(struct seq_file *m, struct crypto_alg *alg)
 	__maybe_unused;
@@ -75,6 +66,29 @@ static void crypto_kpp_free_instance(struct crypto_instance *inst)
 	kpp->free(kpp);
 }
 
+static int __maybe_unused crypto_kpp_report_stat(
+	struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct kpp_alg *kpp = __crypto_kpp_alg(alg);
+	struct crypto_istat_kpp *istat;
+	struct crypto_stat_kpp rkpp;
+
+	istat = kpp_get_stat(kpp);
+
+	memset(&rkpp, 0, sizeof(rkpp));
+
+	strscpy(rkpp.type, "kpp", sizeof(rkpp.type));
+
+	rkpp.stat_setsecret_cnt = atomic64_read(&istat->setsecret_cnt);
+	rkpp.stat_generate_public_key_cnt =
+		atomic64_read(&istat->generate_public_key_cnt);
+	rkpp.stat_compute_shared_secret_cnt =
+		atomic64_read(&istat->compute_shared_secret_cnt);
+	rkpp.stat_err_cnt = atomic64_read(&istat->err_cnt);
+
+	return nla_put(skb, CRYPTOCFGA_STAT_KPP, sizeof(rkpp), &rkpp);
+}
+
 static const struct crypto_type crypto_kpp_type = {
 	.extsize = crypto_alg_extsize,
 	.init_tfm = crypto_kpp_init_tfm,
@@ -82,7 +96,12 @@ static const struct crypto_type crypto_kpp_type = {
 #ifdef CONFIG_PROC_FS
 	.show = crypto_kpp_show,
 #endif
+#ifdef CONFIG_CRYPTO_USER
 	.report = crypto_kpp_report,
+#endif
+#ifdef CONFIG_CRYPTO_STATS
+	.report_stat = crypto_kpp_report_stat,
+#endif
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_MASK,
 	.type = CRYPTO_ALG_TYPE_KPP,
@@ -112,11 +131,15 @@ EXPORT_SYMBOL_GPL(crypto_has_kpp);
 
 static void kpp_prepare_alg(struct kpp_alg *alg)
 {
+	struct crypto_istat_kpp *istat = kpp_get_stat(alg);
 	struct crypto_alg *base = &alg->base;
 
 	base->cra_type = &crypto_kpp_type;
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_KPP;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		memset(istat, 0, sizeof(*istat));
 }
 
 int crypto_register_kpp(struct kpp_alg *alg)
diff --git a/crypto/rng.c b/crypto/rng.c
index fea082b25fe4..ffde0f64fb25 100644
--- a/crypto/rng.c
+++ b/crypto/rng.c
@@ -8,17 +8,17 @@
  * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
  */
 
-#include <linux/atomic.h>
 #include <crypto/internal/rng.h>
+#include <linux/atomic.h>
+#include <linux/cryptouser.h>
 #include <linux/err.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/random.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/cryptouser.h>
-#include <linux/compiler.h>
 #include <net/netlink.h>
 
 #include "internal.h"
@@ -30,27 +30,30 @@ static int crypto_default_rng_refcnt;
 
 int crypto_rng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen)
 {
-	struct crypto_alg *alg = tfm->base.__crt_alg;
+	struct rng_alg *alg = crypto_rng_alg(tfm);
 	u8 *buf = NULL;
 	int err;
 
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_inc(&rng_get_stat(alg)->seed_cnt);
+
 	if (!seed && slen) {
 		buf = kmalloc(slen, GFP_KERNEL);
+		err = -ENOMEM;
 		if (!buf)
-			return -ENOMEM;
+			goto out;
 
 		err = get_random_bytes_wait(buf, slen);
 		if (err)
-			goto out;
+			goto free_buf;
 		seed = buf;
 	}
 
-	crypto_stats_get(alg);
-	err = crypto_rng_alg(tfm)->seed(tfm, seed, slen);
-	crypto_stats_rng_seed(alg, err);
-out:
+	err = alg->seed(tfm, seed, slen);
+free_buf:
 	kfree_sensitive(buf);
-	return err;
+out:
+	return crypto_rng_errstat(alg, err);
 }
 EXPORT_SYMBOL_GPL(crypto_rng_reset);
 
@@ -66,8 +69,8 @@ static unsigned int seedsize(struct crypto_alg *alg)
 	return ralg->seedsize;
 }
 
-#ifdef CONFIG_NET
-static int crypto_rng_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int __maybe_unused crypto_rng_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_rng rrng;
 
@@ -79,12 +82,6 @@ static int crypto_rng_report(struct sk_buff *skb, struct crypto_alg *alg)
 
 	return nla_put(skb, CRYPTOCFGA_REPORT_RNG, sizeof(rrng), &rrng);
 }
-#else
-static int crypto_rng_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
 
 static void crypto_rng_show(struct seq_file *m, struct crypto_alg *alg)
 	__maybe_unused;
@@ -94,13 +91,39 @@ static void crypto_rng_show(struct seq_file *m, struct crypto_alg *alg)
 	seq_printf(m, "seedsize     : %u\n", seedsize(alg));
 }
 
+static int __maybe_unused crypto_rng_report_stat(
+	struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct rng_alg *rng = __crypto_rng_alg(alg);
+	struct crypto_istat_rng *istat;
+	struct crypto_stat_rng rrng;
+
+	istat = rng_get_stat(rng);
+
+	memset(&rrng, 0, sizeof(rrng));
+
+	strscpy(rrng.type, "rng", sizeof(rrng.type));
+
+	rrng.stat_generate_cnt = atomic64_read(&istat->generate_cnt);
+	rrng.stat_generate_tlen = atomic64_read(&istat->generate_tlen);
+	rrng.stat_seed_cnt = atomic64_read(&istat->seed_cnt);
+	rrng.stat_err_cnt = atomic64_read(&istat->err_cnt);
+
+	return nla_put(skb, CRYPTOCFGA_STAT_RNG, sizeof(rrng), &rrng);
+}
+
 static const struct crypto_type crypto_rng_type = {
 	.extsize = crypto_alg_extsize,
 	.init_tfm = crypto_rng_init_tfm,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_rng_show,
 #endif
+#ifdef CONFIG_CRYPTO_USER
 	.report = crypto_rng_report,
+#endif
+#ifdef CONFIG_CRYPTO_STATS
+	.report_stat = crypto_rng_report_stat,
+#endif
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_MASK,
 	.type = CRYPTO_ALG_TYPE_RNG,
@@ -176,6 +199,7 @@ EXPORT_SYMBOL_GPL(crypto_del_default_rng);
 
 int crypto_register_rng(struct rng_alg *alg)
 {
+	struct crypto_istat_rng *istat = rng_get_stat(alg);
 	struct crypto_alg *base = &alg->base;
 
 	if (alg->seedsize > PAGE_SIZE / 8)
@@ -185,6 +209,9 @@ int crypto_register_rng(struct rng_alg *alg)
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_RNG;
 
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		memset(istat, 0, sizeof(*istat));
+
 	return crypto_register_alg(base);
 }
 EXPORT_SYMBOL_GPL(crypto_register_rng);
diff --git a/crypto/scompress.c b/crypto/scompress.c
index 738f4f8f0f41..24138b42a648 100644
--- a/crypto/scompress.c
+++ b/crypto/scompress.c
@@ -6,23 +6,22 @@
  * Copyright (c) 2016, Intel Corporation
  * Author: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
  */
-#include <linux/errno.h>
+
+#include <crypto/internal/acompress.h>
+#include <crypto/internal/scompress.h>
+#include <crypto/scatterwalk.h>
+#include <linux/cryptouser.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/scatterlist.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/crypto.h>
-#include <linux/compiler.h>
 #include <linux/vmalloc.h>
-#include <crypto/algapi.h>
-#include <linux/cryptouser.h>
 #include <net/netlink.h>
-#include <linux/scatterlist.h>
-#include <crypto/scatterwalk.h>
-#include <crypto/internal/acompress.h>
-#include <crypto/internal/scompress.h>
-#include "internal.h"
+
+#include "compress.h"
 
 struct scomp_scratch {
 	spinlock_t	lock;
@@ -38,8 +37,8 @@ static const struct crypto_type crypto_scomp_type;
 static int scomp_scratch_users;
 static DEFINE_MUTEX(scomp_lock);
 
-#ifdef CONFIG_NET
-static int crypto_scomp_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int __maybe_unused crypto_scomp_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_comp rscomp;
 
@@ -50,12 +49,6 @@ static int crypto_scomp_report(struct sk_buff *skb, struct crypto_alg *alg)
 	return nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS,
 		       sizeof(rscomp), &rscomp);
 }
-#else
-static int crypto_scomp_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
 
 static void crypto_scomp_show(struct seq_file *m, struct crypto_alg *alg)
 	__maybe_unused;
@@ -247,7 +240,12 @@ static const struct crypto_type crypto_scomp_type = {
 #ifdef CONFIG_PROC_FS
 	.show = crypto_scomp_show,
 #endif
+#ifdef CONFIG_CRYPTO_USER
 	.report = crypto_scomp_report,
+#endif
+#ifdef CONFIG_CRYPTO_STATS
+	.report_stat = crypto_acomp_report_stat,
+#endif
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_MASK,
 	.type = CRYPTO_ALG_TYPE_SCOMPRESS,
@@ -256,10 +254,11 @@ static const struct crypto_type crypto_scomp_type = {
 
 int crypto_register_scomp(struct scomp_alg *alg)
 {
-	struct crypto_alg *base = &alg->base;
+	struct crypto_alg *base = &alg->calg.base;
+
+	comp_prepare_alg(&alg->calg);
 
 	base->cra_type = &crypto_scomp_type;
-	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_SCOMPRESS;
 
 	return crypto_register_alg(base);
diff --git a/crypto/shash.c b/crypto/shash.c
index 58b46f198449..5845b7d59b2f 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -6,22 +6,31 @@
  */
 
 #include <crypto/scatterwalk.h>
-#include <crypto/internal/hash.h>
+#include <linux/cryptouser.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
-#include <linux/cryptouser.h>
+#include <linux/string.h>
 #include <net/netlink.h>
-#include <linux/compiler.h>
 
-#include "internal.h"
+#include "hash.h"
 
 #define MAX_SHASH_ALIGNMASK 63
 
 static const struct crypto_type crypto_shash_type;
 
+static inline struct crypto_istat_hash *shash_get_stat(struct shash_alg *alg)
+{
+	return hash_get_stat(&alg->halg);
+}
+
+static inline int crypto_shash_errstat(struct shash_alg *alg, int err)
+{
+	return crypto_hash_errstat(&alg->halg, err);
+}
+
 int shash_no_setkey(struct crypto_shash *tfm, const u8 *key,
 		    unsigned int keylen)
 {
@@ -114,11 +123,17 @@ int crypto_shash_update(struct shash_desc *desc, const u8 *data,
 	struct crypto_shash *tfm = desc->tfm;
 	struct shash_alg *shash = crypto_shash_alg(tfm);
 	unsigned long alignmask = crypto_shash_alignmask(tfm);
+	int err;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_add(len, &shash_get_stat(shash)->hash_tlen);
 
 	if ((unsigned long)data & alignmask)
-		return shash_update_unaligned(desc, data, len);
+		err = shash_update_unaligned(desc, data, len);
+	else
+		err = shash->update(desc, data, len);
 
-	return shash->update(desc, data, len);
+	return crypto_shash_errstat(shash, err);
 }
 EXPORT_SYMBOL_GPL(crypto_shash_update);
 
@@ -155,19 +170,25 @@ int crypto_shash_final(struct shash_desc *desc, u8 *out)
 	struct crypto_shash *tfm = desc->tfm;
 	struct shash_alg *shash = crypto_shash_alg(tfm);
 	unsigned long alignmask = crypto_shash_alignmask(tfm);
+	int err;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_inc(&shash_get_stat(shash)->hash_cnt);
 
 	if ((unsigned long)out & alignmask)
-		return shash_final_unaligned(desc, out);
+		err = shash_final_unaligned(desc, out);
+	else
+		err = shash->final(desc, out);
 
-	return shash->final(desc, out);
+	return crypto_shash_errstat(shash, err);
 }
 EXPORT_SYMBOL_GPL(crypto_shash_final);
 
 static int shash_finup_unaligned(struct shash_desc *desc, const u8 *data,
 				 unsigned int len, u8 *out)
 {
-	return crypto_shash_update(desc, data, len) ?:
-	       crypto_shash_final(desc, out);
+	return shash_update_unaligned(desc, data, len) ?:
+	       shash_final_unaligned(desc, out);
 }
 
 int crypto_shash_finup(struct shash_desc *desc, const u8 *data,
@@ -176,11 +197,22 @@ int crypto_shash_finup(struct shash_desc *desc, const u8 *data,
 	struct crypto_shash *tfm = desc->tfm;
 	struct shash_alg *shash = crypto_shash_alg(tfm);
 	unsigned long alignmask = crypto_shash_alignmask(tfm);
+	int err;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_hash *istat = shash_get_stat(shash);
+
+		atomic64_inc(&istat->hash_cnt);
+		atomic64_add(len, &istat->hash_tlen);
+	}
 
 	if (((unsigned long)data | (unsigned long)out) & alignmask)
-		return shash_finup_unaligned(desc, data, len, out);
+		err = shash_finup_unaligned(desc, data, len, out);
+	else
+		err = shash->finup(desc, data, len, out);
 
-	return shash->finup(desc, data, len, out);
+
+	return crypto_shash_errstat(shash, err);
 }
 EXPORT_SYMBOL_GPL(crypto_shash_finup);
 
@@ -188,7 +220,8 @@ static int shash_digest_unaligned(struct shash_desc *desc, const u8 *data,
 				  unsigned int len, u8 *out)
 {
 	return crypto_shash_init(desc) ?:
-	       crypto_shash_finup(desc, data, len, out);
+	       shash_update_unaligned(desc, data, len) ?:
+	       shash_final_unaligned(desc, out);
 }
 
 int crypto_shash_digest(struct shash_desc *desc, const u8 *data,
@@ -197,14 +230,23 @@ int crypto_shash_digest(struct shash_desc *desc, const u8 *data,
 	struct crypto_shash *tfm = desc->tfm;
 	struct shash_alg *shash = crypto_shash_alg(tfm);
 	unsigned long alignmask = crypto_shash_alignmask(tfm);
+	int err;
 
-	if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
-		return -ENOKEY;
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_hash *istat = shash_get_stat(shash);
 
-	if (((unsigned long)data | (unsigned long)out) & alignmask)
-		return shash_digest_unaligned(desc, data, len, out);
+		atomic64_inc(&istat->hash_cnt);
+		atomic64_add(len, &istat->hash_tlen);
+	}
 
-	return shash->digest(desc, data, len, out);
+	if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
+		err = -ENOKEY;
+	else if (((unsigned long)data | (unsigned long)out) & alignmask)
+		err = shash_digest_unaligned(desc, data, len, out);
+	else
+		err = shash->digest(desc, data, len, out);
+
+	return crypto_shash_errstat(shash, err);
 }
 EXPORT_SYMBOL_GPL(crypto_shash_digest);
 
@@ -403,6 +445,24 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm)
 	return 0;
 }
 
+struct crypto_ahash *crypto_clone_shash_ops_async(struct crypto_ahash *nhash,
+						  struct crypto_ahash *hash)
+{
+	struct crypto_shash **nctx = crypto_ahash_ctx(nhash);
+	struct crypto_shash **ctx = crypto_ahash_ctx(hash);
+	struct crypto_shash *shash;
+
+	shash = crypto_clone_shash(*ctx);
+	if (IS_ERR(shash)) {
+		crypto_free_ahash(nhash);
+		return ERR_CAST(shash);
+	}
+
+	*nctx = shash;
+
+	return nhash;
+}
+
 static void crypto_shash_exit_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_shash *hash = __crypto_shash_cast(tfm);
@@ -448,8 +508,8 @@ static void crypto_shash_free_instance(struct crypto_instance *inst)
 	shash->free(shash);
 }
 
-#ifdef CONFIG_NET
-static int crypto_shash_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int __maybe_unused crypto_shash_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_hash rhash;
 	struct shash_alg *salg = __crypto_shash_alg(alg);
@@ -463,12 +523,6 @@ static int crypto_shash_report(struct sk_buff *skb, struct crypto_alg *alg)
 
 	return nla_put(skb, CRYPTOCFGA_REPORT_HASH, sizeof(rhash), &rhash);
 }
-#else
-static int crypto_shash_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
 
 static void crypto_shash_show(struct seq_file *m, struct crypto_alg *alg)
 	__maybe_unused;
@@ -481,6 +535,12 @@ static void crypto_shash_show(struct seq_file *m, struct crypto_alg *alg)
 	seq_printf(m, "digestsize   : %u\n", salg->digestsize);
 }
 
+static int __maybe_unused crypto_shash_report_stat(
+	struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return crypto_hash_report_stat(skb, alg, "shash");
+}
+
 static const struct crypto_type crypto_shash_type = {
 	.extsize = crypto_alg_extsize,
 	.init_tfm = crypto_shash_init_tfm,
@@ -488,7 +548,12 @@ static const struct crypto_type crypto_shash_type = {
 #ifdef CONFIG_PROC_FS
 	.show = crypto_shash_show,
 #endif
+#ifdef CONFIG_CRYPTO_USER
 	.report = crypto_shash_report,
+#endif
+#ifdef CONFIG_CRYPTO_STATS
+	.report_stat = crypto_shash_report_stat,
+#endif
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_MASK,
 	.type = CRYPTO_ALG_TYPE_SHASH,
@@ -517,13 +582,62 @@ int crypto_has_shash(const char *alg_name, u32 type, u32 mask)
 }
 EXPORT_SYMBOL_GPL(crypto_has_shash);
 
-static int shash_prepare_alg(struct shash_alg *alg)
+struct crypto_shash *crypto_clone_shash(struct crypto_shash *hash)
+{
+	struct crypto_tfm *tfm = crypto_shash_tfm(hash);
+	struct shash_alg *alg = crypto_shash_alg(hash);
+	struct crypto_shash *nhash;
+	int err;
+
+	if (!crypto_shash_alg_has_setkey(alg)) {
+		tfm = crypto_tfm_get(tfm);
+		if (IS_ERR(tfm))
+			return ERR_CAST(tfm);
+
+		return hash;
+	}
+
+	if (!alg->clone_tfm)
+		return ERR_PTR(-ENOSYS);
+
+	nhash = crypto_clone_tfm(&crypto_shash_type, tfm);
+	if (IS_ERR(nhash))
+		return nhash;
+
+	nhash->descsize = hash->descsize;
+
+	err = alg->clone_tfm(nhash, hash);
+	if (err) {
+		crypto_free_shash(nhash);
+		return ERR_PTR(err);
+	}
+
+	return nhash;
+}
+EXPORT_SYMBOL_GPL(crypto_clone_shash);
+
+int hash_prepare_alg(struct hash_alg_common *alg)
 {
+	struct crypto_istat_hash *istat = hash_get_stat(alg);
 	struct crypto_alg *base = &alg->base;
 
-	if (alg->digestsize > HASH_MAX_DIGESTSIZE ||
-	    alg->descsize > HASH_MAX_DESCSIZE ||
-	    alg->statesize > HASH_MAX_STATESIZE)
+	if (alg->digestsize > HASH_MAX_DIGESTSIZE)
+		return -EINVAL;
+
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		memset(istat, 0, sizeof(*istat));
+
+	return 0;
+}
+
+static int shash_prepare_alg(struct shash_alg *alg)
+{
+	struct crypto_alg *base = &alg->halg.base;
+	int err;
+
+	if (alg->descsize > HASH_MAX_DESCSIZE)
 		return -EINVAL;
 
 	if (base->cra_alignmask > MAX_SHASH_ALIGNMASK)
@@ -532,8 +646,11 @@ static int shash_prepare_alg(struct shash_alg *alg)
 	if ((alg->export && !alg->import) || (alg->import && !alg->export))
 		return -EINVAL;
 
+	err = hash_prepare_alg(&alg->halg);
+	if (err)
+		return err;
+
 	base->cra_type = &crypto_shash_type;
-	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_SHASH;
 
 	if (!alg->finup)
@@ -543,7 +660,7 @@ static int shash_prepare_alg(struct shash_alg *alg)
 	if (!alg->export) {
 		alg->export = shash_default_export;
 		alg->import = shash_default_import;
-		alg->statesize = alg->descsize;
+		alg->halg.statesize = alg->descsize;
 	}
 	if (!alg->setkey)
 		alg->setkey = shash_no_setkey;
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 7bf4871fec80..6caca02d7e55 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -15,11 +15,14 @@
 #include <crypto/scatterwalk.h>
 #include <linux/bug.h>
 #include <linux/cryptouser.h>
-#include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/mm.h>
 #include <linux/module.h>
-#include <linux/rtnetlink.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/string.h>
 #include <net/netlink.h>
 
 #include "internal.h"
@@ -77,6 +80,35 @@ static inline u8 *skcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
+static inline struct skcipher_alg *__crypto_skcipher_alg(
+	struct crypto_alg *alg)
+{
+	return container_of(alg, struct skcipher_alg, base);
+}
+
+static inline struct crypto_istat_cipher *skcipher_get_stat(
+	struct skcipher_alg *alg)
+{
+#ifdef CONFIG_CRYPTO_STATS
+	return &alg->stat;
+#else
+	return NULL;
+#endif
+}
+
+static inline int crypto_skcipher_errstat(struct skcipher_alg *alg, int err)
+{
+	struct crypto_istat_cipher *istat = skcipher_get_stat(alg);
+
+	if (!IS_ENABLED(CONFIG_CRYPTO_STATS))
+		return err;
+
+	if (err && err != -EINPROGRESS && err != -EBUSY)
+		atomic64_inc(&istat->err_cnt);
+
+	return err;
+}
+
 static int skcipher_done_slow(struct skcipher_walk *walk, unsigned int bsize)
 {
 	u8 *addr;
@@ -605,34 +637,44 @@ EXPORT_SYMBOL_GPL(crypto_skcipher_setkey);
 int crypto_skcipher_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct crypto_alg *alg = tfm->base.__crt_alg;
-	unsigned int cryptlen = req->cryptlen;
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
 	int ret;
 
-	crypto_stats_get(alg);
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_cipher *istat = skcipher_get_stat(alg);
+
+		atomic64_inc(&istat->encrypt_cnt);
+		atomic64_add(req->cryptlen, &istat->encrypt_tlen);
+	}
+
 	if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		ret = -ENOKEY;
 	else
-		ret = crypto_skcipher_alg(tfm)->encrypt(req);
-	crypto_stats_skcipher_encrypt(cryptlen, ret, alg);
-	return ret;
+		ret = alg->encrypt(req);
+
+	return crypto_skcipher_errstat(alg, ret);
 }
 EXPORT_SYMBOL_GPL(crypto_skcipher_encrypt);
 
 int crypto_skcipher_decrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct crypto_alg *alg = tfm->base.__crt_alg;
-	unsigned int cryptlen = req->cryptlen;
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
 	int ret;
 
-	crypto_stats_get(alg);
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_cipher *istat = skcipher_get_stat(alg);
+
+		atomic64_inc(&istat->decrypt_cnt);
+		atomic64_add(req->cryptlen, &istat->decrypt_tlen);
+	}
+
 	if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		ret = -ENOKEY;
 	else
-		ret = crypto_skcipher_alg(tfm)->decrypt(req);
-	crypto_stats_skcipher_decrypt(cryptlen, ret, alg);
-	return ret;
+		ret = alg->decrypt(req);
+
+	return crypto_skcipher_errstat(alg, ret);
 }
 EXPORT_SYMBOL_GPL(crypto_skcipher_decrypt);
 
@@ -672,8 +714,7 @@ static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg)
 	__maybe_unused;
 static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg)
 {
-	struct skcipher_alg *skcipher = container_of(alg, struct skcipher_alg,
-						     base);
+	struct skcipher_alg *skcipher = __crypto_skcipher_alg(alg);
 
 	seq_printf(m, "type         : skcipher\n");
 	seq_printf(m, "async        : %s\n",
@@ -686,12 +727,11 @@ static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg)
 	seq_printf(m, "walksize     : %u\n", skcipher->walksize);
 }
 
-#ifdef CONFIG_NET
-static int crypto_skcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int __maybe_unused crypto_skcipher_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
+	struct skcipher_alg *skcipher = __crypto_skcipher_alg(alg);
 	struct crypto_report_blkcipher rblkcipher;
-	struct skcipher_alg *skcipher = container_of(alg, struct skcipher_alg,
-						     base);
 
 	memset(&rblkcipher, 0, sizeof(rblkcipher));
 
@@ -706,12 +746,28 @@ static int crypto_skcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
 	return nla_put(skb, CRYPTOCFGA_REPORT_BLKCIPHER,
 		       sizeof(rblkcipher), &rblkcipher);
 }
-#else
-static int crypto_skcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+
+static int __maybe_unused crypto_skcipher_report_stat(
+	struct sk_buff *skb, struct crypto_alg *alg)
 {
-	return -ENOSYS;
+	struct skcipher_alg *skcipher = __crypto_skcipher_alg(alg);
+	struct crypto_istat_cipher *istat;
+	struct crypto_stat_cipher rcipher;
+
+	istat = skcipher_get_stat(skcipher);
+
+	memset(&rcipher, 0, sizeof(rcipher));
+
+	strscpy(rcipher.type, "cipher", sizeof(rcipher.type));
+
+	rcipher.stat_encrypt_cnt = atomic64_read(&istat->encrypt_cnt);
+	rcipher.stat_encrypt_tlen = atomic64_read(&istat->encrypt_tlen);
+	rcipher.stat_decrypt_cnt =  atomic64_read(&istat->decrypt_cnt);
+	rcipher.stat_decrypt_tlen = atomic64_read(&istat->decrypt_tlen);
+	rcipher.stat_err_cnt =  atomic64_read(&istat->err_cnt);
+
+	return nla_put(skb, CRYPTOCFGA_STAT_CIPHER, sizeof(rcipher), &rcipher);
 }
-#endif
 
 static const struct crypto_type crypto_skcipher_type = {
 	.extsize = crypto_alg_extsize,
@@ -720,7 +776,12 @@ static const struct crypto_type crypto_skcipher_type = {
 #ifdef CONFIG_PROC_FS
 	.show = crypto_skcipher_show,
 #endif
+#ifdef CONFIG_CRYPTO_USER
 	.report = crypto_skcipher_report,
+#endif
+#ifdef CONFIG_CRYPTO_STATS
+	.report_stat = crypto_skcipher_report_stat,
+#endif
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_MASK,
 	.type = CRYPTO_ALG_TYPE_SKCIPHER,
@@ -775,6 +836,7 @@ EXPORT_SYMBOL_GPL(crypto_has_skcipher);
 
 static int skcipher_prepare_alg(struct skcipher_alg *alg)
 {
+	struct crypto_istat_cipher *istat = skcipher_get_stat(alg);
 	struct crypto_alg *base = &alg->base;
 
 	if (alg->ivsize > PAGE_SIZE / 8 || alg->chunksize > PAGE_SIZE / 8 ||
@@ -790,6 +852,9 @@ static int skcipher_prepare_alg(struct skcipher_alg *alg)
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_SKCIPHER;
 
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		memset(istat, 0, sizeof(*istat));
+
 	return 0;
 }
 
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 6521feec7756..202ca1a3105d 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -25,14 +25,17 @@
 #include <linux/err.h>
 #include <linux/fips.h>
 #include <linux/init.h>
-#include <linux/gfp.h>
+#include <linux/interrupt.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/scatterlist.h>
+#include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/moduleparam.h>
-#include <linux/jiffies.h>
 #include <linux/timex.h>
-#include <linux/interrupt.h>
+
+#include "internal.h"
 #include "tcrypt.h"
 
 /*
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index c91e93ece20b..216878c8bc3d 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -860,12 +860,50 @@ static int prepare_keybuf(const u8 *key, unsigned int ksize,
 
 #ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
 
+/*
+ * The fuzz tests use prandom instead of the normal Linux RNG since they don't
+ * need cryptographically secure random numbers.  This greatly improves the
+ * performance of these tests, especially if they are run before the Linux RNG
+ * has been initialized or if they are run on a lockdep-enabled kernel.
+ */
+
+static inline void init_rnd_state(struct rnd_state *rng)
+{
+	prandom_seed_state(rng, get_random_u64());
+}
+
+static inline u8 prandom_u8(struct rnd_state *rng)
+{
+	return prandom_u32_state(rng);
+}
+
+static inline u32 prandom_u32_below(struct rnd_state *rng, u32 ceil)
+{
+	/*
+	 * This is slightly biased for non-power-of-2 values of 'ceil', but this
+	 * isn't important here.
+	 */
+	return prandom_u32_state(rng) % ceil;
+}
+
+static inline bool prandom_bool(struct rnd_state *rng)
+{
+	return prandom_u32_below(rng, 2);
+}
+
+static inline u32 prandom_u32_inclusive(struct rnd_state *rng,
+					u32 floor, u32 ceil)
+{
+	return floor + prandom_u32_below(rng, ceil - floor + 1);
+}
+
 /* Generate a random length in range [0, max_len], but prefer smaller values */
-static unsigned int generate_random_length(unsigned int max_len)
+static unsigned int generate_random_length(struct rnd_state *rng,
+					   unsigned int max_len)
 {
-	unsigned int len = get_random_u32_below(max_len + 1);
+	unsigned int len = prandom_u32_below(rng, max_len + 1);
 
-	switch (get_random_u32_below(4)) {
+	switch (prandom_u32_below(rng, 4)) {
 	case 0:
 		return len % 64;
 	case 1:
@@ -878,43 +916,44 @@ static unsigned int generate_random_length(unsigned int max_len)
 }
 
 /* Flip a random bit in the given nonempty data buffer */
-static void flip_random_bit(u8 *buf, size_t size)
+static void flip_random_bit(struct rnd_state *rng, u8 *buf, size_t size)
 {
 	size_t bitpos;
 
-	bitpos = get_random_u32_below(size * 8);
+	bitpos = prandom_u32_below(rng, size * 8);
 	buf[bitpos / 8] ^= 1 << (bitpos % 8);
 }
 
 /* Flip a random byte in the given nonempty data buffer */
-static void flip_random_byte(u8 *buf, size_t size)
+static void flip_random_byte(struct rnd_state *rng, u8 *buf, size_t size)
 {
-	buf[get_random_u32_below(size)] ^= 0xff;
+	buf[prandom_u32_below(rng, size)] ^= 0xff;
 }
 
 /* Sometimes make some random changes to the given nonempty data buffer */
-static void mutate_buffer(u8 *buf, size_t size)
+static void mutate_buffer(struct rnd_state *rng, u8 *buf, size_t size)
 {
 	size_t num_flips;
 	size_t i;
 
 	/* Sometimes flip some bits */
-	if (get_random_u32_below(4) == 0) {
-		num_flips = min_t(size_t, 1 << get_random_u32_below(8), size * 8);
+	if (prandom_u32_below(rng, 4) == 0) {
+		num_flips = min_t(size_t, 1 << prandom_u32_below(rng, 8),
+				  size * 8);
 		for (i = 0; i < num_flips; i++)
-			flip_random_bit(buf, size);
+			flip_random_bit(rng, buf, size);
 	}
 
 	/* Sometimes flip some bytes */
-	if (get_random_u32_below(4) == 0) {
-		num_flips = min_t(size_t, 1 << get_random_u32_below(8), size);
+	if (prandom_u32_below(rng, 4) == 0) {
+		num_flips = min_t(size_t, 1 << prandom_u32_below(rng, 8), size);
 		for (i = 0; i < num_flips; i++)
-			flip_random_byte(buf, size);
+			flip_random_byte(rng, buf, size);
 	}
 }
 
 /* Randomly generate 'count' bytes, but sometimes make them "interesting" */
-static void generate_random_bytes(u8 *buf, size_t count)
+static void generate_random_bytes(struct rnd_state *rng, u8 *buf, size_t count)
 {
 	u8 b;
 	u8 increment;
@@ -923,11 +962,11 @@ static void generate_random_bytes(u8 *buf, size_t count)
 	if (count == 0)
 		return;
 
-	switch (get_random_u32_below(8)) { /* Choose a generation strategy */
+	switch (prandom_u32_below(rng, 8)) { /* Choose a generation strategy */
 	case 0:
 	case 1:
 		/* All the same byte, plus optional mutations */
-		switch (get_random_u32_below(4)) {
+		switch (prandom_u32_below(rng, 4)) {
 		case 0:
 			b = 0x00;
 			break;
@@ -935,28 +974,28 @@ static void generate_random_bytes(u8 *buf, size_t count)
 			b = 0xff;
 			break;
 		default:
-			b = get_random_u8();
+			b = prandom_u8(rng);
 			break;
 		}
 		memset(buf, b, count);
-		mutate_buffer(buf, count);
+		mutate_buffer(rng, buf, count);
 		break;
 	case 2:
 		/* Ascending or descending bytes, plus optional mutations */
-		increment = get_random_u8();
-		b = get_random_u8();
+		increment = prandom_u8(rng);
+		b = prandom_u8(rng);
 		for (i = 0; i < count; i++, b += increment)
 			buf[i] = b;
-		mutate_buffer(buf, count);
+		mutate_buffer(rng, buf, count);
 		break;
 	default:
 		/* Fully random bytes */
-		for (i = 0; i < count; i++)
-			buf[i] = get_random_u8();
+		prandom_bytes_state(rng, buf, count);
 	}
 }
 
-static char *generate_random_sgl_divisions(struct test_sg_division *divs,
+static char *generate_random_sgl_divisions(struct rnd_state *rng,
+					   struct test_sg_division *divs,
 					   size_t max_divs, char *p, char *end,
 					   bool gen_flushes, u32 req_flags)
 {
@@ -967,24 +1006,26 @@ static char *generate_random_sgl_divisions(struct test_sg_division *divs,
 		unsigned int this_len;
 		const char *flushtype_str;
 
-		if (div == &divs[max_divs - 1] || get_random_u32_below(2) == 0)
+		if (div == &divs[max_divs - 1] || prandom_bool(rng))
 			this_len = remaining;
 		else
-			this_len = get_random_u32_inclusive(1, remaining);
+			this_len = prandom_u32_inclusive(rng, 1, remaining);
 		div->proportion_of_total = this_len;
 
-		if (get_random_u32_below(4) == 0)
-			div->offset = get_random_u32_inclusive(PAGE_SIZE - 128, PAGE_SIZE - 1);
-		else if (get_random_u32_below(2) == 0)
-			div->offset = get_random_u32_below(32);
+		if (prandom_u32_below(rng, 4) == 0)
+			div->offset = prandom_u32_inclusive(rng,
+							    PAGE_SIZE - 128,
+							    PAGE_SIZE - 1);
+		else if (prandom_bool(rng))
+			div->offset = prandom_u32_below(rng, 32);
 		else
-			div->offset = get_random_u32_below(PAGE_SIZE);
-		if (get_random_u32_below(8) == 0)
+			div->offset = prandom_u32_below(rng, PAGE_SIZE);
+		if (prandom_u32_below(rng, 8) == 0)
 			div->offset_relative_to_alignmask = true;
 
 		div->flush_type = FLUSH_TYPE_NONE;
 		if (gen_flushes) {
-			switch (get_random_u32_below(4)) {
+			switch (prandom_u32_below(rng, 4)) {
 			case 0:
 				div->flush_type = FLUSH_TYPE_REIMPORT;
 				break;
@@ -996,7 +1037,7 @@ static char *generate_random_sgl_divisions(struct test_sg_division *divs,
 
 		if (div->flush_type != FLUSH_TYPE_NONE &&
 		    !(req_flags & CRYPTO_TFM_REQ_MAY_SLEEP) &&
-		    get_random_u32_below(2) == 0)
+		    prandom_bool(rng))
 			div->nosimd = true;
 
 		switch (div->flush_type) {
@@ -1031,7 +1072,8 @@ static char *generate_random_sgl_divisions(struct test_sg_division *divs,
 }
 
 /* Generate a random testvec_config for fuzz testing */
-static void generate_random_testvec_config(struct testvec_config *cfg,
+static void generate_random_testvec_config(struct rnd_state *rng,
+					   struct testvec_config *cfg,
 					   char *name, size_t max_namelen)
 {
 	char *p = name;
@@ -1043,7 +1085,7 @@ static void generate_random_testvec_config(struct testvec_config *cfg,
 
 	p += scnprintf(p, end - p, "random:");
 
-	switch (get_random_u32_below(4)) {
+	switch (prandom_u32_below(rng, 4)) {
 	case 0:
 	case 1:
 		cfg->inplace_mode = OUT_OF_PLACE;
@@ -1058,12 +1100,12 @@ static void generate_random_testvec_config(struct testvec_config *cfg,
 		break;
 	}
 
-	if (get_random_u32_below(2) == 0) {
+	if (prandom_bool(rng)) {
 		cfg->req_flags |= CRYPTO_TFM_REQ_MAY_SLEEP;
 		p += scnprintf(p, end - p, " may_sleep");
 	}
 
-	switch (get_random_u32_below(4)) {
+	switch (prandom_u32_below(rng, 4)) {
 	case 0:
 		cfg->finalization_type = FINALIZATION_TYPE_FINAL;
 		p += scnprintf(p, end - p, " use_final");
@@ -1078,36 +1120,37 @@ static void generate_random_testvec_config(struct testvec_config *cfg,
 		break;
 	}
 
-	if (!(cfg->req_flags & CRYPTO_TFM_REQ_MAY_SLEEP) &&
-	    get_random_u32_below(2) == 0) {
+	if (!(cfg->req_flags & CRYPTO_TFM_REQ_MAY_SLEEP) && prandom_bool(rng)) {
 		cfg->nosimd = true;
 		p += scnprintf(p, end - p, " nosimd");
 	}
 
 	p += scnprintf(p, end - p, " src_divs=[");
-	p = generate_random_sgl_divisions(cfg->src_divs,
+	p = generate_random_sgl_divisions(rng, cfg->src_divs,
 					  ARRAY_SIZE(cfg->src_divs), p, end,
 					  (cfg->finalization_type !=
 					   FINALIZATION_TYPE_DIGEST),
 					  cfg->req_flags);
 	p += scnprintf(p, end - p, "]");
 
-	if (cfg->inplace_mode == OUT_OF_PLACE && get_random_u32_below(2) == 0) {
+	if (cfg->inplace_mode == OUT_OF_PLACE && prandom_bool(rng)) {
 		p += scnprintf(p, end - p, " dst_divs=[");
-		p = generate_random_sgl_divisions(cfg->dst_divs,
+		p = generate_random_sgl_divisions(rng, cfg->dst_divs,
 						  ARRAY_SIZE(cfg->dst_divs),
 						  p, end, false,
 						  cfg->req_flags);
 		p += scnprintf(p, end - p, "]");
 	}
 
-	if (get_random_u32_below(2) == 0) {
-		cfg->iv_offset = get_random_u32_inclusive(1, MAX_ALGAPI_ALIGNMASK);
+	if (prandom_bool(rng)) {
+		cfg->iv_offset = prandom_u32_inclusive(rng, 1,
+						       MAX_ALGAPI_ALIGNMASK);
 		p += scnprintf(p, end - p, " iv_offset=%u", cfg->iv_offset);
 	}
 
-	if (get_random_u32_below(2) == 0) {
-		cfg->key_offset = get_random_u32_inclusive(1, MAX_ALGAPI_ALIGNMASK);
+	if (prandom_bool(rng)) {
+		cfg->key_offset = prandom_u32_inclusive(rng, 1,
+							MAX_ALGAPI_ALIGNMASK);
 		p += scnprintf(p, end - p, " key_offset=%u", cfg->key_offset);
 	}
 
@@ -1620,11 +1663,14 @@ static int test_hash_vec(const struct hash_testvec *vec, unsigned int vec_num,
 
 #ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
 	if (!noextratests) {
+		struct rnd_state rng;
 		struct testvec_config cfg;
 		char cfgname[TESTVEC_CONFIG_NAMELEN];
 
+		init_rnd_state(&rng);
+
 		for (i = 0; i < fuzz_iterations; i++) {
-			generate_random_testvec_config(&cfg, cfgname,
+			generate_random_testvec_config(&rng, &cfg, cfgname,
 						       sizeof(cfgname));
 			err = test_hash_vec_cfg(vec, vec_name, &cfg,
 						req, desc, tsgl, hashstate);
@@ -1642,15 +1688,16 @@ static int test_hash_vec(const struct hash_testvec *vec, unsigned int vec_num,
  * Generate a hash test vector from the given implementation.
  * Assumes the buffers in 'vec' were already allocated.
  */
-static void generate_random_hash_testvec(struct shash_desc *desc,
+static void generate_random_hash_testvec(struct rnd_state *rng,
+					 struct shash_desc *desc,
 					 struct hash_testvec *vec,
 					 unsigned int maxkeysize,
 					 unsigned int maxdatasize,
 					 char *name, size_t max_namelen)
 {
 	/* Data */
-	vec->psize = generate_random_length(maxdatasize);
-	generate_random_bytes((u8 *)vec->plaintext, vec->psize);
+	vec->psize = generate_random_length(rng, maxdatasize);
+	generate_random_bytes(rng, (u8 *)vec->plaintext, vec->psize);
 
 	/*
 	 * Key: length in range [1, maxkeysize], but usually choose maxkeysize.
@@ -1660,9 +1707,9 @@ static void generate_random_hash_testvec(struct shash_desc *desc,
 	vec->ksize = 0;
 	if (maxkeysize) {
 		vec->ksize = maxkeysize;
-		if (get_random_u32_below(4) == 0)
-			vec->ksize = get_random_u32_inclusive(1, maxkeysize);
-		generate_random_bytes((u8 *)vec->key, vec->ksize);
+		if (prandom_u32_below(rng, 4) == 0)
+			vec->ksize = prandom_u32_inclusive(rng, 1, maxkeysize);
+		generate_random_bytes(rng, (u8 *)vec->key, vec->ksize);
 
 		vec->setkey_error = crypto_shash_setkey(desc->tfm, vec->key,
 							vec->ksize);
@@ -1696,6 +1743,7 @@ static int test_hash_vs_generic_impl(const char *generic_driver,
 	const unsigned int maxdatasize = (2 * PAGE_SIZE) - TESTMGR_POISON_LEN;
 	const char *algname = crypto_hash_alg_common(tfm)->base.cra_name;
 	const char *driver = crypto_ahash_driver_name(tfm);
+	struct rnd_state rng;
 	char _generic_driver[CRYPTO_MAX_ALG_NAME];
 	struct crypto_shash *generic_tfm = NULL;
 	struct shash_desc *generic_desc = NULL;
@@ -1709,6 +1757,8 @@ static int test_hash_vs_generic_impl(const char *generic_driver,
 	if (noextratests)
 		return 0;
 
+	init_rnd_state(&rng);
+
 	if (!generic_driver) { /* Use default naming convention? */
 		err = build_generic_driver_name(algname, _generic_driver);
 		if (err)
@@ -1777,10 +1827,11 @@ static int test_hash_vs_generic_impl(const char *generic_driver,
 	}
 
 	for (i = 0; i < fuzz_iterations * 8; i++) {
-		generate_random_hash_testvec(generic_desc, &vec,
+		generate_random_hash_testvec(&rng, generic_desc, &vec,
 					     maxkeysize, maxdatasize,
 					     vec_name, sizeof(vec_name));
-		generate_random_testvec_config(cfg, cfgname, sizeof(cfgname));
+		generate_random_testvec_config(&rng, cfg, cfgname,
+					       sizeof(cfgname));
 
 		err = test_hash_vec_cfg(&vec, vec_name, cfg,
 					req, desc, tsgl, hashstate);
@@ -2182,11 +2233,14 @@ static int test_aead_vec(int enc, const struct aead_testvec *vec,
 
 #ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
 	if (!noextratests) {
+		struct rnd_state rng;
 		struct testvec_config cfg;
 		char cfgname[TESTVEC_CONFIG_NAMELEN];
 
+		init_rnd_state(&rng);
+
 		for (i = 0; i < fuzz_iterations; i++) {
-			generate_random_testvec_config(&cfg, cfgname,
+			generate_random_testvec_config(&rng, &cfg, cfgname,
 						       sizeof(cfgname));
 			err = test_aead_vec_cfg(enc, vec, vec_name,
 						&cfg, req, tsgls);
@@ -2202,6 +2256,7 @@ static int test_aead_vec(int enc, const struct aead_testvec *vec,
 #ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
 
 struct aead_extra_tests_ctx {
+	struct rnd_state rng;
 	struct aead_request *req;
 	struct crypto_aead *tfm;
 	const struct alg_test_desc *test_desc;
@@ -2220,24 +2275,26 @@ struct aead_extra_tests_ctx {
  * here means the full ciphertext including the authentication tag.  The
  * authentication tag (and hence also the ciphertext) is assumed to be nonempty.
  */
-static void mutate_aead_message(struct aead_testvec *vec, bool aad_iv,
+static void mutate_aead_message(struct rnd_state *rng,
+				struct aead_testvec *vec, bool aad_iv,
 				unsigned int ivsize)
 {
 	const unsigned int aad_tail_size = aad_iv ? ivsize : 0;
 	const unsigned int authsize = vec->clen - vec->plen;
 
-	if (get_random_u32_below(2) == 0 && vec->alen > aad_tail_size) {
+	if (prandom_bool(rng) && vec->alen > aad_tail_size) {
 		 /* Mutate the AAD */
-		flip_random_bit((u8 *)vec->assoc, vec->alen - aad_tail_size);
-		if (get_random_u32_below(2) == 0)
+		flip_random_bit(rng, (u8 *)vec->assoc,
+				vec->alen - aad_tail_size);
+		if (prandom_bool(rng))
 			return;
 	}
-	if (get_random_u32_below(2) == 0) {
+	if (prandom_bool(rng)) {
 		/* Mutate auth tag (assuming it's at the end of ciphertext) */
-		flip_random_bit((u8 *)vec->ctext + vec->plen, authsize);
+		flip_random_bit(rng, (u8 *)vec->ctext + vec->plen, authsize);
 	} else {
 		/* Mutate any part of the ciphertext */
-		flip_random_bit((u8 *)vec->ctext, vec->clen);
+		flip_random_bit(rng, (u8 *)vec->ctext, vec->clen);
 	}
 }
 
@@ -2248,7 +2305,8 @@ static void mutate_aead_message(struct aead_testvec *vec, bool aad_iv,
  */
 #define MIN_COLLISION_FREE_AUTHSIZE 8
 
-static void generate_aead_message(struct aead_request *req,
+static void generate_aead_message(struct rnd_state *rng,
+				  struct aead_request *req,
 				  const struct aead_test_suite *suite,
 				  struct aead_testvec *vec,
 				  bool prefer_inauthentic)
@@ -2257,17 +2315,18 @@ static void generate_aead_message(struct aead_request *req,
 	const unsigned int ivsize = crypto_aead_ivsize(tfm);
 	const unsigned int authsize = vec->clen - vec->plen;
 	const bool inauthentic = (authsize >= MIN_COLLISION_FREE_AUTHSIZE) &&
-				 (prefer_inauthentic || get_random_u32_below(4) == 0);
+				 (prefer_inauthentic ||
+				  prandom_u32_below(rng, 4) == 0);
 
 	/* Generate the AAD. */
-	generate_random_bytes((u8 *)vec->assoc, vec->alen);
+	generate_random_bytes(rng, (u8 *)vec->assoc, vec->alen);
 	if (suite->aad_iv && vec->alen >= ivsize)
 		/* Avoid implementation-defined behavior. */
 		memcpy((u8 *)vec->assoc + vec->alen - ivsize, vec->iv, ivsize);
 
-	if (inauthentic && get_random_u32_below(2) == 0) {
+	if (inauthentic && prandom_bool(rng)) {
 		/* Generate a random ciphertext. */
-		generate_random_bytes((u8 *)vec->ctext, vec->clen);
+		generate_random_bytes(rng, (u8 *)vec->ctext, vec->clen);
 	} else {
 		int i = 0;
 		struct scatterlist src[2], dst;
@@ -2279,7 +2338,7 @@ static void generate_aead_message(struct aead_request *req,
 		if (vec->alen)
 			sg_set_buf(&src[i++], vec->assoc, vec->alen);
 		if (vec->plen) {
-			generate_random_bytes((u8 *)vec->ptext, vec->plen);
+			generate_random_bytes(rng, (u8 *)vec->ptext, vec->plen);
 			sg_set_buf(&src[i++], vec->ptext, vec->plen);
 		}
 		sg_init_one(&dst, vec->ctext, vec->alen + vec->clen);
@@ -2299,7 +2358,7 @@ static void generate_aead_message(struct aead_request *req,
 		 * Mutate the authentic (ciphertext, AAD) pair to get an
 		 * inauthentic one.
 		 */
-		mutate_aead_message(vec, suite->aad_iv, ivsize);
+		mutate_aead_message(rng, vec, suite->aad_iv, ivsize);
 	}
 	vec->novrfy = 1;
 	if (suite->einval_allowed)
@@ -2313,7 +2372,8 @@ static void generate_aead_message(struct aead_request *req,
  * If 'prefer_inauthentic' is true, then this function will generate inauthentic
  * test vectors (i.e. vectors with 'vec->novrfy=1') more often.
  */
-static void generate_random_aead_testvec(struct aead_request *req,
+static void generate_random_aead_testvec(struct rnd_state *rng,
+					 struct aead_request *req,
 					 struct aead_testvec *vec,
 					 const struct aead_test_suite *suite,
 					 unsigned int maxkeysize,
@@ -2329,18 +2389,18 @@ static void generate_random_aead_testvec(struct aead_request *req,
 
 	/* Key: length in [0, maxkeysize], but usually choose maxkeysize */
 	vec->klen = maxkeysize;
-	if (get_random_u32_below(4) == 0)
-		vec->klen = get_random_u32_below(maxkeysize + 1);
-	generate_random_bytes((u8 *)vec->key, vec->klen);
+	if (prandom_u32_below(rng, 4) == 0)
+		vec->klen = prandom_u32_below(rng, maxkeysize + 1);
+	generate_random_bytes(rng, (u8 *)vec->key, vec->klen);
 	vec->setkey_error = crypto_aead_setkey(tfm, vec->key, vec->klen);
 
 	/* IV */
-	generate_random_bytes((u8 *)vec->iv, ivsize);
+	generate_random_bytes(rng, (u8 *)vec->iv, ivsize);
 
 	/* Tag length: in [0, maxauthsize], but usually choose maxauthsize */
 	authsize = maxauthsize;
-	if (get_random_u32_below(4) == 0)
-		authsize = get_random_u32_below(maxauthsize + 1);
+	if (prandom_u32_below(rng, 4) == 0)
+		authsize = prandom_u32_below(rng, maxauthsize + 1);
 	if (prefer_inauthentic && authsize < MIN_COLLISION_FREE_AUTHSIZE)
 		authsize = MIN_COLLISION_FREE_AUTHSIZE;
 	if (WARN_ON(authsize > maxdatasize))
@@ -2349,11 +2409,11 @@ static void generate_random_aead_testvec(struct aead_request *req,
 	vec->setauthsize_error = crypto_aead_setauthsize(tfm, authsize);
 
 	/* AAD, plaintext, and ciphertext lengths */
-	total_len = generate_random_length(maxdatasize);
-	if (get_random_u32_below(4) == 0)
+	total_len = generate_random_length(rng, maxdatasize);
+	if (prandom_u32_below(rng, 4) == 0)
 		vec->alen = 0;
 	else
-		vec->alen = generate_random_length(total_len);
+		vec->alen = generate_random_length(rng, total_len);
 	vec->plen = total_len - vec->alen;
 	vec->clen = vec->plen + authsize;
 
@@ -2364,7 +2424,7 @@ static void generate_random_aead_testvec(struct aead_request *req,
 	vec->novrfy = 0;
 	vec->crypt_error = 0;
 	if (vec->setkey_error == 0 && vec->setauthsize_error == 0)
-		generate_aead_message(req, suite, vec, prefer_inauthentic);
+		generate_aead_message(rng, req, suite, vec, prefer_inauthentic);
 	snprintf(name, max_namelen,
 		 "\"random: alen=%u plen=%u authsize=%u klen=%u novrfy=%d\"",
 		 vec->alen, vec->plen, authsize, vec->klen, vec->novrfy);
@@ -2376,7 +2436,7 @@ static void try_to_generate_inauthentic_testvec(
 	int i;
 
 	for (i = 0; i < 10; i++) {
-		generate_random_aead_testvec(ctx->req, &ctx->vec,
+		generate_random_aead_testvec(&ctx->rng, ctx->req, &ctx->vec,
 					     &ctx->test_desc->suite.aead,
 					     ctx->maxkeysize, ctx->maxdatasize,
 					     ctx->vec_name,
@@ -2407,7 +2467,8 @@ static int test_aead_inauthentic_inputs(struct aead_extra_tests_ctx *ctx)
 		 */
 		try_to_generate_inauthentic_testvec(ctx);
 		if (ctx->vec.novrfy) {
-			generate_random_testvec_config(&ctx->cfg, ctx->cfgname,
+			generate_random_testvec_config(&ctx->rng, &ctx->cfg,
+						       ctx->cfgname,
 						       sizeof(ctx->cfgname));
 			err = test_aead_vec_cfg(DECRYPT, &ctx->vec,
 						ctx->vec_name, &ctx->cfg,
@@ -2497,12 +2558,13 @@ static int test_aead_vs_generic_impl(struct aead_extra_tests_ctx *ctx)
 	 * the other implementation against them.
 	 */
 	for (i = 0; i < fuzz_iterations * 8; i++) {
-		generate_random_aead_testvec(generic_req, &ctx->vec,
+		generate_random_aead_testvec(&ctx->rng, generic_req, &ctx->vec,
 					     &ctx->test_desc->suite.aead,
 					     ctx->maxkeysize, ctx->maxdatasize,
 					     ctx->vec_name,
 					     sizeof(ctx->vec_name), false);
-		generate_random_testvec_config(&ctx->cfg, ctx->cfgname,
+		generate_random_testvec_config(&ctx->rng, &ctx->cfg,
+					       ctx->cfgname,
 					       sizeof(ctx->cfgname));
 		if (!ctx->vec.novrfy) {
 			err = test_aead_vec_cfg(ENCRYPT, &ctx->vec,
@@ -2541,6 +2603,7 @@ static int test_aead_extra(const struct alg_test_desc *test_desc,
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
+	init_rnd_state(&ctx->rng);
 	ctx->req = req;
 	ctx->tfm = crypto_aead_reqtfm(req);
 	ctx->test_desc = test_desc;
@@ -2930,11 +2993,14 @@ static int test_skcipher_vec(int enc, const struct cipher_testvec *vec,
 
 #ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
 	if (!noextratests) {
+		struct rnd_state rng;
 		struct testvec_config cfg;
 		char cfgname[TESTVEC_CONFIG_NAMELEN];
 
+		init_rnd_state(&rng);
+
 		for (i = 0; i < fuzz_iterations; i++) {
-			generate_random_testvec_config(&cfg, cfgname,
+			generate_random_testvec_config(&rng, &cfg, cfgname,
 						       sizeof(cfgname));
 			err = test_skcipher_vec_cfg(enc, vec, vec_name,
 						    &cfg, req, tsgls);
@@ -2952,7 +3018,8 @@ static int test_skcipher_vec(int enc, const struct cipher_testvec *vec,
  * Generate a symmetric cipher test vector from the given implementation.
  * Assumes the buffers in 'vec' were already allocated.
  */
-static void generate_random_cipher_testvec(struct skcipher_request *req,
+static void generate_random_cipher_testvec(struct rnd_state *rng,
+					   struct skcipher_request *req,
 					   struct cipher_testvec *vec,
 					   unsigned int maxdatasize,
 					   char *name, size_t max_namelen)
@@ -2966,17 +3033,17 @@ static void generate_random_cipher_testvec(struct skcipher_request *req,
 
 	/* Key: length in [0, maxkeysize], but usually choose maxkeysize */
 	vec->klen = maxkeysize;
-	if (get_random_u32_below(4) == 0)
-		vec->klen = get_random_u32_below(maxkeysize + 1);
-	generate_random_bytes((u8 *)vec->key, vec->klen);
+	if (prandom_u32_below(rng, 4) == 0)
+		vec->klen = prandom_u32_below(rng, maxkeysize + 1);
+	generate_random_bytes(rng, (u8 *)vec->key, vec->klen);
 	vec->setkey_error = crypto_skcipher_setkey(tfm, vec->key, vec->klen);
 
 	/* IV */
-	generate_random_bytes((u8 *)vec->iv, ivsize);
+	generate_random_bytes(rng, (u8 *)vec->iv, ivsize);
 
 	/* Plaintext */
-	vec->len = generate_random_length(maxdatasize);
-	generate_random_bytes((u8 *)vec->ptext, vec->len);
+	vec->len = generate_random_length(rng, maxdatasize);
+	generate_random_bytes(rng, (u8 *)vec->ptext, vec->len);
 
 	/* If the key couldn't be set, no need to continue to encrypt. */
 	if (vec->setkey_error)
@@ -3018,6 +3085,7 @@ static int test_skcipher_vs_generic_impl(const char *generic_driver,
 	const unsigned int maxdatasize = (2 * PAGE_SIZE) - TESTMGR_POISON_LEN;
 	const char *algname = crypto_skcipher_alg(tfm)->base.cra_name;
 	const char *driver = crypto_skcipher_driver_name(tfm);
+	struct rnd_state rng;
 	char _generic_driver[CRYPTO_MAX_ALG_NAME];
 	struct crypto_skcipher *generic_tfm = NULL;
 	struct skcipher_request *generic_req = NULL;
@@ -3035,6 +3103,8 @@ static int test_skcipher_vs_generic_impl(const char *generic_driver,
 	if (strncmp(algname, "kw(", 3) == 0)
 		return 0;
 
+	init_rnd_state(&rng);
+
 	if (!generic_driver) { /* Use default naming convention? */
 		err = build_generic_driver_name(algname, _generic_driver);
 		if (err)
@@ -3119,9 +3189,11 @@ static int test_skcipher_vs_generic_impl(const char *generic_driver,
 	}
 
 	for (i = 0; i < fuzz_iterations * 8; i++) {
-		generate_random_cipher_testvec(generic_req, &vec, maxdatasize,
+		generate_random_cipher_testvec(&rng, generic_req, &vec,
+					       maxdatasize,
 					       vec_name, sizeof(vec_name));
-		generate_random_testvec_config(cfg, cfgname, sizeof(cfgname));
+		generate_random_testvec_config(&rng, cfg, cfgname,
+					       sizeof(cfgname));
 
 		err = test_skcipher_vec_cfg(ENCRYPT, &vec, vec_name,
 					    cfg, req, tsgls);
@@ -4573,6 +4645,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.hash = __VECS(aes_cmac128_tv_template)
 		}
 	}, {
+		.alg = "cmac(camellia)",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = __VECS(camellia_cmac128_tv_template)
+		}
+	}, {
 		.alg = "cmac(des3_ede)",
 		.test = alg_test_hash,
 		.suite = {
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index f10bfb9d9973..5ca7a412508f 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -25665,6 +25665,53 @@ static const struct cipher_testvec fcrypt_pcbc_tv_template[] = {
 /*
  * CAMELLIA test vectors.
  */
+static const struct hash_testvec camellia_cmac128_tv_template[] = {
+	{ /* From draft-kato-ipsec-camellia-cmac96and128-01 */
+		.key		= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
+				  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
+		.plaintext	= zeroed_string,
+		.digest		= "\xba\x92\x57\x82\xaa\xa1\xf5\xd9"
+				  "\xa0\x0f\x89\x64\x80\x94\xfc\x71",
+		.psize		= 0,
+		.ksize		= 16,
+	}, {
+		.key		= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
+				  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
+		.plaintext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+				  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a",
+		.digest		= "\x6d\x96\x28\x54\xa3\xb9\xfd\xa5"
+				  "\x6d\x7d\x45\xa9\x5e\xe1\x79\x93",
+		.psize		= 16,
+		.ksize		= 16,
+	}, {
+		.key		= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
+				  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
+		.plaintext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+				  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
+				  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
+				  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
+				  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11",
+		.digest		= "\x5c\x18\xd1\x19\xcc\xd6\x76\x61"
+				  "\x44\xac\x18\x66\x13\x1d\x9f\x22",
+		.psize		= 40,
+		.ksize		= 16,
+	}, {
+		.key		= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
+				  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
+		.plaintext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+				  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
+				  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
+				  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
+				  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
+				  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
+				  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
+				  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
+		.digest		= "\xc2\x69\x9a\x6e\xba\x55\xce\x9d"
+				  "\x93\x9a\x8a\x4e\x19\x46\x6e\xe9",
+		.psize		= 64,
+		.ksize		= 16,
+	}
+};
 static const struct cipher_testvec camellia_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
diff --git a/drivers/char/hw_random/meson-rng.c b/drivers/char/hw_random/meson-rng.c
index 8bb30282ca46..a4eb8e35f13d 100644
--- a/drivers/char/hw_random/meson-rng.c
+++ b/drivers/char/hw_random/meson-rng.c
@@ -18,9 +18,7 @@
 
 struct meson_rng_data {
 	void __iomem *base;
-	struct platform_device *pdev;
 	struct hwrng rng;
-	struct clk *core_clk;
 };
 
 static int meson_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
@@ -33,47 +31,28 @@ static int meson_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
 	return sizeof(u32);
 }
 
-static void meson_rng_clk_disable(void *data)
-{
-	clk_disable_unprepare(data);
-}
-
 static int meson_rng_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct meson_rng_data *data;
-	int ret;
+	struct clk *core_clk;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	data->pdev = pdev;
-
 	data->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(data->base))
 		return PTR_ERR(data->base);
 
-	data->core_clk = devm_clk_get_optional(dev, "core");
-	if (IS_ERR(data->core_clk))
-		return dev_err_probe(dev, PTR_ERR(data->core_clk),
+	core_clk = devm_clk_get_optional_enabled(dev, "core");
+	if (IS_ERR(core_clk))
+		return dev_err_probe(dev, PTR_ERR(core_clk),
 				     "Failed to get core clock\n");
 
-	if (data->core_clk) {
-		ret = clk_prepare_enable(data->core_clk);
-		if (ret)
-			return ret;
-		ret = devm_add_action_or_reset(dev, meson_rng_clk_disable,
-					       data->core_clk);
-		if (ret)
-			return ret;
-	}
-
 	data->rng.name = pdev->name;
 	data->rng.read = meson_rng_read;
 
-	platform_set_drvdata(pdev, data);
-
 	return devm_hwrng_register(dev, &data->rng);
 }
 
diff --git a/drivers/char/hw_random/xgene-rng.c b/drivers/char/hw_random/xgene-rng.c
index 008e6db9ce01..7c8f3cb7c6af 100644
--- a/drivers/char/hw_random/xgene-rng.c
+++ b/drivers/char/hw_random/xgene-rng.c
@@ -84,7 +84,6 @@ struct xgene_rng_dev {
 	unsigned long failure_ts;/* First failure timestamp */
 	struct timer_list failure_timer;
 	struct device *dev;
-	struct clk *clk;
 };
 
 static void xgene_rng_expired_timer(struct timer_list *t)
@@ -200,7 +199,7 @@ static void xgene_rng_chk_overflow(struct xgene_rng_dev *ctx)
 
 static irqreturn_t xgene_rng_irq_handler(int irq, void *id)
 {
-	struct xgene_rng_dev *ctx = (struct xgene_rng_dev *) id;
+	struct xgene_rng_dev *ctx = id;
 
 	/* RNG Alarm Counter overflow */
 	xgene_rng_chk_overflow(ctx);
@@ -314,6 +313,7 @@ static struct hwrng xgene_rng_func = {
 static int xgene_rng_probe(struct platform_device *pdev)
 {
 	struct xgene_rng_dev *ctx;
+	struct clk *clk;
 	int rc = 0;
 
 	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
@@ -337,58 +337,36 @@ static int xgene_rng_probe(struct platform_device *pdev)
 
 	rc = devm_request_irq(&pdev->dev, ctx->irq, xgene_rng_irq_handler, 0,
 				dev_name(&pdev->dev), ctx);
-	if (rc) {
-		dev_err(&pdev->dev, "Could not request RNG alarm IRQ\n");
-		return rc;
-	}
+	if (rc)
+		return dev_err_probe(&pdev->dev, rc, "Could not request RNG alarm IRQ\n");
 
 	/* Enable IP clock */
-	ctx->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(ctx->clk)) {
-		dev_warn(&pdev->dev, "Couldn't get the clock for RNG\n");
-	} else {
-		rc = clk_prepare_enable(ctx->clk);
-		if (rc) {
-			dev_warn(&pdev->dev,
-				 "clock prepare enable failed for RNG");
-			return rc;
-		}
-	}
+	clk = devm_clk_get_optional_enabled(&pdev->dev, NULL);
+	if (IS_ERR(clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(clk), "Couldn't get the clock for RNG\n");
 
 	xgene_rng_func.priv = (unsigned long) ctx;
 
 	rc = devm_hwrng_register(&pdev->dev, &xgene_rng_func);
-	if (rc) {
-		dev_err(&pdev->dev, "RNG registering failed error %d\n", rc);
-		if (!IS_ERR(ctx->clk))
-			clk_disable_unprepare(ctx->clk);
-		return rc;
-	}
+	if (rc)
+		return dev_err_probe(&pdev->dev, rc, "RNG registering failed\n");
 
 	rc = device_init_wakeup(&pdev->dev, 1);
-	if (rc) {
-		dev_err(&pdev->dev, "RNG device_init_wakeup failed error %d\n",
-			rc);
-		if (!IS_ERR(ctx->clk))
-			clk_disable_unprepare(ctx->clk);
-		return rc;
-	}
+	if (rc)
+		return dev_err_probe(&pdev->dev, rc, "RNG device_init_wakeup failed\n");
 
 	return 0;
 }
 
 static int xgene_rng_remove(struct platform_device *pdev)
 {
-	struct xgene_rng_dev *ctx = platform_get_drvdata(pdev);
 	int rc;
 
 	rc = device_init_wakeup(&pdev->dev, 0);
 	if (rc)
 		dev_err(&pdev->dev, "RNG init wakeup failed error %d\n", rc);
-	if (!IS_ERR(ctx->clk))
-		clk_disable_unprepare(ctx->clk);
 
-	return rc;
+	return 0;
 }
 
 static const struct of_device_id xgene_rng_of_match[] = {
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 3b2516d1433f..9c440cd0fed0 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -240,21 +240,6 @@ config CRYPTO_DEV_TALITOS2
 	  Say 'Y' here to use the Freescale Security Engine (SEC)
 	  version 2 and following as found on MPC83xx, MPC85xx, etc ...
 
-config CRYPTO_DEV_IXP4XX
-	tristate "Driver for IXP4xx crypto hardware acceleration"
-	depends on ARCH_IXP4XX && IXP4XX_QMGR && IXP4XX_NPE
-	select CRYPTO_AES
-	select CRYPTO_DES
-	select CRYPTO_ECB
-	select CRYPTO_CBC
-	select CRYPTO_CTR
-	select CRYPTO_LIB_DES
-	select CRYPTO_AEAD
-	select CRYPTO_AUTHENC
-	select CRYPTO_SKCIPHER
-	help
-	  Driver for the IXP4xx NPE crypto engine.
-
 config CRYPTO_DEV_PPC4XX
 	tristate "Driver AMCC PPC4xx crypto accelerator"
 	depends on PPC && 4xx
@@ -502,10 +487,10 @@ config CRYPTO_DEV_MXS_DCP
 	  To compile this driver as a module, choose M here: the module
 	  will be called mxs-dcp.
 
-source "drivers/crypto/qat/Kconfig"
 source "drivers/crypto/cavium/cpt/Kconfig"
 source "drivers/crypto/cavium/nitrox/Kconfig"
 source "drivers/crypto/marvell/Kconfig"
+source "drivers/crypto/intel/Kconfig"
 
 config CRYPTO_DEV_CAVIUM_ZIP
 	tristate "Cavium ZIP driver"
@@ -774,7 +759,7 @@ config CRYPTO_DEV_ARTPEC6
 config CRYPTO_DEV_CCREE
 	tristate "Support for ARM TrustZone CryptoCell family of security processors"
 	depends on CRYPTO && CRYPTO_HW && OF && HAS_DMA
-	default n
+	depends on HAS_IOMEM
 	select CRYPTO_HASH
 	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
@@ -810,6 +795,7 @@ config CRYPTO_DEV_SA2UL
 	select CRYPTO_AES
 	select CRYPTO_ALGAPI
 	select CRYPTO_AUTHENC
+	select CRYPTO_DES
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
@@ -820,7 +806,6 @@ config CRYPTO_DEV_SA2UL
 	  used for crypto offload.  Select this if you want to use hardware
 	  acceleration for cryptographic algorithms on these devices.
 
-source "drivers/crypto/keembay/Kconfig"
 source "drivers/crypto/aspeed/Kconfig"
 
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 476f1a25ca32..51d36701e785 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_COMMON) += caam/
 obj-$(CONFIG_CRYPTO_DEV_GEODE) += geode-aes.o
 obj-$(CONFIG_CRYPTO_DEV_HIFN_795X) += hifn_795x.o
 obj-$(CONFIG_CRYPTO_DEV_IMGTEC_HASH) += img-hash.o
-obj-$(CONFIG_CRYPTO_DEV_IXP4XX) += ixp4xx_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_MARVELL) += marvell/
 obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o
 obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o
@@ -33,7 +32,6 @@ obj-$(CONFIG_CRYPTO_DEV_OMAP_SHAM) += omap-sham.o
 obj-$(CONFIG_CRYPTO_DEV_PADLOCK_AES) += padlock-aes.o
 obj-$(CONFIG_CRYPTO_DEV_PADLOCK_SHA) += padlock-sha.o
 obj-$(CONFIG_CRYPTO_DEV_PPC4XX) += amcc/
-obj-$(CONFIG_CRYPTO_DEV_QAT) += qat/
 obj-$(CONFIG_CRYPTO_DEV_QCE) += qce/
 obj-$(CONFIG_CRYPTO_DEV_QCOM_RNG) += qcom-rng.o
 obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rockchip/
@@ -51,4 +49,4 @@ obj-$(CONFIG_CRYPTO_DEV_ARTPEC6) += axis/
 obj-y += xilinx/
 obj-y += hisilicon/
 obj-$(CONFIG_CRYPTO_DEV_AMLOGIC_GXL) += amlogic/
-obj-y += keembay/
+obj-y += intel/
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 50dc783821b6..d553f3f1efbe 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -1101,7 +1101,7 @@ static void crypto4xx_bh_tasklet_cb(unsigned long data)
 static inline irqreturn_t crypto4xx_interrupt_handler(int irq, void *data,
 						      u32 clr_val)
 {
-	struct device *dev = (struct device *)data;
+	struct device *dev = data;
 	struct crypto4xx_core_device *core_dev = dev_get_drvdata(dev);
 
 	writel(clr_val, core_dev->dev->ce_base + CRYPTO4XX_INT_CLR);
diff --git a/drivers/crypto/aspeed/aspeed-acry.c b/drivers/crypto/aspeed/aspeed-acry.c
index 1f77ebd73489..470122c87fea 100644
--- a/drivers/crypto/aspeed/aspeed-acry.c
+++ b/drivers/crypto/aspeed/aspeed-acry.c
@@ -289,7 +289,7 @@ static int aspeed_acry_rsa_ctx_copy(struct aspeed_acry_dev *acry_dev, void *buf,
 
 			if (mode == ASPEED_RSA_EXP_MODE)
 				idx = acry_dev->exp_dw_mapping[j - 1];
-			else if (mode == ASPEED_RSA_MOD_MODE)
+			else /* mode == ASPEED_RSA_MOD_MODE */
 				idx = acry_dev->mod_dw_mapping[j - 1];
 
 			dw_buf[idx] = cpu_to_le32(data);
@@ -712,7 +712,6 @@ static int aspeed_acry_probe(struct platform_device *pdev)
 {
 	struct aspeed_acry_dev *acry_dev;
 	struct device *dev = &pdev->dev;
-	struct resource *res;
 	int rc;
 
 	acry_dev = devm_kzalloc(dev, sizeof(struct aspeed_acry_dev),
@@ -724,13 +723,11 @@ static int aspeed_acry_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, acry_dev);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	acry_dev->regs = devm_ioremap_resource(dev, res);
+	acry_dev->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(acry_dev->regs))
 		return PTR_ERR(acry_dev->regs);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	acry_dev->acry_sram = devm_ioremap_resource(dev, res);
+	acry_dev->acry_sram = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(acry_dev->acry_sram))
 		return PTR_ERR(acry_dev->acry_sram);
 
@@ -782,7 +779,10 @@ static int aspeed_acry_probe(struct platform_device *pdev)
 	acry_dev->buf_addr = dmam_alloc_coherent(dev, ASPEED_ACRY_BUFF_SIZE,
 						 &acry_dev->buf_dma_addr,
 						 GFP_KERNEL);
-	memzero_explicit(acry_dev->buf_addr, ASPEED_ACRY_BUFF_SIZE);
+	if (!acry_dev->buf_addr) {
+		rc = -ENOMEM;
+		goto err_engine_rsa_start;
+	}
 
 	aspeed_acry_register(acry_dev);
 
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index ed10f2ae4523..143d33fbb316 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -493,17 +493,11 @@ static void atmel_aes_set_iv_as_last_ciphertext_block(struct atmel_aes_dev *dd)
 	if (req->cryptlen < ivsize)
 		return;
 
-	if (rctx->mode & AES_FLAGS_ENCRYPT) {
+	if (rctx->mode & AES_FLAGS_ENCRYPT)
 		scatterwalk_map_and_copy(req->iv, req->dst,
 					 req->cryptlen - ivsize, ivsize, 0);
-	} else {
-		if (req->src == req->dst)
-			memcpy(req->iv, rctx->lastc, ivsize);
-		else
-			scatterwalk_map_and_copy(req->iv, req->src,
-						 req->cryptlen - ivsize,
-						 ivsize, 0);
-	}
+	else
+		memcpy(req->iv, rctx->lastc, ivsize);
 }
 
 static inline struct atmel_aes_ctr_ctx *
@@ -1146,7 +1140,7 @@ static int atmel_aes_crypt(struct skcipher_request *req, unsigned long mode)
 	rctx->mode = mode;
 
 	if (opmode != AES_FLAGS_ECB &&
-	    !(mode & AES_FLAGS_ENCRYPT) && req->src == req->dst) {
+	    !(mode & AES_FLAGS_ENCRYPT)) {
 		unsigned int ivsize = crypto_skcipher_ivsize(skcipher);
 
 		if (req->cryptlen >= ivsize)
@@ -1341,7 +1335,7 @@ static struct skcipher_alg aes_algs[] = {
 {
 	.base.cra_name		= "cfb(aes)",
 	.base.cra_driver_name	= "atmel-cfb-aes",
-	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_blocksize	= 1,
 	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
 
 	.init			= atmel_aes_init_tfm,
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index e7c1db2739ec..6bef634d3c86 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -1948,14 +1948,32 @@ static int atmel_sha_hmac_digest2(struct atmel_sha_dev *dd)
 	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct atmel_sha_hmac_ctx *hmac = crypto_ahash_ctx(tfm);
+	struct scatterlist *sgbuf;
 	size_t hs = ctx->hash_size;
 	size_t i, num_words = hs / sizeof(u32);
 	bool use_dma = false;
 	u32 mr;
 
 	/* Special case for empty message. */
-	if (!req->nbytes)
-		return atmel_sha_complete(dd, -EINVAL); // TODO:
+	if (!req->nbytes) {
+		req->nbytes = 0;
+		ctx->bufcnt = 0;
+		ctx->digcnt[0] = 0;
+		ctx->digcnt[1] = 0;
+		switch (ctx->flags & SHA_FLAGS_ALGO_MASK) {
+		case SHA_FLAGS_SHA1:
+		case SHA_FLAGS_SHA224:
+		case SHA_FLAGS_SHA256:
+			atmel_sha_fill_padding(ctx, 64);
+			break;
+
+		case SHA_FLAGS_SHA384:
+		case SHA_FLAGS_SHA512:
+			atmel_sha_fill_padding(ctx, 128);
+			break;
+		}
+		sg_init_one(&dd->tmp, ctx->buffer, ctx->bufcnt);
+	}
 
 	/* Check DMA threshold and alignment. */
 	if (req->nbytes > ATMEL_SHA_DMA_THRESHOLD &&
@@ -1985,12 +2003,20 @@ static int atmel_sha_hmac_digest2(struct atmel_sha_dev *dd)
 
 	atmel_sha_write(dd, SHA_CR, SHA_CR_FIRST);
 
+	/* Special case for empty message. */
+	if (!req->nbytes) {
+		sgbuf = &dd->tmp;
+		req->nbytes = ctx->bufcnt;
+	} else {
+		sgbuf = req->src;
+	}
+
 	/* Process data. */
 	if (use_dma)
-		return atmel_sha_dma_start(dd, req->src, req->nbytes,
+		return atmel_sha_dma_start(dd, sgbuf, req->nbytes,
 					   atmel_sha_hmac_final_done);
 
-	return atmel_sha_cpu_start(dd, req->src, req->nbytes, false, true,
+	return atmel_sha_cpu_start(dd, sgbuf, req->nbytes, false, true,
 				   atmel_sha_hmac_final_done);
 }
 
diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index 4403dbb0f0b1..44a185a84760 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -126,7 +126,7 @@ static void atmel_sha204a_remove(struct i2c_client *client)
 	kfree((void *)i2c_priv->hwrng.priv);
 }
 
-static const struct of_device_id atmel_sha204a_dt_ids[] = {
+static const struct of_device_id atmel_sha204a_dt_ids[] __maybe_unused = {
 	{ .compatible = "atmel,atsha204", },
 	{ .compatible = "atmel,atsha204a", },
 	{ /* sentinel */ }
diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c
index b2d48c1649b9..c9ded8be9c39 100644
--- a/drivers/crypto/atmel-tdes.c
+++ b/drivers/crypto/atmel-tdes.c
@@ -565,17 +565,12 @@ atmel_tdes_set_iv_as_last_ciphertext_block(struct atmel_tdes_dev *dd)
 	if (req->cryptlen < ivsize)
 		return;
 
-	if (rctx->mode & TDES_FLAGS_ENCRYPT) {
+	if (rctx->mode & TDES_FLAGS_ENCRYPT)
 		scatterwalk_map_and_copy(req->iv, req->dst,
 					 req->cryptlen - ivsize, ivsize, 0);
-	} else {
-		if (req->src == req->dst)
-			memcpy(req->iv, rctx->lastc, ivsize);
-		else
-			scatterwalk_map_and_copy(req->iv, req->src,
-						 req->cryptlen - ivsize,
-						 ivsize, 0);
-	}
+	else
+		memcpy(req->iv, rctx->lastc, ivsize);
+
 }
 
 static void atmel_tdes_finish_req(struct atmel_tdes_dev *dd, int err)
@@ -722,7 +717,7 @@ static int atmel_tdes_crypt(struct skcipher_request *req, unsigned long mode)
 	rctx->mode = mode;
 
 	if ((mode & TDES_FLAGS_OPMODE_MASK) != TDES_FLAGS_ECB &&
-	    !(mode & TDES_FLAGS_ENCRYPT) && req->src == req->dst) {
+	    !(mode & TDES_FLAGS_ENCRYPT)) {
 		unsigned int ivsize = crypto_skcipher_ivsize(skcipher);
 
 		if (req->cryptlen >= ivsize)
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 12b1c8346243..feb86013dbf6 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -3,7 +3,7 @@
  * caam - Freescale FSL CAAM support for crypto API
  *
  * Copyright 2008-2011 Freescale Semiconductor, Inc.
- * Copyright 2016-2019 NXP
+ * Copyright 2016-2019, 2023 NXP
  *
  * Based on talitos crypto API driver.
  *
@@ -3542,13 +3542,14 @@ int caam_algapi_init(struct device *ctrldev)
 	 * First, detect presence and attributes of DES, AES, and MD blocks.
 	 */
 	if (priv->era < 10) {
+		struct caam_perfmon __iomem *perfmon = &priv->jr[0]->perfmon;
 		u32 cha_vid, cha_inst, aes_rn;
 
-		cha_vid = rd_reg32(&priv->ctrl->perfmon.cha_id_ls);
+		cha_vid = rd_reg32(&perfmon->cha_id_ls);
 		aes_vid = cha_vid & CHA_ID_LS_AES_MASK;
 		md_vid = (cha_vid & CHA_ID_LS_MD_MASK) >> CHA_ID_LS_MD_SHIFT;
 
-		cha_inst = rd_reg32(&priv->ctrl->perfmon.cha_num_ls);
+		cha_inst = rd_reg32(&perfmon->cha_num_ls);
 		des_inst = (cha_inst & CHA_ID_LS_DES_MASK) >>
 			   CHA_ID_LS_DES_SHIFT;
 		aes_inst = cha_inst & CHA_ID_LS_AES_MASK;
@@ -3556,23 +3557,23 @@ int caam_algapi_init(struct device *ctrldev)
 		ccha_inst = 0;
 		ptha_inst = 0;
 
-		aes_rn = rd_reg32(&priv->ctrl->perfmon.cha_rev_ls) &
-			 CHA_ID_LS_AES_MASK;
+		aes_rn = rd_reg32(&perfmon->cha_rev_ls) & CHA_ID_LS_AES_MASK;
 		gcm_support = !(aes_vid == CHA_VER_VID_AES_LP && aes_rn < 8);
 	} else {
+		struct version_regs __iomem *vreg = &priv->jr[0]->vreg;
 		u32 aesa, mdha;
 
-		aesa = rd_reg32(&priv->ctrl->vreg.aesa);
-		mdha = rd_reg32(&priv->ctrl->vreg.mdha);
+		aesa = rd_reg32(&vreg->aesa);
+		mdha = rd_reg32(&vreg->mdha);
 
 		aes_vid = (aesa & CHA_VER_VID_MASK) >> CHA_VER_VID_SHIFT;
 		md_vid = (mdha & CHA_VER_VID_MASK) >> CHA_VER_VID_SHIFT;
 
-		des_inst = rd_reg32(&priv->ctrl->vreg.desa) & CHA_VER_NUM_MASK;
+		des_inst = rd_reg32(&vreg->desa) & CHA_VER_NUM_MASK;
 		aes_inst = aesa & CHA_VER_NUM_MASK;
 		md_inst = mdha & CHA_VER_NUM_MASK;
-		ccha_inst = rd_reg32(&priv->ctrl->vreg.ccha) & CHA_VER_NUM_MASK;
-		ptha_inst = rd_reg32(&priv->ctrl->vreg.ptha) & CHA_VER_NUM_MASK;
+		ccha_inst = rd_reg32(&vreg->ccha) & CHA_VER_NUM_MASK;
+		ptha_inst = rd_reg32(&vreg->ptha) & CHA_VER_NUM_MASK;
 
 		gcm_support = aesa & CHA_VER_MISC_AES_GCM;
 	}
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 82d3c730a502..80deb003f0a5 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -3,7 +3,7 @@
  * caam - Freescale FSL CAAM support for ahash functions of crypto API
  *
  * Copyright 2011 Freescale Semiconductor, Inc.
- * Copyright 2018-2019 NXP
+ * Copyright 2018-2019, 2023 NXP
  *
  * Based on caamalg.c crypto API driver.
  *
@@ -1956,12 +1956,14 @@ int caam_algapi_hash_init(struct device *ctrldev)
 	 * presence and attributes of MD block.
 	 */
 	if (priv->era < 10) {
-		md_vid = (rd_reg32(&priv->ctrl->perfmon.cha_id_ls) &
+		struct caam_perfmon __iomem *perfmon = &priv->jr[0]->perfmon;
+
+		md_vid = (rd_reg32(&perfmon->cha_id_ls) &
 			  CHA_ID_LS_MD_MASK) >> CHA_ID_LS_MD_SHIFT;
-		md_inst = (rd_reg32(&priv->ctrl->perfmon.cha_num_ls) &
+		md_inst = (rd_reg32(&perfmon->cha_num_ls) &
 			   CHA_ID_LS_MD_MASK) >> CHA_ID_LS_MD_SHIFT;
 	} else {
-		u32 mdha = rd_reg32(&priv->ctrl->vreg.mdha);
+		u32 mdha = rd_reg32(&priv->jr[0]->vreg.mdha);
 
 		md_vid = (mdha & CHA_VER_VID_MASK) >> CHA_VER_VID_SHIFT;
 		md_inst = mdha & CHA_VER_NUM_MASK;
diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
index e40614fef39d..72afc249d42f 100644
--- a/drivers/crypto/caam/caampkc.c
+++ b/drivers/crypto/caam/caampkc.c
@@ -3,7 +3,7 @@
  * caam - Freescale FSL CAAM support for Public Key Cryptography
  *
  * Copyright 2016 Freescale Semiconductor, Inc.
- * Copyright 2018-2019 NXP
+ * Copyright 2018-2019, 2023 NXP
  *
  * There is no Shared Descriptor for PKC so that the Job Descriptor must carry
  * all the desired key parameters, input and output pointers.
@@ -1168,10 +1168,10 @@ int caam_pkc_init(struct device *ctrldev)
 
 	/* Determine public key hardware accelerator presence. */
 	if (priv->era < 10) {
-		pk_inst = (rd_reg32(&priv->ctrl->perfmon.cha_num_ls) &
+		pk_inst = (rd_reg32(&priv->jr[0]->perfmon.cha_num_ls) &
 			   CHA_ID_LS_PK_MASK) >> CHA_ID_LS_PK_SHIFT;
 	} else {
-		pkha = rd_reg32(&priv->ctrl->vreg.pkha);
+		pkha = rd_reg32(&priv->jr[0]->vreg.pkha);
 		pk_inst = pkha & CHA_VER_NUM_MASK;
 
 		/*
diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c
index 1fd8ff965006..50eb55da45c2 100644
--- a/drivers/crypto/caam/caamrng.c
+++ b/drivers/crypto/caam/caamrng.c
@@ -3,7 +3,7 @@
  * caam - Freescale FSL CAAM support for hw_random
  *
  * Copyright 2011 Freescale Semiconductor, Inc.
- * Copyright 2018-2019 NXP
+ * Copyright 2018-2019, 2023 NXP
  *
  * Based on caamalg.c crypto API driver.
  *
@@ -227,10 +227,10 @@ int caam_rng_init(struct device *ctrldev)
 
 	/* Check for an instantiated RNG before registration */
 	if (priv->era < 10)
-		rng_inst = (rd_reg32(&priv->ctrl->perfmon.cha_num_ls) &
+		rng_inst = (rd_reg32(&priv->jr[0]->perfmon.cha_num_ls) &
 			    CHA_ID_LS_RNG_MASK) >> CHA_ID_LS_RNG_SHIFT;
 	else
-		rng_inst = rd_reg32(&priv->ctrl->vreg.rng) & CHA_VER_NUM_MASK;
+		rng_inst = rd_reg32(&priv->jr[0]->vreg.rng) & CHA_VER_NUM_MASK;
 
 	if (!rng_inst)
 		return 0;
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 6278afb951c3..bedcc2ab3a00 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -3,7 +3,7 @@
  * Controller-level driver, kernel property detection, initialization
  *
  * Copyright 2008-2012 Freescale Semiconductor, Inc.
- * Copyright 2018-2019 NXP
+ * Copyright 2018-2019, 2023 NXP
  */
 
 #include <linux/device.h>
@@ -284,6 +284,10 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask,
 		const u32 rdsta_if = RDSTA_IF0 << sh_idx;
 		const u32 rdsta_pr = RDSTA_PR0 << sh_idx;
 		const u32 rdsta_mask = rdsta_if | rdsta_pr;
+
+		/* Clear the contents before using the descriptor */
+		memset(desc, 0x00, CAAM_CMD_SZ * 7);
+
 		/*
 		 * If the corresponding bit is set, this state handle
 		 * was initialized by somebody else, so it's left alone.
@@ -327,8 +331,6 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask,
 		}
 
 		dev_info(ctrldev, "Instantiated RNG4 SH%d\n", sh_idx);
-		/* Clear the contents before recreating the descriptor */
-		memset(desc, 0x00, CAAM_CMD_SZ * 7);
 	}
 
 	kfree(desc);
@@ -395,7 +397,7 @@ start_rng:
 		      RTMCTL_SAMP_MODE_RAW_ES_SC);
 }
 
-static int caam_get_era_from_hw(struct caam_ctrl __iomem *ctrl)
+static int caam_get_era_from_hw(struct caam_perfmon __iomem *perfmon)
 {
 	static const struct {
 		u16 ip_id;
@@ -421,12 +423,12 @@ static int caam_get_era_from_hw(struct caam_ctrl __iomem *ctrl)
 	u16 ip_id;
 	int i;
 
-	ccbvid = rd_reg32(&ctrl->perfmon.ccb_id);
+	ccbvid = rd_reg32(&perfmon->ccb_id);
 	era = (ccbvid & CCBVID_ERA_MASK) >> CCBVID_ERA_SHIFT;
 	if (era)	/* This is '0' prior to CAAM ERA-6 */
 		return era;
 
-	id_ms = rd_reg32(&ctrl->perfmon.caam_id_ms);
+	id_ms = rd_reg32(&perfmon->caam_id_ms);
 	ip_id = (id_ms & SECVID_MS_IPID_MASK) >> SECVID_MS_IPID_SHIFT;
 	maj_rev = (id_ms & SECVID_MS_MAJ_REV_MASK) >> SECVID_MS_MAJ_REV_SHIFT;
 
@@ -444,9 +446,9 @@ static int caam_get_era_from_hw(struct caam_ctrl __iomem *ctrl)
  * In case this property is not passed an attempt to retrieve the CAAM
  * era via register reads will be made.
  *
- * @ctrl:	controller region
+ * @perfmon:	Performance Monitor Registers
  */
-static int caam_get_era(struct caam_ctrl __iomem *ctrl)
+static int caam_get_era(struct caam_perfmon __iomem *perfmon)
 {
 	struct device_node *caam_node;
 	int ret;
@@ -459,7 +461,7 @@ static int caam_get_era(struct caam_ctrl __iomem *ctrl)
 	if (!ret)
 		return prop;
 	else
-		return caam_get_era_from_hw(ctrl);
+		return caam_get_era_from_hw(perfmon);
 }
 
 /*
@@ -626,12 +628,14 @@ static int caam_probe(struct platform_device *pdev)
 	struct device_node *nprop, *np;
 	struct caam_ctrl __iomem *ctrl;
 	struct caam_drv_private *ctrlpriv;
+	struct caam_perfmon __iomem *perfmon;
 	struct dentry *dfs_root;
 	u32 scfgr, comp_params;
 	u8 rng_vid;
 	int pg_size;
 	int BLOCK_OFFSET = 0;
 	bool pr_support = false;
+	bool reg_access = true;
 
 	ctrlpriv = devm_kzalloc(&pdev->dev, sizeof(*ctrlpriv), GFP_KERNEL);
 	if (!ctrlpriv)
@@ -645,6 +649,17 @@ static int caam_probe(struct platform_device *pdev)
 	caam_imx = (bool)imx_soc_match;
 
 	if (imx_soc_match) {
+		/*
+		 * Until Layerscape and i.MX OP-TEE get in sync,
+		 * only i.MX OP-TEE use cases disallow access to
+		 * caam page 0 (controller) registers.
+		 */
+		np = of_find_compatible_node(NULL, NULL, "linaro,optee-tz");
+		ctrlpriv->optee_en = !!np;
+		of_node_put(np);
+
+		reg_access = !ctrlpriv->optee_en;
+
 		if (!imx_soc_match->data) {
 			dev_err(dev, "No clock data provided for i.MX SoC");
 			return -EINVAL;
@@ -665,10 +680,38 @@ static int caam_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	caam_little_end = !(bool)(rd_reg32(&ctrl->perfmon.status) &
+	ring = 0;
+	for_each_available_child_of_node(nprop, np)
+		if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") ||
+		    of_device_is_compatible(np, "fsl,sec4.0-job-ring")) {
+			u32 reg;
+
+			if (of_property_read_u32_index(np, "reg", 0, &reg)) {
+				dev_err(dev, "%s read reg property error\n",
+					np->full_name);
+				continue;
+			}
+
+			ctrlpriv->jr[ring] = (struct caam_job_ring __iomem __force *)
+					     ((__force uint8_t *)ctrl + reg);
+
+			ctrlpriv->total_jobrs++;
+			ring++;
+		}
+
+	/*
+	 * Wherever possible, instead of accessing registers from the global page,
+	 * use the alias registers in the first (cf. DT nodes order)
+	 * job ring's page.
+	 */
+	perfmon = ring ? (struct caam_perfmon __iomem *)&ctrlpriv->jr[0]->perfmon :
+			 (struct caam_perfmon __iomem *)&ctrl->perfmon;
+
+	caam_little_end = !(bool)(rd_reg32(&perfmon->status) &
 				  (CSTA_PLEND | CSTA_ALT_PLEND));
-	comp_params = rd_reg32(&ctrl->perfmon.comp_parms_ms);
-	if (comp_params & CTPR_MS_PS && rd_reg32(&ctrl->mcr) & MCFGR_LONG_PTR)
+	comp_params = rd_reg32(&perfmon->comp_parms_ms);
+	if (reg_access && comp_params & CTPR_MS_PS &&
+	    rd_reg32(&ctrl->mcr) & MCFGR_LONG_PTR)
 		caam_ptr_sz = sizeof(u64);
 	else
 		caam_ptr_sz = sizeof(u32);
@@ -733,6 +776,9 @@ static int caam_probe(struct platform_device *pdev)
 	}
 #endif
 
+	if (!reg_access)
+		goto set_dma_mask;
+
 	/*
 	 * Enable DECO watchdogs and, if this is a PHYS_ADDR_T_64BIT kernel,
 	 * long pointers in master configuration register.
@@ -772,13 +818,14 @@ static int caam_probe(struct platform_device *pdev)
 			      JRSTART_JR1_START | JRSTART_JR2_START |
 			      JRSTART_JR3_START);
 
+set_dma_mask:
 	ret = dma_set_mask_and_coherent(dev, caam_get_dma_mask(dev));
 	if (ret) {
 		dev_err(dev, "dma_set_mask_and_coherent failed (%d)\n", ret);
 		return ret;
 	}
 
-	ctrlpriv->era = caam_get_era(ctrl);
+	ctrlpriv->era = caam_get_era(perfmon);
 	ctrlpriv->domain = iommu_get_domain_for_dev(dev);
 
 	dfs_root = debugfs_create_dir(dev_name(dev), NULL);
@@ -789,7 +836,7 @@ static int caam_probe(struct platform_device *pdev)
 			return ret;
 	}
 
-	caam_debugfs_init(ctrlpriv, dfs_root);
+	caam_debugfs_init(ctrlpriv, perfmon, dfs_root);
 
 	/* Check to see if (DPAA 1.x) QI present. If so, enable */
 	if (ctrlpriv->qi_present && !caam_dpaa2) {
@@ -808,26 +855,16 @@ static int caam_probe(struct platform_device *pdev)
 #endif
 	}
 
-	ring = 0;
-	for_each_available_child_of_node(nprop, np)
-		if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") ||
-		    of_device_is_compatible(np, "fsl,sec4.0-job-ring")) {
-			ctrlpriv->jr[ring] = (struct caam_job_ring __iomem __force *)
-					     ((__force uint8_t *)ctrl +
-					     (ring + JR_BLOCK_NUMBER) *
-					      BLOCK_OFFSET
-					     );
-			ctrlpriv->total_jobrs++;
-			ring++;
-		}
-
 	/* If no QI and no rings specified, quit and go home */
 	if ((!ctrlpriv->qi_present) && (!ctrlpriv->total_jobrs)) {
 		dev_err(dev, "no queues configured, terminating\n");
 		return -ENOMEM;
 	}
 
-	comp_params = rd_reg32(&ctrl->perfmon.comp_parms_ls);
+	if (!reg_access)
+		goto report_live;
+
+	comp_params = rd_reg32(&perfmon->comp_parms_ls);
 	ctrlpriv->blob_present = !!(comp_params & CTPR_LS_BLOB);
 
 	/*
@@ -836,15 +873,21 @@ static int caam_probe(struct platform_device *pdev)
 	 * check both here.
 	 */
 	if (ctrlpriv->era < 10) {
-		rng_vid = (rd_reg32(&ctrl->perfmon.cha_id_ls) &
+		rng_vid = (rd_reg32(&perfmon->cha_id_ls) &
 			   CHA_ID_LS_RNG_MASK) >> CHA_ID_LS_RNG_SHIFT;
 		ctrlpriv->blob_present = ctrlpriv->blob_present &&
-			(rd_reg32(&ctrl->perfmon.cha_num_ls) & CHA_ID_LS_AES_MASK);
+			(rd_reg32(&perfmon->cha_num_ls) & CHA_ID_LS_AES_MASK);
 	} else {
-		rng_vid = (rd_reg32(&ctrl->vreg.rng) & CHA_VER_VID_MASK) >>
+		struct version_regs __iomem *vreg;
+
+		vreg =  ctrlpriv->total_jobrs ?
+			(struct version_regs __iomem *)&ctrlpriv->jr[0]->vreg :
+			(struct version_regs __iomem *)&ctrl->vreg;
+
+		rng_vid = (rd_reg32(&vreg->rng) & CHA_VER_VID_MASK) >>
 			   CHA_VER_VID_SHIFT;
 		ctrlpriv->blob_present = ctrlpriv->blob_present &&
-			(rd_reg32(&ctrl->vreg.aesa) & CHA_VER_MISC_AES_NUM_MASK);
+			(rd_reg32(&vreg->aesa) & CHA_VER_MISC_AES_NUM_MASK);
 	}
 
 	/*
@@ -923,10 +966,11 @@ static int caam_probe(struct platform_device *pdev)
 		clrsetbits_32(&ctrl->scfgr, 0, SCFGR_RDBENABLE);
 	}
 
+report_live:
 	/* NOTE: RTIC detection ought to go here, around Si time */
 
-	caam_id = (u64)rd_reg32(&ctrl->perfmon.caam_id_ms) << 32 |
-		  (u64)rd_reg32(&ctrl->perfmon.caam_id_ls);
+	caam_id = (u64)rd_reg32(&perfmon->caam_id_ms) << 32 |
+		  (u64)rd_reg32(&perfmon->caam_id_ls);
 
 	/* Report "alive" for developer to see */
 	dev_info(dev, "device ID = 0x%016llx (Era %d)\n", caam_id,
diff --git a/drivers/crypto/caam/debugfs.c b/drivers/crypto/caam/debugfs.c
index 806bb20d2aa1..6358d3cabf57 100644
--- a/drivers/crypto/caam/debugfs.c
+++ b/drivers/crypto/caam/debugfs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
-/* Copyright 2019 NXP */
+/* Copyright 2019, 2023 NXP */
 
 #include <linux/debugfs.h>
 #include "compat.h"
@@ -42,16 +42,15 @@ void caam_debugfs_qi_init(struct caam_drv_private *ctrlpriv)
 }
 #endif
 
-void caam_debugfs_init(struct caam_drv_private *ctrlpriv, struct dentry *root)
+void caam_debugfs_init(struct caam_drv_private *ctrlpriv,
+		       struct caam_perfmon __force *perfmon,
+		       struct dentry *root)
 {
-	struct caam_perfmon *perfmon;
-
 	/*
 	 * FIXME: needs better naming distinction, as some amalgamation of
 	 * "caam" and nprop->full_name. The OF name isn't distinctive,
 	 * but does separate instances
 	 */
-	perfmon = (struct caam_perfmon __force *)&ctrlpriv->ctrl->perfmon;
 
 	ctrlpriv->ctl = debugfs_create_dir("ctl", root);
 
@@ -78,6 +77,9 @@ void caam_debugfs_init(struct caam_drv_private *ctrlpriv, struct dentry *root)
 	debugfs_create_file("fault_status", 0444, ctrlpriv->ctl,
 			    &perfmon->status, &caam_fops_u32_ro);
 
+	if (ctrlpriv->optee_en)
+		return;
+
 	/* Internal covering keys (useful in non-secure mode only) */
 	ctrlpriv->ctl_kek_wrap.data = (__force void *)&ctrlpriv->ctrl->kek[0];
 	ctrlpriv->ctl_kek_wrap.size = KEK_KEY_SIZE * sizeof(u32);
diff --git a/drivers/crypto/caam/debugfs.h b/drivers/crypto/caam/debugfs.h
index 661d768acdbf..8b5d1acd21a7 100644
--- a/drivers/crypto/caam/debugfs.h
+++ b/drivers/crypto/caam/debugfs.h
@@ -1,16 +1,19 @@
 /* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
-/* Copyright 2019 NXP */
+/* Copyright 2019, 2023 NXP */
 
 #ifndef CAAM_DEBUGFS_H
 #define CAAM_DEBUGFS_H
 
 struct dentry;
 struct caam_drv_private;
+struct caam_perfmon;
 
 #ifdef CONFIG_DEBUG_FS
-void caam_debugfs_init(struct caam_drv_private *ctrlpriv, struct dentry *root);
+void caam_debugfs_init(struct caam_drv_private *ctrlpriv,
+		       struct caam_perfmon __force *perfmon, struct dentry *root);
 #else
 static inline void caam_debugfs_init(struct caam_drv_private *ctrlpriv,
+				     struct caam_perfmon __force *perfmon,
 				     struct dentry *root)
 {}
 #endif
diff --git a/drivers/crypto/caam/dpseci-debugfs.c b/drivers/crypto/caam/dpseci-debugfs.c
index 0eca8c2fd916..020a9d8a8a07 100644
--- a/drivers/crypto/caam/dpseci-debugfs.c
+++ b/drivers/crypto/caam/dpseci-debugfs.c
@@ -8,7 +8,7 @@
 
 static int dpseci_dbg_fqs_show(struct seq_file *file, void *offset)
 {
-	struct dpaa2_caam_priv *priv = (struct dpaa2_caam_priv *)file->private;
+	struct dpaa2_caam_priv *priv = file->private;
 	u32 fqid, fcnt, bcnt;
 	int i, err;
 
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index 572cf66c887a..86ed1b91c22d 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -94,6 +94,7 @@ struct caam_drv_private {
 	u8 qi_present;		/* Nonzero if QI present in device */
 	u8 blob_present;	/* Nonzero if BLOB support present in device */
 	u8 mc_en;		/* Nonzero if MC f/w is active */
+	u8 optee_en;		/* Nonzero if OP-TEE f/w is active */
 	int secvio_irq;		/* Security violation interrupt number */
 	int virt_en;		/* Virtualization enabled in CAAM */
 	int era;		/* CAAM Era (internal HW revision) */
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index 724fdec18bf9..96dea5304d22 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -4,7 +4,7 @@
  * JobR backend functionality
  *
  * Copyright 2008-2012 Freescale Semiconductor, Inc.
- * Copyright 2019 NXP
+ * Copyright 2019, 2023 NXP
  */
 
 #include <linux/of_irq.h>
@@ -72,19 +72,27 @@ static void caam_jr_crypto_engine_exit(void *data)
 	crypto_engine_exit(jrpriv->engine);
 }
 
-static int caam_reset_hw_jr(struct device *dev)
+/*
+ * Put the CAAM in quiesce, ie stop
+ *
+ * Must be called with itr disabled
+ */
+static int caam_jr_stop_processing(struct device *dev, u32 jrcr_bits)
 {
 	struct caam_drv_private_jr *jrp = dev_get_drvdata(dev);
 	unsigned int timeout = 100000;
 
-	/*
-	 * mask interrupts since we are going to poll
-	 * for reset completion status
-	 */
-	clrsetbits_32(&jrp->rregs->rconfig_lo, 0, JRCFG_IMSK);
+	/* Check the current status */
+	if (rd_reg32(&jrp->rregs->jrintstatus) & JRINT_ERR_HALT_INPROGRESS)
+		goto wait_quiesce_completion;
 
-	/* initiate flush (required prior to reset) */
-	wr_reg32(&jrp->rregs->jrcommand, JRCR_RESET);
+	/* Reset the field */
+	clrsetbits_32(&jrp->rregs->jrintstatus, JRINT_ERR_HALT_MASK, 0);
+
+	/* initiate flush / park (required prior to reset) */
+	wr_reg32(&jrp->rregs->jrcommand, jrcr_bits);
+
+wait_quiesce_completion:
 	while (((rd_reg32(&jrp->rregs->jrintstatus) & JRINT_ERR_HALT_MASK) ==
 		JRINT_ERR_HALT_INPROGRESS) && --timeout)
 		cpu_relax();
@@ -95,8 +103,35 @@ static int caam_reset_hw_jr(struct device *dev)
 		return -EIO;
 	}
 
+	return 0;
+}
+
+/*
+ * Flush the job ring, so the jobs running will be stopped, jobs queued will be
+ * invalidated and the CAAM will no longer fetch fron input ring.
+ *
+ * Must be called with itr disabled
+ */
+static int caam_jr_flush(struct device *dev)
+{
+	return caam_jr_stop_processing(dev, JRCR_RESET);
+}
+
+static int caam_reset_hw_jr(struct device *dev)
+{
+	struct caam_drv_private_jr *jrp = dev_get_drvdata(dev);
+	unsigned int timeout = 100000;
+	int err;
+	/*
+	 * mask interrupts since we are going to poll
+	 * for reset completion status
+	 */
+	clrsetbits_32(&jrp->rregs->rconfig_lo, 0, JRCFG_IMSK);
+	err = caam_jr_flush(dev);
+	if (err)
+		return err;
+
 	/* initiate reset */
-	timeout = 100000;
 	wr_reg32(&jrp->rregs->jrcommand, JRCR_RESET);
 	while ((rd_reg32(&jrp->rregs->jrcommand) & JRCR_RESET) && --timeout)
 		cpu_relax();
@@ -163,6 +198,11 @@ static int caam_jr_remove(struct platform_device *pdev)
 	return ret;
 }
 
+static void caam_jr_platform_shutdown(struct platform_device *pdev)
+{
+	caam_jr_remove(pdev);
+}
+
 /* Main per-ring interrupt handler */
 static irqreturn_t caam_jr_interrupt(int irq, void *st_dev)
 {
@@ -618,6 +658,7 @@ static struct platform_driver caam_jr_driver = {
 	},
 	.probe       = caam_jr_probe,
 	.remove      = caam_jr_remove,
+	.shutdown    = caam_jr_platform_shutdown,
 };
 
 static int __init jr_driver_init(void)
diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c
index 432a61aca0c5..65114f766e7d 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_main.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_main.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include <linux/aer.h>
 #include <linux/delay.h>
 #include <linux/firmware.h>
 #include <linux/list.h>
diff --git a/drivers/crypto/ccp/Makefile b/drivers/crypto/ccp/Makefile
index db362fe472ea..f6196495e862 100644
--- a/drivers/crypto/ccp/Makefile
+++ b/drivers/crypto/ccp/Makefile
@@ -10,7 +10,8 @@ ccp-$(CONFIG_CRYPTO_DEV_CCP_DEBUGFS) += ccp-debugfs.o
 ccp-$(CONFIG_PCI) += sp-pci.o
 ccp-$(CONFIG_CRYPTO_DEV_SP_PSP) += psp-dev.o \
                                    sev-dev.o \
-                                   tee-dev.o
+                                   tee-dev.o \
+                                   platform-access.o
 
 obj-$(CONFIG_CRYPTO_DEV_CCP_CRYPTO) += ccp-crypto.o
 ccp-crypto-objs := ccp-crypto-main.o \
diff --git a/drivers/crypto/ccp/platform-access.c b/drivers/crypto/ccp/platform-access.c
new file mode 100644
index 000000000000..939c924fc383
--- /dev/null
+++ b/drivers/crypto/ccp/platform-access.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD Platform Security Processor (PSP) Platform Access interface
+ *
+ * Copyright (C) 2023 Advanced Micro Devices, Inc.
+ *
+ * Author: Mario Limonciello <mario.limonciello@amd.com>
+ *
+ * Some of this code is adapted from drivers/i2c/busses/i2c-designware-amdpsp.c
+ * developed by Jan Dabros <jsd@semihalf.com> and Copyright (C) 2022 Google Inc.
+ *
+ */
+
+#include <linux/bitfield.h>
+#include <linux/errno.h>
+#include <linux/iopoll.h>
+#include <linux/mutex.h>
+
+#include "platform-access.h"
+
+#define PSP_CMD_TIMEOUT_US	(500 * USEC_PER_MSEC)
+#define DOORBELL_CMDRESP_STS	GENMASK(7, 0)
+
+/* Recovery field should be equal 0 to start sending commands */
+static int check_recovery(u32 __iomem *cmd)
+{
+	return FIELD_GET(PSP_CMDRESP_RECOVERY, ioread32(cmd));
+}
+
+static int wait_cmd(u32 __iomem *cmd)
+{
+	u32 tmp, expected;
+
+	/* Expect mbox_cmd to be cleared and ready bit to be set by PSP */
+	expected = FIELD_PREP(PSP_CMDRESP_RESP, 1);
+
+	/*
+	 * Check for readiness of PSP mailbox in a tight loop in order to
+	 * process further as soon as command was consumed.
+	 */
+	return readl_poll_timeout(cmd, tmp, (tmp & expected), 0,
+				  PSP_CMD_TIMEOUT_US);
+}
+
+int psp_check_platform_access_status(void)
+{
+	struct psp_device *psp = psp_get_master_device();
+
+	if (!psp || !psp->platform_access_data)
+		return -ENODEV;
+
+	return 0;
+}
+EXPORT_SYMBOL(psp_check_platform_access_status);
+
+int psp_send_platform_access_msg(enum psp_platform_access_msg msg,
+				 struct psp_request *req)
+{
+	struct psp_device *psp = psp_get_master_device();
+	u32 __iomem *cmd, *lo, *hi;
+	struct psp_platform_access_device *pa_dev;
+	phys_addr_t req_addr;
+	u32 cmd_reg;
+	int ret;
+
+	if (!psp || !psp->platform_access_data)
+		return -ENODEV;
+
+	pa_dev = psp->platform_access_data;
+	cmd = psp->io_regs + pa_dev->vdata->cmdresp_reg;
+	lo = psp->io_regs + pa_dev->vdata->cmdbuff_addr_lo_reg;
+	hi = psp->io_regs + pa_dev->vdata->cmdbuff_addr_hi_reg;
+
+	mutex_lock(&pa_dev->mailbox_mutex);
+
+	if (check_recovery(cmd)) {
+		dev_dbg(psp->dev, "platform mailbox is in recovery\n");
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	if (wait_cmd(cmd)) {
+		dev_dbg(psp->dev, "platform mailbox is not done processing command\n");
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	/*
+	 * Fill mailbox with address of command-response buffer, which will be
+	 * used for sending i2c requests as well as reading status returned by
+	 * PSP. Use physical address of buffer, since PSP will map this region.
+	 */
+	req_addr = __psp_pa(req);
+	iowrite32(lower_32_bits(req_addr), lo);
+	iowrite32(upper_32_bits(req_addr), hi);
+
+	print_hex_dump_debug("->psp ", DUMP_PREFIX_OFFSET, 16, 2, req,
+			     req->header.payload_size, false);
+
+	/* Write command register to trigger processing */
+	cmd_reg = FIELD_PREP(PSP_CMDRESP_CMD, msg);
+	iowrite32(cmd_reg, cmd);
+
+	if (wait_cmd(cmd)) {
+		ret = -ETIMEDOUT;
+		goto unlock;
+	}
+
+	/* Ensure it was triggered by this driver */
+	if (ioread32(lo) != lower_32_bits(req_addr) ||
+	    ioread32(hi) != upper_32_bits(req_addr)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	/* Store the status in request header for caller to investigate */
+	cmd_reg = ioread32(cmd);
+	req->header.status = FIELD_GET(PSP_CMDRESP_STS, cmd_reg);
+	if (req->header.status) {
+		ret = -EIO;
+		goto unlock;
+	}
+
+	print_hex_dump_debug("<-psp ", DUMP_PREFIX_OFFSET, 16, 2, req,
+			     req->header.payload_size, false);
+
+	ret = 0;
+
+unlock:
+	mutex_unlock(&pa_dev->mailbox_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(psp_send_platform_access_msg);
+
+int psp_ring_platform_doorbell(int msg, u32 *result)
+{
+	struct psp_device *psp = psp_get_master_device();
+	struct psp_platform_access_device *pa_dev;
+	u32 __iomem *button, *cmd;
+	int ret, val;
+
+	if (!psp || !psp->platform_access_data)
+		return -ENODEV;
+
+	pa_dev = psp->platform_access_data;
+	button = psp->io_regs + pa_dev->vdata->doorbell_button_reg;
+	cmd = psp->io_regs + pa_dev->vdata->doorbell_cmd_reg;
+
+	mutex_lock(&pa_dev->doorbell_mutex);
+
+	if (wait_cmd(cmd)) {
+		dev_err(psp->dev, "doorbell command not done processing\n");
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	iowrite32(FIELD_PREP(DOORBELL_CMDRESP_STS, msg), cmd);
+	iowrite32(PSP_DRBL_RING, button);
+
+	if (wait_cmd(cmd)) {
+		ret = -ETIMEDOUT;
+		goto unlock;
+	}
+
+	val = FIELD_GET(DOORBELL_CMDRESP_STS, ioread32(cmd));
+	if (val) {
+		if (result)
+			*result = val;
+		ret = -EIO;
+		goto unlock;
+	}
+
+	ret = 0;
+unlock:
+	mutex_unlock(&pa_dev->doorbell_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(psp_ring_platform_doorbell);
+
+void platform_access_dev_destroy(struct psp_device *psp)
+{
+	struct psp_platform_access_device *pa_dev = psp->platform_access_data;
+
+	if (!pa_dev)
+		return;
+
+	mutex_destroy(&pa_dev->mailbox_mutex);
+	mutex_destroy(&pa_dev->doorbell_mutex);
+	psp->platform_access_data = NULL;
+}
+
+int platform_access_dev_init(struct psp_device *psp)
+{
+	struct device *dev = psp->dev;
+	struct psp_platform_access_device *pa_dev;
+
+	pa_dev = devm_kzalloc(dev, sizeof(*pa_dev), GFP_KERNEL);
+	if (!pa_dev)
+		return -ENOMEM;
+
+	psp->platform_access_data = pa_dev;
+	pa_dev->psp = psp;
+	pa_dev->dev = dev;
+
+	pa_dev->vdata = (struct platform_access_vdata *)psp->vdata->platform_access;
+
+	mutex_init(&pa_dev->mailbox_mutex);
+	mutex_init(&pa_dev->doorbell_mutex);
+
+	dev_dbg(dev, "platform access enabled\n");
+
+	return 0;
+}
diff --git a/drivers/crypto/ccp/platform-access.h b/drivers/crypto/ccp/platform-access.h
new file mode 100644
index 000000000000..a83f03beb869
--- /dev/null
+++ b/drivers/crypto/ccp/platform-access.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AMD Platform Security Processor (PSP) Platform Access interface
+ *
+ * Copyright (C) 2023 Advanced Micro Devices, Inc.
+ *
+ * Author: Mario Limonciello <mario.limonciello@amd.com>
+ */
+
+#ifndef __PSP_PLATFORM_ACCESS_H__
+#define __PSP_PLATFORM_ACCESS_H__
+
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+#include <linux/mutex.h>
+#include <linux/psp-platform-access.h>
+
+#include "psp-dev.h"
+
+struct psp_platform_access_device {
+	struct device *dev;
+	struct psp_device *psp;
+
+	struct platform_access_vdata *vdata;
+
+	struct mutex mailbox_mutex;
+	struct mutex doorbell_mutex;
+
+	void *platform_access_data;
+};
+
+void platform_access_dev_destroy(struct psp_device *psp);
+int platform_access_dev_init(struct psp_device *psp);
+
+#endif /* __PSP_PLATFORM_ACCESS_H__ */
diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index c9c741ac8442..e3d6955d3265 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -14,6 +14,7 @@
 #include "psp-dev.h"
 #include "sev-dev.h"
 #include "tee-dev.h"
+#include "platform-access.h"
 
 struct psp_device *psp_master;
 
@@ -42,18 +43,15 @@ static irqreturn_t psp_irq_handler(int irq, void *data)
 	/* Read the interrupt status: */
 	status = ioread32(psp->io_regs + psp->vdata->intsts_reg);
 
+	/* Clear the interrupt status by writing the same value we read. */
+	iowrite32(status, psp->io_regs + psp->vdata->intsts_reg);
+
 	/* invoke subdevice interrupt handlers */
 	if (status) {
 		if (psp->sev_irq_handler)
 			psp->sev_irq_handler(irq, psp->sev_irq_data, status);
-
-		if (psp->tee_irq_handler)
-			psp->tee_irq_handler(irq, psp->tee_irq_data, status);
 	}
 
-	/* Clear the interrupt status by writing the same value we read. */
-	iowrite32(status, psp->io_regs + psp->vdata->intsts_reg);
-
 	return IRQ_HANDLED;
 }
 
@@ -105,6 +103,17 @@ static int psp_check_tee_support(struct psp_device *psp)
 	return 0;
 }
 
+static void psp_init_platform_access(struct psp_device *psp)
+{
+	int ret;
+
+	ret = platform_access_dev_init(psp);
+	if (ret) {
+		dev_warn(psp->dev, "platform access init failed: %d\n", ret);
+		return;
+	}
+}
+
 static int psp_init(struct psp_device *psp)
 {
 	int ret;
@@ -121,6 +130,9 @@ static int psp_init(struct psp_device *psp)
 			return ret;
 	}
 
+	if (psp->vdata->platform_access)
+		psp_init_platform_access(psp);
+
 	return 0;
 }
 
@@ -201,6 +213,8 @@ void psp_dev_destroy(struct sp_device *sp)
 
 	tee_dev_destroy(psp);
 
+	platform_access_dev_destroy(psp);
+
 	sp_free_psp_irq(sp, psp);
 
 	if (sp->clear_psp_master_device)
@@ -219,18 +233,6 @@ void psp_clear_sev_irq_handler(struct psp_device *psp)
 	psp_set_sev_irq_handler(psp, NULL, NULL);
 }
 
-void psp_set_tee_irq_handler(struct psp_device *psp, psp_irq_handler_t handler,
-			     void *data)
-{
-	psp->tee_irq_data = data;
-	psp->tee_irq_handler = handler;
-}
-
-void psp_clear_tee_irq_handler(struct psp_device *psp)
-{
-	psp_set_tee_irq_handler(psp, NULL, NULL);
-}
-
 struct psp_device *psp_get_master_device(void)
 {
 	struct sp_device *sp = sp_get_psp_master_device();
diff --git a/drivers/crypto/ccp/psp-dev.h b/drivers/crypto/ccp/psp-dev.h
index d528eb04c3ef..505e4bdeaca8 100644
--- a/drivers/crypto/ccp/psp-dev.h
+++ b/drivers/crypto/ccp/psp-dev.h
@@ -17,9 +17,6 @@
 
 #include "sp-dev.h"
 
-#define PSP_CMDRESP_RESP		BIT(31)
-#define PSP_CMDRESP_ERR_MASK		0xffff
-
 #define MAX_PSP_NAME_LEN		16
 
 extern struct psp_device *psp_master;
@@ -40,11 +37,9 @@ struct psp_device {
 	psp_irq_handler_t sev_irq_handler;
 	void *sev_irq_data;
 
-	psp_irq_handler_t tee_irq_handler;
-	void *tee_irq_data;
-
 	void *sev_data;
 	void *tee_data;
+	void *platform_access_data;
 
 	unsigned int capability;
 };
@@ -53,10 +48,6 @@ void psp_set_sev_irq_handler(struct psp_device *psp, psp_irq_handler_t handler,
 			     void *data);
 void psp_clear_sev_irq_handler(struct psp_device *psp);
 
-void psp_set_tee_irq_handler(struct psp_device *psp, psp_irq_handler_t handler,
-			     void *data);
-void psp_clear_tee_irq_handler(struct psp_device *psp);
-
 struct psp_device *psp_get_master_device(void);
 
 #define PSP_CAPABILITY_SEV			BIT(0)
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index e346c00b132a..b1f3327f65e0 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -7,6 +7,7 @@
  * Author: Brijesh Singh <brijesh.singh@amd.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
@@ -24,6 +25,7 @@
 #include <linux/cpufeature.h>
 #include <linux/fs.h>
 #include <linux/fs_struct.h>
+#include <linux/psp.h>
 
 #include <asm/smp.h>
 #include <asm/cacheflush.h>
@@ -102,7 +104,7 @@ static void sev_irq_handler(int irq, void *data, unsigned int status)
 
 	/* Check if it is SEV command completion: */
 	reg = ioread32(sev->io_regs + sev->vdata->cmdresp_reg);
-	if (reg & PSP_CMDRESP_RESP) {
+	if (FIELD_GET(PSP_CMDRESP_RESP, reg)) {
 		sev->int_rcvd = 1;
 		wake_up(&sev->int_queue);
 	}
@@ -346,9 +348,7 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 
 	sev->int_rcvd = 0;
 
-	reg = cmd;
-	reg <<= SEV_CMDRESP_CMD_SHIFT;
-	reg |= SEV_CMDRESP_IOC;
+	reg = FIELD_PREP(SEV_CMDRESP_CMD, cmd) | SEV_CMDRESP_IOC;
 	iowrite32(reg, sev->io_regs + sev->vdata->cmdresp_reg);
 
 	/* wait for command completion */
@@ -366,11 +366,11 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 	psp_timeout = psp_cmd_timeout;
 
 	if (psp_ret)
-		*psp_ret = reg & PSP_CMDRESP_ERR_MASK;
+		*psp_ret = FIELD_GET(PSP_CMDRESP_STS, reg);
 
-	if (reg & PSP_CMDRESP_ERR_MASK) {
-		dev_dbg(sev->dev, "sev command %#x failed (%#010x)\n",
-			cmd, reg & PSP_CMDRESP_ERR_MASK);
+	if (FIELD_GET(PSP_CMDRESP_STS, reg)) {
+		dev_dbg(sev->dev, "sev command %#x failed (%#010lx)\n",
+			cmd, FIELD_GET(PSP_CMDRESP_STS, reg));
 		ret = -EIO;
 	} else {
 		ret = sev_write_init_ex_file_if_required(cmd);
diff --git a/drivers/crypto/ccp/sev-dev.h b/drivers/crypto/ccp/sev-dev.h
index 666c21eb81ab..778c95155e74 100644
--- a/drivers/crypto/ccp/sev-dev.h
+++ b/drivers/crypto/ccp/sev-dev.h
@@ -25,8 +25,8 @@
 #include <linux/miscdevice.h>
 #include <linux/capability.h>
 
+#define SEV_CMDRESP_CMD			GENMASK(26, 16)
 #define SEV_CMD_COMPLETE		BIT(1)
-#define SEV_CMDRESP_CMD_SHIFT		16
 #define SEV_CMDRESP_IOC			BIT(0)
 
 struct sev_misc_dev {
diff --git a/drivers/crypto/ccp/sp-dev.h b/drivers/crypto/ccp/sp-dev.h
index 20377e67f65d..1253a0217985 100644
--- a/drivers/crypto/ccp/sp-dev.h
+++ b/drivers/crypto/ccp/sp-dev.h
@@ -53,9 +53,19 @@ struct tee_vdata {
 	const unsigned int ring_rptr_reg;
 };
 
+struct platform_access_vdata {
+	const unsigned int cmdresp_reg;
+	const unsigned int cmdbuff_addr_lo_reg;
+	const unsigned int cmdbuff_addr_hi_reg;
+	const unsigned int doorbell_button_reg;
+	const unsigned int doorbell_cmd_reg;
+
+};
+
 struct psp_vdata {
 	const struct sev_vdata *sev;
 	const struct tee_vdata *tee;
+	const struct platform_access_vdata *platform_access;
 	const unsigned int feature_reg;
 	const unsigned int inten_reg;
 	const unsigned int intsts_reg;
diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c
index cde33b2ac71b..aa15bc4cac2b 100644
--- a/drivers/crypto/ccp/sp-pci.c
+++ b/drivers/crypto/ccp/sp-pci.c
@@ -361,6 +361,14 @@ static const struct tee_vdata teev1 = {
 	.ring_rptr_reg          = 0x10554,	/* C2PMSG_21 */
 };
 
+static const struct platform_access_vdata pa_v1 = {
+	.cmdresp_reg		= 0x10570,	/* C2PMSG_28 */
+	.cmdbuff_addr_lo_reg	= 0x10574,	/* C2PMSG_29 */
+	.cmdbuff_addr_hi_reg	= 0x10578,	/* C2PMSG_30 */
+	.doorbell_button_reg	= 0x10a24,	/* C2PMSG_73 */
+	.doorbell_cmd_reg	= 0x10a40,	/* C2PMSG_80 */
+};
+
 static const struct psp_vdata pspv1 = {
 	.sev			= &sevv1,
 	.feature_reg		= 0x105fc,	/* C2PMSG_63 */
@@ -377,6 +385,7 @@ static const struct psp_vdata pspv2 = {
 
 static const struct psp_vdata pspv3 = {
 	.tee			= &teev1,
+	.platform_access	= &pa_v1,
 	.feature_reg		= 0x109fc,	/* C2PMSG_63 */
 	.inten_reg		= 0x10690,	/* P2CMSG_INTEN */
 	.intsts_reg		= 0x10694,	/* P2CMSG_INTSTS */
@@ -451,9 +460,9 @@ static const struct pci_device_id sp_pci_table[] = {
 	{ PCI_VDEVICE(AMD, 0x1468), (kernel_ulong_t)&dev_vdata[2] },
 	{ PCI_VDEVICE(AMD, 0x1486), (kernel_ulong_t)&dev_vdata[3] },
 	{ PCI_VDEVICE(AMD, 0x15DF), (kernel_ulong_t)&dev_vdata[4] },
-	{ PCI_VDEVICE(AMD, 0x1649), (kernel_ulong_t)&dev_vdata[4] },
 	{ PCI_VDEVICE(AMD, 0x14CA), (kernel_ulong_t)&dev_vdata[5] },
 	{ PCI_VDEVICE(AMD, 0x15C7), (kernel_ulong_t)&dev_vdata[6] },
+	{ PCI_VDEVICE(AMD, 0x1649), (kernel_ulong_t)&dev_vdata[6] },
 	/* Last entry must be zero */
 	{ 0, }
 };
diff --git a/drivers/crypto/ccp/tee-dev.c b/drivers/crypto/ccp/tee-dev.c
index 5c9d47f3be37..5560bf8329a1 100644
--- a/drivers/crypto/ccp/tee-dev.c
+++ b/drivers/crypto/ccp/tee-dev.c
@@ -8,12 +8,13 @@
  * Copyright (C) 2019,2021 Advanced Micro Devices, Inc.
  */
 
+#include <linux/bitfield.h>
 #include <linux/types.h>
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/gfp.h>
-#include <linux/psp-sev.h>
+#include <linux/psp.h>
 #include <linux/psp-tee.h>
 
 #include "psp-dev.h"
@@ -69,7 +70,7 @@ static int tee_wait_cmd_poll(struct psp_tee_device *tee, unsigned int timeout,
 
 	while (--nloop) {
 		*reg = ioread32(tee->io_regs + tee->vdata->cmdresp_reg);
-		if (*reg & PSP_CMDRESP_RESP)
+		if (FIELD_GET(PSP_CMDRESP_RESP, *reg))
 			return 0;
 
 		usleep_range(10000, 10100);
@@ -149,9 +150,9 @@ static int tee_init_ring(struct psp_tee_device *tee)
 		goto free_buf;
 	}
 
-	if (reg & PSP_CMDRESP_ERR_MASK) {
-		dev_err(tee->dev, "tee: ring init command failed (%#010x)\n",
-			reg & PSP_CMDRESP_ERR_MASK);
+	if (FIELD_GET(PSP_CMDRESP_STS, reg)) {
+		dev_err(tee->dev, "tee: ring init command failed (%#010lx)\n",
+			FIELD_GET(PSP_CMDRESP_STS, reg));
 		tee_free_ring(tee);
 		ret = -EIO;
 	}
@@ -179,9 +180,9 @@ static void tee_destroy_ring(struct psp_tee_device *tee)
 	ret = tee_wait_cmd_poll(tee, TEE_DEFAULT_TIMEOUT, &reg);
 	if (ret) {
 		dev_err(tee->dev, "tee: ring destroy command timed out\n");
-	} else if (reg & PSP_CMDRESP_ERR_MASK) {
-		dev_err(tee->dev, "tee: ring destroy command failed (%#010x)\n",
-			reg & PSP_CMDRESP_ERR_MASK);
+	} else if (FIELD_GET(PSP_CMDRESP_STS, reg)) {
+		dev_err(tee->dev, "tee: ring destroy command failed (%#010lx)\n",
+			FIELD_GET(PSP_CMDRESP_STS, reg));
 	}
 
 free_ring:
diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c
index d489c6f80892..c57f929805d5 100644
--- a/drivers/crypto/ccree/cc_driver.c
+++ b/drivers/crypto/ccree/cc_driver.c
@@ -350,9 +350,9 @@ static int init_cc_resources(struct platform_device *plat_dev)
 
 	/* Get device resources */
 	/* First CC registers space */
-	req_mem_cc_regs = platform_get_resource(plat_dev, IORESOURCE_MEM, 0);
 	/* Map registers space */
-	new_drvdata->cc_base = devm_ioremap_resource(dev, req_mem_cc_regs);
+	new_drvdata->cc_base = devm_platform_get_and_ioremap_resource(plat_dev,
+								      0, &req_mem_cc_regs);
 	if (IS_ERR(new_drvdata->cc_base))
 		return PTR_ERR(new_drvdata->cc_base);
 
diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c
index 5a7f6611803c..8e4a49b7ab4f 100644
--- a/drivers/crypto/hifn_795x.c
+++ b/drivers/crypto/hifn_795x.c
@@ -879,7 +879,7 @@ static int hifn_enable_crypto(struct hifn_device *dev)
 
 static void hifn_init_dma(struct hifn_device *dev)
 {
-	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+	struct hifn_dma *dma = dev->desc_virt;
 	u32 dptr = dev->desc_dma;
 	int i;
 
@@ -1072,7 +1072,7 @@ static int hifn_setup_crypto_command(struct hifn_device *dev,
 		u8 *buf, unsigned dlen, unsigned slen,
 		u8 *key, int keylen, u8 *iv, int ivsize, u16 mode)
 {
-	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+	struct hifn_dma *dma = dev->desc_virt;
 	struct hifn_crypt_command *cry_cmd;
 	u8 *buf_pos = buf;
 	u16 cmd_len;
@@ -1113,7 +1113,7 @@ static int hifn_setup_cmd_desc(struct hifn_device *dev,
 		struct hifn_context *ctx, struct hifn_request_context *rctx,
 		void *priv, unsigned int nbytes)
 {
-	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+	struct hifn_dma *dma = dev->desc_virt;
 	int cmd_len, sa_idx;
 	u8 *buf, *buf_pos;
 	u16 mask;
@@ -1231,7 +1231,7 @@ err_out:
 static int hifn_setup_src_desc(struct hifn_device *dev, struct page *page,
 		unsigned int offset, unsigned int size, int last)
 {
-	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+	struct hifn_dma *dma = dev->desc_virt;
 	int idx;
 	dma_addr_t addr;
 
@@ -1264,7 +1264,7 @@ static int hifn_setup_src_desc(struct hifn_device *dev, struct page *page,
 
 static void hifn_setup_res_desc(struct hifn_device *dev)
 {
-	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+	struct hifn_dma *dma = dev->desc_virt;
 
 	dma->resr[dma->resi].l = __cpu_to_le32(HIFN_USED_RESULT |
 			HIFN_D_VALID | HIFN_D_LAST);
@@ -1290,7 +1290,7 @@ static void hifn_setup_res_desc(struct hifn_device *dev)
 static void hifn_setup_dst_desc(struct hifn_device *dev, struct page *page,
 		unsigned offset, unsigned size, int last)
 {
-	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+	struct hifn_dma *dma = dev->desc_virt;
 	int idx;
 	dma_addr_t addr;
 
@@ -1710,7 +1710,7 @@ static void hifn_process_ready(struct skcipher_request *req, int error)
 
 static void hifn_clear_rings(struct hifn_device *dev, int error)
 {
-	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+	struct hifn_dma *dma = dev->desc_virt;
 	int i, u;
 
 	dev_dbg(&dev->pdev->dev, "ring cleanup 1: i: %d.%d.%d.%d, u: %d.%d.%d.%d, "
@@ -1784,7 +1784,7 @@ static void hifn_work(struct work_struct *work)
 
 	spin_lock_irqsave(&dev->lock, flags);
 	if (dev->active == 0) {
-		struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+		struct hifn_dma *dma = dev->desc_virt;
 
 		if (dma->cmdu == 0 && (dev->flags & HIFN_FLAG_CMD_BUSY)) {
 			dev->flags &= ~HIFN_FLAG_CMD_BUSY;
@@ -1815,7 +1815,7 @@ static void hifn_work(struct work_struct *work)
 	if (reset) {
 		if (++dev->reset >= 5) {
 			int i;
-			struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+			struct hifn_dma *dma = dev->desc_virt;
 
 			dev_info(&dev->pdev->dev,
 				 "r: %08x, active: %d, started: %d, "
@@ -1848,8 +1848,8 @@ static void hifn_work(struct work_struct *work)
 
 static irqreturn_t hifn_interrupt(int irq, void *data)
 {
-	struct hifn_device *dev = (struct hifn_device *)data;
-	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+	struct hifn_device *dev = data;
+	struct hifn_dma *dma = dev->desc_virt;
 	u32 dmacsr, restart;
 
 	dmacsr = hifn_read_1(dev, HIFN_1_DMA_CSR);
@@ -1914,7 +1914,7 @@ static void hifn_flush(struct hifn_device *dev)
 	unsigned long flags;
 	struct crypto_async_request *async_req;
 	struct skcipher_request *req;
-	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
+	struct hifn_dma *dma = dev->desc_virt;
 	int i;
 
 	for (i = 0; i < HIFN_D_RES_RSIZE; ++i) {
diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig
index 4137a8bf131f..e8690c223584 100644
--- a/drivers/crypto/hisilicon/Kconfig
+++ b/drivers/crypto/hisilicon/Kconfig
@@ -82,3 +82,10 @@ config CRYPTO_DEV_HISI_TRNG
 	select CRYPTO_RNG
 	help
 	  Support for HiSilicon TRNG Driver.
+
+config CRYPTO_DEV_HISTB_TRNG
+	tristate "Support for HiSTB TRNG Driver"
+	depends on ARCH_HISI || COMPILE_TEST
+	select HW_RANDOM
+	help
+	  Support for HiSTB TRNG Driver.
diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile
index 8595a5a5d228..fc51e0edec69 100644
--- a/drivers/crypto/hisilicon/Makefile
+++ b/drivers/crypto/hisilicon/Makefile
@@ -5,4 +5,4 @@ obj-$(CONFIG_CRYPTO_DEV_HISI_SEC2) += sec2/
 obj-$(CONFIG_CRYPTO_DEV_HISI_QM) += hisi_qm.o
 hisi_qm-objs = qm.o sgl.o debugfs.o
 obj-$(CONFIG_CRYPTO_DEV_HISI_ZIP) += zip/
-obj-$(CONFIG_CRYPTO_DEV_HISI_TRNG) += trng/
+obj-y += trng/
diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c
index 923f9c279265..5d0adfb54a34 100644
--- a/drivers/crypto/hisilicon/hpre/hpre_main.c
+++ b/drivers/crypto/hisilicon/hpre/hpre_main.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2018-2019 HiSilicon Limited. */
 #include <linux/acpi.h>
-#include <linux/aer.h>
 #include <linux/bitops.h>
 #include <linux/debugfs.h>
 #include <linux/init.h>
diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index e4c84433a88a..8b563ab47484 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2019 HiSilicon Limited. */
 #include <asm/page.h>
 #include <linux/acpi.h>
-#include <linux/aer.h>
 #include <linux/bitmap.h>
 #include <linux/dma-mapping.h>
 #include <linux/idr.h>
diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c
index 93572c0d4faa..77f9f131b850 100644
--- a/drivers/crypto/hisilicon/sec2/sec_main.c
+++ b/drivers/crypto/hisilicon/sec2/sec_main.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2019 HiSilicon Limited. */
 
 #include <linux/acpi.h>
-#include <linux/aer.h>
 #include <linux/bitops.h>
 #include <linux/debugfs.h>
 #include <linux/init.h>
diff --git a/drivers/crypto/hisilicon/trng/Makefile b/drivers/crypto/hisilicon/trng/Makefile
index d909079f351c..cf20b057c66b 100644
--- a/drivers/crypto/hisilicon/trng/Makefile
+++ b/drivers/crypto/hisilicon/trng/Makefile
@@ -1,2 +1,5 @@
 obj-$(CONFIG_CRYPTO_DEV_HISI_TRNG) += hisi-trng-v2.o
 hisi-trng-v2-objs = trng.o
+
+obj-$(CONFIG_CRYPTO_DEV_HISTB_TRNG) += histb-trng.o
+histb-trng-objs += trng-stb.o
diff --git a/drivers/crypto/hisilicon/trng/trng-stb.c b/drivers/crypto/hisilicon/trng/trng-stb.c
new file mode 100644
index 000000000000..29200a7d3d81
--- /dev/null
+++ b/drivers/crypto/hisilicon/trng/trng-stb.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Device driver for True RNG in HiSTB SoCs
+ *
+ * Copyright (c) 2023 David Yang
+ */
+
+#include <crypto/internal/rng.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/hw_random.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_device.h>
+
+#define HISTB_TRNG_CTRL		0x0
+#define  RNG_SOURCE			GENMASK(1, 0)
+#define  DROP_ENABLE			BIT(5)
+#define  POST_PROCESS_ENABLE		BIT(7)
+#define  POST_PROCESS_DEPTH		GENMASK(15, 8)
+#define HISTB_TRNG_NUMBER	0x4
+#define HISTB_TRNG_STAT		0x8
+#define  DATA_COUNT			GENMASK(2, 0)	/* max 4 */
+
+struct histb_trng_priv {
+	struct hwrng rng;
+	void __iomem *base;
+};
+
+/*
+ * Observed:
+ * depth = 1 -> ~1ms
+ * depth = 255 -> ~16ms
+ */
+static int histb_trng_wait(void __iomem *base)
+{
+	u32 val;
+
+	return readl_relaxed_poll_timeout(base + HISTB_TRNG_STAT, val,
+					  val & DATA_COUNT, 1000, 30 * 1000);
+}
+
+static void histb_trng_init(void __iomem *base, unsigned int depth)
+{
+	u32 val;
+
+	val = readl_relaxed(base + HISTB_TRNG_CTRL);
+
+	val &= ~RNG_SOURCE;
+	val |= 2;
+
+	val &= ~POST_PROCESS_DEPTH;
+	val |= min(depth, 0xffu) << 8;
+
+	val |= POST_PROCESS_ENABLE;
+	val |= DROP_ENABLE;
+
+	writel_relaxed(val, base + HISTB_TRNG_CTRL);
+}
+
+static int histb_trng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	struct histb_trng_priv *priv = container_of(rng, typeof(*priv), rng);
+	void __iomem *base = priv->base;
+
+	for (int i = 0; i < max; i += sizeof(u32)) {
+		if (!(readl_relaxed(base + HISTB_TRNG_STAT) & DATA_COUNT)) {
+			if (!wait)
+				return i;
+			if (histb_trng_wait(base)) {
+				pr_err("failed to generate random number, generated %d\n",
+				       i);
+				return i ? i : -ETIMEDOUT;
+			}
+		}
+		*(u32 *) (data + i) = readl_relaxed(base + HISTB_TRNG_NUMBER);
+	}
+
+	return max;
+}
+
+static unsigned int histb_trng_get_depth(void __iomem *base)
+{
+	return (readl_relaxed(base + HISTB_TRNG_CTRL) & POST_PROCESS_DEPTH) >> 8;
+}
+
+static ssize_t
+depth_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct histb_trng_priv *priv = dev_get_drvdata(dev);
+	void __iomem *base = priv->base;
+
+	return sprintf(buf, "%d\n", histb_trng_get_depth(base));
+}
+
+static ssize_t
+depth_store(struct device *dev, struct device_attribute *attr,
+	    const char *buf, size_t count)
+{
+	struct histb_trng_priv *priv = dev_get_drvdata(dev);
+	void __iomem *base = priv->base;
+	unsigned int depth;
+
+	if (kstrtouint(buf, 0, &depth))
+		return -ERANGE;
+
+	histb_trng_init(base, depth);
+	return count;
+}
+
+static DEVICE_ATTR_RW(depth);
+
+static struct attribute *histb_trng_attrs[] = {
+	&dev_attr_depth.attr,
+	NULL,
+};
+
+ATTRIBUTE_GROUPS(histb_trng);
+
+static int histb_trng_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct histb_trng_priv *priv;
+	void __iomem *base;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return -ENOMEM;
+
+	histb_trng_init(base, 144);
+	if (histb_trng_wait(base)) {
+		dev_err(dev, "cannot bring up device\n");
+		return -ENODEV;
+	}
+
+	priv->base = base;
+	priv->rng.name = pdev->name;
+	priv->rng.read = histb_trng_read;
+	ret = devm_hwrng_register(dev, &priv->rng);
+	if (ret) {
+		dev_err(dev, "failed to register hwrng: %d\n", ret);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, priv);
+	dev_set_drvdata(dev, priv);
+	return 0;
+}
+
+static const struct of_device_id histb_trng_of_match[] = {
+	{ .compatible = "hisilicon,histb-trng", },
+	{ }
+};
+
+static struct platform_driver histb_trng_driver = {
+	.probe = histb_trng_probe,
+	.driver = {
+		.name = "histb-trng",
+		.of_match_table = histb_trng_of_match,
+		.dev_groups = histb_trng_groups,
+	},
+};
+
+module_platform_driver(histb_trng_driver);
+
+MODULE_DESCRIPTION("HiSTB True RNG");
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_AUTHOR("David Yang <mmyangfl@gmail.com>");
diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c
index 1549bec3aea5..f3ce34198775 100644
--- a/drivers/crypto/hisilicon/zip/zip_main.c
+++ b/drivers/crypto/hisilicon/zip/zip_main.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 HiSilicon Limited. */
 #include <linux/acpi.h>
-#include <linux/aer.h>
 #include <linux/bitops.h>
 #include <linux/debugfs.h>
 #include <linux/init.h>
diff --git a/drivers/crypto/img-hash.c b/drivers/crypto/img-hash.c
index fe93d19e3044..359aa2b41016 100644
--- a/drivers/crypto/img-hash.c
+++ b/drivers/crypto/img-hash.c
@@ -209,7 +209,7 @@ static int img_hash_xmit_cpu(struct img_hash_dev *hdev, const u8 *buf,
 
 static void img_hash_dma_callback(void *data)
 {
-	struct img_hash_dev *hdev = (struct img_hash_dev *)data;
+	struct img_hash_dev *hdev = data;
 	struct img_hash_request_ctx *ctx = ahash_request_ctx(hdev->req);
 
 	if (ctx->bufcnt) {
@@ -927,7 +927,7 @@ finish:
 	img_hash_finish_req(hdev->req, err);
 }
 
-static const struct of_device_id img_hash_match[] = {
+static const struct of_device_id img_hash_match[] __maybe_unused = {
 	{ .compatible = "img,hash-accelerator" },
 	{}
 };
@@ -966,8 +966,7 @@ static int img_hash_probe(struct platform_device *pdev)
 	}
 
 	/* Write port (DMA or CPU) */
-	hash_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	hdev->cpu_addr = devm_ioremap_resource(dev, hash_res);
+	hdev->cpu_addr = devm_platform_get_and_ioremap_resource(pdev, 1, &hash_res);
 	if (IS_ERR(hdev->cpu_addr)) {
 		err = PTR_ERR(hdev->cpu_addr);
 		goto res_err;
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 6858753af6b3..9ff02b5abc4a 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -474,7 +474,7 @@ release_fw:
 		goto retry_fw;
 	}
 
-	dev_dbg(priv->dev, "Firmware load failed.\n");
+	dev_err(priv->dev, "Firmware load failed.\n");
 
 	return ret;
 }
@@ -1628,19 +1628,23 @@ static int safexcel_probe_generic(void *pdev,
 						     &priv->ring[i].rdr);
 		if (ret) {
 			dev_err(dev, "Failed to initialize rings\n");
-			return ret;
+			goto err_cleanup_rings;
 		}
 
 		priv->ring[i].rdr_req = devm_kcalloc(dev,
 			EIP197_DEFAULT_RING_SIZE,
 			sizeof(*priv->ring[i].rdr_req),
 			GFP_KERNEL);
-		if (!priv->ring[i].rdr_req)
-			return -ENOMEM;
+		if (!priv->ring[i].rdr_req) {
+			ret = -ENOMEM;
+			goto err_cleanup_rings;
+		}
 
 		ring_irq = devm_kzalloc(dev, sizeof(*ring_irq), GFP_KERNEL);
-		if (!ring_irq)
-			return -ENOMEM;
+		if (!ring_irq) {
+			ret = -ENOMEM;
+			goto err_cleanup_rings;
+		}
 
 		ring_irq->priv = priv;
 		ring_irq->ring = i;
@@ -1654,7 +1658,8 @@ static int safexcel_probe_generic(void *pdev,
 						ring_irq);
 		if (irq < 0) {
 			dev_err(dev, "Failed to get IRQ ID for ring %d\n", i);
-			return irq;
+			ret = irq;
+			goto err_cleanup_rings;
 		}
 
 		priv->ring[i].irq = irq;
@@ -1666,8 +1671,10 @@ static int safexcel_probe_generic(void *pdev,
 		snprintf(wq_name, 9, "wq_ring%d", i);
 		priv->ring[i].workqueue =
 			create_singlethread_workqueue(wq_name);
-		if (!priv->ring[i].workqueue)
-			return -ENOMEM;
+		if (!priv->ring[i].workqueue) {
+			ret = -ENOMEM;
+			goto err_cleanup_rings;
+		}
 
 		priv->ring[i].requests = 0;
 		priv->ring[i].busy = false;
@@ -1684,16 +1691,26 @@ static int safexcel_probe_generic(void *pdev,
 	ret = safexcel_hw_init(priv);
 	if (ret) {
 		dev_err(dev, "HW init failed (%d)\n", ret);
-		return ret;
+		goto err_cleanup_rings;
 	}
 
 	ret = safexcel_register_algorithms(priv);
 	if (ret) {
 		dev_err(dev, "Failed to register algorithms (%d)\n", ret);
-		return ret;
+		goto err_cleanup_rings;
 	}
 
 	return 0;
+
+err_cleanup_rings:
+	for (i = 0; i < priv->config.rings; i++) {
+		if (priv->ring[i].irq)
+			irq_set_affinity_hint(priv->ring[i].irq, NULL);
+		if (priv->ring[i].workqueue)
+			destroy_workqueue(priv->ring[i].workqueue);
+	}
+
+	return ret;
 }
 
 static void safexcel_hw_reset_rings(struct safexcel_crypto_priv *priv)
diff --git a/drivers/crypto/intel/Kconfig b/drivers/crypto/intel/Kconfig
new file mode 100644
index 000000000000..3d90c87d4094
--- /dev/null
+++ b/drivers/crypto/intel/Kconfig
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+source "drivers/crypto/intel/keembay/Kconfig"
+source "drivers/crypto/intel/ixp4xx/Kconfig"
+source "drivers/crypto/intel/qat/Kconfig"
diff --git a/drivers/crypto/intel/Makefile b/drivers/crypto/intel/Makefile
new file mode 100644
index 000000000000..b3d0352ae188
--- /dev/null
+++ b/drivers/crypto/intel/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-y += keembay/
+obj-y += ixp4xx/
+obj-$(CONFIG_CRYPTO_DEV_QAT) += qat/
diff --git a/drivers/crypto/intel/ixp4xx/Kconfig b/drivers/crypto/intel/ixp4xx/Kconfig
new file mode 100644
index 000000000000..af3cc5688328
--- /dev/null
+++ b/drivers/crypto/intel/ixp4xx/Kconfig
@@ -0,0 +1,14 @@
+config CRYPTO_DEV_IXP4XX
+	tristate "Driver for IXP4xx crypto hardware acceleration"
+	depends on (ARCH_IXP4XX || COMPILE_TEST) && IXP4XX_QMGR && IXP4XX_NPE
+	select CRYPTO_AES
+	select CRYPTO_DES
+	select CRYPTO_ECB
+	select CRYPTO_CBC
+	select CRYPTO_CTR
+	select CRYPTO_LIB_DES
+	select CRYPTO_AEAD
+	select CRYPTO_AUTHENC
+	select CRYPTO_SKCIPHER
+	help
+	  Driver for the IXP4xx NPE crypto engine.
diff --git a/drivers/crypto/intel/ixp4xx/Makefile b/drivers/crypto/intel/ixp4xx/Makefile
new file mode 100644
index 000000000000..74ebefd93046
--- /dev/null
+++ b/drivers/crypto/intel/ixp4xx/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CRYPTO_DEV_IXP4XX) += ixp4xx_crypto.o
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c
index b63e2359a133..ed15379a9818 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c
@@ -118,9 +118,9 @@ struct crypt_ctl {
 	u8 mode;		/* NPE_OP_*  operation mode */
 #endif
 	u8 iv[MAX_IVLEN];	/* IV for CBC mode or CTR IV for CTR mode */
-	dma_addr_t icv_rev_aes;	/* icv or rev aes */
-	dma_addr_t src_buf;
-	dma_addr_t dst_buf;
+	u32 icv_rev_aes;	/* icv or rev aes */
+	u32 src_buf;
+	u32 dst_buf;
 #ifdef __ARMEB__
 	u16 auth_offs;		/* Authentication start offset */
 	u16 auth_len;		/* Authentication data length */
@@ -263,7 +263,9 @@ static int setup_crypt_desc(void)
 {
 	struct device *dev = &pdev->dev;
 
-	BUILD_BUG_ON(sizeof(struct crypt_ctl) != 64);
+	BUILD_BUG_ON(!(IS_ENABLED(CONFIG_COMPILE_TEST) &&
+		       IS_ENABLED(CONFIG_64BIT)) &&
+		     sizeof(struct crypt_ctl) != 64);
 	crypt_virt = dma_alloc_coherent(dev,
 					NPE_QLEN * sizeof(struct crypt_ctl),
 					&crypt_phys, GFP_ATOMIC);
@@ -1169,10 +1171,11 @@ static int aead_perform(struct aead_request *req, int encrypt,
 	}
 
 	if (unlikely(lastlen < authsize)) {
+		dma_addr_t dma;
 		/* The 12 hmac bytes are scattered,
 		 * we need to copy them into a safe buffer */
-		req_ctx->hmac_virt = dma_pool_alloc(buffer_pool, flags,
-						    &crypt->icv_rev_aes);
+		req_ctx->hmac_virt = dma_pool_alloc(buffer_pool, flags, &dma);
+		crypt->icv_rev_aes = dma;
 		if (unlikely(!req_ctx->hmac_virt))
 			goto free_buf_dst;
 		if (!encrypt) {
diff --git a/drivers/crypto/keembay/Kconfig b/drivers/crypto/intel/keembay/Kconfig
index 1cd62f9c3e3a..1cd62f9c3e3a 100644
--- a/drivers/crypto/keembay/Kconfig
+++ b/drivers/crypto/intel/keembay/Kconfig
diff --git a/drivers/crypto/keembay/Makefile b/drivers/crypto/intel/keembay/Makefile
index 7c12c3c138bd..7c12c3c138bd 100644
--- a/drivers/crypto/keembay/Makefile
+++ b/drivers/crypto/intel/keembay/Makefile
diff --git a/drivers/crypto/keembay/keembay-ocs-aes-core.c b/drivers/crypto/intel/keembay/keembay-ocs-aes-core.c
index 9953f5590ac4..ae31be00357a 100644
--- a/drivers/crypto/keembay/keembay-ocs-aes-core.c
+++ b/drivers/crypto/intel/keembay/keembay-ocs-aes-core.c
@@ -1580,8 +1580,6 @@ static int kmb_ocs_aes_remove(struct platform_device *pdev)
 	struct ocs_aes_dev *aes_dev;
 
 	aes_dev = platform_get_drvdata(pdev);
-	if (!aes_dev)
-		return -ENODEV;
 
 	unregister_aes_algs(aes_dev);
 
diff --git a/drivers/crypto/keembay/keembay-ocs-ecc.c b/drivers/crypto/intel/keembay/keembay-ocs-ecc.c
index 2269df17514c..2269df17514c 100644
--- a/drivers/crypto/keembay/keembay-ocs-ecc.c
+++ b/drivers/crypto/intel/keembay/keembay-ocs-ecc.c
diff --git a/drivers/crypto/keembay/keembay-ocs-hcu-core.c b/drivers/crypto/intel/keembay/keembay-ocs-hcu-core.c
index d4bcbed1f546..d4bcbed1f546 100644
--- a/drivers/crypto/keembay/keembay-ocs-hcu-core.c
+++ b/drivers/crypto/intel/keembay/keembay-ocs-hcu-core.c
diff --git a/drivers/crypto/keembay/ocs-aes.c b/drivers/crypto/intel/keembay/ocs-aes.c
index be9f32fc8f42..be9f32fc8f42 100644
--- a/drivers/crypto/keembay/ocs-aes.c
+++ b/drivers/crypto/intel/keembay/ocs-aes.c
diff --git a/drivers/crypto/keembay/ocs-aes.h b/drivers/crypto/intel/keembay/ocs-aes.h
index c035fc48b7ed..c035fc48b7ed 100644
--- a/drivers/crypto/keembay/ocs-aes.h
+++ b/drivers/crypto/intel/keembay/ocs-aes.h
diff --git a/drivers/crypto/keembay/ocs-hcu.c b/drivers/crypto/intel/keembay/ocs-hcu.c
index deb9bd460ee6..deb9bd460ee6 100644
--- a/drivers/crypto/keembay/ocs-hcu.c
+++ b/drivers/crypto/intel/keembay/ocs-hcu.c
diff --git a/drivers/crypto/keembay/ocs-hcu.h b/drivers/crypto/intel/keembay/ocs-hcu.h
index fbbbb92a0592..fbbbb92a0592 100644
--- a/drivers/crypto/keembay/ocs-hcu.h
+++ b/drivers/crypto/intel/keembay/ocs-hcu.h
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/intel/qat/Kconfig
index 1220cc86f910..1220cc86f910 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/intel/qat/Kconfig
diff --git a/drivers/crypto/qat/Makefile b/drivers/crypto/intel/qat/Makefile
index 258c8a626ce0..258c8a626ce0 100644
--- a/drivers/crypto/qat/Makefile
+++ b/drivers/crypto/intel/qat/Makefile
diff --git a/drivers/crypto/qat/qat_4xxx/Makefile b/drivers/crypto/intel/qat/qat_4xxx/Makefile
index ff9c8b5897ea..ff9c8b5897ea 100644
--- a/drivers/crypto/qat/qat_4xxx/Makefile
+++ b/drivers/crypto/intel/qat/qat_4xxx/Makefile
diff --git a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
index 834a705180c0..7324b86a4f40 100644
--- a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
@@ -28,13 +28,31 @@ static struct adf_fw_config adf_4xxx_fw_dc_config[] = {
 	{0x100, ADF_4XXX_ADMIN_OBJ},
 };
 
+static struct adf_fw_config adf_402xx_fw_cy_config[] = {
+	{0xF0, ADF_402XX_SYM_OBJ},
+	{0xF, ADF_402XX_ASYM_OBJ},
+	{0x100, ADF_402XX_ADMIN_OBJ},
+};
+
+static struct adf_fw_config adf_402xx_fw_dc_config[] = {
+	{0xF0, ADF_402XX_DC_OBJ},
+	{0xF, ADF_402XX_DC_OBJ},
+	{0x100, ADF_402XX_ADMIN_OBJ},
+};
+
 /* Worker thread to service arbiter mappings */
-static const u32 thrd_to_arb_map[ADF_4XXX_MAX_ACCELENGINES] = {
+static const u32 thrd_to_arb_map_cy[ADF_4XXX_MAX_ACCELENGINES] = {
 	0x5555555, 0x5555555, 0x5555555, 0x5555555,
 	0xAAAAAAA, 0xAAAAAAA, 0xAAAAAAA, 0xAAAAAAA,
 	0x0
 };
 
+static const u32 thrd_to_arb_map_dc[ADF_4XXX_MAX_ACCELENGINES] = {
+	0x000000FF, 0x000000FF, 0x000000FF, 0x000000FF,
+	0x000000FF, 0x000000FF, 0x000000FF, 0x000000FF,
+	0x0
+};
+
 static struct adf_hw_device_class adf_4xxx_class = {
 	.name = ADF_4XXX_DEVICE_NAME,
 	.type = DEV_4XXX,
@@ -206,9 +224,16 @@ static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
 	return DEV_SKU_1;
 }
 
-static const u32 *adf_get_arbiter_mapping(void)
+static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev)
 {
-	return thrd_to_arb_map;
+	switch (get_service_enabled(accel_dev)) {
+	case SVC_CY:
+		return thrd_to_arb_map_cy;
+	case SVC_DC:
+		return thrd_to_arb_map_dc;
+	}
+
+	return NULL;
 }
 
 static void get_arb_info(struct arb_info *arb_info)
@@ -286,7 +311,7 @@ static u32 uof_get_num_objs(void)
 	return ARRAY_SIZE(adf_4xxx_fw_cy_config);
 }
 
-static char *uof_get_name(struct adf_accel_dev *accel_dev, u32 obj_num)
+static char *uof_get_name_4xxx(struct adf_accel_dev *accel_dev, u32 obj_num)
 {
 	switch (get_service_enabled(accel_dev)) {
 	case SVC_CY:
@@ -298,6 +323,18 @@ static char *uof_get_name(struct adf_accel_dev *accel_dev, u32 obj_num)
 	return NULL;
 }
 
+static char *uof_get_name_402xx(struct adf_accel_dev *accel_dev, u32 obj_num)
+{
+	switch (get_service_enabled(accel_dev)) {
+	case SVC_CY:
+		return adf_402xx_fw_cy_config[obj_num].obj_name;
+	case SVC_DC:
+		return adf_402xx_fw_dc_config[obj_num].obj_name;
+	}
+
+	return NULL;
+}
+
 static u32 uof_get_ae_mask(struct adf_accel_dev *accel_dev, u32 obj_num)
 {
 	switch (get_service_enabled(accel_dev)) {
@@ -310,7 +347,7 @@ static u32 uof_get_ae_mask(struct adf_accel_dev *accel_dev, u32 obj_num)
 	return 0;
 }
 
-void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data)
+void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id)
 {
 	hw_data->dev_class = &adf_4xxx_class;
 	hw_data->instance_id = adf_4xxx_class.instances++;
@@ -337,8 +374,6 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data)
 	hw_data->get_admin_info = get_admin_info;
 	hw_data->get_accel_cap = get_accel_cap;
 	hw_data->get_sku = get_sku;
-	hw_data->fw_name = ADF_4XXX_FW;
-	hw_data->fw_mmp_name = ADF_4XXX_MMP;
 	hw_data->init_admin_comms = adf_init_admin_comms;
 	hw_data->exit_admin_comms = adf_exit_admin_comms;
 	hw_data->send_admin_init = adf_send_admin_init;
@@ -349,8 +384,19 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data)
 	hw_data->init_device = adf_init_device;
 	hw_data->reset_device = adf_reset_flr;
 	hw_data->admin_ae_mask = ADF_4XXX_ADMIN_AE_MASK;
+	switch (dev_id) {
+	case ADF_402XX_PCI_DEVICE_ID:
+		hw_data->fw_name = ADF_402XX_FW;
+		hw_data->fw_mmp_name = ADF_402XX_MMP;
+		hw_data->uof_get_name = uof_get_name_402xx;
+		break;
+
+	default:
+		hw_data->fw_name = ADF_4XXX_FW;
+		hw_data->fw_mmp_name = ADF_4XXX_MMP;
+		hw_data->uof_get_name = uof_get_name_4xxx;
+	}
 	hw_data->uof_get_num_objs = uof_get_num_objs;
-	hw_data->uof_get_name = uof_get_name;
 	hw_data->uof_get_ae_mask = uof_get_ae_mask;
 	hw_data->set_msix_rttable = set_msix_default_rttable;
 	hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer;
diff --git a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.h b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.h
index e98428ba78e2..085e259c245a 100644
--- a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.h
@@ -56,6 +56,13 @@
 #define ADF_4XXX_DC_OBJ		"qat_4xxx_dc.bin"
 #define ADF_4XXX_ASYM_OBJ	"qat_4xxx_asym.bin"
 #define ADF_4XXX_ADMIN_OBJ	"qat_4xxx_admin.bin"
+/* Firmware for 402XXX */
+#define ADF_402XX_FW		"qat_402xx.bin"
+#define ADF_402XX_MMP		"qat_402xx_mmp.bin"
+#define ADF_402XX_SYM_OBJ	"qat_402xx_sym.bin"
+#define ADF_402XX_DC_OBJ	"qat_402xx_dc.bin"
+#define ADF_402XX_ASYM_OBJ	"qat_402xx_asym.bin"
+#define ADF_402XX_ADMIN_OBJ	"qat_402xx_admin.bin"
 
 /* qat_4xxx fuse bits are different from old GENs, redefine them */
 enum icp_qat_4xxx_slice_mask {
@@ -68,7 +75,7 @@ enum icp_qat_4xxx_slice_mask {
 	ICP_ACCEL_4XXX_MASK_SMX_SLICE = BIT(6),
 };
 
-void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data);
+void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id);
 void adf_clean_hw_data_4xxx(struct adf_hw_device_data *hw_data);
 int adf_gen4_dev_config(struct adf_accel_dev *accel_dev);
 
diff --git a/drivers/crypto/qat/qat_4xxx/adf_drv.c b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
index b3a4c7b23864..ceb87327a5fe 100644
--- a/drivers/crypto/qat/qat_4xxx/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
@@ -16,6 +16,7 @@
 static const struct pci_device_id adf_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, ADF_4XXX_PCI_DEVICE_ID), },
 	{ PCI_VDEVICE(INTEL, ADF_401XX_PCI_DEVICE_ID), },
+	{ PCI_VDEVICE(INTEL, ADF_402XX_PCI_DEVICE_ID), },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, adf_pci_tbl);
@@ -330,7 +331,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	accel_dev->hw_device = hw_data;
-	adf_init_hw_data_4xxx(accel_dev->hw_device);
+	adf_init_hw_data_4xxx(accel_dev->hw_device, ent->device);
 
 	pci_read_config_byte(pdev, PCI_REVISION_ID, &accel_pci_dev->revid);
 	pci_read_config_dword(pdev, ADF_4XXX_FUSECTL4_OFFSET, &hw_data->fuses);
@@ -403,38 +404,24 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_master(pdev);
 
-	adf_enable_aer(accel_dev);
-
 	if (pci_save_state(pdev)) {
 		dev_err(&pdev->dev, "Failed to save pci state.\n");
 		ret = -ENOMEM;
-		goto out_err_disable_aer;
+		goto out_err;
 	}
 
-	ret = adf_sysfs_init(accel_dev);
-	if (ret)
-		goto out_err_disable_aer;
-
-	ret = hw_data->dev_config(accel_dev);
+	ret = adf_dev_up(accel_dev, true);
 	if (ret)
-		goto out_err_disable_aer;
-
-	ret = adf_dev_init(accel_dev);
-	if (ret)
-		goto out_err_dev_shutdown;
+		goto out_err_dev_stop;
 
-	ret = adf_dev_start(accel_dev);
+	ret = adf_sysfs_init(accel_dev);
 	if (ret)
 		goto out_err_dev_stop;
 
 	return ret;
 
 out_err_dev_stop:
-	adf_dev_stop(accel_dev);
-out_err_dev_shutdown:
-	adf_dev_shutdown(accel_dev);
-out_err_disable_aer:
-	adf_disable_aer(accel_dev);
+	adf_dev_down(accel_dev, false);
 out_err:
 	adf_cleanup_accel(accel_dev);
 	return ret;
@@ -448,9 +435,7 @@ static void adf_remove(struct pci_dev *pdev)
 		pr_err("QAT: Driver removal failed\n");
 		return;
 	}
-	adf_dev_stop(accel_dev);
-	adf_dev_shutdown(accel_dev);
-	adf_disable_aer(accel_dev);
+	adf_dev_down(accel_dev, false);
 	adf_cleanup_accel(accel_dev);
 }
 
diff --git a/drivers/crypto/qat/qat_c3xxx/Makefile b/drivers/crypto/intel/qat/qat_c3xxx/Makefile
index 92ef416ccc78..92ef416ccc78 100644
--- a/drivers/crypto/qat/qat_c3xxx/Makefile
+++ b/drivers/crypto/intel/qat/qat_c3xxx/Makefile
diff --git a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c b/drivers/crypto/intel/qat/qat_c3xxx/adf_c3xxx_hw_data.c
index c55c51a07677..475643654e64 100644
--- a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_c3xxx/adf_c3xxx_hw_data.c
@@ -75,7 +75,7 @@ static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
 	return DEV_SKU_UNKNOWN;
 }
 
-static const u32 *adf_get_arbiter_mapping(void)
+static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev)
 {
 	return thrd_to_arb_map;
 }
diff --git a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.h b/drivers/crypto/intel/qat/qat_c3xxx/adf_c3xxx_hw_data.h
index 336a06f11dbd..336a06f11dbd 100644
--- a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_c3xxx/adf_c3xxx_hw_data.h
diff --git a/drivers/crypto/qat/qat_c3xxx/adf_drv.c b/drivers/crypto/intel/qat/qat_c3xxx/adf_drv.c
index 1f4fbf4562b2..bb4dca735ab5 100644
--- a/drivers/crypto/qat/qat_c3xxx/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_c3xxx/adf_drv.c
@@ -193,34 +193,20 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	pci_set_master(pdev);
 
-	adf_enable_aer(accel_dev);
-
 	if (pci_save_state(pdev)) {
 		dev_err(&pdev->dev, "Failed to save pci state\n");
 		ret = -ENOMEM;
-		goto out_err_disable_aer;
+		goto out_err_free_reg;
 	}
 
-	ret = hw_data->dev_config(accel_dev);
-	if (ret)
-		goto out_err_disable_aer;
-
-	ret = adf_dev_init(accel_dev);
-	if (ret)
-		goto out_err_dev_shutdown;
-
-	ret = adf_dev_start(accel_dev);
+	ret = adf_dev_up(accel_dev, true);
 	if (ret)
 		goto out_err_dev_stop;
 
 	return ret;
 
 out_err_dev_stop:
-	adf_dev_stop(accel_dev);
-out_err_dev_shutdown:
-	adf_dev_shutdown(accel_dev);
-out_err_disable_aer:
-	adf_disable_aer(accel_dev);
+	adf_dev_down(accel_dev, false);
 out_err_free_reg:
 	pci_release_regions(accel_pci_dev->pci_dev);
 out_err_disable:
@@ -239,9 +225,7 @@ static void adf_remove(struct pci_dev *pdev)
 		pr_err("QAT: Driver removal failed\n");
 		return;
 	}
-	adf_dev_stop(accel_dev);
-	adf_dev_shutdown(accel_dev);
-	adf_disable_aer(accel_dev);
+	adf_dev_down(accel_dev, false);
 	adf_cleanup_accel(accel_dev);
 	adf_cleanup_pci_dev(accel_dev);
 	kfree(accel_dev);
diff --git a/drivers/crypto/qat/qat_c3xxxvf/Makefile b/drivers/crypto/intel/qat/qat_c3xxxvf/Makefile
index b6d76825a92c..b6d76825a92c 100644
--- a/drivers/crypto/qat/qat_c3xxxvf/Makefile
+++ b/drivers/crypto/intel/qat/qat_c3xxxvf/Makefile
diff --git a/drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c b/drivers/crypto/intel/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c
index 84d9486e04de..84d9486e04de 100644
--- a/drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c
diff --git a/drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.h b/drivers/crypto/intel/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.h
index 6b4bf181d15b..6b4bf181d15b 100644
--- a/drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.h
diff --git a/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c b/drivers/crypto/intel/qat/qat_c3xxxvf/adf_drv.c
index cf4ef83e186f..e8cc10f64134 100644
--- a/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_c3xxxvf/adf_drv.c
@@ -173,20 +173,14 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Completion for VF2PF request/response message exchange */
 	init_completion(&accel_dev->vf.msg_received);
 
-	ret = adf_dev_init(accel_dev);
-	if (ret)
-		goto out_err_dev_shutdown;
-
-	ret = adf_dev_start(accel_dev);
+	ret = adf_dev_up(accel_dev, false);
 	if (ret)
 		goto out_err_dev_stop;
 
 	return ret;
 
 out_err_dev_stop:
-	adf_dev_stop(accel_dev);
-out_err_dev_shutdown:
-	adf_dev_shutdown(accel_dev);
+	adf_dev_down(accel_dev, false);
 out_err_free_reg:
 	pci_release_regions(accel_pci_dev->pci_dev);
 out_err_disable:
@@ -206,8 +200,7 @@ static void adf_remove(struct pci_dev *pdev)
 		return;
 	}
 	adf_flush_vf_wq(accel_dev);
-	adf_dev_stop(accel_dev);
-	adf_dev_shutdown(accel_dev);
+	adf_dev_down(accel_dev, false);
 	adf_cleanup_accel(accel_dev);
 	adf_cleanup_pci_dev(accel_dev);
 	kfree(accel_dev);
diff --git a/drivers/crypto/qat/qat_c62x/Makefile b/drivers/crypto/intel/qat/qat_c62x/Makefile
index d581f7c87d6c..d581f7c87d6c 100644
--- a/drivers/crypto/qat/qat_c62x/Makefile
+++ b/drivers/crypto/intel/qat/qat_c62x/Makefile
diff --git a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c b/drivers/crypto/intel/qat/qat_c62x/adf_c62x_hw_data.c
index b7aa19d2fa80..e14270703670 100644
--- a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_c62x/adf_c62x_hw_data.c
@@ -77,7 +77,7 @@ static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
 	return DEV_SKU_UNKNOWN;
 }
 
-static const u32 *adf_get_arbiter_mapping(void)
+static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev)
 {
 	return thrd_to_arb_map;
 }
diff --git a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.h b/drivers/crypto/intel/qat/qat_c62x/adf_c62x_hw_data.h
index 008c0a3a9769..008c0a3a9769 100644
--- a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_c62x/adf_c62x_hw_data.h
diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/intel/qat/qat_c62x/adf_drv.c
index 4ccaf298250c..ca18ae14c099 100644
--- a/drivers/crypto/qat/qat_c62x/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_c62x/adf_drv.c
@@ -193,34 +193,20 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	pci_set_master(pdev);
 
-	adf_enable_aer(accel_dev);
-
 	if (pci_save_state(pdev)) {
 		dev_err(&pdev->dev, "Failed to save pci state\n");
 		ret = -ENOMEM;
-		goto out_err_disable_aer;
+		goto out_err_free_reg;
 	}
 
-	ret = hw_data->dev_config(accel_dev);
-	if (ret)
-		goto out_err_disable_aer;
-
-	ret = adf_dev_init(accel_dev);
-	if (ret)
-		goto out_err_dev_shutdown;
-
-	ret = adf_dev_start(accel_dev);
+	ret = adf_dev_up(accel_dev, true);
 	if (ret)
 		goto out_err_dev_stop;
 
 	return ret;
 
 out_err_dev_stop:
-	adf_dev_stop(accel_dev);
-out_err_dev_shutdown:
-	adf_dev_shutdown(accel_dev);
-out_err_disable_aer:
-	adf_disable_aer(accel_dev);
+	adf_dev_down(accel_dev, false);
 out_err_free_reg:
 	pci_release_regions(accel_pci_dev->pci_dev);
 out_err_disable:
@@ -239,9 +225,7 @@ static void adf_remove(struct pci_dev *pdev)
 		pr_err("QAT: Driver removal failed\n");
 		return;
 	}
-	adf_dev_stop(accel_dev);
-	adf_dev_shutdown(accel_dev);
-	adf_disable_aer(accel_dev);
+	adf_dev_down(accel_dev, false);
 	adf_cleanup_accel(accel_dev);
 	adf_cleanup_pci_dev(accel_dev);
 	kfree(accel_dev);
diff --git a/drivers/crypto/qat/qat_c62xvf/Makefile b/drivers/crypto/intel/qat/qat_c62xvf/Makefile
index 446c3d638605..446c3d638605 100644
--- a/drivers/crypto/qat/qat_c62xvf/Makefile
+++ b/drivers/crypto/intel/qat/qat_c62xvf/Makefile
diff --git a/drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.c b/drivers/crypto/intel/qat/qat_c62xvf/adf_c62xvf_hw_data.c
index 751d7aa57fc7..751d7aa57fc7 100644
--- a/drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_c62xvf/adf_c62xvf_hw_data.c
diff --git a/drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.h b/drivers/crypto/intel/qat/qat_c62xvf/adf_c62xvf_hw_data.h
index a1a62c003ebf..a1a62c003ebf 100644
--- a/drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_c62xvf/adf_c62xvf_hw_data.h
diff --git a/drivers/crypto/qat/qat_c62xvf/adf_drv.c b/drivers/crypto/intel/qat/qat_c62xvf/adf_drv.c
index 0e642c94b929..37566309df94 100644
--- a/drivers/crypto/qat/qat_c62xvf/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_c62xvf/adf_drv.c
@@ -173,20 +173,14 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Completion for VF2PF request/response message exchange */
 	init_completion(&accel_dev->vf.msg_received);
 
-	ret = adf_dev_init(accel_dev);
-	if (ret)
-		goto out_err_dev_shutdown;
-
-	ret = adf_dev_start(accel_dev);
+	ret = adf_dev_up(accel_dev, false);
 	if (ret)
 		goto out_err_dev_stop;
 
 	return ret;
 
 out_err_dev_stop:
-	adf_dev_stop(accel_dev);
-out_err_dev_shutdown:
-	adf_dev_shutdown(accel_dev);
+	adf_dev_down(accel_dev, false);
 out_err_free_reg:
 	pci_release_regions(accel_pci_dev->pci_dev);
 out_err_disable:
@@ -206,8 +200,7 @@ static void adf_remove(struct pci_dev *pdev)
 		return;
 	}
 	adf_flush_vf_wq(accel_dev);
-	adf_dev_stop(accel_dev);
-	adf_dev_shutdown(accel_dev);
+	adf_dev_down(accel_dev, false);
 	adf_cleanup_accel(accel_dev);
 	adf_cleanup_pci_dev(accel_dev);
 	kfree(accel_dev);
diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/intel/qat/qat_common/Makefile
index 1fb8d50f509f..1fb8d50f509f 100644
--- a/drivers/crypto/qat/qat_common/Makefile
+++ b/drivers/crypto/intel/qat/qat_common/Makefile
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h
index 284f5aad3ee0..bd19e6460899 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h
@@ -21,6 +21,8 @@
 #define ADF_4XXXIOV_PCI_DEVICE_ID 0x4941
 #define ADF_401XX_PCI_DEVICE_ID 0x4942
 #define ADF_401XXIOV_PCI_DEVICE_ID 0x4943
+#define ADF_402XX_PCI_DEVICE_ID 0x4944
+#define ADF_402XXIOV_PCI_DEVICE_ID 0x4945
 #define ADF_DEVICE_FUSECTL_OFFSET 0x40
 #define ADF_DEVICE_LEGFUSE_OFFSET 0x4C
 #define ADF_DEVICE_FUSECTL_MASK 0x80000000
@@ -188,7 +190,7 @@ struct adf_hw_device_data {
 	int (*send_admin_init)(struct adf_accel_dev *accel_dev);
 	int (*init_arb)(struct adf_accel_dev *accel_dev);
 	void (*exit_arb)(struct adf_accel_dev *accel_dev);
-	const u32 *(*get_arb_mapping)(void);
+	const u32 *(*get_arb_mapping)(struct adf_accel_dev *accel_dev);
 	int (*init_device)(struct adf_accel_dev *accel_dev);
 	int (*enable_pm)(struct adf_accel_dev *accel_dev);
 	bool (*handle_pm_interrupt)(struct adf_accel_dev *accel_dev);
@@ -310,6 +312,7 @@ struct adf_accel_dev {
 			u8 pf_compat_ver;
 		} vf;
 	};
+	struct mutex state_lock; /* protect state of the device */
 	bool is_vf;
 	u32 accel_id;
 };
diff --git a/drivers/crypto/qat/qat_common/adf_accel_engine.c b/drivers/crypto/intel/qat/qat_common/adf_accel_engine.c
index 4ce2b666929e..4ce2b666929e 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_engine.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_accel_engine.c
diff --git a/drivers/crypto/qat/qat_common/adf_admin.c b/drivers/crypto/intel/qat/qat_common/adf_admin.c
index 3b6184c35081..3b6184c35081 100644
--- a/drivers/crypto/qat/qat_common/adf_admin.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_admin.c
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/intel/qat/qat_common/adf_aer.c
index fe9bb2f3536a..04af32a2811c 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_aer.c
@@ -2,7 +2,6 @@
 /* Copyright(c) 2014 - 2020 Intel Corporation */
 #include <linux/kernel.h>
 #include <linux/pci.h>
-#include <linux/aer.h>
 #include <linux/completion.h>
 #include <linux/workqueue.h>
 #include <linux/delay.h>
@@ -90,9 +89,7 @@ static void adf_device_reset_worker(struct work_struct *work)
 	struct adf_accel_dev *accel_dev = reset_data->accel_dev;
 
 	adf_dev_restarting_notify(accel_dev);
-	adf_dev_stop(accel_dev);
-	adf_dev_shutdown(accel_dev);
-	if (adf_dev_init(accel_dev) || adf_dev_start(accel_dev)) {
+	if (adf_dev_restart(accel_dev)) {
 		/* The device hanged and we can't restart it so stop here */
 		dev_err(&GET_DEV(accel_dev), "Restart device failed\n");
 		kfree(reset_data);
@@ -173,40 +170,6 @@ const struct pci_error_handlers adf_err_handler = {
 };
 EXPORT_SYMBOL_GPL(adf_err_handler);
 
-/**
- * adf_enable_aer() - Enable Advance Error Reporting for acceleration device
- * @accel_dev:  Pointer to acceleration device.
- *
- * Function enables PCI Advance Error Reporting for the
- * QAT acceleration device accel_dev.
- * To be used by QAT device specific drivers.
- */
-void adf_enable_aer(struct adf_accel_dev *accel_dev)
-{
-	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
-
-	pci_enable_pcie_error_reporting(pdev);
-}
-EXPORT_SYMBOL_GPL(adf_enable_aer);
-
-/**
- * adf_disable_aer() - Disable Advance Error Reporting for acceleration device
- * @accel_dev:  Pointer to acceleration device.
- *
- * Function disables PCI Advance Error Reporting for the
- * QAT acceleration device accel_dev.
- * To be used by QAT device specific drivers.
- *
- * Return: void
- */
-void adf_disable_aer(struct adf_accel_dev *accel_dev)
-{
-	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
-
-	pci_disable_pcie_error_reporting(pdev);
-}
-EXPORT_SYMBOL_GPL(adf_disable_aer);
-
 int adf_init_aer(void)
 {
 	device_reset_wq = alloc_workqueue("qat_device_reset_wq",
diff --git a/drivers/crypto/qat/qat_common/adf_cfg.c b/drivers/crypto/intel/qat/qat_common/adf_cfg.c
index 1931e5b37f2b..1931e5b37f2b 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_cfg.c
diff --git a/drivers/crypto/qat/qat_common/adf_cfg.h b/drivers/crypto/intel/qat/qat_common/adf_cfg.h
index 376cde61a60e..376cde61a60e 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_cfg.h
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_common.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h
index 6e5de1dab97b..6e5de1dab97b 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg_common.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_strings.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h
index 5d8c3bdb258c..5d8c3bdb258c 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg_strings.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_user.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_user.h
index 421f4fb8b4dd..421f4fb8b4dd 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg_user.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_user.h
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/intel/qat/qat_common/adf_common_drv.h
index 7189265573c0..db79759bee61 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_common_drv.h
@@ -52,11 +52,9 @@ struct service_hndl {
 int adf_service_register(struct service_hndl *service);
 int adf_service_unregister(struct service_hndl *service);
 
-int adf_dev_init(struct adf_accel_dev *accel_dev);
-int adf_dev_start(struct adf_accel_dev *accel_dev);
-void adf_dev_stop(struct adf_accel_dev *accel_dev);
-void adf_dev_shutdown(struct adf_accel_dev *accel_dev);
-int adf_dev_shutdown_cache_cfg(struct adf_accel_dev *accel_dev);
+int adf_dev_up(struct adf_accel_dev *accel_dev, bool init_config);
+int adf_dev_down(struct adf_accel_dev *accel_dev, bool cache_config);
+int adf_dev_restart(struct adf_accel_dev *accel_dev);
 
 void adf_devmgr_update_class_index(struct adf_hw_device_data *hw_data);
 void adf_clean_vf_map(bool);
@@ -88,8 +86,6 @@ int adf_ae_start(struct adf_accel_dev *accel_dev);
 int adf_ae_stop(struct adf_accel_dev *accel_dev);
 
 extern const struct pci_error_handlers adf_err_handler;
-void adf_enable_aer(struct adf_accel_dev *accel_dev);
-void adf_disable_aer(struct adf_accel_dev *accel_dev);
 void adf_reset_sbr(struct adf_accel_dev *accel_dev);
 void adf_reset_flr(struct adf_accel_dev *accel_dev);
 void adf_dev_restore(struct adf_accel_dev *accel_dev);
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/intel/qat/qat_common/adf_ctl_drv.c
index 9190532b27eb..88c41d6fbb7c 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_ctl_drv.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only)
 /* Copyright(c) 2014 - 2020 Intel Corporation */
+
+#include <crypto/algapi.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
@@ -8,7 +10,6 @@
 #include <linux/pci.h>
 #include <linux/cdev.h>
 #include <linux/uaccess.h>
-#include <linux/crypto.h>
 
 #include "adf_accel_devices.h"
 #include "adf_common_drv.h"
@@ -243,8 +244,7 @@ static void adf_ctl_stop_devices(u32 id)
 			if (!accel_dev->is_vf)
 				continue;
 
-			adf_dev_stop(accel_dev);
-			adf_dev_shutdown(accel_dev);
+			adf_dev_down(accel_dev, false);
 		}
 	}
 
@@ -253,8 +253,7 @@ static void adf_ctl_stop_devices(u32 id)
 			if (!adf_dev_started(accel_dev))
 				continue;
 
-			adf_dev_stop(accel_dev);
-			adf_dev_shutdown(accel_dev);
+			adf_dev_down(accel_dev, false);
 		}
 	}
 }
@@ -308,23 +307,16 @@ static int adf_ctl_ioctl_dev_start(struct file *fp, unsigned int cmd,
 	if (!accel_dev)
 		goto out;
 
-	if (!adf_dev_started(accel_dev)) {
-		dev_info(&GET_DEV(accel_dev),
-			 "Starting acceleration device qat_dev%d.\n",
-			 ctl_data->device_id);
-		ret = adf_dev_init(accel_dev);
-		if (!ret)
-			ret = adf_dev_start(accel_dev);
-	} else {
-		dev_info(&GET_DEV(accel_dev),
-			 "Acceleration device qat_dev%d already started.\n",
-			 ctl_data->device_id);
-	}
+	dev_info(&GET_DEV(accel_dev),
+		 "Starting acceleration device qat_dev%d.\n",
+		 ctl_data->device_id);
+
+	ret = adf_dev_up(accel_dev, false);
+
 	if (ret) {
 		dev_err(&GET_DEV(accel_dev), "Failed to start qat_dev%d\n",
 			ctl_data->device_id);
-		adf_dev_stop(accel_dev);
-		adf_dev_shutdown(accel_dev);
+		adf_dev_down(accel_dev, false);
 	}
 out:
 	kfree(ctl_data);
diff --git a/drivers/crypto/qat/qat_common/adf_dev_mgr.c b/drivers/crypto/intel/qat/qat_common/adf_dev_mgr.c
index 4c752eed10fe..86ee36feefad 100644
--- a/drivers/crypto/qat/qat_common/adf_dev_mgr.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_dev_mgr.c
@@ -223,6 +223,7 @@ int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev,
 		map->attached = true;
 		list_add_tail(&map->list, &vfs_table);
 	}
+	mutex_init(&accel_dev->state_lock);
 unlock:
 	mutex_unlock(&table_lock);
 	return ret;
@@ -269,6 +270,7 @@ void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev,
 		}
 	}
 unlock:
+	mutex_destroy(&accel_dev->state_lock);
 	list_del(&accel_dev->list);
 	mutex_unlock(&table_lock);
 }
diff --git a/drivers/crypto/qat/qat_common/adf_gen2_config.c b/drivers/crypto/intel/qat/qat_common/adf_gen2_config.c
index eeb30da7587a..eeb30da7587a 100644
--- a/drivers/crypto/qat/qat_common/adf_gen2_config.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_config.c
diff --git a/drivers/crypto/qat/qat_common/adf_gen2_config.h b/drivers/crypto/intel/qat/qat_common/adf_gen2_config.h
index 4bf9da2de68a..4bf9da2de68a 100644
--- a/drivers/crypto/qat/qat_common/adf_gen2_config.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_config.h
diff --git a/drivers/crypto/qat/qat_common/adf_gen2_dc.c b/drivers/crypto/intel/qat/qat_common/adf_gen2_dc.c
index 47261b1c1da6..47261b1c1da6 100644
--- a/drivers/crypto/qat/qat_common/adf_gen2_dc.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_dc.c
diff --git a/drivers/crypto/qat/qat_common/adf_gen2_dc.h b/drivers/crypto/intel/qat/qat_common/adf_gen2_dc.h
index 6eae023354d7..6eae023354d7 100644
--- a/drivers/crypto/qat/qat_common/adf_gen2_dc.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_dc.h
diff --git a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c b/drivers/crypto/intel/qat/qat_common/adf_gen2_hw_data.c
index d1884547b5a1..d1884547b5a1 100644
--- a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_hw_data.c
diff --git a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h b/drivers/crypto/intel/qat/qat_common/adf_gen2_hw_data.h
index e4bc07529be4..e4bc07529be4 100644
--- a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_hw_data.h
diff --git a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c b/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c
index 70ef11963938..70ef11963938 100644
--- a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c
diff --git a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.h b/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.h
index a716545a764c..a716545a764c 100644
--- a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.h
diff --git a/drivers/crypto/qat/qat_common/adf_gen4_dc.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_dc.c
index 5859238e37de..5859238e37de 100644
--- a/drivers/crypto/qat/qat_common/adf_gen4_dc.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_dc.c
diff --git a/drivers/crypto/qat/qat_common/adf_gen4_dc.h b/drivers/crypto/intel/qat/qat_common/adf_gen4_dc.h
index 0b1a6774412e..0b1a6774412e 100644
--- a/drivers/crypto/qat/qat_common/adf_gen4_dc.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_dc.h
diff --git a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c
index 3148a62938fd..3148a62938fd 100644
--- a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c
diff --git a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h
index 4fb4b3df5a18..4fb4b3df5a18 100644
--- a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h
diff --git a/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_pfvf.c
index 8e8efe93f3ee..8e8efe93f3ee 100644
--- a/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_pfvf.c
diff --git a/drivers/crypto/qat/qat_common/adf_gen4_pfvf.h b/drivers/crypto/intel/qat/qat_common/adf_gen4_pfvf.h
index 17d1b774d4a8..17d1b774d4a8 100644
--- a/drivers/crypto/qat/qat_common/adf_gen4_pfvf.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_pfvf.h
diff --git a/drivers/crypto/qat/qat_common/adf_gen4_pm.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_pm.c
index 7037c0892a8a..7037c0892a8a 100644
--- a/drivers/crypto/qat/qat_common/adf_gen4_pm.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_pm.c
diff --git a/drivers/crypto/qat/qat_common/adf_gen4_pm.h b/drivers/crypto/intel/qat/qat_common/adf_gen4_pm.h
index f8f8a9ee29e5..f8f8a9ee29e5 100644
--- a/drivers/crypto/qat/qat_common/adf_gen4_pm.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_pm.h
diff --git a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c b/drivers/crypto/intel/qat/qat_common/adf_hw_arbiter.c
index 64e4596a24f4..da6956699246 100644
--- a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_hw_arbiter.c
@@ -36,7 +36,7 @@ int adf_init_arb(struct adf_accel_dev *accel_dev)
 		WRITE_CSR_ARB_SARCONFIG(csr, arb_off, arb, arb_cfg);
 
 	/* Map worker threads to service arbiters */
-	thd_2_arb_cfg = hw_data->get_arb_mapping();
+	thd_2_arb_cfg = hw_data->get_arb_mapping(accel_dev);
 
 	for_each_set_bit(i, &ae_mask, hw_data->num_engines)
 		WRITE_CSR_ARB_WT2SAM(csr, arb_off, wt_off, i, thd_2_arb_cfg[i]);
diff --git a/drivers/crypto/qat/qat_common/adf_init.c b/drivers/crypto/intel/qat/qat_common/adf_init.c
index cef7bb8ec007..0985f64ab11a 100644
--- a/drivers/crypto/qat/qat_common/adf_init.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_init.c
@@ -56,7 +56,7 @@ int adf_service_unregister(struct service_hndl *service)
  *
  * Return: 0 on success, error code otherwise.
  */
-int adf_dev_init(struct adf_accel_dev *accel_dev)
+static int adf_dev_init(struct adf_accel_dev *accel_dev)
 {
 	struct service_hndl *service;
 	struct list_head *list_itr;
@@ -146,7 +146,6 @@ int adf_dev_init(struct adf_accel_dev *accel_dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(adf_dev_init);
 
 /**
  * adf_dev_start() - Start acceleration service for the given accel device
@@ -158,7 +157,7 @@ EXPORT_SYMBOL_GPL(adf_dev_init);
  *
  * Return: 0 on success, error code otherwise.
  */
-int adf_dev_start(struct adf_accel_dev *accel_dev)
+static int adf_dev_start(struct adf_accel_dev *accel_dev)
 {
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	struct service_hndl *service;
@@ -219,7 +218,6 @@ int adf_dev_start(struct adf_accel_dev *accel_dev)
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(adf_dev_start);
 
 /**
  * adf_dev_stop() - Stop acceleration service for the given accel device
@@ -231,7 +229,7 @@ EXPORT_SYMBOL_GPL(adf_dev_start);
  *
  * Return: void
  */
-void adf_dev_stop(struct adf_accel_dev *accel_dev)
+static void adf_dev_stop(struct adf_accel_dev *accel_dev)
 {
 	struct service_hndl *service;
 	struct list_head *list_itr;
@@ -276,7 +274,6 @@ void adf_dev_stop(struct adf_accel_dev *accel_dev)
 			clear_bit(ADF_STATUS_AE_STARTED, &accel_dev->status);
 	}
 }
-EXPORT_SYMBOL_GPL(adf_dev_stop);
 
 /**
  * adf_dev_shutdown() - shutdown acceleration services and data strucutures
@@ -285,7 +282,7 @@ EXPORT_SYMBOL_GPL(adf_dev_stop);
  * Cleanup the ring data structures and the admin comms and arbitration
  * services.
  */
-void adf_dev_shutdown(struct adf_accel_dev *accel_dev)
+static void adf_dev_shutdown(struct adf_accel_dev *accel_dev)
 {
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	struct service_hndl *service;
@@ -343,7 +340,6 @@ void adf_dev_shutdown(struct adf_accel_dev *accel_dev)
 	adf_cleanup_etr_data(accel_dev);
 	adf_dev_restore(accel_dev);
 }
-EXPORT_SYMBOL_GPL(adf_dev_shutdown);
 
 int adf_dev_restarting_notify(struct adf_accel_dev *accel_dev)
 {
@@ -375,7 +371,7 @@ int adf_dev_restarted_notify(struct adf_accel_dev *accel_dev)
 	return 0;
 }
 
-int adf_dev_shutdown_cache_cfg(struct adf_accel_dev *accel_dev)
+static int adf_dev_shutdown_cache_cfg(struct adf_accel_dev *accel_dev)
 {
 	char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0};
 	int ret;
@@ -400,3 +396,85 @@ int adf_dev_shutdown_cache_cfg(struct adf_accel_dev *accel_dev)
 
 	return 0;
 }
+
+int adf_dev_down(struct adf_accel_dev *accel_dev, bool reconfig)
+{
+	int ret = 0;
+
+	if (!accel_dev)
+		return -EINVAL;
+
+	mutex_lock(&accel_dev->state_lock);
+
+	if (!adf_dev_started(accel_dev)) {
+		dev_info(&GET_DEV(accel_dev), "Device qat_dev%d already down\n",
+			 accel_dev->accel_id);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (reconfig) {
+		ret = adf_dev_shutdown_cache_cfg(accel_dev);
+		goto out;
+	}
+
+	adf_dev_stop(accel_dev);
+	adf_dev_shutdown(accel_dev);
+
+out:
+	mutex_unlock(&accel_dev->state_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adf_dev_down);
+
+int adf_dev_up(struct adf_accel_dev *accel_dev, bool config)
+{
+	int ret = 0;
+
+	if (!accel_dev)
+		return -EINVAL;
+
+	mutex_lock(&accel_dev->state_lock);
+
+	if (adf_dev_started(accel_dev)) {
+		dev_info(&GET_DEV(accel_dev), "Device qat_dev%d already up\n",
+			 accel_dev->accel_id);
+		ret = -EALREADY;
+		goto out;
+	}
+
+	if (config && GET_HW_DATA(accel_dev)->dev_config) {
+		ret = GET_HW_DATA(accel_dev)->dev_config(accel_dev);
+		if (unlikely(ret))
+			goto out;
+	}
+
+	ret = adf_dev_init(accel_dev);
+	if (unlikely(ret))
+		goto out;
+
+	ret = adf_dev_start(accel_dev);
+
+out:
+	mutex_unlock(&accel_dev->state_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adf_dev_up);
+
+int adf_dev_restart(struct adf_accel_dev *accel_dev)
+{
+	int ret = 0;
+
+	if (!accel_dev)
+		return -EFAULT;
+
+	adf_dev_down(accel_dev, false);
+
+	ret = adf_dev_up(accel_dev, false);
+	/* if device is already up return success*/
+	if (ret == -EALREADY)
+		return 0;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adf_dev_restart);
diff --git a/drivers/crypto/qat/qat_common/adf_isr.c b/drivers/crypto/intel/qat/qat_common/adf_isr.c
index ad9e135b8560..ad9e135b8560 100644
--- a/drivers/crypto/qat/qat_common/adf_isr.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_isr.c
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_msg.h b/drivers/crypto/intel/qat/qat_common/adf_pfvf_msg.h
index 204a42438992..204a42438992 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_msg.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_msg.h
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_pf_msg.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c
index 14c069f0d71a..14c069f0d71a 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_pf_msg.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_pf_msg.h b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.h
index e8982d1ac896..e8982d1ac896 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_pf_msg.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.h
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_pf_proto.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c
index 388e58bcbcaf..388e58bcbcaf 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_pf_proto.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_pf_proto.h b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.h
index 165d266d023d..165d266d023d 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_pf_proto.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.h
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_utils.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_utils.c
index c5f6d77d4bb8..c5f6d77d4bb8 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_utils.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_utils.c
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_utils.h b/drivers/crypto/intel/qat/qat_common/adf_pfvf_utils.h
index 2be048e2287b..2be048e2287b 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_utils.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_utils.h
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_vf_msg.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.c
index 1141258db4b6..1141258db4b6 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_vf_msg.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.c
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_vf_msg.h b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.h
index 71bc0e3f1d93..71bc0e3f1d93 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_vf_msg.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.h
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_vf_proto.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_proto.c
index 1015155b6374..1015155b6374 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_vf_proto.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_proto.c
diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_vf_proto.h b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_proto.h
index f6ee9b38c0e1..f6ee9b38c0e1 100644
--- a/drivers/crypto/qat/qat_common/adf_pfvf_vf_proto.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_proto.h
diff --git a/drivers/crypto/qat/qat_common/adf_sriov.c b/drivers/crypto/intel/qat/qat_common/adf_sriov.c
index d85a90cc387b..f44025bb6f99 100644
--- a/drivers/crypto/qat/qat_common/adf_sriov.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_sriov.c
@@ -159,7 +159,7 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
 			return -EBUSY;
 		}
 
-		ret = adf_dev_shutdown_cache_cfg(accel_dev);
+		ret = adf_dev_down(accel_dev, true);
 		if (ret)
 			return ret;
 	}
@@ -184,13 +184,7 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
 	if (!accel_dev->pf.vf_info)
 		return -ENOMEM;
 
-	if (adf_dev_init(accel_dev)) {
-		dev_err(&GET_DEV(accel_dev), "Failed to init qat_dev%d\n",
-			accel_dev->accel_id);
-		return -EFAULT;
-	}
-
-	if (adf_dev_start(accel_dev)) {
+	if (adf_dev_up(accel_dev, false)) {
 		dev_err(&GET_DEV(accel_dev), "Failed to start qat_dev%d\n",
 			accel_dev->accel_id);
 		return -EFAULT;
diff --git a/drivers/crypto/qat/qat_common/adf_sysfs.c b/drivers/crypto/intel/qat/qat_common/adf_sysfs.c
index e8b078e719c2..3eb6611ab1b1 100644
--- a/drivers/crypto/qat/qat_common/adf_sysfs.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_sysfs.c
@@ -50,38 +50,21 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr,
 
 	switch (ret) {
 	case DEV_DOWN:
-		if (!adf_dev_started(accel_dev)) {
-			dev_info(dev, "Device qat_dev%d already down\n",
-				 accel_id);
-			return -EINVAL;
-		}
-
 		dev_info(dev, "Stopping device qat_dev%d\n", accel_id);
 
-		ret = adf_dev_shutdown_cache_cfg(accel_dev);
+		ret = adf_dev_down(accel_dev, true);
 		if (ret < 0)
 			return -EINVAL;
 
 		break;
 	case DEV_UP:
-		if (adf_dev_started(accel_dev)) {
-			dev_info(dev, "Device qat_dev%d already up\n",
-				 accel_id);
-			return -EINVAL;
-		}
-
 		dev_info(dev, "Starting device qat_dev%d\n", accel_id);
 
-		ret = GET_HW_DATA(accel_dev)->dev_config(accel_dev);
-		if (!ret)
-			ret = adf_dev_init(accel_dev);
-		if (!ret)
-			ret = adf_dev_start(accel_dev);
-
+		ret = adf_dev_up(accel_dev, true);
 		if (ret < 0) {
 			dev_err(dev, "Failed to start device qat_dev%d\n",
 				accel_id);
-			adf_dev_shutdown_cache_cfg(accel_dev);
+			adf_dev_down(accel_dev, true);
 			return ret;
 		}
 		break;
diff --git a/drivers/crypto/qat/qat_common/adf_transport.c b/drivers/crypto/intel/qat/qat_common/adf_transport.c
index 630d0483c4e0..630d0483c4e0 100644
--- a/drivers/crypto/qat/qat_common/adf_transport.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_transport.c
diff --git a/drivers/crypto/qat/qat_common/adf_transport.h b/drivers/crypto/intel/qat/qat_common/adf_transport.h
index e6ef6f9b7691..e6ef6f9b7691 100644
--- a/drivers/crypto/qat/qat_common/adf_transport.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_transport.h
diff --git a/drivers/crypto/qat/qat_common/adf_transport_access_macros.h b/drivers/crypto/intel/qat/qat_common/adf_transport_access_macros.h
index d3667dbd9826..d3667dbd9826 100644
--- a/drivers/crypto/qat/qat_common/adf_transport_access_macros.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_transport_access_macros.h
diff --git a/drivers/crypto/qat/qat_common/adf_transport_debug.c b/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c
index 08bca1c506c0..08bca1c506c0 100644
--- a/drivers/crypto/qat/qat_common/adf_transport_debug.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c
diff --git a/drivers/crypto/qat/qat_common/adf_transport_internal.h b/drivers/crypto/intel/qat/qat_common/adf_transport_internal.h
index 8b2c92ba7ca1..8b2c92ba7ca1 100644
--- a/drivers/crypto/qat/qat_common/adf_transport_internal.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_transport_internal.h
diff --git a/drivers/crypto/qat/qat_common/adf_vf_isr.c b/drivers/crypto/intel/qat/qat_common/adf_vf_isr.c
index 8c95fcd8e64b..b05c3957a160 100644
--- a/drivers/crypto/qat/qat_common/adf_vf_isr.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_vf_isr.c
@@ -71,8 +71,7 @@ static void adf_dev_stop_async(struct work_struct *work)
 	struct adf_accel_dev *accel_dev = stop_data->accel_dev;
 
 	adf_dev_restarting_notify(accel_dev);
-	adf_dev_stop(accel_dev);
-	adf_dev_shutdown(accel_dev);
+	adf_dev_down(accel_dev, false);
 
 	/* Re-enable PF2VF interrupts */
 	adf_enable_pf2vf_interrupts(accel_dev);
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw.h b/drivers/crypto/intel/qat/qat_common/icp_qat_fw.h
index c141160421e1..c141160421e1 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_fw.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_fw.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_comp.h b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_comp.h
index a03d43fef2b3..a03d43fef2b3 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_fw_comp.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_comp.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_init_admin.h b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h
index 56cb827f93ea..56cb827f93ea 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_fw_init_admin.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_la.h b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_la.h
index 28fa17f14be4..28fa17f14be4 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_fw_la.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_la.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_loader_handle.h b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_loader_handle.h
index 7eb5daef4f88..7eb5daef4f88 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_fw_loader_handle.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_loader_handle.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_pke.h b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_pke.h
index 9dddae0009fc..9dddae0009fc 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_fw_pke.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_pke.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_hal.h b/drivers/crypto/intel/qat/qat_common/icp_qat_hal.h
index 20b2ee1fc65a..20b2ee1fc65a 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_hal.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_hal.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_hw.h b/drivers/crypto/intel/qat/qat_common/icp_qat_hw.h
index 4042739bb6fa..4042739bb6fa 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_hw.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_hw.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_hw_20_comp.h b/drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h
index 7ea8962272f2..7ea8962272f2 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_hw_20_comp.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_hw_20_comp_defs.h b/drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp_defs.h
index 208d4554283b..208d4554283b 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_hw_20_comp_defs.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp_defs.h
diff --git a/drivers/crypto/qat/qat_common/icp_qat_uclo.h b/drivers/crypto/intel/qat/qat_common/icp_qat_uclo.h
index 69482abdb8b9..69482abdb8b9 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_uclo.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_uclo.h
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/intel/qat/qat_common/qat_algs.c
index 538dcbfbcd26..538dcbfbcd26 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_algs.c
diff --git a/drivers/crypto/qat/qat_common/qat_algs_send.c b/drivers/crypto/intel/qat/qat_common/qat_algs_send.c
index bb80455b3e81..bb80455b3e81 100644
--- a/drivers/crypto/qat/qat_common/qat_algs_send.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_algs_send.c
diff --git a/drivers/crypto/qat/qat_common/qat_algs_send.h b/drivers/crypto/intel/qat/qat_common/qat_algs_send.h
index 0baca16e1eff..0baca16e1eff 100644
--- a/drivers/crypto/qat/qat_common/qat_algs_send.h
+++ b/drivers/crypto/intel/qat/qat_common/qat_algs_send.h
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/intel/qat/qat_common/qat_asym_algs.c
index 935a7e012946..935a7e012946 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_asym_algs.c
diff --git a/drivers/crypto/qat/qat_common/qat_bl.c b/drivers/crypto/intel/qat/qat_common/qat_bl.c
index 76baed0a76c0..76baed0a76c0 100644
--- a/drivers/crypto/qat/qat_common/qat_bl.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_bl.c
diff --git a/drivers/crypto/qat/qat_common/qat_bl.h b/drivers/crypto/intel/qat/qat_common/qat_bl.h
index d87e4f35ac39..d87e4f35ac39 100644
--- a/drivers/crypto/qat/qat_common/qat_bl.h
+++ b/drivers/crypto/intel/qat/qat_common/qat_bl.h
diff --git a/drivers/crypto/qat/qat_common/qat_comp_algs.c b/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c
index b533984906ec..b533984906ec 100644
--- a/drivers/crypto/qat/qat_common/qat_comp_algs.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c
diff --git a/drivers/crypto/qat/qat_common/qat_comp_req.h b/drivers/crypto/intel/qat/qat_common/qat_comp_req.h
index 404e32c5e778..404e32c5e778 100644
--- a/drivers/crypto/qat/qat_common/qat_comp_req.h
+++ b/drivers/crypto/intel/qat/qat_common/qat_comp_req.h
diff --git a/drivers/crypto/qat/qat_common/qat_compression.c b/drivers/crypto/intel/qat/qat_common/qat_compression.c
index 3f1f35283266..3f1f35283266 100644
--- a/drivers/crypto/qat/qat_common/qat_compression.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_compression.c
diff --git a/drivers/crypto/qat/qat_common/qat_compression.h b/drivers/crypto/intel/qat/qat_common/qat_compression.h
index aebac2302dcf..aebac2302dcf 100644
--- a/drivers/crypto/qat/qat_common/qat_compression.h
+++ b/drivers/crypto/intel/qat/qat_common/qat_compression.h
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.c b/drivers/crypto/intel/qat/qat_common/qat_crypto.c
index 40c8e74d1cf9..40c8e74d1cf9 100644
--- a/drivers/crypto/qat/qat_common/qat_crypto.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_crypto.c
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.h b/drivers/crypto/intel/qat/qat_common/qat_crypto.h
index 6a0e961bb9dc..6a0e961bb9dc 100644
--- a/drivers/crypto/qat/qat_common/qat_crypto.h
+++ b/drivers/crypto/intel/qat/qat_common/qat_crypto.h
diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/intel/qat/qat_common/qat_hal.c
index 7bba35280dac..cbb946a80076 100644
--- a/drivers/crypto/qat/qat_common/qat_hal.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_hal.c
@@ -696,6 +696,7 @@ static int qat_hal_chip_init(struct icp_qat_fw_loader_handle *handle,
 	switch (handle->pci_dev->device) {
 	case ADF_4XXX_PCI_DEVICE_ID:
 	case ADF_401XX_PCI_DEVICE_ID:
+	case ADF_402XX_PCI_DEVICE_ID:
 		handle->chip_info->mmp_sram_size = 0;
 		handle->chip_info->nn = false;
 		handle->chip_info->lm2lm3 = true;
diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/intel/qat/qat_common/qat_uclo.c
index b7f7869ef8b2..3ba8ca20b3d7 100644
--- a/drivers/crypto/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_uclo.c
@@ -732,6 +732,7 @@ qat_uclo_get_dev_type(struct icp_qat_fw_loader_handle *handle)
 		return ICP_QAT_AC_C3XXX_DEV_TYPE;
 	case ADF_4XXX_PCI_DEVICE_ID:
 	case ADF_401XX_PCI_DEVICE_ID:
+	case ADF_402XX_PCI_DEVICE_ID:
 		return ICP_QAT_AC_4XXX_A_DEV_TYPE;
 	default:
 		pr_err("QAT: unsupported device 0x%x\n",
diff --git a/drivers/crypto/qat/qat_dh895xcc/Makefile b/drivers/crypto/intel/qat/qat_dh895xcc/Makefile
index 38d6f8e1624a..38d6f8e1624a 100644
--- a/drivers/crypto/qat/qat_dh895xcc/Makefile
+++ b/drivers/crypto/intel/qat/qat_dh895xcc/Makefile
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
index bc80bb475118..1ebe0b351fae 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
@@ -106,7 +106,7 @@ static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
 	return DEV_SKU_UNKNOWN;
 }
 
-static const u32 *adf_get_arbiter_mapping(void)
+static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev)
 {
 	return thrd_to_arb_map;
 }
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h b/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
index 7b674bbe4192..7b674bbe4192 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/intel/qat/qat_dh895xcc/adf_drv.c
index ebeb17b67fcd..e18860ab5c8e 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_dh895xcc/adf_drv.c
@@ -193,34 +193,20 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	pci_set_master(pdev);
 
-	adf_enable_aer(accel_dev);
-
 	if (pci_save_state(pdev)) {
 		dev_err(&pdev->dev, "Failed to save pci state\n");
 		ret = -ENOMEM;
-		goto out_err_disable_aer;
+		goto out_err_free_reg;
 	}
 
-	ret = hw_data->dev_config(accel_dev);
-	if (ret)
-		goto out_err_disable_aer;
-
-	ret = adf_dev_init(accel_dev);
-	if (ret)
-		goto out_err_dev_shutdown;
-
-	ret = adf_dev_start(accel_dev);
+	ret = adf_dev_up(accel_dev, true);
 	if (ret)
 		goto out_err_dev_stop;
 
 	return ret;
 
 out_err_dev_stop:
-	adf_dev_stop(accel_dev);
-out_err_dev_shutdown:
-	adf_dev_shutdown(accel_dev);
-out_err_disable_aer:
-	adf_disable_aer(accel_dev);
+	adf_dev_down(accel_dev, false);
 out_err_free_reg:
 	pci_release_regions(accel_pci_dev->pci_dev);
 out_err_disable:
@@ -239,9 +225,7 @@ static void adf_remove(struct pci_dev *pdev)
 		pr_err("QAT: Driver removal failed\n");
 		return;
 	}
-	adf_dev_stop(accel_dev);
-	adf_dev_shutdown(accel_dev);
-	adf_disable_aer(accel_dev);
+	adf_dev_down(accel_dev, false);
 	adf_cleanup_accel(accel_dev);
 	adf_cleanup_pci_dev(accel_dev);
 	kfree(accel_dev);
diff --git a/drivers/crypto/qat/qat_dh895xccvf/Makefile b/drivers/crypto/intel/qat/qat_dh895xccvf/Makefile
index 0153c85ce743..0153c85ce743 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/Makefile
+++ b/drivers/crypto/intel/qat/qat_dh895xccvf/Makefile
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c b/drivers/crypto/intel/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c
index 70e56cc16ece..70e56cc16ece 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h b/drivers/crypto/intel/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h
index 6973fa967bc8..6973fa967bc8 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c b/drivers/crypto/intel/qat/qat_dh895xccvf/adf_drv.c
index c1485e702b3e..96854a1cd87e 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_dh895xccvf/adf_drv.c
@@ -173,20 +173,14 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Completion for VF2PF request/response message exchange */
 	init_completion(&accel_dev->vf.msg_received);
 
-	ret = adf_dev_init(accel_dev);
-	if (ret)
-		goto out_err_dev_shutdown;
-
-	ret = adf_dev_start(accel_dev);
+	ret = adf_dev_up(accel_dev, false);
 	if (ret)
 		goto out_err_dev_stop;
 
 	return ret;
 
 out_err_dev_stop:
-	adf_dev_stop(accel_dev);
-out_err_dev_shutdown:
-	adf_dev_shutdown(accel_dev);
+	adf_dev_down(accel_dev, false);
 out_err_free_reg:
 	pci_release_regions(accel_pci_dev->pci_dev);
 out_err_disable:
@@ -206,8 +200,7 @@ static void adf_remove(struct pci_dev *pdev)
 		return;
 	}
 	adf_flush_vf_wq(accel_dev);
-	adf_dev_stop(accel_dev);
-	adf_dev_shutdown(accel_dev);
+	adf_dev_down(accel_dev, false);
 	adf_cleanup_accel(accel_dev);
 	adf_cleanup_pci_dev(accel_dev);
 	kfree(accel_dev);
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index 1c11946a4f0b..f6b7bce0e656 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -1022,21 +1022,15 @@ static int mxs_dcp_probe(struct platform_device *pdev)
 	sdcp->coh = PTR_ALIGN(sdcp->coh, DCP_ALIGNMENT);
 
 	/* DCP clock is optional, only used on some SOCs */
-	sdcp->dcp_clk = devm_clk_get(dev, "dcp");
-	if (IS_ERR(sdcp->dcp_clk)) {
-		if (sdcp->dcp_clk != ERR_PTR(-ENOENT))
-			return PTR_ERR(sdcp->dcp_clk);
-		sdcp->dcp_clk = NULL;
-	}
-	ret = clk_prepare_enable(sdcp->dcp_clk);
-	if (ret)
-		return ret;
+	sdcp->dcp_clk = devm_clk_get_optional_enabled(dev, "dcp");
+	if (IS_ERR(sdcp->dcp_clk))
+		return PTR_ERR(sdcp->dcp_clk);
 
 	/* Restart the DCP block. */
 	ret = stmp_reset_block(sdcp->base);
 	if (ret) {
 		dev_err(dev, "Failed reset\n");
-		goto err_disable_unprepare_clk;
+		return ret;
 	}
 
 	/* Initialize control register. */
@@ -1076,7 +1070,7 @@ static int mxs_dcp_probe(struct platform_device *pdev)
 	if (IS_ERR(sdcp->thread[DCP_CHAN_HASH_SHA])) {
 		dev_err(dev, "Error starting SHA thread!\n");
 		ret = PTR_ERR(sdcp->thread[DCP_CHAN_HASH_SHA]);
-		goto err_disable_unprepare_clk;
+		return ret;
 	}
 
 	sdcp->thread[DCP_CHAN_CRYPTO] = kthread_run(dcp_chan_thread_aes,
@@ -1134,9 +1128,6 @@ err_destroy_aes_thread:
 err_destroy_sha_thread:
 	kthread_stop(sdcp->thread[DCP_CHAN_HASH_SHA]);
 
-err_disable_unprepare_clk:
-	clk_disable_unprepare(sdcp->dcp_clk);
-
 	return ret;
 }
 
@@ -1156,8 +1147,6 @@ static int mxs_dcp_remove(struct platform_device *pdev)
 	kthread_stop(sdcp->thread[DCP_CHAN_HASH_SHA]);
 	kthread_stop(sdcp->thread[DCP_CHAN_CRYPTO]);
 
-	clk_disable_unprepare(sdcp->dcp_clk);
-
 	platform_set_drvdata(pdev, NULL);
 
 	global_sdcp = NULL;
diff --git a/drivers/crypto/qce/core.c b/drivers/crypto/qce/core.c
index 74deca4f96e0..fce49c0dee3e 100644
--- a/drivers/crypto/qce/core.c
+++ b/drivers/crypto/qce/core.c
@@ -5,6 +5,7 @@
 
 #include <linux/clk.h>
 #include <linux/dma-mapping.h>
+#include <linux/interconnect.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -22,6 +23,8 @@
 #define QCE_MAJOR_VERSION5	0x05
 #define QCE_QUEUE_LENGTH	1
 
+#define QCE_DEFAULT_MEM_BANDWIDTH	393600
+
 static const struct qce_algo_ops *qce_ops[] = {
 #ifdef CONFIG_CRYPTO_DEV_QCE_SKCIPHER
 	&skcipher_ops,
@@ -206,22 +209,30 @@ static int qce_crypto_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
-	qce->core = devm_clk_get(qce->dev, "core");
+	qce->core = devm_clk_get_optional(qce->dev, "core");
 	if (IS_ERR(qce->core))
 		return PTR_ERR(qce->core);
 
-	qce->iface = devm_clk_get(qce->dev, "iface");
+	qce->iface = devm_clk_get_optional(qce->dev, "iface");
 	if (IS_ERR(qce->iface))
 		return PTR_ERR(qce->iface);
 
-	qce->bus = devm_clk_get(qce->dev, "bus");
+	qce->bus = devm_clk_get_optional(qce->dev, "bus");
 	if (IS_ERR(qce->bus))
 		return PTR_ERR(qce->bus);
 
-	ret = clk_prepare_enable(qce->core);
+	qce->mem_path = devm_of_icc_get(qce->dev, "memory");
+	if (IS_ERR(qce->mem_path))
+		return PTR_ERR(qce->mem_path);
+
+	ret = icc_set_bw(qce->mem_path, QCE_DEFAULT_MEM_BANDWIDTH, QCE_DEFAULT_MEM_BANDWIDTH);
 	if (ret)
 		return ret;
 
+	ret = clk_prepare_enable(qce->core);
+	if (ret)
+		goto err_mem_path_disable;
+
 	ret = clk_prepare_enable(qce->iface);
 	if (ret)
 		goto err_clks_core;
@@ -260,6 +271,9 @@ err_clks_iface:
 	clk_disable_unprepare(qce->iface);
 err_clks_core:
 	clk_disable_unprepare(qce->core);
+err_mem_path_disable:
+	icc_set_bw(qce->mem_path, 0, 0);
+
 	return ret;
 }
 
@@ -279,6 +293,7 @@ static int qce_crypto_remove(struct platform_device *pdev)
 static const struct of_device_id qce_crypto_of_match[] = {
 	{ .compatible = "qcom,crypto-v5.1", },
 	{ .compatible = "qcom,crypto-v5.4", },
+	{ .compatible = "qcom,qce", },
 	{}
 };
 MODULE_DEVICE_TABLE(of, qce_crypto_of_match);
diff --git a/drivers/crypto/qce/core.h b/drivers/crypto/qce/core.h
index 085774cdf641..228fcd69ec51 100644
--- a/drivers/crypto/qce/core.h
+++ b/drivers/crypto/qce/core.h
@@ -35,6 +35,7 @@ struct qce_device {
 	void __iomem *base;
 	struct device *dev;
 	struct clk *core, *iface, *bus;
+	struct icc_path *mem_path;
 	struct qce_dma_data dma;
 	int burst_size;
 	unsigned int pipe_pair_id;
diff --git a/drivers/crypto/sa2ul.c b/drivers/crypto/sa2ul.c
index f4bc06c24ad8..df5f9d675c57 100644
--- a/drivers/crypto/sa2ul.c
+++ b/drivers/crypto/sa2ul.c
@@ -1037,7 +1037,7 @@ static void sa_free_sa_rx_data(struct sa_rx_data *rxd)
 
 static void sa_aes_dma_in_callback(void *data)
 {
-	struct sa_rx_data *rxd = (struct sa_rx_data *)data;
+	struct sa_rx_data *rxd = data;
 	struct skcipher_request *req;
 	u32 *result;
 	__be32 *mdptr;
@@ -1351,7 +1351,7 @@ static int sa_decrypt(struct skcipher_request *req)
 
 static void sa_sha_dma_in_callback(void *data)
 {
-	struct sa_rx_data *rxd = (struct sa_rx_data *)data;
+	struct sa_rx_data *rxd = data;
 	struct ahash_request *req;
 	struct crypto_ahash *tfm;
 	unsigned int authsize;
@@ -1689,7 +1689,7 @@ static void sa_sha_cra_exit(struct crypto_tfm *tfm)
 
 static void sa_aead_dma_in_callback(void *data)
 {
-	struct sa_rx_data *rxd = (struct sa_rx_data *)data;
+	struct sa_rx_data *rxd = data;
 	struct aead_request *req;
 	struct crypto_aead *tfm;
 	unsigned int start;
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index dd4c703cd855..4c799df3e883 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -1035,7 +1035,7 @@ static int sahara_sha_process(struct ahash_request *req)
 
 static int sahara_queue_manage(void *data)
 {
-	struct sahara_dev *dev = (struct sahara_dev *)data;
+	struct sahara_dev *dev = data;
 	struct crypto_async_request *async_req;
 	struct crypto_async_request *backlog;
 	int ret = 0;
@@ -1270,7 +1270,7 @@ static struct ahash_alg sha_v4_algs[] = {
 
 static irqreturn_t sahara_irq_handler(int irq, void *data)
 {
-	struct sahara_dev *dev = (struct sahara_dev *)data;
+	struct sahara_dev *dev = data;
 	unsigned int stat = sahara_read(dev, SAHARA_REG_STATUS);
 	unsigned int err = sahara_read(dev, SAHARA_REG_ERRSTATUS);
 
diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index 7bf805563ac2..f0df32382719 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/clk.h>
-#include <linux/crypto.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
@@ -68,7 +67,7 @@
 #define HASH_MASK_DATA_INPUT		BIT(1)
 
 /* Context swap register */
-#define HASH_CSR_REGISTER_NUMBER	53
+#define HASH_CSR_REGISTER_NUMBER	54
 
 /* Status Flags */
 #define HASH_SR_DATA_INPUT_READY	BIT(0)
@@ -96,7 +95,7 @@
 #define HASH_FLAGS_SHA1			BIT(19)
 #define HASH_FLAGS_SHA224		BIT(20)
 #define HASH_FLAGS_SHA256		BIT(21)
-#define HASH_FLAGS_ERRORS		BIT(22)
+#define HASH_FLAGS_EMPTY		BIT(22)
 #define HASH_FLAGS_HMAC			BIT(23)
 
 #define HASH_OP_UPDATE			1
@@ -127,15 +126,24 @@ struct stm32_hash_ctx {
 	int			keylen;
 };
 
+struct stm32_hash_state {
+	u32			flags;
+
+	u16			bufcnt;
+	u16			buflen;
+
+	u8 buffer[HASH_BUFLEN] __aligned(4);
+
+	/* hash state */
+	u32			hw_context[3 + HASH_CSR_REGISTER_NUMBER];
+};
+
 struct stm32_hash_request_ctx {
 	struct stm32_hash_dev	*hdev;
-	unsigned long		flags;
 	unsigned long		op;
 
 	u8 digest[SHA256_DIGEST_SIZE] __aligned(sizeof(u32));
 	size_t			digcnt;
-	size_t			bufcnt;
-	size_t			buflen;
 
 	/* DMA */
 	struct scatterlist	*sg;
@@ -149,10 +157,7 @@ struct stm32_hash_request_ctx {
 
 	u8			data_type;
 
-	u8 buffer[HASH_BUFLEN] __aligned(sizeof(u32));
-
-	/* Export Context */
-	u32			*hw_context;
+	struct stm32_hash_state state;
 };
 
 struct stm32_hash_algs_info {
@@ -183,7 +188,6 @@ struct stm32_hash_dev {
 	struct ahash_request	*req;
 	struct crypto_engine	*engine;
 
-	int			err;
 	unsigned long		flags;
 
 	struct dma_chan		*dma_lch;
@@ -270,11 +274,12 @@ static void stm32_hash_write_ctrl(struct stm32_hash_dev *hdev, int bufcnt)
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(hdev->req);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(hdev->req);
 	struct stm32_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct stm32_hash_state *state = &rctx->state;
 
 	u32 reg = HASH_CR_INIT;
 
 	if (!(hdev->flags & HASH_FLAGS_INIT)) {
-		switch (rctx->flags & HASH_FLAGS_ALGO_MASK) {
+		switch (state->flags & HASH_FLAGS_ALGO_MASK) {
 		case HASH_FLAGS_MD5:
 			reg |= HASH_CR_ALGO_MD5;
 			break;
@@ -299,20 +304,13 @@ static void stm32_hash_write_ctrl(struct stm32_hash_dev *hdev, int bufcnt)
 
 		reg |= (rctx->data_type << HASH_CR_DATATYPE_POS);
 
-		if (rctx->flags & HASH_FLAGS_HMAC) {
+		if (state->flags & HASH_FLAGS_HMAC) {
 			hdev->flags |= HASH_FLAGS_HMAC;
 			reg |= HASH_CR_MODE;
 			if (ctx->keylen > HASH_LONG_KEY)
 				reg |= HASH_CR_LKEY;
 		}
 
-		/*
-		 * On the Ux500 we need to set a special flag to indicate that
-		 * the message is zero length.
-		 */
-		if (hdev->pdata->ux500 && bufcnt == 0)
-			reg |= HASH_CR_UX500_EMPTYMSG;
-
 		if (!hdev->polled)
 			stm32_hash_write(hdev, HASH_IMR, HASH_DCIE);
 
@@ -326,11 +324,12 @@ static void stm32_hash_write_ctrl(struct stm32_hash_dev *hdev, int bufcnt)
 
 static void stm32_hash_append_sg(struct stm32_hash_request_ctx *rctx)
 {
+	struct stm32_hash_state *state = &rctx->state;
 	size_t count;
 
-	while ((rctx->bufcnt < rctx->buflen) && rctx->total) {
+	while ((state->bufcnt < state->buflen) && rctx->total) {
 		count = min(rctx->sg->length - rctx->offset, rctx->total);
-		count = min(count, rctx->buflen - rctx->bufcnt);
+		count = min_t(size_t, count, state->buflen - state->bufcnt);
 
 		if (count <= 0) {
 			if ((rctx->sg->length == 0) && !sg_is_last(rctx->sg)) {
@@ -341,10 +340,10 @@ static void stm32_hash_append_sg(struct stm32_hash_request_ctx *rctx)
 			}
 		}
 
-		scatterwalk_map_and_copy(rctx->buffer + rctx->bufcnt, rctx->sg,
-					 rctx->offset, count, 0);
+		scatterwalk_map_and_copy(state->buffer + state->bufcnt,
+					 rctx->sg, rctx->offset, count, 0);
 
-		rctx->bufcnt += count;
+		state->bufcnt += count;
 		rctx->offset += count;
 		rctx->total -= count;
 
@@ -361,13 +360,23 @@ static void stm32_hash_append_sg(struct stm32_hash_request_ctx *rctx)
 static int stm32_hash_xmit_cpu(struct stm32_hash_dev *hdev,
 			       const u8 *buf, size_t length, int final)
 {
+	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(hdev->req);
+	struct stm32_hash_state *state = &rctx->state;
 	unsigned int count, len32;
 	const u32 *buffer = (const u32 *)buf;
 	u32 reg;
 
-	if (final)
+	if (final) {
 		hdev->flags |= HASH_FLAGS_FINAL;
 
+		/* Do not process empty messages if hw is buggy. */
+		if (!(hdev->flags & HASH_FLAGS_INIT) && !length &&
+		    hdev->pdata->broken_emptymsg) {
+			state->flags |= HASH_FLAGS_EMPTY;
+			return 0;
+		}
+	}
+
 	len32 = DIV_ROUND_UP(length, sizeof(u32));
 
 	dev_dbg(hdev->dev, "%s: length: %zd, final: %x len32 %i\n",
@@ -413,36 +422,48 @@ static int stm32_hash_xmit_cpu(struct stm32_hash_dev *hdev,
 static int stm32_hash_update_cpu(struct stm32_hash_dev *hdev)
 {
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(hdev->req);
+	struct stm32_hash_state *state = &rctx->state;
+	u32 *preg = state->hw_context;
 	int bufcnt, err = 0, final;
+	int i;
 
-	dev_dbg(hdev->dev, "%s flags %lx\n", __func__, rctx->flags);
+	dev_dbg(hdev->dev, "%s flags %x\n", __func__, state->flags);
 
-	final = (rctx->flags & HASH_FLAGS_FINUP);
+	final = state->flags & HASH_FLAGS_FINAL;
 
-	while ((rctx->total >= rctx->buflen) ||
-	       (rctx->bufcnt + rctx->total >= rctx->buflen)) {
+	while ((rctx->total >= state->buflen) ||
+	       (state->bufcnt + rctx->total >= state->buflen)) {
 		stm32_hash_append_sg(rctx);
-		bufcnt = rctx->bufcnt;
-		rctx->bufcnt = 0;
-		err = stm32_hash_xmit_cpu(hdev, rctx->buffer, bufcnt, 0);
+		bufcnt = state->bufcnt;
+		state->bufcnt = 0;
+		err = stm32_hash_xmit_cpu(hdev, state->buffer, bufcnt, 0);
+		if (err)
+			return err;
 	}
 
 	stm32_hash_append_sg(rctx);
 
 	if (final) {
-		bufcnt = rctx->bufcnt;
-		rctx->bufcnt = 0;
-		err = stm32_hash_xmit_cpu(hdev, rctx->buffer, bufcnt, 1);
-
-		/* If we have an IRQ, wait for that, else poll for completion */
-		if (hdev->polled) {
-			if (stm32_hash_wait_busy(hdev))
-				return -ETIMEDOUT;
-			hdev->flags |= HASH_FLAGS_OUTPUT_READY;
-			err = 0;
-		}
+		bufcnt = state->bufcnt;
+		state->bufcnt = 0;
+		return stm32_hash_xmit_cpu(hdev, state->buffer, bufcnt, 1);
 	}
 
+	if (!(hdev->flags & HASH_FLAGS_INIT))
+		return 0;
+
+	if (stm32_hash_wait_busy(hdev))
+		return -ETIMEDOUT;
+
+	if (!hdev->pdata->ux500)
+		*preg++ = stm32_hash_read(hdev, HASH_IMR);
+	*preg++ = stm32_hash_read(hdev, HASH_STR);
+	*preg++ = stm32_hash_read(hdev, HASH_CR);
+	for (i = 0; i < HASH_CSR_REGISTER_NUMBER; i++)
+		*preg++ = stm32_hash_read(hdev, HASH_CSR(i));
+
+	state->flags |= HASH_FLAGS_INIT;
+
 	return err;
 }
 
@@ -584,10 +605,10 @@ static int stm32_hash_dma_init(struct stm32_hash_dev *hdev)
 static int stm32_hash_dma_send(struct stm32_hash_dev *hdev)
 {
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(hdev->req);
+	u32 *buffer = (void *)rctx->state.buffer;
 	struct scatterlist sg[1], *tsg;
 	int err = 0, len = 0, reg, ncp = 0;
 	unsigned int i;
-	u32 *buffer = (void *)rctx->buffer;
 
 	rctx->sg = hdev->req->src;
 	rctx->total = hdev->req->nbytes;
@@ -615,7 +636,7 @@ static int stm32_hash_dma_send(struct stm32_hash_dev *hdev)
 
 				ncp = sg_pcopy_to_buffer(
 					rctx->sg, rctx->nents,
-					rctx->buffer, sg->length - len,
+					rctx->state.buffer, sg->length - len,
 					rctx->total - sg->length + len);
 
 				sg->length = len;
@@ -726,47 +747,52 @@ static int stm32_hash_init(struct ahash_request *req)
 	struct stm32_hash_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
 	struct stm32_hash_dev *hdev = stm32_hash_find_dev(ctx);
+	struct stm32_hash_state *state = &rctx->state;
 
 	rctx->hdev = hdev;
 
-	rctx->flags = HASH_FLAGS_CPU;
+	state->flags = HASH_FLAGS_CPU;
 
 	rctx->digcnt = crypto_ahash_digestsize(tfm);
 	switch (rctx->digcnt) {
 	case MD5_DIGEST_SIZE:
-		rctx->flags |= HASH_FLAGS_MD5;
+		state->flags |= HASH_FLAGS_MD5;
 		break;
 	case SHA1_DIGEST_SIZE:
-		rctx->flags |= HASH_FLAGS_SHA1;
+		state->flags |= HASH_FLAGS_SHA1;
 		break;
 	case SHA224_DIGEST_SIZE:
-		rctx->flags |= HASH_FLAGS_SHA224;
+		state->flags |= HASH_FLAGS_SHA224;
 		break;
 	case SHA256_DIGEST_SIZE:
-		rctx->flags |= HASH_FLAGS_SHA256;
+		state->flags |= HASH_FLAGS_SHA256;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	rctx->bufcnt = 0;
-	rctx->buflen = HASH_BUFLEN;
+	rctx->state.bufcnt = 0;
+	rctx->state.buflen = HASH_BUFLEN;
 	rctx->total = 0;
 	rctx->offset = 0;
 	rctx->data_type = HASH_DATA_8_BITS;
 
-	memset(rctx->buffer, 0, HASH_BUFLEN);
-
 	if (ctx->flags & HASH_FLAGS_HMAC)
-		rctx->flags |= HASH_FLAGS_HMAC;
+		state->flags |= HASH_FLAGS_HMAC;
 
-	dev_dbg(hdev->dev, "%s Flags %lx\n", __func__, rctx->flags);
+	dev_dbg(hdev->dev, "%s Flags %x\n", __func__, state->flags);
 
 	return 0;
 }
 
 static int stm32_hash_update_req(struct stm32_hash_dev *hdev)
 {
+	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(hdev->req);
+	struct stm32_hash_state *state = &rctx->state;
+
+	if (!(state->flags & HASH_FLAGS_CPU))
+		return stm32_hash_dma_send(hdev);
+
 	return stm32_hash_update_cpu(hdev);
 }
 
@@ -774,26 +800,15 @@ static int stm32_hash_final_req(struct stm32_hash_dev *hdev)
 {
 	struct ahash_request *req = hdev->req;
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
-	int err;
-	int buflen = rctx->bufcnt;
+	struct stm32_hash_state *state = &rctx->state;
+	int buflen = state->bufcnt;
 
-	rctx->bufcnt = 0;
+	if (state->flags & HASH_FLAGS_FINUP)
+		return stm32_hash_update_req(hdev);
 
-	if (!(rctx->flags & HASH_FLAGS_CPU))
-		err = stm32_hash_dma_send(hdev);
-	else
-		err = stm32_hash_xmit_cpu(hdev, rctx->buffer, buflen, 1);
+	state->bufcnt = 0;
 
-	/* If we have an IRQ, wait for that, else poll for completion */
-	if (hdev->polled) {
-		if (stm32_hash_wait_busy(hdev))
-			return -ETIMEDOUT;
-		hdev->flags |= HASH_FLAGS_OUTPUT_READY;
-		/* Caller will call stm32_hash_finish_req() */
-		err = 0;
-	}
-
-	return err;
+	return stm32_hash_xmit_cpu(hdev, state->buffer, buflen, 1);
 }
 
 static void stm32_hash_emptymsg_fallback(struct ahash_request *req)
@@ -828,14 +843,15 @@ static void stm32_hash_emptymsg_fallback(struct ahash_request *req)
 static void stm32_hash_copy_hash(struct ahash_request *req)
 {
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
+	struct stm32_hash_state *state = &rctx->state;
 	struct stm32_hash_dev *hdev = rctx->hdev;
 	__be32 *hash = (void *)rctx->digest;
 	unsigned int i, hashsize;
 
-	if (hdev->pdata->broken_emptymsg && !req->nbytes)
+	if (hdev->pdata->broken_emptymsg && (state->flags & HASH_FLAGS_EMPTY))
 		return stm32_hash_emptymsg_fallback(req);
 
-	switch (rctx->flags & HASH_FLAGS_ALGO_MASK) {
+	switch (state->flags & HASH_FLAGS_ALGO_MASK) {
 	case HASH_FLAGS_MD5:
 		hashsize = MD5_DIGEST_SIZE;
 		break;
@@ -882,13 +898,6 @@ static void stm32_hash_finish_req(struct ahash_request *req, int err)
 	if (!err && (HASH_FLAGS_FINAL & hdev->flags)) {
 		stm32_hash_copy_hash(req);
 		err = stm32_hash_finish(req);
-		hdev->flags &= ~(HASH_FLAGS_FINAL | HASH_FLAGS_CPU |
-				 HASH_FLAGS_INIT | HASH_FLAGS_DMA_READY |
-				 HASH_FLAGS_OUTPUT_READY | HASH_FLAGS_HMAC |
-				 HASH_FLAGS_HMAC_INIT | HASH_FLAGS_HMAC_FINAL |
-				 HASH_FLAGS_HMAC_KEY);
-	} else {
-		rctx->flags |= HASH_FLAGS_ERRORS;
 	}
 
 	pm_runtime_mark_last_busy(hdev->dev);
@@ -897,73 +906,70 @@ static void stm32_hash_finish_req(struct ahash_request *req, int err)
 	crypto_finalize_hash_request(hdev->engine, req, err);
 }
 
-static int stm32_hash_hw_init(struct stm32_hash_dev *hdev,
-			      struct stm32_hash_request_ctx *rctx)
-{
-	pm_runtime_get_sync(hdev->dev);
-
-	if (!(HASH_FLAGS_INIT & hdev->flags)) {
-		stm32_hash_write(hdev, HASH_CR, HASH_CR_INIT);
-		stm32_hash_write(hdev, HASH_STR, 0);
-		stm32_hash_write(hdev, HASH_DIN, 0);
-		stm32_hash_write(hdev, HASH_IMR, 0);
-		hdev->err = 0;
-	}
-
-	return 0;
-}
-
-static int stm32_hash_one_request(struct crypto_engine *engine, void *areq);
-static int stm32_hash_prepare_req(struct crypto_engine *engine, void *areq);
-
 static int stm32_hash_handle_queue(struct stm32_hash_dev *hdev,
 				   struct ahash_request *req)
 {
 	return crypto_transfer_hash_request_to_engine(hdev->engine, req);
 }
 
-static int stm32_hash_prepare_req(struct crypto_engine *engine, void *areq)
+static int stm32_hash_one_request(struct crypto_engine *engine, void *areq)
 {
 	struct ahash_request *req = container_of(areq, struct ahash_request,
 						 base);
 	struct stm32_hash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
+	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
 	struct stm32_hash_dev *hdev = stm32_hash_find_dev(ctx);
-	struct stm32_hash_request_ctx *rctx;
+	struct stm32_hash_state *state = &rctx->state;
+	int err = 0;
 
 	if (!hdev)
 		return -ENODEV;
 
-	hdev->req = req;
-
-	rctx = ahash_request_ctx(req);
-
 	dev_dbg(hdev->dev, "processing new req, op: %lu, nbytes %d\n",
 		rctx->op, req->nbytes);
 
-	return stm32_hash_hw_init(hdev, rctx);
-}
+	pm_runtime_get_sync(hdev->dev);
 
-static int stm32_hash_one_request(struct crypto_engine *engine, void *areq)
-{
-	struct ahash_request *req = container_of(areq, struct ahash_request,
-						 base);
-	struct stm32_hash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
-	struct stm32_hash_dev *hdev = stm32_hash_find_dev(ctx);
-	struct stm32_hash_request_ctx *rctx;
-	int err = 0;
+	hdev->req = req;
+	hdev->flags = 0;
+
+	if (state->flags & HASH_FLAGS_INIT) {
+		u32 *preg = rctx->state.hw_context;
+		u32 reg;
+		int i;
+
+		if (!hdev->pdata->ux500)
+			stm32_hash_write(hdev, HASH_IMR, *preg++);
+		stm32_hash_write(hdev, HASH_STR, *preg++);
+		stm32_hash_write(hdev, HASH_CR, *preg);
+		reg = *preg++ | HASH_CR_INIT;
+		stm32_hash_write(hdev, HASH_CR, reg);
 
-	if (!hdev)
-		return -ENODEV;
+		for (i = 0; i < HASH_CSR_REGISTER_NUMBER; i++)
+			stm32_hash_write(hdev, HASH_CSR(i), *preg++);
 
-	hdev->req = req;
+		hdev->flags |= HASH_FLAGS_INIT;
 
-	rctx = ahash_request_ctx(req);
+		if (state->flags & HASH_FLAGS_HMAC)
+			hdev->flags |= HASH_FLAGS_HMAC |
+				       HASH_FLAGS_HMAC_KEY;
+	}
 
 	if (rctx->op == HASH_OP_UPDATE)
 		err = stm32_hash_update_req(hdev);
 	else if (rctx->op == HASH_OP_FINAL)
 		err = stm32_hash_final_req(hdev);
 
+	/* If we have an IRQ, wait for that, else poll for completion */
+	if (err == -EINPROGRESS && hdev->polled) {
+		if (stm32_hash_wait_busy(hdev))
+			err = -ETIMEDOUT;
+		else {
+			hdev->flags |= HASH_FLAGS_OUTPUT_READY;
+			err = 0;
+		}
+	}
+
 	if (err != -EINPROGRESS)
 	/* done task will not finish it, so do it here */
 		stm32_hash_finish_req(req, err);
@@ -985,15 +991,16 @@ static int stm32_hash_enqueue(struct ahash_request *req, unsigned int op)
 static int stm32_hash_update(struct ahash_request *req)
 {
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
+	struct stm32_hash_state *state = &rctx->state;
 
-	if (!req->nbytes || !(rctx->flags & HASH_FLAGS_CPU))
+	if (!req->nbytes || !(state->flags & HASH_FLAGS_CPU))
 		return 0;
 
 	rctx->total = req->nbytes;
 	rctx->sg = req->src;
 	rctx->offset = 0;
 
-	if ((rctx->bufcnt + rctx->total < rctx->buflen)) {
+	if ((state->bufcnt + rctx->total < state->buflen)) {
 		stm32_hash_append_sg(rctx);
 		return 0;
 	}
@@ -1004,8 +1011,9 @@ static int stm32_hash_update(struct ahash_request *req)
 static int stm32_hash_final(struct ahash_request *req)
 {
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
+	struct stm32_hash_state *state = &rctx->state;
 
-	rctx->flags |= HASH_FLAGS_FINUP;
+	state->flags |= HASH_FLAGS_FINAL;
 
 	return stm32_hash_enqueue(req, HASH_OP_FINAL);
 }
@@ -1015,25 +1023,21 @@ static int stm32_hash_finup(struct ahash_request *req)
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
 	struct stm32_hash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
 	struct stm32_hash_dev *hdev = stm32_hash_find_dev(ctx);
-	int err1, err2;
+	struct stm32_hash_state *state = &rctx->state;
 
-	rctx->flags |= HASH_FLAGS_FINUP;
+	if (!req->nbytes)
+		goto out;
 
-	if (hdev->dma_lch && stm32_hash_dma_aligned_data(req))
-		rctx->flags &= ~HASH_FLAGS_CPU;
-
-	err1 = stm32_hash_update(req);
-
-	if (err1 == -EINPROGRESS || err1 == -EBUSY)
-		return err1;
+	state->flags |= HASH_FLAGS_FINUP;
+	rctx->total = req->nbytes;
+	rctx->sg = req->src;
+	rctx->offset = 0;
 
-	/*
-	 * final() has to be always called to cleanup resources
-	 * even if update() failed, except EINPROGRESS
-	 */
-	err2 = stm32_hash_final(req);
+	if (hdev->dma_lch && stm32_hash_dma_aligned_data(req))
+		state->flags &= ~HASH_FLAGS_CPU;
 
-	return err1 ?: err2;
+out:
+	return stm32_hash_final(req);
 }
 
 static int stm32_hash_digest(struct ahash_request *req)
@@ -1044,35 +1048,8 @@ static int stm32_hash_digest(struct ahash_request *req)
 static int stm32_hash_export(struct ahash_request *req, void *out)
 {
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
-	struct stm32_hash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
-	struct stm32_hash_dev *hdev = stm32_hash_find_dev(ctx);
-	u32 *preg;
-	unsigned int i;
-	int ret;
 
-	pm_runtime_get_sync(hdev->dev);
-
-	ret = stm32_hash_wait_busy(hdev);
-	if (ret)
-		return ret;
-
-	rctx->hw_context = kmalloc_array(3 + HASH_CSR_REGISTER_NUMBER,
-					 sizeof(u32),
-					 GFP_KERNEL);
-
-	preg = rctx->hw_context;
-
-	if (!hdev->pdata->ux500)
-		*preg++ = stm32_hash_read(hdev, HASH_IMR);
-	*preg++ = stm32_hash_read(hdev, HASH_STR);
-	*preg++ = stm32_hash_read(hdev, HASH_CR);
-	for (i = 0; i < HASH_CSR_REGISTER_NUMBER; i++)
-		*preg++ = stm32_hash_read(hdev, HASH_CSR(i));
-
-	pm_runtime_mark_last_busy(hdev->dev);
-	pm_runtime_put_autosuspend(hdev->dev);
-
-	memcpy(out, rctx, sizeof(*rctx));
+	memcpy(out, &rctx->state, sizeof(rctx->state));
 
 	return 0;
 }
@@ -1080,32 +1057,9 @@ static int stm32_hash_export(struct ahash_request *req, void *out)
 static int stm32_hash_import(struct ahash_request *req, const void *in)
 {
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
-	struct stm32_hash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
-	struct stm32_hash_dev *hdev = stm32_hash_find_dev(ctx);
-	const u32 *preg = in;
-	u32 reg;
-	unsigned int i;
-
-	memcpy(rctx, in, sizeof(*rctx));
-
-	preg = rctx->hw_context;
-
-	pm_runtime_get_sync(hdev->dev);
-
-	if (!hdev->pdata->ux500)
-		stm32_hash_write(hdev, HASH_IMR, *preg++);
-	stm32_hash_write(hdev, HASH_STR, *preg++);
-	stm32_hash_write(hdev, HASH_CR, *preg);
-	reg = *preg++ | HASH_CR_INIT;
-	stm32_hash_write(hdev, HASH_CR, reg);
-
-	for (i = 0; i < HASH_CSR_REGISTER_NUMBER; i++)
-		stm32_hash_write(hdev, HASH_CSR(i), *preg++);
-
-	pm_runtime_mark_last_busy(hdev->dev);
-	pm_runtime_put_autosuspend(hdev->dev);
 
-	kfree(rctx->hw_context);
+	stm32_hash_init(req);
+	memcpy(&rctx->state, in, sizeof(rctx->state));
 
 	return 0;
 }
@@ -1162,8 +1116,6 @@ static int stm32_hash_cra_init_algs(struct crypto_tfm *tfm,
 		ctx->flags |= HASH_FLAGS_HMAC;
 
 	ctx->enginectx.op.do_one_request = stm32_hash_one_request;
-	ctx->enginectx.op.prepare_request = stm32_hash_prepare_req;
-	ctx->enginectx.op.unprepare_request = NULL;
 
 	return stm32_hash_init_fallback(tfm);
 }
@@ -1255,7 +1207,7 @@ static struct ahash_alg algs_md5[] = {
 		.import = stm32_hash_import,
 		.halg = {
 			.digestsize = MD5_DIGEST_SIZE,
-			.statesize = sizeof(struct stm32_hash_request_ctx),
+			.statesize = sizeof(struct stm32_hash_state),
 			.base = {
 				.cra_name = "md5",
 				.cra_driver_name = "stm32-md5",
@@ -1282,7 +1234,7 @@ static struct ahash_alg algs_md5[] = {
 		.setkey = stm32_hash_setkey,
 		.halg = {
 			.digestsize = MD5_DIGEST_SIZE,
-			.statesize = sizeof(struct stm32_hash_request_ctx),
+			.statesize = sizeof(struct stm32_hash_state),
 			.base = {
 				.cra_name = "hmac(md5)",
 				.cra_driver_name = "stm32-hmac-md5",
@@ -1311,7 +1263,7 @@ static struct ahash_alg algs_sha1[] = {
 		.import = stm32_hash_import,
 		.halg = {
 			.digestsize = SHA1_DIGEST_SIZE,
-			.statesize = sizeof(struct stm32_hash_request_ctx),
+			.statesize = sizeof(struct stm32_hash_state),
 			.base = {
 				.cra_name = "sha1",
 				.cra_driver_name = "stm32-sha1",
@@ -1338,7 +1290,7 @@ static struct ahash_alg algs_sha1[] = {
 		.setkey = stm32_hash_setkey,
 		.halg = {
 			.digestsize = SHA1_DIGEST_SIZE,
-			.statesize = sizeof(struct stm32_hash_request_ctx),
+			.statesize = sizeof(struct stm32_hash_state),
 			.base = {
 				.cra_name = "hmac(sha1)",
 				.cra_driver_name = "stm32-hmac-sha1",
@@ -1367,7 +1319,7 @@ static struct ahash_alg algs_sha224[] = {
 		.import = stm32_hash_import,
 		.halg = {
 			.digestsize = SHA224_DIGEST_SIZE,
-			.statesize = sizeof(struct stm32_hash_request_ctx),
+			.statesize = sizeof(struct stm32_hash_state),
 			.base = {
 				.cra_name = "sha224",
 				.cra_driver_name = "stm32-sha224",
@@ -1394,7 +1346,7 @@ static struct ahash_alg algs_sha224[] = {
 		.import = stm32_hash_import,
 		.halg = {
 			.digestsize = SHA224_DIGEST_SIZE,
-			.statesize = sizeof(struct stm32_hash_request_ctx),
+			.statesize = sizeof(struct stm32_hash_state),
 			.base = {
 				.cra_name = "hmac(sha224)",
 				.cra_driver_name = "stm32-hmac-sha224",
@@ -1423,7 +1375,7 @@ static struct ahash_alg algs_sha256[] = {
 		.import = stm32_hash_import,
 		.halg = {
 			.digestsize = SHA256_DIGEST_SIZE,
-			.statesize = sizeof(struct stm32_hash_request_ctx),
+			.statesize = sizeof(struct stm32_hash_state),
 			.base = {
 				.cra_name = "sha256",
 				.cra_driver_name = "stm32-sha256",
@@ -1450,7 +1402,7 @@ static struct ahash_alg algs_sha256[] = {
 		.setkey = stm32_hash_setkey,
 		.halg = {
 			.digestsize = SHA256_DIGEST_SIZE,
-			.statesize = sizeof(struct stm32_hash_request_ctx),
+			.statesize = sizeof(struct stm32_hash_state),
 			.base = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "stm32-hmac-sha256",
@@ -1616,8 +1568,7 @@ static int stm32_hash_probe(struct platform_device *pdev)
 	if (!hdev)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	hdev->io_base = devm_ioremap_resource(dev, res);
+	hdev->io_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(hdev->io_base))
 		return PTR_ERR(hdev->io_base);
 
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 25eb4e8fd22f..4b4323bbf268 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -566,9 +566,12 @@ config I2C_DESIGNWARE_PLATFORM
 
 config I2C_DESIGNWARE_AMDPSP
 	bool "AMD PSP I2C semaphore support"
-	depends on X86_MSR
 	depends on ACPI
+	depends on CRYPTO_DEV_SP_PSP
+	depends on PCI
 	depends on I2C_DESIGNWARE_PLATFORM
+	depends on (I2C_DESIGNWARE_PLATFORM=y && CRYPTO_DEV_CCP_DD=y) || \
+		   (I2C_DESIGNWARE_PLATFORM=m && CRYPTO_DEV_CCP_DD)
 	help
 	  This driver enables managed host access to the selected I2C bus shared
 	  between AMD CPU and AMD PSP.
diff --git a/drivers/i2c/busses/i2c-designware-amdpsp.c b/drivers/i2c/busses/i2c-designware-amdpsp.c
index 8f36167bce62..63454b06e5da 100644
--- a/drivers/i2c/busses/i2c-designware-amdpsp.c
+++ b/drivers/i2c/busses/i2c-designware-amdpsp.c
@@ -1,41 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/bitfield.h>
-#include <linux/bits.h>
 #include <linux/i2c.h>
-#include <linux/io-64-nonatomic-lo-hi.h>
-#include <linux/psp-sev.h>
-#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/psp-platform-access.h>
+#include <linux/psp.h>
 #include <linux/workqueue.h>
 
-#include <asm/msr.h>
-
 #include "i2c-designware-core.h"
 
-#define MSR_AMD_PSP_ADDR	0xc00110a2
-#define PSP_MBOX_OFFSET		0x10570
-#define PSP_CMD_TIMEOUT_US	(500 * USEC_PER_MSEC)
-
 #define PSP_I2C_RESERVATION_TIME_MS 100
 
-#define PSP_I2C_REQ_BUS_CMD		0x64
 #define PSP_I2C_REQ_RETRY_CNT		400
 #define PSP_I2C_REQ_RETRY_DELAY_US	(25 * USEC_PER_MSEC)
 #define PSP_I2C_REQ_STS_OK		0x0
 #define PSP_I2C_REQ_STS_BUS_BUSY	0x1
 #define PSP_I2C_REQ_STS_INV_PARAM	0x3
 
-#define PSP_MBOX_FIELDS_STS		GENMASK(15, 0)
-#define PSP_MBOX_FIELDS_CMD		GENMASK(23, 16)
-#define PSP_MBOX_FIELDS_RESERVED	GENMASK(29, 24)
-#define PSP_MBOX_FIELDS_RECOVERY	BIT(30)
-#define PSP_MBOX_FIELDS_READY		BIT(31)
-
-struct psp_req_buffer_hdr {
-	u32 total_size;
-	u32 status;
-};
-
 enum psp_i2c_req_type {
 	PSP_I2C_REQ_ACQUIRE,
 	PSP_I2C_REQ_RELEASE,
@@ -47,118 +27,13 @@ struct psp_i2c_req {
 	enum psp_i2c_req_type type;
 };
 
-struct psp_mbox {
-	u32 cmd_fields;
-	u64 i2c_req_addr;
-} __packed;
-
 static DEFINE_MUTEX(psp_i2c_access_mutex);
 static unsigned long psp_i2c_sem_acquired;
-static void __iomem *mbox_iomem;
 static u32 psp_i2c_access_count;
 static bool psp_i2c_mbox_fail;
 static struct device *psp_i2c_dev;
 
-/*
- * Implementation of PSP-x86 i2c-arbitration mailbox introduced for AMD Cezanne
- * family of SoCs.
- */
-
-static int psp_get_mbox_addr(unsigned long *mbox_addr)
-{
-	unsigned long long psp_mmio;
-
-	if (rdmsrl_safe(MSR_AMD_PSP_ADDR, &psp_mmio))
-		return -EIO;
-
-	*mbox_addr = (unsigned long)(psp_mmio + PSP_MBOX_OFFSET);
-
-	return 0;
-}
-
-static int psp_mbox_probe(void)
-{
-	unsigned long mbox_addr;
-	int ret;
-
-	ret = psp_get_mbox_addr(&mbox_addr);
-	if (ret)
-		return ret;
-
-	mbox_iomem = ioremap(mbox_addr, sizeof(struct psp_mbox));
-	if (!mbox_iomem)
-		return -ENOMEM;
-
-	return 0;
-}
-
-/* Recovery field should be equal 0 to start sending commands */
-static int psp_check_mbox_recovery(struct psp_mbox __iomem *mbox)
-{
-	u32 tmp;
-
-	tmp = readl(&mbox->cmd_fields);
-
-	return FIELD_GET(PSP_MBOX_FIELDS_RECOVERY, tmp);
-}
-
-static int psp_wait_cmd(struct psp_mbox __iomem *mbox)
-{
-	u32 tmp, expected;
-
-	/* Expect mbox_cmd to be cleared and ready bit to be set by PSP */
-	expected = FIELD_PREP(PSP_MBOX_FIELDS_READY, 1);
-
-	/*
-	 * Check for readiness of PSP mailbox in a tight loop in order to
-	 * process further as soon as command was consumed.
-	 */
-	return readl_poll_timeout(&mbox->cmd_fields, tmp, (tmp == expected),
-				  0, PSP_CMD_TIMEOUT_US);
-}
-
-/* Status equal to 0 means that PSP succeed processing command */
-static u32 psp_check_mbox_sts(struct psp_mbox __iomem *mbox)
-{
-	u32 cmd_reg;
-
-	cmd_reg = readl(&mbox->cmd_fields);
-
-	return FIELD_GET(PSP_MBOX_FIELDS_STS, cmd_reg);
-}
-
-static int psp_send_cmd(struct psp_i2c_req *req)
-{
-	struct psp_mbox __iomem *mbox = mbox_iomem;
-	phys_addr_t req_addr;
-	u32 cmd_reg;
-
-	if (psp_check_mbox_recovery(mbox))
-		return -EIO;
-
-	if (psp_wait_cmd(mbox))
-		return -EBUSY;
-
-	/*
-	 * Fill mailbox with address of command-response buffer, which will be
-	 * used for sending i2c requests as well as reading status returned by
-	 * PSP. Use physical address of buffer, since PSP will map this region.
-	 */
-	req_addr = __psp_pa((void *)req);
-	writeq(req_addr, &mbox->i2c_req_addr);
-
-	/* Write command register to trigger processing */
-	cmd_reg = FIELD_PREP(PSP_MBOX_FIELDS_CMD, PSP_I2C_REQ_BUS_CMD);
-	writel(cmd_reg, &mbox->cmd_fields);
-
-	if (psp_wait_cmd(mbox))
-		return -ETIMEDOUT;
-
-	if (psp_check_mbox_sts(mbox))
-		return -EIO;
-
-	return 0;
-}
+static int (*_psp_send_i2c_req)(struct psp_i2c_req *req);
 
 /* Helper to verify status returned by PSP */
 static int check_i2c_req_sts(struct psp_i2c_req *req)
@@ -179,22 +54,36 @@ static int check_i2c_req_sts(struct psp_i2c_req *req)
 	}
 }
 
-static int psp_send_check_i2c_req(struct psp_i2c_req *req)
+/*
+ * Errors in x86-PSP i2c-arbitration protocol may occur at two levels:
+ * 1. mailbox communication - PSP is not operational or some IO errors with
+ *    basic communication had happened.
+ * 2. i2c-requests - PSP refuses to grant i2c arbitration to x86 for too long.
+ *
+ * In order to distinguish between these in error handling code all mailbox
+ * communication errors on the first level (from CCP symbols) will be passed
+ * up and if -EIO is returned the second level will be checked.
+ */
+static int psp_send_i2c_req_cezanne(struct psp_i2c_req *req)
 {
-	/*
-	 * Errors in x86-PSP i2c-arbitration protocol may occur at two levels:
-	 * 1. mailbox communication - PSP is not operational or some IO errors
-	 * with basic communication had happened;
-	 * 2. i2c-requests - PSP refuses to grant i2c arbitration to x86 for too
-	 * long.
-	 * In order to distinguish between these two in error handling code, all
-	 * errors on the first level (returned by psp_send_cmd) are shadowed by
-	 * -EIO.
-	 */
-	if (psp_send_cmd(req))
-		return -EIO;
+	int ret;
+
+	ret = psp_send_platform_access_msg(PSP_I2C_REQ_BUS_CMD, (struct psp_request *)req);
+	if (ret == -EIO)
+		return check_i2c_req_sts(req);
 
-	return check_i2c_req_sts(req);
+	return ret;
+}
+
+static int psp_send_i2c_req_doorbell(struct psp_i2c_req *req)
+{
+	int ret;
+
+	ret = psp_ring_platform_doorbell(req->type, &req->hdr.status);
+	if (ret == -EIO)
+		return check_i2c_req_sts(req);
+
+	return ret;
 }
 
 static int psp_send_i2c_req(enum psp_i2c_req_type i2c_req_type)
@@ -208,11 +97,11 @@ static int psp_send_i2c_req(enum psp_i2c_req_type i2c_req_type)
 	if (!req)
 		return -ENOMEM;
 
-	req->hdr.total_size = sizeof(*req);
+	req->hdr.payload_size = sizeof(*req);
 	req->type = i2c_req_type;
 
 	start = jiffies;
-	ret = read_poll_timeout(psp_send_check_i2c_req, status,
+	ret = read_poll_timeout(_psp_send_i2c_req, status,
 				(status != -EBUSY),
 				PSP_I2C_REQ_RETRY_DELAY_US,
 				PSP_I2C_REQ_RETRY_CNT * PSP_I2C_REQ_RETRY_DELAY_US,
@@ -387,7 +276,10 @@ static const struct i2c_lock_operations i2c_dw_psp_lock_ops = {
 
 int i2c_dw_amdpsp_probe_lock_support(struct dw_i2c_dev *dev)
 {
-	int ret;
+	struct pci_dev *rdev;
+
+	if (!IS_REACHABLE(CONFIG_CRYPTO_DEV_CCP_DD))
+		return -ENODEV;
 
 	if (!dev)
 		return -ENODEV;
@@ -399,11 +291,18 @@ int i2c_dw_amdpsp_probe_lock_support(struct dw_i2c_dev *dev)
 	if (psp_i2c_dev)
 		return -EEXIST;
 
-	psp_i2c_dev = dev->dev;
+	/* Cezanne uses platform mailbox, Mendocino and later use doorbell */
+	rdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0));
+	if (rdev->device == 0x1630)
+		_psp_send_i2c_req = psp_send_i2c_req_cezanne;
+	else
+		_psp_send_i2c_req = psp_send_i2c_req_doorbell;
+	pci_dev_put(rdev);
 
-	ret = psp_mbox_probe();
-	if (ret)
-		return ret;
+	if (psp_check_platform_access_status())
+		return -EPROBE_DEFER;
+
+	psp_i2c_dev = dev->dev;
 
 	dev_info(psp_i2c_dev, "I2C bus managed by AMD PSP\n");
 
@@ -417,9 +316,3 @@ int i2c_dw_amdpsp_probe_lock_support(struct dw_i2c_dev *dev)
 
 	return 0;
 }
-
-/* Unmap area used as a mailbox with PSP */
-void i2c_dw_amdpsp_remove_lock_support(struct dw_i2c_dev *dev)
-{
-	iounmap(mbox_iomem);
-}
diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h
index 050d8c63ad3c..c5d87aae39c6 100644
--- a/drivers/i2c/busses/i2c-designware-core.h
+++ b/drivers/i2c/busses/i2c-designware-core.h
@@ -383,7 +383,6 @@ int i2c_dw_baytrail_probe_lock_support(struct dw_i2c_dev *dev);
 
 #if IS_ENABLED(CONFIG_I2C_DESIGNWARE_AMDPSP)
 int i2c_dw_amdpsp_probe_lock_support(struct dw_i2c_dev *dev);
-void i2c_dw_amdpsp_remove_lock_support(struct dw_i2c_dev *dev);
 #endif
 
 int i2c_dw_validate_speed(struct dw_i2c_dev *dev);
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 74182db03a88..89ad88c54754 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -214,7 +214,6 @@ static const struct i2c_dw_semaphore_callbacks i2c_dw_semaphore_cb_table[] = {
 #ifdef CONFIG_I2C_DESIGNWARE_AMDPSP
 	{
 		.probe = i2c_dw_amdpsp_probe_lock_support,
-		.remove = i2c_dw_amdpsp_remove_lock_support,
 	},
 #endif
 	{}
diff --git a/drivers/tee/amdtee/call.c b/drivers/tee/amdtee/call.c
index cec6e70f0ac9..e8cd9aaa3467 100644
--- a/drivers/tee/amdtee/call.c
+++ b/drivers/tee/amdtee/call.c
@@ -8,7 +8,7 @@
 #include <linux/tee_drv.h>
 #include <linux/psp-tee.h>
 #include <linux/slab.h>
-#include <linux/psp-sev.h>
+#include <linux/psp.h>
 #include "amdtee_if.h"
 #include "amdtee_private.h"
 
diff --git a/drivers/tee/amdtee/shm_pool.c b/drivers/tee/amdtee/shm_pool.c
index f87f96a291c9..f0303126f199 100644
--- a/drivers/tee/amdtee/shm_pool.c
+++ b/drivers/tee/amdtee/shm_pool.c
@@ -5,7 +5,7 @@
 
 #include <linux/slab.h>
 #include <linux/tee_drv.h>
-#include <linux/psp-sev.h>
+#include <linux/psp.h>
 #include "amdtee_private.h"
 
 static int pool_op_alloc(struct tee_shm_pool *pool, struct tee_shm *shm,
diff --git a/include/crypto/acompress.h b/include/crypto/acompress.h
index e4bc96528902..574cffc90730 100644
--- a/include/crypto/acompress.h
+++ b/include/crypto/acompress.h
@@ -8,6 +8,9 @@
  */
 #ifndef _CRYPTO_ACOMP_H
 #define _CRYPTO_ACOMP_H
+
+#include <linux/atomic.h>
+#include <linux/container_of.h>
 #include <linux/crypto.h>
 
 #define CRYPTO_ACOMP_ALLOC_OUTPUT	0x00000001
@@ -53,37 +56,35 @@ struct crypto_acomp {
 	struct crypto_tfm base;
 };
 
-/**
- * struct acomp_alg - asynchronous compression algorithm
- *
- * @compress:	Function performs a compress operation
- * @decompress:	Function performs a de-compress operation
- * @dst_free:	Frees destination buffer if allocated inside the algorithm
- * @init:	Initialize the cryptographic transformation object.
- *		This function is used to initialize the cryptographic
- *		transformation object. This function is called only once at
- *		the instantiation time, right after the transformation context
- *		was allocated. In case the cryptographic hardware has some
- *		special requirements which need to be handled by software, this
- *		function shall check for the precise requirement of the
- *		transformation and put any software fallbacks in place.
- * @exit:	Deinitialize the cryptographic transformation object. This is a
- *		counterpart to @init, used to remove various changes set in
- *		@init.
- *
- * @reqsize:	Context size for (de)compression requests
- * @base:	Common crypto API algorithm data structure
+/*
+ * struct crypto_istat_compress - statistics for compress algorithm
+ * @compress_cnt:	number of compress requests
+ * @compress_tlen:	total data size handled by compress requests
+ * @decompress_cnt:	number of decompress requests
+ * @decompress_tlen:	total data size handled by decompress requests
+ * @err_cnt:		number of error for compress requests
  */
-struct acomp_alg {
-	int (*compress)(struct acomp_req *req);
-	int (*decompress)(struct acomp_req *req);
-	void (*dst_free)(struct scatterlist *dst);
-	int (*init)(struct crypto_acomp *tfm);
-	void (*exit)(struct crypto_acomp *tfm);
-	unsigned int reqsize;
-	struct crypto_alg base;
+struct crypto_istat_compress {
+	atomic64_t compress_cnt;
+	atomic64_t compress_tlen;
+	atomic64_t decompress_cnt;
+	atomic64_t decompress_tlen;
+	atomic64_t err_cnt;
 };
 
+#ifdef CONFIG_CRYPTO_STATS
+#define COMP_ALG_COMMON_STATS struct crypto_istat_compress stat;
+#else
+#define COMP_ALG_COMMON_STATS
+#endif
+
+#define COMP_ALG_COMMON {			\
+	COMP_ALG_COMMON_STATS			\
+						\
+	struct crypto_alg base;			\
+}
+struct comp_alg_common COMP_ALG_COMMON;
+
 /**
  * DOC: Asynchronous Compression API
  *
@@ -131,9 +132,10 @@ static inline struct crypto_tfm *crypto_acomp_tfm(struct crypto_acomp *tfm)
 	return &tfm->base;
 }
 
-static inline struct acomp_alg *__crypto_acomp_alg(struct crypto_alg *alg)
+static inline struct comp_alg_common *__crypto_comp_alg_common(
+	struct crypto_alg *alg)
 {
-	return container_of(alg, struct acomp_alg, base);
+	return container_of(alg, struct comp_alg_common, base);
 }
 
 static inline struct crypto_acomp *__crypto_acomp_tfm(struct crypto_tfm *tfm)
@@ -141,9 +143,10 @@ static inline struct crypto_acomp *__crypto_acomp_tfm(struct crypto_tfm *tfm)
 	return container_of(tfm, struct crypto_acomp, base);
 }
 
-static inline struct acomp_alg *crypto_acomp_alg(struct crypto_acomp *tfm)
+static inline struct comp_alg_common *crypto_comp_alg_common(
+	struct crypto_acomp *tfm)
 {
-	return __crypto_acomp_alg(crypto_acomp_tfm(tfm)->__crt_alg);
+	return __crypto_comp_alg_common(crypto_acomp_tfm(tfm)->__crt_alg);
 }
 
 static inline unsigned int crypto_acomp_reqsize(struct crypto_acomp *tfm)
@@ -219,7 +222,8 @@ static inline void acomp_request_set_callback(struct acomp_req *req,
 {
 	req->base.complete = cmpl;
 	req->base.data = data;
-	req->base.flags = flgs;
+	req->base.flags &= CRYPTO_ACOMP_ALLOC_OUTPUT;
+	req->base.flags |= flgs & ~CRYPTO_ACOMP_ALLOC_OUTPUT;
 }
 
 /**
@@ -246,10 +250,32 @@ static inline void acomp_request_set_params(struct acomp_req *req,
 	req->slen = slen;
 	req->dlen = dlen;
 
+	req->flags &= ~CRYPTO_ACOMP_ALLOC_OUTPUT;
 	if (!req->dst)
 		req->flags |= CRYPTO_ACOMP_ALLOC_OUTPUT;
 }
 
+static inline struct crypto_istat_compress *comp_get_stat(
+	struct comp_alg_common *alg)
+{
+#ifdef CONFIG_CRYPTO_STATS
+	return &alg->stat;
+#else
+	return NULL;
+#endif
+}
+
+static inline int crypto_comp_errstat(struct comp_alg_common *alg, int err)
+{
+	if (!IS_ENABLED(CONFIG_CRYPTO_STATS))
+		return err;
+
+	if (err && err != -EINPROGRESS && err != -EBUSY)
+		atomic64_inc(&comp_get_stat(alg)->err_cnt);
+
+	return err;
+}
+
 /**
  * crypto_acomp_compress() -- Invoke asynchronous compress operation
  *
@@ -262,14 +288,18 @@ static inline void acomp_request_set_params(struct acomp_req *req,
 static inline int crypto_acomp_compress(struct acomp_req *req)
 {
 	struct crypto_acomp *tfm = crypto_acomp_reqtfm(req);
-	struct crypto_alg *alg = tfm->base.__crt_alg;
-	unsigned int slen = req->slen;
-	int ret;
-
-	crypto_stats_get(alg);
-	ret = tfm->compress(req);
-	crypto_stats_compress(slen, ret, alg);
-	return ret;
+	struct comp_alg_common *alg;
+
+	alg = crypto_comp_alg_common(tfm);
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_compress *istat = comp_get_stat(alg);
+
+		atomic64_inc(&istat->compress_cnt);
+		atomic64_add(req->slen, &istat->compress_tlen);
+	}
+
+	return crypto_comp_errstat(alg, tfm->compress(req));
 }
 
 /**
@@ -284,14 +314,18 @@ static inline int crypto_acomp_compress(struct acomp_req *req)
 static inline int crypto_acomp_decompress(struct acomp_req *req)
 {
 	struct crypto_acomp *tfm = crypto_acomp_reqtfm(req);
-	struct crypto_alg *alg = tfm->base.__crt_alg;
-	unsigned int slen = req->slen;
-	int ret;
-
-	crypto_stats_get(alg);
-	ret = tfm->decompress(req);
-	crypto_stats_decompress(slen, ret, alg);
-	return ret;
+	struct comp_alg_common *alg;
+
+	alg = crypto_comp_alg_common(tfm);
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_compress *istat = comp_get_stat(alg);
+
+		atomic64_inc(&istat->decompress_cnt);
+		atomic64_add(req->slen, &istat->decompress_tlen);
+	}
+
+	return crypto_comp_errstat(alg, tfm->decompress(req));
 }
 
 #endif
diff --git a/include/crypto/aead.h b/include/crypto/aead.h
index 4a2b7e6e0c1f..35e45b854a6f 100644
--- a/include/crypto/aead.h
+++ b/include/crypto/aead.h
@@ -8,6 +8,7 @@
 #ifndef _CRYPTO_AEAD_H
 #define _CRYPTO_AEAD_H
 
+#include <linux/atomic.h>
 #include <linux/container_of.h>
 #include <linux/crypto.h>
 #include <linux/slab.h>
@@ -100,6 +101,22 @@ struct aead_request {
 	void *__ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
+/*
+ * struct crypto_istat_aead - statistics for AEAD algorithm
+ * @encrypt_cnt:	number of encrypt requests
+ * @encrypt_tlen:	total data size handled by encrypt requests
+ * @decrypt_cnt:	number of decrypt requests
+ * @decrypt_tlen:	total data size handled by decrypt requests
+ * @err_cnt:		number of error for AEAD requests
+ */
+struct crypto_istat_aead {
+	atomic64_t encrypt_cnt;
+	atomic64_t encrypt_tlen;
+	atomic64_t decrypt_cnt;
+	atomic64_t decrypt_tlen;
+	atomic64_t err_cnt;
+};
+
 /**
  * struct aead_alg - AEAD cipher definition
  * @maxauthsize: Set the maximum authentication tag size supported by the
@@ -118,6 +135,7 @@ struct aead_request {
  * @setkey: see struct skcipher_alg
  * @encrypt: see struct skcipher_alg
  * @decrypt: see struct skcipher_alg
+ * @stat: statistics for AEAD algorithm
  * @ivsize: see struct skcipher_alg
  * @chunksize: see struct skcipher_alg
  * @init: Initialize the cryptographic transformation object. This function
@@ -144,6 +162,10 @@ struct aead_alg {
 	int (*init)(struct crypto_aead *tfm);
 	void (*exit)(struct crypto_aead *tfm);
 
+#ifdef CONFIG_CRYPTO_STATS
+	struct crypto_istat_aead stat;
+#endif
+
 	unsigned int ivsize;
 	unsigned int maxauthsize;
 	unsigned int chunksize;
diff --git a/include/crypto/akcipher.h b/include/crypto/akcipher.h
index 734c213918bd..f35fd653e4e5 100644
--- a/include/crypto/akcipher.h
+++ b/include/crypto/akcipher.h
@@ -7,6 +7,8 @@
  */
 #ifndef _CRYPTO_AKCIPHER_H
 #define _CRYPTO_AKCIPHER_H
+
+#include <linux/atomic.h>
 #include <linux/crypto.h>
 
 /**
@@ -52,6 +54,26 @@ struct crypto_akcipher {
 	struct crypto_tfm base;
 };
 
+/*
+ * struct crypto_istat_akcipher - statistics for akcipher algorithm
+ * @encrypt_cnt:	number of encrypt requests
+ * @encrypt_tlen:	total data size handled by encrypt requests
+ * @decrypt_cnt:	number of decrypt requests
+ * @decrypt_tlen:	total data size handled by decrypt requests
+ * @verify_cnt:		number of verify operation
+ * @sign_cnt:		number of sign requests
+ * @err_cnt:		number of error for akcipher requests
+ */
+struct crypto_istat_akcipher {
+	atomic64_t encrypt_cnt;
+	atomic64_t encrypt_tlen;
+	atomic64_t decrypt_cnt;
+	atomic64_t decrypt_tlen;
+	atomic64_t verify_cnt;
+	atomic64_t sign_cnt;
+	atomic64_t err_cnt;
+};
+
 /**
  * struct akcipher_alg - generic public key algorithm
  *
@@ -88,6 +110,7 @@ struct crypto_akcipher {
  * @exit:	Deinitialize the cryptographic transformation object. This is a
  *		counterpart to @init, used to remove various changes set in
  *		@init.
+ * @stat:	Statistics for akcipher algorithm
  *
  * @base:	Common crypto API algorithm data structure
  */
@@ -104,6 +127,10 @@ struct akcipher_alg {
 	int (*init)(struct crypto_akcipher *tfm);
 	void (*exit)(struct crypto_akcipher *tfm);
 
+#ifdef CONFIG_CRYPTO_STATS
+	struct crypto_istat_akcipher stat;
+#endif
+
 	struct crypto_alg base;
 };
 
@@ -275,6 +302,27 @@ static inline unsigned int crypto_akcipher_maxsize(struct crypto_akcipher *tfm)
 	return alg->max_size(tfm);
 }
 
+static inline struct crypto_istat_akcipher *akcipher_get_stat(
+	struct akcipher_alg *alg)
+{
+#ifdef CONFIG_CRYPTO_STATS
+	return &alg->stat;
+#else
+	return NULL;
+#endif
+}
+
+static inline int crypto_akcipher_errstat(struct akcipher_alg *alg, int err)
+{
+	if (!IS_ENABLED(CONFIG_CRYPTO_STATS))
+		return err;
+
+	if (err && err != -EINPROGRESS && err != -EBUSY)
+		atomic64_inc(&akcipher_get_stat(alg)->err_cnt);
+
+	return err;
+}
+
 /**
  * crypto_akcipher_encrypt() - Invoke public key encrypt operation
  *
@@ -289,14 +337,15 @@ static inline int crypto_akcipher_encrypt(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct akcipher_alg *alg = crypto_akcipher_alg(tfm);
-	struct crypto_alg *calg = tfm->base.__crt_alg;
-	unsigned int src_len = req->src_len;
-	int ret;
-
-	crypto_stats_get(calg);
-	ret = alg->encrypt(req);
-	crypto_stats_akcipher_encrypt(src_len, ret, calg);
-	return ret;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_akcipher *istat = akcipher_get_stat(alg);
+
+		atomic64_inc(&istat->encrypt_cnt);
+		atomic64_add(req->src_len, &istat->encrypt_tlen);
+	}
+
+	return crypto_akcipher_errstat(alg, alg->encrypt(req));
 }
 
 /**
@@ -313,14 +362,15 @@ static inline int crypto_akcipher_decrypt(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct akcipher_alg *alg = crypto_akcipher_alg(tfm);
-	struct crypto_alg *calg = tfm->base.__crt_alg;
-	unsigned int src_len = req->src_len;
-	int ret;
-
-	crypto_stats_get(calg);
-	ret = alg->decrypt(req);
-	crypto_stats_akcipher_decrypt(src_len, ret, calg);
-	return ret;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_akcipher *istat = akcipher_get_stat(alg);
+
+		atomic64_inc(&istat->decrypt_cnt);
+		atomic64_add(req->src_len, &istat->decrypt_tlen);
+	}
+
+	return crypto_akcipher_errstat(alg, alg->decrypt(req));
 }
 
 /**
@@ -337,13 +387,11 @@ static inline int crypto_akcipher_sign(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct akcipher_alg *alg = crypto_akcipher_alg(tfm);
-	struct crypto_alg *calg = tfm->base.__crt_alg;
-	int ret;
 
-	crypto_stats_get(calg);
-	ret = alg->sign(req);
-	crypto_stats_akcipher_sign(ret, calg);
-	return ret;
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_inc(&akcipher_get_stat(alg)->sign_cnt);
+
+	return crypto_akcipher_errstat(alg, alg->sign(req));
 }
 
 /**
@@ -364,13 +412,11 @@ static inline int crypto_akcipher_verify(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct akcipher_alg *alg = crypto_akcipher_alg(tfm);
-	struct crypto_alg *calg = tfm->base.__crt_alg;
-	int ret;
 
-	crypto_stats_get(calg);
-	ret = alg->verify(req);
-	crypto_stats_akcipher_verify(ret, calg);
-	return ret;
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_inc(&akcipher_get_stat(alg)->verify_cnt);
+
+	return crypto_akcipher_errstat(alg, alg->verify(req));
 }
 
 /**
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index fede394ae2ab..016d5a302b84 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -7,15 +7,12 @@
 #ifndef _CRYPTO_ALGAPI_H
 #define _CRYPTO_ALGAPI_H
 
+#include <crypto/utils.h>
 #include <linux/align.h>
 #include <linux/cache.h>
 #include <linux/crypto.h>
-#include <linux/kconfig.h>
-#include <linux/list.h>
 #include <linux/types.h>
 
-#include <asm/unaligned.h>
-
 /*
  * Maximum values for blocksize and alignmask, used to allocate
  * static buffers that are big enough for any combination of
@@ -34,11 +31,25 @@
 
 #define CRYPTO_DMA_PADDING ((CRYPTO_DMA_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))
 
+/*
+ * Autoloaded crypto modules should only use a prefixed name to avoid allowing
+ * arbitrary modules to be loaded. Loading from userspace may still need the
+ * unprefixed names, so retains those aliases as well.
+ * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3
+ * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro
+ * expands twice on the same line. Instead, use a separate base name for the
+ * alias.
+ */
+#define MODULE_ALIAS_CRYPTO(name)	\
+		__MODULE_INFO(alias, alias_userspace, name);	\
+		__MODULE_INFO(alias, alias_crypto, "crypto-" name)
+
 struct crypto_aead;
 struct crypto_instance;
 struct module;
 struct notifier_block;
 struct rtattr;
+struct scatterlist;
 struct seq_file;
 struct sk_buff;
 
@@ -50,6 +61,9 @@ struct crypto_type {
 	void (*show)(struct seq_file *m, struct crypto_alg *alg);
 	int (*report)(struct sk_buff *skb, struct crypto_alg *alg);
 	void (*free)(struct crypto_instance *inst);
+#ifdef CONFIG_CRYPTO_STATS
+	int (*report_stat)(struct sk_buff *skb, struct crypto_alg *alg);
+#endif
 
 	unsigned int type;
 	unsigned int maskclear;
@@ -119,6 +133,14 @@ struct crypto_attr_type {
 	u32 mask;
 };
 
+/*
+ * Algorithm registration interface.
+ */
+int crypto_register_alg(struct crypto_alg *alg);
+void crypto_unregister_alg(struct crypto_alg *alg);
+int crypto_register_algs(struct crypto_alg *algs, int count);
+void crypto_unregister_algs(struct crypto_alg *algs, int count);
+
 void crypto_mod_put(struct crypto_alg *alg);
 
 int crypto_register_template(struct crypto_template *tmpl);
@@ -156,47 +178,6 @@ static inline unsigned int crypto_queue_len(struct crypto_queue *queue)
 }
 
 void crypto_inc(u8 *a, unsigned int size);
-void __crypto_xor(u8 *dst, const u8 *src1, const u8 *src2, unsigned int size);
-
-static inline void crypto_xor(u8 *dst, const u8 *src, unsigned int size)
-{
-	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
-	    __builtin_constant_p(size) &&
-	    (size % sizeof(unsigned long)) == 0) {
-		unsigned long *d = (unsigned long *)dst;
-		unsigned long *s = (unsigned long *)src;
-		unsigned long l;
-
-		while (size > 0) {
-			l = get_unaligned(d) ^ get_unaligned(s++);
-			put_unaligned(l, d++);
-			size -= sizeof(unsigned long);
-		}
-	} else {
-		__crypto_xor(dst, dst, src, size);
-	}
-}
-
-static inline void crypto_xor_cpy(u8 *dst, const u8 *src1, const u8 *src2,
-				  unsigned int size)
-{
-	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
-	    __builtin_constant_p(size) &&
-	    (size % sizeof(unsigned long)) == 0) {
-		unsigned long *d = (unsigned long *)dst;
-		unsigned long *s1 = (unsigned long *)src1;
-		unsigned long *s2 = (unsigned long *)src2;
-		unsigned long l;
-
-		while (size > 0) {
-			l = get_unaligned(s1++) ^ get_unaligned(s2++);
-			put_unaligned(l, d++);
-			size -= sizeof(unsigned long);
-		}
-	} else {
-		__crypto_xor(dst, src1, src2, size);
-	}
-}
 
 static inline void *crypto_tfm_ctx(struct crypto_tfm *tfm)
 {
@@ -275,23 +256,6 @@ static inline u32 crypto_algt_inherited_mask(struct crypto_attr_type *algt)
 	return crypto_requires_off(algt, CRYPTO_ALG_INHERITED_FLAGS);
 }
 
-noinline unsigned long __crypto_memneq(const void *a, const void *b, size_t size);
-
-/**
- * crypto_memneq - Compare two areas of memory without leaking
- *		   timing information.
- *
- * @a: One area of memory
- * @b: Another area of memory
- * @size: The size of the area.
- *
- * Returns 0 when data is equal, 1 otherwise.
- */
-static inline int crypto_memneq(const void *a, const void *b, size_t size)
-{
-	return __crypto_memneq(a, b, size) != 0UL ? 1 : 0;
-}
-
 int crypto_register_notifier(struct notifier_block *nb);
 int crypto_unregister_notifier(struct notifier_block *nb);
 
@@ -308,4 +272,9 @@ static inline void crypto_request_complete(struct crypto_async_request *req,
 	req->complete(req->data, err);
 }
 
+static inline u32 crypto_tfm_alg_type(struct crypto_tfm *tfm)
+{
+	return tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK;
+}
+
 #endif	/* _CRYPTO_ALGAPI_H */
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index f5841992dc9b..e69542d86a2b 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -8,6 +8,7 @@
 #ifndef _CRYPTO_HASH_H
 #define _CRYPTO_HASH_H
 
+#include <linux/atomic.h>
 #include <linux/crypto.h>
 #include <linux/string.h>
 
@@ -22,8 +23,27 @@ struct crypto_ahash;
  * crypto_unregister_shash().
  */
 
-/**
+/*
+ * struct crypto_istat_hash - statistics for has algorithm
+ * @hash_cnt:		number of hash requests
+ * @hash_tlen:		total data size hashed
+ * @err_cnt:		number of error for hash requests
+ */
+struct crypto_istat_hash {
+	atomic64_t hash_cnt;
+	atomic64_t hash_tlen;
+	atomic64_t err_cnt;
+};
+
+#ifdef CONFIG_CRYPTO_STATS
+#define HASH_ALG_COMMON_STAT struct crypto_istat_hash stat;
+#else
+#define HASH_ALG_COMMON_STAT
+#endif
+
+/*
  * struct hash_alg_common - define properties of message digest
+ * @stat: Statistics for hash algorithm.
  * @digestsize: Size of the result of the transformation. A buffer of this size
  *	        must be available to the @final and @finup calls, so they can
  *	        store the resulting hash into it. For various predefined sizes,
@@ -39,12 +59,15 @@ struct crypto_ahash;
  *	  The hash_alg_common data structure now adds the hash-specific
  *	  information.
  */
-struct hash_alg_common {
-	unsigned int digestsize;
-	unsigned int statesize;
-
-	struct crypto_alg base;
-};
+#define HASH_ALG_COMMON {		\
+	HASH_ALG_COMMON_STAT		\
+					\
+	unsigned int digestsize;	\
+	unsigned int statesize;		\
+					\
+	struct crypto_alg base;		\
+}
+struct hash_alg_common HASH_ALG_COMMON;
 
 struct ahash_request {
 	struct crypto_async_request base;
@@ -129,6 +152,7 @@ struct ahash_request {
  * @exit_tfm: Deinitialize the cryptographic transformation object.
  *	      This is a counterpart to @init_tfm, used to remove
  *	      various changes set in @init_tfm.
+ * @clone_tfm: Copy transform into new object, may allocate memory.
  * @halg: see struct hash_alg_common
  */
 struct ahash_alg {
@@ -143,6 +167,7 @@ struct ahash_alg {
 		      unsigned int keylen);
 	int (*init_tfm)(struct crypto_ahash *tfm);
 	void (*exit_tfm)(struct crypto_ahash *tfm);
+	int (*clone_tfm)(struct crypto_ahash *dst, struct crypto_ahash *src);
 
 	struct hash_alg_common halg;
 };
@@ -160,8 +185,6 @@ struct shash_desc {
  */
 #define HASH_MAX_DESCSIZE	(sizeof(struct shash_desc) + 360)
 
-#define HASH_MAX_STATESIZE	512
-
 #define SHASH_DESC_ON_STACK(shash, ctx)					     \
 	char __##shash##_desc[sizeof(struct shash_desc) + HASH_MAX_DESCSIZE] \
 		__aligned(__alignof__(struct shash_desc));		     \
@@ -188,12 +211,16 @@ struct shash_desc {
  * @exit_tfm: Deinitialize the cryptographic transformation object.
  *	      This is a counterpart to @init_tfm, used to remove
  *	      various changes set in @init_tfm.
+ * @clone_tfm: Copy transform into new object, may allocate memory.
  * @digestsize: see struct ahash_alg
  * @statesize: see struct ahash_alg
  * @descsize: Size of the operational state for the message digest. This state
  * 	      size is the memory size that needs to be allocated for
  *	      shash_desc.__ctx
+ * @stat: Statistics for hash algorithm.
  * @base: internally used
+ * @halg: see struct hash_alg_common
+ * @HASH_ALG_COMMON: see struct hash_alg_common
  */
 struct shash_alg {
 	int (*init)(struct shash_desc *desc);
@@ -210,16 +237,17 @@ struct shash_alg {
 		      unsigned int keylen);
 	int (*init_tfm)(struct crypto_shash *tfm);
 	void (*exit_tfm)(struct crypto_shash *tfm);
+	int (*clone_tfm)(struct crypto_shash *dst, struct crypto_shash *src);
 
 	unsigned int descsize;
 
-	/* These fields must match hash_alg_common. */
-	unsigned int digestsize
-		__attribute__ ((aligned(__alignof__(struct hash_alg_common))));
-	unsigned int statesize;
-
-	struct crypto_alg base;
+	union {
+		struct HASH_ALG_COMMON;
+		struct hash_alg_common halg;
+	};
 };
+#undef HASH_ALG_COMMON
+#undef HASH_ALG_COMMON_STAT
 
 struct crypto_ahash {
 	int (*init)(struct ahash_request *req);
@@ -273,6 +301,8 @@ static inline struct crypto_ahash *__crypto_ahash_cast(struct crypto_tfm *tfm)
 struct crypto_ahash *crypto_alloc_ahash(const char *alg_name, u32 type,
 					u32 mask);
 
+struct crypto_ahash *crypto_clone_ahash(struct crypto_ahash *tfm);
+
 static inline struct crypto_tfm *crypto_ahash_tfm(struct crypto_ahash *tfm)
 {
 	return &tfm->base;
@@ -535,6 +565,27 @@ static inline int crypto_ahash_init(struct ahash_request *req)
 	return tfm->init(req);
 }
 
+static inline struct crypto_istat_hash *hash_get_stat(
+	struct hash_alg_common *alg)
+{
+#ifdef CONFIG_CRYPTO_STATS
+	return &alg->stat;
+#else
+	return NULL;
+#endif
+}
+
+static inline int crypto_hash_errstat(struct hash_alg_common *alg, int err)
+{
+	if (!IS_ENABLED(CONFIG_CRYPTO_STATS))
+		return err;
+
+	if (err && err != -EINPROGRESS && err != -EBUSY)
+		atomic64_inc(&hash_get_stat(alg)->err_cnt);
+
+	return err;
+}
+
 /**
  * crypto_ahash_update() - add data to message digest for processing
  * @req: ahash_request handle that was previously initialized with the
@@ -549,14 +600,12 @@ static inline int crypto_ahash_init(struct ahash_request *req)
 static inline int crypto_ahash_update(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct crypto_alg *alg = tfm->base.__crt_alg;
-	unsigned int nbytes = req->nbytes;
-	int ret;
+	struct hash_alg_common *alg = crypto_hash_alg_common(tfm);
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_add(req->nbytes, &hash_get_stat(alg)->hash_tlen);
 
-	crypto_stats_get(alg);
-	ret = crypto_ahash_reqtfm(req)->update(req);
-	crypto_stats_ahash_update(nbytes, ret, alg);
-	return ret;
+	return crypto_hash_errstat(alg, tfm->update(req));
 }
 
 /**
@@ -718,6 +767,8 @@ static inline void ahash_request_set_crypt(struct ahash_request *req,
 struct crypto_shash *crypto_alloc_shash(const char *alg_name, u32 type,
 					u32 mask);
 
+struct crypto_shash *crypto_clone_shash(struct crypto_shash *tfm);
+
 int crypto_has_shash(const char *alg_name, u32 type, u32 mask);
 
 static inline struct crypto_tfm *crypto_shash_tfm(struct crypto_shash *tfm)
diff --git a/include/crypto/internal/acompress.h b/include/crypto/internal/acompress.h
index 978b57a3f4f0..4ac46bafba9d 100644
--- a/include/crypto/internal/acompress.h
+++ b/include/crypto/internal/acompress.h
@@ -12,6 +12,44 @@
 #include <crypto/acompress.h>
 #include <crypto/algapi.h>
 
+/**
+ * struct acomp_alg - asynchronous compression algorithm
+ *
+ * @compress:	Function performs a compress operation
+ * @decompress:	Function performs a de-compress operation
+ * @dst_free:	Frees destination buffer if allocated inside the algorithm
+ * @init:	Initialize the cryptographic transformation object.
+ *		This function is used to initialize the cryptographic
+ *		transformation object. This function is called only once at
+ *		the instantiation time, right after the transformation context
+ *		was allocated. In case the cryptographic hardware has some
+ *		special requirements which need to be handled by software, this
+ *		function shall check for the precise requirement of the
+ *		transformation and put any software fallbacks in place.
+ * @exit:	Deinitialize the cryptographic transformation object. This is a
+ *		counterpart to @init, used to remove various changes set in
+ *		@init.
+ *
+ * @reqsize:	Context size for (de)compression requests
+ * @stat:	Statistics for compress algorithm
+ * @base:	Common crypto API algorithm data structure
+ * @calg:	Cmonn algorithm data structure shared with scomp
+ */
+struct acomp_alg {
+	int (*compress)(struct acomp_req *req);
+	int (*decompress)(struct acomp_req *req);
+	void (*dst_free)(struct scatterlist *dst);
+	int (*init)(struct crypto_acomp *tfm);
+	void (*exit)(struct crypto_acomp *tfm);
+
+	unsigned int reqsize;
+
+	union {
+		struct COMP_ALG_COMMON;
+		struct comp_alg_common calg;
+	};
+};
+
 /*
  * Transform internal helpers.
  */
@@ -31,11 +69,6 @@ static inline void acomp_request_complete(struct acomp_req *req,
 	crypto_request_complete(&req->base, err);
 }
 
-static inline const char *acomp_alg_name(struct crypto_acomp *tfm)
-{
-	return crypto_acomp_tfm(tfm)->__crt_alg->cra_name;
-}
-
 static inline struct acomp_req *__acomp_request_alloc(struct crypto_acomp *tfm)
 {
 	struct acomp_req *req;
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 0b259dbb97af..37edf3f4e8af 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -133,8 +133,6 @@ int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc);
 int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc);
 int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc);
 
-int crypto_init_shash_ops_async(struct crypto_tfm *tfm);
-
 static inline void *crypto_ahash_ctx(struct crypto_ahash *tfm)
 {
 	return crypto_tfm_ctx(crypto_ahash_tfm(tfm));
diff --git a/include/crypto/internal/scompress.h b/include/crypto/internal/scompress.h
index 252cc949d4ee..858fe3965ae3 100644
--- a/include/crypto/internal/scompress.h
+++ b/include/crypto/internal/scompress.h
@@ -9,10 +9,13 @@
 #ifndef _CRYPTO_SCOMP_INT_H
 #define _CRYPTO_SCOMP_INT_H
 
+#include <crypto/acompress.h>
 #include <crypto/algapi.h>
 
 #define SCOMP_SCRATCH_SIZE	131072
 
+struct acomp_req;
+
 struct crypto_scomp {
 	struct crypto_tfm base;
 };
@@ -24,7 +27,9 @@ struct crypto_scomp {
  * @free_ctx:	Function frees context allocated with alloc_ctx
  * @compress:	Function performs a compress operation
  * @decompress:	Function performs a de-compress operation
+ * @stat:	Statistics for compress algorithm
  * @base:	Common crypto API algorithm data structure
+ * @calg:	Cmonn algorithm data structure shared with acomp
  */
 struct scomp_alg {
 	void *(*alloc_ctx)(struct crypto_scomp *tfm);
@@ -35,7 +40,11 @@ struct scomp_alg {
 	int (*decompress)(struct crypto_scomp *tfm, const u8 *src,
 			  unsigned int slen, u8 *dst, unsigned int *dlen,
 			  void *ctx);
-	struct crypto_alg base;
+
+	union {
+		struct COMP_ALG_COMMON;
+		struct comp_alg_common calg;
+	};
 };
 
 static inline struct scomp_alg *__crypto_scomp_alg(struct crypto_alg *alg)
@@ -90,10 +99,6 @@ static inline int crypto_scomp_decompress(struct crypto_scomp *tfm,
 						 ctx);
 }
 
-int crypto_init_scomp_ops_async(struct crypto_tfm *tfm);
-struct acomp_req *crypto_acomp_scomp_alloc_ctx(struct acomp_req *req);
-void crypto_acomp_scomp_free_ctx(struct acomp_req *req);
-
 /**
  * crypto_register_scomp() -- Register synchronous compression algorithm
  *
diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h
index 33ff32878802..1988e24a0d1d 100644
--- a/include/crypto/kpp.h
+++ b/include/crypto/kpp.h
@@ -8,7 +8,11 @@
 
 #ifndef _CRYPTO_KPP_
 #define _CRYPTO_KPP_
+
+#include <linux/atomic.h>
+#include <linux/container_of.h>
 #include <linux/crypto.h>
+#include <linux/slab.h>
 
 /**
  * struct kpp_request
@@ -47,6 +51,20 @@ struct crypto_kpp {
 	struct crypto_tfm base;
 };
 
+/*
+ * struct crypto_istat_kpp - statistics for KPP algorithm
+ * @setsecret_cnt:		number of setsecrey operation
+ * @generate_public_key_cnt:	number of generate_public_key operation
+ * @compute_shared_secret_cnt:	number of compute_shared_secret operation
+ * @err_cnt:			number of error for KPP requests
+ */
+struct crypto_istat_kpp {
+	atomic64_t setsecret_cnt;
+	atomic64_t generate_public_key_cnt;
+	atomic64_t compute_shared_secret_cnt;
+	atomic64_t err_cnt;
+};
+
 /**
  * struct kpp_alg - generic key-agreement protocol primitives
  *
@@ -69,6 +87,7 @@ struct crypto_kpp {
  * @exit:		Undo everything @init did.
  *
  * @base:		Common crypto API algorithm data structure
+ * @stat:		Statistics for KPP algorithm
  */
 struct kpp_alg {
 	int (*set_secret)(struct crypto_kpp *tfm, const void *buffer,
@@ -81,6 +100,10 @@ struct kpp_alg {
 	int (*init)(struct crypto_kpp *tfm);
 	void (*exit)(struct crypto_kpp *tfm);
 
+#ifdef CONFIG_CRYPTO_STATS
+	struct crypto_istat_kpp stat;
+#endif
+
 	struct crypto_alg base;
 };
 
@@ -268,6 +291,26 @@ struct kpp_secret {
 	unsigned short len;
 };
 
+static inline struct crypto_istat_kpp *kpp_get_stat(struct kpp_alg *alg)
+{
+#ifdef CONFIG_CRYPTO_STATS
+	return &alg->stat;
+#else
+	return NULL;
+#endif
+}
+
+static inline int crypto_kpp_errstat(struct kpp_alg *alg, int err)
+{
+	if (!IS_ENABLED(CONFIG_CRYPTO_STATS))
+		return err;
+
+	if (err && err != -EINPROGRESS && err != -EBUSY)
+		atomic64_inc(&kpp_get_stat(alg)->err_cnt);
+
+	return err;
+}
+
 /**
  * crypto_kpp_set_secret() - Invoke kpp operation
  *
@@ -287,13 +330,11 @@ static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm,
 					const void *buffer, unsigned int len)
 {
 	struct kpp_alg *alg = crypto_kpp_alg(tfm);
-	struct crypto_alg *calg = tfm->base.__crt_alg;
-	int ret;
 
-	crypto_stats_get(calg);
-	ret = alg->set_secret(tfm, buffer, len);
-	crypto_stats_kpp_set_secret(calg, ret);
-	return ret;
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_inc(&kpp_get_stat(alg)->setsecret_cnt);
+
+	return crypto_kpp_errstat(alg, alg->set_secret(tfm, buffer, len));
 }
 
 /**
@@ -313,13 +354,11 @@ static inline int crypto_kpp_generate_public_key(struct kpp_request *req)
 {
 	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
 	struct kpp_alg *alg = crypto_kpp_alg(tfm);
-	struct crypto_alg *calg = tfm->base.__crt_alg;
-	int ret;
 
-	crypto_stats_get(calg);
-	ret = alg->generate_public_key(req);
-	crypto_stats_kpp_generate_public_key(calg, ret);
-	return ret;
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_inc(&kpp_get_stat(alg)->generate_public_key_cnt);
+
+	return crypto_kpp_errstat(alg, alg->generate_public_key(req));
 }
 
 /**
@@ -336,13 +375,11 @@ static inline int crypto_kpp_compute_shared_secret(struct kpp_request *req)
 {
 	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
 	struct kpp_alg *alg = crypto_kpp_alg(tfm);
-	struct crypto_alg *calg = tfm->base.__crt_alg;
-	int ret;
 
-	crypto_stats_get(calg);
-	ret = alg->compute_shared_secret(req);
-	crypto_stats_kpp_compute_shared_secret(calg, ret);
-	return ret;
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS))
+		atomic64_inc(&kpp_get_stat(alg)->compute_shared_secret_cnt);
+
+	return crypto_kpp_errstat(alg, alg->compute_shared_secret(req));
 }
 
 /**
diff --git a/include/crypto/rng.h b/include/crypto/rng.h
index 17bb3673d3c1..6abe5102e5fb 100644
--- a/include/crypto/rng.h
+++ b/include/crypto/rng.h
@@ -9,10 +9,26 @@
 #ifndef _CRYPTO_RNG_H
 #define _CRYPTO_RNG_H
 
+#include <linux/atomic.h>
+#include <linux/container_of.h>
 #include <linux/crypto.h>
 
 struct crypto_rng;
 
+/*
+ * struct crypto_istat_rng: statistics for RNG algorithm
+ * @generate_cnt:	number of RNG generate requests
+ * @generate_tlen:	total data size of generated data by the RNG
+ * @seed_cnt:		number of times the RNG was seeded
+ * @err_cnt:		number of error for RNG requests
+ */
+struct crypto_istat_rng {
+	atomic64_t generate_cnt;
+	atomic64_t generate_tlen;
+	atomic64_t seed_cnt;
+	atomic64_t err_cnt;
+};
+
 /**
  * struct rng_alg - random number generator definition
  *
@@ -30,6 +46,7 @@ struct crypto_rng;
  *		size of the seed is defined with @seedsize .
  * @set_ent:	Set entropy that would otherwise be obtained from
  *		entropy source.  Internal use only.
+ * @stat:	Statistics for rng algorithm
  * @seedsize:	The seed size required for a random number generator
  *		initialization defined with this variable. Some
  *		random number generators does not require a seed
@@ -46,6 +63,10 @@ struct rng_alg {
 	void (*set_ent)(struct crypto_rng *tfm, const u8 *data,
 			unsigned int len);
 
+#ifdef CONFIG_CRYPTO_STATS
+	struct crypto_istat_rng stat;
+#endif
+
 	unsigned int seedsize;
 
 	struct crypto_alg base;
@@ -94,6 +115,11 @@ static inline struct crypto_tfm *crypto_rng_tfm(struct crypto_rng *tfm)
 	return &tfm->base;
 }
 
+static inline struct rng_alg *__crypto_rng_alg(struct crypto_alg *alg)
+{
+	return container_of(alg, struct rng_alg, base);
+}
+
 /**
  * crypto_rng_alg - obtain name of RNG
  * @tfm: cipher handle
@@ -104,8 +130,7 @@ static inline struct crypto_tfm *crypto_rng_tfm(struct crypto_rng *tfm)
  */
 static inline struct rng_alg *crypto_rng_alg(struct crypto_rng *tfm)
 {
-	return container_of(crypto_rng_tfm(tfm)->__crt_alg,
-			    struct rng_alg, base);
+	return __crypto_rng_alg(crypto_rng_tfm(tfm)->__crt_alg);
 }
 
 /**
@@ -119,6 +144,26 @@ static inline void crypto_free_rng(struct crypto_rng *tfm)
 	crypto_destroy_tfm(tfm, crypto_rng_tfm(tfm));
 }
 
+static inline struct crypto_istat_rng *rng_get_stat(struct rng_alg *alg)
+{
+#ifdef CONFIG_CRYPTO_STATS
+	return &alg->stat;
+#else
+	return NULL;
+#endif
+}
+
+static inline int crypto_rng_errstat(struct rng_alg *alg, int err)
+{
+	if (!IS_ENABLED(CONFIG_CRYPTO_STATS))
+		return err;
+
+	if (err && err != -EINPROGRESS && err != -EBUSY)
+		atomic64_inc(&rng_get_stat(alg)->err_cnt);
+
+	return err;
+}
+
 /**
  * crypto_rng_generate() - get random number
  * @tfm: cipher handle
@@ -137,13 +182,17 @@ static inline int crypto_rng_generate(struct crypto_rng *tfm,
 				      const u8 *src, unsigned int slen,
 				      u8 *dst, unsigned int dlen)
 {
-	struct crypto_alg *alg = tfm->base.__crt_alg;
-	int ret;
+	struct rng_alg *alg = crypto_rng_alg(tfm);
+
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS)) {
+		struct crypto_istat_rng *istat = rng_get_stat(alg);
+
+		atomic64_inc(&istat->generate_cnt);
+		atomic64_add(dlen, &istat->generate_tlen);
+	}
 
-	crypto_stats_get(alg);
-	ret = crypto_rng_alg(tfm)->generate(tfm, src, slen, dst, dlen);
-	crypto_stats_rng_generate(alg, dlen, ret);
-	return ret;
+	return crypto_rng_errstat(alg,
+				  alg->generate(tfm, src, slen, dst, dlen));
 }
 
 /**
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index 39f5b67c3069..080d1ba3611d 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -8,6 +8,7 @@
 #ifndef _CRYPTO_SKCIPHER_H
 #define _CRYPTO_SKCIPHER_H
 
+#include <linux/atomic.h>
 #include <linux/container_of.h>
 #include <linux/crypto.h>
 #include <linux/slab.h>
@@ -48,6 +49,22 @@ struct crypto_sync_skcipher {
 	struct crypto_skcipher base;
 };
 
+/*
+ * struct crypto_istat_cipher - statistics for cipher algorithm
+ * @encrypt_cnt:	number of encrypt requests
+ * @encrypt_tlen:	total data size handled by encrypt requests
+ * @decrypt_cnt:	number of decrypt requests
+ * @decrypt_tlen:	total data size handled by decrypt requests
+ * @err_cnt:		number of error for cipher requests
+ */
+struct crypto_istat_cipher {
+	atomic64_t encrypt_cnt;
+	atomic64_t encrypt_tlen;
+	atomic64_t decrypt_cnt;
+	atomic64_t decrypt_tlen;
+	atomic64_t err_cnt;
+};
+
 /**
  * struct skcipher_alg - symmetric key cipher definition
  * @min_keysize: Minimum key size supported by the transformation. This is the
@@ -101,6 +118,7 @@ struct crypto_sync_skcipher {
  * @walksize: Equal to the chunk size except in cases where the algorithm is
  * 	      considerably more efficient if it can operate on multiple chunks
  * 	      in parallel. Should be a multiple of chunksize.
+ * @stat: Statistics for cipher algorithm
  * @base: Definition of a generic crypto algorithm.
  *
  * All fields except @ivsize are mandatory and must be filled.
@@ -119,6 +137,10 @@ struct skcipher_alg {
 	unsigned int chunksize;
 	unsigned int walksize;
 
+#ifdef CONFIG_CRYPTO_STATS
+	struct crypto_istat_cipher stat;
+#endif
+
 	struct crypto_alg base;
 };
 
diff --git a/include/crypto/utils.h b/include/crypto/utils.h
new file mode 100644
index 000000000000..acbb917a00c6
--- /dev/null
+++ b/include/crypto/utils.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Cryptographic utilities
+ *
+ * Copyright (c) 2023 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+#ifndef _CRYPTO_UTILS_H
+#define _CRYPTO_UTILS_H
+
+#include <asm/unaligned.h>
+#include <linux/compiler_attributes.h>
+#include <linux/types.h>
+
+void __crypto_xor(u8 *dst, const u8 *src1, const u8 *src2, unsigned int size);
+
+static inline void crypto_xor(u8 *dst, const u8 *src, unsigned int size)
+{
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
+	    __builtin_constant_p(size) &&
+	    (size % sizeof(unsigned long)) == 0) {
+		unsigned long *d = (unsigned long *)dst;
+		unsigned long *s = (unsigned long *)src;
+		unsigned long l;
+
+		while (size > 0) {
+			l = get_unaligned(d) ^ get_unaligned(s++);
+			put_unaligned(l, d++);
+			size -= sizeof(unsigned long);
+		}
+	} else {
+		__crypto_xor(dst, dst, src, size);
+	}
+}
+
+static inline void crypto_xor_cpy(u8 *dst, const u8 *src1, const u8 *src2,
+				  unsigned int size)
+{
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
+	    __builtin_constant_p(size) &&
+	    (size % sizeof(unsigned long)) == 0) {
+		unsigned long *d = (unsigned long *)dst;
+		unsigned long *s1 = (unsigned long *)src1;
+		unsigned long *s2 = (unsigned long *)src2;
+		unsigned long l;
+
+		while (size > 0) {
+			l = get_unaligned(s1++) ^ get_unaligned(s2++);
+			put_unaligned(l, d++);
+			size -= sizeof(unsigned long);
+		}
+	} else {
+		__crypto_xor(dst, src1, src2, size);
+	}
+}
+
+noinline unsigned long __crypto_memneq(const void *a, const void *b, size_t size);
+
+/**
+ * crypto_memneq - Compare two areas of memory without leaking
+ *		   timing information.
+ *
+ * @a: One area of memory
+ * @b: Another area of memory
+ * @size: The size of the area.
+ *
+ * Returns 0 when data is equal, 1 otherwise.
+ */
+static inline int crypto_memneq(const void *a, const void *b, size_t size)
+{
+	return __crypto_memneq(a, b, size) != 0UL ? 1 : 0;
+}
+
+#endif	/* _CRYPTO_UTILS_H */
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index bb1d9b0e1647..fa310ac1db59 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -12,26 +12,10 @@
 #ifndef _LINUX_CRYPTO_H
 #define _LINUX_CRYPTO_H
 
-#include <linux/atomic.h>
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/bug.h>
+#include <linux/completion.h>
 #include <linux/refcount.h>
 #include <linux/slab.h>
-#include <linux/completion.h>
-
-/*
- * Autoloaded crypto modules should only use a prefixed name to avoid allowing
- * arbitrary modules to be loaded. Loading from userspace may still need the
- * unprefixed names, so retains those aliases as well.
- * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3
- * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro
- * expands twice on the same line. Instead, use a separate base name for the
- * alias.
- */
-#define MODULE_ALIAS_CRYPTO(name)	\
-		__MODULE_INFO(alias, alias_userspace, name);	\
-		__MODULE_INFO(alias, alias_crypto, "crypto-" name)
+#include <linux/types.h>
 
 /*
  * Algorithm masks and types.
@@ -171,10 +155,9 @@
 
 #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN)))
 
-struct scatterlist;
-struct crypto_async_request;
 struct crypto_tfm;
 struct crypto_type;
+struct module;
 
 typedef void (*crypto_completion_t)(void *req, int err);
 
@@ -275,116 +258,6 @@ struct compress_alg {
 			      unsigned int slen, u8 *dst, unsigned int *dlen);
 };
 
-#ifdef CONFIG_CRYPTO_STATS
-/*
- * struct crypto_istat_aead - statistics for AEAD algorithm
- * @encrypt_cnt:	number of encrypt requests
- * @encrypt_tlen:	total data size handled by encrypt requests
- * @decrypt_cnt:	number of decrypt requests
- * @decrypt_tlen:	total data size handled by decrypt requests
- * @err_cnt:		number of error for AEAD requests
- */
-struct crypto_istat_aead {
-	atomic64_t encrypt_cnt;
-	atomic64_t encrypt_tlen;
-	atomic64_t decrypt_cnt;
-	atomic64_t decrypt_tlen;
-	atomic64_t err_cnt;
-};
-
-/*
- * struct crypto_istat_akcipher - statistics for akcipher algorithm
- * @encrypt_cnt:	number of encrypt requests
- * @encrypt_tlen:	total data size handled by encrypt requests
- * @decrypt_cnt:	number of decrypt requests
- * @decrypt_tlen:	total data size handled by decrypt requests
- * @verify_cnt:		number of verify operation
- * @sign_cnt:		number of sign requests
- * @err_cnt:		number of error for akcipher requests
- */
-struct crypto_istat_akcipher {
-	atomic64_t encrypt_cnt;
-	atomic64_t encrypt_tlen;
-	atomic64_t decrypt_cnt;
-	atomic64_t decrypt_tlen;
-	atomic64_t verify_cnt;
-	atomic64_t sign_cnt;
-	atomic64_t err_cnt;
-};
-
-/*
- * struct crypto_istat_cipher - statistics for cipher algorithm
- * @encrypt_cnt:	number of encrypt requests
- * @encrypt_tlen:	total data size handled by encrypt requests
- * @decrypt_cnt:	number of decrypt requests
- * @decrypt_tlen:	total data size handled by decrypt requests
- * @err_cnt:		number of error for cipher requests
- */
-struct crypto_istat_cipher {
-	atomic64_t encrypt_cnt;
-	atomic64_t encrypt_tlen;
-	atomic64_t decrypt_cnt;
-	atomic64_t decrypt_tlen;
-	atomic64_t err_cnt;
-};
-
-/*
- * struct crypto_istat_compress - statistics for compress algorithm
- * @compress_cnt:	number of compress requests
- * @compress_tlen:	total data size handled by compress requests
- * @decompress_cnt:	number of decompress requests
- * @decompress_tlen:	total data size handled by decompress requests
- * @err_cnt:		number of error for compress requests
- */
-struct crypto_istat_compress {
-	atomic64_t compress_cnt;
-	atomic64_t compress_tlen;
-	atomic64_t decompress_cnt;
-	atomic64_t decompress_tlen;
-	atomic64_t err_cnt;
-};
-
-/*
- * struct crypto_istat_hash - statistics for has algorithm
- * @hash_cnt:		number of hash requests
- * @hash_tlen:		total data size hashed
- * @err_cnt:		number of error for hash requests
- */
-struct crypto_istat_hash {
-	atomic64_t hash_cnt;
-	atomic64_t hash_tlen;
-	atomic64_t err_cnt;
-};
-
-/*
- * struct crypto_istat_kpp - statistics for KPP algorithm
- * @setsecret_cnt:		number of setsecrey operation
- * @generate_public_key_cnt:	number of generate_public_key operation
- * @compute_shared_secret_cnt:	number of compute_shared_secret operation
- * @err_cnt:			number of error for KPP requests
- */
-struct crypto_istat_kpp {
-	atomic64_t setsecret_cnt;
-	atomic64_t generate_public_key_cnt;
-	atomic64_t compute_shared_secret_cnt;
-	atomic64_t err_cnt;
-};
-
-/*
- * struct crypto_istat_rng: statistics for RNG algorithm
- * @generate_cnt:	number of RNG generate requests
- * @generate_tlen:	total data size of generated data by the RNG
- * @seed_cnt:		number of times the RNG was seeded
- * @err_cnt:		number of error for RNG requests
- */
-struct crypto_istat_rng {
-	atomic64_t generate_cnt;
-	atomic64_t generate_tlen;
-	atomic64_t seed_cnt;
-	atomic64_t err_cnt;
-};
-#endif /* CONFIG_CRYPTO_STATS */
-
 #define cra_cipher	cra_u.cipher
 #define cra_compress	cra_u.compress
 
@@ -462,15 +335,6 @@ struct crypto_istat_rng {
  * @cra_refcnt: internally used
  * @cra_destroy: internally used
  *
- * @stats: union of all possible crypto_istat_xxx structures
- * @stats.aead:		statistics for AEAD algorithm
- * @stats.akcipher:	statistics for akcipher algorithm
- * @stats.cipher:	statistics for cipher algorithm
- * @stats.compress:	statistics for compress algorithm
- * @stats.hash:		statistics for hash algorithm
- * @stats.rng:		statistics for rng algorithm
- * @stats.kpp:		statistics for KPP algorithm
- *
  * The struct crypto_alg describes a generic Crypto API algorithm and is common
  * for all of the transformations. Any variable not documented here shall not
  * be used by a cipher implementation as it is internal to the Crypto API.
@@ -502,81 +366,8 @@ struct crypto_alg {
 	void (*cra_destroy)(struct crypto_alg *alg);
 	
 	struct module *cra_module;
-
-#ifdef CONFIG_CRYPTO_STATS
-	union {
-		struct crypto_istat_aead aead;
-		struct crypto_istat_akcipher akcipher;
-		struct crypto_istat_cipher cipher;
-		struct crypto_istat_compress compress;
-		struct crypto_istat_hash hash;
-		struct crypto_istat_rng rng;
-		struct crypto_istat_kpp kpp;
-	} stats;
-#endif /* CONFIG_CRYPTO_STATS */
-
 } CRYPTO_MINALIGN_ATTR;
 
-#ifdef CONFIG_CRYPTO_STATS
-void crypto_stats_init(struct crypto_alg *alg);
-void crypto_stats_get(struct crypto_alg *alg);
-void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret);
-void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret);
-void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg);
-void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg);
-void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg);
-void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg);
-void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg);
-void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg);
-void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg);
-void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg);
-void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret);
-void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret);
-void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret);
-void crypto_stats_rng_seed(struct crypto_alg *alg, int ret);
-void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret);
-void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg);
-void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg);
-#else
-static inline void crypto_stats_init(struct crypto_alg *alg)
-{}
-static inline void crypto_stats_get(struct crypto_alg *alg)
-{}
-static inline void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret)
-{}
-static inline void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret)
-{}
-static inline void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret)
-{}
-static inline void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret)
-{}
-static inline void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret)
-{}
-static inline void crypto_stats_rng_seed(struct crypto_alg *alg, int ret)
-{}
-static inline void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret)
-{}
-static inline void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg)
-{}
-#endif
 /*
  * A helper struct for waiting for completion of async crypto ops
  */
@@ -617,14 +408,6 @@ static inline void crypto_init_wait(struct crypto_wait *wait)
 }
 
 /*
- * Algorithm registration interface.
- */
-int crypto_register_alg(struct crypto_alg *alg);
-void crypto_unregister_alg(struct crypto_alg *alg);
-int crypto_register_algs(struct crypto_alg *algs, int count);
-void crypto_unregister_algs(struct crypto_alg *algs, int count);
-
-/*
  * Algorithm query interface.
  */
 int crypto_has_alg(const char *name, u32 type, u32 mask);
@@ -636,6 +419,7 @@ int crypto_has_alg(const char *name, u32 type, u32 mask);
  */
 
 struct crypto_tfm {
+	refcount_t refcnt;
 
 	u32 crt_flags;
 
@@ -664,8 +448,6 @@ static inline void crypto_free_tfm(struct crypto_tfm *tfm)
 	return crypto_destroy_tfm(tfm, tfm);
 }
 
-int alg_test(const char *driver, const char *alg, u32 type, u32 mask);
-
 /*
  * Transform helpers which query the underlying algorithm.
  */
@@ -679,16 +461,6 @@ static inline const char *crypto_tfm_alg_driver_name(struct crypto_tfm *tfm)
 	return tfm->__crt_alg->cra_driver_name;
 }
 
-static inline int crypto_tfm_alg_priority(struct crypto_tfm *tfm)
-{
-	return tfm->__crt_alg->cra_priority;
-}
-
-static inline u32 crypto_tfm_alg_type(struct crypto_tfm *tfm)
-{
-	return tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK;
-}
-
 static inline unsigned int crypto_tfm_alg_blocksize(struct crypto_tfm *tfm)
 {
 	return tfm->__crt_alg->cra_blocksize;
diff --git a/include/linux/psp-platform-access.h b/include/linux/psp-platform-access.h
new file mode 100644
index 000000000000..75da8f5f7ad8
--- /dev/null
+++ b/include/linux/psp-platform-access.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __PSP_PLATFORM_ACCESS_H
+#define __PSP_PLATFORM_ACCESS_H
+
+#include <linux/psp.h>
+
+enum psp_platform_access_msg {
+	PSP_CMD_NONE = 0x0,
+	PSP_I2C_REQ_BUS_CMD = 0x64,
+};
+
+struct psp_req_buffer_hdr {
+	u32 payload_size;
+	u32 status;
+} __packed;
+
+struct psp_request {
+	struct psp_req_buffer_hdr header;
+	void *buf;
+} __packed;
+
+/**
+ * psp_send_platform_access_msg() - Send a message to control platform features
+ *
+ * This function is intended to be used by drivers outside of ccp to communicate
+ * with the platform.
+ *
+ * Returns:
+ *  0:           success
+ *  -%EBUSY:     mailbox in recovery or in use
+ *  -%ENODEV:    driver not bound with PSP device
+ *  -%ETIMEDOUT: request timed out
+ *  -%EIO:       unknown error (see kernel log)
+ */
+int psp_send_platform_access_msg(enum psp_platform_access_msg, struct psp_request *req);
+
+/**
+ * psp_ring_platform_doorbell() - Ring platform doorbell
+ *
+ * This function is intended to be used by drivers outside of ccp to ring the
+ * platform doorbell with a message.
+ *
+ * Returns:
+ *  0:           success
+ *  -%EBUSY:     mailbox in recovery or in use
+ *  -%ENODEV:    driver not bound with PSP device
+ *  -%ETIMEDOUT: request timed out
+ *  -%EIO:       error will be stored in result argument
+ */
+int psp_ring_platform_doorbell(int msg, u32 *result);
+
+/**
+ * psp_check_platform_access_status() - Checks whether platform features is ready
+ *
+ * This function is intended to be used by drivers outside of ccp to determine
+ * if platform features has initialized.
+ *
+ * Returns:
+ * 0          platform features is ready
+ * -%ENODEV   platform features is not ready or present
+ */
+int psp_check_platform_access_status(void);
+
+#endif /* __PSP_PLATFORM_ACCESS_H */
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 1595088c428b..7fd17e82bab4 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -14,14 +14,6 @@
 
 #include <uapi/linux/psp-sev.h>
 
-#ifdef CONFIG_X86
-#include <linux/mem_encrypt.h>
-
-#define __psp_pa(x)	__sme_pa(x)
-#else
-#define __psp_pa(x)	__pa(x)
-#endif
-
 #define SEV_FW_BLOB_MAX_SIZE	0x4000	/* 16KB */
 
 /**
diff --git a/include/linux/psp.h b/include/linux/psp.h
new file mode 100644
index 000000000000..92e60aeef21e
--- /dev/null
+++ b/include/linux/psp.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __PSP_H
+#define __PSP_H
+
+#ifdef CONFIG_X86
+#include <linux/mem_encrypt.h>
+
+#define __psp_pa(x)	__sme_pa(x)
+#else
+#define __psp_pa(x)	__pa(x)
+#endif
+
+/*
+ * Fields and bits used by most PSP mailboxes
+ *
+ * Note: Some mailboxes (such as SEV) have extra bits or different meanings
+ * and should include an appropriate local definition in their source file.
+ */
+#define PSP_CMDRESP_STS		GENMASK(15, 0)
+#define PSP_CMDRESP_CMD		GENMASK(23, 16)
+#define PSP_CMDRESP_RESERVED	GENMASK(29, 24)
+#define PSP_CMDRESP_RECOVERY	BIT(30)
+#define PSP_CMDRESP_RESP	BIT(31)
+
+#define PSP_DRBL_MSG		PSP_CMDRESP_CMD
+#define PSP_DRBL_RING		BIT(0)
+
+#endif /* __PSP_H */
diff --git a/kernel/padata.c b/kernel/padata.c
index e007b8a4b738..222d60195de6 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -491,7 +491,7 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
 		return;
 
 	/* Ensure at least one thread when size < min_chunk. */
-	nworks = max(job->size / job->min_chunk, 1ul);
+	nworks = max(job->size / max(job->min_chunk, job->align), 1ul);
 	nworks = min(nworks, job->max_threads);
 
 	if (nworks == 1) {
@@ -967,7 +967,7 @@ static const struct sysfs_ops padata_sysfs_ops = {
 	.store = padata_sysfs_store,
 };
 
-static struct kobj_type padata_attr_type = {
+static const struct kobj_type padata_attr_type = {
 	.sysfs_ops = &padata_sysfs_ops,
 	.default_groups = padata_default_groups,
 	.release = padata_sysfs_release,
diff --git a/lib/crypto/utils.c b/lib/crypto/utils.c
index 53230ab1b195..c852c7151b0a 100644
--- a/lib/crypto/utils.c
+++ b/lib/crypto/utils.c
@@ -6,7 +6,7 @@
  */
 
 #include <asm/unaligned.h>
-#include <crypto/algapi.h>
+#include <crypto/utils.h>
 #include <linux/module.h>
 
 /*