Merge tag 'v6.9-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
"API:

- Avoid unnecessary copying in scomp for trivial SG lists

Algorithms:

- Optimise NEON CCM implementation on ARM64

Drivers:

- Add queue stop/query debugfs support in hisilicon/qm

- Intel qat updates and cleanups"

* tag 'v6.9-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (79 commits)
Revert "crypto: remove CONFIG_CRYPTO_STATS"
crypto: scomp - remove memcpy if sg_nents is 1 and pages are lowmem
crypto: tcrypt - add ffdhe2048(dh) test
crypto: iaa - fix the missing CRYPTO_ALG_ASYNC in cra_flags
crypto: hisilicon/zip - fix the missing CRYPTO_ALG_ASYNC in cra_flags
hwrng: hisi - use dev_err_probe
MAINTAINERS: Remove T Ambarus from few mchp entries
crypto: iaa - Fix comp/decomp delay statistics
crypto: iaa - Fix async_disable descriptor leak
dt-bindings: rng: atmel,at91-trng: add sam9x7 TRNG
dt-bindings: crypto: add sam9x7 in Atmel TDES
dt-bindings: crypto: add sam9x7 in Atmel SHA
dt-bindings: crypto: add sam9x7 in Atmel AES
crypto: remove CONFIG_CRYPTO_STATS
crypto: dh - Make public key test FIPS-only
crypto: rockchip - fix to check return value
crypto: jitter - fix CRYPTO_JITTERENTROPY help text
crypto: qat - make ring to service map common for QAT GEN4
crypto: qat - fix ring to service map for dcc in 420xx
crypto: qat - fix ring to service map for dcc in 4xxx
...

Documentation/ABI/testing/debugfs-driver-qat

···
 			<N>: Number of Compress and Verify (CnV) errors and type
 			     of the last CnV error detected by Acceleration
 			     Engine N.
+
+What:		/sys/kernel/debug/qat_<device>_<BDF>/heartbeat/inject_error
+Date:		March 2024
+KernelVersion:	6.8
+Contact:	[e-mail]
+Description:	(WO) Write to inject an error that simulates an heartbeat
+		failure. This is to be used for testing purposes.
+
+		After writing this file, the driver stops arbitration on a
+		random engine and disables the fetching of heartbeat counters.
+		If a workload is running on the device, a job submitted to the
+		accelerator might not get a response and a read of the
+		`heartbeat/status` attribute might report -1, i.e. device
+		unresponsive.
+		The error is unrecoverable thus the device must be restarted to
+		restore its functionality.
+
+		This attribute is available only when the kernel is built with
+		CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION=y.
+
+		A write of 1 enables error injection.
+
+		The following example shows how to enable error injection::
+
+			# cd /sys/kernel/debug/qat_<device>_<BDF>
+			# echo 1 > heartbeat/inject_error

Documentation/ABI/testing/debugfs-hisi-hpre

···
 		node is used to show the change of the qm register values. This
 		node can be help users to check the change of register values.
 
+What:		/sys/kernel/debug/hisi_hpre/<bdf>/qm/qm_state
+Date:		Jan 2024
+Contact:	[e-mail]
+Description:	Dump the state of the device.
+		0: busy, 1: idle.
+		Only available for PF, and take no other effect on HPRE.
+
+What:		/sys/kernel/debug/hisi_hpre/<bdf>/qm/dev_timeout
+Date:		Feb 2024
+Contact:	[e-mail]
+Description:	Set the wait time when stop queue fails. Available for both PF
+		and VF, and take no other effect on HPRE.
+		0: not wait(default), others value: wait dev_timeout * 20 microsecond.
+
+What:		/sys/kernel/debug/hisi_hpre/<bdf>/qm/dev_state
+Date:		Feb 2024
+Contact:	[e-mail]
+Description:	Dump the stop queue status of the QM. The default value is 0,
+		if dev_timeout is set, when stop queue fails, the dev_state
+		will return non-zero value. Available for both PF and VF,
+		and take no other effect on HPRE.
+
 What:		/sys/kernel/debug/hisi_hpre/<bdf>/hpre_dfx/diff_regs
 Date:		Mar 2022
 Contact:	[e-mail]

Documentation/ABI/testing/debugfs-hisi-sec

···
 		node is used to show the change of the qm register values. This
 		node can be help users to check the change of register values.
 
+What:		/sys/kernel/debug/hisi_sec2/<bdf>/qm/qm_state
+Date:		Jan 2024
+Contact:	[e-mail]
+Description:	Dump the state of the device.
+		0: busy, 1: idle.
+		Only available for PF, and take no other effect on SEC.
+
+What:		/sys/kernel/debug/hisi_sec2/<bdf>/qm/dev_timeout
+Date:		Feb 2024
+Contact:	[e-mail]
+Description:	Set the wait time when stop queue fails. Available for both PF
+		and VF, and take no other effect on SEC.
+		0: not wait(default), others value: wait dev_timeout * 20 microsecond.
+
+What:		/sys/kernel/debug/hisi_sec2/<bdf>/qm/dev_state
+Date:		Feb 2024
+Contact:	[e-mail]
+Description:	Dump the stop queue status of the QM. The default value is 0,
+		if dev_timeout is set, when stop queue fails, the dev_state
+		will return non-zero value. Available for both PF and VF,
+		and take no other effect on SEC.
+
 What:		/sys/kernel/debug/hisi_sec2/<bdf>/sec_dfx/diff_regs
 Date:		Mar 2022
 Contact:	[e-mail]

Documentation/ABI/testing/debugfs-hisi-zip

···
 		node is used to show the change of the qm registers value. This
 		node can be help users to check the change of register values.
 
+What:		/sys/kernel/debug/hisi_zip/<bdf>/qm/qm_state
+Date:		Jan 2024
+Contact:	[e-mail]
+Description:	Dump the state of the device.
+		0: busy, 1: idle.
+		Only available for PF, and take no other effect on ZIP.
+
+What:		/sys/kernel/debug/hisi_zip/<bdf>/qm/dev_timeout
+Date:		Feb 2024
+Contact:	[e-mail]
+Description:	Set the wait time when stop queue fails. Available for both PF
+		and VF, and take no other effect on ZIP.
+		0: not wait(default), others value: wait dev_timeout * 20 microsecond.
+
+What:		/sys/kernel/debug/hisi_zip/<bdf>/qm/dev_state
+Date:		Feb 2024
+Contact:	[e-mail]
+Description:	Dump the stop queue status of the QM. The default value is 0,
+		if dev_timeout is set, when stop queue fails, the dev_state
+		will return non-zero value. Available for both PF and VF,
+		and take no other effect on ZIP.
+
 What:		/sys/kernel/debug/hisi_zip/<bdf>/zip_dfx/diff_regs
 Date:		Mar 2022
 Contact:	[e-mail]

Documentation/ABI/testing/sysfs-driver-qat

···
 			64
 
 		This attribute is only available for qat_4xxx devices.
+
+What:		/sys/bus/pci/devices/<BDF>/qat/auto_reset
+Date:		March 2024
+KernelVersion:	6.8
+Contact:	[e-mail]
+Description:	(RW) Reports the current state of the autoreset feature
+		for a QAT device
+
+		Write to the attribute to enable or disable device auto reset.
+
+		Device auto reset is disabled by default.
+
+		The values are:
+
+		* 1/Yy/on: auto reset enabled. If the device encounters an
+		  unrecoverable error, it will be reset automatically.
+		* 0/Nn/off: auto reset disabled. If the device encounters an
+		  unrecoverable error, it will not be reset.
+
+		This attribute is only available for qat_4xxx devices.

Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml

···
 
 properties:
   compatible:
-    const: atmel,at91sam9g46-aes
+    oneOf:
+      - const: atmel,at91sam9g46-aes
+      - items:
+          - const: microchip,sam9x7-aes
+          - const: atmel,at91sam9g46-aes
 
   reg:
     maxItems: 1

Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml

···
 
 properties:
   compatible:
-    const: atmel,at91sam9g46-sha
+    oneOf:
+      - const: atmel,at91sam9g46-sha
+      - items:
+          - const: microchip,sam9x7-sha
+          - const: atmel,at91sam9g46-sha
 
   reg:
     maxItems: 1

Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml

···
 
 properties:
   compatible:
-    const: atmel,at91sam9g46-tdes
+    oneOf:
+      - const: atmel,at91sam9g46-tdes
+      - items:
+          - const: microchip,sam9x7-tdes
+          - const: atmel,at91sam9g46-tdes
 
   reg:
     maxItems: 1

Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml

···
     items:
       - enum:
           - qcom,sa8775p-inline-crypto-engine
+          - qcom,sc7180-inline-crypto-engine
           - qcom,sm8450-inline-crypto-engine
           - qcom,sm8550-inline-crypto-engine
           - qcom,sm8650-inline-crypto-engine

Documentation/devicetree/bindings/crypto/qcom-qce.yaml

···
       - items:
           - enum:
               - qcom,sc7280-qce
+              - qcom,sm6350-qce
               - qcom,sm8250-qce
               - qcom,sm8350-qce
               - qcom,sm8450-qce

Documentation/devicetree/bindings/rng/atmel,at91-trng.yaml

···
           - enum:
               - microchip,sama7g5-trng
           - const: atmel,at91sam9g45-trng
+      - items:
+          - enum:
+              - microchip,sam9x7-trng
+          - const: microchip,sam9x60-trng
 
   clocks:
     maxItems: 1

MAINTAINERS

···
 M:	Paulo Flabiano Smorigo <[e-mail]>
 L:	[e-mail]
 S:	Supported
-F:	drivers/crypto/vmx/Kconfig
-F:	drivers/crypto/vmx/Makefile
-F:	drivers/crypto/vmx/aes*
-F:	drivers/crypto/vmx/ghash*
-F:	drivers/crypto/vmx/ppc-xlate.pl
-F:	drivers/crypto/vmx/vmx.c
+F:	arch/powerpc/crypto/Kconfig
+F:	arch/powerpc/crypto/Makefile
+F:	arch/powerpc/crypto/aes.c
+F:	arch/powerpc/crypto/aes_cbc.c
+F:	arch/powerpc/crypto/aes_ctr.c
+F:	arch/powerpc/crypto/aes_xts.c
+F:	arch/powerpc/crypto/aesp8-ppc.*
+F:	arch/powerpc/crypto/ghash.c
+F:	arch/powerpc/crypto/ghashp8-ppc.pl
+F:	arch/powerpc/crypto/ppc-xlate.pl
+F:	arch/powerpc/crypto/vmx.c
 
 IBM ServeRAID RAID DRIVER
 S:	Orphan
···
 F:	drivers/*/*pasemi*
 F:	drivers/char/tpm/tpm_ibmvtpm*
 F:	drivers/crypto/nx/
-F:	drivers/crypto/vmx/
 F:	drivers/i2c/busses/i2c-opal.c
 F:	drivers/net/ethernet/ibm/ibmveth.*
 F:	drivers/net/ethernet/ibm/ibmvnic.*
···
 
 MICROCHIP AT91 DMA DRIVERS
 M:	Ludovic Desroches <[e-mail]>
-M:	Tudor Ambarus <[e-mail]>
 L:	[e-mail] (moderated for non-subscribers)
 L:	[e-mail]
 S:	Supported
···
 F:	drivers/media/platform/microchip/microchip-csi2dc.c
 
 MICROCHIP ECC DRIVER
-M:	Tudor Ambarus <[e-mail]>
 L:	[e-mail]
-S:	Maintained
+S:	Orphan
 F:	drivers/crypto/atmel-ecc.*
 
 MICROCHIP EIC DRIVER
···
 F:	drivers/mmc/host/atmel-mci.c
 
 MICROCHIP NAND DRIVER
-M:	Tudor Ambarus <[e-mail]>
 L:	[e-mail]
-S:	Supported
+S:	Orphan
 F:	Documentation/devicetree/bindings/mtd/atmel-nand.txt
 F:	drivers/mtd/nand/raw/atmel/*
 

arch/arm/crypto/sha256_glue.c

···
 
 #include "sha256_glue.h"
 
-asmlinkage void sha256_block_data_order(u32 *digest, const void *data,
-					unsigned int num_blks);
+asmlinkage void sha256_block_data_order(struct sha256_state *state,
+					const u8 *data, int num_blks);
 
 int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data,
 			     unsigned int len)
···
 	/* make sure casting to sha256_block_fn() is safe */
 	BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0);
 
-	return sha256_base_do_update(desc, data, len,
-				(sha256_block_fn *)sha256_block_data_order);
+	return sha256_base_do_update(desc, data, len, sha256_block_data_order);
 }
 EXPORT_SYMBOL(crypto_sha256_arm_update);
 
 static int crypto_sha256_arm_final(struct shash_desc *desc, u8 *out)
 {
-	sha256_base_do_finalize(desc,
-				(sha256_block_fn *)sha256_block_data_order);
+	sha256_base_do_finalize(desc, sha256_block_data_order);
 	return sha256_base_finish(desc, out);
 }
 
 int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data,
 			    unsigned int len, u8 *out)
 {
-	sha256_base_do_update(desc, data, len,
-			      (sha256_block_fn *)sha256_block_data_order);
+	sha256_base_do_update(desc, data, len, sha256_block_data_order);
 	return crypto_sha256_arm_final(desc, out);
 }
 EXPORT_SYMBOL(crypto_sha256_arm_finup);

arch/arm/crypto/sha512-glue.c

···
 MODULE_ALIAS_CRYPTO("sha384-arm");
 MODULE_ALIAS_CRYPTO("sha512-arm");
 
-asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks);
+asmlinkage void sha512_block_data_order(struct sha512_state *state,
+					u8 const *src, int blocks);
 
 int sha512_arm_update(struct shash_desc *desc, const u8 *data,
 		      unsigned int len)
 {
-	return sha512_base_do_update(desc, data, len,
-		(sha512_block_fn *)sha512_block_data_order);
+	return sha512_base_do_update(desc, data, len, sha512_block_data_order);
 }
 
 static int sha512_arm_final(struct shash_desc *desc, u8 *out)
 {
-	sha512_base_do_finalize(desc,
-		(sha512_block_fn *)sha512_block_data_order);
+	sha512_base_do_finalize(desc, sha512_block_data_order);
 	return sha512_base_finish(desc, out);
 }
 
 int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
 		     unsigned int len, u8 *out)
 {
-	sha512_base_do_update(desc, data, len,
-		(sha512_block_fn *)sha512_block_data_order);
+	sha512_base_do_update(desc, data, len, sha512_block_data_order);
 	return sha512_arm_final(desc, out);
 }
 

arch/arm64/crypto/Kconfig

···
 	depends on ARM64 && KERNEL_MODE_NEON
 	select CRYPTO_ALGAPI
 	select CRYPTO_AES_ARM64_CE
+	select CRYPTO_AES_ARM64_CE_BLK
 	select CRYPTO_AEAD
 	select CRYPTO_LIB_AES
 	help

arch/arm64/crypto/aes-ce-ccm-core.S

···
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
+ * aes-ce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
  *
- * Copyright (C) 2013 - 2017 Linaro Ltd <[e-mail]>
+ * Copyright (C) 2013 - 2017 Linaro Ltd.
+ * Copyright (C) 2024 Google LLC
+ *
+ * Author: Ard Biesheuvel <[e-mail]>
  */
 
 #include <linux/linkage.h>
···
 	.text
 	.arch	armv8-a+crypto
 
-	/*
-	 * u32 ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
-	 *			    u32 macp, u8 const rk[], u32 rounds);
-	 */
-SYM_FUNC_START(ce_aes_ccm_auth_data)
-	ld1	{v0.16b}, [x0]			/* load mac */
-	cbz	w3, 1f
-	sub	w3, w3, #16
-	eor	v1.16b, v1.16b, v1.16b
-0:	ldrb	w7, [x1], #1			/* get 1 byte of input */
-	subs	w2, w2, #1
-	add	w3, w3, #1
-	ins	v1.b[0], w7
-	ext	v1.16b, v1.16b, v1.16b, #1	/* rotate in the input bytes */
-	beq	8f				/* out of input? */
-	cbnz	w3, 0b
-	eor	v0.16b, v0.16b, v1.16b
-1:	ld1	{v3.4s}, [x4]			/* load first round key */
-	prfm	pldl1strm, [x1]
-	cmp	w5, #12				/* which key size? */
-	add	x6, x4, #16
-	sub	w7, w5, #2			/* modified # of rounds */
-	bmi	2f
-	bne	5f
-	mov	v5.16b, v3.16b
-	b	4f
-2:	mov	v4.16b, v3.16b
-	ld1	{v5.4s}, [x6], #16		/* load 2nd round key */
-3:	aese	v0.16b, v4.16b
-	aesmc	v0.16b, v0.16b
-4:	ld1	{v3.4s}, [x6], #16		/* load next round key */
-	aese	v0.16b, v5.16b
-	aesmc	v0.16b, v0.16b
-5:	ld1	{v4.4s}, [x6], #16		/* load next round key */
-	subs	w7, w7, #3
-	aese	v0.16b, v3.16b
-	aesmc	v0.16b, v0.16b
-	ld1	{v5.4s}, [x6], #16		/* load next round key */
-	bpl	3b
-	aese	v0.16b, v4.16b
-	subs	w2, w2, #16			/* last data? */
-	eor	v0.16b, v0.16b, v5.16b		/* final round */
-	bmi	6f
-	ld1	{v1.16b}, [x1], #16		/* load next input block */
-	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
-	bne	1b
-6:	st1	{v0.16b}, [x0]			/* store mac */
-	beq	10f
-	adds	w2, w2, #16
-	beq	10f
-	mov	w3, w2
-7:	ldrb	w7, [x1], #1
-	umov	w6, v0.b[0]
-	eor	w6, w6, w7
-	strb	w6, [x0], #1
-	subs	w2, w2, #1
-	beq	10f
-	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
-	b	7b
-8:	cbz	w3, 91f
-	mov	w7, w3
-	add	w3, w3, #16
-9:	ext	v1.16b, v1.16b, v1.16b, #1
-	adds	w7, w7, #1
-	bne	9b
-91:	eor	v0.16b, v0.16b, v1.16b
-	st1	{v0.16b}, [x0]
-10:	mov	w0, w3
-	ret
-SYM_FUNC_END(ce_aes_ccm_auth_data)
+	.macro	load_round_keys, rk, nr, tmp
+	sub	w\tmp, \nr, #10
+	add	\tmp, \rk, w\tmp, sxtw #4
+	ld1	{v10.4s-v13.4s}, [\rk]
+	ld1	{v14.4s-v17.4s}, [\tmp], #64
+	ld1	{v18.4s-v21.4s}, [\tmp], #64
+	ld1	{v3.4s-v5.4s}, [\tmp]
+	.endm
 
-	/*
-	 * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[],
-	 * 			 u32 rounds);
-	 */
-SYM_FUNC_START(ce_aes_ccm_final)
-	ld1	{v3.4s}, [x2], #16		/* load first round key */
-	ld1	{v0.16b}, [x0]			/* load mac */
-	cmp	w3, #12				/* which key size? */
-	sub	w3, w3, #2			/* modified # of rounds */
-	ld1	{v1.16b}, [x1]			/* load 1st ctriv */
-	bmi	0f
-	bne	3f
-	mov	v5.16b, v3.16b
-	b	2f
-0:	mov	v4.16b, v3.16b
-1:	ld1	{v5.4s}, [x2], #16		/* load next round key */
-	aese	v0.16b, v4.16b
-	aesmc	v0.16b, v0.16b
-	aese	v1.16b, v4.16b
-	aesmc	v1.16b, v1.16b
-2:	ld1	{v3.4s}, [x2], #16		/* load next round key */
-	aese	v0.16b, v5.16b
-	aesmc	v0.16b, v0.16b
-	aese	v1.16b, v5.16b
-	aesmc	v1.16b, v1.16b
-3:	ld1	{v4.4s}, [x2], #16		/* load next round key */
-	subs	w3, w3, #3
-	aese	v0.16b, v3.16b
-	aesmc	v0.16b, v0.16b
-	aese	v1.16b, v3.16b
-	aesmc	v1.16b, v1.16b
-	bpl	1b
-	aese	v0.16b, v4.16b
-	aese	v1.16b, v4.16b
-	/* final round key cancels out */
-	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
-	st1	{v0.16b}, [x0]			/* store result */
-	ret
-SYM_FUNC_END(ce_aes_ccm_final)
+	.macro	dround, va, vb, vk
+	aese	\va\().16b, \vk\().16b
+	aesmc	\va\().16b, \va\().16b
+	aese	\vb\().16b, \vk\().16b
+	aesmc	\vb\().16b, \vb\().16b
+	.endm
+
+	.macro	aes_encrypt, va, vb, nr
+	tbz	\nr, #2, .L\@
+	dround	\va, \vb, v10
+	dround	\va, \vb, v11
+	tbz	\nr, #1, .L\@
+	dround	\va, \vb, v12
+	dround	\va, \vb, v13
+.L\@:	.irp	v, v14, v15, v16, v17, v18, v19, v20, v21, v3
+	dround	\va, \vb, \v
+	.endr
+	aese	\va\().16b, v4.16b
+	aese	\vb\().16b, v4.16b
+	.endm
 
 	.macro	aes_ccm_do_crypt,enc
-	cbz	x2, 5f
-	ldr	x8, [x6, #8]			/* load lower ctr */
+	load_round_keys	x3, w4, x10
+
 	ld1	{v0.16b}, [x5]			/* load mac */
+	cbz	x2, ce_aes_ccm_final
+	ldr	x8, [x6, #8]			/* load lower ctr */
 CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 0:	/* outer loop */
 	ld1	{v1.8b}, [x6]			/* load upper ctr */
 	prfm	pldl1strm, [x1]
 	add	x8, x8, #1
 	rev	x9, x8
-	cmp	w4, #12				/* which key size? */
-	sub	w7, w4, #2			/* get modified # of rounds */
 	ins	v1.d[1], x9			/* no carry in lower ctr */
-	ld1	{v3.4s}, [x3]			/* load first round key */
-	add	x10, x3, #16
-	bmi	1f
-	bne	4f
-	mov	v5.16b, v3.16b
-	b	3f
-1:	mov	v4.16b, v3.16b
-	ld1	{v5.4s}, [x10], #16		/* load 2nd round key */
-2:	/* inner loop: 3 rounds, 2x interleaved */
-	aese	v0.16b, v4.16b
-	aesmc	v0.16b, v0.16b
-	aese	v1.16b, v4.16b
-	aesmc	v1.16b, v1.16b
-3:	ld1	{v3.4s}, [x10], #16		/* load next round key */
-	aese	v0.16b, v5.16b
-	aesmc	v0.16b, v0.16b
-	aese	v1.16b, v5.16b
-	aesmc	v1.16b, v1.16b
-4:	ld1	{v4.4s}, [x10], #16		/* load next round key */
-	subs	w7, w7, #3
-	aese	v0.16b, v3.16b
-	aesmc	v0.16b, v0.16b
-	aese	v1.16b, v3.16b
-	aesmc	v1.16b, v1.16b
-	ld1	{v5.4s}, [x10], #16		/* load next round key */
-	bpl	2b
-	aese	v0.16b, v4.16b
-	aese	v1.16b, v4.16b
+
+	aes_encrypt	v0, v1, w4
+
 	subs	w2, w2, #16
-	bmi	6f				/* partial block? */
+	bmi	ce_aes_ccm_crypt_tail
 	ld1	{v2.16b}, [x1], #16		/* load next input block */
 	.if	\enc == 1
 	eor	v2.16b, v2.16b, v5.16b		/* final round enc+mac */
-	eor	v1.16b, v1.16b, v2.16b		/* xor with crypted ctr */
+	eor	v6.16b, v1.16b, v2.16b		/* xor with crypted ctr */
 	.else
 	eor	v2.16b, v2.16b, v1.16b		/* xor with crypted ctr */
-	eor	v1.16b, v2.16b, v5.16b		/* final round enc */
+	eor	v6.16b, v2.16b, v5.16b		/* final round enc */
 	.endif
 	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
-	st1	{v1.16b}, [x0], #16		/* write output block */
+	st1	{v6.16b}, [x0], #16		/* write output block */
 	bne	0b
 CPU_LE(	rev	x8, x8			)
-	st1	{v0.16b}, [x5]			/* store mac */
 	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
-5:	ret
-
-6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
-	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
+	cbnz	x7, ce_aes_ccm_final
 	st1	{v0.16b}, [x5]			/* store mac */
-	add	w2, w2, #16			/* process partial tail block */
-7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
-	umov	w6, v1.b[0]			/* get top crypted ctr byte */
-	umov	w7, v0.b[0]			/* get top mac byte */
-	.if	\enc == 1
-	eor	w7, w7, w9
-	eor	w9, w9, w6
-	.else
-	eor	w9, w9, w6
-	eor	w7, w7, w9
-	.endif
-	strb	w9, [x0], #1			/* store out byte */
-	strb	w7, [x5], #1			/* store mac byte */
-	subs	w2, w2, #1
-	beq	5b
-	ext	v0.16b, v0.16b, v0.16b, #1	/* shift out mac byte */
-	ext	v1.16b, v1.16b, v1.16b, #1	/* shift out ctr byte */
-	b	7b
+	ret
 	.endm
+
+SYM_FUNC_START_LOCAL(ce_aes_ccm_crypt_tail)
+	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
+	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
+
+	add	x1, x1, w2, sxtw		/* rewind the input pointer (w2 < 0) */
+	add	x0, x0, w2, sxtw		/* rewind the output pointer */
+
+	adr_l	x8, .Lpermute			/* load permute vectors */
+	add	x9, x8, w2, sxtw
+	sub	x8, x8, w2, sxtw
+	ld1	{v7.16b-v8.16b}, [x9]
+	ld1	{v9.16b}, [x8]
+
+	ld1	{v2.16b}, [x1]			/* load a full block of input */
+	tbl	v1.16b, {v1.16b}, v7.16b	/* move keystream to end of register */
+	eor	v7.16b, v2.16b, v1.16b		/* encrypt partial input block */
+	bif	v2.16b, v7.16b, v22.16b		/* select plaintext */
+	tbx	v7.16b, {v6.16b}, v8.16b	/* insert output from previous iteration */
+	tbl	v2.16b, {v2.16b}, v9.16b	/* copy plaintext to start of v2 */
+	eor	v0.16b, v0.16b, v2.16b		/* fold plaintext into mac */
+
+	st1	{v7.16b}, [x0]			/* store output block */
+	cbz	x7, 0f
+
+SYM_INNER_LABEL(ce_aes_ccm_final, SYM_L_LOCAL)
+	ld1	{v1.16b}, [x7]			/* load 1st ctriv */
+
+	aes_encrypt	v0, v1, w4
+
+	/* final round key cancels out */
+	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
+0:	st1	{v0.16b}, [x5]			/* store result */
+	ret
+SYM_FUNC_END(ce_aes_ccm_crypt_tail)
 
 	/*
 	 * void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
 	 * 			   u8 const rk[], u32 rounds, u8 mac[],
-	 * 			   u8 ctr[]);
+	 * 			   u8 ctr[], u8 const final_iv[]);
 	 * void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
 	 * 			   u8 const rk[], u32 rounds, u8 mac[],
-	 * 			   u8 ctr[]);
+	 * 			   u8 ctr[], u8 const final_iv[]);
 	 */
 SYM_FUNC_START(ce_aes_ccm_encrypt)
+	movi	v22.16b, #255
 	aes_ccm_do_crypt	1
 SYM_FUNC_END(ce_aes_ccm_encrypt)
 
 SYM_FUNC_START(ce_aes_ccm_decrypt)
+	movi	v22.16b, #0
 	aes_ccm_do_crypt	0
 SYM_FUNC_END(ce_aes_ccm_decrypt)
+
+	.section ".rodata", "a"
+	.align	6
+	.fill	15, 1, 0xff
+.Lpermute:
+	.byte	0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7
+	.byte	0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf
+	.fill	15, 1, 0xff

arch/arm64/crypto/aes-ce-ccm-glue.c

···
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
+ * aes-ce-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
  *
- * Copyright (C) 2013 - 2017 Linaro Ltd <[e-mail]>
+ * Copyright (C) 2013 - 2017 Linaro Ltd.
+ * Copyright (C) 2024 Google LLC
+ *
+ * Author: Ard Biesheuvel <[e-mail]>
  */
 
 #include <asm/neon.h>
···
 #include <linux/module.h>
 
 #include "aes-ce-setkey.h"
+
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
 
 static int num_rounds(struct crypto_aes_ctx *ctx)
 {
···
 	return 6 + ctx->key_length / 4;
 }
 
-asmlinkage u32 ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
-				    u32 macp, u32 const rk[], u32 rounds);
+asmlinkage u32 ce_aes_mac_update(u8 const in[], u32 const rk[], int rounds,
+				 int blocks, u8 dg[], int enc_before,
+				 int enc_after);
 
 asmlinkage void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
 				   u32 const rk[], u32 rounds, u8 mac[],
-				   u8 ctr[]);
+				   u8 ctr[], u8 const final_iv[]);
 
 asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
 				   u32 const rk[], u32 rounds, u8 mac[],
-				   u8 ctr[]);
-
-asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[],
-				 u32 rounds);
+				   u8 ctr[], u8 const final_iv[]);
 
 static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
 		      unsigned int key_len)
···
 	return 0;
 }
 
+static u32 ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+				u32 macp, u32 const rk[], u32 rounds)
+{
+	int enc_after = (macp + abytes) % AES_BLOCK_SIZE;
+
+	do {
+		u32 blocks = abytes / AES_BLOCK_SIZE;
+
+		if (macp == AES_BLOCK_SIZE || (!macp && blocks > 0)) {
+			u32 rem = ce_aes_mac_update(in, rk, rounds, blocks, mac,
+						    macp, enc_after);
+			u32 adv = (blocks - rem) * AES_BLOCK_SIZE;
+
+			macp = enc_after ? 0 : AES_BLOCK_SIZE;
+			in += adv;
+			abytes -= adv;
+
+			if (unlikely(rem)) {
+				kernel_neon_end();
+				kernel_neon_begin();
+				macp = 0;
+			}
+		} else {
+			u32 l = min(AES_BLOCK_SIZE - macp, abytes);
+
+			crypto_xor(&mac[macp], in, l);
+			in += l;
+			macp += l;
+			abytes -= l;
+		}
+	} while (abytes > 0);
+
+	return macp;
+}
+
 static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
···
 	struct __packed { __be16 l; __be32 h; u16 len; } ltag;
 	struct scatter_walk walk;
 	u32 len = req->assoclen;
-	u32 macp = 0;
+	u32 macp = AES_BLOCK_SIZE;
 
 	/* prepend the AAD with a length tag */
 	if (len < 0xff00) {
···
 			scatterwalk_start(&walk, sg_next(walk.sg));
 			n = scatterwalk_clamp(&walk, len);
 		}
-		n = min_t(u32, n, SZ_4K); /* yield NEON at least every 4k */
 		p = scatterwalk_map(&walk);
 
 		macp = ce_aes_ccm_auth_data(mac, p, n, macp, ctx->key_enc,
 					    num_rounds(ctx));
 
-		if (len / SZ_4K > (len - n) / SZ_4K) {
-			kernel_neon_end();
-			kernel_neon_begin();
-		}
 		len -= n;
 
 		scatterwalk_unmap(p);
···
 	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
 	struct skcipher_walk walk;
 	u8 __aligned(8) mac[AES_BLOCK_SIZE];
-	u8 buf[AES_BLOCK_SIZE];
+	u8 orig_iv[AES_BLOCK_SIZE];
 	u32 len = req->cryptlen;
 	int err;
 
···
 		return err;
 
 	/* preserve the original iv for the final round */
-	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+	memcpy(orig_iv, req->iv, AES_BLOCK_SIZE);
 
 	err = skcipher_walk_aead_encrypt(&walk, req, false);
+	if (unlikely(err))
+		return err;
 
 	kernel_neon_begin();
 
 	if (req->assoclen)
 		ccm_calculate_auth_mac(req, mac);
 
-	while (walk.nbytes) {
+	do {
 		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
-		bool final = walk.nbytes == walk.total;
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+		u8 buf[AES_BLOCK_SIZE];
+		u8 *final_iv = NULL;
 
-		if (final)
+		if (walk.nbytes == walk.total) {
 			tail = 0;
+			final_iv = orig_iv;
+		}
 
-		ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   walk.nbytes - tail, ctx->key_enc,
-				   num_rounds(ctx), mac, walk.iv);
+		if (unlikely(walk.nbytes < AES_BLOCK_SIZE))
+			src = dst = memcpy(&buf[sizeof(buf) - walk.nbytes],
+					   src, walk.nbytes);
 
-		if (!final)
-			kernel_neon_end();
-		err = skcipher_walk_done(&walk, tail);
-		if (!final)
-			kernel_neon_begin();
-	}
+		ce_aes_ccm_encrypt(dst, src, walk.nbytes - tail,
+				   ctx->key_enc, num_rounds(ctx),
+				   mac, walk.iv, final_iv);
 
-	ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+		if (unlikely(walk.nbytes < AES_BLOCK_SIZE))
+			memcpy(walk.dst.virt.addr, dst, walk.nbytes);
+
+		if (walk.nbytes) {
+			err = skcipher_walk_done(&walk, tail);
+		}
+	} while (walk.nbytes);
 
 	kernel_neon_end();
+
+	if (unlikely(err))
+		return err;
 
 	/* copy authtag to end of dst */
 	scatterwalk_map_and_copy(mac, req->dst, req->assoclen + req->cryptlen,
 				 crypto_aead_authsize(aead), 1);
 
-	return err;
+	return 0;
 }
 
 static int ccm_decrypt(struct aead_request *req)
···
 	unsigned int authsize = crypto_aead_authsize(aead);
 	struct skcipher_walk walk;
 	u8 __aligned(8) mac[AES_BLOCK_SIZE];
-	u8 buf[AES_BLOCK_SIZE];
+	u8 orig_iv[AES_BLOCK_SIZE];
 	u32 len = req->cryptlen - authsize;
 	int err;
 
···
 		return err;
 
 	/* preserve the original iv for the final round */
-	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+	memcpy(orig_iv, req->iv, AES_BLOCK_SIZE);
 
 	err = skcipher_walk_aead_decrypt(&walk, req, false);
+	if (unlikely(err))
+		return err;
 
 	kernel_neon_begin();
 
 	if (req->assoclen)
 		ccm_calculate_auth_mac(req, mac);
 
-	while (walk.nbytes) {
+	do {
 		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
-		bool final = walk.nbytes == walk.total;
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+		u8 buf[AES_BLOCK_SIZE];
+		u8 *final_iv = NULL;
 
-		if (final)
+		if (walk.nbytes == walk.total) {
 			tail = 0;
+			final_iv = orig_iv;
+		}
 
-		ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   walk.nbytes - tail, ctx->key_enc,
-				   num_rounds(ctx), mac, walk.iv);
+		if (unlikely(walk.nbytes < AES_BLOCK_SIZE))
+			src = dst = memcpy(&buf[sizeof(buf) - walk.nbytes],
+					   src, walk.nbytes);
 
-		if (!final)
-			kernel_neon_end();
-		err = skcipher_walk_done(&walk, tail);
-		if (!final)
-			kernel_neon_begin();
-	}
+		ce_aes_ccm_decrypt(dst, src, walk.nbytes - tail,
+				   ctx->key_enc, num_rounds(ctx),
+				   mac, walk.iv, final_iv);
 
-	ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+		if (unlikely(walk.nbytes < AES_BLOCK_SIZE))
+			memcpy(walk.dst.virt.addr, dst, walk.nbytes);
+
+		if (walk.nbytes) {
+			err = skcipher_walk_done(&walk, tail);
+		}
+	} while (walk.nbytes);
 
 	kernel_neon_end();
 
···
 		return err;
 
 	/* compare calculated auth tag with the stored one */
-	scatterwalk_map_and_copy(buf, req->src,
+	scatterwalk_map_and_copy(orig_iv, req->src,
 				 req->assoclen + req->cryptlen - authsize,
 				 authsize, 0);
 
-	if (crypto_memneq(mac, buf, authsize))
+	if (crypto_memneq(mac, orig_iv, authsize))
 		return -EBADMSG;
 	return 0;
 }
···
 module_exit(aes_mod_exit);
 
 MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
-MODULE_AUTHOR("Ard Biesheuvel <[e-mail]>");
+MODULE_AUTHOR("Ard Biesheuvel <[e-mail]>");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_CRYPTO("ccm(aes)");

arch/arm64/crypto/aes-glue.c

···
 
 #ifdef USE_V8_CRYPTO_EXTENSIONS
 module_cpu_feature_match(AES, aes_init);
+EXPORT_SYMBOL_NS(ce_aes_mac_update, CRYPTO_INTERNAL);
 #else
 module_init(aes_init);
 EXPORT_SYMBOL(neon_aes_ecb_encrypt);

arch/powerpc/crypto/Kconfig

···
 	  - Power10 or later
 	  - Little-endian
 
+config CRYPTO_DEV_VMX
+        bool "Support for VMX cryptographic acceleration instructions"
+        depends on PPC64 && VSX
+        help
+          Support for VMX cryptographic acceleration instructions.
+
+config CRYPTO_DEV_VMX_ENCRYPT
+	tristate "Encryption acceleration support on P8 CPU"
+	depends on CRYPTO_DEV_VMX
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_CTR
+	select CRYPTO_GHASH
+	select CRYPTO_XTS
+	default m
+	help
+	  Support for VMX cryptographic acceleration instructions on Power8 CPU.
+	  This module supports acceleration for AES and GHASH in hardware. If you
+	  choose 'M' here, this module will be called vmx-crypto.
+
 endmenu

arch/powerpc/crypto/Makefile

···
 obj-$(CONFIG_CRYPTO_AES_GCM_P10) += aes-gcm-p10-crypto.o
 obj-$(CONFIG_CRYPTO_CHACHA20_P10) += chacha-p10-crypto.o
 obj-$(CONFIG_CRYPTO_POLY1305_P10) += poly1305-p10-crypto.o
+obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-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
···
 aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp10-ppc.o aesp10-ppc.o
 chacha-p10-crypto-y := chacha-p10-glue.o chacha-p10le-8x.o
 poly1305-p10-crypto-y := poly1305-p10-glue.o poly1305-p10le_64.o
+vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o
+
+ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
+override flavour := linux-ppc64le
+else
+ifdef CONFIG_PPC64_ELF_ABI_V2
+override flavour := linux-ppc64-elfv2
+else
+override flavour := linux-ppc64
+endif
+endif
 
 quiet_cmd_perl = PERL    $@
-      cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@
+      cmd_perl = $(PERL) $< $(flavour) > $@
 
-targets += aesp10-ppc.S ghashp10-ppc.S
+targets += aesp10-ppc.S ghashp10-ppc.S aesp8-ppc.S ghashp8-ppc.S
 
 $(obj)/aesp10-ppc.S $(obj)/ghashp10-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
 	$(call if_changed,perl)
 
+$(obj)/aesp8-ppc.S $(obj)/ghashp8-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
+	$(call if_changed,perl)
+
 OBJECT_FILES_NON_STANDARD_aesp10-ppc.o := y
 OBJECT_FILES_NON_STANDARD_ghashp10-ppc.o := y
+OBJECT_FILES_NON_STANDARD_aesp8-ppc.o := y

crypto/Kconfig

···
 
 	  A non-physical non-deterministic ("true") RNG (e.g., an entropy source
 	  compliant with NIST SP800-90B) intended to provide a seed to a
-	  deterministic RNG (e.g.  per NIST SP800-90C).
+	  deterministic RNG (e.g., per NIST SP800-90C).
 	  This RNG does not perform any cryptographic whitening of the generated
+	  random numbers.
 
-	  See https://www.chronox.de/jent.html
+	  See https://www.chronox.de/jent/
 
 if CRYPTO_JITTERENTROPY
 if CRYPTO_FIPS && EXPERT

crypto/ahash.c

···
 }
 EXPORT_SYMBOL_GPL(crypto_has_ahash);
 
+static bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg)
+{
+	struct crypto_alg *alg = &halg->base;
+
+	if (alg->cra_type == &crypto_shash_type)
+		return crypto_shash_alg_has_setkey(__crypto_shash_alg(alg));
+
+	return __crypto_ahash_alg(alg)->setkey != ahash_nosetkey;
+}
+
 struct crypto_ahash *crypto_clone_ahash(struct crypto_ahash *hash)
 {
 	struct hash_alg_common *halg = crypto_hash_alg_common(hash);
···
 	return crypto_register_instance(tmpl, ahash_crypto_instance(inst));
 }
 EXPORT_SYMBOL_GPL(ahash_register_instance);
-
-bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg)
-{
-	struct crypto_alg *alg = &halg->base;
-
-	if (alg->cra_type == &crypto_shash_type)
-		return crypto_shash_alg_has_setkey(__crypto_shash_alg(alg));
-
-	return __crypto_ahash_alg(alg)->setkey != ahash_nosetkey;
-}
-EXPORT_SYMBOL_GPL(crypto_hash_alg_has_setkey);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Asynchronous cryptographic hash type");

crypto/asymmetric_keys/verify_pefile.c

···
 	const struct pe32plus_opt_hdr *pe64;
 	const struct data_directory *ddir;
 	const struct data_dirent *dde;
-	const struct section_header *secs, *sec;
+	const struct section_header *sec;
 	size_t cursor, datalen = pelen;
 
 	kenter("");
···
 	ctx->n_sections = pe->sections;
 	if (ctx->n_sections > (ctx->header_size - cursor) / sizeof(*sec))
 		return -ELIBBAD;
-	ctx->secs = secs = pebuf + cursor;
+	ctx->secs = pebuf + cursor;
 
 	return 0;
 }

crypto/dh.c

···
  */
 static int dh_is_pubkey_valid(struct dh_ctx *ctx, MPI y)
 {
+	MPI val, q;
+	int ret;
+
+	if (!fips_enabled)
+		return 0;
+
 	if (unlikely(!ctx->p))
 		return -EINVAL;
 
···
 	 *
 	 * For the safe-prime groups q = (p - 1)/2.
 	 */
-	if (fips_enabled) {
-		MPI val, q;
-		int ret;
+	val = mpi_alloc(0);
+	if (!val)
+		return -ENOMEM;
 
-		val = mpi_alloc(0);
-		if (!val)
-			return -ENOMEM;
-
-		q = mpi_alloc(mpi_get_nlimbs(ctx->p));
-		if (!q) {
-			mpi_free(val);
-			return -ENOMEM;
-		}
-
-		/*
-		 * ->p is odd, so no need to explicitly subtract one
-		 * from it before shifting to the right.
-		 */
-		mpi_rshift(q, ctx->p, 1);
-
-		ret = mpi_powm(val, y, q, ctx->p);
-		mpi_free(q);
-		if (ret) {
-			mpi_free(val);
-			return ret;
-		}
-
-		ret = mpi_cmp_ui(val, 1);
-
+	q = mpi_alloc(mpi_get_nlimbs(ctx->p));
+	if (!q) {
 		mpi_free(val);
-
-		if (ret != 0)
-			return -EINVAL;
+		return -ENOMEM;
 	}
+
+	/*
+	 * ->p is odd, so no need to explicitly subtract one
+	 * from it before shifting to the right.
+	 */
+	mpi_rshift(q, ctx->p, 1);
+
+	ret = mpi_powm(val, y, q, ctx->p);
+	mpi_free(q);
+	if (ret) {
+		mpi_free(val);
+		return ret;
+	}
+
+	ret = mpi_cmp_ui(val, 1);
+
+	mpi_free(val);
+
+	if (ret != 0)
+		return -EINVAL;
 
 	return 0;
 }

crypto/pcbc.c

···
 
 	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk.nbytes)) {
+	while (walk.nbytes) {
 		if (walk.src.virt.addr == walk.dst.virt.addr)
 			nbytes = crypto_pcbc_encrypt_inplace(req, &walk,
 							     cipher);
···
 
 	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk.nbytes)) {
+	while (walk.nbytes) {
 		if (walk.src.virt.addr == walk.dst.virt.addr)
 			nbytes = crypto_pcbc_decrypt_inplace(req, &walk,
 							     cipher);

crypto/rsa.c

···
 	MPI qinv;
 };
 
+static int rsa_check_payload(MPI x, MPI n)
+{
+	MPI n1;
+
+	if (mpi_cmp_ui(x, 1) <= 0)
+		return -EINVAL;
+
+	n1 = mpi_alloc(0);
+	if (!n1)
+		return -ENOMEM;
+
+	if (mpi_sub_ui(n1, n, 1) || mpi_cmp(x, n1) >= 0) {
+		mpi_free(n1);
+		return -EINVAL;
+	}
+
+	mpi_free(n1);
+	return 0;
+}
+
 /*
  * RSAEP function [RFC3447 sec 5.1.1]
  * c = m^e mod n;
  */
 static int _rsa_enc(const struct rsa_mpi_key *key, MPI c, MPI m)
 {
-	/* (1) Validate 0 <= m < n */
-	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
+	/*
+	 * Even though (1) in RFC3447 only requires 0 <= m <= n - 1, we are
+	 * slightly more conservative and require 1 < m < n - 1. This is in line
+	 * with SP 800-56Br2, Section 7.1.1.
+	 */
+	if (rsa_check_payload(m, key->n))
 		return -EINVAL;
 
 	/* (2) c = m^e mod n */
···
 	MPI m2, m12_or_qh;
 	int ret = -ENOMEM;
 
-	/* (1) Validate 0 <= c < n */
-	if (mpi_cmp_ui(c, 0) < 0 || mpi_cmp(c, key->n) >= 0)
+	/*
+	 * Even though (1) in RFC3447 only requires 0 <= c <= n - 1, we are
+	 * slightly more conservative and require 1 < c < n - 1. This is in line
+	 * with SP 800-56Br2, Section 7.1.2.
+	 */
+	if (rsa_check_payload(c, key->n))
 		return -EINVAL;
 
 	m2 = mpi_alloc(0);

crypto/scompress.c

···
 	struct crypto_scomp *scomp = *tfm_ctx;
 	void **ctx = acomp_request_ctx(req);
 	struct scomp_scratch *scratch;
+	void *src, *dst;
 	unsigned int dlen;
 	int ret;
 
···
 	scratch = raw_cpu_ptr(&scomp_scratch);
 	spin_lock(&scratch->lock);
 
-	scatterwalk_map_and_copy(scratch->src, req->src, 0, req->slen, 0);
-	if (dir)
-		ret = crypto_scomp_compress(scomp, scratch->src, req->slen,
-					    scratch->dst, &req->dlen, *ctx);
+	if (sg_nents(req->src) == 1 && !PageHighMem(sg_page(req->src))) {
+		src = page_to_virt(sg_page(req->src)) + req->src->offset;
+	} else {
+		scatterwalk_map_and_copy(scratch->src, req->src, 0,
+					 req->slen, 0);
+		src = scratch->src;
+	}
+
+	if (req->dst && sg_nents(req->dst) == 1 && !PageHighMem(sg_page(req->dst)))
+		dst = page_to_virt(sg_page(req->dst)) + req->dst->offset;
 	else
-		ret = crypto_scomp_decompress(scomp, scratch->src, req->slen,
-					      scratch->dst, &req->dlen, *ctx);
+		dst = scratch->dst;
+
+	if (dir)
+		ret = crypto_scomp_compress(scomp, src, req->slen,
+					    dst, &req->dlen, *ctx);
+	else
+		ret = crypto_scomp_decompress(scomp, src, req->slen,
+					      dst, &req->dlen, *ctx);
 	if (!ret) {
 		if (!req->dst) {
 			req->dst = sgl_alloc(req->dlen, GFP_ATOMIC, NULL);
···
 			ret = -ENOSPC;
 			goto out;
 		}
-		scatterwalk_map_and_copy(scratch->dst, req->dst, 0, req->dlen,
-					 1);
+		if (dst == scratch->dst) {
+			scatterwalk_map_and_copy(scratch->dst, req->dst, 0,
+						 req->dlen, 1);
+		} else {
+			int nr_pages = DIV_ROUND_UP(req->dst->offset + req->dlen, PAGE_SIZE);
+			int i;
+			struct page *dst_page = sg_page(req->dst);
+
+			for (i = 0; i < nr_pages; i++)
+				flush_dcache_page(dst_page + i);
+		}
 	}
 out:
 	spin_unlock(&scratch->lock);

crypto/tcrypt.c

···
 		ret = min(ret, tcrypt_test("cbc(aria)"));
 		ret = min(ret, tcrypt_test("ctr(aria)"));
 		break;
+	case 193:
+		ret = min(ret, tcrypt_test("ffdhe2048(dh)"));
+		break;
 	case 200:
 		test_cipher_speed("ecb(aes)", ENCRYPT, sec, NULL, 0,
 				speed_template_16_24_32);

crypto/testmgr.c

···
 		}
 	}, {
 #endif
-		.alg = "xts4096(paes)",
-		.test = alg_test_null,
-		.fips_allowed = 1,
-	}, {
-		.alg = "xts512(paes)",
-		.test = alg_test_null,
-		.fips_allowed = 1,
-	}, {
 		.alg = "xxhash64",
 		.test = alg_test_hash,
 		.fips_allowed = 1,

drivers/char/hw_random/hisi-rng.c

···
 	rng->rng.read = hisi_rng_read;
 
 	ret = devm_hwrng_register(&pdev->dev, &rng->rng);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register hwrng\n");
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "failed to register hwrng\n");
 
 	return 0;
 }

drivers/crypto/Kconfig

···
 	  To compile this driver as a module, choose M here. The
 	  module will be called qcom-rng. If unsure, say N.
 
-config CRYPTO_DEV_VMX
-	bool "Support for VMX cryptographic acceleration instructions"
-	depends on PPC64 && VSX
-	help
-	  Support for VMX cryptographic acceleration instructions.
-
-source "drivers/crypto/vmx/Kconfig"
+#config CRYPTO_DEV_VMX
+#	bool "Support for VMX cryptographic acceleration instructions"
+#	depends on PPC64 && VSX
+#	help
+#	  Support for VMX cryptographic acceleration instructions.
+#
+#source "drivers/crypto/vmx/Kconfig"
 
 config CRYPTO_DEV_IMGTEC_HASH
 	tristate "Imagination Technologies hardware hash accelerator"

drivers/crypto/Makefile

···
 obj-y += stm32/
 obj-$(CONFIG_CRYPTO_DEV_TALITOS) += talitos.o
 obj-$(CONFIG_CRYPTO_DEV_VIRTIO) += virtio/
-obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/
+#obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/
 obj-$(CONFIG_CRYPTO_DEV_BCM_SPU) += bcm/
 obj-$(CONFIG_CRYPTO_DEV_SAFEXCEL) += inside-secure/
 obj-$(CONFIG_CRYPTO_DEV_ARTPEC6) += axis/

drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c

···
 		digestsize = SHA512_DIGEST_SIZE;
 
 	/* the padding could be up to two block. */
-	buf = kzalloc(bs * 2, GFP_KERNEL | GFP_DMA);
+	buf = kcalloc(2, bs, GFP_KERNEL | GFP_DMA);
 	if (!buf) {
 		err = -ENOMEM;
 		goto theend;

drivers/crypto/ccp/platform-access.c

···
 		goto unlock;
 	}
 
-	/* Store the status in request header for caller to investigate */
+	/*
+	 * Read status from PSP. If status is non-zero, it indicates an error
+	 * occurred during "processing" of the command.
+	 * If status is zero, it indicates the command was "processed"
+	 * successfully, but the result of the command is in the payload.
+	 * Return both cases to the caller as -EIO to investigate.
+	 */
 	cmd_reg = ioread32(cmd);
-	req->header.status = FIELD_GET(PSP_CMDRESP_STS, cmd_reg);
+	if (FIELD_GET(PSP_CMDRESP_STS, cmd_reg))
+		req->header.status = FIELD_GET(PSP_CMDRESP_STS, cmd_reg);
 	if (req->header.status) {
 		ret = -EIO;
 		goto unlock;

drivers/crypto/ccp/psp-dev.c

···
 	}
 	psp->capability = val;
 
-	/* Detect if TSME and SME are both enabled */
+	/* Detect TSME and/or SME status */
 	if (PSP_CAPABILITY(psp, PSP_SECURITY_REPORTING) &&
-	    psp->capability & (PSP_SECURITY_TSME_STATUS << PSP_CAPABILITY_PSP_SECURITY_OFFSET) &&
-	    cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
-		dev_notice(psp->dev, "psp: Both TSME and SME are active, SME is unnecessary when TSME is active.\n");
+	    psp->capability & (PSP_SECURITY_TSME_STATUS << PSP_CAPABILITY_PSP_SECURITY_OFFSET)) {
+		if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+			dev_notice(psp->dev, "psp: Both TSME and SME are active, SME is unnecessary when TSME is active.\n");
+		else
+			dev_notice(psp->dev, "psp: TSME enabled\n");
+	}
 
 	return 0;
 }

drivers/crypto/hisilicon/debugfs.c

···
 #define QM_DFX_QN_SHIFT			16
 #define QM_DFX_CNT_CLR_CE		0x100118
 #define QM_DBG_WRITE_LEN		1024
+#define QM_IN_IDLE_ST_REG		0x1040e4
+#define QM_IN_IDLE_STATE		0x1
 
 static const char * const qm_debug_file_name[] = {
 	[CURRENT_QM]   = "current_qm",
···
 	{"QM_DFX_FF_ST5                 ",  0x1040dc},
 	{"QM_DFX_FF_ST6                 ",  0x1040e0},
 	{"QM_IN_IDLE_ST                 ",  0x1040e4},
+	{"QM_CACHE_CTL                  ",  0x100050},
+	{"QM_TIMEOUT_CFG                ",  0x100070},
+	{"QM_DB_TIMEOUT_CFG             ",  0x100074},
+	{"QM_FLR_PENDING_TIME_CFG       ",  0x100078},
+	{"QM_ARUSR_MCFG1                ",  0x100088},
+	{"QM_AWUSR_MCFG1                ",  0x100098},
+	{"QM_AXI_M_CFG_ENABLE           ",  0x1000B0},
+	{"QM_RAS_CE_THRESHOLD           ",  0x1000F8},
+	{"QM_AXI_TIMEOUT_CTRL           ",  0x100120},
+	{"QM_AXI_TIMEOUT_STATUS         ",  0x100124},
+	{"QM_CQE_AGGR_TIMEOUT_CTRL      ",  0x100144},
+	{"ACC_RAS_MSI_INT_SEL           ",  0x1040fc},
+	{"QM_CQE_OUT                    ",  0x104100},
+	{"QM_EQE_OUT                    ",  0x104104},
+	{"QM_AEQE_OUT                   ",  0x104108},
+	{"QM_DB_INFO0                   ",  0x104180},
+	{"QM_DB_INFO1                   ",  0x104184},
+	{"QM_AM_CTRL_GLOBAL             ",  0x300000},
+	{"QM_AM_CURR_PORT_STS           ",  0x300100},
+	{"QM_AM_CURR_TRANS_RETURN       ",  0x300150},
+	{"QM_AM_CURR_RD_MAX_TXID        ",  0x300154},
+	{"QM_AM_CURR_WR_MAX_TXID        ",  0x300158},
+	{"QM_AM_ALARM_RRESP             ",  0x300180},
+	{"QM_AM_ALARM_BRESP             ",  0x300184},
 };
 
 static const struct debugfs_reg32 qm_vf_dfx_regs[] = {
···
 }
 DEFINE_SHOW_ATTRIBUTE(qm_diff_regs);
 
+static int qm_state_show(struct seq_file *s, void *unused)
+{
+	struct hisi_qm *qm = s->private;
+	u32 val;
+	int ret;
+
+	/* If device is in suspended, directly return the idle state. */
+	ret = hisi_qm_get_dfx_access(qm);
+	if (!ret) {
+		val = readl(qm->io_base + QM_IN_IDLE_ST_REG);
+		hisi_qm_put_dfx_access(qm);
+	} else if (ret == -EAGAIN) {
+		val = QM_IN_IDLE_STATE;
+	} else {
+		return ret;
+	}
+
+	seq_printf(s, "%u\n", val);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(qm_state);
+
 static ssize_t qm_status_read(struct file *filp, char __user *buffer,
 			      size_t count, loff_t *pos)
 {
···
 void hisi_qm_debug_init(struct hisi_qm *qm)
 {
 	struct dfx_diff_registers *qm_regs = qm->debug.qm_diff_regs;
+	struct qm_dev_dfx *dev_dfx = &qm->debug.dev_dfx;
 	struct qm_dfx *dfx = &qm->debug.dfx;
 	struct dentry *qm_d;
 	void *data;
···
 
 	/* only show this in PF */
 	if (qm->fun_type == QM_HW_PF) {
+		debugfs_create_file("qm_state", 0444, qm->debug.qm_d,
+					qm, &qm_state_fops);
+
 		qm_create_debugfs_file(qm, qm->debug.debug_root, CURRENT_QM);
 		for (i = CURRENT_Q; i < DEBUG_FILE_NUM; i++)
 			qm_create_debugfs_file(qm, qm->debug.qm_d, i);
···
 
 	debugfs_create_file("status", 0444, qm->debug.qm_d, qm,
 			&qm_status_fops);
+
+	debugfs_create_u32("dev_state", 0444, qm->debug.qm_d, &dev_dfx->dev_state);
+	debugfs_create_u32("dev_timeout", 0644, qm->debug.qm_d, &dev_dfx->dev_timeout);
+
 	for (i = 0; i < ARRAY_SIZE(qm_dfx_files); i++) {
 		data = (atomic64_t *)((uintptr_t)dfx + qm_dfx_files[i].offset);
 		debugfs_create_file(qm_dfx_files[i].name,

drivers/crypto/hisilicon/hpre/hpre_main.c

···
 
 struct hisi_qp *hpre_create_qp(u8 type)
 {
-	int node = cpu_to_node(smp_processor_id());
+	int node = cpu_to_node(raw_smp_processor_id());
 	struct hisi_qp *qp = NULL;
 	int ret;
 

drivers/crypto/hisilicon/qm.c

···
 
 #define QM_DEV_ALG_MAX_LEN		256
 
+ /* abnormal status value for stopping queue */
+#define QM_STOP_QUEUE_FAIL		1
+#define	QM_DUMP_SQC_FAIL		3
+#define	QM_DUMP_CQC_FAIL		4
+#define	QM_FINISH_WAIT			5
+
 #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \
 	(((hop_num) << QM_CQ_HOP_NUM_SHIFT) | \
 	((pg_sz) << QM_CQ_PAGE_SIZE_SHIFT) | \
···
 	{QM_SUPPORT_DB_ISOLATION, 0x30,   0, BIT(0),  0x0, 0x0, 0x0},
 	{QM_SUPPORT_FUNC_QOS,     0x3100, 0, BIT(8),  0x0, 0x0, 0x1},
 	{QM_SUPPORT_STOP_QP,      0x3100, 0, BIT(9),  0x0, 0x0, 0x1},
+	{QM_SUPPORT_STOP_FUNC,     0x3100, 0, BIT(10), 0x0, 0x0, 0x1},
 	{QM_SUPPORT_MB_COMMAND,   0x3100, 0, BIT(11), 0x0, 0x0, 0x1},
 	{QM_SUPPORT_SVA_PREFETCH, 0x3100, 0, BIT(14), 0x0, 0x0, 0x1},
 };
···
 	return ret;
 }
 
+static int qm_drain_qm(struct hisi_qm *qm)
+{
+	return hisi_qm_mb(qm, QM_MB_CMD_FLUSH_QM, 0, 0, 0);
+}
+
 static int qm_stop_qp(struct hisi_qp *qp)
 {
 	return hisi_qm_mb(qp->qm, QM_MB_CMD_STOP_QP, 0, qp->qp_id, 0);
···
 	}
 }
 
-/**
- * qm_drain_qp() - Drain a qp.
- * @qp: The qp we want to drain.
- *
- * Determine whether the queue is cleared by judging the tail pointers of
- * sq and cq.
- */
-static int qm_drain_qp(struct hisi_qp *qp)
+static int qm_wait_qp_empty(struct hisi_qm *qm, u32 *state, u32 qp_id)
 {
-	struct hisi_qm *qm = qp->qm;
 	struct device *dev = &qm->pdev->dev;
 	struct qm_sqc sqc;
 	struct qm_cqc cqc;
 	int ret, i = 0;
 
-	/* No need to judge if master OOO is blocked. */
-	if (qm_check_dev_error(qm))
-		return 0;
-
-	/* Kunpeng930 supports drain qp by device */
-	if (test_bit(QM_SUPPORT_STOP_QP, &qm->caps)) {
-		ret = qm_stop_qp(qp);
-		if (ret)
-			dev_err(dev, "Failed to stop qp(%u)!\n", qp->qp_id);
-		return ret;
-	}
-
 	while (++i) {
-		ret = qm_set_and_get_xqc(qm, QM_MB_CMD_SQC, &sqc, qp->qp_id, 1);
+		ret = qm_set_and_get_xqc(qm, QM_MB_CMD_SQC, &sqc, qp_id, 1);
 		if (ret) {
 			dev_err_ratelimited(dev, "Failed to dump sqc!\n");
+			*state = QM_DUMP_SQC_FAIL;
 			return ret;
 		}
 
-		ret = qm_set_and_get_xqc(qm, QM_MB_CMD_CQC, &cqc, qp->qp_id, 1);
+		ret = qm_set_and_get_xqc(qm, QM_MB_CMD_CQC, &cqc, qp_id, 1);
 		if (ret) {
 			dev_err_ratelimited(dev, "Failed to dump cqc!\n");
+			*state = QM_DUMP_CQC_FAIL;
 			return ret;
 		}
 
···
 			break;
 
 		if (i == MAX_WAIT_COUNTS) {
-			dev_err(dev, "Fail to empty queue %u!\n", qp->qp_id);
-			return -EBUSY;
+			dev_err(dev, "Fail to empty queue %u!\n", qp_id);
+			*state = QM_STOP_QUEUE_FAIL;
+			return -ETIMEDOUT;
 		}
 
 		usleep_range(WAIT_PERIOD_US_MIN, WAIT_PERIOD_US_MAX);
···
 	return 0;
 }
 
-static int qm_stop_qp_nolock(struct hisi_qp *qp)
+/**
+ * qm_drain_qp() - Drain a qp.
+ * @qp: The qp we want to drain.
+ *
+ * If the device does not support stopping queue by sending mailbox,
+ * determine whether the queue is cleared by judging the tail pointers of
+ * sq and cq.
+ */
+static int qm_drain_qp(struct hisi_qp *qp)
 {
-	struct device *dev = &qp->qm->pdev->dev;
+	struct hisi_qm *qm = qp->qm;
+	struct hisi_qm *pf_qm = pci_get_drvdata(pci_physfn(qm->pdev));
+	u32 state = 0;
+	int ret;
+
+	/* No need to judge if master OOO is blocked. */
+	if (qm_check_dev_error(pf_qm))
+		return 0;
+
+	/* HW V3 supports drain qp by device */
+	if (test_bit(QM_SUPPORT_STOP_QP, &qm->caps)) {
+		ret = qm_stop_qp(qp);
+		if (ret) {
+			dev_err(&qm->pdev->dev, "Failed to stop qp!\n");
+			state = QM_STOP_QUEUE_FAIL;
+			goto set_dev_state;
+		}
+		return ret;
+	}
+
+	ret = qm_wait_qp_empty(qm, &state, qp->qp_id);
+	if (ret)
+		goto set_dev_state;
+
+	return 0;
+
+set_dev_state:
+	if (qm->debug.dev_dfx.dev_timeout)
+		qm->debug.dev_dfx.dev_state = state;
+
+	return ret;
+}
+
+static void qm_stop_qp_nolock(struct hisi_qp *qp)
+{
+	struct hisi_qm *qm = qp->qm;
+	struct device *dev = &qm->pdev->dev;
 	int ret;
 
 	/*
···
 	 */
 	if (atomic_read(&qp->qp_status.flags) != QP_START) {
 		qp->is_resetting = false;
-		return 0;
+		return;
 	}
 
 	atomic_set(&qp->qp_status.flags, QP_STOP);
 
-	ret = qm_drain_qp(qp);
-	if (ret)
-		dev_err(dev, "Failed to drain out data for stopping!\n");
+	/* V3 supports direct stop function when FLR prepare */
+	if (qm->ver < QM_HW_V3 || qm->status.stop_reason == QM_NORMAL) {
+		ret = qm_drain_qp(qp);
+		if (ret)
+			dev_err(dev, "Failed to drain out data for stopping qp(%u)!\n", qp->qp_id);
+	}
 
-	flush_workqueue(qp->qm->wq);
+	flush_workqueue(qm->wq);
 	if (unlikely(qp->is_resetting && atomic_read(&qp->qp_status.used)))
 		qp_stop_fail_cb(qp);
 
 	dev_dbg(dev, "stop queue %u!", qp->qp_id);
-
-	return 0;
 }
 
 /**
  * hisi_qm_stop_qp() - Stop a qp in qm.
  * @qp: The qp we want to stop.
  *
- * This function is reverse of hisi_qm_start_qp. Return 0 if successful.
+ * This function is reverse of hisi_qm_start_qp.
  */
-int hisi_qm_stop_qp(struct hisi_qp *qp)
+void hisi_qm_stop_qp(struct hisi_qp *qp)
 {
-	int ret;
-
 	down_write(&qp->qm->qps_lock);
-	ret = qm_stop_qp_nolock(qp);
+	qm_stop_qp_nolock(qp);
 	up_write(&qp->qm->qps_lock);
-
-	return ret;
 }
 EXPORT_SYMBOL_GPL(hisi_qm_stop_qp);
 
···
 
 static void hisi_qm_uacce_stop_queue(struct uacce_queue *q)
 {
-	hisi_qm_stop_qp(q->priv);
+	struct hisi_qp *qp = q->priv;
+	struct hisi_qm *qm = qp->qm;
+	struct qm_dev_dfx *dev_dfx = &qm->debug.dev_dfx;
+	u32 i = 0;
+
+	hisi_qm_stop_qp(qp);
+
+	if (!dev_dfx->dev_timeout || !dev_dfx->dev_state)
+		return;
+
+	/*
+	 * After the queue fails to be stopped,
+	 * wait for a period of time before releasing the queue.
+	 */
+	while (++i) {
+		msleep(WAIT_PERIOD);
+
+		/* Since dev_timeout maybe modified, check i >= dev_timeout */
+		if (i >= dev_dfx->dev_timeout) {
+			dev_err(&qm->pdev->dev, "Stop q %u timeout, state %u\n",
+			       qp->qp_id, dev_dfx->dev_state);
+			dev_dfx->dev_state = QM_FINISH_WAIT;
+			break;
+		}
+	}
 }
 
 static int hisi_qm_is_q_updated(struct uacce_queue *q)
···
 }
 
 /* Stop started qps in reset flow */
-static int qm_stop_started_qp(struct hisi_qm *qm)
+static void qm_stop_started_qp(struct hisi_qm *qm)
 {
-	struct device *dev = &qm->pdev->dev;
 	struct hisi_qp *qp;
-	int i, ret;
+	int i;
 
 	for (i = 0; i < qm->qp_num; i++) {
 		qp = &qm->qp_array[i];
-		if (qp && atomic_read(&qp->qp_status.flags) == QP_START) {
+		if (atomic_read(&qp->qp_status.flags) == QP_START) {
 			qp->is_resetting = true;
-			ret = qm_stop_qp_nolock(qp);
-			if (ret < 0) {
-				dev_err(dev, "Failed to stop qp%d!\n", i);
-				return ret;
-			}
+			qm_stop_qp_nolock(qp);
 		}
 	}
-
-	return 0;
 }
 
 /**
···
 
 	down_write(&qm->qps_lock);
 
-	qm->status.stop_reason = r;
 	if (atomic_read(&qm->status.flags) == QM_STOP)
 		goto err_unlock;
 
 	/* Stop all the request sending at first. */
 	atomic_set(&qm->status.flags, QM_STOP);
+	qm->status.stop_reason = r;
 
-	if (qm->status.stop_reason == QM_SOFT_RESET ||
-	    qm->status.stop_reason == QM_DOWN) {
+	if (qm->status.stop_reason != QM_NORMAL) {
 		hisi_qm_set_hw_reset(qm, QM_RESET_STOP_TX_OFFSET);
-		ret = qm_stop_started_qp(qm);
-		if (ret < 0) {
-			dev_err(dev, "Failed to stop started qp!\n");
-			goto err_unlock;
+		/*
+		 * When performing soft reset, the hardware will no longer
+		 * do tasks, and the tasks in the device will be flushed
+		 * out directly since the master ooo is closed.
+		 */
+		if (test_bit(QM_SUPPORT_STOP_FUNC, &qm->caps) &&
+		    r != QM_SOFT_RESET) {
+			ret = qm_drain_qm(qm);
+			if (ret) {
+				dev_err(dev, "failed to drain qm!\n");
+				goto err_unlock;
+			}
 		}
+
+		qm_stop_started_qp(qm);
+
 		hisi_qm_set_hw_reset(qm, QM_RESET_STOP_RX_OFFSET);
 	}
 
···
 	}
 
 	qm_clear_queues(qm);
+	qm->status.stop_reason = QM_NORMAL;
 
 err_unlock:
 	up_write(&qm->qps_lock);

drivers/crypto/hisilicon/sec2/sec_crypto.c

···
 };
 
 /* Get an en/de-cipher queue cyclically to balance load over queues of TFM */
-static inline int sec_alloc_queue_id(struct sec_ctx *ctx, struct sec_req *req)
+static inline u32 sec_alloc_queue_id(struct sec_ctx *ctx, struct sec_req *req)
 {
 	if (req->c_req.encrypt)
 		return (u32)atomic_inc_return(&ctx->enc_qcyclic) %
···
 		sec_free_mac_resource(dev, qp_ctx->res);
 }
 
-static int sec_alloc_qp_ctx_resource(struct hisi_qm *qm, struct sec_ctx *ctx,
-				     struct sec_qp_ctx *qp_ctx)
+static int sec_alloc_qp_ctx_resource(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx)
 {
 	u16 q_depth = qp_ctx->qp->sq_depth;
 	struct device *dev = ctx->dev;
···
 	kfree(qp_ctx->req_list);
 }
 
-static int sec_create_qp_ctx(struct hisi_qm *qm, struct sec_ctx *ctx,
-			     int qp_ctx_id, int alg_type)
+static int sec_create_qp_ctx(struct sec_ctx *ctx, int qp_ctx_id)
 {
 	struct sec_qp_ctx *qp_ctx;
 	struct hisi_qp *qp;
···
 	idr_init(&qp_ctx->req_idr);
 	INIT_LIST_HEAD(&qp_ctx->backlog);
 
-	ret = sec_alloc_qp_ctx_resource(qm, ctx, qp_ctx);
+	ret = sec_alloc_qp_ctx_resource(ctx, qp_ctx);
 	if (ret)
 		goto err_destroy_idr;
 
···
 	}
 
 	for (i = 0; i < sec->ctx_q_num; i++) {
-		ret = sec_create_qp_ctx(&sec->qm, ctx, i, 0);
+		ret = sec_create_qp_ctx(ctx, i);
 		if (ret)
 			goto err_sec_release_qp_ctx;
 	}
···
 	sec_ctx_base_uninit(ctx);
 }
 
-static int sec_skcipher_3des_setkey(struct crypto_skcipher *tfm, const u8 *key,
-				    const u32 keylen,
-				    const enum sec_cmode c_mode)
+static int sec_skcipher_3des_setkey(struct crypto_skcipher *tfm, const u8 *key, const u32 keylen)
 {
 	struct sec_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct sec_cipher_ctx *c_ctx = &ctx->c_ctx;
···
 
 	switch (c_alg) {
 	case SEC_CALG_3DES:
-		ret = sec_skcipher_3des_setkey(tfm, key, keylen, c_mode);
+		ret = sec_skcipher_3des_setkey(tfm, key, keylen);
 		break;
 	case SEC_CALG_AES:
 	case SEC_CALG_SM4:
···
 	sec_sqe3->bd_param = cpu_to_le32(bd_param);
 
 	sec_sqe3->c_len_ivin |= cpu_to_le32(c_req->c_len);
-	sec_sqe3->tag = cpu_to_le64(req);
+	sec_sqe3->tag = cpu_to_le64((unsigned long)req);
 
 	return 0;
 }
···
 	return sec_skcipher_crypto(sk_req, false);
 }
 
-#define SEC_SKCIPHER_GEN_ALG(sec_cra_name, sec_set_key, sec_min_key_size, \
-	sec_max_key_size, ctx_init, ctx_exit, blk_size, iv_size)\
+#define SEC_SKCIPHER_ALG(sec_cra_name, sec_set_key, \
+	sec_min_key_size, sec_max_key_size, blk_size, iv_size)\
 {\
 	.base = {\
 		.cra_name = sec_cra_name,\
···
 		.cra_ctxsize = sizeof(struct sec_ctx),\
 		.cra_module = THIS_MODULE,\
 	},\
-	.init = ctx_init,\
-	.exit = ctx_exit,\
+	.init = sec_skcipher_ctx_init,\
+	.exit = sec_skcipher_ctx_exit,\
 	.setkey = sec_set_key,\
 	.decrypt = sec_skcipher_decrypt,\
 	.encrypt = sec_skcipher_encrypt,\
···
 	.max_keysize = sec_max_key_size,\
 	.ivsize = iv_size,\
 }
-
-#define SEC_SKCIPHER_ALG(name, key_func, min_key_size, \
-	max_key_size, blk_size, iv_size) \
-	SEC_SKCIPHER_GEN_ALG(name, key_func, min_key_size, max_key_size, \
-	sec_skcipher_ctx_init, sec_skcipher_ctx_exit, blk_size, iv_size)
 
 static struct sec_skcipher sec_skciphers[] = {
 	{

drivers/crypto/hisilicon/sec2/sec_main.c

···
 	{"SEC_BD_SAA6                   ",  0x301C38},
 	{"SEC_BD_SAA7                   ",  0x301C3C},
 	{"SEC_BD_SAA8                   ",  0x301C40},
+	{"SEC_RAS_CE_ENABLE             ",  0x301050},
+	{"SEC_RAS_FE_ENABLE             ",  0x301054},
+	{"SEC_RAS_NFE_ENABLE            ",  0x301058},
+	{"SEC_REQ_TRNG_TIME_TH          ",  0x30112C},
+	{"SEC_CHANNEL_RNG_REQ_THLD      ",  0x302110},
 };
 
 /* define the SEC's dfx regs region and region length */
···
 
 struct hisi_qp **sec_create_qps(void)
 {
-	int node = cpu_to_node(smp_processor_id());
+	int node = cpu_to_node(raw_smp_processor_id());
 	u32 ctx_num = ctx_q_num;
 	struct hisi_qp **qps;
 	int ret;

drivers/crypto/hisilicon/zip/zip_crypto.c

···
 	.base			= {
 		.cra_name		= "deflate",
 		.cra_driver_name	= "hisi-deflate-acomp",
+		.cra_flags		= CRYPTO_ALG_ASYNC,
 		.cra_module		= THIS_MODULE,
 		.cra_priority		= HZIP_ALG_PRIORITY,
 		.cra_ctxsize		= sizeof(struct hisi_zip_ctx),

drivers/crypto/hisilicon/zip/zip_main.c

···
 int zip_create_qps(struct hisi_qp **qps, int qp_num, int node)
 {
 	if (node == NUMA_NO_NODE)
-		node = cpu_to_node(smp_processor_id());
+		node = cpu_to_node(raw_smp_processor_id());
 
 	return hisi_qm_alloc_qps_node(&zip_devices, qp_num, 0, node, qps);
 }

drivers/crypto/intel/iaa/iaa_crypto.h

···
 	const char			*name;
 
 	struct aecs_comp_table_record	*aecs_comp_table;
-	struct aecs_decomp_table_record	*aecs_decomp_table;
 
 	dma_addr_t			aecs_comp_table_dma_addr;
-	dma_addr_t			aecs_decomp_table_dma_addr;
 };
 
 /* Representation of IAA device with wqs, populated by probe */
···
 	u32 reserved_padding[2];
 } __packed;
 
-/* AECS for decompress */
-struct aecs_decomp_table_record {
-	u32 crc;
-	u32 xor_checksum;
-	u32 low_filter_param;
-	u32 high_filter_param;
-	u32 output_mod_idx;
-	u32 drop_init_decomp_out_bytes;
-	u32 reserved[36];
-	u32 output_accum_data[2];
-	u32 out_bits_valid;
-	u32 bit_off_indexing;
-	u32 input_accum_data[64];
-	u8  size_qw[32];
-	u32 decomp_state[1220];
-} __packed;
-
 int iaa_aecs_init_fixed(void);
 void iaa_aecs_cleanup_fixed(void);
 
···
 	int			ll_table_size;
 	u32			*d_table;
 	int			d_table_size;
-	u32			*header_table;
-	int			header_table_size;
-	u16			gen_decomp_table_flags;
 	iaa_dev_comp_init_fn_t	init;
 	iaa_dev_comp_free_fn_t	free;
 };
···
 			     int ll_table_size,
 			     const u32 *d_table,
 			     int d_table_size,
-			     const u8 *header_table,
-			     int header_table_size,
-			     u16 gen_decomp_table_flags,
 			     iaa_dev_comp_init_fn_t init,
 			     iaa_dev_comp_free_fn_t free);
 

drivers/crypto/intel/iaa/iaa_crypto_comp_fixed.c

···
 				       sizeof(fixed_ll_sym),
 				       fixed_d_sym,
 				       sizeof(fixed_d_sym),
-				       NULL, 0, 0,
 				       init_fixed_mode, NULL);
 	if (!ret)
 		pr_debug("IAA fixed compression mode initialized\n");

drivers/crypto/intel/iaa/iaa_crypto_main.c

···
 	kfree(mode->name);
 	kfree(mode->ll_table);
 	kfree(mode->d_table);
-	kfree(mode->header_table);
 
 	kfree(mode);
 }
 
 /*
- * IAA Compression modes are defined by an ll_table, a d_table, and an
- * optional header_table.  These tables are typically generated and
- * captured using statistics collected from running actual
- * compress/decompress workloads.
+ * IAA Compression modes are defined by an ll_table and a d_table.
+ * These tables are typically generated and captured using statistics
+ * collected from running actual compress/decompress workloads.
  *
  * A module or other kernel code can add and remove compression modes
  * with a given name using the exported @add_iaa_compression_mode()
···
  * @ll_table_size: The ll table size in bytes
  * @d_table: The d table
  * @d_table_size: The d table size in bytes
- * @header_table: Optional header table
- * @header_table_size: Optional header table size in bytes
- * @gen_decomp_table_flags: Otional flags used to generate the decomp table
  * @init: Optional callback function to init the compression mode data
  * @free: Optional callback function to free the compression mode data
  *
···
 			     int ll_table_size,
 			     const u32 *d_table,
 			     int d_table_size,
-			     const u8 *header_table,
-			     int header_table_size,
-			     u16 gen_decomp_table_flags,
 			     iaa_dev_comp_init_fn_t init,
 			     iaa_dev_comp_free_fn_t free)
 {
···
 		memcpy(mode->d_table, d_table, d_table_size);
 		mode->d_table_size = d_table_size;
 	}
-
-	if (header_table) {
-		mode->header_table = kzalloc(header_table_size, GFP_KERNEL);
-		if (!mode->header_table)
-			goto free;
-		memcpy(mode->header_table, header_table, header_table_size);
-		mode->header_table_size = header_table_size;
-	}
-
-	mode->gen_decomp_table_flags = gen_decomp_table_flags;
 
 	mode->init = init;
 	mode->free = free;
···
 	if (device_mode->aecs_comp_table)
 		dma_free_coherent(dev, size, device_mode->aecs_comp_table,
 				  device_mode->aecs_comp_table_dma_addr);
-	if (device_mode->aecs_decomp_table)
-		dma_free_coherent(dev, size, device_mode->aecs_decomp_table,
-				  device_mode->aecs_decomp_table_dma_addr);
-
 	kfree(device_mode);
 }
 
···
 			    struct iax_completion_record *comp,
 			    bool compress,
 			    bool only_once);
-
-static int decompress_header(struct iaa_device_compression_mode *device_mode,
-			     struct iaa_compression_mode *mode,
-			     struct idxd_wq *wq)
-{
-	dma_addr_t src_addr, src2_addr;
-	struct idxd_desc *idxd_desc;
-	struct iax_hw_desc *desc;
-	struct device *dev;
-	int ret = 0;
-
-	idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
-	if (IS_ERR(idxd_desc))
-		return PTR_ERR(idxd_desc);
-
-	desc = idxd_desc->iax_hw;
-
-	dev = &wq->idxd->pdev->dev;
-
-	src_addr = dma_map_single(dev, (void *)mode->header_table,
-				  mode->header_table_size, DMA_TO_DEVICE);
-	dev_dbg(dev, "%s: mode->name %s, src_addr %llx, dev %p, src %p, slen %d\n",
-		__func__, mode->name, src_addr,	dev,
-		mode->header_table, mode->header_table_size);
-	if (unlikely(dma_mapping_error(dev, src_addr))) {
-		dev_dbg(dev, "dma_map_single err, exiting\n");
-		ret = -ENOMEM;
-		return ret;
-	}
-
-	desc->flags = IAX_AECS_GEN_FLAG;
-	desc->opcode = IAX_OPCODE_DECOMPRESS;
-
-	desc->src1_addr = (u64)src_addr;
-	desc->src1_size = mode->header_table_size;
-
-	src2_addr = device_mode->aecs_decomp_table_dma_addr;
-	desc->src2_addr = (u64)src2_addr;
-	desc->src2_size = 1088;
-	dev_dbg(dev, "%s: mode->name %s, src2_addr %llx, dev %p, src2_size %d\n",
-		__func__, mode->name, desc->src2_addr, dev, desc->src2_size);
-	desc->max_dst_size = 0; // suppressed output
-
-	desc->decompr_flags = mode->gen_decomp_table_flags;
-
-	desc->priv = 0;
-
-	desc->completion_addr = idxd_desc->compl_dma;
-
-	ret = idxd_submit_desc(wq, idxd_desc);
-	if (ret) {
-		pr_err("%s: submit_desc failed ret=0x%x\n", __func__, ret);
-		goto out;
-	}
-
-	ret = check_completion(dev, idxd_desc->iax_completion, false, false);
-	if (ret)
-		dev_dbg(dev, "%s: mode->name %s check_completion failed ret=%d\n",
-			__func__, mode->name, ret);
-	else
-		dev_dbg(dev, "%s: mode->name %s succeeded\n", __func__,
-			mode->name);
-out:
-	dma_unmap_single(dev, src_addr, 1088, DMA_TO_DEVICE);
-
-	return ret;
-}
 
 static int init_device_compression_mode(struct iaa_device *iaa_device,
 					struct iaa_compression_mode *mode,
···
 	if (!device_mode->aecs_comp_table)
 		goto free;
 
-	device_mode->aecs_decomp_table = dma_alloc_coherent(dev, size,
-							    &device_mode->aecs_decomp_table_dma_addr, GFP_KERNEL);
-	if (!device_mode->aecs_decomp_table)
-		goto free;
-
 	/* Add Huffman table to aecs */
 	memset(device_mode->aecs_comp_table, 0, sizeof(*device_mode->aecs_comp_table));
 	memcpy(device_mode->aecs_comp_table->ll_sym, mode->ll_table, mode->ll_table_size);
 	memcpy(device_mode->aecs_comp_table->d_sym, mode->d_table, mode->d_table_size);
-
-	if (mode->header_table) {
-		ret = decompress_header(device_mode, mode, wq);
-		if (ret) {
-			pr_debug("iaa header decompression failed: ret=%d\n", ret);
-			goto free;
-		}
-	}
 
 	if (mode->init) {
 		ret = mode->init(device_mode);
···
 
 	*compression_crc = idxd_desc->iax_completion->crc;
 
-	if (!ctx->async_mode)
+	if (!ctx->async_mode || disable_async)
 		idxd_free_desc(wq, idxd_desc);
 out:
 	return ret;
···
 
 	*dlen = req->dlen;
 
-	if (!ctx->async_mode)
+	if (!ctx->async_mode || disable_async)
 		idxd_free_desc(wq, idxd_desc);
 
 	/* Update stats */
···
 	u32 compression_crc;
 	struct idxd_wq *wq;
 	struct device *dev;
+	u64 start_time_ns;
 	int order = -1;
 
 	compression_ctx = crypto_tfm_ctx(tfm);
···
 		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
 		req->dst, req->dlen, sg_dma_len(req->dst));
 
+	start_time_ns = iaa_get_ts();
 	ret = iaa_compress(tfm, req, wq, src_addr, req->slen, dst_addr,
 			   &req->dlen, &compression_crc, disable_async);
+	update_max_comp_delay_ns(start_time_ns);
 	if (ret == -EINPROGRESS)
 		return ret;
 
···
 	struct iaa_wq *iaa_wq;
 	struct device *dev;
 	struct idxd_wq *wq;
+	u64 start_time_ns;
 	int order = -1;
 
 	cpu = get_cpu();
···
 	dev_dbg(dev, "dma_map_sg, dst_addr %llx, nr_sgs %d, req->dst %p,"
 		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
 		req->dst, req->dlen, sg_dma_len(req->dst));
+	start_time_ns = iaa_get_ts();
 	ret = iaa_decompress(tfm, req, wq, src_addr, req->slen,
 			     dst_addr, &req->dlen, true);
+	update_max_decomp_delay_ns(start_time_ns);
 	if (ret == -EOVERFLOW) {
 		dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
 		req->dlen *= 2;
···
 	int nr_sgs, cpu, ret = 0;
 	struct iaa_wq *iaa_wq;
 	struct device *dev;
+	u64 start_time_ns;
 	struct idxd_wq *wq;
 
 	if (!iaa_crypto_enabled) {
···
 		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
 		req->dst, req->dlen, sg_dma_len(req->dst));
 
+	start_time_ns = iaa_get_ts();
 	ret = iaa_decompress(tfm, req, wq, src_addr, req->slen,
 			     dst_addr, &req->dlen, false);
+	update_max_decomp_delay_ns(start_time_ns);
 	if (ret == -EINPROGRESS)
 		return ret;
 
···
 	.base			= {
 		.cra_name		= "deflate",
 		.cra_driver_name	= "deflate-iaa",
+		.cra_flags		= CRYPTO_ALG_ASYNC,
 		.cra_ctxsize		= sizeof(struct iaa_compression_ctx),
 		.cra_module		= THIS_MODULE,
 		.cra_priority		= IAA_ALG_PRIORITY,

drivers/crypto/intel/iaa/iaa_crypto_stats.c

···
 static u64 total_sw_decomp_calls;
 static u64 max_comp_delay_ns;
 static u64 max_decomp_delay_ns;
-static u64 max_acomp_delay_ns;
-static u64 max_adecomp_delay_ns;
 static u64 total_comp_bytes_out;
 static u64 total_decomp_bytes_in;
 static u64 total_completion_einval_errors;
···
 		max_decomp_delay_ns = time_diff;
 }
 
-void update_max_acomp_delay_ns(u64 start_time_ns)
-{
-	u64 time_diff;
-
-	time_diff = ktime_get_ns() - start_time_ns;
-
-	if (time_diff > max_acomp_delay_ns)
-		max_acomp_delay_ns = time_diff;
-}
-
-void update_max_adecomp_delay_ns(u64 start_time_ns)
-{
-	u64 time_diff;
-
-	time_diff = ktime_get_ns() - start_time_ns;
-
-	if (time_diff > max_adecomp_delay_ns)
-		max_adecomp_delay_ns = time_diff;
-}
-
 void update_wq_comp_calls(struct idxd_wq *idxd_wq)
 {
 	struct iaa_wq *wq = idxd_wq_get_private(idxd_wq);
···
 	total_sw_decomp_calls = 0;
 	max_comp_delay_ns = 0;
 	max_decomp_delay_ns = 0;
-	max_acomp_delay_ns = 0;
-	max_adecomp_delay_ns = 0;
 	total_comp_bytes_out = 0;
 	total_decomp_bytes_in = 0;
 	total_completion_einval_errors = 0;
···
 		return -ENODEV;
 
 	iaa_crypto_debugfs_root = debugfs_create_dir("iaa_crypto", NULL);
-	if (!iaa_crypto_debugfs_root)
-		return -ENOMEM;
 
 	debugfs_create_u64("max_comp_delay_ns", 0644,
 			   iaa_crypto_debugfs_root, &max_comp_delay_ns);
 	debugfs_create_u64("max_decomp_delay_ns", 0644,
-			   iaa_crypto_debugfs_root, &max_decomp_delay_ns);
-	debugfs_create_u64("max_acomp_delay_ns", 0644,
-			   iaa_crypto_debugfs_root, &max_comp_delay_ns);
-	debugfs_create_u64("max_adecomp_delay_ns", 0644,
 			   iaa_crypto_debugfs_root, &max_decomp_delay_ns);
 	debugfs_create_u64("total_comp_calls", 0644,
 			   iaa_crypto_debugfs_root, &total_comp_calls);

drivers/crypto/intel/iaa/iaa_crypto_stats.h

···
 void	update_total_decomp_bytes_in(int n);
 void	update_max_comp_delay_ns(u64 start_time_ns);
 void	update_max_decomp_delay_ns(u64 start_time_ns);
-void	update_max_acomp_delay_ns(u64 start_time_ns);
-void	update_max_adecomp_delay_ns(u64 start_time_ns);
 void	update_completion_einval_errs(void);
 void	update_completion_timeout_errs(void);
 void	update_completion_comp_buf_overflow_errs(void);
···
 void	update_wq_comp_bytes(struct idxd_wq *idxd_wq, int n);
 void	update_wq_decomp_calls(struct idxd_wq *idxd_wq);
 void	update_wq_decomp_bytes(struct idxd_wq *idxd_wq, int n);
+
+static inline u64	iaa_get_ts(void) { return ktime_get_ns(); }
 
 #else
 static inline int	iaa_crypto_debugfs_init(void) { return 0; }
···
 static inline void	update_total_decomp_bytes_in(int n) {}
 static inline void	update_max_comp_delay_ns(u64 start_time_ns) {}
 static inline void	update_max_decomp_delay_ns(u64 start_time_ns) {}
-static inline void	update_max_acomp_delay_ns(u64 start_time_ns) {}
-static inline void	update_max_adecomp_delay_ns(u64 start_time_ns) {}
 static inline void	update_completion_einval_errs(void) {}
 static inline void	update_completion_timeout_errs(void) {}
 static inline void	update_completion_comp_buf_overflow_errs(void) {}
···
 static inline void	update_wq_comp_bytes(struct idxd_wq *idxd_wq, int n) {}
 static inline void	update_wq_decomp_calls(struct idxd_wq *idxd_wq) {}
 static inline void	update_wq_decomp_bytes(struct idxd_wq *idxd_wq, int n) {}
+
+static inline u64	iaa_get_ts(void) { return 0; }
 
 #endif // CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS
 

drivers/crypto/intel/qat/Kconfig

···
 
 	  To compile this as a module, choose M here: the module
 	  will be called qat_c62xvf.
+
+config CRYPTO_DEV_QAT_ERROR_INJECTION
+	bool "Support for Intel(R) QAT Devices Heartbeat Error Injection"
+	depends on CRYPTO_DEV_QAT
+	depends on DEBUG_FS
+	help
+	  Enables a mechanism that allows to inject a heartbeat error on
+	  Intel(R) QuickAssist devices for testing purposes.
+
+	  This is intended for developer use only.
+	  If unsure, say N.
+
+	  This functionality is available via debugfs entry of the Intel(R)
+	  QuickAssist device

drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c

···
 	}
 }
 
-static u16 get_ring_to_svc_map(struct adf_accel_dev *accel_dev)
-{
-	enum adf_cfg_service_type rps[RP_GROUP_COUNT] = { };
-	const struct adf_fw_config *fw_config;
-	u16 ring_to_svc_map;
-	int i, j;
-
-	fw_config = get_fw_config(accel_dev);
-	if (!fw_config)
-		return 0;
-
-	for (i = 0; i < RP_GROUP_COUNT; i++) {
-		switch (fw_config[i].ae_mask) {
-		case ADF_AE_GROUP_0:
-			j = RP_GROUP_0;
-			break;
-		case ADF_AE_GROUP_1:
-			j = RP_GROUP_1;
-			break;
-		default:
-			return 0;
-		}
-
-		switch (fw_config[i].obj) {
-		case ADF_FW_SYM_OBJ:
-			rps[j] = SYM;
-			break;
-		case ADF_FW_ASYM_OBJ:
-			rps[j] = ASYM;
-			break;
-		case ADF_FW_DC_OBJ:
-			rps[j] = COMP;
-			break;
-		default:
-			rps[j] = 0;
-			break;
-		}
-	}
-
-	ring_to_svc_map = rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_0_SHIFT |
-			  rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_1_SHIFT |
-			  rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_2_SHIFT |
-			  rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_3_SHIFT;
-
-	return ring_to_svc_map;
-}
-
 static const char *uof_get_name(struct adf_accel_dev *accel_dev, u32 obj_num,
 				const char * const fw_objs[], int num_objs)
 {
···
 	int num_fw_objs = ARRAY_SIZE(adf_420xx_fw_objs);
 
 	return uof_get_name(accel_dev, obj_num, adf_420xx_fw_objs, num_fw_objs);
+}
+
+static int uof_get_obj_type(struct adf_accel_dev *accel_dev, u32 obj_num)
+{
+	const struct adf_fw_config *fw_config;
+
+	if (obj_num >= uof_get_num_objs(accel_dev))
+		return -EINVAL;
+
+	fw_config = get_fw_config(accel_dev);
+	if (!fw_config)
+		return -EINVAL;
+
+	return fw_config[obj_num].obj;
 }
 
 static u32 uof_get_ae_mask(struct adf_accel_dev *accel_dev, u32 obj_num)
···
 	hw_data->fw_mmp_name = ADF_420XX_MMP;
 	hw_data->uof_get_name = uof_get_name_420xx;
 	hw_data->uof_get_num_objs = uof_get_num_objs;
+	hw_data->uof_get_obj_type = uof_get_obj_type;
 	hw_data->uof_get_ae_mask = uof_get_ae_mask;
 	hw_data->get_rp_group = get_rp_group;
 	hw_data->get_ena_thd_mask = get_ena_thd_mask;
 	hw_data->set_msix_rttable = adf_gen4_set_msix_default_rttable;
 	hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer;
-	hw_data->get_ring_to_svc_map = get_ring_to_svc_map;
+	hw_data->get_ring_to_svc_map = adf_gen4_get_ring_to_svc_map;
 	hw_data->disable_iov = adf_disable_sriov;
 	hw_data->ring_pair_reset = adf_gen4_ring_pair_reset;
 	hw_data->enable_pm = adf_gen4_enable_pm;

drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c

···
 	}
 }
 
-static u16 get_ring_to_svc_map(struct adf_accel_dev *accel_dev)
-{
-	enum adf_cfg_service_type rps[RP_GROUP_COUNT];
-	const struct adf_fw_config *fw_config;
-	u16 ring_to_svc_map;
-	int i, j;
-
-	fw_config = get_fw_config(accel_dev);
-	if (!fw_config)
-		return 0;
-
-	for (i = 0; i < RP_GROUP_COUNT; i++) {
-		switch (fw_config[i].ae_mask) {
-		case ADF_AE_GROUP_0:
-			j = RP_GROUP_0;
-			break;
-		case ADF_AE_GROUP_1:
-			j = RP_GROUP_1;
-			break;
-		default:
-			return 0;
-		}
-
-		switch (fw_config[i].obj) {
-		case ADF_FW_SYM_OBJ:
-			rps[j] = SYM;
-			break;
-		case ADF_FW_ASYM_OBJ:
-			rps[j] = ASYM;
-			break;
-		case ADF_FW_DC_OBJ:
-			rps[j] = COMP;
-			break;
-		default:
-			rps[j] = 0;
-			break;
-		}
-	}
-
-	ring_to_svc_map = rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_0_SHIFT |
-			  rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_1_SHIFT |
-			  rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_2_SHIFT |
-			  rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_3_SHIFT;
-
-	return ring_to_svc_map;
-}
-
 static const char *uof_get_name(struct adf_accel_dev *accel_dev, u32 obj_num,
 				const char * const fw_objs[], int num_objs)
 {
···
 	int num_fw_objs = ARRAY_SIZE(adf_402xx_fw_objs);
 
 	return uof_get_name(accel_dev, obj_num, adf_402xx_fw_objs, num_fw_objs);
+}
+
+static int uof_get_obj_type(struct adf_accel_dev *accel_dev, u32 obj_num)
+{
+	const struct adf_fw_config *fw_config;
+
+	if (obj_num >= uof_get_num_objs(accel_dev))
+		return -EINVAL;
+
+	fw_config = get_fw_config(accel_dev);
+	if (!fw_config)
+		return -EINVAL;
+
+	return fw_config[obj_num].obj;
 }
 
 static u32 uof_get_ae_mask(struct adf_accel_dev *accel_dev, u32 obj_num)
···
 		break;
 	}
 	hw_data->uof_get_num_objs = uof_get_num_objs;
+	hw_data->uof_get_obj_type = uof_get_obj_type;
 	hw_data->uof_get_ae_mask = uof_get_ae_mask;
 	hw_data->get_rp_group = get_rp_group;
 	hw_data->set_msix_rttable = adf_gen4_set_msix_default_rttable;
 	hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer;
-	hw_data->get_ring_to_svc_map = get_ring_to_svc_map;
+	hw_data->get_ring_to_svc_map = adf_gen4_get_ring_to_svc_map;
 	hw_data->disable_iov = adf_disable_sriov;
 	hw_data->ring_pair_reset = adf_gen4_ring_pair_reset;
 	hw_data->enable_pm = adf_gen4_enable_pm;

drivers/crypto/intel/qat/qat_common/Makefile

···
 			       adf_pfvf_pf_msg.o adf_pfvf_pf_proto.o \
 			       adf_pfvf_vf_msg.o adf_pfvf_vf_proto.o \
 			       adf_gen2_pfvf.o adf_gen4_pfvf.o
+
+intel_qat-$(CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION) += adf_heartbeat_inject.o

drivers/crypto/intel/qat/qat_common/adf_accel_devices.h

···
 	void (*set_msix_rttable)(struct adf_accel_dev *accel_dev);
 	const char *(*uof_get_name)(struct adf_accel_dev *accel_dev, u32 obj_num);
 	u32 (*uof_get_num_objs)(struct adf_accel_dev *accel_dev);
+	int (*uof_get_obj_type)(struct adf_accel_dev *accel_dev, u32 obj_num);
 	u32 (*uof_get_ae_mask)(struct adf_accel_dev *accel_dev, u32 obj_num);
 	int (*get_rp_group)(struct adf_accel_dev *accel_dev, u32 ae_mask);
 	u32 (*get_ena_thd_mask)(struct adf_accel_dev *accel_dev, u32 obj_num);
···
 	struct ratelimit_state vf2pf_ratelimit;
 	u32 vf_nr;
 	bool init;
+	bool restarting;
 	u8 vf_compat_ver;
 };
 
···
 	struct adf_error_counters ras_errors;
 	struct mutex state_lock; /* protect state of the device */
 	bool is_vf;
+	bool autoreset_on_error;
 	u32 accel_id;
 };
 #endif

drivers/crypto/intel/qat/qat_common/adf_aer.c

···
 #include <linux/delay.h>
 #include "adf_accel_devices.h"
 #include "adf_common_drv.h"
+#include "adf_pfvf_pf_msg.h"
+
+struct adf_fatal_error_data {
+	struct adf_accel_dev *accel_dev;
+	struct work_struct work;
+};
 
 static struct workqueue_struct *device_reset_wq;
+static struct workqueue_struct *device_sriov_wq;
 
 static pci_ers_result_t adf_error_detected(struct pci_dev *pdev,
 					   pci_channel_state_t state)
···
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
+	set_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
+	if (accel_dev->hw_device->exit_arb) {
+		dev_dbg(&pdev->dev, "Disabling arbitration\n");
+		accel_dev->hw_device->exit_arb(accel_dev);
+	}
+	adf_error_notifier(accel_dev);
+	adf_pf2vf_notify_fatal_error(accel_dev);
+	adf_dev_restarting_notify(accel_dev);
+	adf_pf2vf_notify_restarting(accel_dev);
+	adf_pf2vf_wait_for_restarting_complete(accel_dev);
+	pci_clear_master(pdev);
+	adf_dev_down(accel_dev, false);
+
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 
···
 	struct adf_accel_dev *accel_dev;
 	struct completion compl;
 	struct work_struct reset_work;
+};
+
+/* sriov dev data */
+struct adf_sriov_dev_data {
+	struct adf_accel_dev *accel_dev;
+	struct completion compl;
+	struct work_struct sriov_work;
 };
 
 void adf_reset_sbr(struct adf_accel_dev *accel_dev)
···
 	}
 }
 
+static void adf_device_sriov_worker(struct work_struct *work)
+{
+	struct adf_sriov_dev_data *sriov_data =
+		container_of(work, struct adf_sriov_dev_data, sriov_work);
+
+	adf_reenable_sriov(sriov_data->accel_dev);
+	complete(&sriov_data->compl);
+}
+
 static void adf_device_reset_worker(struct work_struct *work)
 {
 	struct adf_reset_dev_data *reset_data =
 		  container_of(work, struct adf_reset_dev_data, reset_work);
 	struct adf_accel_dev *accel_dev = reset_data->accel_dev;
+	unsigned long wait_jiffies = msecs_to_jiffies(10000);
+	struct adf_sriov_dev_data sriov_data;
 
 	adf_dev_restarting_notify(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");
-		if (reset_data->mode == ADF_DEV_RESET_ASYNC)
+		if (reset_data->mode == ADF_DEV_RESET_ASYNC ||
+		    completion_done(&reset_data->compl))
 			kfree(reset_data);
 		WARN(1, "QAT: device restart failed. Device is unusable\n");
 		return;
 	}
+
+	sriov_data.accel_dev = accel_dev;
+	init_completion(&sriov_data.compl);
+	INIT_WORK(&sriov_data.sriov_work, adf_device_sriov_worker);
+	queue_work(device_sriov_wq, &sriov_data.sriov_work);
+	if (wait_for_completion_timeout(&sriov_data.compl, wait_jiffies))
+		adf_pf2vf_notify_restarted(accel_dev);
+
 	adf_dev_restarted_notify(accel_dev);
 	clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
 
-	/* The dev is back alive. Notify the caller if in sync mode */
-	if (reset_data->mode == ADF_DEV_RESET_SYNC)
-		complete(&reset_data->compl);
-	else
+	/*
+	 * The dev is back alive. Notify the caller if in sync mode
+	 *
+	 * If device restart will take a more time than expected,
+	 * the schedule_reset() function can timeout and exit. This can be
+	 * detected by calling the completion_done() function. In this case
+	 * the reset_data structure needs to be freed here.
+	 */
+	if (reset_data->mode == ADF_DEV_RESET_ASYNC ||
+	    completion_done(&reset_data->compl))
 		kfree(reset_data);
+	else
+		complete(&reset_data->compl);
 }
 
 static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev,
···
 			dev_err(&GET_DEV(accel_dev),
 				"Reset device timeout expired\n");
 			ret = -EFAULT;
+		} else {
+			kfree(reset_data);
 		}
-		kfree(reset_data);
 		return ret;
 	}
 	return 0;
···
 static pci_ers_result_t adf_slot_reset(struct pci_dev *pdev)
 {
 	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+	int res = 0;
 
 	if (!accel_dev) {
 		pr_err("QAT: Can't find acceleration device\n");
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
-	if (adf_dev_aer_schedule_reset(accel_dev, ADF_DEV_RESET_SYNC))
+
+	if (!pdev->is_busmaster)
+		pci_set_master(pdev);
+	pci_restore_state(pdev);
+	pci_save_state(pdev);
+	res = adf_dev_up(accel_dev, false);
+	if (res && res != -EALREADY)
 		return PCI_ERS_RESULT_DISCONNECT;
 
+	adf_reenable_sriov(accel_dev);
+	adf_pf2vf_notify_restarted(accel_dev);
+	adf_dev_restarted_notify(accel_dev);
+	clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
···
 };
 EXPORT_SYMBOL_GPL(adf_err_handler);
 
+int adf_dev_autoreset(struct adf_accel_dev *accel_dev)
+{
+	if (accel_dev->autoreset_on_error)
+		return adf_dev_aer_schedule_reset(accel_dev, ADF_DEV_RESET_ASYNC);
+
+	return 0;
+}
+
+static void adf_notify_fatal_error_worker(struct work_struct *work)
+{
+	struct adf_fatal_error_data *wq_data =
+			container_of(work, struct adf_fatal_error_data, work);
+	struct adf_accel_dev *accel_dev = wq_data->accel_dev;
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+
+	adf_error_notifier(accel_dev);
+
+	if (!accel_dev->is_vf) {
+		/* Disable arbitration to stop processing of new requests */
+		if (accel_dev->autoreset_on_error && hw_device->exit_arb)
+			hw_device->exit_arb(accel_dev);
+		if (accel_dev->pf.vf_info)
+			adf_pf2vf_notify_fatal_error(accel_dev);
+		adf_dev_autoreset(accel_dev);
+	}
+
+	kfree(wq_data);
+}
+
+int adf_notify_fatal_error(struct adf_accel_dev *accel_dev)
+{
+	struct adf_fatal_error_data *wq_data;
+
+	wq_data = kzalloc(sizeof(*wq_data), GFP_ATOMIC);
+	if (!wq_data)
+		return -ENOMEM;
+
+	wq_data->accel_dev = accel_dev;
+	INIT_WORK(&wq_data->work, adf_notify_fatal_error_worker);
+	adf_misc_wq_queue_work(&wq_data->work);
+
+	return 0;
+}
+
 int adf_init_aer(void)
 {
 	device_reset_wq = alloc_workqueue("qat_device_reset_wq",
 					  WQ_MEM_RECLAIM, 0);
-	return !device_reset_wq ? -EFAULT : 0;
+	if (!device_reset_wq)
+		return -EFAULT;
+
+	device_sriov_wq = alloc_workqueue("qat_device_sriov_wq", 0, 0);
+	if (!device_sriov_wq)
+		return -EFAULT;
+
+	return 0;
 }
 
 void adf_exit_aer(void)
···
 	if (device_reset_wq)
 		destroy_workqueue(device_reset_wq);
 	device_reset_wq = NULL;
+
+	if (device_sriov_wq)
+		destroy_workqueue(device_sriov_wq);
+	device_sriov_wq = NULL;
 }

drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h

···
 	ADF_ETRMGR_BANK "%d" ADF_ETRMGR_CORE_AFFINITY
 #define ADF_ACCEL_STR "Accelerator%d"
 #define ADF_HEARTBEAT_TIMER  "HeartbeatTimer"
+#define ADF_SRIOV_ENABLED "SriovEnabled"
 
 #endif

drivers/crypto/intel/qat/qat_common/adf_clock.c

···
 	}
 
 	delta_us = timespec_to_us(&ts3) - timespec_to_us(&ts1);
+	if (!delta_us)
+		return -EINVAL;
+
 	temp = (timestamp2 - timestamp1) * ME_CLK_DIVIDER * 10;
 	temp = DIV_ROUND_CLOSEST_ULL(temp, delta_us);
 	/*

drivers/crypto/intel/qat/qat_common/adf_cnv_dbgfs.c

···
 
 #define CNV_ERR_INFO_MASK		GENMASK(11, 0)
 #define CNV_ERR_TYPE_MASK		GENMASK(15, 12)
-#define CNV_SLICE_ERR_MASK		GENMASK(7, 0)
 #define CNV_SLICE_ERR_SIGN_BIT_INDEX	7
 #define CNV_DELTA_ERR_SIGN_BIT_INDEX	11
 

drivers/crypto/intel/qat/qat_common/adf_common_drv.h

···
 	ADF_EVENT_SHUTDOWN,
 	ADF_EVENT_RESTARTING,
 	ADF_EVENT_RESTARTED,
+	ADF_EVENT_FATAL_ERROR,
 };
 
 struct service_hndl {
···
 
 void adf_devmgr_update_class_index(struct adf_hw_device_data *hw_data);
 void adf_clean_vf_map(bool);
+int adf_notify_fatal_error(struct adf_accel_dev *accel_dev);
+void adf_error_notifier(struct adf_accel_dev *accel_dev);
 int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev,
 		       struct adf_accel_dev *pf);
 void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev,
···
 extern const struct pci_error_handlers adf_err_handler;
 void adf_reset_sbr(struct adf_accel_dev *accel_dev);
 void adf_reset_flr(struct adf_accel_dev *accel_dev);
+int adf_dev_autoreset(struct adf_accel_dev *accel_dev);
 void adf_dev_restore(struct adf_accel_dev *accel_dev);
 int adf_init_aer(void);
 void adf_exit_aer(void);
 int adf_init_arb(struct adf_accel_dev *accel_dev);
 void adf_exit_arb(struct adf_accel_dev *accel_dev);
 void adf_update_ring_arb(struct adf_etr_ring_data *ring);
+int adf_disable_arb_thd(struct adf_accel_dev *accel_dev, u32 ae, u32 thr);
 
 int adf_dev_get(struct adf_accel_dev *accel_dev);
 void adf_dev_put(struct adf_accel_dev *accel_dev);
···
 #if defined(CONFIG_PCI_IOV)
 int adf_sriov_configure(struct pci_dev *pdev, int numvfs);
 void adf_disable_sriov(struct adf_accel_dev *accel_dev);
+void adf_reenable_sriov(struct adf_accel_dev *accel_dev);
 void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, u32 vf_mask);
 void adf_disable_all_vf2pf_interrupts(struct adf_accel_dev *accel_dev);
 bool adf_recv_and_handle_pf2vf_msg(struct adf_accel_dev *accel_dev);
···
 #define adf_sriov_configure NULL
 
 static inline void adf_disable_sriov(struct adf_accel_dev *accel_dev)
+{
+}
+
+static inline void adf_reenable_sriov(struct adf_accel_dev *accel_dev)
 {
 }
 

drivers/crypto/intel/qat/qat_common/adf_dev_mgr.c

···
 
 /**
  * adf_clean_vf_map() - Cleans VF id mapings
- *
- * Function cleans internal ids for virtual functions.
  * @vf: flag indicating whether mappings is cleaned
  *	for vfs only or for vfs and pfs
+ *
+ * Function cleans internal ids for virtual functions.
  */
 void adf_clean_vf_map(bool vf)
 {

drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c

···
 #include "adf_accel_devices.h"
 #include "adf_cfg_services.h"
 #include "adf_common_drv.h"
+#include "adf_fw_config.h"
 #include "adf_gen4_hw_data.h"
 #include "adf_gen4_pm.h"
 
···
 			 ADF_GEN4_ADMIN_ACCELENGINES;
 
 	if (srv_id == SVC_DCC) {
+		if (ae_cnt > ICP_QAT_HW_AE_DELIMITER)
+			return -EINVAL;
+
 		memcpy(thd2arb_map, thrd_to_arb_map_dcc,
 		       array_size(sizeof(*thd2arb_map), ae_cnt));
 		return 0;
···
 	return 0;
 }
 EXPORT_SYMBOL_GPL(adf_gen4_init_thd2arb_map);
+
+u16 adf_gen4_get_ring_to_svc_map(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_data = GET_HW_DATA(accel_dev);
+	enum adf_cfg_service_type rps[RP_GROUP_COUNT] = { };
+	unsigned int ae_mask, start_id, worker_obj_cnt, i;
+	u16 ring_to_svc_map;
+	int rp_group;
+
+	if (!hw_data->get_rp_group || !hw_data->uof_get_ae_mask ||
+	    !hw_data->uof_get_obj_type || !hw_data->uof_get_num_objs)
+		return 0;
+
+	/* If dcc, all rings handle compression requests */
+	if (adf_get_service_enabled(accel_dev) == SVC_DCC) {
+		for (i = 0; i < RP_GROUP_COUNT; i++)
+			rps[i] = COMP;
+		goto set_mask;
+	}
+
+	worker_obj_cnt = hw_data->uof_get_num_objs(accel_dev) -
+			 ADF_GEN4_ADMIN_ACCELENGINES;
+	start_id = worker_obj_cnt - RP_GROUP_COUNT;
+
+	for (i = start_id; i < worker_obj_cnt; i++) {
+		ae_mask = hw_data->uof_get_ae_mask(accel_dev, i);
+		rp_group = hw_data->get_rp_group(accel_dev, ae_mask);
+		if (rp_group >= RP_GROUP_COUNT || rp_group < RP_GROUP_0)
+			return 0;
+
+		switch (hw_data->uof_get_obj_type(accel_dev, i)) {
+		case ADF_FW_SYM_OBJ:
+			rps[rp_group] = SYM;
+			break;
+		case ADF_FW_ASYM_OBJ:
+			rps[rp_group] = ASYM;
+			break;
+		case ADF_FW_DC_OBJ:
+			rps[rp_group] = COMP;
+			break;
+		default:
+			rps[rp_group] = 0;
+			break;
+		}
+	}
+
+set_mask:
+	ring_to_svc_map = rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_0_SHIFT |
+			  rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_1_SHIFT |
+			  rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_2_SHIFT |
+			  rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_3_SHIFT;
+
+	return ring_to_svc_map;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_ring_to_svc_map);

drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h

···
 void adf_gen4_set_msix_default_rttable(struct adf_accel_dev *accel_dev);
 void adf_gen4_set_ssm_wdtimer(struct adf_accel_dev *accel_dev);
 int adf_gen4_init_thd2arb_map(struct adf_accel_dev *accel_dev);
+u16 adf_gen4_get_ring_to_svc_map(struct adf_accel_dev *accel_dev);
 
 #endif

drivers/crypto/intel/qat/qat_common/adf_gen4_ras.c

···
 static bool adf_handle_ssmcpppar_err(struct adf_accel_dev *accel_dev,
 				     void __iomem *csr, u32 iastatssm)
 {
-	u32 reg = ADF_CSR_RD(csr, ADF_GEN4_SSMCPPERR);
-	u32 bits_num = BITS_PER_REG(reg);
+	u32 reg, bits_num = BITS_PER_REG(reg);
 	bool reset_required = false;
 	unsigned long errs_bits;
 	u32 bit_iterator;
···
 static bool adf_handle_ser_err_ssmsh(struct adf_accel_dev *accel_dev,
 				     void __iomem *csr, u32 iastatssm)
 {
-	u32 reg = ADF_CSR_RD(csr, ADF_GEN4_SER_ERR_SSMSH);
-	u32 bits_num = BITS_PER_REG(reg);
+	u32 reg, bits_num = BITS_PER_REG(reg);
 	bool reset_required = false;
 	unsigned long errs_bits;
 	u32 bit_iterator;

drivers/crypto/intel/qat/qat_common/adf_heartbeat.c

···
 
 #define ADF_HB_EMPTY_SIG 0xA5A5A5A5
 
-/* Heartbeat counter pair */
-struct hb_cnt_pair {
-	__u16 resp_heartbeat_cnt;
-	__u16 req_heartbeat_cnt;
-};
-
 static int adf_hb_check_polling_freq(struct adf_accel_dev *accel_dev)
 {
 	u64 curr_time = adf_clock_get_current_time();
···
 	return ret;
 }
 
+static void adf_heartbeat_reset(struct adf_accel_dev *accel_dev)
+{
+	u64 curr_time = adf_clock_get_current_time();
+	u64 time_since_reset = curr_time - accel_dev->heartbeat->last_hb_reset_time;
+
+	if (time_since_reset < ADF_CFG_HB_RESET_MS)
+		return;
+
+	accel_dev->heartbeat->last_hb_reset_time = curr_time;
+	if (adf_notify_fatal_error(accel_dev))
+		dev_err(&GET_DEV(accel_dev), "Failed to notify fatal error\n");
+}
+
 void adf_heartbeat_status(struct adf_accel_dev *accel_dev,
 			  enum adf_device_heartbeat_status *hb_status)
 {
···
 			"Heartbeat ERROR: QAT is not responding.\n");
 		*hb_status = HB_DEV_UNRESPONSIVE;
 		hb->hb_failed_counter++;
+		adf_heartbeat_reset(accel_dev);
 		return;
 	}
 

drivers/crypto/intel/qat/qat_common/adf_heartbeat.h

···
 #define ADF_CFG_HB_TIMER_DEFAULT_MS 500
 #define ADF_CFG_HB_COUNT_THRESHOLD 3
 
+#define ADF_CFG_HB_RESET_MS 5000
+
 enum adf_device_heartbeat_status {
 	HB_DEV_UNRESPONSIVE = 0,
 	HB_DEV_ALIVE,
 	HB_DEV_UNSUPPORTED,
+};
+
+/* Heartbeat counter pair */
+struct hb_cnt_pair {
+	__u16 resp_heartbeat_cnt;
+	__u16 req_heartbeat_cnt;
 };
 
 struct adf_heartbeat {
···
 	unsigned int hb_failed_counter;
 	unsigned int hb_timer;
 	u64 last_hb_check_time;
+	u64 last_hb_reset_time;
 	bool ctrs_cnt_checked;
 	struct hb_dma_addr {
 		dma_addr_t phy_addr;
···
 		struct dentry *cfg;
 		struct dentry *sent;
 		struct dentry *failed;
+#ifdef CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION
+		struct dentry *inject_error;
+#endif
 	} dbgfs;
 };
 
···
 void adf_heartbeat_status(struct adf_accel_dev *accel_dev,
 			  enum adf_device_heartbeat_status *hb_status);
 void adf_heartbeat_check_ctrs(struct adf_accel_dev *accel_dev);
+
+#ifdef CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION
+int adf_heartbeat_inject_error(struct adf_accel_dev *accel_dev);
+#else
+static inline int adf_heartbeat_inject_error(struct adf_accel_dev *accel_dev)
+{
+	return -EPERM;
+}
+#endif
 
 #else
 static inline int adf_heartbeat_init(struct adf_accel_dev *accel_dev)

drivers/crypto/intel/qat/qat_common/adf_heartbeat_dbgfs.c

···
 	.write = adf_hb_cfg_write,
 };
 
+static ssize_t adf_hb_error_inject_write(struct file *file,
+					 const char __user *user_buf,
+					 size_t count, loff_t *ppos)
+{
+	struct adf_accel_dev *accel_dev = file->private_data;
+	char buf[3];
+	int ret;
+
+	/* last byte left as string termination */
+	if (*ppos != 0 || count != 2)
+		return -EINVAL;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+	buf[count] = '\0';
+
+	if (buf[0] != '1')
+		return -EINVAL;
+
+	ret = adf_heartbeat_inject_error(accel_dev);
+	if (ret) {
+		dev_err(&GET_DEV(accel_dev),
+			"Heartbeat error injection failed with status %d\n",
+			ret);
+		return ret;
+	}
+
+	dev_info(&GET_DEV(accel_dev), "Heartbeat error injection enabled\n");
+
+	return count;
+}
+
+static const struct file_operations adf_hb_error_inject_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = adf_hb_error_inject_write,
+};
+
 void adf_heartbeat_dbgfs_add(struct adf_accel_dev *accel_dev)
 {
 	struct adf_heartbeat *hb = accel_dev->heartbeat;
···
 					       &hb->hb_failed_counter, &adf_hb_stats_fops);
 	hb->dbgfs.cfg = debugfs_create_file("config", 0600, hb->dbgfs.base_dir,
 					    accel_dev, &adf_hb_cfg_fops);
+
+	if (IS_ENABLED(CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION)) {
+		struct dentry *inject_error __maybe_unused;
+
+		inject_error = debugfs_create_file("inject_error", 0200,
+						   hb->dbgfs.base_dir, accel_dev,
+						   &adf_hb_error_inject_fops);
+#ifdef CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION
+		hb->dbgfs.inject_error = inject_error;
+#endif
+	}
 }
 EXPORT_SYMBOL_GPL(adf_heartbeat_dbgfs_add);
 
···
 	hb->dbgfs.failed = NULL;
 	debugfs_remove(hb->dbgfs.cfg);
 	hb->dbgfs.cfg = NULL;
+#ifdef CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION
+	debugfs_remove(hb->dbgfs.inject_error);
+	hb->dbgfs.inject_error = NULL;
+#endif
 	debugfs_remove(hb->dbgfs.base_dir);
 	hb->dbgfs.base_dir = NULL;
 }

drivers/crypto/intel/qat/qat_common/adf_heartbeat_inject.c

···
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Intel Corporation */
+#include <linux/random.h>
+
+#include "adf_admin.h"
+#include "adf_common_drv.h"
+#include "adf_heartbeat.h"
+
+#define MAX_HB_TICKS 0xFFFFFFFF
+
+static int adf_hb_set_timer_to_max(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+
+	accel_dev->heartbeat->hb_timer = 0;
+
+	if (hw_data->stop_timer)
+		hw_data->stop_timer(accel_dev);
+
+	return adf_send_admin_hb_timer(accel_dev, MAX_HB_TICKS);
+}
+
+static void adf_set_hb_counters_fail(struct adf_accel_dev *accel_dev, u32 ae,
+				     u32 thr)
+{
+	struct hb_cnt_pair *stats = accel_dev->heartbeat->dma.virt_addr;
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	const size_t max_aes = hw_device->get_num_aes(hw_device);
+	const size_t hb_ctrs = hw_device->num_hb_ctrs;
+	size_t thr_id = ae * hb_ctrs + thr;
+	u16 num_rsp = stats[thr_id].resp_heartbeat_cnt;
+
+	/*
+	 * Inject live.req != live.rsp and live.rsp == last.rsp
+	 * to trigger the heartbeat error detection
+	 */
+	stats[thr_id].req_heartbeat_cnt++;
+	stats += (max_aes * hb_ctrs);
+	stats[thr_id].resp_heartbeat_cnt = num_rsp;
+}
+
+int adf_heartbeat_inject_error(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	const size_t max_aes = hw_device->get_num_aes(hw_device);
+	const size_t hb_ctrs = hw_device->num_hb_ctrs;
+	u32 rand, rand_ae, rand_thr;
+	unsigned long ae_mask;
+	int ret;
+
+	ae_mask = hw_device->ae_mask;
+
+	do {
+		/* Ensure we have a valid ae */
+		get_random_bytes(&rand, sizeof(rand));
+		rand_ae = rand % max_aes;
+	} while (!test_bit(rand_ae, &ae_mask));
+
+	get_random_bytes(&rand, sizeof(rand));
+	rand_thr = rand % hb_ctrs;
+
+	/* Increase the heartbeat timer to prevent FW updating HB counters */
+	ret = adf_hb_set_timer_to_max(accel_dev);
+	if (ret)
+		return ret;
+
+	/* Configure worker threads to stop processing any packet */
+	ret = adf_disable_arb_thd(accel_dev, rand_ae, rand_thr);
+	if (ret)
+		return ret;
+
+	/* Change HB counters memory to simulate a hang */
+	adf_set_hb_counters_fail(accel_dev, rand_ae, rand_thr);
+
+	return 0;
+}

drivers/crypto/intel/qat/qat_common/adf_hw_arbiter.c

···
 		csr_ops->write_csr_ring_srv_arb_en(csr, i, 0);
 }
 EXPORT_SYMBOL_GPL(adf_exit_arb);
+
+int adf_disable_arb_thd(struct adf_accel_dev *accel_dev, u32 ae, u32 thr)
+{
+	void __iomem *csr = accel_dev->transport->banks[0].csr_addr;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	const u32 *thd_2_arb_cfg;
+	struct arb_info info;
+	u32 ae_thr_map;
+
+	if (ADF_AE_STRAND0_THREAD == thr || ADF_AE_STRAND1_THREAD == thr)
+		thr = ADF_AE_ADMIN_THREAD;
+
+	hw_data->get_arb_info(&info);
+	thd_2_arb_cfg = hw_data->get_arb_mapping(accel_dev);
+	if (!thd_2_arb_cfg)
+		return -EFAULT;
+
+	/* Disable scheduling for this particular AE and thread */
+	ae_thr_map = *(thd_2_arb_cfg + ae);
+	ae_thr_map &= ~(GENMASK(3, 0) << (thr * BIT(2)));
+
+	WRITE_CSR_ARB_WT2SAM(csr, info.arb_offset, info.wt2sam_offset, ae,
+			     ae_thr_map);
+	return 0;
+}

drivers/crypto/intel/qat/qat_common/adf_init.c

···
 	return 0;
 }
 
+void adf_error_notifier(struct adf_accel_dev *accel_dev)
+{
+	struct service_hndl *service;
+
+	list_for_each_entry(service, &service_table, list) {
+		if (service->event_hld(accel_dev, ADF_EVENT_FATAL_ERROR))
+			dev_err(&GET_DEV(accel_dev),
+				"Failed to send error event to %s.\n",
+				service->name);
+	}
+}
+
 static int adf_dev_shutdown_cache_cfg(struct adf_accel_dev *accel_dev)
 {
 	char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0};

drivers/crypto/intel/qat/qat_common/adf_isr.c

···
 
 	if (ras_ops->handle_interrupt &&
 	    ras_ops->handle_interrupt(accel_dev, &reset_required)) {
-		if (reset_required)
+		if (reset_required) {
 			dev_err(&GET_DEV(accel_dev), "Fatal error, reset required\n");
+			if (adf_notify_fatal_error(accel_dev))
+				dev_err(&GET_DEV(accel_dev),
+					"Failed to notify fatal error\n");
+		}
+
 		return true;
 	}
 
···
 	if (!accel_dev->pf.vf_info)
 		msix_num_entries += hw_data->num_banks;
 
-	irqs = kzalloc_node(msix_num_entries * sizeof(*irqs),
+	irqs = kcalloc_node(msix_num_entries, sizeof(*irqs),
 			    GFP_KERNEL, dev_to_node(&GET_DEV(accel_dev)));
 	if (!irqs)
 		return -ENOMEM;
···
 
 /**
  * adf_init_misc_wq() - Init misc workqueue
- *
- * Function init workqueue 'qat_misc_wq' for general purpose.
  *
  * Return: 0 on success, error code otherwise.
  */

drivers/crypto/intel/qat/qat_common/adf_pfvf_msg.h

···
 	ADF_PF2VF_MSGTYPE_RESTARTING		= 0x01,
 	ADF_PF2VF_MSGTYPE_VERSION_RESP		= 0x02,
 	ADF_PF2VF_MSGTYPE_BLKMSG_RESP		= 0x03,
+	ADF_PF2VF_MSGTYPE_FATAL_ERROR		= 0x04,
+	ADF_PF2VF_MSGTYPE_RESTARTED		= 0x05,
 /* Values from 0x10 are Gen4 specific, message type is only 4 bits in Gen2 devices. */
 	ADF_PF2VF_MSGTYPE_RP_RESET_RESP		= 0x10,
 };
···
 	ADF_VF2PF_MSGTYPE_LARGE_BLOCK_REQ	= 0x07,
 	ADF_VF2PF_MSGTYPE_MEDIUM_BLOCK_REQ	= 0x08,
 	ADF_VF2PF_MSGTYPE_SMALL_BLOCK_REQ	= 0x09,
+	ADF_VF2PF_MSGTYPE_RESTARTING_COMPLETE	= 0x0a,
 /* Values from 0x10 are Gen4 specific, message type is only 4 bits in Gen2 devices. */
 	ADF_VF2PF_MSGTYPE_RP_RESET		= 0x10,
 };
···
 	ADF_PFVF_COMPAT_FAST_ACK		= 0x03,
 	/* Ring to service mapping support for non-standard mappings */
 	ADF_PFVF_COMPAT_RING_TO_SVC_MAP		= 0x04,
+	/* Fallback compat */
+	ADF_PFVF_COMPAT_FALLBACK		= 0x05,
 	/* Reference to the latest version */
-	ADF_PFVF_COMPAT_THIS_VERSION		= 0x04,
+	ADF_PFVF_COMPAT_THIS_VERSION		= 0x05,
 };
 
 /* PF->VF Version Response */

drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c

···
 // SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only)
 /* Copyright(c) 2015 - 2021 Intel Corporation */
+#include <linux/delay.h>
 #include <linux/pci.h>
 #include "adf_accel_devices.h"
 #include "adf_pfvf_msg.h"
 #include "adf_pfvf_pf_msg.h"
 #include "adf_pfvf_pf_proto.h"
+
+#define ADF_PF_WAIT_RESTARTING_COMPLETE_DELAY	100
+#define ADF_VF_SHUTDOWN_RETRY			100
 
 void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev)
 {
···
 	struct pfvf_message msg = { .type = ADF_PF2VF_MSGTYPE_RESTARTING };
 	int i, num_vfs = pci_num_vf(accel_to_pci_dev(accel_dev));
 
+	dev_dbg(&GET_DEV(accel_dev), "pf2vf notify restarting\n");
 	for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++) {
-		if (vf->init && adf_send_pf2vf_msg(accel_dev, i, msg))
+		vf->restarting = false;
+		if (!vf->init)
+			continue;
+		if (adf_send_pf2vf_msg(accel_dev, i, msg))
 			dev_err(&GET_DEV(accel_dev),
 				"Failed to send restarting msg to VF%d\n", i);
+		else if (vf->vf_compat_ver >= ADF_PFVF_COMPAT_FALLBACK)
+			vf->restarting = true;
+	}
+}
+
+void adf_pf2vf_wait_for_restarting_complete(struct adf_accel_dev *accel_dev)
+{
+	int num_vfs = pci_num_vf(accel_to_pci_dev(accel_dev));
+	int i, retries = ADF_VF_SHUTDOWN_RETRY;
+	struct adf_accel_vf_info *vf;
+	bool vf_running;
+
+	dev_dbg(&GET_DEV(accel_dev), "pf2vf wait for restarting complete\n");
+	do {
+		vf_running = false;
+		for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++)
+			if (vf->restarting)
+				vf_running = true;
+		if (!vf_running)
+			break;
+		msleep(ADF_PF_WAIT_RESTARTING_COMPLETE_DELAY);
+	} while (--retries);
+
+	if (vf_running)
+		dev_warn(&GET_DEV(accel_dev), "Some VFs are still running\n");
+}
+
+void adf_pf2vf_notify_restarted(struct adf_accel_dev *accel_dev)
+{
+	struct pfvf_message msg = { .type = ADF_PF2VF_MSGTYPE_RESTARTED };
+	int i, num_vfs = pci_num_vf(accel_to_pci_dev(accel_dev));
+	struct adf_accel_vf_info *vf;
+
+	dev_dbg(&GET_DEV(accel_dev), "pf2vf notify restarted\n");
+	for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++) {
+		if (vf->init && vf->vf_compat_ver >= ADF_PFVF_COMPAT_FALLBACK &&
+		    adf_send_pf2vf_msg(accel_dev, i, msg))
+			dev_err(&GET_DEV(accel_dev),
+				"Failed to send restarted msg to VF%d\n", i);
+	}
+}
+
+void adf_pf2vf_notify_fatal_error(struct adf_accel_dev *accel_dev)
+{
+	struct pfvf_message msg = { .type = ADF_PF2VF_MSGTYPE_FATAL_ERROR };
+	int i, num_vfs = pci_num_vf(accel_to_pci_dev(accel_dev));
+	struct adf_accel_vf_info *vf;
+
+	dev_dbg(&GET_DEV(accel_dev), "pf2vf notify fatal error\n");
+	for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++) {
+		if (vf->init && vf->vf_compat_ver >= ADF_PFVF_COMPAT_FALLBACK &&
+		    adf_send_pf2vf_msg(accel_dev, i, msg))
+			dev_err(&GET_DEV(accel_dev),
+				"Failed to send fatal error msg to VF%d\n", i);
 	}
 }
 

drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.h

···
 
 #include "adf_accel_devices.h"
 
+#if defined(CONFIG_PCI_IOV)
 void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev);
+void adf_pf2vf_wait_for_restarting_complete(struct adf_accel_dev *accel_dev);
+void adf_pf2vf_notify_restarted(struct adf_accel_dev *accel_dev);
+void adf_pf2vf_notify_fatal_error(struct adf_accel_dev *accel_dev);
+#else
+static inline void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev)
+{
+}
+
+static inline void adf_pf2vf_wait_for_restarting_complete(struct adf_accel_dev *accel_dev)
+{
+}
+
+static inline void adf_pf2vf_notify_restarted(struct adf_accel_dev *accel_dev)
+{
+}
+
+static inline void adf_pf2vf_notify_fatal_error(struct adf_accel_dev *accel_dev)
+{
+}
+#endif
 
 typedef int (*adf_pf2vf_blkmsg_provider)(struct adf_accel_dev *accel_dev,
 					 u8 *buffer, u8 compat);

drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c

···
 		vf_info->init = false;
 		}
 		break;
+	case ADF_VF2PF_MSGTYPE_RESTARTING_COMPLETE:
+		{
+		dev_dbg(&GET_DEV(accel_dev),
+			"Restarting Complete received from VF%d\n", vf_nr);
+		vf_info->restarting = false;
+		vf_info->init = false;
+		}
+		break;
 	case ADF_VF2PF_MSGTYPE_LARGE_BLOCK_REQ:
 	case ADF_VF2PF_MSGTYPE_MEDIUM_BLOCK_REQ:
 	case ADF_VF2PF_MSGTYPE_SMALL_BLOCK_REQ:

drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_proto.c

···
 
 		adf_pf2vf_handle_pf_restarting(accel_dev);
 		return false;
+	case ADF_PF2VF_MSGTYPE_RESTARTED:
+		dev_dbg(&GET_DEV(accel_dev), "Restarted message received from PF\n");
+		return true;
+	case ADF_PF2VF_MSGTYPE_FATAL_ERROR:
+		dev_err(&GET_DEV(accel_dev), "Fatal error received from PF\n");
+		return true;
 	case ADF_PF2VF_MSGTYPE_VERSION_RESP:
 	case ADF_PF2VF_MSGTYPE_BLKMSG_RESP:
 	case ADF_PF2VF_MSGTYPE_RP_RESET_RESP:

drivers/crypto/intel/qat/qat_common/adf_rl.c

···
 	sla_type_arr[node_id] = NULL;
 }
 
+static void free_all_sla(struct adf_accel_dev *accel_dev)
+{
+	struct adf_rl *rl_data = accel_dev->rate_limiting;
+	int sla_id;
+
+	mutex_lock(&rl_data->rl_lock);
+
+	for (sla_id = 0; sla_id < RL_NODES_CNT_MAX; sla_id++) {
+		if (!rl_data->sla[sla_id])
+			continue;
+
+		kfree(rl_data->sla[sla_id]);
+		rl_data->sla[sla_id] = NULL;
+	}
+
+	mutex_unlock(&rl_data->rl_lock);
+}
+
 /**
  * add_update_sla() - handles the creation and the update of an SLA
  * @accel_dev: pointer to acceleration device structure
···
 		return;
 
 	adf_sysfs_rl_rm(accel_dev);
-	adf_rl_remove_sla_all(accel_dev, true);
+	free_all_sla(accel_dev);
 }
 
 void adf_rl_exit(struct adf_accel_dev *accel_dev)

drivers/crypto/intel/qat/qat_common/adf_sriov.c

···
 		/* This ptr will be populated when VFs will be created */
 		vf_info->accel_dev = accel_dev;
 		vf_info->vf_nr = i;
-		vf_info->vf_compat_ver = 0;
 
 		mutex_init(&vf_info->pf2vf_lock);
 		ratelimit_state_init(&vf_info->vf2pf_ratelimit,
···
 	return pci_enable_sriov(pdev, totalvfs);
 }
 
+void adf_reenable_sriov(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+	char cfg[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0};
+	unsigned long val = 0;
+
+	if (adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC,
+				    ADF_SRIOV_ENABLED, cfg))
+		return;
+
+	if (!accel_dev->pf.vf_info)
+		return;
+
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_CY,
+					&val, ADF_DEC))
+		return;
+
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_DC,
+					&val, ADF_DEC))
+		return;
+
+	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
+	dev_dbg(&pdev->dev, "Re-enabling SRIOV\n");
+	adf_enable_sriov(accel_dev);
+}
+
 /**
  * adf_disable_sriov() - Disable SRIOV for the device
  * @accel_dev:  Pointer to accel device.
···
 		return;
 
 	adf_pf2vf_notify_restarting(accel_dev);
+	adf_pf2vf_wait_for_restarting_complete(accel_dev);
 	pci_disable_sriov(accel_to_pci_dev(accel_dev));
 
 	/* Disable VF to PF interrupts */
···
 	for (i = 0, vf = accel_dev->pf.vf_info; i < totalvfs; i++, vf++)
 		mutex_destroy(&vf->pf2vf_lock);
 
-	kfree(accel_dev->pf.vf_info);
-	accel_dev->pf.vf_info = NULL;
+	if (!test_bit(ADF_STATUS_RESTARTING, &accel_dev->status)) {
+		kfree(accel_dev->pf.vf_info);
+		accel_dev->pf.vf_info = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(adf_disable_sriov);
 
···
 	ret = adf_enable_sriov(accel_dev);
 	if (ret)
 		return ret;
+
+	val = 1;
+	adf_cfg_add_key_value_param(accel_dev, ADF_GENERAL_SEC, ADF_SRIOV_ENABLED,
+				    &val, ADF_DEC);
 
 	return numvfs;
 }

drivers/crypto/intel/qat/qat_common/adf_sysfs.c

···
 }
 static DEVICE_ATTR_RW(pm_idle_enabled);
 
+static ssize_t auto_reset_show(struct device *dev, struct device_attribute *attr,
+			       char *buf)
+{
+	char *auto_reset;
+	struct adf_accel_dev *accel_dev;
+
+	accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev));
+	if (!accel_dev)
+		return -EINVAL;
+
+	auto_reset = accel_dev->autoreset_on_error ? "on" : "off";
+
+	return sysfs_emit(buf, "%s\n", auto_reset);
+}
+
+static ssize_t auto_reset_store(struct device *dev, struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct adf_accel_dev *accel_dev;
+	bool enabled = false;
+	int ret;
+
+	ret = kstrtobool(buf, &enabled);
+	if (ret)
+		return ret;
+
+	accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev));
+	if (!accel_dev)
+		return -EINVAL;
+
+	accel_dev->autoreset_on_error = enabled;
+
+	return count;
+}
+static DEVICE_ATTR_RW(auto_reset);
+
 static DEVICE_ATTR_RW(state);
 static DEVICE_ATTR_RW(cfg_services);
 
···
 	&dev_attr_pm_idle_enabled.attr,
 	&dev_attr_rp2srv.attr,
 	&dev_attr_num_rps.attr,
+	&dev_attr_auto_reset.attr,
 	NULL,
 };
 

drivers/crypto/intel/qat/qat_common/adf_vf_isr.c

···
 /**
  * adf_init_vf_wq() - Init workqueue for VF
  *
- * Function init workqueue 'adf_vf_stop_wq' for VF.
- *
  * Return: 0 on success, error code otherwise.
  */
 int __init adf_init_vf_wq(void)

drivers/crypto/intel/qat/qat_common/qat_comp_algs.c

···
 #include "qat_compression.h"
 #include "qat_algs_send.h"
 
-#define QAT_RFC_1950_HDR_SIZE 2
-#define QAT_RFC_1950_FOOTER_SIZE 4
-#define QAT_RFC_1950_CM_DEFLATE 8
-#define QAT_RFC_1950_CM_DEFLATE_CINFO_32K 7
-#define QAT_RFC_1950_CM_MASK 0x0f
-#define QAT_RFC_1950_CM_OFFSET 4
-#define QAT_RFC_1950_DICT_MASK 0x20
-#define QAT_RFC_1950_COMP_HDR 0x785e
-
 static DEFINE_MUTEX(algs_lock);
 static unsigned int active_devs;
 

drivers/crypto/intel/qat/qat_common/qat_crypto.c

···
 }
 
 /**
- * qat_crypto_vf_dev_config()
- *     create dev config required to create crypto inst.
+ * qat_crypto_vf_dev_config() - create dev config required to create
+ * crypto inst.
  *
  * @accel_dev: Pointer to acceleration device.
  *

drivers/crypto/rockchip/rk3288_crypto.c

···
 	}
 
 	crypto_info->engine = crypto_engine_alloc_init(&pdev->dev, true);
+	if (!crypto_info->engine) {
+		err = -ENOMEM;
+		goto err_crypto;
+	}
+
 	crypto_engine_start(crypto_info->engine);
 	init_completion(&crypto_info->complete);
 

drivers/crypto/virtio/virtio_crypto_akcipher_algs.c

···
 	struct virtio_crypto *vcrypto = ctx->vcrypto;
 	struct virtio_crypto_op_data_req *req_data = vc_req->req_data;
 	struct scatterlist *sgs[4], outhdr_sg, inhdr_sg, srcdata_sg, dstdata_sg;
-	void *src_buf = NULL, *dst_buf = NULL;
+	void *src_buf, *dst_buf = NULL;
 	unsigned int num_out = 0, num_in = 0;
 	int node = dev_to_node(&vcrypto->vdev->dev);
 	unsigned long flags;
-	int ret = -ENOMEM;
+	int ret;
 	bool verify = vc_akcipher_req->opcode == VIRTIO_CRYPTO_AKCIPHER_VERIFY;
 	unsigned int src_len = verify ? req->src_len + req->dst_len : req->src_len;
 
···
 	/* src data */
 	src_buf = kcalloc_node(src_len, 1, GFP_KERNEL, node);
 	if (!src_buf)
-		goto err;
+		return -ENOMEM;
 
 	if (verify) {
 		/* for verify operation, both src and dst data work as OUT direction */
···
 		/* dst data */
 		dst_buf = kcalloc_node(req->dst_len, 1, GFP_KERNEL, node);
 		if (!dst_buf)
-			goto err;
+			goto free_src;
 
 		sg_init_one(&dstdata_sg, dst_buf, req->dst_len);
 		sgs[num_out + num_in++] = &dstdata_sg;
···
 	return 0;
 
 err:
-	kfree(src_buf);
 	kfree(dst_buf);
-
+free_src:
+	kfree(src_buf);
 	return -ENOMEM;
 }
 

drivers/crypto/virtio/virtio_crypto_core.c

···
 			virtio_crypto_ctrlq_callback(vc_ctrl_req);
 			spin_lock_irqsave(&vcrypto->ctrl_lock, flags);
 		}
-		if (unlikely(virtqueue_is_broken(vq)))
-			break;
 	} while (!virtqueue_enable_cb(vq));
 	spin_unlock_irqrestore(&vcrypto->ctrl_lock, flags);
 }

drivers/crypto/vmx/.gitignore

···
-# SPDX-License-Identifier: GPL-2.0-only
-aesp8-ppc.S
-ghashp8-ppc.S

drivers/crypto/vmx/Kconfig

···
-# SPDX-License-Identifier: GPL-2.0-only
-config CRYPTO_DEV_VMX_ENCRYPT
-	tristate "Encryption acceleration support on P8 CPU"
-	depends on CRYPTO_DEV_VMX
-	select CRYPTO_AES
-	select CRYPTO_CBC
-	select CRYPTO_CTR
-	select CRYPTO_GHASH
-	select CRYPTO_XTS
-	default m
-	help
-	  Support for VMX cryptographic acceleration instructions on Power8 CPU.
-	  This module supports acceleration for AES and GHASH in hardware. If you
-	  choose 'M' here, this module will be called vmx-crypto.

drivers/crypto/vmx/Makefile

···
-# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o
-vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o
-
-ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
-override flavour := linux-ppc64le
-else
-ifdef CONFIG_PPC64_ELF_ABI_V2
-override flavour := linux-ppc64-elfv2
-else
-override flavour := linux-ppc64
-endif
-endif
-
-quiet_cmd_perl = PERL    $@
-      cmd_perl = $(PERL) $< $(flavour) > $@
-
-targets += aesp8-ppc.S ghashp8-ppc.S
-
-$(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

drivers/crypto/vmx/ppc-xlate.pl

···
-#!/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;
-my $elfv2abi=(($flavour =~ /linux-ppc64le/) or ($flavour =~ /linux-ppc64-elfv2/))?1:0;
-my $dotfunctions=($elfv2abi=~1)?0:1;
-
-################################################################
-# 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 ($elfv2abi);
-    $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	$name,.-".($dotfunctions?".":"").$name;
-	$ret .= "\n.size	.$name,.-.$name" if ($dotfunctions);
-	$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 $no_vrsave = ($elfv2abi);
-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;

drivers/crypto/xilinx/zynqmp-aes-gcm.c

···
 		err = zynqmp_aes_aead_cipher(areq);
 	}
 
+	local_bh_disable();
 	crypto_finalize_aead_request(engine, areq, err);
+	local_bh_enable();
+
 	return 0;
 }
 

include/crypto/internal/hash.h

···
 		!(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY);
 }
 
-bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg);
-
 int crypto_grab_ahash(struct crypto_ahash_spawn *spawn,
 		      struct crypto_instance *inst,
 		      const char *name, u32 type, u32 mask);

include/crypto/public_key.h

···
 #ifndef _LINUX_PUBLIC_KEY_H
 #define _LINUX_PUBLIC_KEY_H
 
+#include <linux/errno.h>
 #include <linux/keyctl.h>
 #include <linux/oid_registry.h>
 

include/linux/hisi_acc_qm.h

···
 #define QM_MB_CMD_CQC_BT                0x5
 #define QM_MB_CMD_SQC_VFT_V2            0x6
 #define QM_MB_CMD_STOP_QP               0x8
+#define QM_MB_CMD_FLUSH_QM		0x9
 #define QM_MB_CMD_SRC                   0xc
 #define QM_MB_CMD_DST                   0xd
 
···
 	QM_SUPPORT_DB_ISOLATION = 0x0,
 	QM_SUPPORT_FUNC_QOS,
 	QM_SUPPORT_STOP_QP,
+	QM_SUPPORT_STOP_FUNC,
 	QM_SUPPORT_MB_COMMAND,
 	QM_SUPPORT_SVA_PREFETCH,
 	QM_SUPPORT_RPM,
···
 struct qm_dev_alg {
 	u64 alg_msk;
 	const char *alg;
+};
+
+struct qm_dev_dfx {
+	u32 dev_state;
+	u32 dev_timeout;
 };
 
 struct dfx_diff_registers {
···
 	struct dentry *debug_root;
 	struct dentry *qm_d;
 	struct debugfs_file files[DEBUG_FILE_NUM];
+	struct qm_dev_dfx dev_dfx;
 	unsigned int *qm_last_words;
 	/* ACC engines recoreding last regs */
 	unsigned int *last_words;
···
 int hisi_qm_start(struct hisi_qm *qm);
 int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r);
 int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg);
-int hisi_qm_stop_qp(struct hisi_qp *qp);
+void hisi_qm_stop_qp(struct hisi_qp *qp);
 int hisi_qp_send(struct hisi_qp *qp, const void *msg);
 void hisi_qm_debug_init(struct hisi_qm *qm);
 void hisi_qm_debug_regs_clear(struct hisi_qm *qm);

tools/crypto/ccp/test_dbc.py

···
 
     def test_authenticated_nonce(self) -> None:
         """fetch authenticated nonce"""
+        get_nonce(self.d, None)
         with self.assertRaises(OSError) as error:
             get_nonce(self.d, self.signature)
-        self.assertEqual(error.exception.errno, 1)
+        self.assertEqual(error.exception.errno, 22)
 
     def test_set_uid(self) -> None:
         """set uid"""
+        get_nonce(self.d, None)
         with self.assertRaises(OSError) as error:
             set_uid(self.d, self.uid, self.signature)
         self.assertEqual(error.exception.errno, 1)
···
         """fetch a parameter"""
         with self.assertRaises(OSError) as error:
             process_param(self.d, PARAM_GET_SOC_PWR_CUR, self.signature)
-        self.assertEqual(error.exception.errno, 1)
+        self.assertEqual(error.exception.errno, 11)
 
     def test_set_param(self) -> None:
         """set a parameter"""
         with self.assertRaises(OSError) as error:
             process_param(self.d, PARAM_SET_PWR_CAP, self.signature, 1000)
-        self.assertEqual(error.exception.errno, 1)
+        self.assertEqual(error.exception.errno, 11)
 
 
 class TestUnFusedSystem(DynamicBoostControlTest):